diff options
Diffstat (limited to 'net')
52 files changed, 422 insertions, 643 deletions
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 77883b6788cd..833cd3792c51 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -279,13 +279,13 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) grant_ref_t ref; ref = priv->rings[i].intf->ref[j]; - gnttab_end_foreign_access(ref, 0); + gnttab_end_foreign_access(ref, NULL); } free_pages_exact(priv->rings[i].data.in, 1UL << (priv->rings[i].intf->ring_order + XEN_PAGE_SHIFT)); } - gnttab_end_foreign_access(priv->rings[i].ref, 0); + gnttab_end_foreign_access(priv->rings[i].ref, NULL); free_page((unsigned long)priv->rings[i].intf); } kfree(priv->rings); @@ -353,10 +353,10 @@ static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, out: if (bytes) { for (i--; i >= 0; i--) - gnttab_end_foreign_access(ring->intf->ref[i], 0); + gnttab_end_foreign_access(ring->intf->ref[i], NULL); free_pages_exact(bytes, 1UL << (order + XEN_PAGE_SHIFT)); } - gnttab_end_foreign_access(ring->ref, 0); + gnttab_end_foreign_access(ring->ref, NULL); free_page((unsigned long)ring->intf); return ret; } diff --git a/net/Kconfig.debug b/net/Kconfig.debug index a5781cf63b16..e6ae11cc2fb7 100644 --- a/net/Kconfig.debug +++ b/net/Kconfig.debug @@ -20,7 +20,7 @@ config NET_NS_REFCNT_TRACKER config DEBUG_NET bool "Add generic networking debug" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && NET help Enable extra sanity checks in networking. This is mostly used by fuzzers, but is safe to select. diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 116481e4da82..4c7030ed8d33 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -62,12 +62,12 @@ static void ax25_free_sock(struct sock *sk) */ static void ax25_cb_del(ax25_cb *ax25) { + spin_lock_bh(&ax25_list_lock); if (!hlist_unhashed(&ax25->ax25_node)) { - spin_lock_bh(&ax25_list_lock); hlist_del_init(&ax25->ax25_node); - spin_unlock_bh(&ax25_list_lock); ax25_cb_put(ax25); } + spin_unlock_bh(&ax25_list_lock); } /* @@ -81,6 +81,7 @@ static void ax25_kill_by_device(struct net_device *dev) if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; + ax25_dev->device_up = false; spin_lock_bh(&ax25_list_lock); again: @@ -91,6 +92,7 @@ again: spin_unlock_bh(&ax25_list_lock); ax25_disconnect(s, ENETUNREACH); s->ax25_dev = NULL; + ax25_cb_del(s); spin_lock_bh(&ax25_list_lock); goto again; } @@ -103,6 +105,7 @@ again: dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); } + ax25_cb_del(s); release_sock(sk); spin_lock_bh(&ax25_list_lock); sock_put(sk); @@ -995,9 +998,11 @@ static int ax25_release(struct socket *sock) if (sk->sk_type == SOCK_SEQPACKET) { switch (ax25->state) { case AX25_STATE_0: - release_sock(sk); - ax25_disconnect(ax25, 0); - lock_sock(sk); + if (!sock_flag(ax25->sk, SOCK_DEAD)) { + release_sock(sk); + ax25_disconnect(ax25, 0); + lock_sock(sk); + } ax25_destroy_socket(ax25); break; @@ -1053,11 +1058,13 @@ static int ax25_release(struct socket *sock) ax25_destroy_socket(ax25); } if (ax25_dev) { - del_timer_sync(&ax25->timer); - del_timer_sync(&ax25->t1timer); - del_timer_sync(&ax25->t2timer); - del_timer_sync(&ax25->t3timer); - del_timer_sync(&ax25->idletimer); + if (!ax25_dev->device_up) { + del_timer_sync(&ax25->timer); + del_timer_sync(&ax25->t1timer); + del_timer_sync(&ax25->t2timer); + del_timer_sync(&ax25->t3timer); + del_timer_sync(&ax25->idletimer); + } dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); } @@ -1654,9 +1661,12 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; - struct sk_buff *skb; + struct sk_buff *skb, *last; + struct sk_buff_head *sk_queue; int copied; int err = 0; + int off = 0; + long timeo; lock_sock(sk); /* @@ -1668,10 +1678,29 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, goto out; } - /* Now we can treat all alike */ - skb = skb_recv_datagram(sk, flags, &err); - if (skb == NULL) - goto out; + /* We need support for non-blocking reads. */ + sk_queue = &sk->sk_receive_queue; + skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off, &err, &last); + /* If no packet is available, release_sock(sk) and try again. */ + if (!skb) { + if (err != -EAGAIN) + goto out; + release_sock(sk); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + while (timeo && !__skb_wait_for_more_packets(sk, sk_queue, &err, + &timeo, last)) { + skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off, + &err, &last); + if (skb) + break; + + if (err != -EAGAIN) + goto done; + } + if (!skb) + goto done; + lock_sock(sk); + } if (!sk_to_ax25(sk)->pidincl) skb_pull(skb, 1); /* Remove PID */ @@ -1718,6 +1747,7 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, out: release_sock(sk); +done: return err; } diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index b80fccbac62a..95a76d571c44 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -62,6 +62,7 @@ void ax25_dev_device_up(struct net_device *dev) ax25_dev->dev = dev; dev_hold_track(dev, &ax25_dev->dev_tracker, GFP_ATOMIC); ax25_dev->forward = NULL; + ax25_dev->device_up = true; ax25_dev->values[AX25_VALUES_IPDEFMODE] = AX25_DEF_IPDEFMODE; ax25_dev->values[AX25_VALUES_AXDEFMODE] = AX25_DEF_AXDEFMODE; diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index 3a476e4f6cd0..9ff98f46dc6b 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -268,7 +268,7 @@ void ax25_disconnect(ax25_cb *ax25, int reason) del_timer_sync(&ax25->t3timer); del_timer_sync(&ax25->idletimer); } else { - if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY)) + if (ax25->sk && !sock_flag(ax25->sk, SOCK_DESTROY)) ax25_stop_heartbeat(ax25); ax25_stop_t1timer(ax25); ax25_stop_t2timer(ax25); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 5abb2ca5b129..59a5c1341c26 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2153,7 +2153,7 @@ int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; - bitmap_from_u64(entry->flags, flags); + entry->flags = flags; list_add(&entry->list, list); @@ -2634,7 +2634,7 @@ int hci_register_dev(struct hci_dev *hdev) * callback. */ if (hdev->wakeup) - set_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, hdev->conn_flags); + hdev->conn_flags |= HCI_CONN_FLAG_REMOTE_WAKEUP; hci_sock_dev_event(hdev, HCI_DEV_REG); hci_dev_hold(hdev); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 635cc5fb451e..38ecaf9264ee 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -482,7 +482,7 @@ static int add_to_accept_list(struct hci_request *req, /* During suspend, only wakeable devices can be in accept list */ if (hdev->suspended && - !test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, params->flags)) + !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) return 0; *num_entries += 1; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 4d2203c5f1bb..286d6767f017 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1637,7 +1637,7 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, * indicates that LL Privacy has been enabled and * HCI_OP_LE_SET_PRIVACY_MODE is supported. */ - if (!test_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, params->flags)) + if (!(params->flags & HCI_CONN_FLAG_DEVICE_PRIVACY)) return 0; irk = hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type); @@ -1666,7 +1666,7 @@ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, /* During suspend, only wakeable devices can be in acceptlist */ if (hdev->suspended && - !test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, params->flags)) + !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) return 0; /* Select filter policy to accept all advertising */ @@ -4888,7 +4888,7 @@ static int hci_update_event_filter_sync(struct hci_dev *hdev) hci_clear_event_filter_sync(hdev); list_for_each_entry(b, &hdev->accept_list, list) { - if (!test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, b->flags)) + if (!(b->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) continue; bt_dev_dbg(hdev, "Adding event filters for %pMR", &b->bdaddr); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 74937a834648..ae758ab1b558 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -4013,10 +4013,11 @@ static int exp_ll_privacy_feature_changed(bool enabled, struct hci_dev *hdev, memcpy(ev.uuid, rpa_resolution_uuid, 16); ev.flags = cpu_to_le32((enabled ? BIT(0) : 0) | BIT(1)); + // Do we need to be atomic with the conn_flags? if (enabled && privacy_mode_capable(hdev)) - set_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, hdev->conn_flags); + hdev->conn_flags |= HCI_CONN_FLAG_DEVICE_PRIVACY; else - clear_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, hdev->conn_flags); + hdev->conn_flags &= ~HCI_CONN_FLAG_DEVICE_PRIVACY; return mgmt_limited_event(MGMT_EV_EXP_FEATURE_CHANGED, hdev, &ev, sizeof(ev), @@ -4435,8 +4436,7 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - bitmap_to_arr32(&supported_flags, hdev->conn_flags, - __HCI_CONN_NUM_FLAGS); + supported_flags = hdev->conn_flags; memset(&rp, 0, sizeof(rp)); @@ -4447,8 +4447,7 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, if (!br_params) goto done; - bitmap_to_arr32(¤t_flags, br_params->flags, - __HCI_CONN_NUM_FLAGS); + current_flags = br_params->flags; } else { params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); @@ -4456,8 +4455,7 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, if (!params) goto done; - bitmap_to_arr32(¤t_flags, params->flags, - __HCI_CONN_NUM_FLAGS); + current_flags = params->flags; } bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr); @@ -4502,8 +4500,8 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, &cp->addr.bdaddr, cp->addr.type, __le32_to_cpu(current_flags)); - bitmap_to_arr32(&supported_flags, hdev->conn_flags, - __HCI_CONN_NUM_FLAGS); + // We should take hci_dev_lock() early, I think.. conn_flags can change + supported_flags = hdev->conn_flags; if ((supported_flags | current_flags) != supported_flags) { bt_dev_warn(hdev, "Bad flag given (0x%x) vs supported (0x%0x)", @@ -4519,7 +4517,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, cp->addr.type); if (br_params) { - bitmap_from_u64(br_params->flags, current_flags); + br_params->flags = current_flags; status = MGMT_STATUS_SUCCESS; } else { bt_dev_warn(hdev, "No such BR/EDR device %pMR (0x%x)", @@ -4529,15 +4527,11 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); if (params) { - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); - - bitmap_from_u64(flags, current_flags); - /* Devices using RPAs can only be programmed in the * acceptlist LL Privacy has been enable otherwise they * cannot mark HCI_CONN_FLAG_REMOTE_WAKEUP. */ - if (test_bit(HCI_CONN_FLAG_REMOTE_WAKEUP, flags) && + if ((current_flags & HCI_CONN_FLAG_REMOTE_WAKEUP) && !use_ll_privacy(hdev) && hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) { @@ -4546,14 +4540,13 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - bitmap_from_u64(params->flags, current_flags); + params->flags = current_flags; status = MGMT_STATUS_SUCCESS; /* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY * has been set. */ - if (test_bit(HCI_CONN_FLAG_DEVICE_PRIVACY, - params->flags)) + if (params->flags & HCI_CONN_FLAG_DEVICE_PRIVACY) hci_update_passive_scan(hdev); } else { bt_dev_warn(hdev, "No such LE device %pMR (0x%x)", @@ -7154,8 +7147,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, addr_type); if (params) - bitmap_to_arr32(¤t_flags, params->flags, - __HCI_CONN_NUM_FLAGS); + current_flags = params->flags; } err = hci_cmd_sync_queue(hdev, add_device_sync, NULL, NULL); @@ -7164,8 +7156,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, added: device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); - bitmap_to_arr32(&supported_flags, hdev->conn_flags, - __HCI_CONN_NUM_FLAGS); + supported_flags = hdev->conn_flags; device_flags_changed(NULL, hdev, &cp->addr.bdaddr, cp->addr.type, supported_flags, current_flags); diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 7057f8db4f99..1daf95e17d67 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -906,7 +906,6 @@ int crush_do_rule(const struct crush_map *map, int recurse_to_leaf; int wsize = 0; int osize; - int *tmp; const struct crush_rule *rule; __u32 step; int i, j; @@ -1073,9 +1072,7 @@ int crush_do_rule(const struct crush_map *map, memcpy(o, c, osize*sizeof(*o)); /* swap o and w arrays */ - tmp = o; - o = w; - w = tmp; + swap(o, w); wsize = osize; break; diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 73f68d4625f3..929f6379a279 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -595,3 +595,9 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, return (bo && list_empty(&bo->cb_list)) ? -EOPNOTSUPP : count; } EXPORT_SYMBOL(flow_indr_dev_setup_offload); + +bool flow_indr_dev_exists(void) +{ + return !list_empty(&flow_block_indr_dev_list); +} +EXPORT_SYMBOL(flow_indr_dev_exists); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 47b6c1f0fdbb..54625287ee5b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1579,7 +1579,7 @@ static void neigh_managed_work(struct work_struct *work) list_for_each_entry(neigh, &tbl->managed_list, managed_list) neigh_event_send_probe(neigh, NULL, false); queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, - NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); + max(NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME), HZ)); write_unlock_bh(&tbl->lock); } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 2e78458900f2..eb8e128e43e8 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1120,12 +1120,6 @@ static int __init dccp_init(void) SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind_bucket_cachep) goto out_free_hashinfo2; - dccp_hashinfo.bind2_bucket_cachep = - kmem_cache_create("dccp_bind2_bucket", - sizeof(struct inet_bind2_bucket), 0, - SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); - if (!dccp_hashinfo.bind2_bucket_cachep) - goto out_free_bind_bucket_cachep; /* * Size and allocate the main established and bind bucket @@ -1156,7 +1150,7 @@ static int __init dccp_init(void) if (!dccp_hashinfo.ehash) { DCCP_CRIT("Failed to allocate DCCP established hash table"); - goto out_free_bind2_bucket_cachep; + goto out_free_bind_bucket_cachep; } for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) @@ -1182,23 +1176,14 @@ static int __init dccp_init(void) goto out_free_dccp_locks; } - dccp_hashinfo.bhash2 = (struct inet_bind2_hashbucket *) - __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order); - - if (!dccp_hashinfo.bhash2) { - DCCP_CRIT("Failed to allocate DCCP bind2 hash table"); - goto out_free_dccp_bhash; - } - for (i = 0; i < dccp_hashinfo.bhash_size; i++) { spin_lock_init(&dccp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); - INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain); } rc = dccp_mib_init(); if (rc) - goto out_free_dccp_bhash2; + goto out_free_dccp_bhash; rc = dccp_ackvec_init(); if (rc) @@ -1222,38 +1207,30 @@ out_ackvec_exit: dccp_ackvec_exit(); out_free_dccp_mib: dccp_mib_exit(); -out_free_dccp_bhash2: - free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); out_free_dccp_locks: inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); -out_free_bind2_bucket_cachep: - kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); out_free_hashinfo2: inet_hashinfo2_free_mod(&dccp_hashinfo); out_fail: dccp_hashinfo.bhash = NULL; - dccp_hashinfo.bhash2 = NULL; dccp_hashinfo.ehash = NULL; dccp_hashinfo.bind_bucket_cachep = NULL; - dccp_hashinfo.bind2_bucket_cachep = NULL; return rc; } static void __exit dccp_fini(void) { - int bhash_order = get_order(dccp_hashinfo.bhash_size * - sizeof(struct inet_bind_hashbucket)); - ccid_cleanup_builtins(); dccp_mib_exit(); - free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); - free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); + free_pages((unsigned long)dccp_hashinfo.bhash, + get_order(dccp_hashinfo.bhash_size * + sizeof(struct inet_bind_hashbucket))); free_pages((unsigned long)dccp_hashinfo.ehash, get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c0b7e6c21360..53f5f956d948 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -117,32 +117,6 @@ bool inet_rcv_saddr_any(const struct sock *sk) return !sk->sk_rcv_saddr; } -static bool use_bhash2_on_bind(const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - int addr_type; - - if (sk->sk_family == AF_INET6) { - addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); - return addr_type != IPV6_ADDR_ANY && - addr_type != IPV6_ADDR_MAPPED; - } -#endif - return sk->sk_rcv_saddr != htonl(INADDR_ANY); -} - -static u32 get_bhash2_nulladdr_hash(const struct sock *sk, struct net *net, - int port) -{ -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr nulladdr = {}; - - if (sk->sk_family == AF_INET6) - return ipv6_portaddr_hash(net, &nulladdr, port); -#endif - return ipv4_portaddr_hash(net, 0, port); -} - void inet_get_local_port_range(struct net *net, int *low, int *high) { unsigned int seq; @@ -156,71 +130,16 @@ void inet_get_local_port_range(struct net *net, int *low, int *high) } EXPORT_SYMBOL(inet_get_local_port_range); -static bool bind_conflict_exist(const struct sock *sk, struct sock *sk2, - kuid_t sk_uid, bool relax, - bool reuseport_cb_ok, bool reuseport_ok) -{ - int bound_dev_if2; - - if (sk == sk2) - return false; - - bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); - - if (!sk->sk_bound_dev_if || !bound_dev_if2 || - sk->sk_bound_dev_if == bound_dev_if2) { - if (sk->sk_reuse && sk2->sk_reuse && - sk2->sk_state != TCP_LISTEN) { - if (!relax || (!reuseport_ok && sk->sk_reuseport && - sk2->sk_reuseport && reuseport_cb_ok && - (sk2->sk_state == TCP_TIME_WAIT || - uid_eq(sk_uid, sock_i_uid(sk2))))) - return true; - } else if (!reuseport_ok || !sk->sk_reuseport || - !sk2->sk_reuseport || !reuseport_cb_ok || - (sk2->sk_state != TCP_TIME_WAIT && - !uid_eq(sk_uid, sock_i_uid(sk2)))) { - return true; - } - } - return false; -} - -static bool check_bhash2_conflict(const struct sock *sk, - struct inet_bind2_bucket *tb2, kuid_t sk_uid, - bool relax, bool reuseport_cb_ok, - bool reuseport_ok) -{ - struct sock *sk2; - - sk_for_each_bound_bhash2(sk2, &tb2->owners) { - if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) - continue; - - if (bind_conflict_exist(sk, sk2, sk_uid, relax, - reuseport_cb_ok, reuseport_ok)) - return true; - } - return false; -} - -/* This should be called only when the corresponding inet_bind_bucket spinlock - * is held - */ -static int inet_csk_bind_conflict(const struct sock *sk, int port, - struct inet_bind_bucket *tb, - struct inet_bind2_bucket *tb2, /* may be null */ +static int inet_csk_bind_conflict(const struct sock *sk, + const struct inet_bind_bucket *tb, bool relax, bool reuseport_ok) { - struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - kuid_t uid = sock_i_uid((struct sock *)sk); - struct sock_reuseport *reuseport_cb; - struct inet_bind2_hashbucket *head2; - bool reuseport_cb_ok; struct sock *sk2; - struct net *net; - int l3mdev; - u32 hash; + bool reuseport_cb_ok; + bool reuse = sk->sk_reuse; + bool reuseport = !!sk->sk_reuseport; + struct sock_reuseport *reuseport_cb; + kuid_t uid = sock_i_uid((struct sock *)sk); rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); @@ -231,42 +150,40 @@ static int inet_csk_bind_conflict(const struct sock *sk, int port, /* * Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed - * in tb->owners and tb2->owners list belong - * to the same net + * in tb->owners list belong to the same net - the + * one this bucket belongs to. */ - if (!use_bhash2_on_bind(sk)) { - sk_for_each_bound(sk2, &tb->owners) - if (bind_conflict_exist(sk, sk2, uid, relax, - reuseport_cb_ok, reuseport_ok) && - inet_rcv_saddr_equal(sk, sk2, true)) - return true; + sk_for_each_bound(sk2, &tb->owners) { + int bound_dev_if2; - return false; + if (sk == sk2) + continue; + bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); + if ((!sk->sk_bound_dev_if || + !bound_dev_if2 || + sk->sk_bound_dev_if == bound_dev_if2)) { + if (reuse && sk2->sk_reuse && + sk2->sk_state != TCP_LISTEN) { + if ((!relax || + (!reuseport_ok && + reuseport && sk2->sk_reuseport && + reuseport_cb_ok && + (sk2->sk_state == TCP_TIME_WAIT || + uid_eq(uid, sock_i_uid(sk2))))) && + inet_rcv_saddr_equal(sk, sk2, true)) + break; + } else if (!reuseport_ok || + !reuseport || !sk2->sk_reuseport || + !reuseport_cb_ok || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, sock_i_uid(sk2)))) { + if (inet_rcv_saddr_equal(sk, sk2, true)) + break; + } + } } - - if (tb2 && check_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) - return true; - - net = sock_net(sk); - - /* check there's no conflict with an existing IPV6_ADDR_ANY (if ipv6) or - * INADDR_ANY (if ipv4) socket. - */ - hash = get_bhash2_nulladdr_hash(sk, net, port); - head2 = &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; - - l3mdev = inet_sk_bound_l3mdev(sk); - inet_bind_bucket_for_each(tb2, &head2->chain) - if (check_bind2_bucket_match_nulladdr(tb2, net, port, l3mdev, sk)) - break; - - if (tb2 && check_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) - return true; - - return false; + return sk2 != NULL; } /* @@ -274,20 +191,16 @@ static int inet_csk_bind_conflict(const struct sock *sk, int port, * inet_bind_hashbucket lock held. */ static struct inet_bind_hashbucket * -inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, - struct inet_bind2_bucket **tb2_ret, - struct inet_bind2_hashbucket **head2_ret, int *port_ret) +inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *port_ret) { struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - struct inet_bind2_hashbucket *head2; + int port = 0; struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); + bool relax = false; int i, low, high, attempt_half; - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; u32 remaining, offset; - bool relax = false; - int port = 0; int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); @@ -326,12 +239,10 @@ other_parity_scan: head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); - tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk, - &head2); inet_bind_bucket_for_each(tb, &head->chain) - if (check_bind_bucket_match(tb, net, port, l3mdev)) { - if (!inet_csk_bind_conflict(sk, port, tb, tb2, - relax, false)) + if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev && + tb->port == port) { + if (!inet_csk_bind_conflict(sk, tb, relax, false)) goto success; goto next_port; } @@ -361,8 +272,6 @@ next_port: success: *port_ret = port; *tb_ret = tb; - *tb2_ret = tb2; - *head2_ret = head2; return head; } @@ -458,81 +367,54 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) { bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - bool bhash_created = false, bhash2_created = false; - struct inet_bind2_bucket *tb2 = NULL; - struct inet_bind2_hashbucket *head2; - struct inet_bind_bucket *tb = NULL; + int ret = 1, port = snum; struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); - int ret = 1, port = snum; - bool found_port = false; + struct inet_bind_bucket *tb = NULL; int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); if (!port) { - head = inet_csk_find_open_port(sk, &tb, &tb2, &head2, &port); + head = inet_csk_find_open_port(sk, &tb, &port); if (!head) return ret; - if (tb && tb2) - goto success; - found_port = true; - } else { - head = &hinfo->bhash[inet_bhashfn(net, port, - hinfo->bhash_size)]; - spin_lock_bh(&head->lock); - inet_bind_bucket_for_each(tb, &head->chain) - if (check_bind_bucket_match(tb, net, port, l3mdev)) - break; - - tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk, - &head2); - } - - if (!tb) { - tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, net, - head, port, l3mdev); if (!tb) - goto fail_unlock; - bhash_created = true; - } - - if (!tb2) { - tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, - net, head2, port, l3mdev, sk); - if (!tb2) - goto fail_unlock; - bhash2_created = true; + goto tb_not_found; + goto success; } - - /* If we had to find an open port, we already checked for conflicts */ - if (!found_port && !hlist_empty(&tb->owners)) { + head = &hinfo->bhash[inet_bhashfn(net, port, + hinfo->bhash_size)]; + spin_lock_bh(&head->lock); + inet_bind_bucket_for_each(tb, &head->chain) + if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev && + tb->port == port) + goto tb_found; +tb_not_found: + tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, + net, head, port, l3mdev); + if (!tb) + goto fail_unlock; +tb_found: + if (!hlist_empty(&tb->owners)) { if (sk->sk_reuse == SK_FORCE_REUSE) goto success; if ((tb->fastreuse > 0 && reuse) || sk_reuseport_match(tb, sk)) goto success; - if (inet_csk_bind_conflict(sk, port, tb, tb2, true, true)) + if (inet_csk_bind_conflict(sk, tb, true, true)) goto fail_unlock; } success: inet_csk_update_fastreuse(tb, sk); if (!inet_csk(sk)->icsk_bind_hash) - inet_bind_hash(sk, tb, tb2, port); + inet_bind_hash(sk, tb, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); - WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2); ret = 0; fail_unlock: - if (ret) { - if (bhash_created) - inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - if (bhash2_created) - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - tb2); - } spin_unlock_bh(&head->lock); return ret; } @@ -1079,7 +961,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; - newicsk->icsk_bind2_hash = NULL; inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e8de5e699b3f..b9d995b5ce24 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -81,41 +81,6 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, return tb; } -struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep, - struct net *net, - struct inet_bind2_hashbucket *head, - const unsigned short port, - int l3mdev, - const struct sock *sk) -{ - struct inet_bind2_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); - - if (tb) { - write_pnet(&tb->ib_net, net); - tb->l3mdev = l3mdev; - tb->port = port; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr; - else -#endif - tb->rcv_saddr = sk->sk_rcv_saddr; - INIT_HLIST_HEAD(&tb->owners); - hlist_add_head(&tb->node, &head->chain); - } - return tb; -} - -static bool bind2_bucket_addr_match(struct inet_bind2_bucket *tb2, struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - return ipv6_addr_equal(&tb2->v6_rcv_saddr, - &sk->sk_v6_rcv_saddr); -#endif - return tb2->rcv_saddr == sk->sk_rcv_saddr; -} - /* * Caller must hold hashbucket lock for this tb with local BH disabled */ @@ -127,25 +92,12 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket } } -/* Caller must hold the lock for the corresponding hashbucket in the bhash table - * with local BH disabled - */ -void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb) -{ - if (hlist_empty(&tb->owners)) { - __hlist_del(&tb->node); - kmem_cache_free(cachep, tb); - } -} - void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, - struct inet_bind2_bucket *tb2, const unsigned short snum) + const unsigned short snum) { inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &tb->owners); inet_csk(sk)->icsk_bind_hash = tb; - sk_add_bind2_node(sk, &tb2->owners); - inet_csk(sk)->icsk_bind2_hash = tb2; } /* @@ -157,7 +109,6 @@ static void __inet_put_port(struct sock *sk) const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->inet_num, hashinfo->bhash_size); struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash]; - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; spin_lock(&head->lock); @@ -166,13 +117,6 @@ static void __inet_put_port(struct sock *sk) inet_csk(sk)->icsk_bind_hash = NULL; inet_sk(sk)->inet_num = 0; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - - if (inet_csk(sk)->icsk_bind2_hash) { - tb2 = inet_csk(sk)->icsk_bind2_hash; - __sk_del_bind2_node(sk); - inet_csk(sk)->icsk_bind2_hash = NULL; - inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); - } spin_unlock(&head->lock); } @@ -189,19 +133,14 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; unsigned short port = inet_sk(child)->inet_num; const int bhash = inet_bhashfn(sock_net(sk), port, - table->bhash_size); + table->bhash_size); struct inet_bind_hashbucket *head = &table->bhash[bhash]; - struct inet_bind2_hashbucket *head_bhash2; - bool created_inet_bind_bucket = false; - struct net *net = sock_net(sk); - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; int l3mdev; spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; - tb2 = inet_csk(sk)->icsk_bind2_hash; - if (unlikely(!tb || !tb2)) { + if (unlikely(!tb)) { spin_unlock(&head->lock); return -ENOENT; } @@ -214,45 +153,25 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) * as that of the child socket. We have to look up or * create a new bind bucket for the child here. */ inet_bind_bucket_for_each(tb, &head->chain) { - if (check_bind_bucket_match(tb, net, port, l3mdev)) + if (net_eq(ib_net(tb), sock_net(sk)) && + tb->l3mdev == l3mdev && tb->port == port) break; } if (!tb) { tb = inet_bind_bucket_create(table->bind_bucket_cachep, - net, head, port, l3mdev); + sock_net(sk), head, port, + l3mdev); if (!tb) { spin_unlock(&head->lock); return -ENOMEM; } - created_inet_bind_bucket = true; } inet_csk_update_fastreuse(tb, child); - - goto bhash2_find; - } else if (!bind2_bucket_addr_match(tb2, child)) { - l3mdev = inet_sk_bound_l3mdev(sk); - -bhash2_find: - tb2 = inet_bind2_bucket_find(table, net, port, l3mdev, child, - &head_bhash2); - if (!tb2) { - tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep, - net, head_bhash2, port, - l3mdev, child); - if (!tb2) - goto error; - } } - inet_bind_hash(child, tb, tb2, port); + inet_bind_hash(child, tb, port); spin_unlock(&head->lock); return 0; - -error: - if (created_inet_bind_bucket) - inet_bind_bucket_destroy(table->bind_bucket_cachep, tb); - spin_unlock(&head->lock); - return -ENOMEM; } EXPORT_SYMBOL_GPL(__inet_inherit_port); @@ -756,76 +675,6 @@ void inet_unhash(struct sock *sk) } EXPORT_SYMBOL_GPL(inet_unhash); -static bool check_bind2_bucket_match(struct inet_bind2_bucket *tb, - struct net *net, unsigned short port, - int l3mdev, struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); - else -#endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == sk->sk_rcv_saddr; -} - -bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb, - struct net *net, const unsigned short port, - int l3mdev, const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr nulladdr = {}; - - if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &nulladdr); - else -#endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == 0; -} - -static struct inet_bind2_hashbucket * -inet_bhashfn_portaddr(struct inet_hashinfo *hinfo, const struct sock *sk, - const struct net *net, unsigned short port) -{ - u32 hash; - -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - hash = ipv6_portaddr_hash(net, &sk->sk_v6_rcv_saddr, port); - else -#endif - hash = ipv4_portaddr_hash(net, sk->sk_rcv_saddr, port); - return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; -} - -/* This should only be called when the spinlock for the socket's corresponding - * bind_hashbucket is held - */ -struct inet_bind2_bucket * -inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net, - const unsigned short port, int l3mdev, struct sock *sk, - struct inet_bind2_hashbucket **head) -{ - struct inet_bind2_bucket *bhash2 = NULL; - struct inet_bind2_hashbucket *h; - - h = inet_bhashfn_portaddr(hinfo, sk, net, port); - inet_bind_bucket_for_each(bhash2, &h->chain) { - if (check_bind2_bucket_match(bhash2, net, port, l3mdev, sk)) - break; - } - - if (head) - *head = h; - - return bhash2; -} - /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this @@ -846,13 +695,10 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_timewait_sock *tw = NULL; - struct inet_bind2_hashbucket *head2; struct inet_bind_hashbucket *head; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; - bool tb_created = false; u32 remaining, offset; int ret, i, low, high; int l3mdev; @@ -909,7 +755,8 @@ other_parity_scan: * the established check is already unique enough. */ inet_bind_bucket_for_each(tb, &head->chain) { - if (check_bind_bucket_match(tb, net, port, l3mdev)) { + if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev && + tb->port == port) { if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) goto next_port; @@ -927,7 +774,6 @@ other_parity_scan: spin_unlock_bh(&head->lock); return -ENOMEM; } - tb_created = true; tb->fastreuse = -1; tb->fastreuseport = -1; goto ok; @@ -943,17 +789,6 @@ next_port: return -EADDRNOTAVAIL; ok: - /* Find the corresponding tb2 bucket since we need to - * add the socket to the bhash2 table as well - */ - tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk, &head2); - if (!tb2) { - tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net, - head2, port, l3mdev, sk); - if (!tb2) - goto error; - } - /* Here we want to add a little bit of randomness to the next source * port that will be chosen. We use a max() with a random here so that * on low contention the randomness is maximal and on high contention @@ -963,7 +798,7 @@ ok: WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ - inet_bind_hash(sk, tb, tb2, port); + inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); inet_ehash_nolisten(sk, (struct sock *)tw, NULL); @@ -975,12 +810,6 @@ ok: inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; - -error: - if (tb_created) - inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - spin_unlock_bh(&head->lock); - return -ENOMEM; } /* @@ -1026,10 +855,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, init_hashinfo_lhash2(h); /* this one is used for source ports of outgoing connections */ - table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE, - sizeof(*table_perturb), GFP_KERNEL); - if (!table_perturb) - panic("TCP: failed to alloc table_perturb"); + table_perturb = alloc_large_system_hash("Table-perturb", + sizeof(*table_perturb), + INET_TABLE_PERTURB_SIZE, + 0, 0, NULL, NULL, + INET_TABLE_PERTURB_SIZE, + INET_TABLE_PERTURB_SIZE); } int inet_hashinfo2_init_mod(struct inet_hashinfo *h) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7e474a85deaf..3b9cd487075a 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -629,21 +629,20 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { - const int pull_len = tunnel->hlen + sizeof(struct iphdr); - if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - if (pull_len > skb_transport_offset(skb)) - goto free_skb; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing * to gre header. */ - skb_pull(skb, pull_len); + skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); skb_reset_mac_header(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start(skb) < skb->data) + goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9984d23a7f3e..028513d3e2a2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4604,12 +4604,6 @@ void __init tcp_init(void) SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); - tcp_hashinfo.bind2_bucket_cachep = - kmem_cache_create("tcp_bind2_bucket", - sizeof(struct inet_bind2_bucket), 0, - SLAB_HWCACHE_ALIGN | SLAB_PANIC | - SLAB_ACCOUNT, - NULL); /* Size and allocate the main established and bind bucket * hash tables. @@ -4632,9 +4626,8 @@ void __init tcp_init(void) if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = - alloc_large_system_hash("TCP bind bhash tables", - sizeof(struct inet_bind_hashbucket) + - sizeof(struct inet_bind2_hashbucket), + alloc_large_system_hash("TCP bind", + sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, 17, /* one slot per 128 KB of memory */ 0, @@ -4643,12 +4636,9 @@ void __init tcp_init(void) 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; - tcp_hashinfo.bhash2 = - (struct inet_bind2_hashbucket *)(tcp_hashinfo.bhash + tcp_hashinfo.bhash_size); for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); - INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3231af73e430..2e2a9ece9af2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2706,12 +2706,15 @@ static void tcp_mtup_probe_success(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + u64 val; - /* FIXME: breaks with very large cwnd */ tp->prior_ssthresh = tcp_current_ssthresh(sk); - tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) * - tcp_mss_to_mtu(sk, tp->mss_cache) / - icsk->icsk_mtup.probe_size); + + val = (u64)tcp_snd_cwnd(tp) * tcp_mss_to_mtu(sk, tp->mss_cache); + do_div(val, icsk->icsk_mtup.probe_size); + DEBUG_NET_WARN_ON_ONCE((u32)val != val); + tcp_snd_cwnd_set(tp, max_t(u32, 1U, val)); + tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_ssthresh = tcp_current_ssthresh(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index dac2650f3863..fe8f23b95d32 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1207,8 +1207,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key->l3index = l3index; key->flags = flags; memcpy(&key->addr, addr, - (family == AF_INET6) ? sizeof(struct in6_addr) : - sizeof(struct in_addr)); + (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) ? sizeof(struct in6_addr) : + sizeof(struct in_addr)); hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b4b2284ed4a2..1c054431e358 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -4115,8 +4115,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { - __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); if (unlikely(tcp_passive_fastopen(sk))) tcp_sk(sk)->total_retrans++; trace_tcp_retransmit_synack(sk, req); diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index 2fe5860c21d6..b146ce88c5d0 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -304,4 +304,3 @@ void __init xfrm4_protocol_init(void) { xfrm_input_register_afinfo(&xfrm4_input_afinfo); } -EXPORT_SYMBOL(xfrm4_protocol_init); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ca0aa744593e..1b1932502e9e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5586,7 +5586,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; - array[DEVCONF_ACCEPT_UNSOLICITED_NA] = cnf->accept_unsolicited_na; + array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; } static inline size_t inet6_ifla6_size(void) @@ -7038,8 +7038,8 @@ static const struct ctl_table addrconf_sysctl[] = { .extra2 = (void *)SYSCTL_ONE, }, { - .procname = "accept_unsolicited_na", - .data = &ipv6_devconf.accept_unsolicited_na, + .procname = "accept_untracked_na", + .data = &ipv6_devconf.accept_untracked_na, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 4081b12a01ff..77e3f5970ce4 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1450,7 +1450,7 @@ static int __ip6_append_data(struct sock *sk, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; @@ -1798,7 +1798,7 @@ error: int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags) { @@ -1995,7 +1995,7 @@ EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork) { diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 254addad0dd3..b0dfe97ea4ee 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -979,7 +979,7 @@ static void ndisc_recv_na(struct sk_buff *skb) struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; - bool create_neigh; + u8 new_state; if (skb->len < sizeof(struct nd_msg)) { ND_PRINTK(2, warn, "NA: packet too short\n"); @@ -1000,7 +1000,7 @@ static void ndisc_recv_na(struct sk_buff *skb) /* For some 802.11 wireless deployments (and possibly other networks), * there will be a NA proxy and unsolicitd packets are attacks * and thus should not be accepted. - * drop_unsolicited_na takes precedence over accept_unsolicited_na + * drop_unsolicited_na takes precedence over accept_untracked_na */ if (!msg->icmph.icmp6_solicited && idev && idev->cnf.drop_unsolicited_na) @@ -1041,25 +1041,33 @@ static void ndisc_recv_na(struct sk_buff *skb) in6_ifa_put(ifp); return; } + + neigh = neigh_lookup(&nd_tbl, &msg->target, dev); + /* RFC 9131 updates original Neighbour Discovery RFC 4861. - * An unsolicited NA can now create a neighbour cache entry - * on routers if it has Target LL Address option. + * NAs with Target LL Address option without a corresponding + * entry in the neighbour cache can now create a STALE neighbour + * cache entry on routers. + * + * entry accept fwding solicited behaviour + * ------- ------ ------ --------- ---------------------- + * present X X 0 Set state to STALE + * present X X 1 Set state to REACHABLE + * absent 0 X X Do nothing + * absent 1 0 X Do nothing + * absent 1 1 X Add a new STALE entry * - * drop accept fwding behaviour - * ---- ------ ------ ---------------------------------------------- - * 1 X X Drop NA packet and don't pass up the stack - * 0 0 X Pass NA packet up the stack, don't update NC - * 0 1 0 Pass NA packet up the stack, don't update NC - * 0 1 1 Pass NA packet up the stack, and add a STALE - * NC entry * Note that we don't do a (daddr == all-routers-mcast) check. */ - create_neigh = !msg->icmph.icmp6_solicited && lladdr && - idev && idev->cnf.forwarding && - idev->cnf.accept_unsolicited_na; - neigh = __neigh_lookup(&nd_tbl, &msg->target, dev, create_neigh); + new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; + if (!neigh && lladdr && + idev && idev->cnf.forwarding && + idev->cnf.accept_untracked_na) { + neigh = neigh_create(&nd_tbl, &msg->target, dev); + new_state = NUD_STALE; + } - if (neigh) { + if (neigh && !IS_ERR(neigh)) { u8 old_flags = neigh->flags; struct net *net = dev_net(dev); @@ -1079,7 +1087,7 @@ static void ndisc_recv_na(struct sk_buff *skb) } ndisc_update(dev, neigh, lladdr, - msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE, + new_state, NEIGH_UPDATE_F_WEAK_OVERRIDE| (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index ff033d16549e..ecf3a553a0dc 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -101,6 +101,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_oif = oif; + if (msg->msg_controllen) { struct ipv6_txoptions opt = {}; @@ -112,17 +115,14 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return err; /* Changes to txoptions and flow info are not implemented, yet. - * Drop the options, fl6 is wiped below. + * Drop the options. */ ipc6.opt = NULL; } - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; - fl6.flowi6_oif = oif; fl6.flowi6_mark = ipc6.sockc.mark; fl6.flowi6_uid = sk->sk_uid; fl6.fl6_icmp_type = user_icmph.icmp6_type; diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 29bc4e7c3046..6de01185cc68 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -399,7 +399,6 @@ int __init seg6_hmac_init(void) { return seg6_hmac_init_algo(); } -EXPORT_SYMBOL(seg6_hmac_init); int __net_init seg6_hmac_net_init(struct net *net) { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 9fbe243a0e81..98a34287439c 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -218,6 +218,7 @@ seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, struct flowi6 fl6; int dev_flags = 0; + memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_iif = skb->dev->ifindex; fl6.daddr = nhaddr ? *nhaddr : hdr->daddr; fl6.saddr = hdr->saddr; diff --git a/net/key/af_key.c b/net/key/af_key.c index 11e1a3a3e442..fb16d7c4e1b8 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2826,10 +2826,12 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); - if (err) - return err; + /* Non-zero return value of pfkey_broadcast() does not always signal + * an error and even on an actual error we may still want to process + * the message so rather ignore the return value. + */ + pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, + BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index c6ff8bf9b55f..9dbd801ddb98 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -504,14 +504,15 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int transhdrlen = 4; /* zero session-id */ - int ulen = len + transhdrlen; + int ulen; int err; /* Rough check on arithmetic overflow, * better check is made in ip6_append_data(). */ - if (len > INT_MAX) + if (len > INT_MAX - transhdrlen) return -EMSGSIZE; + ulen = len + transhdrlen; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index e3452445b363..d8246e00a10b 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1749,12 +1749,9 @@ int ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata) if (new_ctx->replace_state == IEEE80211_CHANCTX_REPLACE_NONE) { if (old_ctx) - err = ieee80211_vif_use_reserved_reassign(sdata); - else - err = ieee80211_vif_use_reserved_assign(sdata); + return ieee80211_vif_use_reserved_reassign(sdata); - if (err) - return err; + return ieee80211_vif_use_reserved_assign(sdata); } /* diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 12fc9cda4a2c..51144fc66889 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -222,12 +222,18 @@ err_register: } static void nft_netdev_unregister_hooks(struct net *net, - struct list_head *hook_list) + struct list_head *hook_list, + bool release_netdev) { - struct nft_hook *hook; + struct nft_hook *hook, *next; - list_for_each_entry(hook, hook_list, list) + list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); + if (release_netdev) { + list_del(&hook->list); + kfree_rcu(hook, rcu); + } + } } static int nf_tables_register_hook(struct net *net, @@ -253,9 +259,10 @@ static int nf_tables_register_hook(struct net *net, return nf_register_net_hook(net, &basechain->ops); } -static void nf_tables_unregister_hook(struct net *net, - const struct nft_table *table, - struct nft_chain *chain) +static void __nf_tables_unregister_hook(struct net *net, + const struct nft_table *table, + struct nft_chain *chain, + bool release_netdev) { struct nft_base_chain *basechain; const struct nf_hook_ops *ops; @@ -270,11 +277,19 @@ static void nf_tables_unregister_hook(struct net *net, return basechain->type->ops_unregister(net, ops); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) - nft_netdev_unregister_hooks(net, &basechain->hook_list); + nft_netdev_unregister_hooks(net, &basechain->hook_list, + release_netdev); else nf_unregister_net_hook(net, &basechain->ops); } +static void nf_tables_unregister_hook(struct net *net, + const struct nft_table *table, + struct nft_chain *chain) +{ + return __nf_tables_unregister_hook(net, table, chain, false); +} + static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -529,6 +544,7 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); + INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); @@ -1899,7 +1915,6 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, goto err_hook_dev; } hook->ops.dev = dev; - hook->inactive = false; return hook; @@ -2151,7 +2166,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; if (chain->flags & NFT_CHAIN_HW_OFFLOAD && - nft_chain_offload_priority(basechain) < 0) + !nft_chain_offload_support(basechain)) return -EOPNOTSUPP; flow_block_init(&basechain->flow_block); @@ -2873,27 +2888,31 @@ static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err = nf_tables_expr_parse(ctx, nla, &expr_info); if (err < 0) - goto err1; + goto err_expr_parse; + + err = -EOPNOTSUPP; + if (!(expr_info.ops->type->flags & NFT_EXPR_STATEFUL)) + goto err_expr_stateful; err = -ENOMEM; expr = kzalloc(expr_info.ops->size, GFP_KERNEL_ACCOUNT); if (expr == NULL) - goto err2; + goto err_expr_stateful; err = nf_tables_newexpr(ctx, &expr_info, expr); if (err < 0) - goto err3; + goto err_expr_new; return expr; -err3: +err_expr_new: kfree(expr); -err2: +err_expr_stateful: owner = expr_info.ops->type->owner; if (expr_info.ops->type->release_ops) expr_info.ops->type->release_ops(expr_info.ops); module_put(owner); -err1: +err_expr_parse: return ERR_PTR(err); } @@ -4242,6 +4261,9 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, u32 len; int err; + if (desc->field_count >= ARRAY_SIZE(desc->field_len)) + return -E2BIG; + err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, nft_concat_policy, NULL); if (err < 0) @@ -4251,9 +4273,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, return -EINVAL; len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); - - if (len * BITS_PER_BYTE / 32 > NFT_REG32_COUNT) - return -E2BIG; + if (!len || len > U8_MAX) + return -EINVAL; desc->field_len[desc->field_count++] = len; @@ -4264,7 +4285,8 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { struct nlattr *attr; - int rem, err; + u32 num_regs = 0; + int rem, err, i; nla_for_each_nested(attr, nla, rem) { if (nla_type(attr) != NFTA_LIST_ELEM) @@ -4275,6 +4297,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, return err; } + for (i = 0; i < desc->field_count; i++) + num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + + if (num_regs > NFT_REG32_COUNT) + return -E2BIG; + return 0; } @@ -5344,8 +5372,10 @@ static int nf_tables_getsetelem(struct sk_buff *skb, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&ctx, set, attr); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); break; + } } return err; @@ -5413,9 +5443,6 @@ struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, return expr; err = -EOPNOTSUPP; - if (!(expr->ops->type->flags & NFT_EXPR_STATEFUL)) - goto err_set_elem_expr; - if (expr->ops->type->flags & NFT_EXPR_GC) { if (set->flags & NFT_SET_TIMEOUT) goto err_set_elem_expr; @@ -6125,8 +6152,10 @@ static int nf_tables_newsetelem(struct sk_buff *skb, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); return err; + } } if (nft_net->validate_state == NFT_VALIDATE_DO) @@ -6396,8 +6425,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_del_setelem(&ctx, set, attr); - if (err < 0) + if (err < 0) { + NL_SET_BAD_ATTR(extack, attr); break; + } } return err; } @@ -7291,13 +7322,25 @@ static void nft_unregister_flowtable_hook(struct net *net, FLOW_BLOCK_UNBIND); } -static void nft_unregister_flowtable_net_hooks(struct net *net, - struct list_head *hook_list) +static void __nft_unregister_flowtable_net_hooks(struct net *net, + struct list_head *hook_list, + bool release_netdev) { - struct nft_hook *hook; + struct nft_hook *hook, *next; - list_for_each_entry(hook, hook_list, list) + list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); + if (release_netdev) { + list_del(&hook->list); + kfree_rcu(hook, rcu); + } + } +} + +static void nft_unregister_flowtable_net_hooks(struct net *net, + struct list_head *hook_list) +{ + __nft_unregister_flowtable_net_hooks(net, hook_list, false); } static int nft_register_flowtable_net_hooks(struct net *net, @@ -7390,11 +7433,15 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, if (nla[NFTA_FLOWTABLE_FLAGS]) { flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); - if (flags & ~NFT_FLOWTABLE_MASK) - return -EOPNOTSUPP; + if (flags & ~NFT_FLOWTABLE_MASK) { + err = -EOPNOTSUPP; + goto err_flowtable_update_hook; + } if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^ - (flags & NFT_FLOWTABLE_HW_OFFLOAD)) - return -EOPNOTSUPP; + (flags & NFT_FLOWTABLE_HW_OFFLOAD)) { + err = -EOPNOTSUPP; + goto err_flowtable_update_hook; + } } else { flags = flowtable->data.flags; } @@ -7575,6 +7622,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; + LIST_HEAD(flowtable_del_list); struct nft_hook *this, *hook; struct nft_trans *trans; int err; @@ -7590,7 +7638,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, err = -ENOENT; goto err_flowtable_del_hook; } - hook->inactive = true; + list_move(&hook->list, &flowtable_del_list); } trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE, @@ -7603,6 +7651,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); + list_splice(&flowtable_del_list, &nft_trans_flowtable_hooks(trans)); nft_flowtable_hook_release(&flowtable_hook); nft_trans_commit_list_add_tail(ctx->net, trans); @@ -7610,13 +7659,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, return 0; err_flowtable_del_hook: - list_for_each_entry(this, &flowtable_hook.list, list) { - hook = nft_hook_list_find(&flowtable->hook_list, this); - if (!hook) - break; - - hook->inactive = false; - } + list_splice(&flowtable_del_list, &flowtable->hook_list); nft_flowtable_hook_release(&flowtable_hook); return err; @@ -8286,6 +8329,9 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: @@ -8520,17 +8566,6 @@ void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } -static void nft_flowtable_hooks_del(struct nft_flowtable *flowtable, - struct list_head *hook_list) -{ - struct nft_hook *hook, *next; - - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - if (hook->inactive) - list_move(&hook->list, hook_list); - } -} - static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -8785,6 +8820,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_NEWRULE); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_DELRULE: @@ -8875,8 +8913,6 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELFLOWTABLE: if (nft_trans_flowtable_update(trans)) { - nft_flowtable_hooks_del(nft_trans_flowtable(trans), - &nft_trans_flowtable_hooks(trans)); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), @@ -8957,7 +8993,6 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; struct nft_trans_elem *te; - struct nft_hook *hook; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) @@ -9088,8 +9123,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELFLOWTABLE: if (nft_trans_flowtable_update(trans)) { - list_for_each_entry(hook, &nft_trans_flowtable(trans)->hook_list, list) - hook->inactive = false; + list_splice(&nft_trans_flowtable_hooks(trans), + &nft_trans_flowtable(trans)->hook_list); } else { trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); @@ -9739,9 +9774,10 @@ static void __nft_release_hook(struct net *net, struct nft_table *table) struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) - nf_tables_unregister_hook(net, table, chain); + __nf_tables_unregister_hook(net, table, chain, true); list_for_each_entry(flowtable, &table->flowtables, list) - nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list); + __nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list, + true); } static void __nft_release_hooks(struct net *net) @@ -9880,7 +9916,11 @@ static int __net_init nf_tables_init_net(struct net *net) static void __net_exit nf_tables_pre_exit_net(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); + + mutex_lock(&nft_net->commit_mutex); __nft_release_hooks(net); + mutex_unlock(&nft_net->commit_mutex); } static void __net_exit nf_tables_exit_net(struct net *net) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 2d36952b1392..910ef881c3b8 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -208,7 +208,7 @@ static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, return 0; } -int nft_chain_offload_priority(struct nft_base_chain *basechain) +static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) @@ -217,6 +217,27 @@ int nft_chain_offload_priority(struct nft_base_chain *basechain) return 0; } +bool nft_chain_offload_support(const struct nft_base_chain *basechain) +{ + struct net_device *dev; + struct nft_hook *hook; + + if (nft_chain_offload_priority(basechain) < 0) + return false; + + list_for_each_entry(hook, &basechain->hook_list, list) { + if (hook->ops.pf != NFPROTO_NETDEV || + hook->ops.hooknum != NF_NETDEV_INGRESS) + return false; + + dev = hook->ops.dev; + if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) + return false; + } + + return true; +} + static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index ad3bbe34ca88..2f7c477fc9e7 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -45,7 +45,6 @@ MODULE_DESCRIPTION("Netfilter messages via netlink socket"); static unsigned int nfnetlink_pernet_id __read_mostly; struct nfnl_net { - unsigned int ctnetlink_listeners; struct sock *nfnl; }; @@ -673,18 +672,8 @@ static int nfnetlink_bind(struct net *net, int group) #ifdef CONFIG_NF_CONNTRACK_EVENTS if (type == NFNL_SUBSYS_CTNETLINK) { - struct nfnl_net *nfnlnet = nfnl_pernet(net); - nfnl_lock(NFNL_SUBSYS_CTNETLINK); - - if (WARN_ON_ONCE(nfnlnet->ctnetlink_listeners == UINT_MAX)) { - nfnl_unlock(NFNL_SUBSYS_CTNETLINK); - return -EOVERFLOW; - } - - nfnlnet->ctnetlink_listeners++; - if (nfnlnet->ctnetlink_listeners == 1) - WRITE_ONCE(net->ct.ctnetlink_has_listener, true); + WRITE_ONCE(net->ct.ctnetlink_has_listener, true); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); } #endif @@ -694,15 +683,12 @@ static int nfnetlink_bind(struct net *net, int group) static void nfnetlink_unbind(struct net *net, int group) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - int type = nfnl_group2type[group]; - - if (type == NFNL_SUBSYS_CTNETLINK) { - struct nfnl_net *nfnlnet = nfnl_pernet(net); + if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) + return; + if (nfnl_group2type[group] == NFNL_SUBSYS_CTNETLINK) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); - WARN_ON_ONCE(nfnlnet->ctnetlink_listeners == 0); - nfnlnet->ctnetlink_listeners--; - if (nfnlnet->ctnetlink_listeners == 0) + if (!nfnetlink_has_listeners(net, group)) WRITE_ONCE(net->ct.ctnetlink_has_listener, false); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index f069c24c6146..af15102bc696 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -35,12 +35,13 @@ static unsigned int nfct_timeout_id __read_mostly; struct ctnl_timeout { struct list_head head; + struct list_head free_head; struct rcu_head rcu_head; refcount_t refcnt; char name[CTNL_TIMEOUT_NAME_MAX]; - struct nf_ct_timeout timeout; - struct list_head free_head; + /* must be at the end */ + struct nf_ct_timeout timeout; }; struct nfct_timeout_pernet { diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a16cf47199b7..a25c88bc8b75 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -232,19 +232,21 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, switch (nft_pf(pkt)) { case NFPROTO_IPV4: fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; - fl.u.ip4.saddr = ct->tuplehash[dir].tuple.dst.u3.ip; + fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; fl.u.ip4.flowi4_tos = RT_TOS(ip_hdr(pkt->skb)->tos); fl.u.ip4.flowi4_mark = pkt->skb->mark; + fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; case NFPROTO_IPV6: fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; - fl.u.ip6.saddr = ct->tuplehash[dir].tuple.dst.u3.in6; + fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.src.u3.in6; fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; fl.u.ip6.flowi6_iif = this_dst->dev->ifindex; fl.u.ip6.flowlabel = ip6_flowinfo(ipv6_hdr(pkt->skb)); fl.u.ip6.flowi6_mark = pkt->skb->mark; + fl.u.ip6.flowi6_flags = FLOWI_FLAG_ANYSRC; break; } diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 04ea8b9bf202..981addb2d051 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -213,6 +213,8 @@ static int nft_limit_pkts_clone(struct nft_expr *dst, const struct nft_expr *src struct nft_limit_priv_pkts *priv_dst = nft_expr_priv(dst); struct nft_limit_priv_pkts *priv_src = nft_expr_priv(src); + priv_dst->cost = priv_src->cost; + return nft_limit_clone(&priv_dst->limit, &priv_src->limit); } diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 4394df4bc99b..e5fd6995e4bf 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -335,7 +335,8 @@ static void nft_nat_inet_eval(const struct nft_expr *expr, { const struct nft_nat *priv = nft_expr_priv(expr); - if (priv->family == nft_pf(pkt)) + if (priv->family == nft_pf(pkt) || + priv->family == NFPROTO_INET) nft_nat_eval(expr, regs, pkt); } diff --git a/net/nfc/core.c b/net/nfc/core.c index 6ff3e10ff8e3..eb2c0959e5b6 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -975,7 +975,7 @@ static void nfc_release(struct device *d) kfree(se); } - ida_simple_remove(&nfc_index_ida, dev->idx); + ida_free(&nfc_index_ida, dev->idx); kfree(dev); } @@ -1066,7 +1066,7 @@ struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, if (!dev) return NULL; - rc = ida_simple_get(&nfc_index_ida, 0, 0, GFP_KERNEL); + rc = ida_alloc(&nfc_index_ida, GFP_KERNEL); if (rc < 0) goto err_free_dev; dev->idx = rc; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 1b5d73079dc9..868db4669a29 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -373,6 +373,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, update_ip_l4_checksum(skb, nh, *addr, new_addr); csum_replace4(&nh->check, *addr, new_addr); skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); *addr = new_addr; } @@ -420,6 +421,7 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, update_ipv6_checksum(skb, l4_proto, addr, new_addr); skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); memcpy(addr, new_addr, sizeof(__be32[4])); } @@ -660,6 +662,7 @@ static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) { + ovs_ct_clear(skb, NULL); inet_proto_csum_replace2(check, skb, *port, new_port, false); *port = new_port; } @@ -699,6 +702,7 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key, uh->dest = dst; flow_key->tp.src = src; flow_key->tp.dst = dst; + ovs_ct_clear(skb, NULL); } skb_clear_hash(skb); @@ -761,6 +765,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, sh->checksum = old_csum ^ old_correct_csum ^ new_csum; skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); + flow_key->tp.src = sh->source; flow_key->tp.dst = sh->dest; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 4a947c13c813..4e70df91d0f2 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1342,7 +1342,9 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - ovs_ct_fill_key(skb, key, false); + + if (key) + ovs_ct_fill_key(skb, key, false); return 0; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 677f9cfa9660..ca6e92a22923 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1935,8 +1935,10 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) - skb_set_network_header(skb, depth); + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) { + if (pskb_may_pull(skb, depth)) + skb_set_network_header(skb, depth); + } skb_probe_transport_header(skb); } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 8af9d6e5ba61..e013253b10d1 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -548,7 +548,7 @@ tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb, break; #endif default: - return -1; + return false; } if (ip6h->hop_limit <= 1) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a201bf29af98..433bb5a7df31 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2161,6 +2161,7 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, not_found: ini->smcr_version &= ~SMC_V2; + ini->smcrv2.ib_dev_v2 = NULL; ini->check_smcrv2 = false; } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 5c731f27996e..53f63bfbaf5f 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -82,7 +82,7 @@ int smc_cdc_get_free_slot(struct smc_connection *conn, /* abnormal termination */ if (!rc) smc_wr_tx_put_slot(link, - (struct smc_wr_tx_pend_priv *)pend); + (struct smc_wr_tx_pend_priv *)(*pend)); rc = -EPIPE; } return rc; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index df194cc07035..f87a2d8f23a7 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -919,7 +919,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, EXPORT_SYMBOL_GPL(xdr_init_encode); /** - * xdr_commit_encode - Ensure all data is written to buffer + * __xdr_commit_encode - Ensure all data is written to buffer * @xdr: pointer to xdr_stream * * We handle encoding across page boundaries by giving the caller a @@ -931,26 +931,29 @@ EXPORT_SYMBOL_GPL(xdr_init_encode); * required at the end of encoding, or any other time when the xdr_buf * data might be read. */ -inline void xdr_commit_encode(struct xdr_stream *xdr) +void __xdr_commit_encode(struct xdr_stream *xdr) { - int shift = xdr->scratch.iov_len; + size_t shift = xdr->scratch.iov_len; void *page; - if (shift == 0) - return; page = page_address(*xdr->page_ptr); memcpy(xdr->scratch.iov_base, page, shift); memmove(page, page + shift, (void *)xdr->p - page); xdr_reset_scratch_buffer(xdr); } -EXPORT_SYMBOL_GPL(xdr_commit_encode); +EXPORT_SYMBOL_GPL(__xdr_commit_encode); -static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, - size_t nbytes) +/* + * The buffer space to be reserved crosses the boundary between + * xdr->buf->head and xdr->buf->pages, or between two pages + * in xdr->buf->pages. + */ +static noinline __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, + size_t nbytes) { - __be32 *p; int space_left; int frag1bytes, frag2bytes; + void *p; if (nbytes > PAGE_SIZE) goto out_overflow; /* Bigger buffers require special handling */ @@ -964,6 +967,7 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, xdr->buf->page_len += frag1bytes; xdr->page_ptr++; xdr->iov = NULL; + /* * If the last encode didn't end exactly on a page boundary, the * next one will straddle boundaries. Encode into the next @@ -972,14 +976,19 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, * space at the end of the previous buffer: */ xdr_set_scratch_buffer(xdr, xdr->p, frag1bytes); - p = page_address(*xdr->page_ptr); + /* - * Note this is where the next encode will start after we've - * shifted this one back: + * xdr->p is where the next encode will start after + * xdr_commit_encode() has shifted this one back: */ - xdr->p = (void *)p + frag2bytes; + p = page_address(*xdr->page_ptr); + xdr->p = p + frag2bytes; space_left = xdr->buf->buflen - xdr->buf->len; - xdr->end = (void *)p + min_t(int, space_left, PAGE_SIZE); + if (space_left - nbytes >= PAGE_SIZE) + xdr->end = p + PAGE_SIZE; + else + xdr->end = p + space_left - frag1bytes; + xdr->buf->page_len += frag2bytes; xdr->buf->len += nbytes; return p; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 5f0155fdefc7..11cf7c646644 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -478,10 +478,10 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, unsigned int write_len; u64 offset; - seg = &info->wi_chunk->ch_segments[info->wi_seg_no]; - if (!seg) + if (info->wi_seg_no >= info->wi_chunk->ch_segcount) goto out_overflow; + seg = &info->wi_chunk->ch_segments[info->wi_seg_no]; write_len = min(remaining, seg->rs_length - info->wi_seg_off); if (!write_len) goto out_overflow; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 6d39ca05f249..932c87b98eca 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -259,9 +259,8 @@ static int tipc_enable_bearer(struct net *net, const char *name, u32 i; if (!bearer_name_validate(name, &b_names)) { - errstr = "illegal name"; NL_SET_ERR_MSG(extack, "Illegal name"); - goto rejected; + return res; } if (prio > TIPC_MAX_LINK_PRI && prio != TIPC_MEDIA_LINK_PRI) { diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b91ddc110786..da176411c1b5 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -544,7 +544,7 @@ static int do_tls_getsockopt(struct sock *sk, int optname, rc = do_tls_getsockopt_conf(sk, optval, optlen, optname == TLS_TX); break; - case TLS_TX_ZEROCOPY_SENDFILE: + case TLS_TX_ZEROCOPY_RO: rc = do_tls_getsockopt_tx_zc(sk, optval, optlen); break; default: @@ -731,7 +731,7 @@ static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, optname == TLS_TX); release_sock(sk); break; - case TLS_TX_ZEROCOPY_SENDFILE: + case TLS_TX_ZEROCOPY_RO: lock_sock(sk); rc = do_tls_setsockopt_tx_zc(sk, optval, optlen); release_sock(sk); @@ -970,7 +970,7 @@ static int tls_get_info(const struct sock *sk, struct sk_buff *skb) goto nla_failure; if (ctx->tx_conf == TLS_HW && ctx->zerocopy_sendfile) { - err = nla_put_flag(skb, TLS_INFO_ZC_SENDFILE); + err = nla_put_flag(skb, TLS_INFO_ZC_RO_TX); if (err) goto nla_failure; } @@ -994,7 +994,7 @@ static size_t tls_get_info_size(const struct sock *sk) nla_total_size(sizeof(u16)) + /* TLS_INFO_CIPHER */ nla_total_size(sizeof(u16)) + /* TLS_INFO_RXCONF */ nla_total_size(sizeof(u16)) + /* TLS_INFO_TXCONF */ - nla_total_size(0) + /* TLS_INFO_ZC_SENDFILE */ + nla_total_size(0) + /* TLS_INFO_ZC_RO_TX */ 0; return size; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 654dcef7cfb3..2206e6f8902d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -490,7 +490,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) * -ECONNREFUSED. Otherwise, if we haven't queued any skbs * to other and its full, we will hang waiting for POLLOUT. */ - if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD)) + if (unix_recvq_full_lockless(other) && !sock_flag(other, SOCK_DEAD)) return 1; if (connected) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index e0a4526ab66b..19ac872a6624 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -373,7 +373,8 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries) goto out; } - nb_pkts = xskq_cons_peek_desc_batch(xs->tx, pool, max_entries); + max_entries = xskq_cons_nb_entries(xs->tx, max_entries); + nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, max_entries); if (!nb_pkts) { xs->tx->queue_empty_descs++; goto out; @@ -389,7 +390,7 @@ u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max_entries) if (!nb_pkts) goto out; - xskq_cons_release_n(xs->tx, nb_pkts); + xskq_cons_release_n(xs->tx, max_entries); __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index a794410989cc..fb20bf7207cf 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -282,14 +282,6 @@ static inline bool xskq_cons_peek_desc(struct xsk_queue *q, return xskq_cons_read_desc(q, desc, pool); } -static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, - u32 max) -{ - u32 entries = xskq_cons_nb_entries(q, max); - - return xskq_cons_read_desc_batch(q, pool, entries); -} - /* To improve performance in the xskq_cons_release functions, only update local state here. * Reflect this to global state when we get new entries from the ring in * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop. diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index d4935b3b9983..555ab35cd119 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -273,6 +273,7 @@ static int xfrm4_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb) */ static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb) { + bool small_ipv6 = (skb->protocol == htons(ETH_P_IPV6)) && (skb->len <= IPV6_MIN_MTU); struct dst_entry *dst = skb_dst(skb); struct iphdr *top_iph; int flags; @@ -303,7 +304,7 @@ static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb) if (flags & XFRM_STATE_NOECN) IP_ECN_clear(top_iph); - top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? + top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) || small_ipv6 ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst)); |