diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-13 16:27:13 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-13 16:27:13 -0700 |
commit | 96144c58abe7ff767e754b5b80995f7b8846d49b (patch) | |
tree | 7fcc47090ced9be71fa35cbf5e00d0160b04a2d1 /net | |
parent | f82e7b57b5fc48199e2f26ffafe2f96f7338ad3d (diff) | |
parent | bc139119a1708ae3db1ebb379630f286e28d06e8 (diff) | |
download | linux-stable-96144c58abe7ff767e754b5b80995f7b8846d49b.tar.gz linux-stable-96144c58abe7ff767e754b5b80995f7b8846d49b.tar.bz2 linux-stable-96144c58abe7ff767e754b5b80995f7b8846d49b.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller:
1) Fix cfg80211 deadlock, from Johannes Berg.
2) RXRPC fails to send norigications, from David Howells.
3) MPTCP RM_ADDR parsing has an off by one pointer error, fix from
Geliang Tang.
4) Fix crash when using MSG_PEEK with sockmap, from Anny Hu.
5) The ucc_geth driver needs __netdev_watchdog_up exported, from
Valentin Longchamp.
6) Fix hashtable memory leak in dccp, from Wang Hai.
7) Fix how nexthops are marked as FDB nexthops, from David Ahern.
8) Fix mptcp races between shutdown and recvmsg, from Paolo Abeni.
9) Fix crashes in tipc_disc_rcv(), from Tuong Lien.
10) Fix link speed reporting in iavf driver, from Brett Creeley.
11) When a channel is used for XSK and then reused again later for XSK,
we forget to clear out the relevant data structures in mlx5 which
causes all kinds of problems. Fix from Maxim Mikityanskiy.
12) Fix memory leak in genetlink, from Cong Wang.
13) Disallow sockmap attachments to UDP sockets, it simply won't work.
From Lorenz Bauer.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (83 commits)
net: ethernet: ti: ale: fix allmulti for nu type ale
net: ethernet: ti: am65-cpsw-nuss: fix ale parameters init
net: atm: Remove the error message according to the atomic context
bpf: Undo internal BPF_PROBE_MEM in BPF insns dump
libbpf: Support pre-initializing .bss global variables
tools/bpftool: Fix skeleton codegen
bpf: Fix memlock accounting for sock_hash
bpf: sockmap: Don't attach programs to UDP sockets
bpf: tcp: Recv() should return 0 when the peer socket is closed
ibmvnic: Flush existing work items before device removal
genetlink: clean up family attributes allocations
net: ipa: header pad field only valid for AP->modem endpoint
net: ipa: program upper nibbles of sequencer type
net: ipa: fix modem LAN RX endpoint id
net: ipa: program metadata mask differently
ionic: add pcie_print_link_status
rxrpc: Fix race between incoming ACK parser and retransmitter
net/mlx5: E-Switch, Fix some error pointer dereferences
net/mlx5: Don't fail driver on failure to create debugfs
net/mlx5e: CT: Fix ipv6 nat header rewrite actions
...
Diffstat (limited to 'net')
38 files changed, 409 insertions, 266 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index f00bb57f0f60..c8d6a07e23c5 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -494,6 +494,7 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) * separate class since they always nest. */ static struct lock_class_key vlan_netdev_xmit_lock_key; +static struct lock_class_key vlan_netdev_addr_lock_key; static void vlan_dev_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -502,8 +503,11 @@ static void vlan_dev_set_lockdep_one(struct net_device *dev, lockdep_set_class(&txq->_xmit_lock, &vlan_netdev_xmit_lock_key); } -static void vlan_dev_set_lockdep_class(struct net_device *dev) +static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) { + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &vlan_netdev_addr_lock_key, + subclass); netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL); } @@ -597,7 +601,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - vlan_dev_set_lockdep_class(dev); + vlan_dev_set_lockdep_class(dev, dev->lower_level); vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) diff --git a/net/atm/lec.c b/net/atm/lec.c index ca37f5a71f5e..875fc0bc1780 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1536,10 +1536,8 @@ static struct lec_arp_table *make_entry(struct lec_priv *priv, struct lec_arp_table *to_return; to_return = kzalloc(sizeof(struct lec_arp_table), GFP_ATOMIC); - if (!to_return) { - pr_info("LEC: Arp entry kmalloc failed\n"); + if (!to_return) return NULL; - } ether_addr_copy(to_return->mac_addr, mac_addr); INIT_HLIST_NODE(&to_return->next); timer_setup(&to_return->timer, lec_arp_expire_arp, 0); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0ddd80130ea3..f1f1c86f3419 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -745,6 +745,7 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto, * separate class since they always nest. */ static struct lock_class_key batadv_netdev_xmit_lock_key; +static struct lock_class_key batadv_netdev_addr_lock_key; /** * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue @@ -765,6 +766,7 @@ static void batadv_set_lockdep_class_one(struct net_device *dev, */ static void batadv_set_lockdep_class(struct net_device *dev) { + lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL); } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 8ec1362588af..8c7b78f8bc23 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -105,6 +105,13 @@ out: return NETDEV_TX_OK; } +static struct lock_class_key bridge_netdev_addr_lock_key; + +static void br_set_lockdep_class(struct net_device *dev) +{ + lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); +} + static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -143,6 +150,7 @@ static int br_dev_init(struct net_device *dev) br_fdb_hash_fini(br); } + br_set_lockdep_class(dev); return err; } diff --git a/net/core/dev.c b/net/core/dev.c index 061496a1f640..6bc2388141f6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -439,6 +439,7 @@ static const char *const netdev_lock_name[] = { "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; +static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { @@ -460,11 +461,25 @@ static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } + +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ + int i; + + i = netdev_lock_pos(dev->type); + lockdep_set_class_and_name(&dev->addr_list_lock, + &netdev_addr_lock_key[i], + netdev_lock_name[i]); +} #else static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { } + +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ +} #endif /******************************************************************************* @@ -9373,15 +9388,6 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); -void netdev_update_lockdep_key(struct net_device *dev) -{ - lockdep_unregister_key(&dev->addr_list_lock_key); - lockdep_register_key(&dev->addr_list_lock_key); - - lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); -} -EXPORT_SYMBOL(netdev_update_lockdep_key); - /** * register_netdevice - register a network device * @dev: device to register @@ -9420,7 +9426,7 @@ int register_netdevice(struct net_device *dev) return ret; spin_lock_init(&dev->addr_list_lock); - lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); + netdev_set_addr_lockdep_class(dev); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) @@ -9939,8 +9945,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); - lockdep_register_key(&dev->addr_list_lock_key); - dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; dev->upper_level = 1; @@ -10028,8 +10032,6 @@ void free_netdev(struct net_device *dev) free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; - lockdep_unregister_key(&dev->addr_list_lock_key); - /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 2f949b5a1eb9..6393ba930097 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock(to); + netif_addr_lock_nested(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock(to); + netif_addr_lock_nested(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock(to); + netif_addr_lock_nested(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock(to); + netif_addr_lock_nested(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock(to); + netif_addr_lock_nested(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock(to); + netif_addr_lock_nested(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/core/filter.c b/net/core/filter.c index 209482a4eaa2..73395384afe2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1755,25 +1755,27 @@ BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); - u8 *net = skb_network_header(skb); - u8 *mac = skb_mac_header(skb); - u8 *ptr; + u8 *start, *ptr; - if (unlikely(offset > 0xffff || len > (end - mac))) + if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: - ptr = mac + offset; + if (unlikely(!skb_mac_header_was_set(skb))) + goto err_clear; + start = skb_mac_header(skb); break; case BPF_HDR_START_NET: - ptr = net + offset; + start = skb_network_header(skb); break; default: goto err_clear; } - if (likely(ptr >= mac && ptr + len <= end)) { + ptr = start + offset; + + if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } @@ -4340,8 +4342,6 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, } break; case SO_BINDTODEVICE: - ret = -ENOPROTOOPT; -#ifdef CONFIG_NETDEVICES optlen = min_t(long, optlen, IFNAMSIZ - 1); strncpy(devname, optval, optlen); devname[optlen] = 0; @@ -4360,7 +4360,6 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, dev_put(dev); } ret = sock_bindtoindex(sk, ifindex, false); -#endif break; default: ret = -EINVAL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2269199c5891..9aedc15736ad 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2462,7 +2462,6 @@ static int do_set_master(struct net_device *dev, int ifindex, err = ops->ndo_del_slave(upper_dev, dev); if (err) return err; - netdev_update_lockdep_key(dev); } else { return -EOPNOTSUPP; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 00a26cf2cfe9..4059f94e9bb5 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -424,10 +424,7 @@ static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next) return 0; } -static bool sock_map_redirect_allowed(const struct sock *sk) -{ - return sk->sk_state != TCP_LISTEN; -} +static bool sock_map_redirect_allowed(const struct sock *sk); static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) @@ -508,6 +505,11 @@ static bool sk_is_udp(const struct sock *sk) sk->sk_protocol == IPPROTO_UDP; } +static bool sock_map_redirect_allowed(const struct sock *sk) +{ + return sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN; +} + static bool sock_map_sk_is_suitable(const struct sock *sk) { return sk_is_tcp(sk) || sk_is_udp(sk); @@ -989,11 +991,15 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) err = -EINVAL; goto free_htab; } + err = bpf_map_charge_init(&htab->map.memory, cost); + if (err) + goto free_htab; htab->buckets = bpf_map_area_alloc(htab->buckets_num * sizeof(struct bpf_htab_bucket), htab->map.numa_node); if (!htab->buckets) { + bpf_map_charge_finish(&htab->map.memory); err = -ENOMEM; goto free_htab; } @@ -1013,6 +1019,7 @@ static void sock_hash_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct bpf_htab_bucket *bucket; + struct hlist_head unlink_list; struct bpf_htab_elem *elem; struct hlist_node *node; int i; @@ -1024,13 +1031,32 @@ static void sock_hash_free(struct bpf_map *map) synchronize_rcu(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); - hlist_for_each_entry_safe(elem, node, &bucket->head, node) { - hlist_del_rcu(&elem->node); + + /* We are racing with sock_hash_delete_from_link to + * enter the spin-lock critical section. Every socket on + * the list is still linked to sockhash. Since link + * exists, psock exists and holds a ref to socket. That + * lets us to grab a socket ref too. + */ + raw_spin_lock_bh(&bucket->lock); + hlist_for_each_entry(elem, &bucket->head, node) + sock_hold(elem->sk); + hlist_move_list(&bucket->head, &unlink_list); + raw_spin_unlock_bh(&bucket->lock); + + /* Process removed entries out of atomic context to + * block for socket lock before deleting the psock's + * link to sockhash. + */ + hlist_for_each_entry_safe(elem, node, &unlink_list, node) { + hlist_del(&elem->node); lock_sock(elem->sk); rcu_read_lock(); sock_map_unref(elem->sk, elem); rcu_read_unlock(); release_sock(elem->sk); + sock_put(elem->sk); + sock_hash_free_elem(htab, elem); } } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 4af8a98fe784..c13b6609474b 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1139,14 +1139,14 @@ static int __init dccp_init(void) inet_hashinfo_init(&dccp_hashinfo); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) - goto out_fail; + goto out_free_percpu; rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN, NULL); if (!dccp_hashinfo.bind_bucket_cachep) - goto out_free_percpu; + goto out_free_hashinfo2; /* * Size and allocate the main established and bind bucket @@ -1242,6 +1242,8 @@ out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); +out_free_hashinfo2: + inet_hashinfo2_free_mod(&dccp_hashinfo); out_free_percpu: percpu_counter_destroy(&dccp_orphan_count); out_fail: @@ -1265,6 +1267,7 @@ static void __exit dccp_fini(void) kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); + inet_hashinfo2_free_mod(&dccp_hashinfo); percpu_counter_destroy(&dccp_orphan_count); } diff --git a/net/dsa/master.c b/net/dsa/master.c index a621367c6e8c..480a61460c23 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -327,6 +327,8 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } +static struct lock_class_key dsa_master_addr_list_lock_key; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -345,6 +347,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; + lockdep_set_class(&dev->addr_list_lock, + &dsa_master_addr_list_lock_key); ret = dsa_master_ethtool_setup(dev); if (ret) return ret; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 400a9f89ebdb..cc8049b100b2 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -247,12 +247,11 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; - if (nh->is_fdb_nh && nla_put_flag(skb, NHA_FDB)) - goto nla_put_failure; - if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) + goto nla_put_failure; if (nla_put_nh_group(skb, nhg)) goto nla_put_failure; goto out; @@ -264,7 +263,10 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nla_put_flag(skb, NHA_BLACKHOLE)) goto nla_put_failure; goto out; - } else if (!nh->is_fdb_nh) { + } else if (nhi->fdb_nh) { + if (nla_put_flag(skb, NHA_FDB)) + goto nla_put_failure; + } else { const struct net_device *dev; dev = nhi->fib_nhc.nhc_dev; @@ -385,7 +387,7 @@ errout: } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, - struct netlink_ext_ack *extack) + bool *is_fdb, struct netlink_ext_ack *extack) { if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); @@ -398,6 +400,7 @@ static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, "Multipath group can not be a nexthop within a group"); return false; } + *is_fdb = nhg->fdb_nh; } else { struct nh_info *nhi = rtnl_dereference(nh->nh_info); @@ -406,6 +409,7 @@ static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, "Blackhole nexthop can not be used in a group with more than 1 path"); return false; } + *is_fdb = nhi->fdb_nh; } return true; @@ -416,12 +420,13 @@ static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, { struct nh_info *nhi; - if (!nh->is_fdb_nh) { + nhi = rtnl_dereference(nh->nh_info); + + if (!nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "FDB nexthop group can only have fdb nexthops"); return -EINVAL; } - nhi = rtnl_dereference(nh->nh_info); if (*nh_family == AF_UNSPEC) { *nh_family = nhi->family; } else if (*nh_family != nhi->family) { @@ -473,19 +478,20 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { struct nexthop *nh; + bool is_fdb_nh; nh = nexthop_find_by_id(net, nhg[i].id); if (!nh) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } - if (!valid_group_nh(nh, len, extack)) + if (!valid_group_nh(nh, len, &is_fdb_nh, extack)) return -EINVAL; if (nhg_fdb && nh_check_attr_fdb_group(nh, &nh_family, extack)) return -EINVAL; - if (!nhg_fdb && nh->is_fdb_nh) { + if (!nhg_fdb && is_fdb_nh) { NL_SET_ERR_MSG(extack, "Non FDB nexthop group cannot have fdb nexthops"); return -EINVAL; } @@ -553,13 +559,13 @@ struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) if (hash > atomic_read(&nhge->upper_bound)) continue; - if (nhge->nh->is_fdb_nh) + nhi = rcu_dereference(nhge->nh->nh_info); + if (nhi->fdb_nh) return nhge->nh; /* nexthops always check if it is good and does * not rely on a sysctl for this behavior */ - nhi = rcu_dereference(nhge->nh->nh_info); switch (nhi->family) { case AF_INET: if (ipv4_good_nh(&nhi->fib_nh)) @@ -624,11 +630,7 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; - - if (nh->is_fdb_nh) { - NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); - return -EINVAL; - } + bool is_fdb_nh; /* fib6_src is unique to a fib6_info and limits the ability to cache * routes in fib6_nh within a nexthop that is potentially shared @@ -645,10 +647,17 @@ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, nhg = rtnl_dereference(nh->nh_grp); if (nhg->has_v4) goto no_v4_nh; + is_fdb_nh = nhg->fdb_nh; } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->family == AF_INET) goto no_v4_nh; + is_fdb_nh = nhi->fdb_nh; + } + + if (is_fdb_nh) { + NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); + return -EINVAL; } return 0; @@ -677,12 +686,9 @@ static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new, return fib6_check_nexthop(new, NULL, extack); } -static int nexthop_check_scope(struct nexthop *nh, u8 scope, +static int nexthop_check_scope(struct nh_info *nhi, u8 scope, struct netlink_ext_ack *extack) { - struct nh_info *nhi; - - nhi = rtnl_dereference(nh->nh_info); if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) { NL_SET_ERR_MSG(extack, "Route with host scope can not have a gateway"); @@ -704,29 +710,38 @@ static int nexthop_check_scope(struct nexthop *nh, u8 scope, int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack) { + struct nh_info *nhi; int err = 0; - if (nh->is_fdb_nh) { - NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); - err = -EINVAL; - goto out; - } - if (nh->is_group) { struct nh_group *nhg; + nhg = rtnl_dereference(nh->nh_grp); + if (nhg->fdb_nh) { + NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); + err = -EINVAL; + goto out; + } + if (scope == RT_SCOPE_HOST) { NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops"); err = -EINVAL; goto out; } - nhg = rtnl_dereference(nh->nh_grp); /* all nexthops in a group have the same scope */ - err = nexthop_check_scope(nhg->nh_entries[0].nh, scope, extack); + nhi = rtnl_dereference(nhg->nh_entries[0].nh->nh_info); + err = nexthop_check_scope(nhi, scope, extack); } else { - err = nexthop_check_scope(nh, scope, extack); + nhi = rtnl_dereference(nh->nh_info); + if (nhi->fdb_nh) { + NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); + err = -EINVAL; + goto out; + } + err = nexthop_check_scope(nhi, scope, extack); } + out: return err; } @@ -787,6 +802,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, newg->has_v4 = nhg->has_v4; newg->mpath = nhg->mpath; + newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; /* copy old entries to new except the one getting removed */ @@ -1216,7 +1232,7 @@ static struct nexthop *nexthop_create_group(struct net *net, } if (cfg->nh_fdb) - nh->is_fdb_nh = 1; + nhg->fdb_nh = 1; rcu_assign_pointer(nh->nh_grp, nhg); @@ -1255,7 +1271,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, goto out; } - if (nh->is_fdb_nh) + if (nhi->fdb_nh) goto out; /* sets nh_dev if successful */ @@ -1326,7 +1342,7 @@ static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; if (cfg->nh_fdb) - nh->is_fdb_nh = 1; + nhi->fdb_nh = 1; if (cfg->nh_blackhole) { nhi->reject_nh = 1; @@ -1349,7 +1365,7 @@ static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, } /* add the entry to the device based hash */ - if (!nh->is_fdb_nh) + if (!nhi->fdb_nh) nexthop_devhash_add(net, nhi); rcu_assign_pointer(nh->nh_info, nhi); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 27716e4932bc..810cc164f795 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1742,14 +1742,48 @@ int tcp_mmap(struct file *file, struct socket *sock, } EXPORT_SYMBOL(tcp_mmap); +static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, + struct page **pages, + unsigned long pages_to_map, + unsigned long *insert_addr, + u32 *length_with_pending, + u32 *seq, + struct tcp_zerocopy_receive *zc) +{ + unsigned long pages_remaining = pages_to_map; + int bytes_mapped; + int ret; + + ret = vm_insert_pages(vma, *insert_addr, pages, &pages_remaining); + bytes_mapped = PAGE_SIZE * (pages_to_map - pages_remaining); + /* Even if vm_insert_pages fails, it may have partially succeeded in + * mapping (some but not all of the pages). + */ + *seq += bytes_mapped; + *insert_addr += bytes_mapped; + if (ret) { + /* But if vm_insert_pages did fail, we have to unroll some state + * we speculatively touched before. + */ + const int bytes_not_mapped = PAGE_SIZE * pages_remaining; + *length_with_pending -= bytes_not_mapped; + zc->recv_skip_hint += bytes_not_mapped; + } + return ret; +} + static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc) { unsigned long address = (unsigned long)zc->address; u32 length = 0, seq, offset, zap_len; + #define PAGE_BATCH_SIZE 8 + struct page *pages[PAGE_BATCH_SIZE]; const skb_frag_t *frags = NULL; struct vm_area_struct *vma; struct sk_buff *skb = NULL; + unsigned long pg_idx = 0; + unsigned long curr_addr; struct tcp_sock *tp; int inq; int ret; @@ -1762,6 +1796,8 @@ static int tcp_zerocopy_receive(struct sock *sk, sock_rps_record_flow(sk); + tp = tcp_sk(sk); + mmap_read_lock(current->mm); vma = find_vma(current->mm, address); @@ -1771,7 +1807,6 @@ static int tcp_zerocopy_receive(struct sock *sk, } zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); - tp = tcp_sk(sk); seq = tp->copied_seq; inq = tcp_inq(sk); zc->length = min_t(u32, zc->length, inq); @@ -1783,8 +1818,20 @@ static int tcp_zerocopy_receive(struct sock *sk, zc->recv_skip_hint = zc->length; } ret = 0; + curr_addr = address; while (length + PAGE_SIZE <= zc->length) { if (zc->recv_skip_hint < PAGE_SIZE) { + /* If we're here, finish the current batch. */ + if (pg_idx) { + ret = tcp_zerocopy_vm_insert_batch(vma, pages, + pg_idx, + &curr_addr, + &length, + &seq, zc); + if (ret) + goto out; + pg_idx = 0; + } if (skb) { if (zc->recv_skip_hint > 0) break; @@ -1793,7 +1840,6 @@ static int tcp_zerocopy_receive(struct sock *sk, } else { skb = tcp_recv_skb(sk, seq, &offset); } - zc->recv_skip_hint = skb->len - offset; offset -= skb_headlen(skb); if ((int)offset < 0 || skb_has_frag_list(skb)) @@ -1817,14 +1863,24 @@ static int tcp_zerocopy_receive(struct sock *sk, zc->recv_skip_hint -= remaining; break; } - ret = vm_insert_page(vma, address + length, - skb_frag_page(frags)); - if (ret) - break; + pages[pg_idx] = skb_frag_page(frags); + pg_idx++; length += PAGE_SIZE; - seq += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; + if (pg_idx == PAGE_BATCH_SIZE) { + ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx, + &curr_addr, &length, + &seq, zc); + if (ret) + goto out; + pg_idx = 0; + } + } + if (pg_idx) { + ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx, + &curr_addr, &length, &seq, + zc); } out: mmap_read_unlock(current->mm); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 629aaa9a1eb9..7aa68f4aae6c 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -64,6 +64,9 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, } while (i != msg_rx->sg.end); if (unlikely(peek)) { + if (msg_rx == list_last_entry(&psock->ingress_msg, + struct sk_msg, list)) + break; msg_rx = list_next_entry(msg_rx, list); continue; } @@ -242,6 +245,9 @@ static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock, DEFINE_WAIT_FUNC(wait, woken_wake_function); int ret = 0; + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + if (!timeo) return ret; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 5820ef02a587..b2a9d47cf86d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -167,6 +167,8 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT | IEEE80211_STA_DISABLE_HE; + else + ret = 0; vht_chandef = *chandef; goto out; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 21854a61a2b7..a88ab6fb16f2 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4694,7 +4694,7 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, * rate_idx is MCS index, which can be [0-76] * as documented on: * - * http://wireless.kernel.org/en/developers/Documentation/ieee80211/802.11n + * https://wireless.wiki.kernel.org/en/developers/Documentation/ieee80211/802.11n * * Anything else would be some sort of driver or * hardware error. The driver should catch hardware diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 01f1f4cf4902..490b92534afc 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -273,6 +273,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, if (opsize != TCPOLEN_MPTCP_RM_ADDR_BASE) break; + ptr++; + mp_opt->rm_addr = 1; mp_opt->rm_id = *ptr++; pr_debug("RM_ADDR: id=%d", mp_opt->rm_id); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 14b253d10ccf..3980fbb6f31e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -374,6 +374,27 @@ void mptcp_subflow_eof(struct sock *sk) sock_hold(sk); } +static void mptcp_check_for_eof(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + int receivers = 0; + + mptcp_for_each_subflow(msk, subflow) + receivers += !subflow->rx_eof; + + if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) { + /* hopefully temporary hack: propagate shutdown status + * to msk, when all subflows agree on it + */ + sk->sk_shutdown |= RCV_SHUTDOWN; + + smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ + set_bit(MPTCP_DATA_READY, &msk->flags); + sk->sk_data_ready(sk); + } +} + static void mptcp_stop_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -1011,6 +1032,9 @@ fallback: break; } + if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags)) + mptcp_check_for_eof(msk); + if (sk->sk_shutdown & RCV_SHUTDOWN) break; @@ -1148,27 +1172,6 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) return 0; } -static void mptcp_check_for_eof(struct mptcp_sock *msk) -{ - struct mptcp_subflow_context *subflow; - struct sock *sk = (struct sock *)msk; - int receivers = 0; - - mptcp_for_each_subflow(msk, subflow) - receivers += !subflow->rx_eof; - - if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) { - /* hopefully temporary hack: propagate shutdown status - * to msk, when all subflows agree on it - */ - sk->sk_shutdown |= RCV_SHUTDOWN; - - smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ - set_bit(MPTCP_DATA_READY, &msk->flags); - sk->sk_data_ready(sk); - } -} - static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 493b98a0825c..bf132575040d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -393,6 +393,7 @@ static void mptcp_sock_destruct(struct sock *sk) sock_orphan(sk); } + mptcp_token_destroy(mptcp_sk(sk)->token); inet_sock_destruct(sk); } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 6c19b91bbb86..55ee680e9db1 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -474,8 +474,7 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, - enum genl_validate_flags no_strict_flag, - bool parallel) + enum genl_validate_flags no_strict_flag) { enum netlink_validation validate = ops->validate & no_strict_flag ? NL_VALIDATE_LIBERAL : @@ -486,7 +485,7 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, if (!family->maxattr) return NULL; - if (parallel) { + if (family->parallel_ops) { attrbuf = kmalloc_array(family->maxattr + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) @@ -498,7 +497,7 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr, family->policy, validate, extack); if (err) { - if (parallel) + if (family->parallel_ops) kfree(attrbuf); return ERR_PTR(err); } @@ -506,10 +505,9 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family, } static void genl_family_rcv_msg_attrs_free(const struct genl_family *family, - struct nlattr **attrbuf, - bool parallel) + struct nlattr **attrbuf) { - if (parallel) + if (family->parallel_ops) kfree(attrbuf); } @@ -537,15 +535,14 @@ static int genl_start(struct netlink_callback *cb) attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack, ops, ctx->hdrlen, - GENL_DONT_VALIDATE_DUMP_STRICT, - true); + GENL_DONT_VALIDATE_DUMP_STRICT); if (IS_ERR(attrs)) return PTR_ERR(attrs); no_attrs: info = genl_dumpit_info_alloc(); if (!info) { - kfree(attrs); + genl_family_rcv_msg_attrs_free(ctx->family, attrs); return -ENOMEM; } info->family = ctx->family; @@ -562,7 +559,7 @@ no_attrs: } if (rc) { - kfree(attrs); + genl_family_rcv_msg_attrs_free(info->family, info->attrs); genl_dumpit_info_free(info); cb->data = NULL; } @@ -591,7 +588,7 @@ static int genl_lock_done(struct netlink_callback *cb) rc = ops->done(cb); genl_unlock(); } - genl_family_rcv_msg_attrs_free(info->family, info->attrs, false); + genl_family_rcv_msg_attrs_free(info->family, info->attrs); genl_dumpit_info_free(info); return rc; } @@ -604,7 +601,7 @@ static int genl_parallel_done(struct netlink_callback *cb) if (ops->done) rc = ops->done(cb); - genl_family_rcv_msg_attrs_free(info->family, info->attrs, true); + genl_family_rcv_msg_attrs_free(info->family, info->attrs); genl_dumpit_info_free(info); return rc; } @@ -671,8 +668,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack, ops, hdrlen, - GENL_DONT_VALIDATE_STRICT, - family->parallel_ops); + GENL_DONT_VALIDATE_STRICT); if (IS_ERR(attrbuf)) return PTR_ERR(attrbuf); @@ -698,7 +694,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, family->post_doit(ops, skb, &info); out: - genl_family_rcv_msg_attrs_free(family, attrbuf, family->parallel_ops); + genl_family_rcv_msg_attrs_free(family, attrbuf); return err; } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index eccc7d366e17..f90ef6934b8f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -70,6 +70,7 @@ static const struct proto_ops nr_proto_ops; * separate class since they always nest. */ static struct lock_class_key nr_netdev_xmit_lock_key; +static struct lock_class_key nr_netdev_addr_lock_key; static void nr_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -80,6 +81,7 @@ static void nr_set_lockdep_one(struct net_device *dev, static void nr_set_lockdep_key(struct net_device *dev) { + lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL); } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index e7a872207b46..ce85656ac9c1 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -71,6 +71,7 @@ ax25_address rose_callsign; * separate class since they always nest. */ static struct lock_class_key rose_netdev_xmit_lock_key; +static struct lock_class_key rose_netdev_addr_lock_key; static void rose_set_lockdep_one(struct net_device *dev, struct netdev_queue *txq, @@ -81,6 +82,7 @@ static void rose_set_lockdep_one(struct net_device *dev, static void rose_set_lockdep_key(struct net_device *dev) { + lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key); netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 9fe264bec70c..9a2139ebd67d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -810,100 +810,6 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) } /* - * Transition a call to the complete state. - */ -static inline bool __rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error) -{ - if (call->state < RXRPC_CALL_COMPLETE) { - call->abort_code = abort_code; - call->error = error; - call->completion = compl, - call->state = RXRPC_CALL_COMPLETE; - trace_rxrpc_call_complete(call); - wake_up(&call->waitq); - return true; - } - return false; -} - -static inline bool rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error) -{ - bool ret; - - write_lock_bh(&call->state_lock); - ret = __rxrpc_set_call_completion(call, compl, abort_code, error); - write_unlock_bh(&call->state_lock); - return ret; -} - -/* - * Record that a call successfully completed. - */ -static inline bool __rxrpc_call_completed(struct rxrpc_call *call) -{ - return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); -} - -static inline bool rxrpc_call_completed(struct rxrpc_call *call) -{ - bool ret; - - write_lock_bh(&call->state_lock); - ret = __rxrpc_call_completed(call); - write_unlock_bh(&call->state_lock); - return ret; -} - -/* - * Record that a call is locally aborted. - */ -static inline bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call, - rxrpc_seq_t seq, - u32 abort_code, int error) -{ - trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, - abort_code, error); - return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, - abort_code, error); -} - -static inline bool rxrpc_abort_call(const char *why, struct rxrpc_call *call, - rxrpc_seq_t seq, u32 abort_code, int error) -{ - bool ret; - - write_lock_bh(&call->state_lock); - ret = __rxrpc_abort_call(why, call, seq, abort_code, error); - write_unlock_bh(&call->state_lock); - return ret; -} - -/* - * Abort a call due to a protocol error. - */ -static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, - struct sk_buff *skb, - const char *eproto_why, - const char *why, - u32 abort_code) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why); - return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO); -} - -#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \ - __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \ - (abort_why), (abort_code)) - -/* * conn_client.c */ extern unsigned int rxrpc_max_client_connections; @@ -1101,9 +1007,34 @@ extern const struct seq_operations rxrpc_peer_seq_ops; * recvmsg.c */ void rxrpc_notify_socket(struct rxrpc_call *); +bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); +bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); +bool __rxrpc_call_completed(struct rxrpc_call *); +bool rxrpc_call_completed(struct rxrpc_call *); +bool __rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); +bool rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* + * Abort a call due to a protocol error. + */ +static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, + struct sk_buff *skb, + const char *eproto_why, + const char *why, + u32 abort_code) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why); + return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO); +} + +#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \ + __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \ + (abort_why), (abort_code)) + +/* * rtt.c */ void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 2a65ac41055f..aa1c8eee6557 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -248,7 +248,18 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) if (anno_type != RXRPC_TX_ANNO_RETRANS) continue; + /* We need to reset the retransmission state, but we need to do + * so before we drop the lock as a new ACK/NAK may come in and + * confuse things + */ + annotation &= ~RXRPC_TX_ANNO_MASK; + annotation |= RXRPC_TX_ANNO_RESENT; + call->rxtx_annotations[ix] = annotation; + skb = call->rxtx_buffer[ix]; + if (!skb) + continue; + rxrpc_get_skb(skb, rxrpc_skb_got); spin_unlock_bh(&call->lock); @@ -262,24 +273,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) rxrpc_free_skb(skb, rxrpc_skb_freed); spin_lock_bh(&call->lock); - - /* We need to clear the retransmit state, but there are two - * things we need to be aware of: A new ACK/NAK might have been - * received and the packet might have been hard-ACK'd (in which - * case it will no longer be in the buffer). - */ - if (after(seq, call->tx_hard_ack)) { - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - if (anno_type == RXRPC_TX_ANNO_RETRANS || - anno_type == RXRPC_TX_ANNO_NAK) { - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_UNACK; - } - annotation |= RXRPC_TX_ANNO_RESENT; - call->rxtx_annotations[ix] = annotation; - } - if (after(call->tx_hard_ack, seq)) seq = call->tx_hard_ack; } @@ -320,7 +313,6 @@ recheck_state: if (call->state == RXRPC_CALL_COMPLETE) { del_timer_sync(&call->timer); - rxrpc_notify_socket(call); goto out_put; } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 06fcff2ebbba..447f55ca6886 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -173,10 +173,9 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, else trace_rxrpc_rx_abort(call, serial, conn->abort_code); - if (rxrpc_set_call_completion(call, compl, - conn->abort_code, - conn->error)) - rxrpc_notify_socket(call); + rxrpc_set_call_completion(call, compl, + conn->abort_code, + conn->error); } } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 3be4177baf70..299ac98e9754 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -275,7 +275,6 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, case RXRPC_CALL_SERVER_AWAIT_ACK: __rxrpc_call_completed(call); - rxrpc_notify_socket(call); state = call->state; break; @@ -1013,9 +1012,8 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); - if (rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, - abort_code, -ECONNABORTED)) - rxrpc_notify_socket(call); + rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + abort_code, -ECONNABORTED); } /* @@ -1102,7 +1100,6 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx, spin_lock(&rx->incoming_lock); __rxrpc_disconnect_call(conn, call); spin_unlock(&rx->incoming_lock); - rxrpc_notify_socket(call); } /* diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 112e490ebbcd..a852f46d5234 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -292,9 +292,7 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) { rxrpc_see_call(call); - if (call->state < RXRPC_CALL_COMPLETE && - rxrpc_set_call_completion(call, compl, 0, -error)) - rxrpc_notify_socket(call); + rxrpc_set_call_completion(call, compl, 0, -error); } } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 8578c39ec839..2989742a4aa1 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -59,6 +59,85 @@ void rxrpc_notify_socket(struct rxrpc_call *call) } /* + * Transition a call to the complete state. + */ +bool __rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error) +{ + if (call->state < RXRPC_CALL_COMPLETE) { + call->abort_code = abort_code; + call->error = error; + call->completion = compl, + call->state = RXRPC_CALL_COMPLETE; + trace_rxrpc_call_complete(call); + wake_up(&call->waitq); + rxrpc_notify_socket(call); + return true; + } + return false; +} + +bool rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error) +{ + bool ret = false; + + if (call->state < RXRPC_CALL_COMPLETE) { + write_lock_bh(&call->state_lock); + ret = __rxrpc_set_call_completion(call, compl, abort_code, error); + write_unlock_bh(&call->state_lock); + } + return ret; +} + +/* + * Record that a call successfully completed. + */ +bool __rxrpc_call_completed(struct rxrpc_call *call) +{ + return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); +} + +bool rxrpc_call_completed(struct rxrpc_call *call) +{ + bool ret = false; + + if (call->state < RXRPC_CALL_COMPLETE) { + write_lock_bh(&call->state_lock); + ret = __rxrpc_call_completed(call); + write_unlock_bh(&call->state_lock); + } + return ret; +} + +/* + * Record that a call is locally aborted. + */ +bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call, + rxrpc_seq_t seq, u32 abort_code, int error) +{ + trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, + abort_code, error); + return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, + abort_code, error); +} + +bool rxrpc_abort_call(const char *why, struct rxrpc_call *call, + rxrpc_seq_t seq, u32 abort_code, int error) +{ + bool ret; + + write_lock_bh(&call->state_lock); + ret = __rxrpc_abort_call(why, call, seq, abort_code, error); + write_unlock_bh(&call->state_lock); + return ret; +} + +/* * Pass a call terminating message to userspace. */ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5e9c43d4a314..1304b8608f56 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -261,10 +261,8 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, case -ENETUNREACH: case -EHOSTUNREACH: case -ECONNREFUSED: - rxrpc_set_call_completion(call, - RXRPC_CALL_LOCAL_ERROR, + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); - rxrpc_notify_socket(call); goto out; } _debug("need instant resend %d", ret); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b19a0021a0bd..265a61d011df 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -464,6 +464,7 @@ void __netdev_watchdog_up(struct net_device *dev) dev_hold(dev); } } +EXPORT_SYMBOL_GPL(__netdev_watchdog_up); static void dev_watchdog_up(struct net_device *dev) { diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 34ca7b789eba..e366ec9a7e4d 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -316,7 +316,6 @@ static int tipc_enable_bearer(struct net *net, const char *name, b->domain = disc_domain; b->net_plane = bearer_id + 'A'; b->priority = prio; - test_and_set_bit_lock(0, &b->up); refcount_set(&b->refcnt, 1); res = tipc_disc_create(net, b, &b->bcast_addr, &skb); @@ -326,6 +325,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, goto rejected; } + test_and_set_bit_lock(0, &b->up); rcu_assign_pointer(tn->bearer_list[bearer_id], b); if (skb) tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 046e4cb3acea..01b64869a173 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -238,14 +238,14 @@ int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen, hdr = buf_msg(skb); curr = msg_blocks(hdr); mlen = msg_size(hdr); - cpy = min_t(int, rem, mss - mlen); + cpy = min_t(size_t, rem, mss - mlen); if (cpy != copy_from_iter(skb->data + mlen, cpy, &m->msg_iter)) return -EFAULT; msg_set_size(hdr, mlen + cpy); skb_put(skb, cpy); rem -= cpy; total += msg_blocks(hdr) - curr; - } while (rem); + } while (rem > 0); return total - accounted; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 26123f4177fd..a94f38333698 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1574,7 +1574,8 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen) break; send = min_t(size_t, dlen - sent, TIPC_MAX_USER_MSG_SIZE); blocks = tsk->snd_backlog; - if (tsk->oneway++ >= tsk->nagle_start && send <= maxnagle) { + if (tsk->oneway++ >= tsk->nagle_start && maxnagle && + send <= maxnagle) { rc = tipc_msg_append(hdr, m, send, maxnagle, txq); if (unlikely(rc < 0)) break; diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index e9a712fb2392..faf74850a1b5 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -31,7 +31,7 @@ config CFG80211 For more information refer to documentation on the wireless wiki: - http://wireless.kernel.org/en/developers/Documentation/cfg80211 + https://wireless.wiki.kernel.org/en/developers/Documentation/cfg80211 When built as a module it will be called cfg80211. diff --git a/net/wireless/core.c b/net/wireless/core.c index f0226ae9561c..c623d9bf5096 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -497,6 +497,8 @@ use_default_name: INIT_WORK(&rdev->propagate_radar_detect_wk, cfg80211_propagate_radar_detect_wk); INIT_WORK(&rdev->propagate_cac_done_wk, cfg80211_propagate_cac_done_wk); + INIT_WORK(&rdev->mgmt_registrations_update_wk, + cfg80211_mgmt_registrations_update_wk); #ifdef CONFIG_CFG80211_DEFAULT_PS rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT; @@ -1047,6 +1049,7 @@ void wiphy_unregister(struct wiphy *wiphy) flush_work(&rdev->sched_scan_stop_wk); flush_work(&rdev->propagate_radar_detect_wk); flush_work(&rdev->propagate_cac_done_wk); + flush_work(&rdev->mgmt_registrations_update_wk); #ifdef CONFIG_PM if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup) @@ -1108,7 +1111,6 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) rdev->devlist_generation++; cfg80211_mlme_purge_registrations(wdev); - flush_work(&wdev->mgmt_registrations_update_wk); switch (wdev->iftype) { case NL80211_IFTYPE_P2P_DEVICE: @@ -1253,8 +1255,6 @@ void cfg80211_init_wdev(struct cfg80211_registered_device *rdev, spin_lock_init(&wdev->event_lock); INIT_LIST_HEAD(&wdev->mgmt_registrations); spin_lock_init(&wdev->mgmt_registrations_lock); - INIT_WORK(&wdev->mgmt_registrations_update_wk, - cfg80211_mgmt_registrations_update_wk); INIT_LIST_HEAD(&wdev->pmsr_list); spin_lock_init(&wdev->pmsr_lock); INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk); diff --git a/net/wireless/core.h b/net/wireless/core.h index e0e5b3ee9699..67b0389fca4d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -99,6 +99,8 @@ struct cfg80211_registered_device { struct cfg80211_chan_def cac_done_chandef; struct work_struct propagate_cac_done_wk; + struct work_struct mgmt_registrations_update_wk; + /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wiphy wiphy __aligned(NETDEV_ALIGN); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 189334314cba..a6c61a2e6569 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -440,9 +440,15 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) ASSERT_RTNL(); + spin_lock_bh(&wdev->mgmt_registrations_lock); + if (!wdev->mgmt_registrations_need_update) { + spin_unlock_bh(&wdev->mgmt_registrations_lock); + return; + } + rcu_read_lock(); list_for_each_entry_rcu(tmp, &rdev->wiphy.wdev_list, list) { - list_for_each_entry_rcu(reg, &tmp->mgmt_registrations, list) { + list_for_each_entry(reg, &tmp->mgmt_registrations, list) { u32 mask = BIT(le16_to_cpu(reg->frame_type) >> 4); u32 mcast_mask = 0; @@ -460,16 +466,23 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev) } rcu_read_unlock(); + wdev->mgmt_registrations_need_update = 0; + spin_unlock_bh(&wdev->mgmt_registrations_lock); + rdev_update_mgmt_frame_registrations(rdev, wdev, &upd); } void cfg80211_mgmt_registrations_update_wk(struct work_struct *wk) { - struct wireless_dev *wdev = container_of(wk, struct wireless_dev, - mgmt_registrations_update_wk); + struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; + + rdev = container_of(wk, struct cfg80211_registered_device, + mgmt_registrations_update_wk); rtnl_lock(); - cfg80211_mgmt_registrations_update(wdev); + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) + cfg80211_mgmt_registrations_update(wdev); rtnl_unlock(); } @@ -557,6 +570,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, nreg->multicast_rx = multicast_rx; list_add(&nreg->list, &wdev->mgmt_registrations); } + wdev->mgmt_registrations_need_update = 1; spin_unlock_bh(&wdev->mgmt_registrations_lock); cfg80211_mgmt_registrations_update(wdev); @@ -585,7 +599,8 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) list_del(®->list); kfree(reg); - schedule_work(&wdev->mgmt_registrations_update_wk); + wdev->mgmt_registrations_need_update = 1; + schedule_work(&rdev->mgmt_registrations_update_wk); } spin_unlock_bh(&wdev->mgmt_registrations_lock); @@ -608,6 +623,7 @@ void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) list_del(®->list); kfree(reg); } + wdev->mgmt_registrations_need_update = 1; spin_unlock_bh(&wdev->mgmt_registrations_lock); cfg80211_mgmt_registrations_update(wdev); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b6c0f08bd80d..3700266229f6 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -352,10 +352,8 @@ static int xsk_generic_xmit(struct sock *sk) len = desc.len; skb = sock_alloc_send_skb(sk, len, 1, &err); - if (unlikely(!skb)) { - err = -EAGAIN; + if (unlikely(!skb)) goto out; - } skb_put(skb, len); addr = desc.addr; |