diff options
author | Takashi Iwai | 2019-09-10 13:03:08 +0200 |
---|---|---|
committer | Takashi Iwai | 2019-09-10 13:03:08 +0200 |
commit | 7711fb7dac1ab77fd1b4d948f4647a569e4a1ae2 (patch) | |
tree | dd35ad21e0eb13572757dab279ae41f6d953baed /net | |
parent | 789492f0c86505e63369907bcb1afdf52dec9366 (diff) | |
parent | bb831786117519fc16dfd3eaa7b84e4f6bbb8d99 (diff) |
Merge tag 'asoc-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-next
ASoC: Updates for v5.4
Quite a big update this time around, particularly in the core
where we've had a lot of cleanups from Morimoto-san - there's
not much functional change but quite a bit of modernization
going on. We've also seen a lot of driver work, a lot of it
cleanups but also some particular drivers.
- Lots and lots of cleanups from Morimoto-san and Yue Haibing.
- Lots of cleanups and enhancements to the Freescale, sunxi dnd
Intel rivers.
- Initial Sound Open Firmware suppot for i.MX8.
- Removal of w90x900 and nuc900 drivers as the platforms are
being removed.
- New support for Cirrus Logic CS47L15 and CS47L92, Freescale
i.MX 7ULP and 8MQ, Meson G12A and NXP UDA1334
Diffstat (limited to 'net')
195 files changed, 1907 insertions, 1131 deletions
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 240ed70912d6..d78938e3e008 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -277,17 +277,23 @@ static u8 batadv_hop_penalty(u8 tq, const struct batadv_priv *bat_priv) * batadv_iv_ogm_aggr_packet() - checks if there is another OGM attached * @buff_pos: current position in the skb * @packet_len: total length of the skb - * @tvlv_len: tvlv length of the previously considered OGM + * @ogm_packet: potential OGM in buffer * * Return: true if there is enough space for another OGM, false otherwise. */ -static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, - __be16 tvlv_len) +static bool +batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, + const struct batadv_ogm_packet *ogm_packet) { int next_buff_pos = 0; - next_buff_pos += buff_pos + BATADV_OGM_HLEN; - next_buff_pos += ntohs(tvlv_len); + /* check if there is enough space for the header */ + next_buff_pos += buff_pos + sizeof(*ogm_packet); + if (next_buff_pos > packet_len) + return false; + + /* check if there is enough space for the optional TVLV */ + next_buff_pos += ntohs(ogm_packet->tvlv_len); return (next_buff_pos <= packet_len) && (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); @@ -315,7 +321,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* adjust all flags and log packets */ while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, - batadv_ogm_packet->tvlv_len)) { + batadv_ogm_packet)) { /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -1704,7 +1710,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, /* unpack the aggregated packets and process them one by one */ while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb), - ogm_packet->tvlv_len)) { + ogm_packet)) { batadv_iv_ogm_process(skb, ogm_offset, if_incoming); ogm_offset += BATADV_OGM_HLEN; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index fad95ef64e01..bc06e3cdfa84 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -631,17 +631,23 @@ batadv_v_ogm_process_per_outif(struct batadv_priv *bat_priv, * batadv_v_ogm_aggr_packet() - checks if there is another OGM aggregated * @buff_pos: current position in the skb * @packet_len: total length of the skb - * @tvlv_len: tvlv length of the previously considered OGM + * @ogm2_packet: potential OGM2 in buffer * * Return: true if there is enough space for another OGM, false otherwise. */ -static bool batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, - __be16 tvlv_len) +static bool +batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, + const struct batadv_ogm2_packet *ogm2_packet) { int next_buff_pos = 0; - next_buff_pos += buff_pos + BATADV_OGM2_HLEN; - next_buff_pos += ntohs(tvlv_len); + /* check if there is enough space for the header */ + next_buff_pos += buff_pos + sizeof(*ogm2_packet); + if (next_buff_pos > packet_len) + return false; + + /* check if there is enough space for the optional TVLV */ + next_buff_pos += ntohs(ogm2_packet->tvlv_len); return (next_buff_pos <= packet_len) && (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); @@ -818,7 +824,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, ogm_packet = (struct batadv_ogm2_packet *)skb->data; while (batadv_v_ogm_aggr_packet(ogm_offset, skb_headlen(skb), - ogm_packet->tvlv_len)) { + ogm_packet)) { batadv_v_ogm_process(skb, ogm_offset, if_incoming); ogm_offset += BATADV_OGM2_HLEN; diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 67d7f83009ae..1d5bdf3a4b65 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -2303,7 +2303,7 @@ __batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid, while (bucket_tmp < hash->size) { if (batadv_mcast_flags_dump_bucket(msg, portid, cb, hash, - *bucket, &idx_tmp)) + bucket_tmp, &idx_tmp)) break; bucket_tmp++; @@ -2420,8 +2420,10 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig) batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS); batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS); - batadv_mcast_want_rtr4_update(bat_priv, orig, BATADV_NO_FLAGS); - batadv_mcast_want_rtr6_update(bat_priv, orig, BATADV_NO_FLAGS); + batadv_mcast_want_rtr4_update(bat_priv, orig, + BATADV_MCAST_WANT_NO_RTR4); + batadv_mcast_want_rtr6_update(bat_priv, orig, + BATADV_MCAST_WANT_NO_RTR6); spin_unlock_bh(&orig->mcast_handler_lock); } diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 6f08fd122a8d..7e052d6f759b 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -164,7 +164,7 @@ batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) { struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); - return attr ? nla_get_u32(attr) : 0; + return (attr && nla_len(attr) == sizeof(u32)) ? nla_get_u32(attr) : 0; } /** diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b9585e7d9d2e..04bc79359a17 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3202,6 +3202,7 @@ struct hci_dev *hci_alloc_dev(void) hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE; hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE; hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT; + hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE; mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index bb67f4a5479a..402e2cc54044 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -433,6 +433,35 @@ static int auto_accept_delay_set(void *data, u64 val) return 0; } +static int min_encrypt_key_size_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val < 1 || val > 16) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->min_enc_key_size = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int min_encrypt_key_size_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->min_enc_key_size; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(min_encrypt_key_size_fops, + min_encrypt_key_size_get, + min_encrypt_key_size_set, "%llu\n"); + static int auto_accept_delay_get(void *data, u64 *val) { struct hci_dev *hdev = data; @@ -545,6 +574,8 @@ void hci_debugfs_create_bredr(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { debugfs_create_file("ssp_debug_mode", 0444, hdev->debugfs, hdev, &ssp_debug_mode_fops); + debugfs_create_file("min_encrypt_key_size", 0644, hdev->debugfs, + hdev, &min_encrypt_key_size_fops); debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs, hdev, &auto_accept_delay_fops); } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 5abd423b55fa..8d889969ae7e 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -101,6 +101,7 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock, { struct sk_buff *skb; struct sock *sk = sock->sk; + int ret; BT_DBG("session %p data %p size %d", session, data, size); @@ -114,13 +115,17 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock, } skb_put_u8(skb, hdr); - if (data && size > 0) + if (data && size > 0) { skb_put_data(skb, data, size); + ret = size; + } else { + ret = 0; + } skb_queue_tail(transmit, skb); wake_up_interruptible(sk_sleep(sk)); - return 0; + return ret; } static int hidp_send_ctrl_message(struct hidp_session *session, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index cc506fe99b4d..dfc1edb168b7 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1361,7 +1361,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon) * actually encrypted before enforcing a key size. */ return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) || - hcon->enc_key_size >= HCI_MIN_ENC_KEY_SIZE); + hcon->enc_key_size >= hcon->hdev->min_enc_key_size); } static void l2cap_do_start(struct l2cap_chan *chan) diff --git a/net/bridge/br.c b/net/bridge/br.c index d164f63a4345..8a8f9e5f264f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -37,12 +37,15 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v int err; if (dev->priv_flags & IFF_EBRIDGE) { + err = br_vlan_bridge_event(dev, event, ptr); + if (err) + return notifier_from_errno(err); + if (event == NETDEV_REGISTER) { /* register of bridge completed, add sysfs entries */ br_sysfs_addbr(dev); return NOTIFY_DONE; } - br_vlan_bridge_event(dev, event, ptr); } /* not a port of a bridge */ diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3d8deac2353d..f8cac3702712 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1388,6 +1388,9 @@ br_multicast_leave_group(struct net_bridge *br, if (!br_port_group_equal(p, port, src)) continue; + if (p->flags & MDB_PG_FLAGS_PERMANENT) + break; + rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e8cf03b43b7d..646504db0220 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -894,8 +894,8 @@ int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); void br_vlan_get_stats(const struct net_bridge_vlan *v, struct br_vlan_stats *stats); void br_vlan_port_event(struct net_bridge_port *p, unsigned long event); -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr); +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, + void *ptr); static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) @@ -1085,9 +1085,10 @@ static inline void br_vlan_port_event(struct net_bridge_port *p, { } -static inline void br_vlan_bridge_event(struct net_device *dev, - unsigned long event, void *ptr) +static inline int br_vlan_bridge_event(struct net_device *dev, + unsigned long event, void *ptr) { + return 0; } #endif diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 021cc9f66804..f5b2aeebbfe9 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1053,7 +1053,6 @@ int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; - bool changed; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) @@ -1068,17 +1067,10 @@ int br_vlan_init(struct net_bridge *br) br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); - ret = br_vlan_add(br, 1, - BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); - if (ret) - goto err_vlan_add; out: return ret; -err_vlan_add: - vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: @@ -1464,13 +1456,23 @@ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) } /* Must be protected by RTNL. */ -void br_vlan_bridge_event(struct net_device *dev, unsigned long event, - void *ptr) +int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; - struct net_bridge *br; + struct net_bridge *br = netdev_priv(dev); + bool changed; + int ret = 0; switch (event) { + case NETDEV_REGISTER: + ret = br_vlan_add(br, br->default_pvid, + BRIDGE_VLAN_INFO_PVID | + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); + break; + case NETDEV_UNREGISTER: + br_vlan_delete(br, br->default_pvid); + break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); @@ -1478,12 +1480,13 @@ void br_vlan_bridge_event(struct net_device *dev, unsigned long event, case NETDEV_CHANGE: case NETDEV_UP: - br = netdev_priv(dev); if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) - return; + break; br_vlan_link_state_change(dev, br); break; } + + return ret; } /* Must be protected by RTNL. */ diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 154fa558bb90..5040fe43f4b4 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -6,7 +6,7 @@ menuconfig NF_TABLES_BRIDGE depends on BRIDGE && NETFILTER && NF_TABLES select NETFILTER_FAMILY_BRIDGE - bool "Ethernet Bridge nf_tables support" + tristate "Ethernet Bridge nf_tables support" if NF_TABLES_BRIDGE @@ -25,6 +25,8 @@ config NF_LOG_BRIDGE tristate "Bridge packet logging" select NF_LOG_COMMON +endif # NF_TABLES_BRIDGE + config NF_CONNTRACK_BRIDGE tristate "IPv4/IPV6 bridge connection tracking support" depends on NF_CONNTRACK @@ -39,8 +41,6 @@ config NF_CONNTRACK_BRIDGE To compile it as a module, choose M here. If unsure, say N. -endif # NF_TABLES_BRIDGE - menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" depends on BRIDGE && NETFILTER && NETFILTER_XTABLES diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 963dfdc14827..4096d8a74a2b 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -221,7 +221,7 @@ unsigned int ebt_do_table(struct sk_buff *skb, return NF_DROP; } - ADD_COUNTER(*(counter_base + i), 1, skb->len); + ADD_COUNTER(*(counter_base + i), skb->len, 1); /* these should only watch: not modify, nor tell us * what to do with the packet @@ -959,8 +959,8 @@ static void get_counters(const struct ebt_counter *oldcounters, continue; counter_base = COUNTER_BASE(oldcounters, nentries, cpu); for (i = 0; i < nentries; i++) - ADD_COUNTER(counters[i], counter_base[i].pcnt, - counter_base[i].bcnt); + ADD_COUNTER(counters[i], counter_base[i].bcnt, + counter_base[i].pcnt); } } @@ -1280,7 +1280,7 @@ static int do_update_counters(struct net *net, const char *name, /* we add to the counters of the first cpu */ for (i = 0; i < num_counters; i++) - ADD_COUNTER(t->private->counters[i], tmp[i].pcnt, tmp[i].bcnt); + ADD_COUNTER(t->private->counters[i], tmp[i].bcnt, tmp[i].pcnt); write_unlock_bh(&t->lock); ret = 0; @@ -1770,20 +1770,28 @@ static int compat_calc_entry(const struct ebt_entry *e, return 0; } +static int ebt_compat_init_offsets(unsigned int number) +{ + if (number > INT_MAX) + return -EINVAL; + + /* also count the base chain policies */ + number += NF_BR_NUMHOOKS; + + return xt_compat_init_offsets(NFPROTO_BRIDGE, number); +} static int compat_table_info(const struct ebt_table_info *info, struct compat_ebt_replace *newinfo) { unsigned int size = info->entries_size; const void *entries = info->entries; + int ret; newinfo->entries_size = size; - if (info->nentries) { - int ret = xt_compat_init_offsets(NFPROTO_BRIDGE, - info->nentries); - if (ret) - return ret; - } + ret = ebt_compat_init_offsets(info->nentries); + if (ret) + return ret; return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); @@ -2234,11 +2242,9 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - if (tmp.nentries) { - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; - } + ret = ebt_compat_init_offsets(tmp.nentries); + if (ret < 0) + goto out_unlock; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) @@ -2261,8 +2267,10 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - if (WARN_ON(ret < 0)) + if (WARN_ON(ret < 0)) { + vfree(entries_tmp); goto out_unlock; + } vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index bed66f536b34..7c9e92b2f806 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -30,13 +30,9 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_META_BRI_IIFNAME: br_dev = nft_meta_get_bridge(in); - if (!br_dev) - goto err; break; case NFT_META_BRI_OIFNAME: br_dev = nft_meta_get_bridge(out); - if (!br_dev) - goto err; break; case NFT_META_BRI_IIFPVID: { u16 p_pvid; @@ -57,17 +53,15 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, goto err; br_vlan_get_proto(br_dev, &p_proto); - nft_reg_store16(dest, p_proto); + nft_reg_store16(dest, htons(p_proto)); return; } default: - goto out; + return nft_meta_get_eval(expr, regs, pkt); } - strncpy((char *)dest, br_dev->name, IFNAMSIZ); + strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; -out: - return nft_meta_get_eval(expr, regs, pkt); err: regs->verdict.code = NFT_BREAK; } diff --git a/net/can/gw.c b/net/can/gw.c index 5275ddf580bc..72711053ebe6 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1046,32 +1046,50 @@ static __init int cgw_module_init(void) pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", max_hops); - register_pernet_subsys(&cangw_pernet_ops); + ret = register_pernet_subsys(&cangw_pernet_ops); + if (ret) + return ret; + + ret = -ENOMEM; cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); - if (!cgw_cache) - return -ENOMEM; + goto out_cache_create; /* set notifier */ notifier.notifier_call = cgw_notifier; - register_netdevice_notifier(¬ifier); + ret = register_netdevice_notifier(¬ifier); + if (ret) + goto out_register_notifier; ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE, NULL, cgw_dump_jobs, 0); - if (ret) { - unregister_netdevice_notifier(¬ifier); - kmem_cache_destroy(cgw_cache); - return -ENOBUFS; - } - - /* Only the first call to rtnl_register_module can fail */ - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, - cgw_create_job, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, - cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register1; + + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE, + cgw_create_job, NULL, 0); + if (ret) + goto out_rtnl_register2; + ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE, + cgw_remove_job, NULL, 0); + if (ret) + goto out_rtnl_register3; return 0; + +out_rtnl_register3: + rtnl_unregister(PF_CAN, RTM_NEWROUTE); +out_rtnl_register2: + rtnl_unregister(PF_CAN, RTM_GETROUTE); +out_rtnl_register1: + unregister_netdevice_notifier(¬ifier); +out_register_notifier: + kmem_cache_destroy(cgw_cache); +out_cache_create: + unregister_pernet_subsys(&cangw_pernet_ops); + + return ret; } static __exit void cgw_module_exit(void) diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 5d6724cee38f..4f75df40fb12 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -136,8 +136,10 @@ void ceph_crypto_key_destroy(struct ceph_crypto_key *key) if (key) { kfree(key->key); key->key = NULL; - crypto_free_sync_skcipher(key->tfm); - key->tfm = NULL; + if (key->tfm) { + crypto_free_sync_skcipher(key->tfm); + key->tfm = NULL; + } } } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 0b2df09b2554..78ae6e8c953d 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1496,7 +1496,7 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_osds up, acting; bool force_resend = false; bool unpaused = false; - bool legacy_change; + bool legacy_change = false; bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); bool recovery_deletes = ceph_osdmap_flag(osdc, @@ -1584,15 +1584,14 @@ static enum calc_target_result calc_target(struct ceph_osd_client *osdc, t->osd = acting.primary; } - if (unpaused || legacy_change || force_resend || - (split && con && CEPH_HAVE_FEATURE(con->peer_features, - RESEND_ON_SPLIT))) + if (unpaused || legacy_change || force_resend || split) ct_res = CALC_TARGET_NEED_RESEND; else ct_res = CALC_TARGET_NO_ACTION; out: - dout("%s t %p -> ct_res %d osd %d\n", __func__, t, ct_res, t->osd); + dout("%s t %p -> %d%d%d%d ct_res %d osd%d\n", __func__, t, unpaused, + legacy_change, force_resend, split, ct_res, t->osd); return ct_res; } diff --git a/net/core/dev.c b/net/core/dev.c index fc676b2610e3..0891f499c1bb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4374,12 +4374,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, act = bpf_prog_run_xdp(xdp_prog, xdp); + /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; - if (off > 0) - __skb_pull(skb, off); - else if (off < 0) - __skb_push(skb, -off); - skb->mac_header += off; + if (off) { + if (off > 0) + __skb_pull(skb, off); + else if (off < 0) + __skb_push(skb, -off); + + skb->mac_header += off; + skb_reset_network_header(skb); + } /* check if bpf_xdp_adjust_tail was used. it can only "shrink" * pckt. @@ -9701,6 +9706,8 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + if (__dev_get_by_name(&init_net, fb_name)) + snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", diff --git a/net/core/filter.c b/net/core/filter.c index 4e2a79b2fd77..4c6a252d4212 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7455,12 +7455,12 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, gso_segs): /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, - offsetof(struct sk_buff, head)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, end)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), @@ -8757,13 +8757,13 @@ sk_reuseport_is_valid_access(int off, int size, return size == size_default; /* Fields that allow narrowing */ - case offsetof(struct sk_reuseport_md, eth_protocol): + case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < FIELD_SIZEOF(struct sk_buff, protocol)) return false; /* fall through */ - case offsetof(struct sk_reuseport_md, ip_protocol): - case offsetof(struct sk_reuseport_md, bind_inany): - case offsetof(struct sk_reuseport_md, len): + case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): + case bpf_ctx_range(struct sk_reuseport_md, bind_inany): + case bpf_ctx_range(struct sk_reuseport_md, len): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3e6fedb57bc1..2470b4b404e6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -142,8 +142,8 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) mutex_unlock(&flow_dissector_mutex); return -ENOENT; } - bpf_prog_put(attached); RCU_INIT_POINTER(net->flow_dissector_prog, NULL); + bpf_prog_put(attached); mutex_unlock(&flow_dissector_mutex); return 0; } diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 76f8db3841d7..d63b970784dc 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -165,7 +165,7 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_enc_opts); -struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, +struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)) { @@ -175,7 +175,6 @@ struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, if (!block_cb) return ERR_PTR(-ENOMEM); - block_cb->net = net; block_cb->cb = cb; block_cb->cb_ident = cb_ident; block_cb->cb_priv = cb_priv; @@ -194,14 +193,13 @@ void flow_block_cb_free(struct flow_block_cb *block_cb) } EXPORT_SYMBOL(flow_block_cb_free); -struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *f, - tc_setup_cb_t *cb, void *cb_ident) +struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, + flow_setup_cb_t *cb, void *cb_ident) { struct flow_block_cb *block_cb; - list_for_each_entry(block_cb, f->driver_block_list, driver_list) { - if (block_cb->net == f->net && - block_cb->cb == cb && + list_for_each_entry(block_cb, &block->cb_list, list) { + if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) return block_cb; } @@ -228,7 +226,7 @@ unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb) } EXPORT_SYMBOL(flow_block_cb_decref); -bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident, +bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list) { struct flow_block_cb *block_cb; @@ -245,7 +243,8 @@ EXPORT_SYMBOL(flow_block_cb_is_busy); int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_block_list, - tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, + flow_setup_cb_t *cb, + void *cb_ident, void *cb_priv, bool ingress_only) { struct flow_block_cb *block_cb; @@ -261,8 +260,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, cb_ident, - cb_priv, NULL); + block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -270,7 +268,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, list_add_tail(&block_cb->driver_list, driver_block_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, cb_ident); + block_cb = flow_block_cb_lookup(f->block, cb, cb_ident); if (!block_cb) return -ENOENT; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2cf27da1baeb..849380a622ef 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -122,7 +122,7 @@ static void queue_process(struct work_struct *work) txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || - netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { + !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) { skb_queue_head(&npinfo->txq, skb); HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); @@ -335,7 +335,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, HARD_TX_UNLOCK(dev, txq); - if (status == NETDEV_TX_OK) + if (dev_xmit_complete(status)) break; } @@ -352,7 +352,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, } - if (status != NETDEV_TX_OK) { + if (!dev_xmit_complete(status)) { skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93bffaad2135..6832eeb4b785 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -585,12 +585,12 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { - rcu_assign_sk_user_data(sk, NULL); sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); - sk_psock_restore_proto(sk, psock); write_lock_bh(&sk->sk_callback_lock); + sk_psock_restore_proto(sk, psock); + rcu_assign_sk_user_data(sk, NULL); if (psock->progs.skb_parser) sk_psock_stop_strp(sk, psock); write_unlock_bh(&sk->sk_callback_lock); diff --git a/net/core/sock.c b/net/core/sock.c index d57b0cc995a0..545fac19a711 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1992,6 +1992,19 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) } EXPORT_SYMBOL(skb_set_owner_w); +static bool can_skb_orphan_partial(const struct sk_buff *skb) +{ +#ifdef CONFIG_TLS_DEVICE + /* Drivers depend on in-order delivery for crypto offload, + * partial orphan breaks out-of-order-OK logic. + */ + if (skb->decrypted) + return false; +#endif + return (skb->destructor == sock_wfree || + (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); +} + /* This helper is used by netem, as it can hold packets in its * delay queue. We want to allow the owner socket to send more * packets, as if they were already TX completed by a typical driver. @@ -2003,11 +2016,7 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (skb->destructor == sock_wfree -#ifdef CONFIG_INET - || skb->destructor == tcp_wfree -#endif - ) { + if (can_skb_orphan_partial(skb)) { struct sock *sk = skb->sk; if (refcount_inc_not_zero(&sk->sk_refcnt)) { @@ -3278,16 +3287,17 @@ static __init int net_inuse_init(void) core_initcall(net_inuse_init); -static void assign_proto_idx(struct proto *prot) +static int assign_proto_idx(struct proto *prot) { prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { pr_err("PROTO_INUSE_NR exhausted\n"); - return; + return -ENOSPC; } set_bit(prot->inuse_idx, proto_inuse_idx); + return 0; } static void release_proto_idx(struct proto *prot) @@ -3296,8 +3306,9 @@ static void release_proto_idx(struct proto *prot) clear_bit(prot->inuse_idx, proto_inuse_idx); } #else -static inline void assign_proto_idx(struct proto *prot) +static inline int assign_proto_idx(struct proto *prot) { + return 0; } static inline void release_proto_idx(struct proto *prot) @@ -3346,6 +3357,8 @@ static int req_prot_init(const struct proto *prot) int proto_register(struct proto *prot, int alloc_slab) { + int ret = -ENOBUFS; + if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, @@ -3382,20 +3395,27 @@ int proto_register(struct proto *prot, int alloc_slab) } mutex_lock(&proto_list_mutex); + ret = assign_proto_idx(prot); + if (ret) { + mutex_unlock(&proto_list_mutex); + goto out_free_timewait_sock_slab_name; + } list_add(&prot->node, &proto_list); - assign_proto_idx(prot); mutex_unlock(&proto_list_mutex); - return 0; + return ret; out_free_timewait_sock_slab_name: - kfree(prot->twsk_prot->twsk_slab_name); + if (alloc_slab && prot->twsk_prot) + kfree(prot->twsk_prot->twsk_slab_name); out_free_request_sock_slab: - req_prot_cleanup(prot->rsk_prot); + if (alloc_slab) { + req_prot_cleanup(prot->rsk_prot); - kmem_cache_destroy(prot->slab); - prot->slab = NULL; + kmem_cache_destroy(prot->slab); + prot->slab = NULL; + } out: - return -ENOBUFS; + return ret; } EXPORT_SYMBOL(proto_register); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 3312a5849a97..c13ffbd33d8d 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -19,6 +19,7 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; +static atomic64_t cookie_gen; u64 sock_gen_cookie(struct sock *sk) { @@ -27,7 +28,7 @@ u64 sock_gen_cookie(struct sock *sk) if (res) return res; - res = atomic64_inc_return(&sock_net(sk)->cookie_gen); + res = atomic64_inc_return(&cookie_gen); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 52d4faeee18b..1330a7442e5b 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -247,6 +247,8 @@ static void sock_map_free(struct bpf_map *map) raw_spin_unlock_bh(&stab->lock); rcu_read_unlock(); + synchronize_rcu(); + bpf_map_area_free(stab->sks); kfree(stab); } @@ -276,16 +278,20 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { struct sock *sk; + int err = 0; raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) - *psk = NULL; + sk = xchg(psk, NULL); + + if (likely(sk)) + sock_map_unref(sk, psk); + else + err = -EINVAL; + raw_spin_unlock_bh(&stab->lock); - if (unlikely(!sk)) - return -EINVAL; - sock_map_unref(sk, psk); - return 0; + return err; } static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, @@ -328,6 +334,7 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct inet_connection_sock *icsk = inet_csk(sk); struct sk_psock_link *link; struct sk_psock *psock; struct sock *osk; @@ -338,6 +345,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; + if (unlikely(icsk->icsk_ulp_data)) + return -EINVAL; link = sk_psock_init_link(); if (!link) diff --git a/net/core/stream.c b/net/core/stream.c index e94bb02a5629..4f1d4aa5fb38 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -120,7 +120,6 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) int err = 0; long vm_wait = 0; long current_timeo = *timeo_p; - bool noblock = (*timeo_p ? false : true); DEFINE_WAIT_FUNC(wait, woken_wake_function); if (sk_stream_memory_free(sk)) @@ -133,11 +132,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; - if (!*timeo_p) { - if (noblock) - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - goto do_nonblock; - } + if (!*timeo_p) + goto do_eagain; if (signal_pending(current)) goto do_interrupted; sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -169,7 +165,13 @@ out: do_error: err = -EPIPE; goto out; -do_nonblock: +do_eagain: + /* Make sure that whenever EAGAIN is returned, EPOLLOUT event can + * be generated later. + * When TCP receives ACK packets that make room, tcp_check_space() + * only calls tcp_new_space() if SOCK_NOSPACE is set. + */ + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; goto out; do_interrupted: diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 614c38ece104..33f41178afcc 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -951,7 +951,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_slave_setup_tc_block_cb_ig; @@ -967,7 +967,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, dev, dev, NULL); + block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -975,7 +975,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, dev); + block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 4ec5b7f85d51..09d9286b27cc 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -153,6 +153,9 @@ static void dsa_switch_mdb_add_bitmap(struct dsa_switch *ds, { int port; + if (!ds->ops->port_mdb_add) + return; + for_each_set_bit(port, bitmap, ds->num_ports) ds->ops->port_mdb_add(ds, port, mdb); } diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 6ebbd799c4eb..67a1bc635a7b 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -28,6 +28,7 @@ * * RSV - VID[9]: * To be used for further expansion of SWITCH_ID or for other purposes. + * Must be transmitted as zero and ignored on receive. * * SWITCH_ID - VID[8:6]: * Index of switch within DSA tree. Must be between 0 and @@ -35,6 +36,7 @@ * * RSV - VID[5:4]: * To be used for further expansion of PORT or for other purposes. + * Must be transmitted as zero and ignored on receive. * * PORT - VID[3:0]: * Index of switch port. Must be between 0 and DSA_MAX_PORTS - 1. diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 26363d72d25b..47ee88163a9d 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -165,6 +165,7 @@ static struct sk_buff "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); + kfree_skb(sp->data->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv @@ -211,17 +212,8 @@ static struct sk_buff * for further processing up the network stack. */ kfree_skb(skb); - - skb = skb_copy(stampable_skb, GFP_ATOMIC); - if (!skb) { - dev_err_ratelimited(dp->ds->dev, - "Failed to copy stampable skb\n"); - spin_unlock(&sp->data->meta_lock); - return NULL; - } + skb = stampable_skb; sja1105_transfer_meta(skb, meta); - /* The cached copy will be freed now */ - skb_unref(stampable_skb); spin_unlock(&sp->data->meta_lock); } diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index e4aba5d485be..bbe9b3b2d395 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -170,7 +170,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto out_oom; - inet_frag_reasm_finish(&fq->q, skb, reasm_data); + inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->dev = ldev; skb->tstamp = fq->q.stamp; diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index dacbd58e1799..badc5cfe4dc6 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -1092,7 +1092,7 @@ static struct packet_type ieee802154_packet_type = { static int __init af_ieee802154_init(void) { - int rc = -EINVAL; + int rc; rc = proto_register(&ieee802154_raw_prot, 1); if (rc) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2b2b3d291ab0..1ab2fb6bb37d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2145,7 +2145,7 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, - &i_fa, s_fa); + &i_fa, s_fa, flags); if (err < 0) goto stop; } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1510e951f451..4298aae74e0e 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -582,7 +582,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (!rt) goto out; - net = dev_net(rt->dst.dev); + + if (rt->dst.dev) + net = dev_net(rt->dst.dev); + else if (skb_in->dev) + net = dev_net(skb_in->dev); + else + goto out; /* * Find the original header. It is expected to be valid, of course. @@ -902,7 +908,7 @@ static bool icmp_redirect(struct sk_buff *skb) return false; } - icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway); + icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway)); return true; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 180f6896b98b..480d0b22db1a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1475,7 +1475,7 @@ EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { - __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); + __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); @@ -2197,7 +2197,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); - __ip_mc_inc_group(in_dev, addr, mode); + ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index d666756be5f1..10d31733297d 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -331,7 +331,7 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); - if (prev && !IS_ERR(prev)) { + if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; @@ -475,11 +475,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, - void *reasm_data) + void *reasm_data, bool try_coalesce) { struct sk_buff **nextp = (struct sk_buff **)reasm_data; struct rb_node *rbn; struct sk_buff *fp; + int sum_truesize; skb_push(head, head->data - skb_network_header(head)); @@ -487,25 +488,41 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, fp = FRAG_CB(head)->next_frag; rbn = rb_next(&head->rbnode); rb_erase(&head->rbnode, &q->rb_fragments); + + sum_truesize = head->truesize; while (rbn || fp) { /* fp points to the next sk_buff in the current run; * rbn points to the next run. */ /* Go through the current run. */ while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; + struct sk_buff *next_frag = FRAG_CB(fp)->next_frag; + bool stolen; + int delta; + + sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; + + if (try_coalesce && skb_try_coalesce(head, fp, &stolen, + &delta)) { + kfree_skb_partial(fp, stolen); + } else { + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + + *nextp = fp; + nextp = &fp->next; + } + + fp = next_frag; } /* Move to the next run. */ if (rbn) { @@ -516,7 +533,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, rbn = rbnext; } } - sub_frag_mem_limit(q->fqdir, head->truesize); + sub_frag_mem_limit(q->fqdir, sum_truesize); *nextp = NULL; skb_mark_not_on_list(head); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 4385eb9e781f..cfeb8890f94e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -393,6 +393,11 @@ err: return err; } +static bool ip_frag_coalesce_ok(const struct ipq *qp) +{ + return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER; +} + /* Build a new IP datagram from all its fragments. */ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) @@ -421,7 +426,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, if (len > 65535) goto out_oversize; - inet_frag_reasm_finish(&qp->q, skb, reasm_data); + inet_frag_reasm_finish(&qp->q, skb, reasm_data, + ip_frag_coalesce_ok(qp)); skb->dev = dev; IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 43adfc1641ba..2f01cf6fa0de 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -275,6 +275,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; + if (!pskb_inet_may_pull(skb)) + goto tx_error; + switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4d6bf7ac0792..6bdb1ab8af61 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -416,8 +416,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) ctinfo == IP_CT_RELATED_REPLY)) return XT_CONTINUE; - /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, - * TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here + /* nf_conntrack_proto_icmp guarantees us that we only have ICMP_ECHO, + * TIMESTAMP, INFO_REQUEST or ICMP_ADDRESS type icmp packets from here * on, which all have an ID field [relevant for hashing]. */ hash = clusterip_hashfn(skb, cipinfo->config); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 8e7f84ec783d..0e70f3f65f6f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -36,6 +36,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; + opts.mss_encode = opts.mss; + opts.mss = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 59031670b16a..cc23f1ce239c 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; flow.flowi4_tos = RT_TOS(iph->tos); flow.flowi4_scope = RT_SCOPE_UNIVERSE; + flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par)); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 87b711fd5a44..3e2685c120c7 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -221,11 +221,11 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, int ret; rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - ret = nf_ct_expect_related(rtp_exp); + ret = nf_ct_expect_related(rtp_exp, 0); if (ret == 0) { rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); - ret = nf_ct_expect_related(rtcp_exp); + ret = nf_ct_expect_related(rtcp_exp, 0); if (ret == 0) break; else if (ret == -EBUSY) { @@ -296,7 +296,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -352,7 +352,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -444,7 +444,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -537,7 +537,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 517300d587a7..b6a6f18c3dd1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2728,7 +2728,8 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, - struct sk_buff *skb, u32 portid, u32 seq) + struct sk_buff *skb, u32 portid, u32 seq, + unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; @@ -2736,7 +2737,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 error; u32 metrics[RTAX_MAX]; - nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), 0); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; @@ -2860,7 +2861,7 @@ nla_put_failure: static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, - int *fa_index, int fa_start) + int *fa_index, int fa_start, unsigned int flags) { int i; @@ -2891,7 +2892,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, NULL, skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); + cb->nlh->nlmsg_seq, flags); if (err) return err; next: @@ -2904,7 +2905,7 @@ next: int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, - int *fa_index, int fa_start) + int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); @@ -2922,7 +2923,8 @@ int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, - genid, fa_index, fa_start); + genid, fa_index, fa_start, + flags); rcu_read_unlock(); if (err) return err; @@ -3183,7 +3185,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_tos, res.fi, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 776905899ac0..61082065b26a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -935,6 +935,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } +/* In some cases, both sendpage() and sendmsg() could have added + * an skb to the write queue, but failed adding payload on it. + * We need to remove it to consume less memory, but more + * importantly be able to generate EPOLLOUT for Edge Trigger epoll() + * users. + */ +static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) +{ + if (skb && !skb->len) { + tcp_unlink_write_queue(skb, sk); + if (tcp_write_queue_empty(sk)) + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + sk_wmem_free_skb(sk, skb); + } +} + ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -984,6 +1000,9 @@ new_segment: if (!skb) goto wait_for_memory; +#ifdef CONFIG_TLS_DEVICE + skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); +#endif skb_entail(sk, skb); copy = size_goal; } @@ -1061,6 +1080,7 @@ out: return copied; do_error: + tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk)); if (copied) goto out; out_err: @@ -1385,18 +1405,11 @@ out_nopush: sock_zerocopy_put(uarg); return copied + copied_syn; +do_error: + skb = tcp_write_queue_tail(sk); do_fault: - if (!skb->len) { - tcp_unlink_write_queue(skb, sk); - /* It is the one place in all of TCP, except connection - * reset, where we can be unlinking the send_head. - */ - if (tcp_write_queue_empty(sk)) - tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - sk_wmem_free_skb(sk, skb); - } + tcp_remove_empty_skb(sk, skb); -do_error: if (copied + copied_syn) goto out; out_err: diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 3d1e15401384..8a56e09cfb0e 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -398,10 +398,14 @@ more_data: static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct sk_msg tmp, *msg_tx = NULL; - int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS; int copied = 0, err = 0; struct sk_psock *psock; long timeo; + int flags; + + /* Don't let internal do_tcp_sendpages() flags through */ + flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED); + flags |= MSG_NO_SHARED_FRAGS; psock = sk_psock_get(sk); if (unlikely(!psock)) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4af1f5dae9d3..8a645f304e6c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1288,6 +1288,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; + long limit; int nlen; u8 flags; @@ -1298,8 +1299,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, if (nsize < 0) nsize = 0; - if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf && - tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) { + /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. + * We need some allowance to not penalize applications setting small + * SO_SNDBUF values. + * Also allow first and last skb in retransmit queue to be split. + */ + limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE); + if (unlikely((sk->sk_wmem_queued >> 1) > limit && + tcp_queue != TCP_FRAG_IN_WRITE_QUEUE && + skb != tcp_rtx_queue_head(sk) && + skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } @@ -1311,6 +1320,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, buff = sk_stream_alloc_skb(sk, nsize, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ + skb_copy_decrypted(buff, skb); sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); @@ -1865,6 +1875,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) return -ENOMEM; + skb_copy_decrypted(buff, skb); sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); @@ -2042,7 +2053,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor)) + if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; @@ -2134,6 +2145,7 @@ static int tcp_mtu_probe(struct sock *sk) sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); + skb_copy_decrypted(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; @@ -2158,6 +2170,7 @@ static int tcp_mtu_probe(struct sock *sk) * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; + tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 3d8a1d835471..4849edb62d52 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -96,6 +96,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) rcu_read_unlock(); } +void tcp_update_ulp(struct sock *sk, struct proto *proto) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) { + sk->sk_prot = proto; + return; + } + + if (icsk->icsk_ulp_ops->update) + icsk->icsk_ulp_ops->update(sk, proto); +} + void tcp_cleanup_ulp(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index dc73888c7859..6a576ff92c39 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -478,7 +478,7 @@ static struct inet6_dev *ipv6_find_idev(struct net_device *dev) if (!idev) { idev = ipv6_add_dev(dev); if (IS_ERR(idev)) - return NULL; + return idev; } if (dev->flags&IFF_UP) @@ -1045,7 +1045,8 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, int err = 0; if (addr_type == IPV6_ADDR_ANY || - addr_type & IPV6_ADDR_MULTICAST || + (addr_type & IPV6_ADDR_MULTICAST && + !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) || (!(idev->dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(idev->dev) && addr_type & IPV6_ADDR_LOOPBACK)) @@ -2465,8 +2466,8 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev) ASSERT_RTNL(); idev = ipv6_find_idev(dev); - if (!idev) - return ERR_PTR(-ENOBUFS); + if (IS_ERR(idev)) + return idev; if (idev->cnf.disable_ipv6) return ERR_PTR(-EACCES); @@ -3158,7 +3159,7 @@ static void init_loopback(struct net_device *dev) ASSERT_RTNL(); idev = ipv6_find_idev(dev); - if (!idev) { + if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } @@ -3373,7 +3374,7 @@ static void addrconf_sit_config(struct net_device *dev) */ idev = ipv6_find_idev(dev); - if (!idev) { + if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } @@ -3398,7 +3399,7 @@ static void addrconf_gre_config(struct net_device *dev) ASSERT_RTNL(); idev = ipv6_find_idev(dev); - if (!idev) { + if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } @@ -4772,8 +4773,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; idev = ipv6_find_idev(dev); - if (!idev) - return -ENOBUFS; + if (IS_ERR(idev)) + return PTR_ERR(idev); if (!ipv6_allow_optimistic_dad(net, idev)) cfg.ifa_flags &= ~IFA_F_OPTIMISTIC; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c2049c72f3e5..dd2d0b963260 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -660,12 +660,13 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct ipv6hdr *ipv6h; struct ip6_tnl *t = netdev_priv(dev); __u16 offset; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3134fbb65d7f..754a484d35df 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1278,12 +1278,11 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph)); - skb_set_inner_ipproto(skb, IPPROTO_IPIP); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, @@ -1367,12 +1366,11 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); + dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; - dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h)); - skb_set_inner_ipproto(skb, IPPROTO_IPV6); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7f3f13c37916..eaa4c2cc2fbb 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -787,14 +787,15 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) if (pmc) { im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { - im->mca_tomb = pmc->mca_tomb; - im->mca_sources = pmc->mca_sources; + swap(im->mca_tomb, pmc->mca_tomb); + swap(im->mca_sources, pmc->mca_sources); for (psf = im->mca_sources; psf; psf = psf->sf_next) psf->sf_crcount = idev->mc_qrv; } else { im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); + ip6_mc_clear_src(pmc); kfree(pmc); } spin_unlock_bh(&im->mca_lock); diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index e77ea1ed5edd..5cdb4a69d277 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -36,6 +36,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; + opts.mss_encode = opts.mss; + opts.mss = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 6bcaf7357183..d800801a5dd2 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -55,7 +55,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, if (rpfilter_addr_linklocal(&iph->saddr)) { lookup_flags |= RT6_LOOKUP_F_IFACE; fl6.flowi6_oif = dev->ifindex; - } else if ((flags & XT_RPFILTER_LOOSE) == 0) + /* Set flowi6_oif for vrf devices to lookup route in l3mdev domain. */ + } else if (netif_is_l3_master(dev) || netif_is_l3_slave(dev) || + (flags & XT_RPFILTER_LOOSE) == 0) fl6.flowi6_oif = dev->ifindex; rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); @@ -70,7 +72,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, goto out; } - if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE)) + if (rt->rt6i_idev->dev == dev || + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex || + (flags & XT_RPFILTER_LOOSE)) ret = true; out: ip6_rt_put(rt); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 0f82c150543b..fed9666a2f7d 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -348,7 +348,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_reset_transport_header(skb); - inet_frag_reasm_finish(&fq->q, skb, reasm_data); + inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->ignore_df = 1; skb->dev = dev; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index ca05b16f1bb9..1f5d4d196dcc 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -282,7 +282,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_reset_transport_header(skb); - inet_frag_reasm_finish(&fq->q, skb, reasm_data); + inet_frag_reasm_finish(&fq->q, skb, reasm_data, true); skb->dev = dev; ipv6_hdr(skb)->payload_len = htons(payload_len); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e49fec767a10..fd059e08785a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1951,7 +1951,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) - return; + goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 09e1694b6d34..ebb62a4ebe30 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -512,7 +512,9 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); } - case IUCV_DISCONN: /* fall through */ + /* fall through */ + + case IUCV_DISCONN: sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); @@ -525,8 +527,9 @@ static void iucv_sock_close(struct sock *sk) iucv_sock_in_state(sk, IUCV_CLOSED, 0), timeo); } + /* fall through */ - case IUCV_CLOSING: /* fall through */ + case IUCV_CLOSING: sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); @@ -535,8 +538,9 @@ static void iucv_sock_close(struct sock *sk) skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); + /* fall through */ - default: /* fall through */ + default: iucv_sever_path(sk, 1); } @@ -2247,10 +2251,10 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, kfree_skb(skb); break; } - /* fall through and receive non-zero length data */ + /* fall through - and receive non-zero length data */ case (AF_IUCV_FLAG_SHT): /* shutdown request */ - /* fall through and receive zero length data */ + /* fall through - and receive zero length data */ case 0: /* plain data frame */ IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1d0e5904dedf..c54cb59593ef 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1681,6 +1681,9 @@ static const struct proto_ops pppol2tp_ops = { .recvmsg = pppol2tp_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = pppox_compat_ioctl, +#endif }; static const struct pppox_proto pppol2tp_proto = { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 76cc9e967fa6..111c400199ec 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -936,8 +936,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, err = ieee80211_set_probe_resp(sdata, params->probe_resp, params->probe_resp_len, csa); - if (err < 0) + if (err < 0) { + kfree(new); return err; + } if (err == 0) changed |= BSS_CHANGED_AP_PROBE_RESP; @@ -949,8 +951,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, params->civicloc, params->civicloc_len); - if (err < 0) + if (err < 0) { + kfree(new); return err; + } changed |= BSS_CHANGED_FTM_RESPONDER; } @@ -1542,6 +1546,11 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (is_multicast_ether_addr(mac)) return -EINVAL; + if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER) && + sdata->vif.type == NL80211_IFTYPE_STATION && + !sdata->u.mgd.associated) + return -EINVAL; + sta = sta_info_alloc(sdata, mac, GFP_KERNEL); if (!sta) return -ENOMEM; @@ -1549,10 +1558,6 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) sta->sta.tdls = true; - if (sta->sta.tdls && sdata->vif.type == NL80211_IFTYPE_STATION && - !sdata->u.mgd.associated) - return -EINVAL; - err = sta_apply_parameters(local, sta, params); if (err) { sta_info_free(local, sta); diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index acd4afb4944b..c9a8a2433e8a 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -187,11 +187,16 @@ int drv_conf_tx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - if (WARN_ONCE(params->cw_min == 0 || - params->cw_min > params->cw_max, - "%s: invalid CW_min/CW_max: %d/%d\n", - sdata->name, params->cw_min, params->cw_max)) + if (params->cw_min == 0 || params->cw_min > params->cw_max) { + /* + * If we can't configure hardware anyway, don't warn. We may + * never have initialized the CW parameters. + */ + WARN_ONCE(local->ops->conf_tx, + "%s: invalid CW_min/CW_max: %d/%d\n", + sdata->name, params->cw_min, params->cw_max); return -EINVAL; + } trace_drv_conf_tx(local, sdata, ac, params); if (local->ops->conf_tx) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 06aac0aaae64..8dc6580e1787 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1222,7 +1222,6 @@ static void ieee80211_if_setup(struct net_device *dev) static void ieee80211_if_setup_no_queue(struct net_device *dev) { ieee80211_if_setup(dev); - dev->features |= NETIF_F_LLTX; dev->priv_flags |= IFF_NO_QUEUE; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a99ad0325309..4c888dc9bd81 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2042,6 +2042,16 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local, ieee80211_regulatory_limit_wmm_params(sdata, ¶ms[ac], ac); } + /* WMM specification requires all 4 ACIs. */ + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + if (params[ac].cw_min == 0) { + sdata_info(sdata, + "AP has invalid WMM params (missing AC %d), using defaults\n", + ac); + return false; + } + } + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { mlme_dbg(sdata, "WMM AC=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n", diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3c1ab870fefe..768d14c9a716 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2447,11 +2447,13 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, skb->protocol == cpu_to_be16(ETH_P_PREAUTH)) && sdata->control_port_over_nl80211)) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - bool noencrypt = status->flag & RX_FLAG_DECRYPTED; + bool noencrypt = !(status->flag & RX_FLAG_DECRYPTED); cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { + memset(skb->cb, 0, sizeof(skb->cb)); + /* deliver to local stack */ if (rx->napi) napi_gro_receive(rx->napi, skb); @@ -2546,8 +2548,6 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) if (skb) { skb->protocol = eth_type_trans(skb, dev); - memset(skb->cb, 0, sizeof(skb->cb)); - ieee80211_deliver_skb_to_local_stack(skb, rx); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1b224fa27367..ad1e58184c4e 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3796,9 +3796,7 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, } /* Always allow software iftypes */ - if (local->hw.wiphy->software_iftypes & BIT(iftype) || - (iftype == NL80211_IFTYPE_AP_VLAN && - local->hw.wiphy->flags & WIPHY_FLAG_4ADDR_AP)) { + if (cfg80211_iftype_allowed(local->hw.wiphy, iftype, 0, 1)) { if (radar_detect) return -EINVAL; return 0; @@ -3833,7 +3831,8 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, if (sdata_iter == sdata || !ieee80211_sdata_running(sdata_iter) || - local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype)) + cfg80211_iftype_allowed(local->hw.wiphy, + wdev_iter->iftype, 0, 1)) continue; params.iftype_num[wdev_iter->iftype]++; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index d25e91d7bdc1..44b675016393 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -133,12 +133,12 @@ static int mpls_xmit(struct sk_buff *skb) mpls_stats_inc_outucastpkts(out_dev, skb); if (rt) { - if (rt->rt_gw_family == AF_INET) - err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4, - skb); - else if (rt->rt_gw_family == AF_INET6) + if (rt->rt_gw_family == AF_INET6) err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt->rt_gw6, skb); + else + err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4, + skb); } else if (rt6) { if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) { /* 6PE (RFC 4798) */ diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index 5c3fad8cba57..0187e65176c0 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -54,7 +54,7 @@ static void ncsi_cmd_build_header(struct ncsi_pkt_hdr *h, checksum = ncsi_calculate_checksum((unsigned char *)h, sizeof(*h) + nca->payload); pchecksum = (__be32 *)((void *)h + sizeof(struct ncsi_pkt_hdr) + - nca->payload); + ALIGN(nca->payload, 4)); *pchecksum = htonl(checksum); } @@ -309,14 +309,21 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca) { + struct ncsi_cmd_handler *nch = NULL; struct ncsi_request *nr; + unsigned char type; struct ethhdr *eh; - struct ncsi_cmd_handler *nch = NULL; int i, ret; + /* Use OEM generic handler for Netlink request */ + if (nca->req_flags == NCSI_REQ_FLAG_NETLINK_DRIVEN) + type = NCSI_PKT_CMD_OEM; + else + type = nca->type; + /* Search for the handler */ for (i = 0; i < ARRAY_SIZE(ncsi_cmd_handlers); i++) { - if (ncsi_cmd_handlers[i].type == nca->type) { + if (ncsi_cmd_handlers[i].type == type) { if (ncsi_cmd_handlers[i].handler) nch = &ncsi_cmd_handlers[i]; else diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 7581bf919885..d876bd55f356 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -47,7 +47,8 @@ static int ncsi_validate_rsp_pkt(struct ncsi_request *nr, if (ntohs(h->code) != NCSI_PKT_RSP_C_COMPLETED || ntohs(h->reason) != NCSI_PKT_RSP_R_NO_ERROR) { netdev_dbg(nr->ndp->ndev.dev, - "NCSI: non zero response/reason code\n"); + "NCSI: non zero response/reason code %04xh, %04xh\n", + ntohs(h->code), ntohs(h->reason)); return -EPERM; } @@ -55,7 +56,7 @@ static int ncsi_validate_rsp_pkt(struct ncsi_request *nr, * sender doesn't support checksum according to NCSI * specification. */ - pchecksum = (__be32 *)((void *)(h + 1) + payload - 4); + pchecksum = (__be32 *)((void *)(h + 1) + ALIGN(payload, 4) - 4); if (ntohl(*pchecksum) == 0) return 0; @@ -63,7 +64,9 @@ static int ncsi_validate_rsp_pkt(struct ncsi_request *nr, sizeof(*h) + payload - 4); if (*pchecksum != htonl(checksum)) { - netdev_dbg(nr->ndp->ndev.dev, "NCSI: checksum mismatched\n"); + netdev_dbg(nr->ndp->ndev.dev, + "NCSI: checksum mismatched; recd: %08x calc: %08x\n", + *pchecksum, htonl(checksum)); return -EINVAL; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 32a45c03786e..0d65f4d39494 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -223,8 +223,6 @@ config NF_CONNTRACK_FTP of Network Address Translation on them. This is FTP support on Layer 3 independent connection tracking. - Layer 3 independent connection tracking is experimental scheme - which generalize ip_conntrack to support other layer 3 protocols. To compile it as a module, choose M here. If unsure, say N. @@ -338,7 +336,7 @@ config NF_CONNTRACK_SIP help SIP is an application-layer control protocol that can establish, modify, and terminate multimedia sessions (conferences) such as - Internet telephony calls. With the ip_conntrack_sip and + Internet telephony calls. With the nf_conntrack_sip and the nf_nat_sip modules you can support the protocol on a connection tracking/NATing firewall. @@ -1313,7 +1311,7 @@ config NETFILTER_XT_MATCH_HELPER depends on NETFILTER_ADVANCED help Helper matching allows you to match packets in dynamic connections - tracked by a conntrack-helper, ie. ip_conntrack_ftp + tracked by a conntrack-helper, ie. nf_conntrack_ftp To compile it as a module, choose M here. If unsure, say Y. diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index ca7ac4a25ada..1d4e63326e68 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -226,7 +226,7 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, e.id = ip_to_id(map, ip); - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 2e151856ad99..e64d5f9a89dd 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1161,7 +1161,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, return -ENOENT; write_lock_bh(&ip_set_ref_lock); - if (set->ref != 0) { + if (set->ref != 0 || set->ref_netlink != 0) { ret = -IPSET_ERR_REFERENCED; goto out; } diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index faf59b6a998f..24d8f4df4230 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -89,15 +89,11 @@ hash_ipmac4_kadt(struct ip_set *set, const struct sk_buff *skb, struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - /* MAC can be src only */ - if (!(opt->flags & IPSET_DIM_TWO_SRC)) - return 0; - if (skb_mac_header(skb) < skb->head || (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 403541996952..08adcb222986 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -231,7 +231,7 @@ void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct, IP_VS_DBG_BUF(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n", __func__, ct, ARG_TUPLE(&exp->tuple)); - nf_ct_expect_related(exp); + nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); } EXPORT_SYMBOL(ip_vs_nfct_expect_related); diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 42ee659d0d1e..d011d2eb0848 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -159,7 +159,7 @@ static int amanda_help(struct sk_buff *skb, if (nf_nat_amanda && ct->status & IPS_NAT_MASK) ret = nf_nat_amanda(skb, ctinfo, protoff, off - dataoff, len, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index 921a7b95be68..1ba6becc3079 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -68,7 +68,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->class = NF_CT_EXPECT_CLASS_DEFAULT; exp->helper = NULL; - nf_ct_expect_related(exp); + nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); nf_ct_refresh(ct, skb, timeout * HZ); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index bdfeacee0817..81a8ef42b88d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -453,13 +453,12 @@ EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); * table location, we assume id gets exposed to userspace. * * Following nf_conn items do not change throughout lifetime - * of the nf_conn after it has been committed to main hash table: + * of the nf_conn: * * 1. nf_conn address - * 2. nf_conn->ext address - * 3. nf_conn->master address (normally NULL) - * 4. tuple - * 5. the associated net namespace + * 2. nf_conn->master address (normally NULL) + * 3. the associated net namespace + * 4. the original direction tuple */ u32 nf_ct_get_id(const struct nf_conn *ct) { @@ -469,9 +468,10 @@ u32 nf_ct_get_id(const struct nf_conn *ct) net_get_random_once(&ct_id_seed, sizeof(ct_id_seed)); a = (unsigned long)ct; - b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct)); - c = (unsigned long)ct->ext; - d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash), + b = (unsigned long)ct->master; + c = (unsigned long)nf_ct_net(ct); + d = (unsigned long)siphash(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + sizeof(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple), &ct_id_seed); #ifdef CONFIG_64BIT return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed); @@ -1817,9 +1817,7 @@ EXPORT_SYMBOL_GPL(nf_ct_kill_acct); #include <linux/netfilter/nfnetlink_conntrack.h> #include <linux/mutex.h> -/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be - * in ip_conntrack_core, since we don't want the protocols to autoload - * or depend on ctnetlink */ +/* Generic function for tcp/udp/sctp/dccp and alike. */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index ffd1f4906c4f..65364de915d1 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -249,13 +249,22 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { - return a->master == b->master && - nf_ct_tuple_equal(&a->tuple, &b->tuple) && + return nf_ct_tuple_equal(&a->tuple, &b->tuple) && nf_ct_tuple_mask_equal(&a->mask, &b->mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master)); } +static bool master_matches(const struct nf_conntrack_expect *a, + const struct nf_conntrack_expect *b, + unsigned int flags) +{ + if (flags & NF_CT_EXP_F_SKIP_MASTER) + return true; + + return a->master == b->master; +} + /* Generally a bad idea to call this: could have matched already. */ void nf_ct_unexpect_related(struct nf_conntrack_expect *exp) { @@ -399,7 +408,8 @@ static void evict_oldest_expect(struct nf_conn *master, nf_ct_remove_expect(last); } -static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) +static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, + unsigned int flags) { const struct nf_conntrack_expect_policy *p; struct nf_conntrack_expect *i; @@ -417,8 +427,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { - if (expect_matches(i, expect)) { - if (i->class != expect->class) + if (master_matches(i, expect, flags) && + expect_matches(i, expect)) { + if (i->class != expect->class || + i->master != expect->master) return -EALREADY; if (nf_ct_remove_expect(i)) @@ -453,12 +465,12 @@ out: } int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, - u32 portid, int report) + u32 portid, int report, unsigned int flags) { int ret; spin_lock_bh(&nf_conntrack_expect_lock); - ret = __nf_ct_expect_check(expect); + ret = __nf_ct_expect_check(expect, flags); if (ret < 0) goto out; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 8c6c11bab5b6..8d96738b7dfd 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -322,7 +322,7 @@ static int find_pattern(const char *data, size_t dlen, i++; } - pr_debug("Skipped up to `%c'!\n", skip); + pr_debug("Skipped up to 0x%hhx delimiter!\n", skip); *numoff = i; *numlen = getnum(data + i, dlen - i, cmd, term, numoff); @@ -525,7 +525,7 @@ skip_nl_seq: protoff, matchoff, matchlen, exp); else { /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } else diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 8f6ba8162f0b..573cb4481481 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -1,11 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323 - * conntrack/NAT module. + * BER and PER decoding library for H.323 conntrack/NAT module. * * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net> * - * See ip_conntrack_helper_h323_asn1.h for details. + * See nf_conntrack_helper_h323_asn1.h for details. */ #ifdef __KERNEL__ diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 6497e5fc0871..8ba037b76ad3 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -305,8 +305,8 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, ret = nat_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, rtp_port, rtp_exp, rtcp_exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(rtp_exp) == 0) { - if (nf_ct_expect_related(rtcp_exp) == 0) { + if (nf_ct_expect_related(rtp_exp, 0) == 0) { + if (nf_ct_expect_related(rtcp_exp, 0) == 0) { pr_debug("nf_ct_h323: expect RTP "); nf_ct_dump_tuple(&rtp_exp->tuple); pr_debug("nf_ct_h323: expect RTCP "); @@ -364,7 +364,7 @@ static int expect_t120(struct sk_buff *skb, ret = nat_t120(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_h323: expect T.120 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -701,7 +701,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, ret = nat_h245(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_q931: expect H.245 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -825,7 +825,7 @@ static int expect_callforwarding(struct sk_buff *skb, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_q931: expect Call Forwarding "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1284,7 +1284,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, ret = nat_q931(skb, ct, ctinfo, protoff, data, taddr, i, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); @@ -1349,7 +1349,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, IPPROTO_UDP, NULL, &port); exp->helper = nf_conntrack_helper_ras; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1561,7 +1561,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, exp->flags = NF_CT_EXPECT_PERMANENT; exp->helper = nf_conntrack_helper_q931; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1615,7 +1615,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, exp->flags = NF_CT_EXPECT_PERMANENT; exp->helper = nf_conntrack_helper_q931; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); } else diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 7ac156f1f3bc..e40988a2f22f 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -213,7 +213,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, addr_beg_p - ib_ptr, addr_end_p - addr_beg_p, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1b77444d5b52..6aa01eb6fe99 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2616,7 +2616,7 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (IS_ERR(exp)) return PTR_ERR(exp); - err = nf_ct_expect_related_report(exp, portid, report); + err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); return err; } @@ -3367,7 +3367,7 @@ ctnetlink_create_expect(struct net *net, goto err_rcu; } - err = nf_ct_expect_related_report(exp, portid, report); + err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index b22042ad0fca..a971183f11af 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -234,9 +234,9 @@ static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid) nf_nat_pptp_exp_gre = rcu_dereference(nf_nat_pptp_hook_exp_gre); if (nf_nat_pptp_exp_gre && ct->status & IPS_NAT_MASK) nf_nat_pptp_exp_gre(exp_orig, exp_reply); - if (nf_ct_expect_related(exp_orig) != 0) + if (nf_ct_expect_related(exp_orig, 0) != 0) goto out_put_both; - if (nf_ct_expect_related(exp_reply) != 0) + if (nf_ct_expect_related(exp_reply, 0) != 0) goto out_unexpect_orig; /* Add GRE keymap entries */ diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index c2eb365f1723..5b05487a60d2 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ip_conntrack_proto_gre.c - Version 3.0 - * * Connection tracking protocol helper module for GRE. * * GRE is a generic encapsulation protocol, which is generally not very diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index dd53e2b20f6b..097deba7441a 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -215,7 +215,7 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, return -NF_ACCEPT; } - /* See ip_conntrack_proto_tcp.c */ + /* See nf_conntrack_proto_tcp.c */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d5fdfa00d683..85c1f8c213b0 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -472,6 +472,7 @@ static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; + u16 win_raw; s32 receiver_offset; bool res, in_recv_win; @@ -480,7 +481,8 @@ static bool tcp_in_window(const struct nf_conn *ct, */ seq = ntohl(tcph->seq); ack = sack = ntohl(tcph->ack_seq); - win = ntohs(tcph->window); + win_raw = ntohs(tcph->window); + win = win_raw; end = segment_seq_plus_len(seq, skb->len, dataoff, tcph); if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM) @@ -655,14 +657,14 @@ static bool tcp_in_window(const struct nf_conn *ct, && state->last_seq == seq && state->last_ack == ack && state->last_end == end - && state->last_win == win) + && state->last_win == win_raw) state->retrans++; else { state->last_dir = dir; state->last_seq = seq; state->last_ack = ack; state->last_end = end; - state->last_win = win; + state->last_win = win_raw; state->retrans = 0; } } diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index 81448c3db661..1aebd6569d4e 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -153,7 +153,7 @@ static int help(struct sk_buff *skb, nf_ct_dump_tuple(&exp->tuple); /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 107251731809..b83dc9bf0a5d 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -977,11 +977,15 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, /* -EALREADY handling works around end-points that send * SDP messages with identical port but different media type, * we pretend expectation was set up. + * It also works in the case that SDP messages are sent with + * identical expect tuples but for different master conntracks. */ - int errp = nf_ct_expect_related(rtp_exp); + int errp = nf_ct_expect_related(rtp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (errp == 0 || errp == -EALREADY) { - int errcp = nf_ct_expect_related(rtcp_exp); + int errcp = nf_ct_expect_related(rtcp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (errcp == 0 || errcp == -EALREADY) ret = NF_ACCEPT; @@ -1296,7 +1300,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, ret = hooks->expect(skb, protoff, dataoff, dptr, datalen, exp, matchoff, matchlen); else { - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } else diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index e0d392cb3075..0006503d2da9 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1037,9 +1037,14 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_COUNT].data = &net->ct.count; table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum; table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid; + table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct; + table[NF_SYSCTL_CT_HELPER].data = &net->ct.sysctl_auto_assign_helper; #ifdef CONFIG_NF_CONNTRACK_EVENTS table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events; #endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + table[NF_SYSCTL_CT_TIMESTAMP].data = &net->ct.sysctl_tstamp; +#endif table[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC].data = &nf_generic_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP].data = &nf_icmp_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout; diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index df6d6d61bd58..80ee53f29f68 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -78,7 +78,7 @@ static int tftp_help(struct sk_buff *skb, nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook); if (nf_nat_tftp && ct->status & IPS_NAT_MASK) ret = nf_nat_tftp(skb, ctinfo, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index e3d797252a98..80a8f9ae4c93 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -111,15 +111,16 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ) #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ) -static void flow_offload_fixup_ct_state(struct nf_conn *ct) +static inline __s32 nf_flow_timeout_delta(unsigned int timeout) +{ + return (__s32)(timeout - (u32)jiffies); +} + +static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; + int l4num = nf_ct_protonum(ct); unsigned int timeout; - int l4num; - - l4num = nf_ct_protonum(ct); - if (l4num == IPPROTO_TCP) - flow_offload_fixup_tcp(&ct->proto.tcp); l4proto = nf_ct_l4proto_find(l4num); if (!l4proto) @@ -132,7 +133,20 @@ static void flow_offload_fixup_ct_state(struct nf_conn *ct) else return; - ct->timeout = nfct_time_stamp + timeout; + if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) + ct->timeout = nfct_time_stamp + timeout; +} + +static void flow_offload_fixup_ct_state(struct nf_conn *ct) +{ + if (nf_ct_protonum(ct) == IPPROTO_TCP) + flow_offload_fixup_tcp(&ct->proto.tcp); +} + +static void flow_offload_fixup_ct(struct nf_conn *ct) +{ + flow_offload_fixup_ct_state(ct); + flow_offload_fixup_ct_timeout(ct); } void flow_offload_free(struct flow_offload *flow) @@ -208,6 +222,11 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) } EXPORT_SYMBOL_GPL(flow_offload_add); +static inline bool nf_flow_has_expired(const struct flow_offload *flow) +{ + return nf_flow_timeout_delta(flow->timeout) <= 0; +} + static void flow_offload_del(struct nf_flowtable *flow_table, struct flow_offload *flow) { @@ -223,6 +242,11 @@ static void flow_offload_del(struct nf_flowtable *flow_table, e = container_of(flow, struct flow_offload_entry, flow); clear_bit(IPS_OFFLOAD_BIT, &e->ct->status); + if (nf_flow_has_expired(flow)) + flow_offload_fixup_ct(e->ct); + else if (flow->flags & FLOW_OFFLOAD_TEARDOWN) + flow_offload_fixup_ct_timeout(e->ct); + flow_offload_free(flow); } @@ -298,11 +322,6 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } -static inline bool nf_flow_has_expired(const struct flow_offload *flow) -{ - return (__s32)(flow->timeout - (u32)jiffies) <= 0; -} - static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index cdfc33517e85..b9e7dd6e60ce 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -214,6 +214,24 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) return true; } +static int nf_flow_offload_dst_check(struct dst_entry *dst) +{ + if (unlikely(dst_xfrm(dst))) + return dst_check(dst, 0) ? 0 : -1; + + return 0; +} + +static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, + const struct nf_hook_state *state, + struct dst_entry *dst) +{ + skb_orphan(skb); + skb_dst_set_noref(skb, dst); + dst_output(state->net, state->sk, skb); + return NF_STOLEN; +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -254,12 +272,25 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) return NF_ACCEPT; + if (nf_flow_offload_dst_check(&rt->dst)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) return NF_DROP; flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; iph = ip_hdr(skb); ip_decrease_ttl(iph); + skb->tstamp = 0; + + if (unlikely(dst_xfrm(&rt->dst))) { + memset(skb->cb, 0, sizeof(struct inet_skb_parm)); + IPCB(skb)->iif = skb->dev->ifindex; + IPCB(skb)->flags = IPSKB_FORWARDED; + return nf_flow_xmit_xfrm(skb, state, &rt->dst); + } skb->dev = outdev; nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); @@ -467,6 +498,11 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, sizeof(*ip6h))) return NF_ACCEPT; + if (nf_flow_offload_dst_check(&rt->dst)) { + flow_offload_teardown(flow); + return NF_ACCEPT; + } + if (skb_try_make_writable(skb, sizeof(*ip6h))) return NF_DROP; @@ -476,6 +512,14 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; ip6h = ipv6_hdr(skb); ip6h->hop_limit--; + skb->tstamp = 0; + + if (unlikely(dst_xfrm(&rt->dst))) { + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); + IP6CB(skb)->iif = skb->dev->ifindex; + IP6CB(skb)->flags = IP6SKB_FORWARDED; + return nf_flow_xmit_xfrm(skb, state, &rt->dst); + } skb->dev = outdev; nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c index a352604d6186..3bc7e0854efe 100644 --- a/net/netfilter/nf_nat_amanda.c +++ b/net/netfilter/nf_nat_amanda.c @@ -48,7 +48,7 @@ static unsigned int help(struct sk_buff *skb, int res; exp->tuple.dst.u.tcp.port = htons(port); - res = nf_ct_expect_related(exp); + res = nf_ct_expect_related(exp, 0); if (res == 0) break; else if (res != -EBUSY) { diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 9ab410455992..3f6023ed4966 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -519,7 +519,7 @@ another_round: * and NF_INET_LOCAL_OUT, we change the destination to map into the * range. It might not be possible to get a unique tuple, but we try. * At worst (or if we race), we will end up with a final duplicate in - * __ip_conntrack_confirm and drop the packet. */ + * __nf_conntrack_confirm and drop the packet. */ static void get_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig_tuple, diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c index d48484a9d52d..aace6768a64e 100644 --- a/net/netfilter/nf_nat_ftp.c +++ b/net/netfilter/nf_nat_ftp.c @@ -91,7 +91,7 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, int ret; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index dfb7ef8845bd..c691ab8d234c 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -53,7 +53,7 @@ static unsigned int help(struct sk_buff *skb, int ret; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index e338d91980d8..f0a735e86851 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -414,7 +414,7 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, int ret; exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, NF_CT_EXP_F_SKIP_MASTER); if (ret == 0) break; else if (ret != -EBUSY) { @@ -607,7 +607,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, int ret; rtp_exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(rtp_exp); + ret = nf_ct_expect_related(rtp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (ret == -EBUSY) continue; else if (ret < 0) { @@ -615,7 +616,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, break; } rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); - ret = nf_ct_expect_related(rtcp_exp); + ret = nf_ct_expect_related(rtcp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (ret == 0) break; else if (ret == -EBUSY) { diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c index 833a11f68031..1a591132d6eb 100644 --- a/net/netfilter/nf_nat_tftp.c +++ b/net/netfilter/nf_nat_tftp.c @@ -30,7 +30,7 @@ static unsigned int help(struct sk_buff *skb, = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; exp->dir = IP_CT_DIR_REPLY; exp->expectfn = nf_nat_follow_master; - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, exp->master, "cannot add expectation"); return NF_DROP; } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b101f187eda8..c769462a839e 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -470,7 +470,7 @@ synproxy_send_client_synack(struct net *net, struct iphdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; - u16 mss = opts->mss; + u16 mss = opts->mss_encode; iph = ip_hdr(skb); @@ -687,7 +687,7 @@ ipv4_synproxy_hook(void *priv, struct sk_buff *skb, state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: - if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; @@ -884,7 +884,7 @@ synproxy_send_client_synack_ipv6(struct net *net, struct ipv6hdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; - u16 mss = opts->mss; + u16 mss = opts->mss_encode; iph = ipv6_hdr(skb); @@ -1111,7 +1111,7 @@ ipv6_synproxy_hook(void *priv, struct sk_buff *skb, state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: - if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ed17a7c29b86..d47469f824a1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -138,9 +138,14 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) return; list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { - if (trans->msg_type == NFT_MSG_NEWSET && - nft_trans_set(trans) == set) { - set->bound = true; + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_trans_set(trans) == set) + nft_trans_set_bound(trans) = true; + break; + case NFT_MSG_NEWSETELEM: + if (nft_trans_elem_set(trans) == set) + nft_trans_elem_set_bound(trans) = true; break; } } @@ -1662,7 +1667,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, chain->flags |= NFT_BASE_CHAIN | flags; basechain->policy = NF_ACCEPT; - INIT_LIST_HEAD(&basechain->cb_list); + if (chain->flags & NFT_CHAIN_HW_OFFLOAD && + nft_chain_offload_priority(basechain) < 0) + return -EOPNOTSUPP; + + flow_block_init(&basechain->flow_block); } else { chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (chain == NULL) @@ -1900,6 +1909,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nla[NFTA_CHAIN_FLAGS]) flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS])); + else if (chain) + flags = chain->flags; nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); @@ -6904,7 +6915,7 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - if (nft_trans_set(trans)->bound) { + if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; } @@ -6916,7 +6927,7 @@ static int __nf_tables_abort(struct net *net) nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: - if (nft_trans_elem_set(trans)->bound) { + if (nft_trans_elem_set_bound(trans)) { nft_trans_destroy(trans); break; } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 2c3302845f67..c0d18c1d77ac 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -103,10 +103,11 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx, } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, - __be16 proto, - struct netlink_ext_ack *extack) + __be16 proto, int priority, + struct netlink_ext_ack *extack) { common->protocol = proto; + common->prio = priority; common->extack = extack; } @@ -116,7 +117,7 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain, struct flow_block_cb *block_cb; int err; - list_for_each_entry(block_cb, &basechain->cb_list, list) { + list_for_each_entry(block_cb, &basechain->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; @@ -124,6 +125,15 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain, return 0; } +int nft_chain_offload_priority(struct nft_base_chain *basechain) +{ + if (basechain->ops.priority <= 0 || + basechain->ops.priority > USHRT_MAX) + return -1; + + return 0; +} + static int nft_flow_offload_rule(struct nft_trans *trans, enum flow_cls_command command) { @@ -142,7 +152,8 @@ static int nft_flow_offload_rule(struct nft_trans *trans, if (flow) proto = flow->proto; - nft_flow_offload_common_init(&cls_flow.common, proto, &extack); + nft_flow_offload_common_init(&cls_flow.common, proto, + basechain->ops.priority, &extack); cls_flow.command = command; cls_flow.cookie = (unsigned long) rule; if (flow) @@ -154,7 +165,7 @@ static int nft_flow_offload_rule(struct nft_trans *trans, static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { - list_splice(&bo->cb_list, &basechain->cb_list); + list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } @@ -198,6 +209,7 @@ static int nft_flow_offload_chain(struct nft_trans *trans, return -EOPNOTSUPP; bo.command = cmd; + bo.block = &basechain->flow_block; bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo.extack = &extack; INIT_LIST_HEAD(&bo.cb_list); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 92077d459109..4abbb452cf6c 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -578,7 +578,7 @@ static int nfnetlink_bind(struct net *net, int group) ss = nfnetlink_get_subsys(type << 8); rcu_read_unlock(); if (!ss) - request_module("nfnetlink-subsys-%d", type); + request_module_nowait("nfnetlink-subsys-%d", type); return 0; } #endif diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 3fd540b2c6ba..b5d5d071d765 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -193,7 +193,7 @@ static inline void nft_chain_filter_inet_init(void) {} static inline void nft_chain_filter_inet_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV6 */ -#ifdef CONFIG_NF_TABLES_BRIDGE +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) static unsigned int nft_do_chain_bridge(void *priv, struct sk_buff *skb, diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index 2f89bde3c61c..ff9ac8ae0031 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -142,3 +142,6 @@ MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat"); #ifdef CONFIG_NF_TABLES_IPV6 MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); #endif +#ifdef CONFIG_NF_TABLES_INET +MODULE_ALIAS_NFT_CHAIN(1, "nat"); /* NFPROTO_INET */ +#endif diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 827ab6196df9..46ca8bcca1bd 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1252,7 +1252,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, priv->l4proto, NULL, &priv->dport); exp->timeout.expires = jiffies + priv->timeout * HZ; - if (nf_ct_expect_related(exp) != 0) + if (nf_ct_expect_related(exp, 0) != 0) regs->verdict.code = NF_DROP; } diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index aa5f571d4361..01705ad74a9a 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -72,11 +72,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; + struct tcphdr _tcph, *tcph = NULL; enum ip_conntrack_info ctinfo; struct nf_flow_route route; struct flow_offload *flow; enum ip_conntrack_dir dir; - bool is_tcp = false; struct nf_conn *ct; int ret; @@ -89,7 +89,10 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: - is_tcp = true; + tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, + sizeof(_tcph), &_tcph); + if (unlikely(!tcph || tcph->fin || tcph->rst)) + goto out; break; case IPPROTO_UDP: break; @@ -115,7 +118,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (!flow) goto err_flow_alloc; - if (is_tcp) { + if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } @@ -146,6 +149,11 @@ static int nft_flow_offload_validate(const struct nft_ctx *ctx, return nft_chain_validate_hooks(ctx->chain, hook_mask); } +static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = { + [NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING, + .len = NFT_NAME_MAXLEN - 1 }, +}; + static int nft_flow_offload_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -204,6 +212,7 @@ static const struct nft_expr_ops nft_flow_offload_ops = { static struct nft_expr_type nft_flow_offload_type __read_mostly = { .name = "flow_offload", .ops = &nft_flow_offload_ops, + .policy = nft_flow_offload_policy, .maxattr = NFTA_FLOW_MAX, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index fe93e731dc7f..b836d550b919 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -129,7 +129,7 @@ static int nft_symhash_init(const struct nft_ctx *ctx, priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); - if (priv->modulus <= 1) + if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 76866f77e343..f69afb9ff3cb 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -60,24 +60,16 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = skb->mark; break; case NFT_META_IIF: - if (in == NULL) - goto err; - *dest = in->ifindex; + *dest = in ? in->ifindex : 0; break; case NFT_META_OIF: - if (out == NULL) - goto err; - *dest = out->ifindex; + *dest = out ? out->ifindex : 0; break; case NFT_META_IIFNAME: - if (in == NULL) - goto err; - strncpy((char *)dest, in->name, IFNAMSIZ); + strncpy((char *)dest, in ? in->name : "", IFNAMSIZ); break; case NFT_META_OIFNAME: - if (out == NULL) - goto err; - strncpy((char *)dest, out->name, IFNAMSIZ); + strncpy((char *)dest, out ? out->name : "", IFNAMSIZ); break; case NFT_META_IIFTYPE: if (in == NULL) @@ -546,7 +538,7 @@ nft_meta_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) return ERR_PTR(-EINVAL); -#ifdef CONFIG_NF_TABLES_BRIDGE +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META) if (ctx->family == NFPROTO_BRIDGE) return ERR_PTR(-EAGAIN); #endif diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 8487eeff5c0e..43eeb1f609f1 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -291,4 +291,4 @@ module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); -MODULE_ALIAS_NFT_EXPR("nat"); +MODULE_ALIAS_NFT_EXPR("redir"); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 80060ade8a5b..928e661d1517 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -31,6 +31,8 @@ static void nft_synproxy_tcp_options(struct synproxy_options *opts, opts->options |= NF_SYNPROXY_OPT_ECN; opts->options &= priv->info.options; + opts->mss_encode = opts->mss; + opts->mss = info->mss; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, opts); else diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index d0ab1adf5bff..5aab6df74e0f 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -54,25 +54,39 @@ nfacct_mt_destroy(const struct xt_mtdtor_param *par) nfnl_acct_put(info->nfacct); } -static struct xt_match nfacct_mt_reg __read_mostly = { - .name = "nfacct", - .family = NFPROTO_UNSPEC, - .checkentry = nfacct_mt_checkentry, - .match = nfacct_mt, - .destroy = nfacct_mt_destroy, - .matchsize = sizeof(struct xt_nfacct_match_info), - .usersize = offsetof(struct xt_nfacct_match_info, nfacct), - .me = THIS_MODULE, +static struct xt_match nfacct_mt_reg[] __read_mostly = { + { + .name = "nfacct", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = nfacct_mt_checkentry, + .match = nfacct_mt, + .destroy = nfacct_mt_destroy, + .matchsize = sizeof(struct xt_nfacct_match_info), + .usersize = offsetof(struct xt_nfacct_match_info, nfacct), + .me = THIS_MODULE, + }, + { + .name = "nfacct", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = nfacct_mt_checkentry, + .match = nfacct_mt, + .destroy = nfacct_mt_destroy, + .matchsize = sizeof(struct xt_nfacct_match_info_v1), + .usersize = offsetof(struct xt_nfacct_match_info_v1, nfacct), + .me = THIS_MODULE, + }, }; static int __init nfacct_mt_init(void) { - return xt_register_match(&nfacct_mt_reg); + return xt_register_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } static void __exit nfacct_mt_exit(void) { - xt_unregister_match(&nfacct_mt_reg); + xt_unregister_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } module_init(nfacct_mt_init); diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index ead7c6022208..b92b22ce8abd 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -101,11 +101,9 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) && (!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) || info->invert & XT_PHYSDEV_OP_BRIDGED) && - par->hook_mask & ((1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_FORWARD) | (1 << NF_INET_POST_ROUTING))) { + par->hook_mask & (1 << NF_INET_LOCAL_OUT)) { pr_info_ratelimited("--physdev-out and --physdev-is-out only supported in the FORWARD and POSTROUTING chains with bridged traffic\n"); - if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) - return -EINVAL; + return -EINVAL; } if (!brnf_probed) { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 96740d389377..c4f54ad2b98a 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -967,6 +967,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) window = skb->data[20]; + sock_hold(make); skb->sk = make; skb->destructor = sock_efree; make->sk_state = TCP_ESTABLISHED; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 848c6eb55064..05249eb45082 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -67,6 +67,7 @@ struct ovs_conntrack_info { struct md_mark mark; struct md_labels labels; char timeout[CTNL_TIMEOUT_NAME_MAX]; + struct nf_ct_timeout *nf_ct_timeout; #if IS_ENABLED(CONFIG_NF_NAT) struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */ #endif @@ -524,6 +525,11 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, return -EPFNOSUPPORT; } + /* The key extracted from the fragment that completed this datagram + * likely didn't have an L4 header, so regenerate it. + */ + ovs_flow_key_update_l3l4(skb, key); + key->ip.frag = OVS_FRAG_TYPE_NONE; skb_clear_hash(skb); skb->ignore_df = 1; @@ -697,6 +703,14 @@ static bool skb_nfct_cached(struct net *net, if (help && rcu_access_pointer(help->helper) != info->helper) return false; } + if (info->nf_ct_timeout) { + struct nf_conn_timeout *timeout_ext; + + timeout_ext = nf_ct_timeout_find(ct); + if (!timeout_ext || info->nf_ct_timeout != + rcu_dereference(timeout_ext->timeout)) + return false; + } /* Force conntrack entry direction to the current packet? */ if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { /* Delete the conntrack entry if confirmed, else just release @@ -1565,7 +1579,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, case OVS_CT_ATTR_TIMEOUT: memcpy(info->timeout, nla_data(a), nla_len(a)); if (!memchr(info->timeout, '\0', nla_len(a))) { - OVS_NLERR(log, "Invalid conntrack helper"); + OVS_NLERR(log, "Invalid conntrack timeout"); return -EINVAL; } break; @@ -1657,6 +1671,10 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, ct_info.timeout)) pr_info_ratelimited("Failed to associated timeout " "policy `%s'\n", ct_info.timeout); + else + ct_info.nf_ct_timeout = rcu_dereference( + nf_ct_timeout_find(ct_info.ct)->timeout); + } if (helper) { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 892287d06c17..d01410e52097 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1047,7 +1047,7 @@ error: } /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */ -static struct sw_flow_actions *get_flow_actions(struct net *net, +static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net, const struct nlattr *a, const struct sw_flow_key *key, const struct sw_flow_mask *mask, @@ -1081,12 +1081,13 @@ static struct sw_flow_actions *get_flow_actions(struct net *net, * we should not to return match object with dangling reference * to mask. * */ -static int ovs_nla_init_match_and_action(struct net *net, - struct sw_flow_match *match, - struct sw_flow_key *key, - struct nlattr **a, - struct sw_flow_actions **acts, - bool log) +static noinline_for_stack int +ovs_nla_init_match_and_action(struct net *net, + struct sw_flow_match *match, + struct sw_flow_key *key, + struct nlattr **a, + struct sw_flow_actions **acts, + bool log) { struct sw_flow_mask mask; int error = 0; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index dca3b1e2acf0..9d81d2c7bf82 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -59,7 +59,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies) void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, const struct sk_buff *skb) { - struct flow_stats *stats; + struct sw_flow_stats *stats; unsigned int cpu = smp_processor_id(); int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); @@ -87,7 +87,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, if (likely(flow->stats_last_writer != -1) && likely(!rcu_access_pointer(flow->stats[cpu]))) { /* Try to allocate CPU-specific stats. */ - struct flow_stats *new_stats; + struct sw_flow_stats *new_stats; new_stats = kmem_cache_alloc_node(flow_stats_cache, @@ -134,7 +134,7 @@ void ovs_flow_stats_get(const struct sw_flow *flow, /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { - struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); + struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); if (stats) { /* Local CPU may write on non-local stats, so we must @@ -158,7 +158,7 @@ void ovs_flow_stats_clear(struct sw_flow *flow) /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { - struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]); + struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]); if (stats) { spin_lock_bh(&stats->lock); @@ -523,78 +523,15 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) } /** - * key_extract - extracts a flow key from an Ethernet frame. + * key_extract_l3l4 - extracts L3/L4 header information. * @skb: sk_buff that contains the frame, with skb->data pointing to the - * Ethernet header + * L3 header * @key: output flow key * - * The caller must ensure that skb->len >= ETH_HLEN. - * - * Returns 0 if successful, otherwise a negative errno value. - * - * Initializes @skb header fields as follows: - * - * - skb->mac_header: the L2 header. - * - * - skb->network_header: just past the L2 header, or just past the - * VLAN header, to the first byte of the L2 payload. - * - * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6 - * on output, then just past the IP header, if one is present and - * of a correct length, otherwise the same as skb->network_header. - * For other key->eth.type values it is left untouched. - * - * - skb->protocol: the type of the data starting at skb->network_header. - * Equals to key->eth.type. */ -static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) +static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) { int error; - struct ethhdr *eth; - - /* Flags are always used as part of stats */ - key->tp.flags = 0; - - skb_reset_mac_header(skb); - - /* Link layer. */ - clear_vlan(key); - if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) { - if (unlikely(eth_type_vlan(skb->protocol))) - return -EINVAL; - - skb_reset_network_header(skb); - key->eth.type = skb->protocol; - } else { - eth = eth_hdr(skb); - ether_addr_copy(key->eth.src, eth->h_source); - ether_addr_copy(key->eth.dst, eth->h_dest); - - __skb_pull(skb, 2 * ETH_ALEN); - /* We are going to push all headers that we pull, so no need to - * update skb->csum here. - */ - - if (unlikely(parse_vlan(skb, key))) - return -ENOMEM; - - key->eth.type = parse_ethertype(skb); - if (unlikely(key->eth.type == htons(0))) - return -ENOMEM; - - /* Multiple tagged packets need to retain TPID to satisfy - * skb_vlan_pop(), which will later shift the ethertype into - * skb->protocol. - */ - if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK)) - skb->protocol = key->eth.cvlan.tpid; - else - skb->protocol = key->eth.type; - - skb_reset_network_header(skb); - __skb_push(skb, skb->data - skb_mac_header(skb)); - } - skb_reset_mac_len(skb); /* Network layer. */ if (key->eth.type == htons(ETH_P_IP)) { @@ -623,6 +560,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) offset = nh->frag_off & htons(IP_OFFSET); if (offset) { key->ip.frag = OVS_FRAG_TYPE_LATER; + memset(&key->tp, 0, sizeof(key->tp)); return 0; } if (nh->frag_off & htons(IP_MF) || @@ -740,8 +678,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) return error; } - if (key->ip.frag == OVS_FRAG_TYPE_LATER) + if (key->ip.frag == OVS_FRAG_TYPE_LATER) { + memset(&key->tp, 0, sizeof(key->tp)); return 0; + } if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) key->ip.frag = OVS_FRAG_TYPE_FIRST; @@ -788,6 +728,92 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) return 0; } +/** + * key_extract - extracts a flow key from an Ethernet frame. + * @skb: sk_buff that contains the frame, with skb->data pointing to the + * Ethernet header + * @key: output flow key + * + * The caller must ensure that skb->len >= ETH_HLEN. + * + * Returns 0 if successful, otherwise a negative errno value. + * + * Initializes @skb header fields as follows: + * + * - skb->mac_header: the L2 header. + * + * - skb->network_header: just past the L2 header, or just past the + * VLAN header, to the first byte of the L2 payload. + * + * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6 + * on output, then just past the IP header, if one is present and + * of a correct length, otherwise the same as skb->network_header. + * For other key->eth.type values it is left untouched. + * + * - skb->protocol: the type of the data starting at skb->network_header. + * Equals to key->eth.type. + */ +static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) +{ + struct ethhdr *eth; + + /* Flags are always used as part of stats */ + key->tp.flags = 0; + + skb_reset_mac_header(skb); + + /* Link layer. */ + clear_vlan(key); + if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) { + if (unlikely(eth_type_vlan(skb->protocol))) + return -EINVAL; + + skb_reset_network_header(skb); + key->eth.type = skb->protocol; + } else { + eth = eth_hdr(skb); + ether_addr_copy(key->eth.src, eth->h_source); + ether_addr_copy(key->eth.dst, eth->h_dest); + + __skb_pull(skb, 2 * ETH_ALEN); + /* We are going to push all headers that we pull, so no need to + * update skb->csum here. + */ + + if (unlikely(parse_vlan(skb, key))) + return -ENOMEM; + + key->eth.type = parse_ethertype(skb); + if (unlikely(key->eth.type == htons(0))) + return -ENOMEM; + + /* Multiple tagged packets need to retain TPID to satisfy + * skb_vlan_pop(), which will later shift the ethertype into + * skb->protocol. + */ + if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK)) + skb->protocol = key->eth.cvlan.tpid; + else + skb->protocol = key->eth.type; + + skb_reset_network_header(skb); + __skb_push(skb, skb->data - skb_mac_header(skb)); + } + + skb_reset_mac_len(skb); + + /* Fill out L3/L4 key info, if any */ + return key_extract_l3l4(skb, key); +} + +/* In the case of conntrack fragment handling it expects L3 headers, + * add a helper. + */ +int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key) +{ + return key_extract_l3l4(skb, key); +} + int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) { int res; diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 3e2cc2202d66..b830d5ff7af4 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -194,7 +194,7 @@ struct sw_flow_actions { struct nlattr actions[]; }; -struct flow_stats { +struct sw_flow_stats { u64 packet_count; /* Number of packets matched. */ u64 byte_count; /* Number of bytes matched. */ unsigned long used; /* Last used time (in jiffies). */ @@ -216,7 +216,7 @@ struct sw_flow { struct cpumask cpu_used_mask; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; - struct flow_stats __rcu *stats[]; /* One for each CPU. First one + struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one * is allocated at flow creation time, * the rest are allocated on demand * while holding the 'stats[0].lock'. @@ -270,6 +270,7 @@ void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key); +int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key); int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 988fd8a94e43..cf3582c5ed70 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -66,7 +66,7 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, struct sw_flow *ovs_flow_alloc(void) { struct sw_flow *flow; - struct flow_stats *stats; + struct sw_flow_stats *stats; flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL); if (!flow) @@ -110,7 +110,7 @@ static void flow_free(struct sw_flow *flow) for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, - (struct flow_stats __force *)flow->stats[cpu]); + (struct sw_flow_stats __force *)flow->stats[cpu]); kmem_cache_free(flow_cache, flow); } @@ -712,13 +712,13 @@ int ovs_flow_init(void) flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + (nr_cpu_ids - * sizeof(struct flow_stats *)), + * sizeof(struct sw_flow_stats *)), 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; flow_stats_cache - = kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats), + = kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats), 0, SLAB_HWCACHE_ALIGN, NULL); if (flow_stats_cache == NULL) { kmem_cache_destroy(flow_cache); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8d54f3047768..e2742b006d25 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2618,6 +2618,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) mutex_lock(&po->pg_vec_lock); + /* packet_sendmsg() check on tx_ring.pg_vec was lockless, + * we need to confirm it under protection of pg_vec_lock. + */ + if (unlikely(!po->tx_ring.pg_vec)) { + err = -EBUSY; + goto out; + } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; diff --git a/net/psample/psample.c b/net/psample/psample.c index 841f198ea1a8..66e4b61a350d 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -154,7 +154,7 @@ static void psample_group_destroy(struct psample_group *group) { psample_group_notify(group, PSAMPLE_CMD_DEL_GROUP); list_del(&group->list); - kfree(group); + kfree_rcu(group, rcu); } static struct psample_group * diff --git a/net/rds/ib.c b/net/rds/ib.c index ec05d91aa9a2..45acab2de0cf 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -291,7 +291,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, void *buffer) { struct rds_info_rdma_connection *iinfo = buffer; - struct rds_ib_connection *ic; + struct rds_ib_connection *ic = conn->c_transport_data; /* We will only ever look at IB transports */ if (conn->c_trans != &rds_ib_transport) @@ -301,15 +301,16 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, iinfo->src_addr = conn->c_laddr.s6_addr32[3]; iinfo->dst_addr = conn->c_faddr.s6_addr32[3]; - iinfo->tos = conn->c_tos; + if (ic) { + iinfo->tos = conn->c_tos; + iinfo->sl = ic->i_sl; + } memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; - ic = conn->c_transport_data; - rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo->src_gid, (union ib_gid *)&iinfo->dst_gid); @@ -329,7 +330,7 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, void *buffer) { struct rds6_info_rdma_connection *iinfo6 = buffer; - struct rds_ib_connection *ic; + struct rds_ib_connection *ic = conn->c_transport_data; /* We will only ever look at IB transports */ if (conn->c_trans != &rds_ib_transport) @@ -337,6 +338,10 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, iinfo6->src_addr = conn->c_laddr; iinfo6->dst_addr = conn->c_faddr; + if (ic) { + iinfo6->tos = conn->c_tos; + iinfo6->sl = ic->i_sl; + } memset(&iinfo6->src_gid, 0, sizeof(iinfo6->src_gid)); memset(&iinfo6->dst_gid, 0, sizeof(iinfo6->dst_gid)); @@ -344,7 +349,6 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; - ic = conn->c_transport_data; rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo6->src_gid, (union ib_gid *)&iinfo6->dst_gid); rds_ibdev = ic->rds_ibdev; diff --git a/net/rds/ib.h b/net/rds/ib.h index 303c6ee8bdb7..f2b558e8b5ea 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -220,6 +220,7 @@ struct rds_ib_connection { /* Send/Recv vectors */ int i_scq_vector; int i_rcq_vector; + u8 i_sl; }; /* This assumes that atomic_t is at least 32 bits */ diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index fddaa09f7b0d..233f1368162b 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -152,6 +152,9 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even RDS_PROTOCOL_MINOR(conn->c_version), ic->i_flowctl ? ", flow control" : ""); + /* receive sl from the peer */ + ic->i_sl = ic->i_cm_id->route.path_rec->sl; + atomic_set(&ic->i_cq_quiesce, 0); /* Init rings and fill recv. this needs to wait until protocol diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index ff74c4bbb9fc..5f741e51b4ba 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -43,6 +43,9 @@ static struct rdma_cm_id *rds_rdma_listen_id; static struct rdma_cm_id *rds6_rdma_listen_id; #endif +/* Per IB specification 7.7.3, service level is a 4-bit field. */ +#define TOS_TO_SL(tos) ((tos) & 0xF) + static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, struct rdma_cm_event *event, bool isv6) @@ -97,15 +100,19 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, struct rds_ib_connection *ibic; ibic = conn->c_transport_data; - if (ibic && ibic->i_cm_id == cm_id) + if (ibic && ibic->i_cm_id == cm_id) { + cm_id->route.path_rec[0].sl = + TOS_TO_SL(conn->c_tos); ret = trans->cm_initiate_connect(cm_id, isv6); - else + } else { rds_conn_drop(conn); + } } break; case RDMA_CM_EVENT_ESTABLISHED: - trans->cm_connect_complete(conn, event); + if (conn) + trans->cm_connect_complete(conn, event); break; case RDMA_CM_EVENT_REJECTED: @@ -137,6 +144,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_DISCONNECTED: + if (!conn) + break; rdsdebug("DISCONNECT event - dropping connection " "%pI6c->%pI6c\n", &conn->c_laddr, &conn->c_faddr); diff --git a/net/rds/recv.c b/net/rds/recv.c index 853de4876088..a42ba7fa06d5 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -811,6 +811,7 @@ void rds6_inc_info_copy(struct rds_incoming *inc, minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo6.len = be32_to_cpu(inc->i_hdr.h_len); + minfo6.tos = inc->i_conn->c_tos; if (flip) { minfo6.laddr = *daddr; @@ -824,6 +825,8 @@ void rds6_inc_info_copy(struct rds_incoming *inc, minfo6.fport = inc->i_hdr.h_dport; } + minfo6.flags = 0; + rds_info_copy(iter, &minfo6, sizeof(minfo6)); } #endif diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d09eaf153544..d72ddb67bb74 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -193,7 +193,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) service_in_use: write_unlock(&local->services_lock); - rxrpc_put_local(local); + rxrpc_unuse_local(local); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); @@ -402,7 +402,7 @@ EXPORT_SYMBOL(rxrpc_kernel_check_life); */ void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call) { - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_check_life); rxrpc_send_ack_packet(call, true, NULL); } @@ -862,7 +862,6 @@ static void rxrpc_sock_destructor(struct sock *sk) static int rxrpc_release_sock(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); - struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); _enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); @@ -898,10 +897,8 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_release_calls_on_socket(rx); flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); - rxrpc_queue_work(&rxnet->service_conn_reaper); - rxrpc_queue_work(&rxnet->client_conn_reaper); - rxrpc_put_local(rx->local); + rxrpc_unuse_local(rx->local); rx->local = NULL; key_put(rx->key); rx->key = NULL; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 80335b4ee4fd..8051dfdcf26d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -185,11 +185,17 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - union { - u8 nr_jumbo; /* Number of jumbo subpackets */ - }; + atomic_t nr_ring_pins; /* Number of rxtx ring pins */ + u8 nr_subpackets; /* Number of subpackets */ + u8 rx_flags; /* Received packet flags */ +#define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ +#define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */ union { int remain; /* amount of space remaining for next write */ + + /* List of requested ACKs on subpackets */ + unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) / + BITS_PER_LONG]; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ @@ -254,7 +260,8 @@ struct rxrpc_security { */ struct rxrpc_local { struct rcu_head rcu; - atomic_t usage; + atomic_t active_users; /* Number of users of the local endpoint */ + atomic_t usage; /* Number of references to the structure */ struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct list_head link; struct socket *socket; /* my UDP socket */ @@ -612,8 +619,7 @@ struct rxrpc_call { #define RXRPC_TX_ANNO_LAST 0x04 #define RXRPC_TX_ANNO_RESENT 0x08 -#define RXRPC_RX_ANNO_JUMBO 0x3f /* Jumbo subpacket number + 1 if not zero */ -#define RXRPC_RX_ANNO_JLAST 0x40 /* Set if last element of a jumbo packet */ +#define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */ #define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but * not hard-ACK'd packet follows this. @@ -649,7 +655,6 @@ struct rxrpc_call { /* receive-phase ACK management */ u8 ackr_reason; /* reason to ACK */ - u16 ackr_skew; /* skew on packet being ACK'd */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ rxrpc_serial_t ackr_first_seq; /* first sequence number received */ rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ @@ -743,7 +748,7 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * call_event.c */ -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool, +void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); @@ -905,6 +910,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *); void rxrpc_put_client_conn(struct rxrpc_connection *); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); +void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* * conn_event.c @@ -1002,6 +1008,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); void rxrpc_put_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *); +void rxrpc_unuse_local(struct rxrpc_local *); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *); @@ -1061,6 +1069,7 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); void rxrpc_put_peer(struct rxrpc_peer *); +void rxrpc_put_peer_locked(struct rxrpc_peer *); /* * proc.c @@ -1102,6 +1111,7 @@ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_packet_destructor(struct sk_buff *); void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); +void rxrpc_eaten_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index bc2adeb3acb9..cedbbb3a7c2e 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -43,8 +43,7 @@ static void rxrpc_propose_ping(struct rxrpc_call *call, * propose an ACK be sent */ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate, - bool background, + u32 serial, bool immediate, bool background, enum rxrpc_propose_ack_trace why) { enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; @@ -69,14 +68,12 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { outcome = rxrpc_propose_ack_update; call->ackr_serial = serial; - call->ackr_skew = skew; } if (!immediate) goto trace; } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { call->ackr_reason = ack_reason; call->ackr_serial = serial; - call->ackr_skew = skew; } else { outcome = rxrpc_propose_ack_subsume; } @@ -137,11 +134,11 @@ trace: * propose an ACK be sent, locking the call structure */ void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate, bool background, + u32 serial, bool immediate, bool background, enum rxrpc_propose_ack_trace why) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, skew, serial, + __rxrpc_propose_ACK(call, ack_reason, serial, immediate, background, why); spin_unlock_bh(&call->lock); } @@ -202,7 +199,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) continue; skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_tx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); if (anno_type == RXRPC_TX_ANNO_UNACK) { if (ktime_after(skb->tstamp, max_age)) { @@ -239,7 +236,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_ns(ack_ts) < call->peer->rtt) goto out; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); rxrpc_send_ack_packet(call, true, NULL); goto out; @@ -258,18 +255,18 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) continue; skb = call->rxtx_buffer[ix]; - rxrpc_get_skb(skb, rxrpc_skb_tx_got); + rxrpc_get_skb(skb, rxrpc_skb_got); spin_unlock_bh(&call->lock); if (rxrpc_send_data_packet(call, skb, true) < 0) { - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); return; } if (rxrpc_is_client_call(call)) rxrpc_expose_client_call(call); - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); spin_lock_bh(&call->lock); /* We need to clear the retransmit state, but there are two @@ -372,7 +369,7 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true, rxrpc_propose_ack_ping_for_keepalive); set_bit(RXRPC_CALL_EV_PING, &call->events); } @@ -407,7 +404,7 @@ recheck_state: send_ack = NULL; if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { call->acks_lost_top = call->tx_top; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); send_ack = &call->acks_lost_ping; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 217b12be9e08..014548c259ce 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -422,6 +422,19 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* + * Clean up the RxTx skb ring. + */ +static void rxrpc_cleanup_ring(struct rxrpc_call *call) +{ + int i; + + for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { + rxrpc_free_skb(call->rxtx_buffer[i], rxrpc_skb_cleaned); + call->rxtx_buffer[i] = NULL; + } +} + +/* * Detach a call from its owning socket. */ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) @@ -429,7 +442,6 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) const void *here = __builtin_return_address(0); struct rxrpc_connection *conn = call->conn; bool put = false; - int i; _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); @@ -479,13 +491,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) if (conn) rxrpc_disconnect_call(call); - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { - rxrpc_free_skb(call->rxtx_buffer[i], - (call->tx_phase ? rxrpc_skb_tx_cleaned : - rxrpc_skb_rx_cleaned)); - call->rxtx_buffer[i] = NULL; - } - + rxrpc_cleanup_ring(call); _leave(""); } @@ -568,8 +574,6 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { - int i; - _net("DESTROY CALL %d", call->debug_id); memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); @@ -580,13 +584,8 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); ASSERTCMP(call->conn, ==, NULL); - /* Clean up the Rx/Tx buffer */ - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) - rxrpc_free_skb(call->rxtx_buffer[i], - (call->tx_phase ? rxrpc_skb_tx_cleaned : - rxrpc_skb_rx_cleaned)); - - rxrpc_free_skb(call->tx_pending, rxrpc_skb_tx_cleaned); + rxrpc_cleanup_ring(call); + rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index aea82f909c60..3f1da1b49f69 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -1162,3 +1162,47 @@ void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet) _leave(""); } + +/* + * Clean up the client connections on a local endpoint. + */ +void rxrpc_clean_up_local_conns(struct rxrpc_local *local) +{ + struct rxrpc_connection *conn, *tmp; + struct rxrpc_net *rxnet = local->rxnet; + unsigned int nr_active; + LIST_HEAD(graveyard); + + _enter(""); + + spin_lock(&rxnet->client_conn_cache_lock); + nr_active = rxnet->nr_active_client_conns; + + list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, + cache_link) { + if (conn->params.local == local) { + ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_IDLE); + + trace_rxrpc_client(conn, -1, rxrpc_client_discard); + if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags)) + BUG(); + conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE; + list_move(&conn->cache_link, &graveyard); + nr_active--; + } + } + + rxnet->nr_active_client_conns = nr_active; + spin_unlock(&rxnet->client_conn_cache_lock); + ASSERTCMP(nr_active, >=, 0); + + while (!list_empty(&graveyard)) { + conn = list_entry(graveyard.next, + struct rxrpc_connection, cache_link); + list_del_init(&conn->cache_link); + + rxrpc_put_connection(conn); + } + + _leave(" [culled]"); +} diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index df6624c140be..a1ceef4f5cd0 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -472,7 +472,7 @@ void rxrpc_process_connection(struct work_struct *work) /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); ret = rxrpc_process_event(conn, skb, &abort_code); switch (ret) { case -EPROTO: @@ -484,7 +484,7 @@ void rxrpc_process_connection(struct work_struct *work) goto requeue_and_leave; case -ECONNABORTED: default: - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); break; } } @@ -501,6 +501,6 @@ requeue_and_leave: protocol_error: if (rxrpc_abort_connection(conn, ret, abort_code) < 0) goto requeue_and_leave; - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); goto out; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 434ef392212b..ed05b6922132 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -398,7 +398,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; - if (rxnet->live) { + if (rxnet->live && !conn->params.local->dead) { idle_timestamp = READ_ONCE(conn->idle_timestamp); expire_at = idle_timestamp + rxrpc_connection_expiry * HZ; if (conn->params.local->service_closed) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 5bd6f1546e5c..d122c53c8697 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -196,15 +196,14 @@ send_extra_data: * Ping the other end to fill our RTT cache and to retrieve the rwind * and MTU parameters. */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb, - int skew) +static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); ktime_t now = skb->tstamp; if (call->peer->rtt_usage < 3 || ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, true, true, rxrpc_propose_ack_ping_for_params); } @@ -234,7 +233,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; skb = call->rxtx_buffer[ix]; annotation = call->rxtx_annotations[ix]; - rxrpc_see_skb(skb, rxrpc_skb_tx_rotated); + rxrpc_see_skb(skb, rxrpc_skb_rotated); call->rxtx_buffer[ix] = NULL; call->rxtx_annotations[ix] = 0; skb->next = list; @@ -259,7 +258,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, skb = list; list = skb->next; skb_mark_not_on_list(skb); - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } return rot_last; @@ -348,7 +347,7 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) } /* - * Scan a jumbo packet to validate its structure and to work out how many + * Scan a data packet to validate its structure and to work out how many * subpackets it contains. * * A jumbo packet is a collection of consecutive packets glued together with @@ -359,16 +358,21 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any * size. */ -static bool rxrpc_validate_jumbo(struct sk_buff *skb) +static bool rxrpc_validate_data(struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len = skb->len; - int nr_jumbo = 1; u8 flags = sp->hdr.flags; - do { - nr_jumbo++; + for (;;) { + if (flags & RXRPC_REQUEST_ACK) + __set_bit(sp->nr_subpackets, sp->rx_req_ack); + sp->nr_subpackets++; + + if (!(flags & RXRPC_JUMBO_PACKET)) + break; + if (len - offset < RXRPC_JUMBO_SUBPKTLEN) goto protocol_error; if (flags & RXRPC_LAST_PACKET) @@ -377,9 +381,10 @@ static bool rxrpc_validate_jumbo(struct sk_buff *skb) if (skb_copy_bits(skb, offset, &flags, 1) < 0) goto protocol_error; offset += sizeof(struct rxrpc_jumbo_header); - } while (flags & RXRPC_JUMBO_PACKET); + } - sp->nr_jumbo = nr_jumbo; + if (flags & RXRPC_LAST_PACKET) + sp->rx_flags |= RXRPC_SKB_INCL_LAST; return true; protocol_error: @@ -400,10 +405,10 @@ protocol_error: * (that information is encoded in the ACK packet). */ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, - u8 annotation, bool *_jumbo_bad) + bool is_jumbo, bool *_jumbo_bad) { /* Discard normal packets that are duplicates. */ - if (annotation == 0) + if (is_jumbo) return; /* Skip jumbo subpackets that are duplicates. When we've had three or @@ -417,30 +422,30 @@ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, } /* - * Process a DATA packet, adding the packet to the Rx ring. + * Process a DATA packet, adding the packet to the Rx ring. The caller's + * packet ref must be passed on or discarded. */ -static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, - u16 skew) +static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int ix; + unsigned int j; rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0; - rxrpc_seq_t seq = sp->hdr.seq, hard_ack; - bool immediate_ack = false, jumbo_bad = false, queued; - u16 len; - u8 ack = 0, flags, annotation = 0; + rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; + bool immediate_ack = false, jumbo_bad = false; + u8 ack = 0; _enter("{%u,%u},{%u,%u}", - call->rx_hard_ack, call->rx_top, skb->len, seq); + call->rx_hard_ack, call->rx_top, skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x }", - sp->hdr.serial, seq, sp->hdr.flags); + _proto("Rx DATA %%%u { #%u f=%02x n=%u }", + sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets); state = READ_ONCE(call->state); - if (state >= RXRPC_CALL_COMPLETE) + if (state >= RXRPC_CALL_COMPLETE) { + rxrpc_free_skb(skb, rxrpc_skb_freed); return; + } if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); @@ -465,156 +470,157 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, !rxrpc_receiving_reply(call)) goto unlock; - call->ackr_prev_seq = seq; - + call->ackr_prev_seq = seq0; hard_ack = READ_ONCE(call->rx_hard_ack); - if (after(seq, hard_ack + call->rx_winsize)) { - ack = RXRPC_ACK_EXCEEDS_WINDOW; - ack_serial = serial; - goto ack; - } - flags = sp->hdr.flags; - if (flags & RXRPC_JUMBO_PACKET) { + if (sp->nr_subpackets > 1) { if (call->nr_jumbo_bad > 3) { ack = RXRPC_ACK_NOSPACE; ack_serial = serial; goto ack; } - annotation = 1; } -next_subpacket: - queued = false; - ix = seq & RXRPC_RXTX_BUFF_MASK; - len = skb->len; - if (flags & RXRPC_JUMBO_PACKET) - len = RXRPC_JUMBO_DATALEN; - - if (flags & RXRPC_LAST_PACKET) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { - rxrpc_proto_abort("LSN", call, seq); - goto unlock; - } - } else { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { - rxrpc_proto_abort("LSA", call, seq); - goto unlock; + for (j = 0; j < sp->nr_subpackets; j++) { + rxrpc_serial_t serial = sp->hdr.serial + j; + rxrpc_seq_t seq = seq0 + j; + unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; + bool terminal = (j == sp->nr_subpackets - 1); + bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); + u8 flags, annotation = j; + + _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", + j, serial, seq, terminal, last); + + if (last) { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq != call->rx_top) { + rxrpc_proto_abort("LSN", call, seq); + goto unlock; + } + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, call->rx_top)) { + rxrpc_proto_abort("LSA", call, seq); + goto unlock; + } } - } - - trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - if (before_eq(seq, hard_ack)) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - goto skip; - } - if (flags & RXRPC_REQUEST_ACK && !ack) { - ack = RXRPC_ACK_REQUESTED; - ack_serial = serial; - } + flags = 0; + if (last) + flags |= RXRPC_LAST_PACKET; + if (!terminal) + flags |= RXRPC_JUMBO_PACKET; + if (test_bit(j, sp->rx_req_ack)) + flags |= RXRPC_REQUEST_ACK; + trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, annotation, &jumbo_bad); - if (ack != RXRPC_ACK_DUPLICATE) { + if (before_eq(seq, hard_ack)) { ack = RXRPC_ACK_DUPLICATE; ack_serial = serial; + continue; } - immediate_ack = true; - goto skip; - } - - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - rxrpc_get_skb(skb, rxrpc_skb_rx_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } - immediate_ack = true; - } - if (flags & RXRPC_LAST_PACKET) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); - } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } - queued = true; - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - ack_serial = serial; + if (call->rxtx_buffer[ix]) { + rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1, + &jumbo_bad); + if (ack != RXRPC_ACK_DUPLICATE) { + ack = RXRPC_ACK_DUPLICATE; + ack_serial = serial; + } + immediate_ack = true; + continue; } - call->rx_expect_next = seq + 1; - } -skip: - offset += len; - if (flags & RXRPC_JUMBO_PACKET) { - if (skb_copy_bits(skb, offset, &flags, 1) < 0) { - rxrpc_proto_abort("XJF", call, seq); - goto unlock; - } - offset += sizeof(struct rxrpc_jumbo_header); - seq++; - serial++; - annotation++; - if (flags & RXRPC_JUMBO_PACKET) - annotation |= RXRPC_RX_ANNO_JLAST; if (after(seq, hard_ack + call->rx_winsize)) { ack = RXRPC_ACK_EXCEEDS_WINDOW; ack_serial = serial; - if (!jumbo_bad) { - call->nr_jumbo_bad++; - jumbo_bad = true; + if (flags & RXRPC_JUMBO_PACKET) { + if (!jumbo_bad) { + call->nr_jumbo_bad++; + jumbo_bad = true; + } } + goto ack; } - _proto("Rx DATA Jumbo %%%u", serial); - goto next_subpacket; - } + if (flags & RXRPC_REQUEST_ACK && !ack) { + ack = RXRPC_ACK_REQUESTED; + ack_serial = serial; + } + + /* Queue the packet. We use a couple of memory barriers here as need + * to make sure that rx_top is perceived to be set after the buffer + * pointer and that the buffer pointer is set after the annotation and + * the skb data. + * + * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() + * and also rxrpc_fill_out_ack(). + */ + if (!terminal) + rxrpc_get_skb(skb, rxrpc_skb_got); + call->rxtx_annotations[ix] = annotation; + smp_wmb(); + call->rxtx_buffer[ix] = skb; + if (after(seq, call->rx_top)) { + smp_store_release(&call->rx_top, seq); + } else if (before(seq, call->rx_top)) { + /* Send an immediate ACK if we fill in a hole */ + if (!ack) { + ack = RXRPC_ACK_DELAY; + ack_serial = serial; + } + immediate_ack = true; + } - if (queued && flags & RXRPC_LAST_PACKET && !ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; + if (terminal) { + /* From this point on, we're not allowed to touch the + * packet any longer as its ref now belongs to the Rx + * ring. + */ + skb = NULL; + } + + if (last) { + set_bit(RXRPC_CALL_RX_LAST, &call->flags); + if (!ack) { + ack = RXRPC_ACK_DELAY; + ack_serial = serial; + } + trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); + } else { + trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); + } + + if (after_eq(seq, call->rx_expect_next)) { + if (after(seq, call->rx_expect_next)) { + _net("OOS %u > %u", seq, call->rx_expect_next); + ack = RXRPC_ACK_OUT_OF_SEQUENCE; + ack_serial = serial; + } + call->rx_expect_next = seq + 1; + } } ack: if (ack) - rxrpc_propose_ACK(call, ack, skew, ack_serial, + rxrpc_propose_ACK(call, ack, ack_serial, immediate_ack, true, rxrpc_propose_ack_input_data); else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, rxrpc_propose_ack_input_data); - if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) { + if (seq0 == READ_ONCE(call->rx_hard_ack) + 1) { trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); } unlock: spin_unlock(&call->input_lock); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [queued]"); } @@ -822,8 +828,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, * soft-ACK means that the packet may be discarded and retransmission * requested. A phase is complete when all packets are hard-ACK'd. */ -static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, - u16 skew) +static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -867,11 +872,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, if (buf.ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", sp->hdr.serial); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - skew, sp->hdr.serial, true, true, + sp->hdr.serial, true, true, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - skew, sp->hdr.serial, true, true, + sp->hdr.serial, true, true, rxrpc_propose_ack_respond_to_ack); } @@ -948,7 +953,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); @@ -1004,7 +1009,7 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) * Process an incoming call packet. */ static void rxrpc_input_call_packet(struct rxrpc_call *call, - struct sk_buff *skb, u16 skew) + struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; @@ -1023,11 +1028,11 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: - rxrpc_input_data(call, skb, skew); - break; + rxrpc_input_data(call, skb); + goto no_free; case RXRPC_PACKET_TYPE_ACK: - rxrpc_input_ack(call, skb, skew); + rxrpc_input_ack(call, skb); break; case RXRPC_PACKET_TYPE_BUSY: @@ -1051,6 +1056,8 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, break; } + rxrpc_free_skb(skb, rxrpc_skb_freed); +no_free: _leave(""); } @@ -1108,8 +1115,12 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, { _enter("%p,%p", local, skb); - skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->event_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_freed); + } } /* @@ -1119,8 +1130,12 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { CHECK_SLAB_OKAY(&local->usage); - skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); + if (rxrpc_get_local_maybe(local)) { + skb_queue_tail(&local->reject_queue, skb); + rxrpc_queue_local(local); + } else { + rxrpc_free_skb(skb, rxrpc_skb_freed); + } } /* @@ -1173,7 +1188,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; unsigned int channel; - int skew = 0; _enter("%p", udp_sk); @@ -1184,7 +1198,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); - rxrpc_new_skb(skb, rxrpc_skb_rx_received); + rxrpc_new_skb(skb, rxrpc_skb_received); skb_pull(skb, sizeof(struct udphdr)); @@ -1201,7 +1215,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_free_skb(skb, rxrpc_skb_rx_lost); + rxrpc_free_skb(skb, rxrpc_skb_lost); return 0; } } @@ -1233,9 +1247,26 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.callNumber == 0 || sp->hdr.seq == 0) goto bad_message; - if (sp->hdr.flags & RXRPC_JUMBO_PACKET && - !rxrpc_validate_jumbo(skb)) + if (!rxrpc_validate_data(skb)) goto bad_message; + + /* Unshare the packet so that it can be modified for in-place + * decryption. + */ + if (sp->hdr.securityIndex != 0) { + struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); + if (!nskb) { + rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + goto out; + } + + if (nskb != skb) { + rxrpc_eaten_skb(skb, rxrpc_skb_received); + rxrpc_new_skb(skb, rxrpc_skb_unshared); + skb = nskb; + sp = rxrpc_skb(skb); + } + } break; case RXRPC_PACKET_TYPE_CHALLENGE: @@ -1301,15 +1332,8 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) goto out; } - /* Note the serial number skew here */ - skew = (int)sp->hdr.serial - (int)conn->hi_serial; - if (skew >= 0) { - if (skew > 0) - conn->hi_serial = sp->hdr.serial; - } else { - skew = -skew; - skew = min(skew, 65535); - } + if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) + conn->hi_serial = sp->hdr.serial; /* Call-bound packets are routed by connection channel. */ channel = sp->hdr.cid & RXRPC_CHANNELMASK; @@ -1372,15 +1396,18 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; - rxrpc_send_ping(call, skb, skew); + rxrpc_send_ping(call, skb); mutex_unlock(&call->user_mutex); } - rxrpc_input_call_packet(call, skb, skew); - goto discard; + /* Process a call packet; this either discards or passes on the ref + * elsewhere. + */ + rxrpc_input_call_packet(call, skb); + goto out; discard: - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); out: trace_rxrpc_rx_done(0, 0); return 0; diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index e93a78f7c05e..3ce6d628cd75 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -90,7 +90,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); _debug("{%d},{%u}", local->debug_id, sp->hdr.type); switch (sp->hdr.type) { @@ -108,7 +108,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) break; } - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } _leave(""); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index b1c71bad510b..36587260cabd 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -79,6 +79,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { atomic_set(&local->usage, 1); + atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_LIST_HEAD(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); @@ -92,7 +93,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); local->srx.srx_service = 0; - trace_rxrpc_local(local, rxrpc_local_new, 1, NULL); + trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL); } _leave(" = %p", local); @@ -266,11 +267,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, * bind the transport socket may still fail if we're attempting * to use a local address that the dying object is still using. */ - if (!rxrpc_get_local_maybe(local)) { - cursor = cursor->next; - list_del_init(&local->link); + if (!rxrpc_use_local(local)) break; - } age = "old"; goto found; @@ -284,7 +282,10 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, if (ret < 0) goto sock_error; - list_add_tail(&local->link, cursor); + if (cursor != &rxnet->local_endpoints) + list_replace_init(cursor, &local->link); + else + list_add_tail(&local->link, cursor); age = "new"; found: @@ -320,7 +321,7 @@ struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local) int n; n = atomic_inc_return(&local->usage); - trace_rxrpc_local(local, rxrpc_local_got, n, here); + trace_rxrpc_local(local->debug_id, rxrpc_local_got, n, here); return local; } @@ -334,7 +335,8 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) if (local) { int n = atomic_fetch_add_unless(&local->usage, 1, 0); if (n > 0) - trace_rxrpc_local(local, rxrpc_local_got, n + 1, here); + trace_rxrpc_local(local->debug_id, rxrpc_local_got, + n + 1, here); else local = NULL; } @@ -342,24 +344,18 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) } /* - * Queue a local endpoint. + * Queue a local endpoint and pass the caller's reference to the work item. */ void rxrpc_queue_local(struct rxrpc_local *local) { const void *here = __builtin_return_address(0); + unsigned int debug_id = local->debug_id; + int n = atomic_read(&local->usage); if (rxrpc_queue_work(&local->processor)) - trace_rxrpc_local(local, rxrpc_local_queued, - atomic_read(&local->usage), here); -} - -/* - * A local endpoint reached its end of life. - */ -static void __rxrpc_put_local(struct rxrpc_local *local) -{ - _enter("%d", local->debug_id); - rxrpc_queue_work(&local->processor); + trace_rxrpc_local(debug_id, rxrpc_local_queued, n, here); + else + rxrpc_put_local(local); } /* @@ -372,10 +368,47 @@ void rxrpc_put_local(struct rxrpc_local *local) if (local) { n = atomic_dec_return(&local->usage); - trace_rxrpc_local(local, rxrpc_local_put, n, here); + trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here); if (n == 0) - __rxrpc_put_local(local); + call_rcu(&local->rcu, rxrpc_local_rcu); + } +} + +/* + * Start using a local endpoint. + */ +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) +{ + unsigned int au; + + local = rxrpc_get_local_maybe(local); + if (!local) + return NULL; + + au = atomic_fetch_add_unless(&local->active_users, 1, 0); + if (au == 0) { + rxrpc_put_local(local); + return NULL; + } + + return local; +} + +/* + * Cease using a local endpoint. Once the number of active users reaches 0, we + * start the closure of the transport in the work processor. + */ +void rxrpc_unuse_local(struct rxrpc_local *local) +{ + unsigned int au; + + if (local) { + au = atomic_dec_return(&local->active_users); + if (au == 0) + rxrpc_queue_local(local); + else + rxrpc_put_local(local); } } @@ -393,21 +426,14 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) _enter("%d", local->debug_id); - /* We can get a race between an incoming call packet queueing the - * processor again and the work processor starting the destruction - * process which will shut down the UDP socket. - */ - if (local->dead) { - _leave(" [already dead]"); - return; - } local->dead = true; mutex_lock(&rxnet->local_mutex); list_del_init(&local->link); mutex_unlock(&rxnet->local_mutex); - ASSERT(RB_EMPTY_ROOT(&local->client_conns)); + rxrpc_clean_up_local_conns(local); + rxrpc_service_connection_reaper(&rxnet->service_conn_reaper); ASSERT(!local->service); if (socket) { @@ -422,13 +448,11 @@ static void rxrpc_local_destroyer(struct rxrpc_local *local) */ rxrpc_purge_queue(&local->reject_queue); rxrpc_purge_queue(&local->event_queue); - - _debug("rcu local %d", local->debug_id); - call_rcu(&local->rcu, rxrpc_local_rcu); } /* - * Process events on an endpoint + * Process events on an endpoint. The work item carries a ref which + * we must release. */ static void rxrpc_local_processor(struct work_struct *work) { @@ -436,13 +460,15 @@ static void rxrpc_local_processor(struct work_struct *work) container_of(work, struct rxrpc_local, processor); bool again; - trace_rxrpc_local(local, rxrpc_local_processing, + trace_rxrpc_local(local->debug_id, rxrpc_local_processing, atomic_read(&local->usage), NULL); do { again = false; - if (atomic_read(&local->usage) == 0) - return rxrpc_local_destroyer(local); + if (atomic_read(&local->active_users) == 0) { + rxrpc_local_destroyer(local); + break; + } if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); @@ -454,6 +480,8 @@ static void rxrpc_local_processor(struct work_struct *work) again = true; } } while (again); + + rxrpc_put_local(local); } /* diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 948e3fe249ec..935bb60fff56 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -87,7 +87,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, *_top = top; pkt->ack.bufferSpace = htons(8); - pkt->ack.maxSkew = htons(call->ackr_skew); + pkt->ack.maxSkew = htons(0); pkt->ack.firstPacket = htonl(hard_ack + 1); pkt->ack.previousPacket = htonl(call->ackr_prev_seq); pkt->ack.serial = htonl(serial); @@ -228,7 +228,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (ping) clear_bit(RXRPC_CALL_PINGING, &call->flags); rxrpc_propose_ACK(call, pkt->ack.reason, - ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), false, true, rxrpc_propose_ack_retry_tx); @@ -566,7 +565,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) memset(&whdr, 0, sizeof(whdr)); while ((skb = skb_dequeue(&local->reject_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); switch (skb->mark) { @@ -582,7 +581,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) ioc = 2; break; default: - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); continue; } @@ -607,7 +606,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) rxrpc_tx_point_reject); } - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); } _leave(""); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 9f2f45c09e58..c97ebdc043e4 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -163,11 +163,11 @@ void rxrpc_error_report(struct sock *sk) _leave("UDP socket errqueue empty"); return; } - rxrpc_new_skb(skb, rxrpc_skb_rx_received); + rxrpc_new_skb(skb, rxrpc_skb_received); serr = SKB_EXT_ERR(skb); if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); return; } @@ -177,7 +177,7 @@ void rxrpc_error_report(struct sock *sk) peer = NULL; if (!peer) { rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [no peer]"); return; } @@ -189,7 +189,7 @@ void rxrpc_error_report(struct sock *sk) serr->ee.ee_code == ICMP_FRAG_NEEDED)) { rxrpc_adjust_mtu(peer, serr); rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); rxrpc_put_peer(peer); _leave(" [MTU update]"); return; @@ -197,7 +197,7 @@ void rxrpc_error_report(struct sock *sk) rxrpc_store_error(peer, serr); rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); rxrpc_put_peer(peer); _leave(""); @@ -378,7 +378,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_put_peer(peer); + rxrpc_put_peer_locked(peer); } spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9d3ce81cf8ae..9c3ac96f71cb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -437,6 +437,24 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) } /* + * Drop a ref on a peer record where the caller already holds the + * peer_hash_lock. + */ +void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +{ + const void *here = __builtin_return_address(0); + int n; + + n = atomic_dec_return(&peer->usage); + trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + if (n == 0) { + hash_del_rcu(&peer->hash_link); + list_del_init(&peer->keepalive_link); + kfree_rcu(peer, rcu); + } +} + +/* * Make sure all peer records have been discarded. */ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet) diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index 99ce322d7caa..49bb972539aa 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -89,6 +89,15 @@ struct rxrpc_jumbo_header { #define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ #define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) +/* + * The maximum number of subpackets that can possibly fit in a UDP packet is: + * + * ((max_IP - IP_hdr - UDP_hdr) / RXRPC_JUMBO_SUBPKTLEN) + 1 + * = ((65535 - 28 - 28) / 1416) + 1 + * = 46 non-terminal packets and 1 terminal packet. + */ +#define RXRPC_MAX_NR_JUMBO 47 + /*****************************************************************************/ /* * on-the-wire Rx ACK packet data payload diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 5abf46cf9e6c..3b0becb12041 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -141,7 +141,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true, rxrpc_propose_ack_terminal_ack); //rxrpc_send_ack_packet(call, false, NULL); } @@ -159,7 +159,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, rxrpc_propose_ack_processing_op); break; default: @@ -177,7 +177,8 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) struct sk_buff *skb; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; - u8 flags; + bool last = false; + u8 subpacket; int ix; _enter("%d", call->debug_id); @@ -189,30 +190,32 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) hard_ack++; ix = hard_ack & RXRPC_RXTX_BUFF_MASK; skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_rx_rotated); + rxrpc_see_skb(skb, rxrpc_skb_rotated); sp = rxrpc_skb(skb); - flags = sp->hdr.flags; - serial = sp->hdr.serial; - if (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) - serial += (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) - 1; + + subpacket = call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; + serial = sp->hdr.serial + subpacket; + + if (subpacket == sp->nr_subpackets - 1 && + sp->rx_flags & RXRPC_SKB_INCL_LAST) + last = true; call->rxtx_buffer[ix] = NULL; call->rxtx_annotations[ix] = 0; /* Barrier against rxrpc_input_data(). */ smp_store_release(&call->rx_hard_ack, hard_ack); - rxrpc_free_skb(skb, rxrpc_skb_rx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); - _debug("%u,%u,%02x", hard_ack, top, flags); trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack); - if (flags & RXRPC_LAST_PACKET) { + if (last) { rxrpc_end_rx_phase(call, serial); } else { /* Check to see if there's an ACK that needs sending. */ if (after_eq(hard_ack, call->ackr_consumed + 2) || after_eq(top, call->ackr_seen + 2) || (hard_ack == top && after(hard_ack, call->ackr_consumed))) - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, true, true, rxrpc_propose_ack_rotate_rx); if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY) @@ -233,18 +236,19 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); rxrpc_seq_t seq = sp->hdr.seq; u16 cksum = sp->hdr.cksum; + u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; _enter(""); /* For all but the head jumbo subpacket, the security checksum is in a * jumbo header immediately prior to the data. */ - if ((annotation & RXRPC_RX_ANNO_JUMBO) > 1) { + if (subpacket > 0) { __be16 tmp; if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0) BUG(); cksum = ntohs(tmp); - seq += (annotation & RXRPC_RX_ANNO_JUMBO) - 1; + seq += subpacket; } return call->conn->security->verify_packet(call, skb, offset, len, @@ -265,19 +269,18 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, u8 *_annotation, unsigned int *_offset, unsigned int *_len) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len; int ret; u8 annotation = *_annotation; + u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; /* Locate the subpacket */ + offset += subpacket * RXRPC_JUMBO_SUBPKTLEN; len = skb->len - offset; - if ((annotation & RXRPC_RX_ANNO_JUMBO) > 0) { - offset += (((annotation & RXRPC_RX_ANNO_JUMBO) - 1) * - RXRPC_JUMBO_SUBPKTLEN); - len = (annotation & RXRPC_RX_ANNO_JLAST) ? - skb->len - offset : RXRPC_JUMBO_SUBPKTLEN; - } + if (subpacket < sp->nr_subpackets - 1) + len = RXRPC_JUMBO_DATALEN; if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { ret = rxrpc_verify_packet(call, skb, annotation, offset, len); @@ -303,6 +306,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, { struct rxrpc_skb_priv *sp; struct sk_buff *skb; + rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; size_t remain; bool last; @@ -336,12 +340,15 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, break; } smp_rmb(); - rxrpc_see_skb(skb, rxrpc_skb_rx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); - if (!(flags & MSG_PEEK)) + if (!(flags & MSG_PEEK)) { + serial = sp->hdr.serial; + serial += call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; trace_rxrpc_receive(call, rxrpc_receive_front, - sp->hdr.serial, seq); + serial, seq); + } if (msg) sock_recv_timestamp(msg, sock->sk, skb); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index ae8cd8926456..c60c520fde7c 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -187,10 +187,8 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct rxrpc_skb_priv *sp; struct rxrpc_crypt iv; struct scatterlist sg[16]; - struct sk_buff *trailer; unsigned int len; u16 check; - int nsg; int err; sp = rxrpc_skb(skb); @@ -214,15 +212,14 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, crypto_skcipher_encrypt(req); /* we want to encrypt the skbuff in-place */ - nsg = skb_cow_data(skb, 0, &trailer); - err = -ENOMEM; - if (nsg < 0 || nsg > 16) + err = -EMSGSIZE; + if (skb_shinfo(skb)->nr_frags > 16) goto out; len = data_size + call->conn->size_align - 1; len &= ~(call->conn->size_align - 1); - sg_init_table(sg, nsg); + sg_init_table(sg, ARRAY_SIZE(sg)); err = skb_to_sgvec(skb, sg, 0, len); if (unlikely(err < 0)) goto out; @@ -319,11 +316,10 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, struct rxkad_level1_hdr sechdr; struct rxrpc_crypt iv; struct scatterlist sg[16]; - struct sk_buff *trailer; bool aborted; u32 data_size, buf; u16 check; - int nsg, ret; + int ret; _enter(""); @@ -336,11 +332,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. */ - nsg = skb_cow_data(skb, 0, &trailer); - if (nsg < 0 || nsg > 16) - goto nomem; - - sg_init_table(sg, nsg); + sg_init_table(sg, ARRAY_SIZE(sg)); ret = skb_to_sgvec(skb, sg, offset, 8); if (unlikely(ret < 0)) return ret; @@ -388,10 +380,6 @@ protocol_error: if (aborted) rxrpc_send_abort_packet(call); return -EPROTO; - -nomem: - _leave(" = -ENOMEM"); - return -ENOMEM; } /* @@ -406,7 +394,6 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, struct rxkad_level2_hdr sechdr; struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; - struct sk_buff *trailer; bool aborted; u32 data_size, buf; u16 check; @@ -423,12 +410,11 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. */ - nsg = skb_cow_data(skb, 0, &trailer); - if (nsg < 0) - goto nomem; - sg = _sg; - if (unlikely(nsg > 4)) { + nsg = skb_shinfo(skb)->nr_frags; + if (nsg <= 4) { + nsg = 4; + } else { sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO); if (!sg) goto nomem; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5d3f33ce6d41..6a1547b270fe 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -176,7 +176,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, skb->tstamp = ktime_get_real(); ix = seq & RXRPC_RXTX_BUFF_MASK; - rxrpc_get_skb(skb, rxrpc_skb_tx_got); + rxrpc_get_skb(skb, rxrpc_skb_got); call->rxtx_annotations[ix] = annotation; smp_wmb(); call->rxtx_buffer[ix] = skb; @@ -226,6 +226,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_notify_socket(call); goto out; } _debug("need instant resend %d", ret); @@ -247,7 +248,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, } out: - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" = %d", ret); return ret; } @@ -288,7 +289,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, skb = call->tx_pending; call->tx_pending = NULL; - rxrpc_see_skb(skb, rxrpc_skb_tx_seen); + rxrpc_see_skb(skb, rxrpc_skb_seen); copied = 0; do { @@ -335,7 +336,9 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (!skb) goto maybe_error; - rxrpc_new_skb(skb, rxrpc_skb_tx_new); + sp = rxrpc_skb(skb); + sp->rx_flags |= RXRPC_SKB_TX_BUFFER; + rxrpc_new_skb(skb, rxrpc_skb_new); _debug("ALLOC SEND %p", skb); @@ -345,7 +348,6 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, skb_reserve(skb, call->conn->security_size); skb->len += call->conn->security_size; - sp = rxrpc_skb(skb); sp->remain = chunk; if (sp->remain > skb_tailroom(skb)) sp->remain = skb_tailroom(skb); @@ -438,7 +440,7 @@ out: return ret; call_terminated: - rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" = %d", call->error); return call->error; diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 9ad5045b7c2f..0348d2bf6f7d 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -14,7 +14,8 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -#define select_skb_count(op) (op >= rxrpc_skb_tx_cleaned ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) +#define is_tx_skb(skb) (rxrpc_skb(skb)->rx_flags & RXRPC_SKB_TX_BUFFER) +#define select_skb_count(skb) (is_tx_skb(skb) ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. @@ -22,8 +23,9 @@ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_inc_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); } /* @@ -33,8 +35,9 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); if (skb) { - int n = atomic_read(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_read(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); } } @@ -44,12 +47,23 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); - int n = atomic_inc_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_inc_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); skb_get(skb); } /* + * Note the dropping of a ref on a socket buffer by the core. + */ +void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +{ + const void *here = __builtin_return_address(0); + int n = atomic_inc_return(&rxrpc_n_rx_skbs); + trace_rxrpc_skb(skb, op, 0, n, 0, here); +} + +/* * Note the destruction of a socket buffer. */ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) @@ -58,8 +72,9 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) if (skb) { int n; CHECK_SLAB_OKAY(&skb->users); - n = atomic_dec_return(select_skb_count(op)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + n = atomic_dec_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); kfree_skb(skb); } } @@ -72,9 +87,10 @@ void rxrpc_purge_queue(struct sk_buff_head *list) const void *here = __builtin_return_address(0); struct sk_buff *skb; while ((skb = skb_dequeue((list))) != NULL) { - int n = atomic_dec_return(select_skb_count(rxrpc_skb_rx_purged)); - trace_rxrpc_skb(skb, rxrpc_skb_rx_purged, - refcount_read(&skb->users), n, here); + int n = atomic_dec_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, rxrpc_skb_purged, + refcount_read(&skb->users), n, + rxrpc_skb(skb)->rx_flags, here); kfree_skb(skb); } } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 8126b26f125e..04b7bd4ec751 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -285,6 +285,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; + u32 index; if (!nla) return -EINVAL; @@ -298,13 +299,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, act, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, act, + ret = tcf_idr_create(tn, index, est, act, &act_bpf_ops, bind, true); if (ret < 0) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -421,7 +422,7 @@ static __net_init int bpf_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, bpf_net_id); - return tc_action_net_init(tn, &act_bpf_ops); + return tc_action_net_init(net, tn, &act_bpf_ops); } static void __net_exit bpf_exit_net(struct list_head *net_list) diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index ce36b0f7e1dc..2b43cacf82af 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -103,6 +103,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct tcf_connmark_info *ci; struct tc_connmark *parm; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -116,13 +117,13 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_CONNMARK_PARMS]); - - ret = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + ret = tcf_idr_check_alloc(tn, &index, a, bind); if (!ret) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_connmark_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -230,7 +231,7 @@ static __net_init int connmark_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, connmark_net_id); - return tc_action_net_init(tn, &act_connmark_ops); + return tc_action_net_init(net, tn, &act_connmark_ops); } static void __net_exit connmark_exit_net(struct list_head *net_list) diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 621fb22ce2a9..d3cfad88dc3a 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -52,6 +52,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -64,13 +65,13 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_csum_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; @@ -713,7 +714,7 @@ static __net_init int csum_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, csum_net_id); - return tc_action_net_init(tn, &act_csum_ops); + return tc_action_net_init(net, tn, &act_csum_ops); } static void __net_exit csum_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b501ce0cf116..cdd6f3818097 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -666,6 +666,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, struct tc_ct *parm; struct tcf_ct *c; int err, res = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed"); @@ -681,16 +682,16 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_CT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; if (!err) { - err = tcf_idr_create(tn, parm->index, est, a, + err = tcf_idr_create(tn, index, est, a, &act_ct_ops, bind, true); if (err) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return err; } res = ACT_P_CREATED; @@ -938,7 +939,7 @@ static __net_init int ct_init_net(struct net *net) tn->labels = true; } - return tc_action_net_init(&tn->tn, &act_ct_ops); + return tc_action_net_init(net, &tn->tn, &act_ct_ops); } static void __net_exit ct_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 10eb2bb99861..0dbcfd1dca7b 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -157,10 +157,10 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); + u32 dscpmask = 0, dscpstatemask, index; struct nlattr *tb[TCA_CTINFO_MAX + 1]; struct tcf_ctinfo_params *cp_new; struct tcf_chain *goto_ch = NULL; - u32 dscpmask = 0, dscpstatemask; struct tc_ctinfo *actparm; struct tcf_ctinfo *ci; u8 dscpmaskshift; @@ -206,12 +206,13 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, } /* done the validation:now to the actual action allocation */ - err = tcf_idr_check_alloc(tn, &actparm->index, a, bind); + index = actparm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, actparm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_ctinfo_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, actparm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; @@ -375,7 +376,7 @@ static __net_init int ctinfo_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ctinfo_net_id); - return tc_action_net_init(tn, &act_ctinfo_ops); + return tc_action_net_init(net, tn, &act_ctinfo_ops); } static void __net_exit ctinfo_exit_net(struct list_head *net_list) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b2380c5284e6..324f1d1f6d47 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -61,6 +61,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, struct tc_gact *parm; struct tcf_gact *gact; int ret = 0; + u32 index; int err; #ifdef CONFIG_GACT_PROB struct tc_gact_p *p_parm = NULL; @@ -77,6 +78,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (tb[TCA_GACT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_GACT_PARMS]); + index = parm->index; #ifndef CONFIG_GACT_PROB if (tb[TCA_GACT_PROB] != NULL) @@ -94,12 +96,12 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_gact_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; @@ -276,7 +278,7 @@ static __net_init int gact_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, gact_net_id); - return tc_action_net_init(tn, &act_gact_ops); + return tc_action_net_init(net, tn, &act_gact_ops); } static void __net_exit gact_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 41d5398dd2f2..3a31e241c647 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -479,8 +479,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, u8 *saddr = NULL; bool exists = false; int ret = 0; + u32 index; int err; + if (!nla) { + NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed"); + return -EINVAL; + } + err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy, NULL); if (err < 0) @@ -502,7 +508,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { kfree(p); return err; @@ -514,10 +521,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, + ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); kfree(p); return ret; } @@ -883,7 +890,7 @@ static __net_init int ife_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ife_net_id); - return tc_action_net_init(tn, &act_ife_ops); + return tc_action_net_init(net, tn, &act_ife_ops); } static void __net_exit ife_exit_net(struct list_head *net_list) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index ce2c30a591d2..214a03d405cf 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -61,12 +61,13 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t, return 0; } -static void ipt_destroy_target(struct xt_entry_target *t) +static void ipt_destroy_target(struct xt_entry_target *t, struct net *net) { struct xt_tgdtor_param par = { .target = t->u.kernel.target, .targinfo = t->data, .family = NFPROTO_IPV4, + .net = net, }; if (par.target->destroy != NULL) par.target->destroy(&par); @@ -78,7 +79,7 @@ static void tcf_ipt_release(struct tc_action *a) struct tcf_ipt *ipt = to_ipt(a); if (ipt->tcfi_t) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net); kfree(ipt->tcfi_t); } kfree(ipt->tcfi_tname); @@ -180,7 +181,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, spin_lock_bh(&ipt->tcf_lock); if (ret != ACT_P_CREATED) { - ipt_destroy_target(ipt->tcfi_t); + ipt_destroy_target(ipt->tcfi_t, net); kfree(ipt->tcfi_tname); kfree(ipt->tcfi_t); } @@ -350,7 +351,7 @@ static __net_init int ipt_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ipt_net_id); - return tc_action_net_init(tn, &act_ipt_ops); + return tc_action_net_init(net, tn, &act_ipt_ops); } static void __net_exit ipt_exit_net(struct list_head *net_list) @@ -399,7 +400,7 @@ static __net_init int xt_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, xt_net_id); - return tc_action_net_init(tn, &act_xt_ops); + return tc_action_net_init(net, tn, &act_xt_ops); } static void __net_exit xt_exit_net(struct list_head *net_list) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 055faa298c8e..9d1bf508075a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -104,6 +104,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct net_device *dev; bool exists = false; int ret, err; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); @@ -118,8 +119,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MIRRED_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,21 +137,21 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (!exists) { if (!parm->ifindex) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mirred_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; @@ -452,7 +453,7 @@ static __net_init int mirred_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, mirred_net_id); - return tc_action_net_init(tn, &act_mirred_ops); + return tc_action_net_init(net, tn, &act_mirred_ops); } static void __net_exit mirred_exit_net(struct list_head *net_list) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index ca2597ce4ac9..e168df0e008a 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -138,6 +138,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, struct tcf_mpls *m; int ret = 0, err; u8 mpls_ttl = 0; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes"); @@ -153,6 +154,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } parm = nla_data(tb[TCA_MPLS_PARMS]); + index = parm->index; /* Verify parameters against action type. */ switch (parm->m_action) { @@ -209,7 +211,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return -EINVAL; } - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -217,10 +219,10 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -373,7 +375,7 @@ static __net_init int mpls_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, mpls_net_id); - return tc_action_net_init(tn, &act_mpls_ops); + return tc_action_net_init(net, tn, &act_mpls_ops); } static void __net_exit mpls_exit_net(struct list_head *net_list) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 45923ebb7a4f..ea4c5359e7df 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -44,6 +44,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; + u32 index; if (nla == NULL) return -EINVAL; @@ -56,13 +57,13 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_NAT_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_nat_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; @@ -326,7 +327,7 @@ static __net_init int nat_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, nat_net_id); - return tc_action_net_init(tn, &act_nat_ops); + return tc_action_net_init(net, tn, &act_nat_ops); } static void __net_exit nat_exit_net(struct list_head *net_list) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 45e9d6bfddb3..cdfaa79382a2 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -149,6 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct tcf_pedit *p; int ret = 0, err; int ksize; + u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed"); @@ -179,18 +180,19 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (IS_ERR(keys_ex)) return PTR_ERR(keys_ex); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { if (!parm->nkeys) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); ret = -EINVAL; goto out_free; } - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); goto out_free; } ret = ACT_P_CREATED; @@ -496,7 +498,7 @@ static __net_init int pedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, pedit_net_id); - return tc_action_net_init(tn, &act_pedit_ops); + return tc_action_net_init(net, tn, &act_pedit_ops); } static void __net_exit pedit_exit_net(struct list_head *net_list) diff --git a/net/sched/act_police.c b/net/sched/act_police.c index a065f62fa79c..6315e0f8d26e 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -57,6 +57,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, police_net_id); struct tcf_police_params *new; bool exists = false; + u32 index; if (nla == NULL) return -EINVAL; @@ -73,7 +74,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -81,10 +83,10 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, NULL, a, + ret = tcf_idr_create(tn, index, NULL, a, &act_police_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; @@ -369,7 +371,7 @@ static __net_init int police_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, police_net_id); - return tc_action_net_init(tn, &act_police_ops); + return tc_action_net_init(net, tn, &act_police_ops); } static void __net_exit police_exit_net(struct list_head *net_list) diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 274d7a0c0e25..10229124a992 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -41,8 +41,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + u32 psample_group_num, rate, index; struct tcf_chain *goto_ch = NULL; - u32 psample_group_num, rate; struct tc_sample *parm; struct tcf_sample *s; bool exists = false; @@ -59,8 +59,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -68,10 +68,10 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, return 0; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_sample_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; @@ -102,13 +102,17 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); s->rate = rate; s->psample_group_num = psample_group_num; - RCU_INIT_POINTER(s->psample_group, psample_group); + rcu_swap_protected(s->psample_group, psample_group, + lockdep_is_held(&s->tcf_lock)); if (tb[TCA_SAMPLE_TRUNC_SIZE]) { s->truncate = true; s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } spin_unlock_bh(&s->tcf_lock); + + if (psample_group) + psample_group_put(psample_group); if (goto_ch) tcf_chain_put_by_act(goto_ch); @@ -265,7 +269,7 @@ static __net_init int sample_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, sample_net_id); - return tc_action_net_init(tn, &act_sample_ops); + return tc_action_net_init(net, tn, &act_sample_ops); } static void __net_exit sample_exit_net(struct list_head *net_list) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index f28ddbabff76..6120e56117ca 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -95,6 +95,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct tcf_defact *d; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -108,7 +109,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, return -EINVAL; parm = nla_data(tb[TCA_DEF_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -119,15 +121,15 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_simp_ops, bind, false); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -230,7 +232,7 @@ static __net_init int simp_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, simp_net_id); - return tc_action_net_init(tn, &act_simp_ops); + return tc_action_net_init(net, tn, &act_simp_ops); } static void __net_exit simp_exit_net(struct list_head *net_list) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 215a06705cef..6a8d3337c577 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,6 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, u16 *queue_mapping = NULL, *ptype = NULL; bool exists = false; int ret = 0, err; + u32 index; if (nla == NULL) return -EINVAL; @@ -146,8 +147,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -158,15 +159,15 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbedit_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -306,6 +307,17 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static size_t tcf_skbedit_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_skbedit)) + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */ + + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */ + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */ + + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */ + + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */ + + nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */ +} + static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .id = TCA_ID_SKBEDIT, @@ -315,6 +327,7 @@ static struct tc_action_ops act_skbedit_ops = { .init = tcf_skbedit_init, .cleanup = tcf_skbedit_cleanup, .walk = tcf_skbedit_walker, + .get_fill_size = tcf_skbedit_get_fill_size, .lookup = tcf_skbedit_search, .size = sizeof(struct tcf_skbedit), }; @@ -323,7 +336,7 @@ static __net_init int skbedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - return tc_action_net_init(tn, &act_skbedit_ops); + return tc_action_net_init(net, tn, &act_skbedit_ops); } static void __net_exit skbedit_exit_net(struct list_head *net_list) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 4f07706eff07..888437f97ba6 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -87,12 +87,12 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct tcf_skbmod_params *p, *p_old; struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; + u32 lflags = 0, index; struct tcf_skbmod *d; bool exists = false; u8 *daddr = NULL; u8 *saddr = NULL; u16 eth_type = 0; - u32 lflags = 0; int ret = 0, err; if (!nla) @@ -122,10 +122,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_SKBMOD_PARMS]); + index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -136,15 +137,15 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_skbmod_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -286,7 +287,7 @@ static __net_init int skbmod_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); - return tc_action_net_init(tn, &act_skbmod_ops); + return tc_action_net_init(net, tn, &act_skbmod_ops); } static void __net_exit skbmod_exit_net(struct list_head *net_list) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 10dffda1d5cc..2f83a79f76aa 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -225,6 +225,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, __be16 flags = 0; u8 tos, ttl; int ret = 0; + u32 index; int err; if (!nla) { @@ -245,7 +246,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -345,7 +347,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, } if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); @@ -403,7 +405,7 @@ err_out: if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -598,7 +600,7 @@ static __net_init int tunnel_key_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - return tc_action_net_init(tn, &act_tunnel_key_ops); + return tc_action_net_init(net, tn, &act_tunnel_key_ops); } static void __net_exit tunnel_key_exit_net(struct list_head *net_list) diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 9269d350fb8a..287a30bf8930 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -116,6 +116,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, u8 push_prio = 0; bool exists = false; int ret = 0, err; + u32 index; if (!nla) return -EINVAL; @@ -128,7 +129,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); - err = tcf_idr_check_alloc(tn, &parm->index, a, bind); + index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; @@ -144,7 +146,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); @@ -152,7 +154,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -ERANGE; } @@ -166,7 +168,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EPROTONOSUPPORT; } } else { @@ -180,16 +182,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (exists) tcf_idr_release(*a, bind); else - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return -EINVAL; } action = parm->v_action; if (!exists) { - ret = tcf_idr_create(tn, parm->index, est, a, + ret = tcf_idr_create(tn, index, est, a, &act_vlan_ops, bind, true); if (ret) { - tcf_idr_cleanup(tn, parm->index); + tcf_idr_cleanup(tn, index); return ret; } @@ -306,6 +308,14 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static size_t tcf_vlan_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_vlan)) + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ +} + static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .id = TCA_ID_VLAN, @@ -315,6 +325,7 @@ static struct tc_action_ops act_vlan_ops = { .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, + .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), }; @@ -323,7 +334,7 @@ static __net_init int vlan_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, vlan_net_id); - return tc_action_net_init(tn, &act_vlan_ops); + return tc_action_net_init(net, tn, &act_vlan_ops); } static void __net_exit vlan_exit_net(struct list_head *net_list) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d144233423c5..efd3cfb80a2a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -691,6 +691,8 @@ static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, if (!indr_dev->block) return; + bo.block = &indr_dev->block->flow_block; + indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, &bo); tcf_block_setup(indr_dev->block, &bo); @@ -775,6 +777,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, .command = command, .binder_type = ei->binder_type, .net = dev_net(dev), + .block = &block->flow_block, .block_shared = tcf_block_shared(block), .extack = extack, }; @@ -810,6 +813,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block, bo.net = dev_net(dev); bo.command = command; bo.binder_type = ei->binder_type; + bo.block = &block->flow_block; bo.block_shared = tcf_block_shared(block); bo.extack = extack; INIT_LIST_HEAD(&bo.cb_list); @@ -987,8 +991,8 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); - INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); INIT_LIST_HEAD(&block->chain0.filter_chain_list); @@ -1514,7 +1518,7 @@ void tcf_block_put(struct tcf_block *block) EXPORT_SYMBOL(tcf_block_put); static int -tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, +tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv, bool add, bool offload_in_use, struct netlink_ext_ack *extack) { @@ -1570,7 +1574,7 @@ static int tcf_block_bind(struct tcf_block *block, i++; } - list_splice(&bo->cb_list, &block->cb_list); + list_splice(&bo->cb_list, &block->flow_block.cb_list); return 0; @@ -2152,7 +2156,9 @@ replay: tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false, rtnl_held); tfilter_put(tp, fh); - q->flags &= ~TCQ_F_CAN_BYPASS; + /* q pointer is NULL for shared blocks */ + if (q) + q->flags &= ~TCQ_F_CAN_BYPASS; } errout: @@ -3156,7 +3162,7 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, if (block->nooffloaddevcnt && err_stop) return -EOPNOTSUPP; - list_for_each_entry(block_cb, &block->cb_list, list) { + list_for_each_entry(block_cb, &block->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err) { if (err_stop) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 691f71830134..3f7a9c02b70c 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -651,7 +651,7 @@ skip: } } -static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 38d6e85693fc..054123742e32 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1800,7 +1800,7 @@ fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add) return NULL; } -static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index a30d2f8feb32..455ea2793f9b 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -282,7 +282,7 @@ skip: arg->count++; } -static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index be9e46c77e8b..8614088edd1b 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1152,7 +1152,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, } static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, - bool add, tc_setup_cb_t *cb, void *cb_priv, + bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_cls_u32_offload cls_u32 = {}; @@ -1172,7 +1172,7 @@ static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, } static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, - bool add, tc_setup_cb_t *cb, void *cb_priv, + bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); @@ -1213,7 +1213,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, return 0; } -static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 732e109c3055..810645b5c086 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -181,11 +181,6 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) s64 credits; int len; - if (atomic64_read(&q->port_rate) == -1) { - WARN_ONCE(1, "cbs: dequeue() called with unknown port rate."); - return NULL; - } - if (q->credits < 0) { credits = timediff_to_credits(now - q->last, q->idleslope); @@ -303,11 +298,19 @@ static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q, static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) { struct ethtool_link_ksettings ecmd; + int speed = SPEED_10; int port_rate = -1; + int err; + + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; - if (!__ethtool_get_link_ksettings(dev, &ecmd) && - ecmd.base.speed != SPEED_UNKNOWN) - port_rate = ecmd.base.speed * 1000 * BYTES_PER_KBIT; +skip: + port_rate = speed * 1000 * BYTES_PER_KBIT; atomic64_set(&q->port_rate, port_rate); netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n", diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 25ef172c23df..30169b3adbbb 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -71,10 +71,10 @@ static struct sk_buff *dequeue_func(struct codel_vars *vars, void *ctx) struct Qdisc *sch = ctx; struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); - if (skb) + if (skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); - - prefetch(&skb->end); /* we'll need skb_shinfo() */ + prefetch(&skb->end); /* we'll need skb_shinfo() */ + } return skb; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 11c03cf4aa74..137db1cbde85 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -624,8 +624,12 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, err = skb_array_produce(q, skb); - if (unlikely(err)) - return qdisc_drop_cpu(skb, qdisc, to_free); + if (unlikely(err)) { + if (qdisc_is_percpu_stats(qdisc)) + return qdisc_drop_cpu(skb, qdisc, to_free); + else + return qdisc_drop(skb, qdisc, to_free); + } qdisc_update_stats_at_enqueue(qdisc, pkt_len); return NET_XMIT_SUCCESS; @@ -688,11 +692,14 @@ static void pfifo_fast_reset(struct Qdisc *qdisc) kfree_skb(skb); } - for_each_possible_cpu(i) { - struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i); + if (qdisc_is_percpu_stats(qdisc)) { + for_each_possible_cpu(i) { + struct gnet_stats_queue *q; - q->backlog = 0; - q->qlen = 0; + q = per_cpu_ptr(qdisc->cpu_qstats, i); + q->backlog = 0; + q->qlen = 0; + } } } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c39db507ba3f..8d8bc2ec5cd6 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -477,11 +477,6 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) u32 gate_mask; int i; - if (atomic64_read(&q->picos_per_byte) == -1) { - WARN_ONCE(1, "taprio: dequeue() called with unknown picos per byte."); - return NULL; - } - rcu_read_lock(); entry = rcu_dereference(q->current_entry); /* if there's no entry, it means that the schedule didn't @@ -958,12 +953,20 @@ static void taprio_set_picos_per_byte(struct net_device *dev, struct taprio_sched *q) { struct ethtool_link_ksettings ecmd; - int picos_per_byte = -1; + int speed = SPEED_10; + int picos_per_byte; + int err; - if (!__ethtool_get_link_ksettings(dev, &ecmd) && - ecmd.base.speed != SPEED_UNKNOWN) - picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, - ecmd.base.speed * 1000 * 1000); + err = __ethtool_get_link_ksettings(dev, &ecmd); + if (err < 0) + goto skip; + + if (ecmd.base.speed != SPEED_UNKNOWN) + speed = ecmd.base.speed; + +skip: + picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, + speed * 1000 * 1000); atomic64_set(&q->picos_per_byte, picos_per_byte); netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", @@ -1195,7 +1198,8 @@ unlock: spin_unlock_bh(qdisc_lock(sch)); free_sched: - kfree(new_admin); + if (new_admin) + call_rcu(&new_admin->rcu, taprio_free_sched_cb); return err; } @@ -1248,6 +1252,10 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, */ q->clockid = -1; + spin_lock(&taprio_list_lock); + list_add(&q->taprio_list, &taprio_list); + spin_unlock(&taprio_list_lock); + if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; @@ -1265,10 +1273,6 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, if (!opt) return -EINVAL; - spin_lock(&taprio_list_lock); - list_add(&q->taprio_list, &taprio_list); - spin_unlock(&taprio_list_lock); - for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; struct Qdisc *qdisc; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index a554d6d15d1b..1cf5bb5b73c4 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -546,7 +546,7 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands, */ if (net->sctp.pf_enable && (transport->state == SCTP_ACTIVE) && - (asoc->pf_retrans < transport->pathmaxrxt) && + (transport->error_count < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { sctp_assoc_control_transport(asoc, transport, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index aa80cda36581..9d1f83b10c0a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -985,7 +985,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Walk through the addrs buffer and count the number of addresses. */ @@ -1315,7 +1315,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, return -EINVAL; kaddrs = memdup_user(addrs, addrs_size); - if (unlikely(IS_ERR(kaddrs))) + if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); /* Allow security module to validate connectx addresses. */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 25946604af85..e83cdaa2ab76 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -316,6 +316,7 @@ int sctp_send_reset_streams(struct sctp_association *asoc, nstr_list[i] = htons(str_list[i]); if (out && !sctp_stream_outq_is_empty(stream, str_nums, nstr_list)) { + kfree(nstr_list); retval = -EAGAIN; goto out; } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 302e355f2ebc..5b932583e407 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -263,7 +263,7 @@ static int smc_bind(struct socket *sock, struct sockaddr *uaddr, /* Check if socket is already active */ rc = -EINVAL; - if (sk->sk_state != SMC_INIT) + if (sk->sk_state != SMC_INIT || smc->connect_nonblock) goto out_rel; smc->clcsock->sk->sk_reuse = sk->sk_reuse; @@ -1390,7 +1390,8 @@ static int smc_listen(struct socket *sock, int backlog) lock_sock(sk); rc = -EINVAL; - if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN)) + if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) || + smc->connect_nonblock) goto out; rc = 0; @@ -1518,7 +1519,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; if (msg->msg_flags & MSG_FASTOPEN) { - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { @@ -1732,14 +1733,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, } break; case TCP_NODELAY: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } break; case TCP_CORK: - if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (sk->sk_state != SMC_INIT && + sk->sk_state != SMC_LISTEN && + sk->sk_state != SMC_CLOSED) { if (!val && !smc->use_fallback) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index f0de323d15d6..6c8f09c1ce51 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -76,13 +76,11 @@ static int smc_tx_wait(struct smc_sock *smc, int flags) DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; - bool noblock; long timeo; int rc = 0; /* similar to sk_stream_wait_memory */ timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - noblock = timeo ? false : true; add_wait_queue(sk_sleep(sk), &wait); while (1) { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -97,8 +95,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags) break; } if (!timeo) { - if (noblock) - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + /* ensure EPOLLOUT is subsequently generated */ + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); rc = -EAGAIN; break; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d8679b6027e9..a07b516e503a 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1970,6 +1970,7 @@ call_bind(struct rpc_task *task) static void call_bind_status(struct rpc_task *task) { + struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; int status = -EIO; if (rpc_task_transmitted(task)) { @@ -1977,14 +1978,15 @@ call_bind_status(struct rpc_task *task) return; } - if (task->tk_status >= 0) { - dprint_status(task); + dprint_status(task); + trace_rpc_bind_status(task); + if (task->tk_status >= 0) + goto out_next; + if (xprt_bound(xprt)) { task->tk_status = 0; - task->tk_action = call_connect; - return; + goto out_next; } - trace_rpc_bind_status(task); switch (task->tk_status) { case -ENOMEM: dprintk("RPC: %5u rpcbind out of memory\n", task->tk_pid); @@ -2003,6 +2005,9 @@ call_bind_status(struct rpc_task *task) task->tk_rebind_retry--; rpc_delay(task, 3*HZ); goto retry_timeout; + case -ENOBUFS: + rpc_delay(task, HZ >> 2); + goto retry_timeout; case -EAGAIN: goto retry_timeout; case -ETIMEDOUT: @@ -2026,7 +2031,6 @@ call_bind_status(struct rpc_task *task) case -ENETDOWN: case -EHOSTUNREACH: case -ENETUNREACH: - case -ENOBUFS: case -EPIPE: dprintk("RPC: %5u remote rpcbind unreachable: %d\n", task->tk_pid, task->tk_status); @@ -2043,7 +2047,9 @@ call_bind_status(struct rpc_task *task) rpc_call_rpcerror(task, status); return; - +out_next: + task->tk_action = call_connect; + return; retry_timeout: task->tk_status = 0; task->tk_action = call_bind; @@ -2090,6 +2096,7 @@ call_connect(struct rpc_task *task) static void call_connect_status(struct rpc_task *task) { + struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt; struct rpc_clnt *clnt = task->tk_client; int status = task->tk_status; @@ -2099,8 +2106,17 @@ call_connect_status(struct rpc_task *task) } dprint_status(task); - trace_rpc_connect_status(task); + + if (task->tk_status == 0) { + clnt->cl_stats->netreconn++; + goto out_next; + } + if (xprt_connected(xprt)) { + task->tk_status = 0; + goto out_next; + } + task->tk_status = 0; switch (status) { case -ECONNREFUSED: @@ -2117,8 +2133,6 @@ call_connect_status(struct rpc_task *task) case -ENETDOWN: case -ENETUNREACH: case -EHOSTUNREACH: - case -EADDRINUSE: - case -ENOBUFS: case -EPIPE: xprt_conditional_disconnect(task->tk_rqstp->rq_xprt, task->tk_rqstp->rq_connect_cookie); @@ -2127,17 +2141,20 @@ call_connect_status(struct rpc_task *task) /* retry with existing socket, after a delay */ rpc_delay(task, 3*HZ); /* fall through */ + case -EADDRINUSE: case -ENOTCONN: case -EAGAIN: case -ETIMEDOUT: goto out_retry; - case 0: - clnt->cl_stats->netreconn++; - task->tk_action = call_transmit; - return; + case -ENOBUFS: + rpc_delay(task, HZ >> 2); + goto out_retry; } rpc_call_rpcerror(task, status); return; +out_next: + task->tk_action = call_transmit; + return; out_retry: /* Check for timeouts before looping back to call_bind */ task->tk_action = call_bind; @@ -2365,7 +2382,7 @@ call_status(struct rpc_task *task) case -ECONNABORTED: case -ENOTCONN: rpc_force_rebind(clnt); - /* fall through */ + break; case -EADDRINUSE: rpc_delay(task, 3*HZ); /* fall through */ diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 783748dc5e6f..2e71f5455c6c 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1408,13 +1408,6 @@ xprt_request_transmit(struct rpc_rqst *req, struct rpc_task *snd_task) status = -EBADMSG; goto out_dequeue; } - if (task->tk_ops->rpc_call_prepare_transmit) { - task->tk_ops->rpc_call_prepare_transmit(task, - task->tk_calldata); - status = task->tk_status; - if (status < 0) - goto out_dequeue; - } if (RPC_SIGNALLED(task)) { status = -ERESTARTSYS; goto out_dequeue; diff --git a/net/tipc/addr.c b/net/tipc/addr.c index b88d48d00913..0f1eaed1bd1b 100644 --- a/net/tipc/addr.c +++ b/net/tipc/addr.c @@ -75,6 +75,7 @@ void tipc_set_node_addr(struct net *net, u32 addr) tipc_set_node_id(net, node_id); } tn->trial_addr = addr; + tn->addr_trial_end = jiffies; pr_info("32-bit node address hash set to %x\n", addr); } diff --git a/net/tipc/link.c b/net/tipc/link.c index 66d3a07bc571..c2c5c53cad22 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -106,8 +106,6 @@ struct tipc_stats { * @transmitq: queue for sent, non-acked messages * @backlogq: queue for messages waiting to be sent * @snt_nxt: next sequence number to use for outbound messages - * @prev_from: sequence number of most previous retransmission request - * @stale_limit: time when repeated identical retransmits must force link reset * @ackers: # of peers that needs to ack each packet before it can be released * @acked: # last packet acked by a certain peer. Used for broadcast. * @rcv_nxt: next sequence number to expect for inbound messages @@ -164,9 +162,7 @@ struct tipc_link { u16 limit; } backlog[5]; u16 snd_nxt; - u16 prev_from; u16 window; - unsigned long stale_limit; /* Reception */ u16 rcv_nxt; @@ -1044,47 +1040,53 @@ static void tipc_link_advance_backlog(struct tipc_link *l, * link_retransmit_failure() - Detect repeated retransmit failures * @l: tipc link sender * @r: tipc link receiver (= l in case of unicast) - * @from: seqno of the 1st packet in retransmit request * @rc: returned code * * Return: true if the repeated retransmit failures happens, otherwise * false */ static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r, - u16 from, int *rc) + int *rc) { struct sk_buff *skb = skb_peek(&l->transmq); struct tipc_msg *hdr; if (!skb) return false; - hdr = buf_msg(skb); - /* Detect repeated retransmit failures on same packet */ - if (r->prev_from != from) { - r->prev_from = from; - r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance); - } else if (time_after(jiffies, r->stale_limit)) { - pr_warn("Retransmission failure on link <%s>\n", l->name); - link_print(l, "State of link "); - pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", - msg_user(hdr), msg_type(hdr), msg_size(hdr), - msg_errcode(hdr)); - pr_info("sqno %u, prev: %x, src: %x\n", - msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr)); - - trace_tipc_list_dump(&l->transmq, true, "retrans failure!"); - trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!"); - trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!"); + if (!TIPC_SKB_CB(skb)->retr_cnt) + return false; - if (link_is_bc_sndlink(l)) - *rc = TIPC_LINK_DOWN_EVT; + if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp + + msecs_to_jiffies(r->tolerance))) + return false; + + hdr = buf_msg(skb); + if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr))) + return false; + pr_warn("Retransmission failure on link <%s>\n", l->name); + link_print(l, "State of link "); + pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", + msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr)); + pr_info("sqno %u, prev: %x, dest: %x\n", + msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr)); + pr_info("retr_stamp %d, retr_cnt %d\n", + jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp), + TIPC_SKB_CB(skb)->retr_cnt); + + trace_tipc_list_dump(&l->transmq, true, "retrans failure!"); + trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!"); + trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!"); + + if (link_is_bc_sndlink(l)) { + r->state = LINK_RESET; + *rc = TIPC_LINK_DOWN_EVT; + } else { *rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); - return true; } - return false; + return true; } /* tipc_link_bc_retrans() - retransmit zero or more packets @@ -1110,7 +1112,7 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r, trace_tipc_link_retrans(r, from, to, &l->transmq); - if (link_retransmit_failure(l, r, from, &rc)) + if (link_retransmit_failure(l, r, &rc)) return rc; skb_queue_walk(&l->transmq, skb) { @@ -1119,11 +1121,10 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r, continue; if (more(msg_seqno(hdr), to)) break; - if (link_is_bc_sndlink(l)) { - if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) - continue; - TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; - } + + if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) + continue; + TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM; _skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE, GFP_ATOMIC); if (!_skb) return 0; @@ -1133,6 +1134,10 @@ static int tipc_link_bc_retrans(struct tipc_link *l, struct tipc_link *r, _skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, _skb); l->stats.retransmitted++; + + /* Increase actual retrans counter & mark first time */ + if (!TIPC_SKB_CB(skb)->retr_cnt++) + TIPC_SKB_CB(skb)->retr_stamp = jiffies; } return 0; } @@ -1357,12 +1362,10 @@ static int tipc_link_advance_transmq(struct tipc_link *l, u16 acked, u16 gap, struct tipc_msg *hdr; u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1; u16 ack = l->rcv_nxt - 1; + bool passed = false; u16 seqno, n = 0; int rc = 0; - if (gap && link_retransmit_failure(l, l, acked + 1, &rc)) - return rc; - skb_queue_walk_safe(&l->transmq, skb, tmp) { seqno = buf_seqno(skb); @@ -1372,12 +1375,17 @@ next_gap_ack: __skb_unlink(skb, &l->transmq); kfree_skb(skb); } else if (less_eq(seqno, acked + gap)) { - /* retransmit skb */ + /* First, check if repeated retrans failures occurs? */ + if (!passed && link_retransmit_failure(l, l, &rc)) + return rc; + passed = true; + + /* retransmit skb if unrestricted*/ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr)) continue; TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME; - - _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC); + _skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE, + GFP_ATOMIC); if (!_skb) continue; hdr = buf_msg(_skb); @@ -1386,6 +1394,10 @@ next_gap_ack: _skb->priority = TC_PRIO_CONTROL; __skb_queue_tail(xmitq, _skb); l->stats.retransmitted++; + + /* Increase actual retrans counter & mark first time */ + if (!TIPC_SKB_CB(skb)->retr_cnt++) + TIPC_SKB_CB(skb)->retr_stamp = jiffies; } else { /* retry with Gap ACK blocks if any */ if (!ga || n >= ga->gack_cnt) @@ -2577,7 +2589,7 @@ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf) i += scnprintf(buf + i, sz - i, " %x", l->peer_caps); i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt); i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt); - i += scnprintf(buf + i, sz - i, " %u", l->prev_from); + i += scnprintf(buf + i, sz - i, " %u", 0); i += scnprintf(buf + i, sz - i, " %u", 0); i += scnprintf(buf + i, sz - i, " %u", l->acked); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index da509f0eb9ca..d7ebc9e955f6 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -102,13 +102,15 @@ struct plist; #define TIPC_MEDIA_INFO_OFFSET 5 struct tipc_skb_cb { - u32 bytes_read; - u32 orig_member; struct sk_buff *tail; unsigned long nxt_retr; - bool validated; + unsigned long retr_stamp; + u32 bytes_read; + u32 orig_member; u16 chain_imp; u16 ackers; + u16 retr_cnt; + bool validated; }; #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index d86030ef1232..e135d4e11231 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -55,6 +55,7 @@ struct tipc_nl_compat_msg { int rep_type; int rep_size; int req_type; + int req_size; struct net *net; struct sk_buff *rep; struct tlv_desc *req; @@ -257,7 +258,8 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, int err; struct sk_buff *arg; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; msg->rep = tipc_tlv_alloc(msg->rep_size); @@ -354,7 +356,8 @@ static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd, { int err; - if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type)) + if (msg->req_type && (!msg->req_size || + !TLV_CHECK_TYPE(msg->req, msg->req_type))) return -EINVAL; err = __tipc_nl_compat_doit(cmd, msg); @@ -1278,8 +1281,8 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) goto send; } - len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (!len || !TLV_OK(msg.req, len)) { + msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); + if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index dd8537f988c4..83ae41d7e554 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -485,9 +485,8 @@ static int tipc_sk_create(struct net *net, struct socket *sock, tsk_set_unreturnable(tsk, true); if (sock->type == SOCK_DGRAM) tsk_set_unreliable(tsk, true); - __skb_queue_head_init(&tsk->mc_method.deferredq); } - + __skb_queue_head_init(&tsk->mc_method.deferredq); trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " "); return 0; } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index f345662890a6..ca8ac96d22a9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -476,7 +476,7 @@ static void tipc_topsrv_accept(struct work_struct *work) } } -/* tipc_toprsv_listener_data_ready - interrupt callback with connection request +/* tipc_topsrv_listener_data_ready - interrupt callback with connection request * The queued job is launched into tipc_topsrv_accept() */ static void tipc_topsrv_listener_data_ready(struct sock *sk) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 7c0b2b778703..43922d86e510 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -373,9 +373,9 @@ static int tls_push_data(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); - int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); struct tls_record_info *record = ctx->open_record; + int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; @@ -390,6 +390,9 @@ static int tls_push_data(struct sock *sk, if (sk->sk_err) return -sk->sk_err; + flags |= MSG_SENDPAGE_DECRYPTED; + tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (tls_is_partially_sent_record(tls_ctx)) { rc = tls_push_partial_record(sk, tls_ctx, flags); @@ -576,7 +579,9 @@ void tls_device_write_space(struct sock *sk, struct tls_context *ctx) gfp_t sk_allocation = sk->sk_allocation; sk->sk_allocation = GFP_ATOMIC; - tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL); + tls_push_partial_record(sk, ctx, + MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_SENDPAGE_DECRYPTED); sk->sk_allocation = sk_allocation; } } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 4674e57e66b0..43252a801c3f 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -261,24 +261,9 @@ void tls_ctx_free(struct tls_context *ctx) kfree(ctx); } -static void tls_sk_proto_close(struct sock *sk, long timeout) +static void tls_sk_proto_cleanup(struct sock *sk, + struct tls_context *ctx, long timeo) { - struct tls_context *ctx = tls_get_ctx(sk); - long timeo = sock_sndtimeo(sk, 0); - void (*sk_proto_close)(struct sock *sk, long timeout); - bool free_ctx = false; - - lock_sock(sk); - sk_proto_close = ctx->sk_proto_close; - - if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) - goto skip_tx_cleanup; - - if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) { - free_ctx = true; - goto skip_tx_cleanup; - } - if (unlikely(sk->sk_write_pending) && !wait_on_pending_writer(sk, &timeo)) tls_handle_open_record(sk, 0); @@ -287,7 +272,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) if (ctx->tx_conf == TLS_SW) { kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); - tls_sw_free_resources_tx(sk); + tls_sw_release_resources_tx(sk); #ifdef CONFIG_TLS_DEVICE } else if (ctx->tx_conf == TLS_HW) { tls_device_free_resources_tx(sk); @@ -295,26 +280,46 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) } if (ctx->rx_conf == TLS_SW) - tls_sw_free_resources_rx(sk); + tls_sw_release_resources_rx(sk); #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) tls_device_offload_cleanup_rx(sk); - - if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) { -#else - { #endif - tls_ctx_free(ctx); - ctx = NULL; - } +} -skip_tx_cleanup: +static void tls_sk_proto_close(struct sock *sk, long timeout) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tls_context *ctx = tls_get_ctx(sk); + long timeo = sock_sndtimeo(sk, 0); + bool free_ctx; + + if (ctx->tx_conf == TLS_SW) + tls_sw_cancel_work_tx(ctx); + + lock_sock(sk); + free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW; + + if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE) + tls_sk_proto_cleanup(sk, ctx, timeo); + + write_lock_bh(&sk->sk_callback_lock); + if (free_ctx) + icsk->icsk_ulp_data = NULL; + sk->sk_prot = ctx->sk_proto; + if (sk->sk_write_space == tls_write_space) + sk->sk_write_space = ctx->sk_write_space; + write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); - sk_proto_close(sk, timeout); - /* free ctx for TLS_HW_RECORD, used by tcp_set_state - * for sk->sk_prot->unhash [tls_hw_unhash] - */ + if (ctx->tx_conf == TLS_SW) + tls_sw_free_ctx_tx(ctx); + if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) + tls_sw_strparser_done(ctx); + if (ctx->rx_conf == TLS_SW) + tls_sw_free_ctx_rx(ctx); + ctx->sk_proto_close(sk, timeout); + if (free_ctx) tls_ctx_free(ctx); } @@ -526,6 +531,8 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 1); + if (rc) + goto err_crypto_info; conf = TLS_SW; } } else { @@ -537,13 +544,13 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { #endif rc = tls_set_sw_offload(sk, ctx, 0); + if (rc) + goto err_crypto_info; conf = TLS_SW; } + tls_sw_strparser_arm(sk, ctx); } - if (rc) - goto err_crypto_info; - if (tx) ctx->tx_conf = conf; else @@ -607,6 +614,7 @@ static struct tls_context *create_ctx(struct sock *sk) ctx->setsockopt = sk->sk_prot->setsockopt; ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + ctx->unhash = sk->sk_prot->unhash; return ctx; } @@ -764,7 +772,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash; prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash; - prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close; } static int tls_init(struct sock *sk) @@ -773,7 +780,7 @@ static int tls_init(struct sock *sk) int rc = 0; if (tls_hw_prot(sk)) - goto out; + return 0; /* The TLS ulp is currently supported only for TCP sockets * in ESTABLISHED state. @@ -784,21 +791,38 @@ static int tls_init(struct sock *sk) if (sk->sk_state != TCP_ESTABLISHED) return -ENOTSUPP; + tls_build_proto(sk); + /* allocate tls context */ + write_lock_bh(&sk->sk_callback_lock); ctx = create_ctx(sk); if (!ctx) { rc = -ENOMEM; goto out; } - tls_build_proto(sk); ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; + ctx->sk_proto = sk->sk_prot; update_sk_prot(sk, ctx); out: + write_unlock_bh(&sk->sk_callback_lock); return rc; } +static void tls_update(struct sock *sk, struct proto *p) +{ + struct tls_context *ctx; + + ctx = tls_get_ctx(sk); + if (likely(ctx)) { + ctx->sk_proto_close = p->close; + ctx->sk_proto = p; + } else { + sk->sk_prot = p; + } +} + void tls_register_device(struct tls_device *device) { spin_lock_bh(&device_spinlock); @@ -819,6 +843,7 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .name = "tls", .owner = THIS_MODULE, .init = tls_init, + .update = tls_update, }; static int __init tls_register(void) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 53b4ad94e74a..91d21b048a9b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2054,7 +2054,16 @@ static void tls_data_ready(struct sock *sk) } } -void tls_sw_free_resources_tx(struct sock *sk) +void tls_sw_cancel_work_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + + set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask); + set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask); + cancel_delayed_work_sync(&ctx->tx_work.work); +} + +void tls_sw_release_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); @@ -2065,11 +2074,6 @@ void tls_sw_free_resources_tx(struct sock *sk) if (atomic_read(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); - release_sock(sk); - cancel_delayed_work_sync(&ctx->tx_work.work); - lock_sock(sk); - - /* Tx whatever records we can transmit and abandon the rest */ tls_tx_records(sk, -1); /* Free up un-sent records in tx_list. First, free @@ -2092,6 +2096,11 @@ void tls_sw_free_resources_tx(struct sock *sk) crypto_free_aead(ctx->aead_send); tls_free_open_rec(sk); +} + +void tls_sw_free_ctx_tx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); kfree(ctx); } @@ -2110,25 +2119,40 @@ void tls_sw_release_resources_rx(struct sock *sk) skb_queue_purge(&ctx->rx_list); crypto_free_aead(ctx->aead_recv); strp_stop(&ctx->strp); - write_lock_bh(&sk->sk_callback_lock); - sk->sk_data_ready = ctx->saved_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - release_sock(sk); - strp_done(&ctx->strp); - lock_sock(sk); + /* If tls_sw_strparser_arm() was not called (cleanup paths) + * we still want to strp_stop(), but sk->sk_data_ready was + * never swapped. + */ + if (ctx->saved_data_ready) { + write_lock_bh(&sk->sk_callback_lock); + sk->sk_data_ready = ctx->saved_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + } } } -void tls_sw_free_resources_rx(struct sock *sk) +void tls_sw_strparser_done(struct tls_context *tls_ctx) { - struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - tls_sw_release_resources_rx(sk); + strp_done(&ctx->strp); +} + +void tls_sw_free_ctx_rx(struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); kfree(ctx); } +void tls_sw_free_resources_rx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_sw_release_resources_rx(sk); + tls_sw_free_ctx_rx(tls_ctx); +} + /* The work handler to transmitt the encrypted records in tx_list */ static void tx_work_handler(struct work_struct *work) { @@ -2137,11 +2161,17 @@ static void tx_work_handler(struct work_struct *work) struct tx_work, work); struct sock *sk = tx_work->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_sw_context_tx *ctx; - if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + if (unlikely(!tls_ctx)) return; + ctx = tls_sw_ctx_tx(tls_ctx); + if (test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask)) + return; + + if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) + return; lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); @@ -2160,6 +2190,18 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) } } +void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) +{ + struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx); + + write_lock_bh(&sk->sk_callback_lock); + rx_ctx->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = tls_data_ready; + write_unlock_bh(&sk->sk_callback_lock); + + strp_check_rcv(&rx_ctx->strp); +} + int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -2357,13 +2399,6 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) cb.parse_msg = tls_read_size; strp_init(&sw_ctx_rx->strp, sk, &cb); - - write_lock_bh(&sk->sk_callback_lock); - sw_ctx_rx->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = tls_data_ready; - write_unlock_bh(&sk->sk_callback_lock); - - strp_check_rcv(&sw_ctx_rx->strp); } goto out; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index f2084e3f7aa4..9d864ebeb7b3 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -312,6 +312,11 @@ static void hvs_close_connection(struct vmbus_channel *chan) lock_sock(sk); hvs_do_close_lock_held(vsock_sk(sk), true); release_sock(sk); + + /* Release the refcnt for the channel that's opened in + * hvs_open_connection(). + */ + sock_put(sk); } static void hvs_open_connection(struct vmbus_channel *chan) @@ -407,6 +412,9 @@ static void hvs_open_connection(struct vmbus_channel *chan) } set_per_channel_state(chan, conn_from_host ? new : sk); + + /* This reference will be dropped by hvs_close_connection(). */ + sock_hold(conn_from_host ? new : sk); vmbus_set_chn_rescind_callback(chan, hvs_close_connection); /* Set the pending send size to max packet size to always get diff --git a/net/wireless/core.c b/net/wireless/core.c index 45d9afcff6d5..32b3c719fdfc 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1410,10 +1410,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, } break; case NETDEV_PRE_UP: - if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)) && - !(wdev->iftype == NL80211_IFTYPE_AP_VLAN && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP && - wdev->use_4addr)) + if (!cfg80211_iftype_allowed(wdev->wiphy, wdev->iftype, + wdev->use_4addr, 0)) return notifier_from_errno(-EOPNOTSUPP); if (rfkill_blocked(rdev->rfkill)) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fc83dd179c1a..fd05ae1437a9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3484,9 +3484,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) return err; } - if (!(rdev->wiphy.interface_modes & (1 << type)) && - !(type == NL80211_IFTYPE_AP_VLAN && params.use_4addr && - rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP)) + if (!cfg80211_iftype_allowed(&rdev->wiphy, type, params.use_4addr, 0)) return -EOPNOTSUPP; err = nl80211_parse_mon_options(rdev, type, info, ¶ms); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 4831ad745f91..327479ce69f5 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2788,7 +2788,7 @@ static void reg_process_pending_hints(void) /* When last_request->processed becomes true this will be rescheduled */ if (lr && !lr->processed) { - reg_process_hint(lr); + pr_debug("Pending regulatory request, waiting for it to be processed...\n"); return; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 1c39d6a2e850..e74837824cea 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -233,25 +233,30 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, switch (params->cipher) { case WLAN_CIPHER_SUITE_TKIP: + /* Extended Key ID can only be used with CCMP/GCMP ciphers */ + if ((pairwise && key_idx) || + params->mode != NL80211_KEY_RX_TX) + return -EINVAL; + break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: - /* IEEE802.11-2016 allows only 0 and - when using Extended Key - * ID - 1 as index for pairwise keys. + /* IEEE802.11-2016 allows only 0 and - when supporting + * Extended Key ID - 1 as index for pairwise keys. * @NL80211_KEY_NO_TX is only allowed for pairwise keys when * the driver supports Extended Key ID. * @NL80211_KEY_SET_TX can't be set when installing and * validating a key. */ - if (params->mode == NL80211_KEY_NO_TX) { - if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_EXT_KEY_ID)) - return -EINVAL; - else if (!pairwise || key_idx < 0 || key_idx > 1) + if ((params->mode == NL80211_KEY_NO_TX && !pairwise) || + params->mode == NL80211_KEY_SET_TX) + return -EINVAL; + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_EXT_KEY_ID)) { + if (pairwise && (key_idx < 0 || key_idx > 1)) return -EINVAL; - } else if ((pairwise && key_idx) || - params->mode == NL80211_KEY_SET_TX) { + } else if (pairwise && key_idx) { return -EINVAL; } break; @@ -1697,7 +1702,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += params->iftype_num[iftype]; if (params->iftype_num[iftype] > 0 && - !(wiphy->software_iftypes & BIT(iftype))) + !cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) used_iftypes |= BIT(iftype); } @@ -1719,7 +1724,7 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, return -ENOMEM; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { - if (wiphy->software_iftypes & BIT(iftype)) + if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) continue; for (j = 0; j < c->n_limits; j++) { all_iftypes |= limits[j].types; @@ -2072,3 +2077,26 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, return max_vht_nss; } EXPORT_SYMBOL(ieee80211_get_vht_max_nss); + +bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, + bool is_4addr, u8 check_swif) + +{ + bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN; + + switch (check_swif) { + case 0: + if (is_vlan && is_4addr) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->interface_modes & BIT(iftype); + case 1: + if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan) + return wiphy->flags & WIPHY_FLAG_4ADDR_AP; + return wiphy->software_iftypes & BIT(iftype); + default: + break; + } + + return false; +} +EXPORT_SYMBOL(cfg80211_iftype_allowed); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 83de74ca729a..688aac7a6943 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -365,7 +365,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL); if (!umem->pages) { err = -ENOMEM; - goto out_account; + goto out_pin; } for (i = 0; i < umem->npgs; i++) @@ -373,6 +373,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return 0; +out_pin: + xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); return err; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8ca637a72697..ec94f5795ea4 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3269,7 +3269,7 @@ decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse) struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; - if (skb_dst(skb)) + if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); @@ -3387,7 +3387,7 @@ decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse) nexthdr = nh[nhoff]; - if (skb_dst(skb)) + if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); |