diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/ceph/debugfs.c | 20 | ||||
-rw-r--r-- | net/ceph/mon_client.c | 8 | ||||
-rw-r--r-- | net/ceph/osd_client.c | 82 | ||||
-rw-r--r-- | net/core/dev.c | 3 | ||||
-rw-r--r-- | net/dsa/port.c | 7 | ||||
-rw-r--r-- | net/ipv6/ipv6_sockglue.c | 13 | ||||
-rw-r--r-- | net/ipv6/rpl.c | 7 | ||||
-rw-r--r-- | net/ipv6/seg6.c | 2 | ||||
-rw-r--r-- | net/mac80211/main.c | 24 | ||||
-rw-r--r-- | net/mac80211/mesh.c | 11 | ||||
-rw-r--r-- | net/mptcp/protocol.c | 19 | ||||
-rw-r--r-- | net/mptcp/protocol.h | 8 | ||||
-rw-r--r-- | net/mptcp/subflow.c | 99 | ||||
-rw-r--r-- | net/netfilter/Makefile | 2 | ||||
-rw-r--r-- | net/netfilter/nf_tables_api.c | 2 | ||||
-rw-r--r-- | net/netfilter/nft_set_pipapo.c | 2 | ||||
-rw-r--r-- | net/netfilter/nft_set_pipapo_avx2.h | 4 | ||||
-rw-r--r-- | net/netrom/nr_route.c | 1 | ||||
-rw-r--r-- | net/openvswitch/conntrack.c | 3 | ||||
-rw-r--r-- | net/openvswitch/datapath.c | 4 | ||||
-rw-r--r-- | net/rds/message.c | 19 | ||||
-rw-r--r-- | net/rds/rdma.c | 12 | ||||
-rw-r--r-- | net/rds/rds.h | 3 | ||||
-rw-r--r-- | net/rds/send.c | 6 | ||||
-rw-r--r-- | net/rxrpc/local_object.c | 9 | ||||
-rw-r--r-- | net/rxrpc/output.c | 44 | ||||
-rw-r--r-- | net/tipc/crypto.c | 1 | ||||
-rw-r--r-- | net/tipc/link.c | 2 | ||||
-rw-r--r-- | net/tipc/node.c | 4 | ||||
-rw-r--r-- | net/wireless/nl80211.c | 6 | ||||
-rw-r--r-- | net/xdp/xdp_umem.c | 5 |
31 files changed, 193 insertions, 239 deletions
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 7cb992e55475..1344f232ecc5 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -383,11 +383,11 @@ static int client_options_show(struct seq_file *s, void *p) return 0; } -CEPH_DEFINE_SHOW_FUNC(monmap_show) -CEPH_DEFINE_SHOW_FUNC(osdmap_show) -CEPH_DEFINE_SHOW_FUNC(monc_show) -CEPH_DEFINE_SHOW_FUNC(osdc_show) -CEPH_DEFINE_SHOW_FUNC(client_options_show) +DEFINE_SHOW_ATTRIBUTE(monmap); +DEFINE_SHOW_ATTRIBUTE(osdmap); +DEFINE_SHOW_ATTRIBUTE(monc); +DEFINE_SHOW_ATTRIBUTE(osdc); +DEFINE_SHOW_ATTRIBUTE(client_options); void __init ceph_debugfs_init(void) { @@ -414,31 +414,31 @@ void ceph_debugfs_client_init(struct ceph_client *client) 0400, client->debugfs_dir, client, - &monc_show_fops); + &monc_fops); client->osdc.debugfs_file = debugfs_create_file("osdc", 0400, client->debugfs_dir, client, - &osdc_show_fops); + &osdc_fops); client->debugfs_monmap = debugfs_create_file("monmap", 0400, client->debugfs_dir, client, - &monmap_show_fops); + &monmap_fops); client->debugfs_osdmap = debugfs_create_file("osdmap", 0400, client->debugfs_dir, client, - &osdmap_show_fops); + &osdmap_fops); client->debugfs_options = debugfs_create_file("client_options", 0400, client->debugfs_dir, client, - &client_options_show_fops); + &client_options_fops); } void ceph_debugfs_client_cleanup(struct ceph_client *client) diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 9d9e4e4ea600..3d8c8015e976 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -467,7 +467,7 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, struct ceph_msg *msg) { struct ceph_client *client = monc->client; - struct ceph_monmap *monmap = NULL, *old = monc->monmap; + struct ceph_monmap *monmap; void *p, *end; mutex_lock(&monc->mutex); @@ -484,13 +484,13 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, goto out; } - if (ceph_check_fsid(monc->client, &monmap->fsid) < 0) { + if (ceph_check_fsid(client, &monmap->fsid) < 0) { kfree(monmap); goto out; } - client->monc.monmap = monmap; - kfree(old); + kfree(monc->monmap); + monc->monmap = monmap; __ceph_monc_got_map(monc, CEPH_SUB_MONMAP, monc->monmap->epoch); client->have_fsid = true; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index af868d3923b9..998e26b75a78 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3483,9 +3483,6 @@ static int ceph_redirect_decode(void **p, void *end, goto e_inval; } - len = ceph_decode_32(p); - *p += len; /* skip osd_instructions */ - /* skip the rest */ *p = struct_end; out: @@ -5228,85 +5225,6 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc) ceph_msgpool_destroy(&osdc->msgpool_op_reply); } -/* - * Read some contiguous pages. If we cross a stripe boundary, shorten - * *plen. Return number of bytes read, or error. - */ -int ceph_osdc_readpages(struct ceph_osd_client *osdc, - struct ceph_vino vino, struct ceph_file_layout *layout, - u64 off, u64 *plen, - u32 truncate_seq, u64 truncate_size, - struct page **pages, int num_pages, int page_align) -{ - struct ceph_osd_request *req; - int rc = 0; - - dout("readpages on ino %llx.%llx on %llu~%llu\n", vino.ino, - vino.snap, off, *plen); - req = ceph_osdc_new_request(osdc, layout, vino, off, plen, 0, 1, - CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, - NULL, truncate_seq, truncate_size, - false); - if (IS_ERR(req)) - return PTR_ERR(req); - - /* it may be a short read due to an object boundary */ - osd_req_op_extent_osd_data_pages(req, 0, - pages, *plen, page_align, false, false); - - dout("readpages final extent is %llu~%llu (%llu bytes align %d)\n", - off, *plen, *plen, page_align); - - rc = ceph_osdc_start_request(osdc, req, false); - if (!rc) - rc = ceph_osdc_wait_request(osdc, req); - - ceph_osdc_put_request(req); - dout("readpages result %d\n", rc); - return rc; -} -EXPORT_SYMBOL(ceph_osdc_readpages); - -/* - * do a synchronous write on N pages - */ -int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, - struct ceph_file_layout *layout, - struct ceph_snap_context *snapc, - u64 off, u64 len, - u32 truncate_seq, u64 truncate_size, - struct timespec64 *mtime, - struct page **pages, int num_pages) -{ - struct ceph_osd_request *req; - int rc = 0; - int page_align = off & ~PAGE_MASK; - - req = ceph_osdc_new_request(osdc, layout, vino, off, &len, 0, 1, - CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, - snapc, truncate_seq, truncate_size, - true); - if (IS_ERR(req)) - return PTR_ERR(req); - - /* it may be a short write due to an object boundary */ - osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align, - false, false); - dout("writepages %llu~%llu (%llu bytes)\n", off, len, len); - - req->r_mtime = *mtime; - rc = ceph_osdc_start_request(osdc, req, true); - if (!rc) - rc = ceph_osdc_wait_request(osdc, req); - - ceph_osdc_put_request(req); - if (rc == 0) - rc = len; - dout("writepages result %d\n", rc); - return rc; -} -EXPORT_SYMBOL(ceph_osdc_writepages); - static int osd_req_op_copy_from_init(struct ceph_osd_request *req, u64 src_snapid, u64 src_version, struct ceph_object_id *src_oid, diff --git a/net/core/dev.c b/net/core/dev.c index df8097b8e286..522288177bbd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8667,8 +8667,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, const struct net_device_ops *ops = dev->netdev_ops; enum bpf_netdev_command query; u32 prog_id, expected_id = 0; - struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; + struct bpf_prog *prog; bool offload; int err; @@ -8734,6 +8734,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, } else { if (!prog_id) return 0; + prog = NULL; } err = dev_xdp_install(dev, bpf_op, extack, flags, prog); diff --git a/net/dsa/port.c b/net/dsa/port.c index 231b2d494f1c..a58fdd362574 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -670,11 +670,16 @@ int dsa_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; struct device_node *phy_np; + int port = dp->index; if (!ds->ops->adjust_link) { phy_np = of_parse_phandle(dp->dn, "phy-handle", 0); - if (of_phy_is_fixed_link(dp->dn) || phy_np) + if (of_phy_is_fixed_link(dp->dn) || phy_np) { + if (ds->ops->phylink_mac_link_down) + ds->ops->phylink_mac_link_down(ds, port, + MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); return dsa_port_phylink_register(dp); + } return 0; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index debdaeba5d8c..18d05403d3b5 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -183,15 +183,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol == IPPROTO_TCP) { - if (sk->sk_prot != &tcpv6_prot) { - retv = -EBUSY; - break; - } - break; - } else { + } + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; break; } + if (sk->sk_protocol != IPPROTO_TCP) + break; if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index d38b476fc7f2..307f336b5353 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -8,6 +8,7 @@ #include <net/rpl.h> #define IPV6_PFXTAIL_LEN(x) (sizeof(struct in6_addr) - (x)) +#define IPV6_RPL_BEST_ADDR_COMPRESSION 15 static void ipv6_rpl_addr_decompress(struct in6_addr *dst, const struct in6_addr *daddr, @@ -73,7 +74,7 @@ static unsigned char ipv6_rpl_srh_calc_cmpri(const struct ipv6_rpl_sr_hdr *inhdr } } - return plen; + return IPV6_RPL_BEST_ADDR_COMPRESSION; } static unsigned char ipv6_rpl_srh_calc_cmpre(const struct in6_addr *daddr, @@ -83,10 +84,10 @@ static unsigned char ipv6_rpl_srh_calc_cmpre(const struct in6_addr *daddr, for (plen = 0; plen < sizeof(*daddr); plen++) { if (daddr->s6_addr[plen] != last_segment->s6_addr[plen]) - break; + return plen; } - return plen; + return IPV6_RPL_BEST_ADDR_COMPRESSION; } void ipv6_rpl_srh_compress(struct ipv6_rpl_sr_hdr *outhdr, diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 75421a472d25..4c7e0a27fa9c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -434,7 +434,7 @@ static struct genl_family seg6_genl_family __ro_after_init = { int __init seg6_init(void) { - int err = -ENOMEM; + int err; err = genl_register_family(&seg6_genl_family); if (err) diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 8345926193de..0e9ad60fb2b3 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1069,7 +1069,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC; if (hw->max_signal <= 0) { result = -EINVAL; - goto fail_wiphy_register; + goto fail_workqueue; } } @@ -1135,7 +1135,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) result = ieee80211_init_cipher_suites(local); if (result < 0) - goto fail_wiphy_register; + goto fail_workqueue; if (!local->ops->remain_on_channel) local->hw.wiphy->max_remain_on_channel_duration = 5000; @@ -1161,10 +1161,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; - result = wiphy_register(local->hw.wiphy); - if (result < 0) - goto fail_wiphy_register; - /* * We use the number of queues for feature tests (QoS, HT) internally * so restrict them appropriately. @@ -1217,9 +1213,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_flows; rtnl_lock(); - result = ieee80211_init_rate_ctrl_alg(local, hw->rate_control_algorithm); + rtnl_unlock(); if (result < 0) { wiphy_debug(local->hw.wiphy, "Failed to initialize rate control algorithm\n"); @@ -1273,6 +1269,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->sband_allocated |= BIT(band); } + result = wiphy_register(local->hw.wiphy); + if (result < 0) + goto fail_wiphy_register; + + rtnl_lock(); + /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && !ieee80211_hw_check(hw, NO_AUTO_VIF)) { @@ -1312,17 +1314,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) #if defined(CONFIG_INET) || defined(CONFIG_IPV6) fail_ifa: #endif + wiphy_unregister(local->hw.wiphy); + fail_wiphy_register: rtnl_lock(); rate_control_deinitialize(local); ieee80211_remove_interfaces(local); - fail_rate: rtnl_unlock(); + fail_rate: fail_flows: ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: - wiphy_unregister(local->hw.wiphy); - fail_wiphy_register: if (local->wiphy_ciphers_allocated) kfree(local->hw.wiphy->cipher_suites); kfree(local->int_scan_req); @@ -1372,8 +1374,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue_unreliable); skb_queue_purge(&local->skb_queue_tdls_chsw); - destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); + destroy_workqueue(local->workqueue); ieee80211_led_exit(local); kfree(local->int_scan_req); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index d09b3c789314..36978a0e5000 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1257,15 +1257,15 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal) mesh_neighbour_update(sdata, mgmt->sa, &elems, rx_status); + + if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && + !sdata->vif.csa_active) + ieee80211_mesh_process_chnswitch(sdata, &elems, true); } if (ifmsh->sync_ops) ifmsh->sync_ops->rx_bcn_presp(sdata, stype, mgmt, &elems, rx_status); - - if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && - !sdata->vif.csa_active) - ieee80211_mesh_process_chnswitch(sdata, &elems, true); } int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata) @@ -1373,6 +1373,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(pos, len - baselen, true, &elems, mgmt->bssid, NULL); + if (!mesh_matches_local(sdata, &elems)) + return; + ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl; if (!--ifmsh->chsw_ttl) fwd_csa = false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 9936e33ac351..b22a63ba2348 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1332,7 +1332,9 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req) +struct sock *mptcp_sk_clone(const struct sock *sk, + const struct tcp_options_received *opt_rx, + struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -1355,26 +1357,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req) msk->subflow = NULL; if (unlikely(mptcp_token_new_accept(subflow_req->token, nsk))) { + nsk->sk_state = TCP_CLOSE; bh_unlock_sock(nsk); /* we can't call into mptcp_close() here - possible BH context - * free the sock directly + * free the sock directly. + * sk_clone_lock() sets nsk refcnt to two, hence call sk_free() + * too. */ - nsk->sk_prot->destroy(nsk); + sk_common_release(nsk); sk_free(nsk); return NULL; } msk->write_seq = subflow_req->idsn + 1; atomic64_set(&msk->snd_una, msk->write_seq); - if (subflow_req->remote_key_valid) { + if (opt_rx->mptcp.mp_capable) { msk->can_ack = true; - msk->remote_key = subflow_req->remote_key; + msk->remote_key = opt_rx->mptcp.sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); ack_seq++; msk->ack_seq = ack_seq; } + sock_reset_flag(nsk, SOCK_RCU_FREE); /* will be fully established after successful MPC subflow creation */ inet_sk_state_store(nsk, TCP_SYN_RECV); bh_unlock_sock(nsk); @@ -1431,6 +1437,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, newsk = new_mptcp_sock; mptcp_copy_inaddrs(newsk, ssk); list_add(&subflow->node, &msk->conn_list); + inet_sk_state_store(newsk, TCP_ESTABLISHED); bh_unlock_sock(new_mptcp_sock); @@ -1775,6 +1782,8 @@ static int mptcp_listen(struct socket *sock, int backlog) goto unlock; } + sock_set_flag(sock->sk, SOCK_RCU_FREE); + err = ssock->ops->listen(ssock, backlog); inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); if (!err) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 67448002a2d7..a2b3048037d0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -206,12 +206,10 @@ struct mptcp_subflow_request_sock { struct tcp_request_sock sk; u16 mp_capable : 1, mp_join : 1, - backup : 1, - remote_key_valid : 1; + backup : 1; u8 local_id; u8 remote_id; u64 local_key; - u64 remote_key; u64 idsn; u32 token; u32 ssn_offset; @@ -332,7 +330,9 @@ void mptcp_proto_init(void); int mptcp_proto_v6_init(void); #endif -struct sock *mptcp_sk_clone(const struct sock *sk, struct request_sock *req); +struct sock *mptcp_sk_clone(const struct sock *sk, + const struct tcp_options_received *opt_rx, + struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 50a8bea987c6..fabd06f2ff45 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -133,7 +133,6 @@ static void subflow_init_req(struct request_sock *req, subflow_req->mp_capable = 0; subflow_req->mp_join = 0; - subflow_req->remote_key_valid = 0; #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of @@ -347,6 +346,46 @@ static bool subflow_hmac_valid(const struct request_sock *req, return ret; } +static void mptcp_sock_destruct(struct sock *sk) +{ + /* if new mptcp socket isn't accepted, it is free'd + * from the tcp listener sockets request queue, linked + * from req->sk. The tcp socket is released. + * This calls the ULP release function which will + * also remove the mptcp socket, via + * sock_put(ctx->conn). + * + * Problem is that the mptcp socket will not be in + * SYN_RECV state and doesn't have SOCK_DEAD flag. + * Both result in warnings from inet_sock_destruct. + */ + + if (sk->sk_state == TCP_SYN_RECV) { + sk->sk_state = TCP_CLOSE; + WARN_ON_ONCE(sk->sk_socket); + sock_orphan(sk); + } + + inet_sock_destruct(sk); +} + +static void mptcp_force_close(struct sock *sk) +{ + inet_sk_state_store(sk, TCP_CLOSE); + sk_common_release(sk); +} + +static void subflow_ulp_fallback(struct sock *sk, + struct mptcp_subflow_context *old_ctx) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + mptcp_subflow_tcp_fallback(sk, old_ctx); + icsk->icsk_ulp_ops = NULL; + rcu_assign_pointer(icsk->icsk_ulp_data, NULL); + tcp_sk(sk)->is_mptcp = 0; +} + static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, @@ -359,10 +398,12 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct tcp_options_received opt_rx; bool fallback_is_fatal = false; struct sock *new_msk = NULL; + bool fallback = false; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); + opt_rx.mptcp.mp_capable = 0; if (tcp_rsk(req)->is_mptcp == 0) goto create_child; @@ -377,20 +418,16 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, goto create_msk; } - opt_rx.mptcp.mp_capable = 0; mptcp_get_options(skb, &opt_rx); - if (opt_rx.mptcp.mp_capable) { - subflow_req->remote_key = opt_rx.mptcp.sndr_key; - subflow_req->remote_key_valid = 1; - } else { - subflow_req->mp_capable = 0; + if (!opt_rx.mptcp.mp_capable) { + fallback = true; goto create_child; } create_msk: - new_msk = mptcp_sk_clone(listener->conn, req); + new_msk = mptcp_sk_clone(listener->conn, &opt_rx, req); if (!new_msk) - subflow_req->mp_capable = 0; + fallback = true; } else if (subflow_req->mp_join) { fallback_is_fatal = true; opt_rx.mptcp.mp_join = 0; @@ -409,12 +446,18 @@ create_child: if (child && *own_req) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child); - /* we have null ctx on TCP fallback, which is fatal on - * MPJ handshake + /* we need to fallback on ctx allocation failure and on pre-reqs + * checking above. In the latter scenario we additionally need + * to reset the context to non MPTCP status. */ - if (!ctx) { + if (!ctx || fallback) { if (fallback_is_fatal) goto close_child; + + if (ctx) { + subflow_ulp_fallback(child, ctx); + kfree_rcu(ctx, rcu); + } goto out; } @@ -422,10 +465,17 @@ create_child: /* new mpc subflow takes ownership of the newly * created mptcp socket */ - inet_sk_state_store(new_msk, TCP_ESTABLISHED); + new_msk->sk_destruct = mptcp_sock_destruct; mptcp_pm_new_connection(mptcp_sk(new_msk), 1); ctx->conn = new_msk; new_msk = NULL; + + /* with OoO packets we can reach here without ingress + * mpc option + */ + ctx->remote_key = opt_rx.mptcp.sndr_key; + ctx->fully_established = opt_rx.mptcp.mp_capable; + ctx->can_ack = opt_rx.mptcp.mp_capable; } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -444,7 +494,14 @@ create_child: out: /* dispose of the left over mptcp master, if any */ if (unlikely(new_msk)) - sock_put(new_msk); + mptcp_force_close(new_msk); + + /* check for expected invariant - should never trigger, just help + * catching eariler subtle bugs + */ + WARN_ON_ONCE(*own_req && child && tcp_sk(child)->is_mptcp && + (!mptcp_subflow_ctx(child) || + !mptcp_subflow_ctx(child)->conn)); return child; close_child: @@ -1047,17 +1104,6 @@ static void subflow_ulp_release(struct sock *sk) kfree_rcu(ctx, rcu); } -static void subflow_ulp_fallback(struct sock *sk, - struct mptcp_subflow_context *old_ctx) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - mptcp_subflow_tcp_fallback(sk, old_ctx); - icsk->icsk_ulp_ops = NULL; - rcu_assign_pointer(icsk->icsk_ulp_data, NULL); - tcp_sk(sk)->is_mptcp = 0; -} - static void subflow_ulp_clone(const struct request_sock *req, struct sock *newsk, const gfp_t priority) @@ -1091,9 +1137,6 @@ static void subflow_ulp_clone(const struct request_sock *req, * is fully established only after we receive the remote key */ new_ctx->mp_capable = 1; - new_ctx->fully_established = subflow_req->remote_key_valid; - new_ctx->can_ack = subflow_req->remote_key_valid; - new_ctx->remote_key = subflow_req->remote_key; new_ctx->local_key = subflow_req->local_key; new_ctx->token = subflow_req->token; new_ctx->ssn_offset = subflow_req->ssn_offset; diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 292e71dc7ba4..0e0ded87e27b 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -83,7 +83,7 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nft_set_pipapo.o ifdef CONFIG_X86_64 -ifneq (,$(findstring -DCONFIG_AS_AVX2=1,$(KBUILD_CFLAGS))) +ifndef CONFIG_UML nf_tables-objs += nft_set_pipapo_avx2.o endif endif diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9adfbc7e8ae7..9780bd93b7e4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3291,7 +3291,7 @@ static const struct nft_set_type *nft_set_types[] = { &nft_set_rhash_type, &nft_set_bitmap_type, &nft_set_rbtree_type, -#if defined(CONFIG_X86_64) && defined(CONFIG_AS_AVX2) +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) &nft_set_pipapo_avx2_type, #endif &nft_set_pipapo_type, diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 87aabf651cfe..8b5acc6910fd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2201,7 +2201,7 @@ const struct nft_set_type nft_set_pipapo_type = { }, }; -#if defined(CONFIG_X86_64) && defined(CONFIG_AS_AVX2) +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) const struct nft_set_type nft_set_pipapo_avx2_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, diff --git a/net/netfilter/nft_set_pipapo_avx2.h b/net/netfilter/nft_set_pipapo_avx2.h index 396caf7bfca8..394bcb704db7 100644 --- a/net/netfilter/nft_set_pipapo_avx2.h +++ b/net/netfilter/nft_set_pipapo_avx2.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _NFT_SET_PIPAPO_AVX2_H -#ifdef CONFIG_AS_AVX2 +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) #include <asm/fpu/xstate.h> #define NFT_PIPAPO_ALIGN (XSAVE_YMM_SIZE / BITS_PER_BYTE) @@ -9,6 +9,6 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); -#endif /* CONFIG_AS_AVX2 */ +#endif /* defined(CONFIG_X86_64) && !defined(CONFIG_UML) */ #endif /* _NFT_SET_PIPAPO_AVX2_H */ diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 79f12d8c7b86..0891ee02ca4f 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -208,6 +208,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, /* refcount initialized at 1 */ spin_unlock_bh(&nr_node_list_lock); + nr_neigh_put(nr_neigh); return 0; } nr_node_lock(nr_node); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e726159cfcfa..4340f25fe390 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1895,7 +1895,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node) + hlist_for_each_entry_rcu(ct_limit, head, hlist_node, + lockdep_ovsl_is_held()) kfree_rcu(ct_limit, rcu); } kfree(ovs_net->ct_limit_info->limits); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index d8ae541d22a8..94b024534987 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2466,8 +2466,10 @@ static void __net_exit ovs_exit_net(struct net *dnet) struct net *net; LIST_HEAD(head); - ovs_ct_exit(dnet); ovs_lock(); + + ovs_ct_exit(dnet); + list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); diff --git a/net/rds/message.c b/net/rds/message.c index bbecb8cb873e..071a261fdaab 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -308,26 +308,20 @@ out: /* * RDS ops use this to grab SG entries from the rm's sg pool. */ -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret) +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; - if (WARN_ON(!ret)) - return NULL; - if (nents <= 0) { pr_warn("rds: alloc sgs failed! nents <= 0\n"); - *ret = -EINVAL; - return NULL; + return ERR_PTR(-EINVAL); } if (rm->m_used_sgs + nents > rm->m_total_sgs) { pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", rm->m_total_sgs, rm->m_used_sgs, nents); - *ret = -ENOMEM; - return NULL; + return ERR_PTR(-ENOMEM); } sg_ret = &sg_first[rm->m_used_sgs]; @@ -343,7 +337,6 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in unsigned int i; int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); - int ret; rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) @@ -352,10 +345,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) { + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { rds_message_put(rm); - return ERR_PTR(ret); + return ERR_CAST(rm->data.op_sg); } for (i = 0; i < rm->data.op_nents; ++i) { diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 113e442101ce..a7ae11846cd7 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -665,9 +665,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_odp_mr = NULL; WARN_ON(!nr_pages); - op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); - if (!op->op_sg) + op->op_sg = rds_message_alloc_sgs(rm, nr_pages); + if (IS_ERR(op->op_sg)) { + ret = PTR_ERR(op->op_sg); goto out_pages; + } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because @@ -906,9 +908,11 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; - rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret); - if (!rm->atomic.op_sg) + rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); + if (IS_ERR(rm->atomic.op_sg)) { + ret = PTR_ERR(rm->atomic.op_sg); goto err; + } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { diff --git a/net/rds/rds.h b/net/rds/rds.h index 8e18cd2aec51..6019b0c004a9 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -844,8 +844,7 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret); +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); diff --git a/net/rds/send.c b/net/rds/send.c index 82dcd8b84fe7..68e2bdb08fd0 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1274,9 +1274,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { + ret = PTR_ERR(rm->data.op_sg); goto out; + } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index a6c1349e965d..01135e54d95d 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -165,15 +165,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) goto error; } - /* we want to set the don't fragment bit */ - opt = IPV6_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } - /* Fall through and set IPv4 options too otherwise we don't get * errors from IPv4 packets sent through the IPv6 socket. */ diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index bad3d2420344..90e263c6aa69 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -474,41 +474,21 @@ send_fragmentable: skb->tstamp = ktime_get_real(); switch (conn->params.local->srx.transport.family) { + case AF_INET6: case AF_INET: opt = IP_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IP, IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IP_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, SOL_IP, - IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - opt = IPV6_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IPV6_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + ret = kernel_sendmsg(conn->params.local->socket, &msg, + iov, 2, len); + conn->params.peer->last_tx_at = ktime_get_seconds(); + + opt = IP_PMTUDISC_DO; + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); break; -#endif default: BUG(); diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index c8c47fc72653..8c47ded2edb6 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1712,6 +1712,7 @@ exit: case -EBUSY: this_cpu_inc(stats->stat[STAT_ASYNC]); *skb = NULL; + tipc_aead_put(aead); return rc; default: this_cpu_inc(stats->stat[STAT_NOK]); diff --git a/net/tipc/link.c b/net/tipc/link.c index 467c53a1fb5c..d4675e922a8f 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1065,7 +1065,7 @@ static void tipc_link_update_cwin(struct tipc_link *l, int released, /* Enter fast recovery */ if (unlikely(retransmitted)) { l->ssthresh = max_t(u16, l->window / 2, 300); - l->window = l->ssthresh; + l->window = min_t(u16, l->ssthresh, l->window); return; } /* Enter slow start */ diff --git a/net/tipc/node.c b/net/tipc/node.c index 10292c942384..803a3a6d0f50 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2038,6 +2038,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) n = tipc_node_find_by_id(net, ehdr->id); } tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b); + tipc_node_put(n); if (!skb) return; @@ -2090,7 +2091,7 @@ rcv: /* Check/update node state before receiving */ if (unlikely(skb)) { if (unlikely(skb_linearize(skb))) - goto discard; + goto out_node_put; tipc_node_write_lock(n); if (tipc_node_check_state(n, skb, bearer_id, &xmitq)) { if (le->link) { @@ -2119,6 +2120,7 @@ rcv: if (!skb_queue_empty(&xmitq)) tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr, n); +out_node_put: tipc_node_put(n); discard: kfree_skb(skb); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5fa402144cda..692bcd35f809 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -644,10 +644,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, .len = NL80211_HE_MAX_CAPABILITY_LEN }, - [NL80211_ATTR_FTM_RESPONDER] = { - .type = NLA_NESTED, - .validation_data = nl80211_ftm_responder_policy, - }, + [NL80211_ATTR_FTM_RESPONDER] = + NLA_POLICY_NESTED(nl80211_ftm_responder_policy), [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = NLA_POLICY_NESTED(nl80211_pmsr_attr_policy), diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index fa7bb5e060d0..ed7a6060f73c 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -343,7 +343,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) u32 chunk_size = mr->chunk_size, headroom = mr->headroom; unsigned int chunks, chunks_per_page; u64 addr = mr->addr, size = mr->len; - int size_chk, err; + int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { /* Strictly speaking we could support this, if: @@ -382,8 +382,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM; - if (size_chk < 0) + if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; umem->address = (unsigned long)addr; |