diff options
Diffstat (limited to 'net')
117 files changed, 2543 insertions, 713 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 82a116ba590e..8de138d3306b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,7 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; + vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 4acb1d5417aa..f24b25c25106 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -507,8 +507,8 @@ err_out: /* wakeup anybody waiting for slots to pin pages */ wake_up(&vp_wq); } - kfree(in_pages); - kfree(out_pages); + kvfree(in_pages); + kvfree(out_pages); return err; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ece45e0683fd..0b5f729d08d2 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -250,7 +250,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index c045b3c54768..b0e23dfc5c34 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -262,6 +262,8 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, break; } + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; hdev->req_status = hdev->req_result = 0; BT_DBG("%s end: err %d", hdev->name, err); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 6ef8a01a9ad4..96f04b7b9556 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1091,7 +1091,7 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 54ceb1f2cc9a..d4cad29b033f 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -32,6 +32,7 @@ #include <linux/debugfs.h> #include <linux/crc16.h> +#include <linux/filter.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -5835,6 +5836,9 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, if (chan->sdu) break; + if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE)) + break; + chan->sdu_len = get_unaligned_le16(skb->data); skb_pull(skb, L2CAP_SDULEN_SIZE); @@ -6610,6 +6614,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } + if ((chan->mode == L2CAP_MODE_ERTM || + chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb)) + goto drop; + if (!control->sframe) { int err; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 1842141baedb..a8ba752732c9 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1019,7 +1019,7 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, goto done; if (pi->rx_busy_skb) { - if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb)) + if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb)) pi->rx_busy_skb = NULL; else goto done; @@ -1270,7 +1270,17 @@ static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) goto done; } - err = sock_queue_rcv_skb(sk, skb); + if (chan->mode != L2CAP_MODE_ERTM && + chan->mode != L2CAP_MODE_STREAMING) { + /* Even if no filter is attached, we could potentially + * get errors from security modules, etc. + */ + err = sk_filter(sk, skb); + if (err) + goto done; + } + + err = __sock_queue_rcv_skb(sk, skb); /* For ERTM, handle one skb that doesn't fit into the recv * buffer. This is important to do because the data frames diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c18080ad4085..cd620fab41b0 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -267,7 +267,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) /* If old entry was unassociated with any port, then delete it. */ f = __br_fdb_get(br, br->dev->dev_addr, 0); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); @@ -282,7 +282,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) if (!br_vlan_should_use(v)) continue; f = __br_fdb_get(br, br->dev->dev_addr, v->vid); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, v->vid); } @@ -764,20 +764,25 @@ out: } /* Update (create or replace) forwarding database entry */ -static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, - __u16 state, __u16 flags, __u16 vid) +static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, + const __u8 *addr, __u16 state, __u16 flags, __u16 vid) { - struct net_bridge *br = source->br; struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; bool modified = false; /* If the port cannot learn allow only local and static entries */ - if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) && + if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) && !(source->state == BR_STATE_LEARNING || source->state == BR_STATE_FORWARDING)) return -EPERM; + if (!source && !(state & NUD_PERMANENT)) { + pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n", + br->dev->name); + return -EINVAL; + } + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -832,22 +837,28 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, return 0; } -static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, - const unsigned char *addr, u16 nlh_flags, u16 vid) +static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, + struct net_bridge_port *p, const unsigned char *addr, + u16 nlh_flags, u16 vid) { int err = 0; if (ndm->ndm_flags & NTF_USE) { + if (!p) { + pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n", + br->dev->name); + return -EINVAL; + } local_bh_disable(); rcu_read_lock(); - br_fdb_update(p->br, p, addr, vid, true); + br_fdb_update(br, p, addr, vid, true); rcu_read_unlock(); local_bh_enable(); } else { - spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, + spin_lock_bh(&br->hash_lock); + err = fdb_add_entry(br, p, addr, ndm->ndm_state, nlh_flags, vid); - spin_unlock_bh(&p->br->hash_lock); + spin_unlock_bh(&br->hash_lock); } return err; @@ -884,6 +895,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], dev->name); return -EINVAL; } + br = p->br; vg = nbp_vlan_group(p); } @@ -895,15 +907,9 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* VID was specified, so use it. */ - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid); } else { - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, 0); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0); if (err || !vg || !vg->num_vlans) goto out; @@ -914,11 +920,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], list_for_each_entry(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, v->vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, - v->vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid); if (err) goto out; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8e486203d133..abe11f085479 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -80,13 +80,10 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, BR_INPUT_SKB_CB(skb)->proxyarp_replied = false; - if (dev->flags & IFF_NOARP) + if ((dev->flags & IFF_NOARP) || + !pskb_may_pull(skb, arp_hdr_len(dev))) return; - if (!pskb_may_pull(skb, arp_hdr_len(dev))) { - dev->stats.tx_dropped++; - return; - } parp = arp_hdr(skb); if (parp->ar_pro != htons(ETH_P_IP) || diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index a5423a1eec05..c5fea9393946 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1138,7 +1138,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, } else { err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid); - if (!err) + if (err) break; } } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index cceac5bb658f..0833c251aef7 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -368,6 +368,8 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0); if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) { + if (!IS_ERR(match)) + module_put(match->me); request_module("ebt_%s", m->u.name); match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0); } diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index 4b901d9f2e7c..ad47a921b701 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -86,6 +86,7 @@ static const struct nft_expr_ops nft_meta_bridge_set_ops = { .init = nft_meta_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, + .validate = nft_meta_set_validate, }; static const struct nft_expr_ops * diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index c83326c5ba58..ef34a02719d7 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -574,7 +574,7 @@ static void complete_generic_request(struct ceph_mon_generic_request *req) put_generic_request(req); } -void cancel_generic_request(struct ceph_mon_generic_request *req) +static void cancel_generic_request(struct ceph_mon_generic_request *req) { struct ceph_mon_client *monc = req->monc; struct ceph_mon_generic_request *lookup_req; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b5ec09612ff7..a97e7b506612 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -4220,7 +4220,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); - if (!pages) { + if (IS_ERR(pages)) { ceph_msg_put(m); return NULL; } diff --git a/net/ceph/string_table.c b/net/ceph/string_table.c index ca53c8319209..22fb96efcf34 100644 --- a/net/ceph/string_table.c +++ b/net/ceph/string_table.c @@ -84,12 +84,6 @@ retry: } EXPORT_SYMBOL(ceph_find_or_create_string); -static void ceph_free_string(struct rcu_head *head) -{ - struct ceph_string *cs = container_of(head, struct ceph_string, rcu); - kfree(cs); -} - void ceph_release_string(struct kref *ref) { struct ceph_string *cs = container_of(ref, struct ceph_string, kref); @@ -101,7 +95,7 @@ void ceph_release_string(struct kref *ref) } spin_unlock(&string_tree_lock); - call_rcu(&cs->rcu, ceph_free_string); + kfree_rcu(cs, rcu); } EXPORT_SYMBOL(ceph_release_string); diff --git a/net/core/dev.c b/net/core/dev.c index 4ce07dc25573..ea6312057a71 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3975,6 +3975,22 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } /** + * netdev_is_rx_handler_busy - check if receive handler is registered + * @dev: device to check + * + * Check if a receive handler is already registered for a given device. + * Return true if there one. + * + * The caller must hold the rtnl_mutex. + */ +bool netdev_is_rx_handler_busy(struct net_device *dev) +{ + ASSERT_RTNL(); + return dev && rtnl_dereference(dev->rx_handler); +} +EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); + +/** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for * @rx_handler: receive handler to register @@ -6045,8 +6061,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)) +int dev_get_nest_level(struct net_device *dev) { struct net_device *lower = NULL; struct list_head *iter; @@ -6056,15 +6071,12 @@ int dev_get_nest_level(struct net_device *dev, ASSERT_RTNL(); netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower, type_check); + nest = dev_get_nest_level(lower); if (max_nest < nest) max_nest = nest; } - if (type_check(dev)) - max_nest++; - - return max_nest; + return max_nest + 1; } EXPORT_SYMBOL(dev_get_nest_level); diff --git a/net/core/filter.c b/net/core/filter.c index b5add4ef0d1d..cb06aceb512a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1355,13 +1355,9 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, { int err; - if (!skb_cloned(skb)) - return 0; - if (skb_clone_writable(skb, write_len)) - return 0; - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (!err) - bpf_compute_data_end(skb); + err = skb_ensure_writable(skb, write_len); + bpf_compute_data_end(skb); + return err; } @@ -1379,42 +1375,25 @@ static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) { - struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *from = (void *) (long) r3; unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; - - /* bpf verifier guarantees that: - * 'from' pointer points to bpf program stack - * 'len' bytes of it were initialized - * 'len' > 0 - * 'skb' is a valid pointer to 'struct sk_buff' - * - * so check for invalid 'offset' and too large 'len' - */ - if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff))) + if (unlikely(offset > 0xffff)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, len, sp->buff); - if (unlikely(!ptr)) - return -EFAULT; - + ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); - if (ptr == sp->buff) - /* skb_store_bits cannot return -EFAULT here */ - skb_store_bits(skb, offset, ptr, len); - if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) @@ -1437,12 +1416,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *to = (void *)(unsigned long) r3; unsigned int len = (unsigned int) r4; void *ptr; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); @@ -1470,20 +1449,17 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) { struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) - return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) @@ -1501,10 +1477,6 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; } - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -1524,20 +1496,18 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) - return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !*ptr) return 0; @@ -1560,10 +1530,6 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -2317,7 +2283,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) } #ifdef CONFIG_SOCK_CGROUP_DATA -static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *)(long)r1; struct bpf_map *map = (struct bpf_map *)(long)r2; @@ -2340,8 +2306,8 @@ static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp); } -static const struct bpf_func_proto bpf_skb_in_cgroup_proto = { - .func = bpf_skb_in_cgroup, +static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { + .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -2421,8 +2387,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; #ifdef CONFIG_SOCK_CGROUP_DATA - case BPF_FUNC_skb_in_cgroup: - return &bpf_skb_in_cgroup_proto; + case BPF_FUNC_skb_under_cgroup: + return &bpf_skb_under_cgroup_proto; #endif default: return sk_filter_func_proto(func_id); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 61ad43f61c5e..52742a02814f 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -680,11 +680,13 @@ EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; + u32 hash; __flow_hash_secret_init(); - __skb_set_sw_hash(skb, ___skb_get_hash(skb, &keys, hashrnd), - flow_keys_have_l4(&keys)); + hash = ___skb_get_hash(skb, &keys, hashrnd); + + __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 415e117967c7..062a67ca9a21 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2232,7 +2232,7 @@ static struct devinet_sysctl_table { }; static int __devinet_sysctl_register(struct net *net, char *dev_name, - struct ipv4_devconf *p) + int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; @@ -2255,6 +2255,8 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, goto free; p->sysctl = t; + + inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p); return 0; free: @@ -2286,7 +2288,7 @@ static int devinet_sysctl_register(struct in_device *idev) if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, - &idev->cnf); + idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; @@ -2347,11 +2349,12 @@ static __net_init int devinet_init_net(struct net *net) } #ifdef CONFIG_SYSCTL - err = __devinet_sysctl_register(net, "all", all); + err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; - err = __devinet_sysctl_register(net, "default", dflt); + err = __devinet_sysctl_register(net, "default", + NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ef2ebeb89d0f..1b25daf8c7f1 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -509,6 +509,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; + cfg->fc_table = l3mdev_fib_table(dev); if (colon) { struct in_ifaddr *ifa; struct in_device *in_dev = __in_dev_get_rtnl(dev); @@ -1027,7 +1028,7 @@ no_promotions: * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ - if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local)) + if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 539fa264e67d..e9f56225e53f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1057,6 +1057,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_priority = cfg->fc_priority; fi->fib_prefsrc = cfg->fc_prefsrc; fi->fib_type = cfg->fc_type; + fi->fib_tb_id = cfg->fc_table; fi->fib_nhs = nhs; change_nexthops(fi) { @@ -1337,18 +1338,21 @@ nla_put_failure: * referring to it. * - device went down -> we must shutdown all nexthops going via it. */ -int fib_sync_down_addr(struct net *net, __be32 local) +int fib_sync_down_addr(struct net_device *dev, __be32 local) { int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + struct net *net = dev_net(dev); + int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) return 0; hlist_for_each_entry(fi, head, fib_lhash) { - if (!net_eq(fi->fib_net, net)) + if (!net_eq(fi->fib_net, net) || + fi->fib_tb_id != tb_id) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index febca0f1008c..e2ffc2a5c7db 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -249,7 +249,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * - * The bits from (n->pos + n->bits) to (tn->pos - 1) - "S" - are skipped bits + * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest @@ -258,7 +258,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * - * The rest of the bits, from 0 to (n->pos + n->bits), are completely unknown + * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5b1481be0282..113cc43df789 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -370,7 +370,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->parms.o_flags, proto, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, proto); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 9d847c302551..0f227db0e9ac 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -73,9 +73,11 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && proto == IPPROTO_UDP) { - /* Arrived from an ingress interface and got udp encapuslated. - * The encapsulated network segment length may exceed dst mtu. + if (skb_iif && !(df & htons(IP_DF))) { + /* Arrived from an ingress interface, got encapsulated, with + * fragmentation of encapulating frames allowed. + * If skb is gso, the resulting encapsulated network segments + * may exceed dst mtu. * Allow IP Fragmentation of segments. */ IPCB(skb)->flags |= IPSKB_FRAG_SEGS; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index a917903d5e97..cc701fa70b12 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -557,6 +557,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +static bool is_vti_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti_netdev_ops; +} + +static int vti_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip_tunnel *tunnel = netdev_priv(dev); + + if (!is_vti_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(tunnel->net, dev_net(dev))) + xfrm_garbage_collect(tunnel->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti_notifier_block __read_mostly = { + .notifier_call = vti_device_event, +}; + static int __init vti_init(void) { const char *msg; @@ -564,6 +591,8 @@ static int __init vti_init(void) pr_info("IPv4 over IPsec tunneling driver\n"); + register_netdevice_notifier(&vti_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) @@ -596,6 +625,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti_notifier_block); pr_err("vti init: failed to register %s\n", msg); return err; } @@ -607,6 +637,7 @@ static void __exit vti_fini(void) xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); + unregister_netdevice_notifier(&vti_notifier_block); } module_init(vti_init); diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 2375b0a8be46..30493beb611a 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv, __be32 saddr, daddr; u_int8_t tos; const struct iphdr *iph; + int err; /* root is playing with raw sockets. */ if (skb->len < sizeof(struct iphdr) || @@ -46,15 +47,17 @@ static unsigned int nf_route_table_hook(void *priv, tos = iph->tos; ret = nft_do_chain(&pkt, priv); - if (ret != NF_DROP && ret != NF_QUEUE) { + if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || iph->daddr != daddr || skb->mark != mark || - iph->tos != tos) - if (ip_route_me_harder(state->net, skb, RTN_UNSPEC)) - ret = NF_DROP; + iph->tos != tos) { + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + if (err < 0) + ret = NF_DROP_ERR(err); + } } return ret; } diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index c24f41c816b3..2c2553b9026c 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -46,6 +46,7 @@ static const struct nft_expr_ops nft_reject_ipv4_ops = { .eval = nft_reject_ipv4_eval, .init = nft_reject_init, .dump = nft_reject_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_ipv4_type __read_mostly = { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 032a96d78c99..ffbb218de520 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3193,7 +3193,6 @@ int tcp_abort(struct sock *sk, int err) local_bh_enable(); return 0; } - sock_gen_put(sk); return -EOPNOTSUPP; } @@ -3222,7 +3221,6 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); release_sock(sk); - sock_put(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 4d610934fb39..a748c74aa8b7 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -54,11 +54,16 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req); + int err; if (IS_ERR(sk)) return PTR_ERR(sk); - return sock_diag_destroy(sk, ECONNABORTED); + err = sock_diag_destroy(sk, ECONNABORTED); + + sock_gen_put(sk); + + return err; } #endif diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 54d9f9b0120f..4e777a3243f9 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -150,6 +150,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) tp->segs_in = 0; tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); + sk_forced_mem_schedule(sk, skb->truesize); skb_set_owner_r(skb, sk); TCP_SKB_CB(skb)->seq++; @@ -226,6 +227,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, tcp_fastopen_add_skb(child, skb); tcp_rsk(req)->rcv_nxt = tp->rcv_nxt; + tp->rcv_wup = tp->rcv_nxt; /* tcp_conn_request() is sending the SYNACK, * and queues the child into listener accept queue. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 32b048e524d6..7158d4f8dae4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -814,8 +814,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v4_send_ack(sock_net(sk), skb, seq, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, 0, diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 028eb046ea40..9c5fc973267f 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -76,7 +76,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else if (!yeah->doing_reno_now) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e61f7cd65d08..5fdcb8d108d4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1182,13 +1182,13 @@ out: * @sk: socket * * Drops all bad checksum frames, until a valid one is found. - * Returns the length of found skb, or 0 if none is found. + * Returns the length of found skb, or -1 if none is found. */ -static unsigned int first_packet_length(struct sock *sk) +static int first_packet_length(struct sock *sk) { struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue; struct sk_buff *skb; - unsigned int res; + int res; __skb_queue_head_init(&list_kill); @@ -1203,7 +1203,7 @@ static unsigned int first_packet_length(struct sock *sk) __skb_unlink(skb, rcvq); __skb_queue_tail(&list_kill, skb); } - res = skb ? skb->len : 0; + res = skb ? skb->len : -1; spin_unlock_bh(&rcvq->lock); if (!skb_queue_empty(&list_kill)) { @@ -1232,7 +1232,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) case SIOCINQ: { - unsigned int amount = first_packet_length(sk); + int amount = max_t(int, 0, first_packet_length(sk)); return put_user(amount, (int __user *)arg); } @@ -2184,7 +2184,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Check for false positives due to checksum errors */ if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && - !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk)) + !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(POLLIN | POLLRDNORM); return mask; @@ -2216,7 +2216,6 @@ struct proto udp_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 3b3efbda48e1..2eea073e27ef 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -55,7 +55,6 @@ struct proto udplite_prot = { .unhash = udp_lib_unhash, .get_port = udp_v4_get_port, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index b644a23c3db0..41f5b504a782 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -29,7 +29,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; - fl4->flowi4_oif = oif; + fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif); if (saddr) fl4->saddr = saddr->a4; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ab3e796596b1..2f1f5d439788 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -778,7 +778,14 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) } if (p == &net->ipv6.devconf_all->forwarding) { + int old_dflt = net->ipv6.devconf_dflt->forwarding; + net->ipv6.devconf_dflt->forwarding = newf; + if ((!newf) ^ (!old_dflt)) + inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + addrconf_forward_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING, @@ -1872,7 +1879,6 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) void addrconf_dad_failure(struct inet6_ifaddr *ifp) { - struct in6_addr addr; struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(ifp->idev->dev); @@ -1934,18 +1940,6 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) in6_ifa_put(ifp2); lock_errdad: spin_lock_bh(&ifp->lock); - } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { - addr.s6_addr32[0] = htonl(0xfe800000); - addr.s6_addr32[1] = 0; - - if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && - ipv6_addr_equal(&ifp->addr, &addr)) { - /* DAD failed for link-local based on MAC address */ - idev->cnf.disable_ipv6 = 1; - - pr_info("%s: IPv6 being disabled!\n", - ifp->idev->dev->name); - } } errdad: @@ -1954,6 +1948,7 @@ errdad: spin_unlock_bh(&ifp->lock); addrconf_mod_dad_work(ifp, 0); + in6_ifa_put(ifp); } /* Join to solicited addr multicast group. @@ -3543,7 +3538,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - keep_addr = !(how || _keep_addr <= 0); + keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6); /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { @@ -3599,7 +3594,7 @@ restart: /* re-combine the user config with event to determine if permanent * addresses are to be removed from the interface list */ - keep_addr = (!how && _keep_addr > 0); + keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { @@ -3821,6 +3816,7 @@ static void addrconf_dad_work(struct work_struct *w) dad_work); struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; + bool disable_ipv6 = false; enum { DAD_PROCESS, @@ -3837,6 +3833,24 @@ static void addrconf_dad_work(struct work_struct *w) } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; + + if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 && + !(ifp->flags & IFA_F_STABLE_PRIVACY)) { + struct in6_addr addr; + + addr.s6_addr32[0] = htonl(0xfe800000); + addr.s6_addr32[1] = 0; + + if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && + ipv6_addr_equal(&ifp->addr, &addr)) { + /* DAD failed for link-local based on MAC */ + idev->cnf.disable_ipv6 = 1; + + pr_info("%s: IPv6 being disabled!\n", + ifp->idev->dev->name); + disable_ipv6 = true; + } + } } spin_unlock_bh(&ifp->lock); @@ -3844,7 +3858,10 @@ static void addrconf_dad_work(struct work_struct *w) addrconf_dad_begin(ifp); goto out; } else if (action == DAD_ABORT) { + in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 1); + if (disable_ipv6) + addrconf_ifdown(idev->dev, 0); goto out; } @@ -6017,7 +6034,7 @@ static const struct ctl_table addrconf_sysctl[] = { static int __addrconf_sysctl_register(struct net *net, char *dev_name, struct inet6_dev *idev, struct ipv6_devconf *p) { - int i; + int i, ifindex; struct ctl_table *table; char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; @@ -6037,6 +6054,13 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, if (!p->sysctl_header) goto free; + if (!strcmp(dev_name, "all")) + ifindex = NETCONFA_IFINDEX_ALL; + else if (!strcmp(dev_name, "default")) + ifindex = NETCONFA_IFINDEX_DEFAULT; + else + ifindex = idev->dev->ifindex; + inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p); return 0; free: diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index c53b92c617c5..37ac9de713c6 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -952,8 +952,10 @@ calipso_opt_insert(struct ipv6_opt_hdr *hop, memcpy(new, hop, start); ret_val = calipso_genopt((unsigned char *)new, start, buf_len, doi_def, secattr); - if (ret_val < 0) + if (ret_val < 0) { + kfree(new); return ERR_PTR(ret_val); + } buf_len = start + ret_val; /* At this point buf_len aligns to 4n, so (buf_len & 4) pads to 8n */ diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 776d145113e1..704274cbd495 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -519,8 +519,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, protocol); - return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 7b0481e3738f..888543debe4e 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1174,6 +1174,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPIP; dsfield = ipv4_get_dsfield(iph); @@ -1233,6 +1234,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) encap_limit = t->parms.encap_limit; memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_IPV6; dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index 71d995ff3108..2535223ba956 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -31,6 +31,7 @@ static unsigned int nf_route_table_hook(void *priv, struct in6_addr saddr, daddr; u_int8_t hop_limit; u32 mark, flowlabel; + int err; /* malformed packet, drop it */ if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0) @@ -46,13 +47,16 @@ static unsigned int nf_route_table_hook(void *priv, flowlabel = *((u32 *)ipv6_hdr(skb)); ret = nft_do_chain(&pkt, priv); - if (ret != NF_DROP && ret != NF_QUEUE && + if (ret != NF_DROP && ret != NF_STOLEN && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || - flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) - return ip6_route_me_harder(state->net, skb) == 0 ? ret : NF_DROP; + flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { + err = ip6_route_me_harder(state->net, skb); + if (err < 0) + ret = NF_DROP_ERR(err); + } return ret; } diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index 533cd5719c59..92bda9908bb9 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -47,6 +47,7 @@ static const struct nft_expr_ops nft_reject_ipv6_ops = { .eval = nft_reject_ipv6_eval, .init = nft_reject_init, .dump = nft_reject_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_ipv6_type __read_mostly = { diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index fed40d1ec29b..0e983b694ee8 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -55,7 +55,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct icmp6hdr user_icmph; int addr_type; struct in6_addr *daddr; - int iif = 0; + int oif = 0; struct flowi6 fl6; int err; struct dst_entry *dst; @@ -78,25 +78,30 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (u->sin6_family != AF_INET6) { return -EAFNOSUPPORT; } - if (sk->sk_bound_dev_if && - sk->sk_bound_dev_if != u->sin6_scope_id) { - return -EINVAL; - } daddr = &(u->sin6_addr); - iif = u->sin6_scope_id; + if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) + oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; } - if (!iif) - iif = sk->sk_bound_dev_if; + if (!oif) + oif = sk->sk_bound_dev_if; + + if (!oif) + oif = np->sticky_pktinfo.ipi6_ifindex; + + if (!oif && ipv6_addr_is_multicast(daddr)) + oif = np->mcast_oif; + else if (!oif) + oif = np->ucast_oif; addr_type = ipv6_addr_type(daddr); - if (__ipv6_addr_needs_scope_id(addr_type) && !iif) - return -EINVAL; - if (addr_type & IPV6_ADDR_MAPPED) + if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || + (addr_type & IPV6_ADDR_MAPPED) || + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) return -EINVAL; /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ @@ -106,16 +111,12 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; + fl6.flowi6_oif = oif; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; - else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; - ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); @@ -125,8 +126,10 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rt = (struct rt6_info *) dst; np = inet6_sk(sk); - if (!np) - return -EBADF; + if (!np) { + err = -EBADF; + goto dst_err_out; + } if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; @@ -162,6 +165,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } release_sock(sk); +dst_err_out: + dst_release(dst); + if (err) return err; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 33df8b8575cc..94f4f89d73e7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -944,9 +944,15 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 81e2f98b958d..19ac3a1c308d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1460,7 +1460,6 @@ struct proto udpv6_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 9cf097e206e9..fd6ef414899b 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -50,7 +50,6 @@ struct proto udplitev6_prot = { .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 0eaab1fa6be5..00a2d40677d6 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -23,6 +23,7 @@ int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb) int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); return xfrm_input(skb, nexthdr, spi, 0); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 6cc97003e4a9..70a86adad875 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -36,7 +36,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, int err; memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_oif = oif; + fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif); fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 4a7ae32afa09..1138eaf5c682 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -185,8 +185,12 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv, self->magic = IAS_MAGIC; self->mode = mode; - if (mode == IAS_CLIENT) - iriap_register_lsap(self, slsap_sel, mode); + if (mode == IAS_CLIENT) { + if (iriap_register_lsap(self, slsap_sel, mode)) { + kfree(self); + return NULL; + } + } self->confirm = callback; self->priv = priv; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index cb39e05b166c..411693288648 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -13,6 +13,7 @@ #include <linux/socket.h> #include <linux/uaccess.h> #include <linux/workqueue.h> +#include <linux/syscalls.h> #include <net/kcm.h> #include <net/netns/generic.h> #include <net/sock.h> @@ -2029,7 +2030,7 @@ static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (copy_to_user((void __user *)arg, &info, sizeof(info))) { err = -EFAULT; - sock_release(newsock); + sys_close(info.fd); } } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 1e40dacaa137..a2ed3bda4ddc 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1855,6 +1855,9 @@ static __net_exit void l2tp_exit_net(struct net *net) (void)l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); + + flush_workqueue(l2tp_wq); + rcu_barrier(); } static struct pernet_operations l2tp_net_ops = { diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index d9560aa2dba3..232cb92033e8 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -856,7 +856,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = -ENOTCONN; if (sk == NULL) goto end; - if (sk->sk_state != PPPOX_CONNECTED) + if (!(sk->sk_state & PPPOX_CONNECTED)) goto end; error = -EBADF; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 8f9c3bde835f..faccef977670 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -746,6 +746,7 @@ static void hwmp_perr_frame_process(struct ieee80211_sub_if_data *sdata, sta = next_hop_deref_protected(mpath); if (mpath->flags & MESH_PATH_ACTIVE && ether_addr_equal(ta, sta->sta.addr) && + !(mpath->flags & MESH_PATH_FIXED) && (!(mpath->flags & MESH_PATH_SN_VALID) || SN_GT(target_sn, mpath->sn) || target_sn == 0)) { mpath->flags &= ~MESH_PATH_ACTIVE; @@ -1012,7 +1013,7 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) goto enddiscovery; spin_lock_bh(&mpath->state_lock); - if (mpath->flags & MESH_PATH_DELETED) { + if (mpath->flags & (MESH_PATH_DELETED | MESH_PATH_FIXED)) { spin_unlock_bh(&mpath->state_lock); goto enddiscovery; } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 6db2ddfa0695..f0e6175a9821 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -826,7 +826,7 @@ void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop) mpath->metric = 0; mpath->hop_count = 0; mpath->exp_time = 0; - mpath->flags |= MESH_PATH_FIXED; + mpath->flags = MESH_PATH_FIXED | MESH_PATH_SN_VALID; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); mesh_path_tx_pending(mpath); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 76b737dcc36f..aa58df80ede0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1616,7 +1616,6 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, sta_info_recalc_tim(sta); } else { - unsigned long tids = sta->txq_buffered_tids & driver_release_tids; int tid; /* @@ -1648,7 +1647,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]); - if (!(tids & BIT(tid)) || txqi->tin.backlog_packets) + if (!(driver_release_tids & BIT(tid)) || + txqi->tin.backlog_packets) continue; sta_info_recalc_tim(sta); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index b5d28f14b9cf..afca7d103684 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -333,10 +333,11 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, if (!uc.center_freq1) return; - /* proceed to downgrade the chandef until usable or the same */ + /* proceed to downgrade the chandef until usable or the same as AP BW */ while (uc.width > max_width || - !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc, - sdata->wdev.iftype)) + (uc.width > sta->tdls_chandef.width && + !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc, + sdata->wdev.iftype))) ieee80211_chandef_downgrade(&uc); if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 502396694f47..cc8e95554b48 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -796,6 +796,36 @@ static __le16 ieee80211_tx_next_seq(struct sta_info *sta, int tid) return ret; } +static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, + struct ieee80211_vif *vif, + struct ieee80211_sta *pubsta, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_txq *txq = NULL; + + if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) || + (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) + return NULL; + + if (!ieee80211_is_data(hdr->frame_control)) + return NULL; + + if (pubsta) { + u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + + txq = pubsta->txq[tid]; + } else if (vif) { + txq = vif->txq; + } + + if (!txq) + return NULL; + + return to_txq_info(txq); +} + static ieee80211_tx_result debug_noinline ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) { @@ -853,7 +883,8 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx) tid = *qc & IEEE80211_QOS_CTL_TID_MASK; tx->sta->tx_stats.msdu[tid]++; - if (!tx->sta->sta.txq[0]) + if (!ieee80211_get_txq(tx->local, info->control.vif, &tx->sta->sta, + tx->skb)) hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid); return TX_CONTINUE; @@ -1243,36 +1274,6 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, return TX_CONTINUE; } -static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, - struct ieee80211_vif *vif, - struct ieee80211_sta *pubsta, - struct sk_buff *skb) -{ - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_txq *txq = NULL; - - if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) || - (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) - return NULL; - - if (!ieee80211_is_data(hdr->frame_control)) - return NULL; - - if (pubsta) { - u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; - - txq = pubsta->txq[tid]; - } else if (vif) { - txq = vif->txq; - } - - if (!txq) - return NULL; - - return to_txq_info(txq); -} - static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb) { IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time(); @@ -3264,7 +3265,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { *ieee80211_get_qos_ctl(hdr) = tid; - if (!sta->sta.txq[0]) + if (!ieee80211_get_txq(local, &sdata->vif, &sta->sta, skb)) hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid); } else { info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index dd2c43abf9e2..9934b0c93c1e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1035,9 +1035,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; - if (tmpl && nfct_synproxy(tmpl)) { - nfct_seqadj_ext_add(ct); - nfct_synproxy_ext_add(ct); + if (!nf_ct_add_synproxy(ct, tmpl)) { + nf_conntrack_free(ct); + return ERR_PTR(-ENOMEM); } timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 9e3693128313..f8dbacf66795 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -574,7 +574,7 @@ static int exp_seq_show(struct seq_file *s, void *v) helper = rcu_dereference(nfct_help(expect->master)->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); - if (helper->expect_policy[expect->class].name) + if (helper->expect_policy[expect->class].name[0]) seq_printf(s, "/%s", helper->expect_policy[expect->class].name); } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bb77a97961bf..5c0db5c64734 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1473,7 +1473,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, "timeout to %u seconds for", info->timeout); nf_ct_dump_tuple(&exp->tuple); - mod_timer(&exp->timeout, jiffies + info->timeout * HZ); + mod_timer_pending(&exp->timeout, + jiffies + info->timeout * HZ); } spin_unlock_bh(&nf_conntrack_expect_lock); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 050bb3420a6b..fdfc71f416b7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1894,6 +1894,8 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; + if (otuple.dst.protonum != rtuple.dst.protonum) + return -EINVAL; ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, &rtuple, u3); @@ -2362,12 +2364,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) { - nf_ct_expect_put(exp); - return err; - } - - return 0; + nf_ct_expect_put(exp); + return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 8d9db9d4702b..7d77217de6a3 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1383,7 +1383,7 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1446,7 +1446,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 958a1455ca7f..9f267c3ffb39 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -205,6 +205,7 @@ static int ct_seq_show(struct seq_file *s, void *v) struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + struct net *net = seq_file_net(s); int ret = 0; NF_CT_ASSERT(ct); @@ -215,6 +216,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (NF_CT_DIRECTION(hash)) goto release; + if (!net_eq(nf_ct_net(ct), net)) + goto release; + l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index de31818417b8..ecee105bbada 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -441,7 +441,8 @@ nf_nat_setup_info(struct nf_conn *ct, ct->status |= IPS_DST_NAT; if (nfct_help(ct)) - nfct_seqadj_ext_add(ct); + if (!nfct_seqadj_ext_add(ct)) + return NF_DROP; } if (maniptype == NF_NAT_MANIP_SRC) { @@ -807,7 +808,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, if (err < 0) return err; - return nf_nat_setup_info(ct, &range, manip); + return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0; } #else static int diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index 5eefe4a355c6..75d696f11045 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -30,7 +30,6 @@ nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, if (!iph) return; - iph = ip_hdr(skb); if (iph->ihl < 5 || iph->version != 4) return; diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 39eb1cc62e91..fa24a5b398b1 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -237,7 +237,7 @@ void nft_trace_notify(struct nft_traceinfo *info) break; case NFT_TRACETYPE_POLICY: if (nla_put_be32(skb, NFTA_TRACE_POLICY, - info->basechain->policy)) + htonl(info->basechain->policy))) goto nla_put_failure; break; } diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 1b4de4bd6958..d44d89b56127 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -326,14 +326,14 @@ static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; - /* we want to avoid races with nfnl_acct_find_get. */ - if (atomic_dec_and_test(&cur->refcnt)) { + /* We want to avoid races with nfnl_acct_put. So only when the current + * refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&cur->refcnt); ret = -EBUSY; } return ret; @@ -343,12 +343,12 @@ static int nfnl_acct_del(struct net *net, struct sock *nfnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const tb[]) { - char *acct_name; - struct nf_acct *cur; + struct nf_acct *cur, *tmp; int ret = -ENOENT; + char *acct_name; if (!tb[NFACCT_NAME]) { - list_for_each_entry(cur, &net->nfnl_acct_list, head) + list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) nfnl_acct_try_del(cur); return 0; @@ -443,7 +443,7 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); -static void nfnl_overquota_report(struct nf_acct *nfacct) +static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) { int ret; struct sk_buff *skb; @@ -458,11 +458,12 @@ static void nfnl_overquota_report(struct nf_acct *nfacct) kfree_skb(skb); return; } - netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } -int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct) { u64 now; u64 *quota; @@ -480,7 +481,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) if (now >= *quota && !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { - nfnl_overquota_report(nfacct); + nfnl_overquota_report(net, nfacct); } return ret; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 4cdcd969b64c..139e0867e56e 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -98,31 +98,28 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, break; } - l4proto = nf_ct_l4proto_find_get(l3num, l4num); - - /* This protocol is not supportted, skip. */ - if (l4proto->l4proto != l4num) { - ret = -EOPNOTSUPP; - goto err_proto_put; - } - if (matching) { if (nlh->nlmsg_flags & NLM_F_REPLACE) { /* You cannot replace one timeout policy by another of * different kind, sorry. */ if (matching->l3num != l3num || - matching->l4proto->l4proto != l4num) { - ret = -EINVAL; - goto err_proto_put; - } - - ret = ctnl_timeout_parse_policy(&matching->data, - l4proto, net, - cda[CTA_TIMEOUT_DATA]); - return ret; + matching->l4proto->l4proto != l4num) + return -EINVAL; + + return ctnl_timeout_parse_policy(&matching->data, + matching->l4proto, net, + cda[CTA_TIMEOUT_DATA]); } - ret = -EBUSY; + + return -EBUSY; + } + + l4proto = nf_ct_l4proto_find_get(l3num, l4num); + + /* This protocol is not supportted, skip. */ + if (l4proto->l4proto != l4num) { + ret = -EOPNOTSUPP; goto err_proto_put; } @@ -305,7 +302,16 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) const struct hlist_nulls_node *nn; unsigned int last_hsize; spinlock_t *lock; - int i; + int i, cpu; + + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) + untimeout(h, timeout); + spin_unlock_bh(&pcpu->lock); + } local_bh_disable(); restart: @@ -330,16 +336,16 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) { int ret = 0; - /* we want to avoid races with nf_ct_timeout_find_get. */ - if (atomic_dec_and_test(&timeout->refcnt)) { + /* We want to avoid races with ctnl_timeout_put. So only when the + * current refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); ctnl_untimeout(net, timeout); kfree_rcu(timeout, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&timeout->refcnt); ret = -EBUSY; } return ret; @@ -350,12 +356,13 @@ static int cttimeout_del_timeout(struct net *net, struct sock *ctnl, const struct nlmsghdr *nlh, const struct nlattr * const cda[]) { - struct ctnl_timeout *cur; + struct ctnl_timeout *cur, *tmp; int ret = -ENOENT; char *name; if (!cda[CTA_TIMEOUT_NAME]) { - list_for_each_entry(cur, &net->nfct_timeout_list, head) + list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, + head) ctnl_timeout_try_del(net, cur); return 0; @@ -543,7 +550,9 @@ err: static void ctnl_timeout_put(struct ctnl_timeout *timeout) { - atomic_dec(&timeout->refcnt); + if (atomic_dec_and_test(&timeout->refcnt)) + kfree_rcu(timeout, rcu_head); + module_put(THIS_MODULE); } #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ @@ -591,7 +600,9 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); nf_ct_l4proto_put(cur->l4proto); - kfree_rcu(cur, rcu_head); + + if (atomic_dec_and_test(&cur->refcnt)) + kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index cbcfdfb586a6..6577db524ef6 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1147,6 +1147,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); +MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5d36a0926b4a..f49f45081acb 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1145,10 +1145,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct nfnl_queue_net *q = nfnl_queue_pernet(net); int err; - queue = instance_lookup(q, queue_num); - if (!queue) - queue = verdict_instance_lookup(q, queue_num, - NETLINK_CB(skb).portid); + queue = verdict_instance_lookup(q, queue_num, + NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index ba7aed13e174..82c264e40278 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -59,6 +59,7 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); + u32 offset, len; if (tb[NFTA_EXTHDR_DREG] == NULL || tb[NFTA_EXTHDR_TYPE] == NULL || @@ -66,9 +67,15 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, tb[NFTA_EXTHDR_LEN] == NULL) return -EINVAL; + offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); + len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + + if (offset > U8_MAX || len > U8_MAX) + return -ERANGE; + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); - priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); - priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + priv->offset = offset; + priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); return nft_validate_register_store(ctx, priv->dreg, NULL, diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 2863f3493038..8a6bc7630912 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -291,10 +291,16 @@ int nft_meta_get_init(const struct nft_ctx *ctx, } EXPORT_SYMBOL_GPL(nft_meta_get_init); -static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx) +int nft_meta_set_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { + struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; + if (priv->key != NFT_META_PKTTYPE) + return 0; + switch (ctx->afi->family) { case NFPROTO_BRIDGE: hooks = 1 << NF_BR_PRE_ROUTING; @@ -308,6 +314,7 @@ static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx) return nft_chain_validate_hooks(ctx->chain, hooks); } +EXPORT_SYMBOL_GPL(nft_meta_set_validate); int nft_meta_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, @@ -327,15 +334,16 @@ int nft_meta_set_init(const struct nft_ctx *ctx, len = sizeof(u8); break; case NFT_META_PKTTYPE: - err = nft_meta_set_init_pkttype(ctx); - if (err) - return err; len = sizeof(u8); break; default: return -EOPNOTSUPP; } + err = nft_meta_set_validate(ctx, expr, NULL); + if (err < 0) + return err; + priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); err = nft_validate_register_load(priv->sreg, len); if (err < 0) @@ -407,6 +415,7 @@ static const struct nft_expr_ops nft_meta_set_ops = { .init = nft_meta_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, + .validate = nft_meta_set_validate, }; static const struct nft_expr_ops * diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index 6473936d05c6..ffe9ae062d23 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -70,7 +70,6 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } else if (d > 0) parent = parent->rb_right; else { -found: if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; @@ -84,9 +83,12 @@ found: } } - if (set->flags & NFT_SET_INTERVAL && interval != NULL) { - rbe = interval; - goto found; + if (set->flags & NFT_SET_INTERVAL && interval != NULL && + nft_set_elem_active(&interval->ext, genmask) && + !nft_rbtree_interval_end(interval)) { + spin_unlock_bh(&nft_rbtree_lock); + *ext = &interval->ext; + return true; } out: spin_unlock_bh(&nft_rbtree_lock); diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 0522fc9bfb0a..c64de3f7379d 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -26,11 +26,27 @@ const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { }; EXPORT_SYMBOL_GPL(nft_reject_policy); +int nft_reject_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT)); +} +EXPORT_SYMBOL_GPL(nft_reject_validate); + int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); + int err; + + err = nft_reject_validate(ctx, expr, NULL); + if (err < 0) + return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 759ca5248a3d..e79d9ca2ffee 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -66,7 +66,11 @@ static int nft_reject_inet_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code; + int icmp_code, err; + + err = nft_reject_validate(ctx, expr, NULL); + if (err < 0) + return err; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; @@ -124,6 +128,7 @@ static const struct nft_expr_ops nft_reject_inet_ops = { .eval = nft_reject_inet_eval, .init = nft_reject_inet_init, .dump = nft_reject_inet_dump, + .validate = nft_reject_validate, }; static struct nft_expr_type nft_reject_inet_type __read_mostly = { diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 7f4414d26a66..663c4c3c9072 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -127,6 +127,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, daddr, dport, in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound @@ -195,6 +197,8 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, daddr, ntohs(dport), in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 3048a7e3a90a..cf327593852a 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) nfnl_acct_update(skb, info->nfacct); - overquota = nfnl_acct_overquota(skb, info->nfacct); + overquota = nfnl_acct_overquota(par->net, skb, info->nfacct); return overquota == NFACCT_UNDERQUOTA ? false : true; } diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 1a1fcec88695..5aaf3babfc3f 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -93,7 +93,14 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 7f8897f33a67..0e72d95b0e8f 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -54,6 +54,7 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) struct net *net = ovs_dp_get_net(parms->dp); struct net_device *dev; struct vport *vport; + int err; vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms); if (IS_ERR(vport)) @@ -67,9 +68,15 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); - rtnl_unlock(); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + return ERR_PTR(err); + } + rtnl_unlock(); return vport; } diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 5eb7694348b5..7eb955e453e6 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -130,7 +130,14 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index f5e99163a09e..e60cf65c2232 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -837,6 +837,9 @@ void rxrpc_process_call(struct work_struct *work) return; } + if (!call->conn) + goto skip_msg_init; + /* there's a good chance we're going to have to send a message, so set * one up in advance */ msg.msg_name = &call->conn->params.peer->srx.transport; @@ -859,6 +862,7 @@ void rxrpc_process_call(struct work_struct *work) memset(iov, 0, sizeof(iov)); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); +skip_msg_init: /* deal with events of a final nature */ if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) { diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index c47f14fc5e88..ae057e0740f3 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -275,6 +275,7 @@ error: list_del_init(&call->link); write_unlock_bh(&rxrpc_call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = %d", ret); @@ -287,6 +288,7 @@ error: */ found_user_ID_now_present: write_unlock(&rx->call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = -EEXIST [%p]", call); @@ -493,6 +495,7 @@ void rxrpc_release_call(struct rxrpc_call *call) (skb = skb_dequeue(&call->rx_oos_queue))) { spin_unlock_bh(&call->lock); + sp = rxrpc_skb(skb); _debug("- zap %s %%%u #%u", rxrpc_pkts[sp->hdr.type], sp->hdr.serial, sp->hdr.seq); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9e0f58edcd01..70bb77818dea 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -124,11 +124,15 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, struct rxrpc_skb_priv *sp; bool terminal; int ret, ackbit, ack; + u32 serial; + u8 flags; _enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq); sp = rxrpc_skb(skb); ASSERTCMP(sp->call, ==, NULL); + flags = sp->hdr.flags; + serial = sp->hdr.serial; spin_lock(&call->lock); @@ -192,8 +196,8 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, sp->call = call; rxrpc_get_call(call); atomic_inc(&call->skb_count); - terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) && - !(sp->hdr.flags & RXRPC_CLIENT_INITIATED)); + terminal = ((flags & RXRPC_LAST_PACKET) && + !(flags & RXRPC_CLIENT_INITIATED)); ret = rxrpc_queue_rcv_skb(call, skb, false, terminal); if (ret < 0) { if (ret == -ENOMEM || ret == -ENOBUFS) { @@ -205,12 +209,13 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, } skb = NULL; + sp = NULL; _debug("post #%u", seq); ASSERTCMP(call->rx_data_post, ==, seq); call->rx_data_post++; - if (sp->hdr.flags & RXRPC_LAST_PACKET) + if (flags & RXRPC_LAST_PACKET) set_bit(RXRPC_CALL_RCVD_LAST, &call->flags); /* if we've reached an out of sequence packet then we need to drain @@ -226,7 +231,7 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, spin_unlock(&call->lock); atomic_inc(&call->ackr_not_idle); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, sp->hdr.serial, false); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false); _leave(" = 0 [posted]"); return 0; @@ -239,7 +244,7 @@ out: discard_and_ack: _debug("discard and ACK packet %p", skb); - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, serial, true); discard: spin_unlock(&call->lock); rxrpc_free_skb(skb); @@ -247,7 +252,7 @@ discard: return 0; enqueue_and_ack: - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, serial, true); enqueue_packet: _net("defer skb %p", skb); spin_unlock(&call->lock); @@ -567,13 +572,13 @@ done: * post connection-level events to the connection * - this includes challenges, responses and some aborts */ -static bool rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, +static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, struct sk_buff *skb) { _enter("%p,%p", conn, skb); skb_queue_tail(&conn->rx_queue, skb); - return rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn); } /* @@ -694,7 +699,6 @@ void rxrpc_data_ready(struct sock *sk) rcu_read_lock(); -retry_find_conn: conn = rxrpc_find_connection_rcu(local, skb); if (!conn) goto cant_route_call; @@ -702,8 +706,7 @@ retry_find_conn: if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); - if (!rxrpc_post_packet_to_conn(conn, skb)) - goto retry_find_conn; + rxrpc_post_packet_to_conn(conn, skb); } else { /* Call-bound packets are routed by connection channel. */ unsigned int channel = sp->hdr.cid & RXRPC_CHANNELMASK; @@ -741,6 +744,8 @@ cant_route_call: if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { _debug("reject type %d",sp->hdr.type); rxrpc_reject_packet(local, skb); + } else { + rxrpc_free_skb(skb); } _leave(" [no call]"); return; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e4a5f2607ffa..d09d0687594b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -64,7 +64,6 @@ int __tcf_hash_release(struct tc_action *p, bool bind, bool strict) if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) { if (p->ops->cleanup) p->ops->cleanup(p, bind); - list_del(&p->list); tcf_hash_destroy(p->hinfo, p); ret = ACT_P_DELETED; } @@ -421,18 +420,19 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) return res; } -int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, - struct tcf_result *res) +int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, + int nr_actions, struct tcf_result *res) { - const struct tc_action *a; - int ret = -1; + int ret = -1, i; if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); ret = TC_ACT_OK; goto exec_done; } - list_for_each_entry(a, actions, list) { + for (i = 0; i < nr_actions; i++) { + const struct tc_action *a = actions[i]; + repeat: ret = a->ops->act(skb, a, res); if (ret == TC_ACT_REPEAT) @@ -754,16 +754,6 @@ err_out: return ERR_PTR(err); } -static void cleanup_a(struct list_head *actions) -{ - struct tc_action *a, *tmp; - - list_for_each_entry_safe(a, tmp, actions, list) { - list_del(&a->list); - kfree(a); - } -} - static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -905,7 +895,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, return ret; } err: - cleanup_a(&actions); + tcf_action_destroy(&actions, 0); return ret; } @@ -942,15 +932,9 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); if (ret) - goto done; + return ret; - /* dump then free all the actions after update; inserted policy - * stays intact - */ - ret = tcf_add_notify(net, n, &actions, portid); - cleanup_a(&actions); -done: - return ret; + return tcf_add_notify(net, n, &actions, portid); } static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 141a06eeb1e5..e87cd81315e1 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -53,7 +53,7 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) u32 *tlv = (u32 *)(skbdata); u16 totlen = nla_total_size(dlen); /*alignment + hdr */ char *dptr = (char *)tlv + NLA_HDRLEN; - u32 htlv = attrtype << 16 | totlen; + u32 htlv = attrtype << 16 | dlen; *tlv = htonl(htlv); memset(dptr, 0, totlen - NLA_HDRLEN); @@ -135,7 +135,7 @@ EXPORT_SYMBOL_GPL(ife_release_meta_gen); int ife_validate_meta_u32(void *val, int len) { - if (len == 4) + if (len == sizeof(u32)) return 0; return -EINVAL; @@ -144,8 +144,8 @@ EXPORT_SYMBOL_GPL(ife_validate_meta_u32); int ife_validate_meta_u16(void *val, int len) { - /* length will include padding */ - if (len == NLA_ALIGN(2)) + /* length will not include padding */ + if (len == sizeof(u16)) return 0; return -EINVAL; @@ -652,12 +652,14 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlvdata = (u8 *)tlv; u16 mtype = tlv->type; u16 mlen = tlv->len; + u16 alen; mtype = ntohs(mtype); mlen = ntohs(mlen); + alen = NLA_ALIGN(mlen); - if (find_decode_metaid(skb, ife, mtype, (mlen - 4), - (void *)(tlvdata + 4))) { + if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN), + (void *)(tlvdata + NLA_HDRLEN))) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -666,8 +668,8 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, ife->tcf_qstats.overlimits++; } - tlvdata += mlen; - ifehdrln -= mlen; + tlvdata += alen; + ifehdrln -= alen; tlv = (struct meta_tlvhdr *)tlvdata; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index b3c7e975fc9e..8a3be1d99775 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -63,49 +63,8 @@ static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, const struct tc_action_ops *ops) { struct tc_action_net *tn = net_generic(net, police_net_id); - struct tcf_hashinfo *hinfo = tn->hinfo; - int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; - struct nlattr *nest; - - spin_lock_bh(&hinfo->lock); - - s_i = cb->args[0]; - - for (i = 0; i < (POL_TAB_MASK + 1); i++) { - struct hlist_head *head; - struct tc_action *p; - - head = &hinfo->htab[tcf_hash(i, POL_TAB_MASK)]; - - hlist_for_each_entry_rcu(p, head, tcfa_head) { - index++; - if (index < s_i) - continue; - nest = nla_nest_start(skb, index); - if (nest == NULL) - goto nla_put_failure; - if (type == RTM_DELACTION) - err = tcf_action_dump_1(skb, p, 0, 1); - else - err = tcf_action_dump_1(skb, p, 0, 0); - if (err < 0) { - index--; - nla_nest_cancel(skb, nest); - goto done; - } - nla_nest_end(skb, nest); - n_i++; - } - } -done: - spin_unlock_bh(&hinfo->lock); - if (n_i) - cb->args[0] += n_i; - return n_i; -nla_put_failure: - nla_nest_cancel(skb, nest); - goto done; + return tcf_generic_walker(tn, skb, cb, type, ops); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { @@ -125,6 +84,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + bool exists = false; int size; if (nla == NULL) @@ -139,24 +99,24 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, size = nla_len(tb[TCA_POLICE_TBF]); if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) return -EINVAL; + parm = nla_data(tb[TCA_POLICE_TBF]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; - if (parm->index) { - if (tcf_hash_check(tn, parm->index, a, bind)) { - if (ovr) - goto override; - /* not replacing */ - return -EEXIST; - } - } else { + if (!exists) { ret = tcf_hash_create(tn, parm->index, NULL, a, &act_police_ops, bind, false); if (ret) return ret; ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; } -override: police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 843a716a4303..a7c5645373af 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -541,8 +541,12 @@ out: void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND); - INIT_LIST_HEAD(&exts->actions); + LIST_HEAD(actions); + + tcf_exts_to_list(exts, &actions); + tcf_action_destroy(&actions, TCA_ACT_UNBIND); + kfree(exts->actions); + exts->nr_actions = 0; #endif } EXPORT_SYMBOL(tcf_exts_destroy); @@ -554,7 +558,6 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, { struct tc_action *act; - INIT_LIST_HEAD(&exts->actions); if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tb[exts->police], rate_tlv, "police", ovr, @@ -563,14 +566,20 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, return PTR_ERR(act); act->type = exts->type = TCA_OLD_COMPAT; - list_add(&act->list, &exts->actions); + exts->actions[0] = act; + exts->nr_actions = 1; } else if (exts->action && tb[exts->action]) { - int err; + LIST_HEAD(actions); + int err, i = 0; + err = tcf_action_init(net, tb[exts->action], rate_tlv, NULL, ovr, - TCA_ACT_BIND, &exts->actions); + TCA_ACT_BIND, &actions); if (err) return err; + list_for_each_entry(act, &actions, list) + exts->actions[i++] = act; + exts->nr_actions = i; } } #else @@ -587,37 +596,49 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, struct tcf_exts *src) { #ifdef CONFIG_NET_CLS_ACT - LIST_HEAD(tmp); + struct tcf_exts old = *dst; + tcf_tree_lock(tp); - list_splice_init(&dst->actions, &tmp); - list_splice(&src->actions, &dst->actions); + dst->nr_actions = src->nr_actions; + dst->actions = src->actions; dst->type = src->type; tcf_tree_unlock(tp); - tcf_action_destroy(&tmp, TCA_ACT_UNBIND); + + tcf_exts_destroy(&old); #endif } EXPORT_SYMBOL(tcf_exts_change); -#define tcf_exts_first_act(ext) \ - list_first_entry_or_null(&(exts)->actions, \ - struct tc_action, list) +#ifdef CONFIG_NET_CLS_ACT +static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts) +{ + if (exts->nr_actions == 0) + return NULL; + else + return exts->actions[0]; +} +#endif int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT struct nlattr *nest; - if (exts->action && !list_empty(&exts->actions)) { + if (exts->action && exts->nr_actions) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { + LIST_HEAD(actions); + nest = nla_nest_start(skb, exts->action); if (nest == NULL) goto nla_put_failure; - if (tcf_action_dump(skb, &exts->actions, 0, 0) < 0) + + tcf_exts_to_list(exts, &actions); + if (tcf_action_dump(skb, &actions, 0, 0) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (exts->police) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e95b67cd5718..657c13362b19 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -643,18 +643,19 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc *sch; if (!try_module_get(ops->owner)) - goto errout; + return NULL; sch = qdisc_alloc(dev_queue, ops); - if (IS_ERR(sch)) - goto errout; + if (IS_ERR(sch)) { + module_put(ops->owner); + return NULL; + } sch->parent = parentid; if (!ops->init || ops->init(sch, NULL) == 0) return sch; qdisc_destroy(sch); -errout: return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); diff --git a/net/sctp/input.c b/net/sctp/input.c index c182db7d691f..1555fb8c68e0 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -119,7 +119,13 @@ int sctp_rcv(struct sk_buff *skb) skb_transport_offset(skb)) goto discard_it; - if (!pskb_may_pull(skb, sizeof(struct sctphdr))) + /* If the packet is fragmented and we need to do crc checking, + * it's better to just linearize it otherwise crc computing + * takes longer. + */ + if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + skb_linearize(skb)) || + !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; /* Pull up the IP header. */ @@ -790,27 +796,34 @@ struct sctp_hash_cmp_arg { static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { + struct sctp_transport *t = (struct sctp_transport *)ptr; const struct sctp_hash_cmp_arg *x = arg->key; - const struct sctp_transport *t = ptr; - struct sctp_association *asoc = t->asoc; - const struct net *net = x->net; + struct sctp_association *asoc; + int err = 1; if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr)) - return 1; - if (!net_eq(sock_net(asoc->base.sk), net)) - return 1; + return err; + if (!sctp_transport_hold(t)) + return err; + + asoc = t->asoc; + if (!net_eq(sock_net(asoc->base.sk), x->net)) + goto out; if (x->ep) { if (x->ep != asoc->ep) - return 1; + goto out; } else { if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port)) - return 1; + goto out; if (!sctp_bind_addr_match(&asoc->base.bind_addr, x->laddr, sctp_sk(asoc->base.sk))) - return 1; + goto out; } - return 0; + err = 0; +out: + sctp_transport_put(t); + return err; } static inline u32 sctp_hash_obj(const void *data, u32 len, u32 seed) @@ -1177,9 +1190,6 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) return NULL; - if (skb_linearize(skb)) - return NULL; - ch = (sctp_chunkhdr_t *) skb->data; /* The code below will attempt to walk the chunk and extract diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index c30ddb0f3190..6437aa97cfd7 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,19 +170,6 @@ next_chunk: chunk = list_entry(entry, struct sctp_chunk, list); - /* Linearize if it's not GSO */ - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP && - skb_is_nonlinear(chunk->skb)) { - if (skb_linearize(chunk->skb)) { - __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); - sctp_chunk_free(chunk); - goto next_chunk; - } - - /* Update sctp_hdr as it probably changed */ - chunk->sctp_hdr = sctp_hdr(chunk->skb); - } - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { /* GSO-marked skbs but without frags, handle * them normally diff --git a/net/sctp/output.c b/net/sctp/output.c index 1f1682b9a6a8..31b7bc35895d 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -878,7 +878,7 @@ static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, struct sctp_chunk *chunk, u16 chunk_len) { - size_t psize, pmtu; + size_t psize, pmtu, maxsize; sctp_xmit_t retval = SCTP_XMIT_OK; psize = packet->size; @@ -906,6 +906,17 @@ static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, goto out; } + /* Similarly, if this chunk was built before a PMTU + * reduction, we have to fragment it at IP level now. So + * if the packet already contains something, we need to + * flush. + */ + maxsize = pmtu - packet->overhead; + if (packet->auth) + maxsize -= WORD_ROUND(packet->auth->skb->len); + if (chunk_len > maxsize) + retval = SCTP_XMIT_PMTU_FULL; + /* It is also okay to fragment if the chunk we are * adding is a control chunk, but only if current packet * is not a GSO one otherwise it causes fragmentation of diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 4cb5aedfe3ee..ef8ba77a5bea 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -293,6 +293,7 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) return ERR_PTR(err); } + iter->start_fail = 0; return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos); } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index bb691538adc8..f3508aa75815 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -424,11 +424,13 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, paddr.v4.sin_family = AF_INET; } else { laddr.v6.sin6_port = req->id.idiag_sport; - memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, 64); + memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, + sizeof(laddr.v6.sin6_addr)); laddr.v6.sin6_family = AF_INET6; paddr.v6.sin6_port = req->id.idiag_dport; - memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, 64); + memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, + sizeof(paddr.v6.sin6_addr)); paddr.v6.sin6_family = AF_INET6; } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 23c8e7c39656..976c7812bbd5 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -340,12 +340,14 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) } static struct gss_upcall_msg * -__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid) +__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth) { struct gss_upcall_msg *pos; list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; + if (auth && pos->auth->service != auth->service) + continue; atomic_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); return pos; @@ -365,7 +367,7 @@ gss_add_msg(struct gss_upcall_msg *gss_msg) struct gss_upcall_msg *old; spin_lock(&pipe->lock); - old = __gss_find_upcall(pipe, gss_msg->uid); + old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth); if (old == NULL) { atomic_inc(&gss_msg->count); list_add(&gss_msg->list, &pipe->in_downcall); @@ -714,7 +716,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid); + gss_msg = __gss_find_upcall(pipe, uid, NULL); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index e085f5ae1548..1d281816f2bf 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1230,8 +1230,9 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, if (status) goto out; - dprintk("RPC: svcauth_gss: gss major status = %d\n", - ud.major_status); + dprintk("RPC: svcauth_gss: gss major status = %d " + "minor status = %d\n", + ud.major_status, ud.minor_status); switch (ud.major_status) { case GSS_S_CONTINUE_NEEDED: diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 553bf95f7003..4d8e11f94a35 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -362,7 +362,7 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd) cache_purge(cd); spin_lock(&cache_list_lock); write_lock(&cd->hash_lock); - if (cd->entries || atomic_read(&cd->inuse)) { + if (cd->entries) { write_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); goto out; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cb49898a5a58..66f23b376fa0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -453,7 +453,7 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, struct rpc_xprt_switch *xps; if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) { - WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xps = args->bc_xprt->xpt_bc_xps; xprt_switch_get(xps); } else { @@ -520,7 +520,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) char servername[48]; if (args->bc_xprt) { - WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC)); xprt = args->bc_xprt->xpt_bc_xprt; if (xprt) { xprt_get(xprt); @@ -2638,6 +2638,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; + unsigned long reconnect_timeout; unsigned char resvport; int ret = 0; @@ -2649,6 +2650,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); xprt = xprt_create_transport(xprtargs); @@ -2657,6 +2659,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->max_reconnect_timeout = reconnect_timeout; rpc_xprt_switch_set_roundrobin(xps); if (setup) { @@ -2673,6 +2676,27 @@ out_put_switch: } EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt); +static int +rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + void *data) +{ + unsigned long timeout = *((unsigned long *)data); + + if (timeout < xprt->max_reconnect_timeout) + xprt->max_reconnect_timeout = timeout; + return 0; +} + +void +rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo) +{ + rpc_clnt_iterate_for_each_xprt(clnt, + rpc_xprt_cap_max_reconnect_timeout, + &timeo); +} +EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout); + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(void) { diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 4f01f63102ee..c3f652395a80 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -21,6 +21,10 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +static unsigned int svc_rpc_per_connection_limit __read_mostly; +module_param(svc_rpc_per_connection_limit, uint, 0644); + + static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt); static int svc_deferred_recv(struct svc_rqst *rqstp); static struct cache_deferred_req *svc_defer(struct cache_req *req); @@ -329,12 +333,45 @@ char *svc_print_addr(struct svc_rqst *rqstp, char *buf, size_t len) } EXPORT_SYMBOL_GPL(svc_print_addr); +static bool svc_xprt_slots_in_range(struct svc_xprt *xprt) +{ + unsigned int limit = svc_rpc_per_connection_limit; + int nrqsts = atomic_read(&xprt->xpt_nr_rqsts); + + return limit == 0 || (nrqsts >= 0 && nrqsts < limit); +} + +static bool svc_xprt_reserve_slot(struct svc_rqst *rqstp, struct svc_xprt *xprt) +{ + if (!test_bit(RQ_DATA, &rqstp->rq_flags)) { + if (!svc_xprt_slots_in_range(xprt)) + return false; + atomic_inc(&xprt->xpt_nr_rqsts); + set_bit(RQ_DATA, &rqstp->rq_flags); + } + return true; +} + +static void svc_xprt_release_slot(struct svc_rqst *rqstp) +{ + struct svc_xprt *xprt = rqstp->rq_xprt; + if (test_and_clear_bit(RQ_DATA, &rqstp->rq_flags)) { + atomic_dec(&xprt->xpt_nr_rqsts); + svc_xprt_enqueue(xprt); + } +} + static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) { if (xprt->xpt_flags & ((1<<XPT_CONN)|(1<<XPT_CLOSE))) return true; - if (xprt->xpt_flags & ((1<<XPT_DATA)|(1<<XPT_DEFERRED))) - return xprt->xpt_ops->xpo_has_wspace(xprt); + if (xprt->xpt_flags & ((1<<XPT_DATA)|(1<<XPT_DEFERRED))) { + if (xprt->xpt_ops->xpo_has_wspace(xprt) && + svc_xprt_slots_in_range(xprt)) + return true; + trace_svc_xprt_no_write_space(xprt); + return false; + } return false; } @@ -480,8 +517,6 @@ void svc_reserve(struct svc_rqst *rqstp, int space) atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved); rqstp->rq_reserved = space; - if (xprt->xpt_ops->xpo_adjust_wspace) - xprt->xpt_ops->xpo_adjust_wspace(xprt); svc_xprt_enqueue(xprt); } } @@ -512,8 +547,8 @@ static void svc_xprt_release(struct svc_rqst *rqstp) rqstp->rq_res.head[0].iov_len = 0; svc_reserve(rqstp, 0); + svc_xprt_release_slot(rqstp); rqstp->rq_xprt = NULL; - svc_xprt_put(xprt); } @@ -781,7 +816,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) svc_add_new_temp_xprt(serv, newxpt); else module_put(xprt->xpt_class->xcl_owner); - } else { + } else if (svc_xprt_reserve_slot(rqstp, xprt)) { /* XPT_DATA|XPT_DEFERRED case: */ dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", rqstp, rqstp->rq_pool->sp_id, xprt, @@ -871,6 +906,7 @@ EXPORT_SYMBOL_GPL(svc_recv); */ void svc_drop(struct svc_rqst *rqstp) { + trace_svc_drop(rqstp); dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt); svc_xprt_release(rqstp); } @@ -1148,6 +1184,7 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) spin_unlock(&xprt->xpt_lock); dprintk("revisit canceled\n"); svc_xprt_put(xprt); + trace_svc_drop_deferred(dr); kfree(dr); return; } @@ -1205,6 +1242,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) set_bit(RQ_DROPME, &rqstp->rq_flags); dr->handle.revisit = svc_revisit; + trace_svc_defer(rqstp); return &dr->handle; } @@ -1245,6 +1283,7 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) struct svc_deferred_req, handle.recent); list_del_init(&dr->handle.recent); + trace_svc_revisit_deferred(dr); } else clear_bit(XPT_DEFERRED, &xprt->xpt_flags); spin_unlock(&xprt->xpt_lock); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index dadfec66dbd8..57625f64efd5 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -60,7 +60,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *, int flags); -static void svc_udp_data_ready(struct sock *); static int svc_udp_recvfrom(struct svc_rqst *); static int svc_udp_sendto(struct svc_rqst *); static void svc_sock_detach(struct svc_xprt *); @@ -398,48 +397,21 @@ static int svc_sock_secure_port(struct svc_rqst *rqstp) return svc_port_is_privileged(svc_addr(rqstp)); } -static bool sunrpc_waitqueue_active(wait_queue_head_t *wq) -{ - if (!wq) - return false; - /* - * There should normally be a memory * barrier here--see - * wq_has_sleeper(). - * - * It appears that isn't currently necessary, though, basically - * because callers all appear to have sufficient memory barriers - * between the time the relevant change is made and the - * time they call these callbacks. - * - * The nfsd code itself doesn't actually explicitly wait on - * these waitqueues, but it may wait on them for example in - * sendpage() or sendmsg() calls. (And those may be the only - * places, since it it uses nonblocking reads.) - * - * Maybe we should add the memory barriers anyway, but these are - * hot paths so we'd need to be convinced there's no sigificant - * penalty. - */ - return waitqueue_active(wq); -} - /* * INET callback when data has been received on the socket. */ -static void svc_udp_data_ready(struct sock *sk) +static void svc_data_ready(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - wait_queue_head_t *wq = sk_sleep(sk); if (svsk) { dprintk("svc: socket %p(inet %p), busy=%d\n", svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); - set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); + svsk->sk_odata(sk); + if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags)) + svc_xprt_enqueue(&svsk->sk_xprt); } - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible(wq); } /* @@ -448,56 +420,22 @@ static void svc_udp_data_ready(struct sock *sk) static void svc_write_space(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)(sk->sk_user_data); - wait_queue_head_t *wq = sk_sleep(sk); if (svsk) { dprintk("svc: socket %p(inet %p), write_space busy=%d\n", svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); + svsk->sk_owspace(sk); svc_xprt_enqueue(&svsk->sk_xprt); } - - if (sunrpc_waitqueue_active(wq)) { - dprintk("RPC svc_write_space: someone sleeping on %p\n", - svsk); - wake_up_interruptible(wq); - } } static int svc_tcp_has_wspace(struct svc_xprt *xprt) { - struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - struct svc_serv *serv = svsk->sk_xprt.xpt_server; - int required; + struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) return 1; - required = atomic_read(&xprt->xpt_reserved) + serv->sv_max_mesg; - if (sk_stream_wspace(svsk->sk_sk) >= required || - (sk_stream_min_wspace(svsk->sk_sk) == 0 && - atomic_read(&xprt->xpt_reserved) == 0)) - return 1; - set_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); - return 0; -} - -static void svc_tcp_write_space(struct sock *sk) -{ - struct svc_sock *svsk = (struct svc_sock *)(sk->sk_user_data); - struct socket *sock = sk->sk_socket; - - if (!sk_stream_is_writeable(sk) || !sock) - return; - if (!svsk || svc_tcp_has_wspace(&svsk->sk_xprt)) - clear_bit(SOCK_NOSPACE, &sock->flags); - svc_write_space(sk); -} - -static void svc_tcp_adjust_wspace(struct svc_xprt *xprt) -{ - struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - - if (svc_tcp_has_wspace(xprt)) - clear_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); + return !test_bit(SOCK_NOSPACE, &svsk->sk_sock->flags); } /* @@ -746,7 +684,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class, &svsk->sk_xprt, serv); clear_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags); - svsk->sk_sk->sk_data_ready = svc_udp_data_ready; + svsk->sk_sk->sk_data_ready = svc_data_ready; svsk->sk_sk->sk_write_space = svc_write_space; /* initialise setting must have enough space to @@ -786,11 +724,12 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) static void svc_tcp_listen_data_ready(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - wait_queue_head_t *wq; dprintk("svc: socket %p TCP (listen) state change %d\n", sk, sk->sk_state); + if (svsk) + svsk->sk_odata(sk); /* * This callback may called twice when a new connection * is established as a child socket inherits everything @@ -808,10 +747,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) } else printk("svc: socket %p: no user data\n", sk); } - - wq = sk_sleep(sk); - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible_all(wq); } /* @@ -820,7 +755,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) static void svc_tcp_state_change(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - wait_queue_head_t *wq = sk_sleep(sk); dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n", sk, sk->sk_state, sk->sk_user_data); @@ -828,26 +762,12 @@ static void svc_tcp_state_change(struct sock *sk) if (!svsk) printk("svc: socket %p: no user data\n", sk); else { - set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); - } - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible_all(wq); -} - -static void svc_tcp_data_ready(struct sock *sk) -{ - struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - wait_queue_head_t *wq = sk_sleep(sk); - - dprintk("svc: socket %p TCP data ready (svsk %p)\n", - sk, sk->sk_user_data); - if (svsk) { - set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); + svsk->sk_ostate(sk); + if (sk->sk_state != TCP_ESTABLISHED) { + set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); + svc_xprt_enqueue(&svsk->sk_xprt); + } } - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible(wq); } /* @@ -901,6 +821,11 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) dprintk("%s: connect from %s\n", serv->sv_name, __svc_print_addr(sin, buf, sizeof(buf))); + /* Reset the inherited callbacks before calling svc_setup_socket */ + newsock->sk->sk_state_change = svsk->sk_ostate; + newsock->sk->sk_data_ready = svsk->sk_odata; + newsock->sk->sk_write_space = svsk->sk_owspace; + /* make sure that a write doesn't block forever when * low on memory */ @@ -1317,7 +1242,6 @@ static struct svc_xprt_ops svc_tcp_ops = { .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, .xpo_secure_port = svc_sock_secure_port, - .xpo_adjust_wspace = svc_tcp_adjust_wspace, }; static struct svc_xprt_class svc_tcp_class = { @@ -1357,8 +1281,8 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) } else { dprintk("setting up TCP socket for reading\n"); sk->sk_state_change = svc_tcp_state_change; - sk->sk_data_ready = svc_tcp_data_ready; - sk->sk_write_space = svc_tcp_write_space; + sk->sk_data_ready = svc_data_ready; + sk->sk_write_space = svc_write_space; svsk->sk_reclen = 0; svsk->sk_tcplen = 0; @@ -1368,8 +1292,13 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF; set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - if (sk->sk_state != TCP_ESTABLISHED) + switch (sk->sk_state) { + case TCP_SYN_RECV: + case TCP_ESTABLISHED: + break; + default: set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); + } } } @@ -1428,17 +1357,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, /* Initialize the socket */ if (sock->type == SOCK_DGRAM) svc_udp_init(svsk, serv); - else { - /* initialise setting must have enough space to - * receive and respond to one request. - */ - svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg, - 4 * serv->sv_max_mesg); + else svc_tcp_init(svsk, serv); - } - dprintk("svc: svc_setup_socket created %p (inet %p)\n", - svsk, svsk->sk_sk); + dprintk("svc: svc_setup_socket created %p (inet %p), " + "listen %d close %d\n", + svsk, svsk->sk_sk, + test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags), + test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)); return svsk; } @@ -1606,18 +1532,16 @@ static void svc_sock_detach(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); struct sock *sk = svsk->sk_sk; - wait_queue_head_t *wq; dprintk("svc: svc_sock_detach(%p)\n", svsk); /* put back the old socket callbacks */ + lock_sock(sk); sk->sk_state_change = svsk->sk_ostate; sk->sk_data_ready = svsk->sk_odata; sk->sk_write_space = svsk->sk_owspace; - - wq = sk_sleep(sk); - if (sunrpc_waitqueue_active(wq)) - wake_up_interruptible(wq); + sk->sk_user_data = NULL; + release_sock(sk); } /* diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8313960cac52..ea244b29138b 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -680,6 +680,20 @@ out: spin_unlock_bh(&xprt->transport_lock); } +static bool +xprt_has_timer(const struct rpc_xprt *xprt) +{ + return xprt->idle_timeout != 0; +} + +static void +xprt_schedule_autodisconnect(struct rpc_xprt *xprt) + __must_hold(&xprt->transport_lock) +{ + if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) + mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); +} + static void xprt_init_autodisconnect(unsigned long data) { @@ -688,6 +702,8 @@ xprt_init_autodisconnect(unsigned long data) spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) goto out_abort; + /* Reset xprt->last_used to avoid connect/autodisconnect cycling */ + xprt->last_used = jiffies; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); @@ -725,6 +741,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) goto out; xprt->snd_task =NULL; xprt->ops->release_xprt(xprt, NULL); + xprt_schedule_autodisconnect(xprt); out: spin_unlock_bh(&xprt->transport_lock); wake_up_bit(&xprt->state, XPRT_LOCKED); @@ -888,11 +905,6 @@ static void xprt_timer(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } -static inline int xprt_has_timer(struct rpc_xprt *xprt) -{ - return xprt->idle_timeout != 0; -} - /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1280,9 +1292,7 @@ void xprt_release(struct rpc_task *task) if (!list_empty(&req->rq_list)) list_del(&req->rq_list); xprt->last_used = jiffies; - if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) - mod_timer(&xprt->timer, - xprt->last_used + xprt->idle_timeout); + xprt_schedule_autodisconnect(xprt); spin_unlock_bh(&xprt->transport_lock); if (req->rq_buffer) xprt->ops->buf_free(req->rq_buffer); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 111767ab124a..8ede3bc52481 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -177,7 +177,6 @@ static struct ctl_table sunrpc_table[] = { * increase over time if the server is down or not responding. */ #define XS_TCP_INIT_REEST_TO (3U * HZ) -#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ) /* * TCP idle timeout; client drops the transport socket if it is idle @@ -2173,6 +2172,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); + + xprt->stat.connect_start = jiffies; } static void xs_udp_setup_socket(struct work_struct *work) @@ -2236,6 +2237,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) unsigned int keepcnt = xprt->timeout->to_retries + 1; unsigned int opt_on = 1; unsigned int timeo; + unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC; /* TCP Keepalive options */ kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, @@ -2247,6 +2249,16 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, (char *)&keepcnt, sizeof(keepcnt)); + /* Avoid temporary address, they are bad for long-lived + * connections such as NFS mounts. + * RFC4941, section 3.6 suggests that: + * Individual applications, which have specific + * knowledge about the normal duration of connections, + * MAY override this as appropriate. + */ + kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES, + (char *)&addr_pref, sizeof(addr_pref)); + /* TCP user timeout (see RFC5482) */ timeo = jiffies_to_msecs(xprt->timeout->to_initval) * (xprt->timeout->to_retries + 1); @@ -2295,6 +2307,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* SYN_SENT! */ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + break; + case -EADDRNOTAVAIL: + /* Source port number is unavailable. Try a new one! */ + transport->srcport = 0; } out: return ret; @@ -2369,6 +2385,25 @@ out: xprt_wake_pending_tasks(xprt, status); } +static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt) +{ + unsigned long start, now = jiffies; + + start = xprt->stat.connect_start + xprt->reestablish_timeout; + if (time_after(start, now)) + return start - now; + return 0; +} + +static void xs_reconnect_backoff(struct rpc_xprt *xprt) +{ + xprt->reestablish_timeout <<= 1; + if (xprt->reestablish_timeout > xprt->max_reconnect_timeout) + xprt->reestablish_timeout = xprt->max_reconnect_timeout; + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; +} + /** * xs_connect - connect a socket to a remote endpoint * @xprt: pointer to transport structure @@ -2386,6 +2421,7 @@ out: static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + unsigned long delay = 0; WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); @@ -2397,19 +2433,15 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) /* Start by resetting any existing state */ xs_reset_transport(transport); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, - xprt->reestablish_timeout); - xprt->reestablish_timeout <<= 1; - if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) - xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; - if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO) - xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO; - } else { + delay = xs_reconnect_delay(xprt); + xs_reconnect_backoff(xprt); + + } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, 0); - } + + queue_delayed_work(xprtiod_workqueue, + &transport->connect_worker, + delay); } /** @@ -2961,6 +2993,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->ops = &xs_tcp_ops; xprt->timeout = &xs_tcp_default_timeout; + xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn); INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index b62caa1c770c..ed97a5876ebe 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -728,12 +728,13 @@ int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id, u32 *prev_node) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); - struct tipc_peer *peer = mon->self; + struct tipc_peer *peer; if (!mon) return -EINVAL; read_lock_bh(&mon->lock); + peer = mon->self; do { if (*prev_node) { if (peer->addr == *prev_node) diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 6b626a64b517..a04fe9be1c60 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -62,6 +62,8 @@ static void publ_to_item(struct distr_item *i, struct publication *p) /** * named_prepare_buf - allocate & initialize a publication message + * + * The buffer returned is of size INT_H_SIZE + payload size */ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, u32 dest) @@ -141,9 +143,9 @@ static void named_distribute(struct net *net, struct sk_buff_head *list, struct publication *publ; struct sk_buff *skb = NULL; struct distr_item *item = NULL; - uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) * - ITEM_SIZE; - uint msg_rem = msg_dsz; + u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) / + ITEM_SIZE) * ITEM_SIZE; + u32 msg_rem = msg_dsz; list_for_each_entry(publ, pls, local_list) { /* Prepare next buffer: */ diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c49b8df438cb..f9f5f3c3dab5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2180,7 +2180,8 @@ restart: TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, onode, dport, oport, TIPC_CONN_SHUTDOWN); - tipc_node_xmit_skb(net, skb, dnode, tsk->portid); + if (skb) + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b016c011970b..ae7e14cae085 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -396,10 +396,13 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, tuncfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg); - if (enable_mcast(ub, remote)) + err = enable_mcast(ub, remote); + if (err) goto err; return 0; err: + if (ub->ubsock) + udp_tunnel_sock_release(ub->ubsock); kfree(ub); return err; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f1dffe84f0d5..8309687a56b0 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -661,11 +661,11 @@ static int unix_set_peek_off(struct sock *sk, int val) { struct unix_sock *u = unix_sk(sk); - if (mutex_lock_interruptible(&u->readlock)) + if (mutex_lock_interruptible(&u->iolock)) return -EINTR; sk->sk_peek_off = val; - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); return 0; } @@ -779,7 +779,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) spin_lock_init(&u->lock); atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); - mutex_init(&u->readlock); /* single task reading lock */ + mutex_init(&u->iolock); /* single task reading lock */ + mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay); unix_insert_socket(unix_sockets_unbound(sk), sk); @@ -848,7 +849,7 @@ static int unix_autobind(struct socket *sock) int err; unsigned int retries = 0; - err = mutex_lock_interruptible(&u->readlock); + err = mutex_lock_interruptible(&u->bindlock); if (err) return err; @@ -895,7 +896,7 @@ retry: spin_unlock(&unix_table_lock); err = 0; -out: mutex_unlock(&u->readlock); +out: mutex_unlock(&u->bindlock); return err; } @@ -954,20 +955,32 @@ fail: return NULL; } -static int unix_mknod(struct dentry *dentry, const struct path *path, umode_t mode, - struct path *res) +static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) { - int err; + struct dentry *dentry; + struct path path; + int err = 0; + /* + * Get the parent directory, calculate the hash for last + * component. + */ + dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); + err = PTR_ERR(dentry); + if (IS_ERR(dentry)) + return err; - err = security_path_mknod(path, dentry, mode, 0); + /* + * All right, let's create it. + */ + err = security_path_mknod(&path, dentry, mode, 0); if (!err) { - err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0); + err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); if (!err) { - res->mnt = mntget(path->mnt); + res->mnt = mntget(path.mnt); res->dentry = dget(dentry); } } - + done_path_create(&path, dentry); return err; } @@ -978,12 +991,10 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; - int err, name_err; + int err; unsigned int hash; struct unix_address *addr; struct hlist_head *list; - struct path path; - struct dentry *dentry; err = -EINVAL; if (sunaddr->sun_family != AF_UNIX) @@ -999,34 +1010,14 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; - name_err = 0; - dentry = NULL; - if (sun_path[0]) { - /* Get the parent directory, calculate the hash for last - * component. - */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - - if (IS_ERR(dentry)) { - /* delay report until after 'already bound' check */ - name_err = PTR_ERR(dentry); - dentry = NULL; - } - } - - err = mutex_lock_interruptible(&u->readlock); + err = mutex_lock_interruptible(&u->bindlock); if (err) - goto out_path; + goto out; err = -EINVAL; if (u->addr) goto out_up; - if (name_err) { - err = name_err == -EEXIST ? -EADDRINUSE : name_err; - goto out_up; - } - err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) @@ -1037,11 +1028,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) addr->hash = hash ^ sk->sk_type; atomic_set(&addr->refcnt, 1); - if (dentry) { - struct path u_path; + if (sun_path[0]) { + struct path path; umode_t mode = S_IFSOCK | (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(dentry, &path, mode, &u_path); + err = unix_mknod(sun_path, mode, &path); if (err) { if (err == -EEXIST) err = -EADDRINUSE; @@ -1049,9 +1040,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); + hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); - u->path = u_path; + u->path = path; list = &unix_socket_table[hash]; } else { spin_lock(&unix_table_lock); @@ -1073,11 +1064,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) out_unlock: spin_unlock(&unix_table_lock); out_up: - mutex_unlock(&u->readlock); -out_path: - if (dentry) - done_path_create(&path, dentry); - + mutex_unlock(&u->bindlock); out: return err; } @@ -1969,17 +1956,17 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, &err, 0); if (!newskb) goto err; } - /* we must acquire readlock as we modify already present + /* we must acquire iolock as we modify already present * skbs in the sk_receive_queue and mess with skb->len */ - err = mutex_lock_interruptible(&unix_sk(other)->readlock); + err = mutex_lock_interruptible(&unix_sk(other)->iolock); if (err) { err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS; goto err; @@ -2046,7 +2033,7 @@ alloc_skb: } unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); other->sk_data_ready(other); scm_destroy(&scm); @@ -2055,7 +2042,7 @@ alloc_skb: err_state_unlock: unix_state_unlock(other); err_unlock: - mutex_unlock(&unix_sk(other)->readlock); + mutex_unlock(&unix_sk(other)->iolock); err: kfree_skb(newskb); if (send_sigpipe && !(flags & MSG_NOSIGNAL)) @@ -2123,7 +2110,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err, @@ -2131,14 +2118,14 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, if (skb) break; - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); if (err != -EAGAIN) break; } while (timeo && !__skb_wait_for_more_packets(sk, &err, &timeo, last)); - if (!skb) { /* implies readlock unlocked */ + if (!skb) { /* implies iolock unlocked */ unix_state_lock(sk); /* Signal EOF on disconnected non-blocking SEQPACKET socket. */ if (sk->sk_type == SOCK_SEQPACKET && err == -EAGAIN && @@ -2203,7 +2190,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, out_free: skb_free_datagram(sk, skb); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); out: return err; } @@ -2298,7 +2285,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); if (flags & MSG_PEEK) skip = sk_peek_offset(sk, flags); @@ -2340,7 +2327,7 @@ again: break; } - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, last_len); @@ -2351,7 +2338,7 @@ again: goto out; } - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); goto redo; unlock: unix_state_unlock(sk); @@ -2454,7 +2441,7 @@ unlock: } } while (size); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); if (state->msg) scm_recv(sock, state->msg, &scm, flags); else @@ -2495,9 +2482,9 @@ static ssize_t skb_unix_socket_splice(struct sock *sk, int ret; struct unix_sock *u = unix_sk(sk); - mutex_unlock(&u->readlock); + mutex_unlock(&u->iolock); ret = splice_to_pipe(pipe, spd); - mutex_lock(&u->readlock); + mutex_lock(&u->iolock); return ret; } diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig index 14810abedc2e..8831e7c42167 100644 --- a/net/vmw_vsock/Kconfig +++ b/net/vmw_vsock/Kconfig @@ -26,3 +26,23 @@ config VMWARE_VMCI_VSOCKETS To compile this driver as a module, choose M here: the module will be called vmw_vsock_vmci_transport. If unsure, say N. + +config VIRTIO_VSOCKETS + tristate "virtio transport for Virtual Sockets" + depends on VSOCKETS && VIRTIO + select VIRTIO_VSOCKETS_COMMON + help + This module implements a virtio transport for Virtual Sockets. + + Enable this transport if your Virtual Machine host supports Virtual + Sockets over virtio. + + To compile this driver as a module, choose M here: the module will be + called vmw_vsock_virtio_transport. If unsure, say N. + +config VIRTIO_VSOCKETS_COMMON + tristate + help + This option is selected by any driver which needs to access + the virtio_vsock. The module will be called + vmw_vsock_virtio_transport_common. diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile index 2ce52d70f224..bc27c70e0e59 100644 --- a/net/vmw_vsock/Makefile +++ b/net/vmw_vsock/Makefile @@ -1,7 +1,13 @@ obj-$(CONFIG_VSOCKETS) += vsock.o obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o +obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o +obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o vsock-y += af_vsock.o vsock_addr.o vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \ vmci_transport_notify_qstate.o + +vmw_vsock_virtio_transport-y += virtio_transport.o + +vmw_vsock_virtio_transport_common-y += virtio_transport_common.o diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b96ac918e0ba..17dbbe64cd73 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -344,6 +344,16 @@ static bool vsock_in_connected_table(struct vsock_sock *vsk) return ret; } +void vsock_remove_sock(struct vsock_sock *vsk) +{ + if (vsock_in_bound_table(vsk)) + vsock_remove_bound(vsk); + + if (vsock_in_connected_table(vsk)) + vsock_remove_connected(vsk); +} +EXPORT_SYMBOL_GPL(vsock_remove_sock); + void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)) { int i; @@ -660,12 +670,6 @@ static void __vsock_release(struct sock *sk) vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ - if (vsock_in_bound_table(vsk)) - vsock_remove_bound(vsk); - - if (vsock_in_connected_table(vsk)) - vsock_remove_connected(vsk); - transport->release(vsk); lock_sock(sk); @@ -1995,6 +1999,15 @@ void vsock_core_exit(void) } EXPORT_SYMBOL_GPL(vsock_core_exit); +const struct vsock_transport *vsock_core_get_transport(void) +{ + /* vsock_register_mutex not taken since only the transport uses this + * function and only while registered. + */ + return transport; +} +EXPORT_SYMBOL_GPL(vsock_core_get_transport); + MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); MODULE_VERSION("1.0.1.0-k"); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c new file mode 100644 index 000000000000..936d7eee62d0 --- /dev/null +++ b/net/vmw_vsock/virtio_transport.c @@ -0,0 +1,620 @@ +/* + * virtio transport for vsock + * + * Copyright (C) 2013-2015 Red Hat, Inc. + * Author: Asias He <asias@redhat.com> + * Stefan Hajnoczi <stefanha@redhat.com> + * + * Some of the code is take from Gerd Hoffmann <kraxel@redhat.com>'s + * early virtio-vsock proof-of-concept bits. + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ +#include <linux/spinlock.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/atomic.h> +#include <linux/virtio.h> +#include <linux/virtio_ids.h> +#include <linux/virtio_config.h> +#include <linux/virtio_vsock.h> +#include <net/sock.h> +#include <linux/mutex.h> +#include <net/af_vsock.h> + +static struct workqueue_struct *virtio_vsock_workqueue; +static struct virtio_vsock *the_virtio_vsock; +static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */ + +struct virtio_vsock { + struct virtio_device *vdev; + struct virtqueue *vqs[VSOCK_VQ_MAX]; + + /* Virtqueue processing is deferred to a workqueue */ + struct work_struct tx_work; + struct work_struct rx_work; + struct work_struct event_work; + + /* The following fields are protected by tx_lock. vqs[VSOCK_VQ_TX] + * must be accessed with tx_lock held. + */ + struct mutex tx_lock; + + struct work_struct send_pkt_work; + spinlock_t send_pkt_list_lock; + struct list_head send_pkt_list; + + atomic_t queued_replies; + + /* The following fields are protected by rx_lock. vqs[VSOCK_VQ_RX] + * must be accessed with rx_lock held. + */ + struct mutex rx_lock; + int rx_buf_nr; + int rx_buf_max_nr; + + /* The following fields are protected by event_lock. + * vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held. + */ + struct mutex event_lock; + struct virtio_vsock_event event_list[8]; + + u32 guest_cid; +}; + +static struct virtio_vsock *virtio_vsock_get(void) +{ + return the_virtio_vsock; +} + +static u32 virtio_transport_get_local_cid(void) +{ + struct virtio_vsock *vsock = virtio_vsock_get(); + + return vsock->guest_cid; +} + +static void +virtio_transport_send_pkt_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, send_pkt_work); + struct virtqueue *vq; + bool added = false; + bool restart_rx = false; + + mutex_lock(&vsock->tx_lock); + + vq = vsock->vqs[VSOCK_VQ_TX]; + + for (;;) { + struct virtio_vsock_pkt *pkt; + struct scatterlist hdr, buf, *sgs[2]; + int ret, in_sg = 0, out_sg = 0; + bool reply; + + spin_lock_bh(&vsock->send_pkt_list_lock); + if (list_empty(&vsock->send_pkt_list)) { + spin_unlock_bh(&vsock->send_pkt_list_lock); + break; + } + + pkt = list_first_entry(&vsock->send_pkt_list, + struct virtio_vsock_pkt, list); + list_del_init(&pkt->list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + + reply = pkt->reply; + + sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); + sgs[out_sg++] = &hdr; + if (pkt->buf) { + sg_init_one(&buf, pkt->buf, pkt->len); + sgs[out_sg++] = &buf; + } + + ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL); + /* Usually this means that there is no more space available in + * the vq + */ + if (ret < 0) { + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + break; + } + + if (reply) { + struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; + int val; + + val = atomic_dec_return(&vsock->queued_replies); + + /* Do we now have resources to resume rx processing? */ + if (val + 1 == virtqueue_get_vring_size(rx_vq)) + restart_rx = true; + } + + added = true; + } + + if (added) + virtqueue_kick(vq); + + mutex_unlock(&vsock->tx_lock); + + if (restart_rx) + queue_work(virtio_vsock_workqueue, &vsock->rx_work); +} + +static int +virtio_transport_send_pkt(struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock *vsock; + int len = pkt->len; + + vsock = virtio_vsock_get(); + if (!vsock) { + virtio_transport_free_pkt(pkt); + return -ENODEV; + } + + if (pkt->reply) + atomic_inc(&vsock->queued_replies); + + spin_lock_bh(&vsock->send_pkt_list_lock); + list_add_tail(&pkt->list, &vsock->send_pkt_list); + spin_unlock_bh(&vsock->send_pkt_list_lock); + + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); + return len; +} + +static void virtio_vsock_rx_fill(struct virtio_vsock *vsock) +{ + int buf_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + struct virtio_vsock_pkt *pkt; + struct scatterlist hdr, buf, *sgs[2]; + struct virtqueue *vq; + int ret; + + vq = vsock->vqs[VSOCK_VQ_RX]; + + do { + pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + break; + + pkt->buf = kmalloc(buf_len, GFP_KERNEL); + if (!pkt->buf) { + virtio_transport_free_pkt(pkt); + break; + } + + pkt->len = buf_len; + + sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr)); + sgs[0] = &hdr; + + sg_init_one(&buf, pkt->buf, buf_len); + sgs[1] = &buf; + ret = virtqueue_add_sgs(vq, sgs, 0, 2, pkt, GFP_KERNEL); + if (ret) { + virtio_transport_free_pkt(pkt); + break; + } + vsock->rx_buf_nr++; + } while (vq->num_free); + if (vsock->rx_buf_nr > vsock->rx_buf_max_nr) + vsock->rx_buf_max_nr = vsock->rx_buf_nr; + virtqueue_kick(vq); +} + +static void virtio_transport_tx_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, tx_work); + struct virtqueue *vq; + bool added = false; + + vq = vsock->vqs[VSOCK_VQ_TX]; + mutex_lock(&vsock->tx_lock); + do { + struct virtio_vsock_pkt *pkt; + unsigned int len; + + virtqueue_disable_cb(vq); + while ((pkt = virtqueue_get_buf(vq, &len)) != NULL) { + virtio_transport_free_pkt(pkt); + added = true; + } + } while (!virtqueue_enable_cb(vq)); + mutex_unlock(&vsock->tx_lock); + + if (added) + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); +} + +/* Is there space left for replies to rx packets? */ +static bool virtio_transport_more_replies(struct virtio_vsock *vsock) +{ + struct virtqueue *vq = vsock->vqs[VSOCK_VQ_RX]; + int val; + + smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */ + val = atomic_read(&vsock->queued_replies); + + return val < virtqueue_get_vring_size(vq); +} + +static void virtio_transport_rx_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, rx_work); + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_RX]; + + mutex_lock(&vsock->rx_lock); + + do { + virtqueue_disable_cb(vq); + for (;;) { + struct virtio_vsock_pkt *pkt; + unsigned int len; + + if (!virtio_transport_more_replies(vsock)) { + /* Stop rx until the device processes already + * pending replies. Leave rx virtqueue + * callbacks disabled. + */ + goto out; + } + + pkt = virtqueue_get_buf(vq, &len); + if (!pkt) { + break; + } + + vsock->rx_buf_nr--; + + /* Drop short/long packets */ + if (unlikely(len < sizeof(pkt->hdr) || + len > sizeof(pkt->hdr) + pkt->len)) { + virtio_transport_free_pkt(pkt); + continue; + } + + pkt->len = len - sizeof(pkt->hdr); + virtio_transport_recv_pkt(pkt); + } + } while (!virtqueue_enable_cb(vq)); + +out: + if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) + virtio_vsock_rx_fill(vsock); + mutex_unlock(&vsock->rx_lock); +} + +/* event_lock must be held */ +static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock, + struct virtio_vsock_event *event) +{ + struct scatterlist sg; + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_EVENT]; + + sg_init_one(&sg, event, sizeof(*event)); + + return virtqueue_add_inbuf(vq, &sg, 1, event, GFP_KERNEL); +} + +/* event_lock must be held */ +static void virtio_vsock_event_fill(struct virtio_vsock *vsock) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(vsock->event_list); i++) { + struct virtio_vsock_event *event = &vsock->event_list[i]; + + virtio_vsock_event_fill_one(vsock, event); + } + + virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]); +} + +static void virtio_vsock_reset_sock(struct sock *sk) +{ + lock_sock(sk); + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = ECONNRESET; + sk->sk_error_report(sk); + release_sock(sk); +} + +static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) +{ + struct virtio_device *vdev = vsock->vdev; + u64 guest_cid; + + vdev->config->get(vdev, offsetof(struct virtio_vsock_config, guest_cid), + &guest_cid, sizeof(guest_cid)); + vsock->guest_cid = le64_to_cpu(guest_cid); +} + +/* event_lock must be held */ +static void virtio_vsock_event_handle(struct virtio_vsock *vsock, + struct virtio_vsock_event *event) +{ + switch (le32_to_cpu(event->id)) { + case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET: + virtio_vsock_update_guest_cid(vsock); + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + break; + } +} + +static void virtio_transport_event_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, event_work); + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_EVENT]; + + mutex_lock(&vsock->event_lock); + + do { + struct virtio_vsock_event *event; + unsigned int len; + + virtqueue_disable_cb(vq); + while ((event = virtqueue_get_buf(vq, &len)) != NULL) { + if (len == sizeof(*event)) + virtio_vsock_event_handle(vsock, event); + + virtio_vsock_event_fill_one(vsock, event); + } + } while (!virtqueue_enable_cb(vq)); + + virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]); + + mutex_unlock(&vsock->event_lock); +} + +static void virtio_vsock_event_done(struct virtqueue *vq) +{ + struct virtio_vsock *vsock = vq->vdev->priv; + + if (!vsock) + return; + queue_work(virtio_vsock_workqueue, &vsock->event_work); +} + +static void virtio_vsock_tx_done(struct virtqueue *vq) +{ + struct virtio_vsock *vsock = vq->vdev->priv; + + if (!vsock) + return; + queue_work(virtio_vsock_workqueue, &vsock->tx_work); +} + +static void virtio_vsock_rx_done(struct virtqueue *vq) +{ + struct virtio_vsock *vsock = vq->vdev->priv; + + if (!vsock) + return; + queue_work(virtio_vsock_workqueue, &vsock->rx_work); +} + +static struct virtio_transport virtio_transport = { + .transport = { + .get_local_cid = virtio_transport_get_local_cid, + + .init = virtio_transport_do_socket_init, + .destruct = virtio_transport_destruct, + .release = virtio_transport_release, + .connect = virtio_transport_connect, + .shutdown = virtio_transport_shutdown, + + .dgram_bind = virtio_transport_dgram_bind, + .dgram_dequeue = virtio_transport_dgram_dequeue, + .dgram_enqueue = virtio_transport_dgram_enqueue, + .dgram_allow = virtio_transport_dgram_allow, + + .stream_dequeue = virtio_transport_stream_dequeue, + .stream_enqueue = virtio_transport_stream_enqueue, + .stream_has_data = virtio_transport_stream_has_data, + .stream_has_space = virtio_transport_stream_has_space, + .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, + .stream_is_active = virtio_transport_stream_is_active, + .stream_allow = virtio_transport_stream_allow, + + .notify_poll_in = virtio_transport_notify_poll_in, + .notify_poll_out = virtio_transport_notify_poll_out, + .notify_recv_init = virtio_transport_notify_recv_init, + .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, + .notify_send_init = virtio_transport_notify_send_init, + .notify_send_pre_block = virtio_transport_notify_send_pre_block, + .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + + .set_buffer_size = virtio_transport_set_buffer_size, + .set_min_buffer_size = virtio_transport_set_min_buffer_size, + .set_max_buffer_size = virtio_transport_set_max_buffer_size, + .get_buffer_size = virtio_transport_get_buffer_size, + .get_min_buffer_size = virtio_transport_get_min_buffer_size, + .get_max_buffer_size = virtio_transport_get_max_buffer_size, + }, + + .send_pkt = virtio_transport_send_pkt, +}; + +static int virtio_vsock_probe(struct virtio_device *vdev) +{ + vq_callback_t *callbacks[] = { + virtio_vsock_rx_done, + virtio_vsock_tx_done, + virtio_vsock_event_done, + }; + static const char * const names[] = { + "rx", + "tx", + "event", + }; + struct virtio_vsock *vsock = NULL; + int ret; + + ret = mutex_lock_interruptible(&the_virtio_vsock_mutex); + if (ret) + return ret; + + /* Only one virtio-vsock device per guest is supported */ + if (the_virtio_vsock) { + ret = -EBUSY; + goto out; + } + + vsock = kzalloc(sizeof(*vsock), GFP_KERNEL); + if (!vsock) { + ret = -ENOMEM; + goto out; + } + + vsock->vdev = vdev; + + ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX, + vsock->vqs, callbacks, names); + if (ret < 0) + goto out; + + virtio_vsock_update_guest_cid(vsock); + + ret = vsock_core_init(&virtio_transport.transport); + if (ret < 0) + goto out_vqs; + + vsock->rx_buf_nr = 0; + vsock->rx_buf_max_nr = 0; + atomic_set(&vsock->queued_replies, 0); + + vdev->priv = vsock; + the_virtio_vsock = vsock; + mutex_init(&vsock->tx_lock); + mutex_init(&vsock->rx_lock); + mutex_init(&vsock->event_lock); + spin_lock_init(&vsock->send_pkt_list_lock); + INIT_LIST_HEAD(&vsock->send_pkt_list); + INIT_WORK(&vsock->rx_work, virtio_transport_rx_work); + INIT_WORK(&vsock->tx_work, virtio_transport_tx_work); + INIT_WORK(&vsock->event_work, virtio_transport_event_work); + INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work); + + mutex_lock(&vsock->rx_lock); + virtio_vsock_rx_fill(vsock); + mutex_unlock(&vsock->rx_lock); + + mutex_lock(&vsock->event_lock); + virtio_vsock_event_fill(vsock); + mutex_unlock(&vsock->event_lock); + + mutex_unlock(&the_virtio_vsock_mutex); + return 0; + +out_vqs: + vsock->vdev->config->del_vqs(vsock->vdev); +out: + kfree(vsock); + mutex_unlock(&the_virtio_vsock_mutex); + return ret; +} + +static void virtio_vsock_remove(struct virtio_device *vdev) +{ + struct virtio_vsock *vsock = vdev->priv; + struct virtio_vsock_pkt *pkt; + + flush_work(&vsock->rx_work); + flush_work(&vsock->tx_work); + flush_work(&vsock->event_work); + flush_work(&vsock->send_pkt_work); + + vdev->config->reset(vdev); + + mutex_lock(&vsock->rx_lock); + while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) + virtio_transport_free_pkt(pkt); + mutex_unlock(&vsock->rx_lock); + + mutex_lock(&vsock->tx_lock); + while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX]))) + virtio_transport_free_pkt(pkt); + mutex_unlock(&vsock->tx_lock); + + spin_lock_bh(&vsock->send_pkt_list_lock); + while (!list_empty(&vsock->send_pkt_list)) { + pkt = list_first_entry(&vsock->send_pkt_list, + struct virtio_vsock_pkt, list); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + spin_unlock_bh(&vsock->send_pkt_list_lock); + + mutex_lock(&the_virtio_vsock_mutex); + the_virtio_vsock = NULL; + vsock_core_exit(); + mutex_unlock(&the_virtio_vsock_mutex); + + vdev->config->del_vqs(vdev); + + kfree(vsock); +} + +static struct virtio_device_id id_table[] = { + { VIRTIO_ID_VSOCK, VIRTIO_DEV_ANY_ID }, + { 0 }, +}; + +static unsigned int features[] = { +}; + +static struct virtio_driver virtio_vsock_driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .driver.name = KBUILD_MODNAME, + .driver.owner = THIS_MODULE, + .id_table = id_table, + .probe = virtio_vsock_probe, + .remove = virtio_vsock_remove, +}; + +static int __init virtio_vsock_init(void) +{ + int ret; + + virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); + if (!virtio_vsock_workqueue) + return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); + if (ret) + destroy_workqueue(virtio_vsock_workqueue); + return ret; +} + +static void __exit virtio_vsock_exit(void) +{ + unregister_virtio_driver(&virtio_vsock_driver); + destroy_workqueue(virtio_vsock_workqueue); +} + +module_init(virtio_vsock_init); +module_exit(virtio_vsock_exit); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Asias He"); +MODULE_DESCRIPTION("virtio transport for vsock"); +MODULE_DEVICE_TABLE(virtio, id_table); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c new file mode 100644 index 000000000000..a53b3a16b4f1 --- /dev/null +++ b/net/vmw_vsock/virtio_transport_common.c @@ -0,0 +1,992 @@ +/* + * common code for virtio vsock + * + * Copyright (C) 2013-2015 Red Hat, Inc. + * Author: Asias He <asias@redhat.com> + * Stefan Hajnoczi <stefanha@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ +#include <linux/spinlock.h> +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/list.h> +#include <linux/virtio.h> +#include <linux/virtio_ids.h> +#include <linux/virtio_config.h> +#include <linux/virtio_vsock.h> + +#include <net/sock.h> +#include <net/af_vsock.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/vsock_virtio_transport_common.h> + +/* How long to wait for graceful shutdown of a connection */ +#define VSOCK_CLOSE_TIMEOUT (8 * HZ) + +static const struct virtio_transport *virtio_transport_get_ops(void) +{ + const struct vsock_transport *t = vsock_core_get_transport(); + + return container_of(t, struct virtio_transport, transport); +} + +struct virtio_vsock_pkt * +virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, + size_t len, + u32 src_cid, + u32 src_port, + u32 dst_cid, + u32 dst_port) +{ + struct virtio_vsock_pkt *pkt; + int err; + + pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return NULL; + + pkt->hdr.type = cpu_to_le16(info->type); + pkt->hdr.op = cpu_to_le16(info->op); + pkt->hdr.src_cid = cpu_to_le64(src_cid); + pkt->hdr.dst_cid = cpu_to_le64(dst_cid); + pkt->hdr.src_port = cpu_to_le32(src_port); + pkt->hdr.dst_port = cpu_to_le32(dst_port); + pkt->hdr.flags = cpu_to_le32(info->flags); + pkt->len = len; + pkt->hdr.len = cpu_to_le32(len); + pkt->reply = info->reply; + + if (info->msg && len > 0) { + pkt->buf = kmalloc(len, GFP_KERNEL); + if (!pkt->buf) + goto out_pkt; + err = memcpy_from_msg(pkt->buf, info->msg, len); + if (err) + goto out; + } + + trace_virtio_transport_alloc_pkt(src_cid, src_port, + dst_cid, dst_port, + len, + info->type, + info->op, + info->flags); + + return pkt; + +out: + kfree(pkt->buf); +out_pkt: + kfree(pkt); + return NULL; +} +EXPORT_SYMBOL_GPL(virtio_transport_alloc_pkt); + +static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, + struct virtio_vsock_pkt_info *info) +{ + u32 src_cid, src_port, dst_cid, dst_port; + struct virtio_vsock_sock *vvs; + struct virtio_vsock_pkt *pkt; + u32 pkt_len = info->pkt_len; + + src_cid = vm_sockets_get_local_cid(); + src_port = vsk->local_addr.svm_port; + if (!info->remote_cid) { + dst_cid = vsk->remote_addr.svm_cid; + dst_port = vsk->remote_addr.svm_port; + } else { + dst_cid = info->remote_cid; + dst_port = info->remote_port; + } + + vvs = vsk->trans; + + /* we can send less than pkt_len bytes */ + if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE) + pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + + /* virtio_transport_get_credit might return less than pkt_len credit */ + pkt_len = virtio_transport_get_credit(vvs, pkt_len); + + /* Do not send zero length OP_RW pkt */ + if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW) + return pkt_len; + + pkt = virtio_transport_alloc_pkt(info, pkt_len, + src_cid, src_port, + dst_cid, dst_port); + if (!pkt) { + virtio_transport_put_credit(vvs, pkt_len); + return -ENOMEM; + } + + virtio_transport_inc_tx_pkt(vvs, pkt); + + return virtio_transport_get_ops()->send_pkt(pkt); +} + +static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, + struct virtio_vsock_pkt *pkt) +{ + vvs->rx_bytes += pkt->len; +} + +static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, + struct virtio_vsock_pkt *pkt) +{ + vvs->rx_bytes -= pkt->len; + vvs->fwd_cnt += pkt->len; +} + +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) +{ + spin_lock_bh(&vvs->tx_lock); + pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); + pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); + spin_unlock_bh(&vvs->tx_lock); +} +EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); + +u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) +{ + u32 ret; + + spin_lock_bh(&vvs->tx_lock); + ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + if (ret > credit) + ret = credit; + vvs->tx_cnt += ret; + spin_unlock_bh(&vvs->tx_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_credit); + +void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) +{ + spin_lock_bh(&vvs->tx_lock); + vvs->tx_cnt -= credit; + spin_unlock_bh(&vvs->tx_lock); +} +EXPORT_SYMBOL_GPL(virtio_transport_put_credit); + +static int virtio_transport_send_credit_update(struct vsock_sock *vsk, + int type, + struct virtio_vsock_hdr *hdr) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, + .type = type, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +static ssize_t +virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + size_t bytes, total = 0; + int err = -EFAULT; + + spin_lock_bh(&vvs->rx_lock); + while (total < len && !list_empty(&vvs->rx_queue)) { + pkt = list_first_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + bytes = len - total; + if (bytes > pkt->len - pkt->off) + bytes = pkt->len - pkt->off; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes); + if (err) + goto out; + + spin_lock_bh(&vvs->rx_lock); + + total += bytes; + pkt->off += bytes; + if (pkt->off == pkt->len) { + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + } + spin_unlock_bh(&vvs->rx_lock); + + /* Send a credit pkt to peer */ + virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, + NULL); + + return total; + +out: + if (total) + err = total; + return err; +} + +ssize_t +virtio_transport_stream_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_stream_do_dequeue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); + +int +virtio_transport_dgram_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue); + +s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + spin_lock_bh(&vvs->rx_lock); + bytes = vvs->rx_bytes; + spin_unlock_bh(&vvs->rx_lock); + + return bytes; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); + +static s64 virtio_transport_has_space(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + if (bytes < 0) + bytes = 0; + + return bytes; +} + +s64 virtio_transport_stream_has_space(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + spin_lock_bh(&vvs->tx_lock); + bytes = virtio_transport_has_space(vsk); + spin_unlock_bh(&vvs->tx_lock); + + return bytes; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_has_space); + +int virtio_transport_do_socket_init(struct vsock_sock *vsk, + struct vsock_sock *psk) +{ + struct virtio_vsock_sock *vvs; + + vvs = kzalloc(sizeof(*vvs), GFP_KERNEL); + if (!vvs) + return -ENOMEM; + + vsk->trans = vvs; + vvs->vsk = vsk; + if (psk) { + struct virtio_vsock_sock *ptrans = psk->trans; + + vvs->buf_size = ptrans->buf_size; + vvs->buf_size_min = ptrans->buf_size_min; + vvs->buf_size_max = ptrans->buf_size_max; + vvs->peer_buf_alloc = ptrans->peer_buf_alloc; + } else { + vvs->buf_size = VIRTIO_VSOCK_DEFAULT_BUF_SIZE; + vvs->buf_size_min = VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE; + vvs->buf_size_max = VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE; + } + + vvs->buf_alloc = vvs->buf_size; + + spin_lock_init(&vvs->rx_lock); + spin_lock_init(&vvs->tx_lock); + INIT_LIST_HEAD(&vvs->rx_queue); + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init); + +u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_buffer_size); + +u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size_min; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_min_buffer_size); + +u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size_max; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_max_buffer_size); + +void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val < vvs->buf_size_min) + vvs->buf_size_min = val; + if (val > vvs->buf_size_max) + vvs->buf_size_max = val; + vvs->buf_size = val; + vvs->buf_alloc = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size); + +void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val > vvs->buf_size) + vvs->buf_size = val; + vvs->buf_size_min = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_min_buffer_size); + +void virtio_transport_set_max_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val < vvs->buf_size) + vvs->buf_size = val; + vvs->buf_size_max = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_max_buffer_size); + +int +virtio_transport_notify_poll_in(struct vsock_sock *vsk, + size_t target, + bool *data_ready_now) +{ + if (vsock_stream_has_data(vsk)) + *data_ready_now = true; + else + *data_ready_now = false; + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_in); + +int +virtio_transport_notify_poll_out(struct vsock_sock *vsk, + size_t target, + bool *space_avail_now) +{ + s64 free_space; + + free_space = vsock_stream_has_space(vsk); + if (free_space > 0) + *space_avail_now = true; + else if (free_space == 0) + *space_avail_now = false; + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_out); + +int virtio_transport_notify_recv_init(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_init); + +int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_block); + +int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_dequeue); + +int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk, + size_t target, ssize_t copied, bool data_read, + struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_post_dequeue); + +int virtio_transport_notify_send_init(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_init); + +int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_block); + +int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_enqueue); + +int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, + ssize_t written, struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue); + +u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat); + +bool virtio_transport_stream_is_active(struct vsock_sock *vsk) +{ + return true; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active); + +bool virtio_transport_stream_allow(u32 cid, u32 port) +{ + return true; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_allow); + +int virtio_transport_dgram_bind(struct vsock_sock *vsk, + struct sockaddr_vm *addr) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind); + +bool virtio_transport_dgram_allow(u32 cid, u32 port) +{ + return false; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow); + +int virtio_transport_connect(struct vsock_sock *vsk) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_REQUEST, + .type = VIRTIO_VSOCK_TYPE_STREAM, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_connect); + +int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_SHUTDOWN, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .flags = (mode & RCV_SHUTDOWN ? + VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | + (mode & SEND_SHUTDOWN ? + VIRTIO_VSOCK_SHUTDOWN_SEND : 0), + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_shutdown); + +int +virtio_transport_dgram_enqueue(struct vsock_sock *vsk, + struct sockaddr_vm *remote_addr, + struct msghdr *msg, + size_t dgram_len) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue); + +ssize_t +virtio_transport_stream_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RW, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .msg = msg, + .pkt_len = len, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue); + +void virtio_transport_destruct(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + kfree(vvs); +} +EXPORT_SYMBOL_GPL(virtio_transport_destruct); + +static int virtio_transport_reset(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RST, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .reply = !!pkt, + }; + + /* Send RST only if the original pkt is not a RST pkt */ + if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + return 0; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +/* Normally packets are associated with a socket. There may be no socket if an + * attempt was made to connect to a socket that does not exist. + */ +static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RST, + .type = le16_to_cpu(pkt->hdr.type), + .reply = true, + }; + + /* Send RST only if the original pkt is not a RST pkt */ + if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + return 0; + + pkt = virtio_transport_alloc_pkt(&info, 0, + le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port), + le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + if (!pkt) + return -ENOMEM; + + return virtio_transport_get_ops()->send_pkt(pkt); +} + +static void virtio_transport_wait_close(struct sock *sk, long timeout) +{ + if (timeout) { + DEFINE_WAIT(wait); + + do { + prepare_to_wait(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); + if (sk_wait_event(sk, &timeout, + sock_flag(sk, SOCK_DONE))) + break; + } while (!signal_pending(current) && timeout); + + finish_wait(sk_sleep(sk), &wait); + } +} + +static void virtio_transport_do_close(struct vsock_sock *vsk, + bool cancel_timeout) +{ + struct sock *sk = sk_vsock(vsk); + + sock_set_flag(sk, SOCK_DONE); + vsk->peer_shutdown = SHUTDOWN_MASK; + if (vsock_stream_has_data(vsk) <= 0) + sk->sk_state = SS_DISCONNECTING; + sk->sk_state_change(sk); + + if (vsk->close_work_scheduled && + (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) { + vsk->close_work_scheduled = false; + + vsock_remove_sock(vsk); + + /* Release refcnt obtained when we scheduled the timeout */ + sock_put(sk); + } +} + +static void virtio_transport_close_timeout(struct work_struct *work) +{ + struct vsock_sock *vsk = + container_of(work, struct vsock_sock, close_work.work); + struct sock *sk = sk_vsock(vsk); + + sock_hold(sk); + lock_sock(sk); + + if (!sock_flag(sk, SOCK_DONE)) { + (void)virtio_transport_reset(vsk, NULL); + + virtio_transport_do_close(vsk, false); + } + + vsk->close_work_scheduled = false; + + release_sock(sk); + sock_put(sk); +} + +/* User context, vsk->sk is locked */ +static bool virtio_transport_close(struct vsock_sock *vsk) +{ + struct sock *sk = &vsk->sk; + + if (!(sk->sk_state == SS_CONNECTED || + sk->sk_state == SS_DISCONNECTING)) + return true; + + /* Already received SHUTDOWN from peer, reply with RST */ + if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) { + (void)virtio_transport_reset(vsk, NULL); + return true; + } + + if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK) + (void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK); + + if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) + virtio_transport_wait_close(sk, sk->sk_lingertime); + + if (sock_flag(sk, SOCK_DONE)) { + return true; + } + + sock_hold(sk); + INIT_DELAYED_WORK(&vsk->close_work, + virtio_transport_close_timeout); + vsk->close_work_scheduled = true; + schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT); + return false; +} + +void virtio_transport_release(struct vsock_sock *vsk) +{ + struct sock *sk = &vsk->sk; + bool remove_sock = true; + + lock_sock(sk); + if (sk->sk_type == SOCK_STREAM) + remove_sock = virtio_transport_close(vsk); + release_sock(sk); + + if (remove_sock) + vsock_remove_sock(vsk); +} +EXPORT_SYMBOL_GPL(virtio_transport_release); + +static int +virtio_transport_recv_connecting(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + int err; + int skerr; + + switch (le16_to_cpu(pkt->hdr.op)) { + case VIRTIO_VSOCK_OP_RESPONSE: + sk->sk_state = SS_CONNECTED; + sk->sk_socket->state = SS_CONNECTED; + vsock_insert_connected(vsk); + sk->sk_state_change(sk); + break; + case VIRTIO_VSOCK_OP_INVALID: + break; + case VIRTIO_VSOCK_OP_RST: + skerr = ECONNRESET; + err = 0; + goto destroy; + default: + skerr = EPROTO; + err = -EINVAL; + goto destroy; + } + return 0; + +destroy: + virtio_transport_reset(vsk, pkt); + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = skerr; + sk->sk_error_report(sk); + return err; +} + +static int +virtio_transport_recv_connected(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct virtio_vsock_sock *vvs = vsk->trans; + int err = 0; + + switch (le16_to_cpu(pkt->hdr.op)) { + case VIRTIO_VSOCK_OP_RW: + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + virtio_transport_inc_rx_pkt(vvs, pkt); + list_add_tail(&pkt->list, &vvs->rx_queue); + spin_unlock_bh(&vvs->rx_lock); + + sk->sk_data_ready(sk); + return err; + case VIRTIO_VSOCK_OP_CREDIT_UPDATE: + sk->sk_write_space(sk); + break; + case VIRTIO_VSOCK_OP_SHUTDOWN: + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV) + vsk->peer_shutdown |= RCV_SHUTDOWN; + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) + vsk->peer_shutdown |= SEND_SHUTDOWN; + if (vsk->peer_shutdown == SHUTDOWN_MASK && + vsock_stream_has_data(vsk) <= 0) + sk->sk_state = SS_DISCONNECTING; + if (le32_to_cpu(pkt->hdr.flags)) + sk->sk_state_change(sk); + break; + case VIRTIO_VSOCK_OP_RST: + virtio_transport_do_close(vsk, true); + break; + default: + err = -EINVAL; + break; + } + + virtio_transport_free_pkt(pkt); + return err; +} + +static void +virtio_transport_recv_disconnecting(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + virtio_transport_do_close(vsk, true); +} + +static int +virtio_transport_send_response(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RESPONSE, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .remote_cid = le32_to_cpu(pkt->hdr.src_cid), + .remote_port = le32_to_cpu(pkt->hdr.src_port), + .reply = true, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +/* Handle server socket */ +static int +virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct vsock_sock *vchild; + struct sock *child; + + if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { + virtio_transport_reset(vsk, pkt); + return -EINVAL; + } + + if (sk_acceptq_is_full(sk)) { + virtio_transport_reset(vsk, pkt); + return -ENOMEM; + } + + child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL, + sk->sk_type, 0); + if (!child) { + virtio_transport_reset(vsk, pkt); + return -ENOMEM; + } + + sk->sk_ack_backlog++; + + lock_sock_nested(child, SINGLE_DEPTH_NESTING); + + child->sk_state = SS_CONNECTED; + + vchild = vsock_sk(child); + vsock_addr_init(&vchild->local_addr, le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port)); + vsock_addr_init(&vchild->remote_addr, le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + + vsock_insert_connected(vchild); + vsock_enqueue_accept(sk, child); + virtio_transport_send_response(vchild, pkt); + + release_sock(child); + + sk->sk_data_ready(sk); + return 0; +} + +static bool virtio_transport_space_update(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct virtio_vsock_sock *vvs = vsk->trans; + bool space_available; + + /* buf_alloc and fwd_cnt is always included in the hdr */ + spin_lock_bh(&vvs->tx_lock); + vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc); + vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt); + space_available = virtio_transport_has_space(vsk); + spin_unlock_bh(&vvs->tx_lock); + return space_available; +} + +/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex + * lock. + */ +void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) +{ + struct sockaddr_vm src, dst; + struct vsock_sock *vsk; + struct sock *sk; + bool space_available; + + vsock_addr_init(&src, le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + vsock_addr_init(&dst, le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port)); + + trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port, + dst.svm_cid, dst.svm_port, + le32_to_cpu(pkt->hdr.len), + le16_to_cpu(pkt->hdr.type), + le16_to_cpu(pkt->hdr.op), + le32_to_cpu(pkt->hdr.flags), + le32_to_cpu(pkt->hdr.buf_alloc), + le32_to_cpu(pkt->hdr.fwd_cnt)); + + if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { + (void)virtio_transport_reset_no_sock(pkt); + goto free_pkt; + } + + /* The socket must be in connected or bound table + * otherwise send reset back + */ + sk = vsock_find_connected_socket(&src, &dst); + if (!sk) { + sk = vsock_find_bound_socket(&dst); + if (!sk) { + (void)virtio_transport_reset_no_sock(pkt); + goto free_pkt; + } + } + + vsk = vsock_sk(sk); + + space_available = virtio_transport_space_update(sk, pkt); + + lock_sock(sk); + + /* Update CID in case it has changed after a transport reset event */ + vsk->local_addr.svm_cid = dst.svm_cid; + + if (space_available) + sk->sk_write_space(sk); + + switch (sk->sk_state) { + case VSOCK_SS_LISTEN: + virtio_transport_recv_listen(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + case SS_CONNECTING: + virtio_transport_recv_connecting(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + case SS_CONNECTED: + virtio_transport_recv_connected(sk, pkt); + break; + case SS_DISCONNECTING: + virtio_transport_recv_disconnecting(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + default: + virtio_transport_free_pkt(pkt); + break; + } + release_sock(sk); + + /* Release refcnt obtained when we fetched this socket out of the + * bound or connected list. + */ + sock_put(sk); + return; + +free_pkt: + virtio_transport_free_pkt(pkt); +} +EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt); + +void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt) +{ + kfree(pkt->buf); + kfree(pkt); +} +EXPORT_SYMBOL_GPL(virtio_transport_free_pkt); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Asias He"); +MODULE_DESCRIPTION("common code for virtio vsock"); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 4120b7a538be..4be4fbbc0b50 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1644,6 +1644,8 @@ static void vmci_transport_destruct(struct vsock_sock *vsk) static void vmci_transport_release(struct vsock_sock *vsk) { + vsock_remove_sock(vsk); + if (!vmci_handle_is_invalid(vmci_trans(vsk)->dg_handle)) { vmci_datagram_destroy_handle(vmci_trans(vsk)->dg_handle); vmci_trans(vsk)->dg_handle = VMCI_INVALID_HANDLE; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index bb3d64ee68aa..0f506220a3bd 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -716,7 +716,7 @@ static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, ASSERT_RTNL(); - if (!config_enabled(CONFIG_CFG80211_REG_RELAX_NO_IR) || + if (!IS_ENABLED(CONFIG_CFG80211_REG_RELAX_NO_IR) || !(wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR)) return false; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f02653a08993..4809f4d2cdcc 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6978,7 +6978,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) params.n_counter_offsets_presp = len / sizeof(u16); if (rdev->wiphy.max_num_csa_counters && - (params.n_counter_offsets_beacon > + (params.n_counter_offsets_presp > rdev->wiphy.max_num_csa_counters)) return -EINVAL; diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index dbb2738e356a..6250b1cfcde5 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -958,29 +958,8 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, return private(dev, iwr, cmd, info, handler); } /* Old driver API : call driver ioctl handler */ - if (dev->netdev_ops->ndo_do_ioctl) { -#ifdef CONFIG_COMPAT - if (info->flags & IW_REQUEST_FLAG_COMPAT) { - int ret = 0; - struct iwreq iwr_lcl; - struct compat_iw_point *iwp_compat = (void *) &iwr->u.data; - - memcpy(&iwr_lcl, iwr, sizeof(struct iwreq)); - iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer); - iwr_lcl.u.data.length = iwp_compat->length; - iwr_lcl.u.data.flags = iwp_compat->flags; - - ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd); - - iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer); - iwp_compat->length = iwr_lcl.u.data.length; - iwp_compat->flags = iwr_lcl.u.data.flags; - - return ret; - } else -#endif - return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); - } + if (dev->netdev_ops->ndo_do_ioctl) + return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 1c4ad477ce93..6e3f0254d8a1 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -207,15 +207,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) family = XFRM_SPI_SKB_CB(skb)->family; /* if tunnel is present override skb->mark value with tunnel i_key */ - if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) { - switch (family) { - case AF_INET: + switch (family) { + case AF_INET: + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key); - break; - case AF_INET6: + break; + case AF_INET6: + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key); - break; - } + break; } /* Allocate new secpath or COW existing one. */ diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b5e665b3cfb0..45f9cf97ea25 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -626,6 +626,10 @@ static void xfrm_hash_rebuild(struct work_struct *work) /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { + if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { + /* skip socket policies */ + continue; + } newpos = NULL; chain = policy_hash_bysel(net, &policy->selector, policy->family, diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d516845e16e3..cb65d916a345 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -896,7 +896,8 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb) struct sock *sk = cb->skb->sk; struct net *net = sock_net(sk); - xfrm_state_walk_done(walk, net); + if (cb->args[0]) + xfrm_state_walk_done(walk, net); return 0; } @@ -921,8 +922,6 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) u8 proto = 0; int err; - cb->args[0] = 1; - err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, xfrma_policy); if (err < 0) @@ -939,6 +938,7 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) proto = nla_get_u8(attrs[XFRMA_PROTO]); xfrm_state_walk_init(walk, proto, filter); + cb->args[0] = 1; } (void) xfrm_state_walk(net, walk, dump_one_state, &info); @@ -2051,9 +2051,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (up->hard) { xfrm_policy_delete(xp, p->dir); xfrm_audit_policy_delete(xp, 1, true); - } else { - // reset the timers here? - WARN(1, "Don't know what to do with soft policy expire\n"); } km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid); @@ -2117,7 +2114,7 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, err = verify_newpolicy_info(&ua->policy); if (err) - goto bad_policy; + goto free_state; /* build an XP */ xp = xfrm_policy_construct(net, &ua->policy, attrs, &err); @@ -2149,8 +2146,6 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; -bad_policy: - WARN(1, "BAD policy passed\n"); free_state: kfree(x); nomem: |
