diff options
Diffstat (limited to 'net')
394 files changed, 8845 insertions, 4278 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 39876eff51d2..3efba4f857ac 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -149,7 +149,7 @@ static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) if (max_mtu < new_mtu) return -ERANGE; - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); return 0; } diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index a3b68243fd4b..cf5219df7903 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -117,17 +117,15 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], return err; } if (data[IFLA_VLAN_INGRESS_QOS]) { - nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { - if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) - continue; + nla_for_each_nested_type(attr, IFLA_VLAN_QOS_MAPPING, + data[IFLA_VLAN_INGRESS_QOS], rem) { m = nla_data(attr); vlan_dev_set_ingress_priority(dev, m->to, m->from); } } if (data[IFLA_VLAN_EGRESS_QOS]) { - nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { - if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) - continue; + nla_for_each_nested_type(attr, IFLA_VLAN_QOS_MAPPING, + data[IFLA_VLAN_EGRESS_QOS], rem) { m = nla_data(attr); err = vlan_dev_set_egress_priority(dev, m->from, m->to); if (err) diff --git a/net/9p/Kconfig b/net/9p/Kconfig index 00ebce9e5a65..bcdab9c23b40 100644 --- a/net/9p/Kconfig +++ b/net/9p/Kconfig @@ -5,6 +5,7 @@ menuconfig NET_9P tristate "Plan 9 Resource Sharing Support (9P2000)" + select NETFS_SUPPORT help If you say Y here, you will get experimental support for Plan 9 resource sharing via the 9P2000 protocol. diff --git a/net/9p/client.c b/net/9p/client.c index b05f73c291b4..5cd94721d974 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -18,6 +18,7 @@ #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/uio.h> +#include <linux/netfs.h> #include <net/9p/9p.h> #include <linux/parser.h> #include <linux/seq_file.h> @@ -1663,6 +1664,54 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) } EXPORT_SYMBOL(p9_client_write); +void +p9_client_write_subreq(struct netfs_io_subrequest *subreq) +{ + struct netfs_io_request *wreq = subreq->rreq; + struct p9_fid *fid = wreq->netfs_priv; + struct p9_client *clnt = fid->clnt; + struct p9_req_t *req; + unsigned long long start = subreq->start + subreq->transferred; + int written, len = subreq->len - subreq->transferred; + int err; + + p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu len %d\n", + fid->fid, start, len); + + /* Don't bother zerocopy for small IO (< 1024) */ + if (clnt->trans_mod->zc_request && len > 1024) { + req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, &subreq->io_iter, + 0, wreq->len, P9_ZC_HDR_SZ, "dqd", + fid->fid, start, len); + } else { + req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid, + start, len, &subreq->io_iter); + } + if (IS_ERR(req)) { + netfs_write_subrequest_terminated(subreq, PTR_ERR(req), false); + return; + } + + err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &written); + if (err) { + trace_9p_protocol_dump(clnt, &req->rc); + p9_req_put(clnt, req); + netfs_write_subrequest_terminated(subreq, err, false); + return; + } + + if (written > len) { + pr_err("bogus RWRITE count (%d > %u)\n", written, len); + written = len; + } + + p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", len); + + p9_req_put(clnt, req); + netfs_write_subrequest_terminated(subreq, written, false); +} +EXPORT_SYMBOL(p9_client_write_subreq); + struct p9_wstat *p9_client_stat(struct p9_fid *fid) { int err; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index e305071eb7b8..0b8086f58ad5 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -781,7 +781,6 @@ static struct virtio_driver p9_virtio_drv = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), .driver.name = KBUILD_MODNAME, - .driver.owner = THIS_MODULE, .id_table = id_table, .probe = p9_virtio_probe, .remove = p9_virtio_remove, diff --git a/net/Kconfig b/net/Kconfig index 3e57ccf0da27..f0a8692496ff 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -60,6 +60,9 @@ config NET_XGRESS config NET_REDIRECT bool +config SKB_DECRYPTED + bool + config SKB_EXTENSIONS bool @@ -449,6 +452,9 @@ config GRO_CELLS config SOCK_VALIDATE_XMIT bool +config NET_IEEE8021Q_HELPERS + bool + config NET_SELFTESTS def_tristate PHYLIB depends on PHYLIB && INET diff --git a/net/appletalk/sysctl_net_atalk.c b/net/appletalk/sysctl_net_atalk.c index d945b7c0176d..7aebfe903242 100644 --- a/net/appletalk/sysctl_net_atalk.c +++ b/net/appletalk/sysctl_net_atalk.c @@ -40,7 +40,6 @@ static struct ctl_table atalk_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { }, }; static struct ctl_table_header *atalk_table_header; diff --git a/net/atm/clip.c b/net/atm/clip.c index 015fb679be42..42b910cb4e8e 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -463,7 +463,7 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip) unlink_clip_vcc(clip_vcc); return 0; } - rt = ip_route_output(&init_net, ip, 0, 1, 0); + rt = ip_route_output(&init_net, ip, 0, 0, 0, RT_SCOPE_LINK); if (IS_ERR(rt)) return PTR_ERR(rt); neigh = __neigh_lookup(&arp_tbl, &ip, rt->dst.dev, 1); diff --git a/net/atm/common.c b/net/atm/common.c index 2a1ec014e901..9b75699992ff 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -116,7 +116,7 @@ static void vcc_write_space(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible(&wq->wait); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); diff --git a/net/atm/svc.c b/net/atm/svc.c index 36a814f1fbd1..f8137ae693b0 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -324,8 +324,8 @@ out: return error; } -static int svc_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int svc_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk; struct sk_buff *skb; @@ -336,7 +336,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags, lock_sock(sk); - error = svc_create(sock_net(sk), newsock, 0, kern); + error = svc_create(sock_net(sk), newsock, 0, arg->kern); if (error) goto out; @@ -355,7 +355,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags, error = -sk->sk_err; break; } - if (flags & O_NONBLOCK) { + if (arg->flags & O_NONBLOCK) { error = -EAGAIN; break; } diff --git a/net/ax25/Kconfig b/net/ax25/Kconfig index fdb666607f10..e23a3dc14b93 100644 --- a/net/ax25/Kconfig +++ b/net/ax25/Kconfig @@ -4,7 +4,7 @@ # menuconfig HAMRADIO - depends on NET && !S390 + depends on NET bool "Amateur Radio support" help If you want to connect your Linux box to an amateur radio, answer Y diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 5fff5930e4de..d6f9fae06a9d 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1373,8 +1373,8 @@ out_release: return err; } -static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int ax25_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sk_buff *skb; struct sock *newsk; @@ -1411,7 +1411,7 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, if (skb) break; - if (flags & O_NONBLOCK) { + if (arg->flags & O_NONBLOCK) { err = -EWOULDBLOCK; break; } diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 67ae6b8c5298..9efd6690b344 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -79,7 +79,10 @@ void ax25_dev_device_up(struct net_device *dev) ax25_dev->values[AX25_VALUES_N2] = AX25_DEF_N2; ax25_dev->values[AX25_VALUES_PACLEN] = AX25_DEF_PACLEN; ax25_dev->values[AX25_VALUES_PROTOCOL] = AX25_DEF_PROTOCOL; + +#ifdef CONFIG_AX25_DAMA_SLAVE ax25_dev->values[AX25_VALUES_DS_TIMEOUT]= AX25_DEF_DS_TIMEOUT; +#endif #if defined(CONFIG_AX25_DAMA_SLAVE) || defined(CONFIG_AX25_DAMA_MASTER) ax25_ds_setup_timer(ax25_dev); diff --git a/net/ax25/sysctl_net_ax25.c b/net/ax25/sysctl_net_ax25.c index db66e11e7fe8..68753aa30334 100644 --- a/net/ax25/sysctl_net_ax25.c +++ b/net/ax25/sysctl_net_ax25.c @@ -141,8 +141,6 @@ static const struct ctl_table ax25_param_table[] = { .extra2 = &max_ds_timeout }, #endif - - { } /* that's all, folks! */ }; int ax25_register_dev_sysctl(ax25_dev *ax25_dev) @@ -155,6 +153,7 @@ int ax25_register_dev_sysctl(ax25_dev *ax25_dev) if (!table) return -ENOMEM; + BUILD_BUG_ON(ARRAY_SIZE(ax25_param_table) != AX25_MAX_VALUES); for (k = 0; k < AX25_MAX_VALUES; k++) table[k].data = &ax25_dev->values[k]; @@ -171,7 +170,7 @@ int ax25_register_dev_sysctl(ax25_dev *ax25_dev) void ax25_unregister_dev_sysctl(ax25_dev *ax25_dev) { struct ctl_table_header *header = ax25_dev->sysheader; - struct ctl_table *table; + const struct ctl_table *table; if (header) { ax25_dev->sysheader = NULL; diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 75119f1ffccc..8e0f44c71696 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -14,7 +14,6 @@ #include <linux/crc32c.h> #include <linux/device.h> #include <linux/errno.h> -#include <linux/genetlink.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> @@ -38,6 +37,7 @@ #include <linux/string.h> #include <linux/workqueue.h> #include <net/dsfield.h> +#include <net/genetlink.h> #include <net/rtnetlink.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 8ca854a75a32..3d4c36ae2e1a 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2024.1" +#define BATADV_SOURCE_VERSION "2024.2" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 0954757f0b8b..9362cd9d6f3d 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -15,7 +15,6 @@ #include <linux/cache.h> #include <linux/err.h> #include <linux/errno.h> -#include <linux/genetlink.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index ac74f6ead62d..8f6dd2c6ee41 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -12,6 +12,7 @@ #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> +#include <linux/if_vlan.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> @@ -132,6 +133,29 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, } /** + * batadv_vlan_id_valid() - check if vlan id is in valid batman-adv encoding + * @vid: the VLAN identifier + * + * Return: true when either no vlan is set or if VLAN is in correct range, + * false otherwise + */ +static bool batadv_vlan_id_valid(unsigned short vid) +{ + unsigned short non_vlan = vid & ~(BATADV_VLAN_HAS_TAG | VLAN_VID_MASK); + + if (vid == 0) + return true; + + if (!(vid & BATADV_VLAN_HAS_TAG)) + return false; + + if (non_vlan) + return false; + + return true; +} + +/** * batadv_orig_node_vlan_new() - search and possibly create an orig_node_vlan * object * @orig_node: the originator serving the VLAN @@ -149,6 +173,9 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, { struct batadv_orig_node_vlan *vlan; + if (!batadv_vlan_id_valid(vid)) + return NULL; + spin_lock_bh(&orig_node->vlan_list_lock); /* first look if an object for this vid already exists */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 89c51b3cf430..30ecbc2ef1fd 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -159,7 +159,7 @@ static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) if (new_mtu < ETH_MIN_MTU || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); bat_priv->mtu_set_by_user = new_mtu; return 0; diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index 5dd52bc5cabb..6b816cf1a953 100644 --- a/net/batman-adv/trace.h +++ b/net/batman-adv/trace.h @@ -40,8 +40,8 @@ TRACE_EVENT(batadv_dbg, ), TP_fast_assign( - __assign_str(device, bat_priv->soft_iface->name); - __assign_str(driver, KBUILD_MODNAME); + __assign_str(device); + __assign_str(driver); __assign_vstr(msg, vaf->fmt, vaf->va); ), diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 08ae30fd3155..080053a85b4d 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -241,13 +241,13 @@ static int configure_datapath_sync(struct hci_dev *hdev, struct bt_codec *codec) __u8 vnd_len, *vnd_data = NULL; struct hci_op_configure_data_path *cmd = NULL; + /* Do not take below 2 checks as error since the 1st means user do not + * want to use HFP offload mode and the 2nd means the vendor controller + * do not need to send below HCI command for offload mode. + */ if (!codec->data_path || !hdev->get_codec_config_data) return 0; - /* Do not take me as error */ - if (!hdev->get_codec_config_data) - return 0; - err = hdev->get_codec_config_data(hdev, ESCO_LINK, codec, &vnd_len, &vnd_data); if (err < 0) @@ -664,11 +664,6 @@ static void le_conn_timeout(struct work_struct *work) hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); } -struct iso_cig_params { - struct hci_cp_le_set_cig_params cp; - struct hci_cis_params cis[0x1f]; -}; - struct iso_list_data { union { u8 cig; @@ -904,8 +899,8 @@ static int hci_conn_hash_alloc_unset(struct hci_dev *hdev) U16_MAX, GFP_ATOMIC); } -struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, - u8 role, u16 handle) +static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, + u8 role, u16 handle) { struct hci_conn *conn; @@ -1046,7 +1041,16 @@ struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, if (unlikely(handle < 0)) return ERR_PTR(-ECONNREFUSED); - return hci_conn_add(hdev, type, dst, role, handle); + return __hci_conn_add(hdev, type, dst, role, handle); +} + +struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, + u8 role, u16 handle) +{ + if (handle > HCI_CONN_HANDLE_MAX) + return ERR_PTR(-EINVAL); + + return __hci_conn_add(hdev, type, dst, role, handle); } static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason) @@ -1754,34 +1758,33 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) static int set_cig_params_sync(struct hci_dev *hdev, void *data) { + DEFINE_FLEX(struct hci_cp_le_set_cig_params, pdu, cis, num_cis, 0x1f); u8 cig_id = PTR_UINT(data); struct hci_conn *conn; struct bt_iso_qos *qos; - struct iso_cig_params pdu; + u8 aux_num_cis = 0; u8 cis_id; conn = hci_conn_hash_lookup_cig(hdev, cig_id); if (!conn) return 0; - memset(&pdu, 0, sizeof(pdu)); - qos = &conn->iso_qos; - pdu.cp.cig_id = cig_id; - hci_cpu_to_le24(qos->ucast.out.interval, pdu.cp.c_interval); - hci_cpu_to_le24(qos->ucast.in.interval, pdu.cp.p_interval); - pdu.cp.sca = qos->ucast.sca; - pdu.cp.packing = qos->ucast.packing; - pdu.cp.framing = qos->ucast.framing; - pdu.cp.c_latency = cpu_to_le16(qos->ucast.out.latency); - pdu.cp.p_latency = cpu_to_le16(qos->ucast.in.latency); + pdu->cig_id = cig_id; + hci_cpu_to_le24(qos->ucast.out.interval, pdu->c_interval); + hci_cpu_to_le24(qos->ucast.in.interval, pdu->p_interval); + pdu->sca = qos->ucast.sca; + pdu->packing = qos->ucast.packing; + pdu->framing = qos->ucast.framing; + pdu->c_latency = cpu_to_le16(qos->ucast.out.latency); + pdu->p_latency = cpu_to_le16(qos->ucast.in.latency); /* Reprogram all CIS(s) with the same CIG, valid range are: * num_cis: 0x00 to 0x1F * cis_id: 0x00 to 0xEF */ for (cis_id = 0x00; cis_id < 0xf0 && - pdu.cp.num_cis < ARRAY_SIZE(pdu.cis); cis_id++) { + aux_num_cis < pdu->num_cis; cis_id++) { struct hci_cis_params *cis; conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, cig_id, cis_id); @@ -1790,7 +1793,7 @@ static int set_cig_params_sync(struct hci_dev *hdev, void *data) qos = &conn->iso_qos; - cis = &pdu.cis[pdu.cp.num_cis++]; + cis = &pdu->cis[aux_num_cis++]; cis->cis_id = cis_id; cis->c_sdu = cpu_to_le16(conn->iso_qos.ucast.out.sdu); cis->p_sdu = cpu_to_le16(conn->iso_qos.ucast.in.sdu); @@ -1801,14 +1804,14 @@ static int set_cig_params_sync(struct hci_dev *hdev, void *data) cis->c_rtn = qos->ucast.out.rtn; cis->p_rtn = qos->ucast.in.rtn; } + pdu->num_cis = aux_num_cis; - if (!pdu.cp.num_cis) + if (!pdu->num_cis) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, - sizeof(pdu.cp) + - pdu.cp.num_cis * sizeof(pdu.cis[0]), &pdu, - HCI_CMD_TIMEOUT); + struct_size(pdu, cis, pdu->num_cis), + pdu, HCI_CMD_TIMEOUT); } static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) @@ -2135,13 +2138,10 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]) { - struct _packed { - struct hci_cp_le_big_create_sync cp; - __u8 bis[0x11]; - } pdu; + DEFINE_FLEX(struct hci_cp_le_big_create_sync, pdu, bis, num_bis, 0x11); int err; - if (num_bis < 0x01 || num_bis > sizeof(pdu.bis)) + if (num_bis < 0x01 || num_bis > pdu->num_bis) return -EINVAL; err = qos_set_big(hdev, qos); @@ -2151,18 +2151,17 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, if (hcon) hcon->iso_qos.bcast.big = qos->bcast.big; - memset(&pdu, 0, sizeof(pdu)); - pdu.cp.handle = qos->bcast.big; - pdu.cp.sync_handle = cpu_to_le16(sync_handle); - pdu.cp.encryption = qos->bcast.encryption; - memcpy(pdu.cp.bcode, qos->bcast.bcode, sizeof(pdu.cp.bcode)); - pdu.cp.mse = qos->bcast.mse; - pdu.cp.timeout = cpu_to_le16(qos->bcast.timeout); - pdu.cp.num_bis = num_bis; - memcpy(pdu.bis, bis, num_bis); + pdu->handle = qos->bcast.big; + pdu->sync_handle = cpu_to_le16(sync_handle); + pdu->encryption = qos->bcast.encryption; + memcpy(pdu->bcode, qos->bcast.bcode, sizeof(pdu->bcode)); + pdu->mse = qos->bcast.mse; + pdu->timeout = cpu_to_le16(qos->bcast.timeout); + pdu->num_bis = num_bis; + memcpy(pdu->bis, bis, num_bis); return hci_send_cmd(hdev, HCI_OP_LE_BIG_CREATE_SYNC, - sizeof(pdu.cp) + num_bis, &pdu); + struct_size(pdu, bis, num_bis), pdu); } static void create_big_complete(struct hci_dev *hdev, void *data, int err) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 24f6b6a5c772..9493966cf389 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -63,50 +63,6 @@ DEFINE_MUTEX(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); -static int hci_scan_req(struct hci_request *req, unsigned long opt) -{ - __u8 scan = opt; - - BT_DBG("%s %x", req->hdev->name, scan); - - /* Inquiry and Page scans */ - hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); - return 0; -} - -static int hci_auth_req(struct hci_request *req, unsigned long opt) -{ - __u8 auth = opt; - - BT_DBG("%s %x", req->hdev->name, auth); - - /* Authentication */ - hci_req_add(req, HCI_OP_WRITE_AUTH_ENABLE, 1, &auth); - return 0; -} - -static int hci_encrypt_req(struct hci_request *req, unsigned long opt) -{ - __u8 encrypt = opt; - - BT_DBG("%s %x", req->hdev->name, encrypt); - - /* Encryption */ - hci_req_add(req, HCI_OP_WRITE_ENCRYPT_MODE, 1, &encrypt); - return 0; -} - -static int hci_linkpol_req(struct hci_request *req, unsigned long opt) -{ - __le16 policy = cpu_to_le16(opt); - - BT_DBG("%s %x", req->hdev->name, policy); - - /* Default link policy */ - hci_req_add(req, HCI_OP_WRITE_DEF_LINK_POLICY, 2, &policy); - return 0; -} - /* Get HCI device by index. * Device is held on return. */ struct hci_dev *hci_dev_get(int index) @@ -149,8 +105,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) { int old_state = hdev->discovery.state; - BT_DBG("%s state %u -> %u", hdev->name, hdev->discovery.state, state); - if (old_state == state) return; @@ -173,6 +127,8 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) case DISCOVERY_STOPPING: break; } + + bt_dev_dbg(hdev, "state %u -> %u", old_state, state); } void hci_inquiry_cache_flush(struct hci_dev *hdev) @@ -728,6 +684,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) { struct hci_dev *hdev; struct hci_dev_req dr; + __le16 policy; int err = 0; if (copy_from_user(&dr, arg, sizeof(dr))) @@ -754,8 +711,8 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) switch (cmd) { case HCISETAUTH: - err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE, + 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETENCRYPT: @@ -766,19 +723,21 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) if (!test_bit(HCI_AUTH, &hdev->flags)) { /* Auth must be enabled first */ - err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, + HCI_OP_WRITE_AUTH_ENABLE, + 1, &dr.dev_opt, + HCI_CMD_TIMEOUT); if (err) break; } - err = hci_req_sync(hdev, hci_encrypt_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_ENCRYPT_MODE, + 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETSCAN: - err = hci_req_sync(hdev, hci_scan_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_SCAN_ENABLE, + 1, &dr.dev_opt, HCI_CMD_TIMEOUT); /* Ensure that the connectable and discoverable states * get correctly modified as this was a non-mgmt change. @@ -788,8 +747,10 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) break; case HCISETLINKPOL: - err = hci_req_sync(hdev, hci_linkpol_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + policy = cpu_to_le16(dr.dev_opt); + + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_DEF_LINK_POLICY, + 2, &policy, HCI_CMD_TIMEOUT); break; case HCISETLINKMODE: @@ -2470,10 +2431,16 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, /* To avoid a potential race with hci_unregister_dev. */ hci_dev_hold(hdev); - if (action == PM_SUSPEND_PREPARE) + switch (action) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: ret = hci_suspend_dev(hdev); - else if (action == PM_POST_SUSPEND) + break; + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: ret = hci_resume_dev(hdev); + break; + } if (ret) bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", @@ -2521,16 +2488,16 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) hdev->le_adv_channel_map = 0x07; hdev->le_adv_min_interval = 0x0800; hdev->le_adv_max_interval = 0x0800; - hdev->le_scan_interval = 0x0060; - hdev->le_scan_window = 0x0030; - hdev->le_scan_int_suspend = 0x0400; - hdev->le_scan_window_suspend = 0x0012; + hdev->le_scan_interval = DISCOV_LE_SCAN_INT_FAST; + hdev->le_scan_window = DISCOV_LE_SCAN_WIN_FAST; + hdev->le_scan_int_suspend = DISCOV_LE_SCAN_INT_SLOW1; + hdev->le_scan_window_suspend = DISCOV_LE_SCAN_WIN_SLOW1; hdev->le_scan_int_discovery = DISCOV_LE_SCAN_INT; hdev->le_scan_window_discovery = DISCOV_LE_SCAN_WIN; - hdev->le_scan_int_adv_monitor = 0x0060; - hdev->le_scan_window_adv_monitor = 0x0030; - hdev->le_scan_int_connect = 0x0060; - hdev->le_scan_window_connect = 0x0060; + hdev->le_scan_int_adv_monitor = DISCOV_LE_SCAN_INT_FAST; + hdev->le_scan_window_adv_monitor = DISCOV_LE_SCAN_WIN_FAST; + hdev->le_scan_int_connect = DISCOV_LE_SCAN_INT_CONN; + hdev->le_scan_window_connect = DISCOV_LE_SCAN_WIN_CONN; hdev->le_conn_min_interval = 0x0018; hdev->le_conn_max_interval = 0x0028; hdev->le_conn_latency = 0x0000; @@ -2547,7 +2514,7 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_num_of_adv_sets = HCI_MAX_ADV_INSTANCES; hdev->def_multi_adv_rotation_duration = HCI_DEFAULT_ADV_DURATION; - hdev->def_le_autoconnect_timeout = HCI_LE_AUTOCONN_TIMEOUT; + hdev->def_le_autoconnect_timeout = HCI_LE_CONN_TIMEOUT; hdev->min_le_tx_power = HCI_TX_POWER_INVALID; hdev->max_le_tx_power = HCI_TX_POWER_INVALID; @@ -2744,7 +2711,11 @@ void hci_unregister_dev(struct hci_dev *hdev) list_del(&hdev->list); write_unlock(&hci_dev_list_lock); + cancel_work_sync(&hdev->rx_work); + cancel_work_sync(&hdev->cmd_work); + cancel_work_sync(&hdev->tx_work); cancel_work_sync(&hdev->power_on); + cancel_work_sync(&hdev->error_reset); hci_cmd_sync_clear(hdev); @@ -3709,19 +3680,19 @@ static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; - int quote, cnt, tmp; + int quote, *cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; - cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; + cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; - __check_timeout(hdev, cnt, LE_LINK); + __check_timeout(hdev, *cnt, LE_LINK); - tmp = cnt; - while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { + tmp = *cnt; + while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, @@ -3736,7 +3707,7 @@ static void hci_sched_le(struct hci_dev *hdev) hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies; - cnt--; + (*cnt)--; chan->sent++; chan->conn->sent++; @@ -3746,12 +3717,7 @@ static void hci_sched_le(struct hci_dev *hdev) } } - if (hdev->le_pkts) - hdev->le_cnt = cnt; - else - hdev->acl_cnt = cnt; - - if (cnt != tmp) + if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 1ed734a7fb31..59d9086db75f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1722,10 +1722,10 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable) switch (enable) { case LE_SCAN_ENABLE: hci_dev_set_flag(hdev, HCI_LE_SCAN); - if (hdev->le_scan_type == LE_SCAN_ACTIVE) + if (hdev->le_scan_type == LE_SCAN_ACTIVE) { clear_pending_adv_report(hdev); - if (hci_dev_test_flag(hdev, HCI_MESH)) hci_discovery_set_state(hdev, DISCOVERY_FINDING); + } break; case LE_SCAN_DISABLE: @@ -5921,7 +5921,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || + (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; @@ -6312,6 +6312,13 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK; legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type); + + if (test_bit(HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY, + &hdev->quirks)) { + info->primary_phy &= 0x1f; + info->secondary_phy &= 0x1f; + } + if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, info->bdaddr_type, NULL, 0, @@ -6661,6 +6668,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, struct bt_iso_qos *qos; bool pending = false; u16 handle = __le16_to_cpu(ev->handle); + u32 c_sdu_interval, p_sdu_interval; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6685,12 +6693,25 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, pending = test_and_clear_bit(HCI_CONN_CREATE_CIS, &conn->flags); - /* Convert ISO Interval (1.25 ms slots) to SDU Interval (us) */ - qos->ucast.in.interval = le16_to_cpu(ev->interval) * 1250; - qos->ucast.out.interval = qos->ucast.in.interval; + /* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 6, Part G + * page 3075: + * Transport_Latency_C_To_P = CIG_Sync_Delay + (FT_C_To_P) × + * ISO_Interval + SDU_Interval_C_To_P + * ... + * SDU_Interval = (CIG_Sync_Delay + (FT) x ISO_Interval) - + * Transport_Latency + */ + c_sdu_interval = (get_unaligned_le24(ev->cig_sync_delay) + + (ev->c_ft * le16_to_cpu(ev->interval) * 1250)) - + get_unaligned_le24(ev->c_latency); + p_sdu_interval = (get_unaligned_le24(ev->cig_sync_delay) + + (ev->p_ft * le16_to_cpu(ev->interval) * 1250)) - + get_unaligned_le24(ev->p_latency); switch (conn->role) { case HCI_ROLE_SLAVE: + qos->ucast.in.interval = c_sdu_interval; + qos->ucast.out.interval = p_sdu_interval; /* Convert Transport Latency (us) to Latency (msec) */ qos->ucast.in.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), @@ -6704,6 +6725,8 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, qos->ucast.out.phy = ev->p_phy; break; case HCI_ROLE_MASTER: + qos->ucast.in.interval = p_sdu_interval; + qos->ucast.out.interval = c_sdu_interval; /* Convert Transport Latency (us) to Latency (msec) */ qos->ucast.out.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), @@ -6894,6 +6917,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis = hci_conn_hash_lookup_handle(hdev, handle); if (!bis) { + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_dbg(hdev, "ignore too large handle %u", handle); + continue; + } bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, HCI_ROLE_SLAVE, handle); if (IS_ERR(bis)) @@ -6959,9 +6986,11 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, (hdev, le16_to_cpu(ev->sync_handle)); - if (IS_ERR(pa_sync)) + if (!pa_sync) goto unlock; + pa_sync->iso_qos.bcast.encryption = ev->encryption; + /* Notify iso layer */ hci_connect_cfm(pa_sync, 0); diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index 0be75cf0efed..c91f2838f542 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -29,10 +29,6 @@ #define hci_req_sync_lock(hdev) mutex_lock(&hdev->req_lock) #define hci_req_sync_unlock(hdev) mutex_unlock(&hdev->req_lock) -#define HCI_REQ_DONE 0 -#define HCI_REQ_PEND 1 -#define HCI_REQ_CANCELED 2 - struct hci_request { struct hci_dev *hdev; struct sk_buff_head cmd_q; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 7bfa6b59ba87..4e90bd722e7b 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -280,6 +280,19 @@ int __hci_cmd_sync_status(struct hci_dev *hdev, u16 opcode, u32 plen, } EXPORT_SYMBOL(__hci_cmd_sync_status); +int hci_cmd_sync_status(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout) +{ + int err; + + hci_req_sync_lock(hdev); + err = __hci_cmd_sync_status(hdev, opcode, plen, param, timeout); + hci_req_sync_unlock(hdev); + + return err; +} +EXPORT_SYMBOL(hci_cmd_sync_status); + static void hci_cmd_sync_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_sync_work); @@ -358,8 +371,6 @@ static void le_scan_disable(struct work_struct *work) goto _return; } - hdev->discovery.scan_start = 0; - /* If we were running LE only scan, change discovery state. If * we were running both LE and BR/EDR inquiry simultaneously, * and BR/EDR inquiry is already finished, stop discovery, @@ -2918,6 +2929,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) */ filter_policy = hci_update_accept_list_sync(hdev); + /* If suspended and filter_policy set to 0x00 (no acceptlist) then + * passive scanning cannot be started since that would require the host + * to be woken up to process the reports. + */ + if (hdev->suspended && !filter_policy) { + /* Check if accept list is empty then there is no need to scan + * while suspended. + */ + if (list_empty(&hdev->le_accept_list)) + return 0; + + /* If there are devices is the accept_list that means some + * devices could not be programmed which in non-suspended case + * means filter_policy needs to be set to 0x00 so the host needs + * to filter, but since this is treating suspended case we + * can ignore device needing host to filter to allow devices in + * the acceptlist to be able to wakeup the system. + */ + filter_policy = 0x01; + } + /* When the controller is using random resolvable addresses and * with that having LE privacy enabled, then controllers with * Extended Scanner Filter Policies support can now enable support @@ -2940,6 +2972,20 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) } else if (hci_is_adv_monitoring(hdev)) { window = hdev->le_scan_window_adv_monitor; interval = hdev->le_scan_int_adv_monitor; + + /* Disable duplicates filter when scanning for advertisement + * monitor for the following reasons. + * + * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm + * controllers ignore RSSI_Sampling_Period when the duplicates + * filter is enabled. + * + * For SW pattern filtering, when we're not doing interleaved + * scanning, it is necessary to disable duplicates filter, + * otherwise hosts can only receive one advertisement and it's + * impossible to know if a peer is still in range. + */ + filter_dups = LE_SCAN_FILTER_DUP_DISABLE; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; @@ -6451,7 +6497,7 @@ int hci_le_create_cis_sync(struct hci_dev *hdev) cis->cis_handle = cpu_to_le16(conn->handle); aux_num_cis++; - if (aux_num_cis >= 0x1f) + if (aux_num_cis >= cmd->num_cis) break; } cmd->num_cis = aux_num_cis; diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 00c0d8413c63..398fb81f7a13 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1159,7 +1159,7 @@ done: } static int iso_sock_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; @@ -1168,7 +1168,7 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); @@ -1356,8 +1356,7 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - if (pi->conn->hcon && - test_bit(HCI_CONN_PA_SYNC, &pi->conn->hcon->flags)) { + if (test_bit(BT_SK_PA_SYNC, &pi->flags)) { iso_conn_big_sync(sk); sk->sk_state = BT_LISTEN; } else { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 9394a158d1b1..9988ba382b68 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1284,7 +1284,7 @@ static void l2cap_le_connect(struct l2cap_chan *chan) struct l2cap_ecred_conn_data { struct { - struct l2cap_ecred_conn_req req; + struct l2cap_ecred_conn_req_hdr req; __le16 scid[5]; } __packed pdu; struct l2cap_chan *chan; @@ -3764,7 +3764,7 @@ static void l2cap_ecred_list_defer(struct l2cap_chan *chan, void *data) struct l2cap_ecred_rsp_data { struct { - struct l2cap_ecred_conn_rsp rsp; + struct l2cap_ecred_conn_rsp_hdr rsp; __le16 scid[L2CAP_ECRED_MAX_CID]; } __packed pdu; int count; @@ -3773,6 +3773,8 @@ struct l2cap_ecred_rsp_data { static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) { struct l2cap_ecred_rsp_data *rsp = data; + struct l2cap_ecred_conn_rsp *rsp_flex = + container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr); if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags)) return; @@ -3782,7 +3784,7 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data) /* Include all channels pending with the same ident */ if (!rsp->pdu.rsp.result) - rsp->pdu.rsp.dcid[rsp->count++] = cpu_to_le16(chan->scid); + rsp_flex->dcid[rsp->count++] = cpu_to_le16(chan->scid); else l2cap_chan_del(chan, ECONNRESET); } @@ -5005,10 +5007,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, u8 *data) { struct l2cap_ecred_conn_req *req = (void *) data; - struct { - struct l2cap_ecred_conn_rsp rsp; - __le16 dcid[L2CAP_ECRED_MAX_CID]; - } __packed pdu; + DEFINE_RAW_FLEX(struct l2cap_ecred_conn_rsp, pdu, dcid, L2CAP_ECRED_MAX_CID); struct l2cap_chan *chan, *pchan; u16 mtu, mps; __le16 psm; @@ -5027,7 +5026,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, cmd_len -= sizeof(*req); num_scid = cmd_len / sizeof(u16); - if (num_scid > ARRAY_SIZE(pdu.dcid)) { + if (num_scid > L2CAP_ECRED_MAX_CID) { result = L2CAP_CR_LE_INVALID_PARAMS; goto response; } @@ -5056,7 +5055,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps); - memset(&pdu, 0, sizeof(pdu)); + memset(pdu, 0, sizeof(*pdu)); /* Check if we have socket listening on psm */ pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, @@ -5082,8 +5081,8 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, BT_DBG("scid[%d] 0x%4.4x", i, scid); - pdu.dcid[i] = 0x0000; - len += sizeof(*pdu.dcid); + pdu->dcid[i] = 0x0000; + len += sizeof(*pdu->dcid); /* Check for valid dynamic CID range */ if (scid < L2CAP_CID_DYN_START || scid > L2CAP_CID_LE_DYN_END) { @@ -5117,13 +5116,13 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, l2cap_ecred_init(chan, __le16_to_cpu(req->credits)); /* Init response */ - if (!pdu.rsp.credits) { - pdu.rsp.mtu = cpu_to_le16(chan->imtu); - pdu.rsp.mps = cpu_to_le16(chan->mps); - pdu.rsp.credits = cpu_to_le16(chan->rx_credits); + if (!pdu->credits) { + pdu->mtu = cpu_to_le16(chan->imtu); + pdu->mps = cpu_to_le16(chan->mps); + pdu->credits = cpu_to_le16(chan->rx_credits); } - pdu.dcid[i] = cpu_to_le16(chan->scid); + pdu->dcid[i] = cpu_to_le16(chan->scid); __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); @@ -5145,13 +5144,13 @@ unlock: l2cap_chan_put(pchan); response: - pdu.rsp.result = cpu_to_le16(result); + pdu->result = cpu_to_le16(result); if (defer) return 0; l2cap_send_cmd(conn, cmd->ident, L2CAP_ECRED_CONN_RSP, - sizeof(pdu.rsp) + len, &pdu); + sizeof(*pdu) + len, pdu); return 0; } @@ -6762,6 +6761,8 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, BT_DBG("chan %p, len %d", chan, skb->len); + l2cap_chan_lock(chan); + if (chan->state != BT_BOUND && chan->state != BT_CONNECTED) goto drop; @@ -6773,11 +6774,13 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, bt_cb(skb)->l2cap.psm = psm; if (!chan->ops->recv(chan, skb)) { + l2cap_chan_unlock(chan); l2cap_chan_put(chan); return; } drop: + l2cap_chan_unlock(chan); l2cap_chan_put(chan); free_skb: kfree_skb(skb); @@ -7129,14 +7132,11 @@ EXPORT_SYMBOL_GPL(l2cap_chan_connect); static void l2cap_ecred_reconfigure(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; - struct { - struct l2cap_ecred_reconf_req req; - __le16 scid; - } pdu; + DEFINE_RAW_FLEX(struct l2cap_ecred_reconf_req, pdu, scid, 1); - pdu.req.mtu = cpu_to_le16(chan->imtu); - pdu.req.mps = cpu_to_le16(chan->mps); - pdu.scid = cpu_to_le16(chan->scid); + pdu->mtu = cpu_to_le16(chan->imtu); + pdu->mps = cpu_to_le16(chan->mps); + pdu->scid[0] = cpu_to_le16(chan->scid); chan->ident = l2cap_get_ident(conn); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 8645461d45e8..ba437c6f6ee5 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -327,7 +327,7 @@ done: } static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; @@ -336,7 +336,7 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, lock_sock_nested(sk, L2CAP_NESTING_PARENT); - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); @@ -1239,6 +1239,10 @@ static void l2cap_sock_kill(struct sock *sk) BT_DBG("sk %p state %s", sk, state_to_string(sk->sk_state)); + /* Sock is dead, so set chan data to NULL, avoid other task use invalid + * sock pointer. + */ + l2cap_pi(sk)->chan->data = NULL; /* Kill poor orphan */ l2cap_chan_put(l2cap_pi(sk)->chan); @@ -1481,12 +1485,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) { - struct sock *sk = chan->data; - struct l2cap_pinfo *pi = l2cap_pi(sk); + struct sock *sk; + struct l2cap_pinfo *pi; int err; - lock_sock(sk); + sk = chan->data; + if (!sk) + return -ENXIO; + pi = l2cap_pi(sk); + lock_sock(sk); if (chan->mode == L2CAP_MODE_ERTM && !list_empty(&pi->rx_busy)) { err = -ENOMEM; goto done; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 80f220b7e19d..ad4793ea052d 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3457,6 +3457,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * will be kept and this function does nothing. */ p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + if (!p) { + err = -EIO; + goto unlock; + } if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) p->auto_connect = HCI_AUTO_CONN_DISABLED; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 29aa07e9db9d..37d63d768afb 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -468,8 +468,8 @@ done: return err; } -static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; @@ -483,7 +483,7 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f goto done; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 71d36582d4ef..a5ac160c592e 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -647,7 +647,7 @@ done: } static int sco_sock_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; @@ -656,7 +656,7 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, lock_sock(sk); - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1e7ea3a4b7ef..4f9fdf400584 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { - if (hcon->role == HCI_ROLE_MASTER) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp->method = CFM_PASSKEY; else smp->method = REQ_PASSKEY; @@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp) smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); else SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp) int ret; bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp) return SMP_CONFIRM_FAILED; } - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 stk[16]; __le64 rand = 0; __le16 ediv = 0; @@ -1256,14 +1257,15 @@ static void smp_distribute_keys(struct smp_chan *smp) rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ - if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) && + (smp->remote_key_dist & KEY_DIST_MASK)) { smp_allow_key_dist(smp); return; } req = (void *) &smp->preq[1]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -1432,7 +1434,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16]) struct hci_conn *hcon = smp->conn->hcon; u8 *na, *nb, a[7], b[7]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { na = smp->prnd; nb = smp->rrnd; } else { @@ -1460,7 +1462,7 @@ static void sc_dhkey_check(struct smp_chan *smp) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->preq[1], 3); @@ -1539,7 +1541,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) /* The round is only complete when the initiator * receives pairing random. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); if (smp->passkey_round == 20) @@ -1567,7 +1569,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); return 0; @@ -1578,7 +1580,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) case SMP_CMD_PUBLIC_KEY: default: /* Initiating device starts the round */ - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; bt_dev_dbg(hdev, "Starting passkey round %u", @@ -1623,7 +1625,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey) } /* Initiator sends DHKey check first */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) { @@ -1746,7 +1748,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_pairing rsp, *req = (void *) skb->data; struct l2cap_chan *chan = conn->smp; struct hci_dev *hdev = conn->hcon->hdev; - struct smp_chan *smp; + struct smp_chan *smp = chan->data; u8 key_size, auth, sec_level; int ret; @@ -1755,16 +1757,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*req)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_SLAVE) + if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; - if (!chan->data) + if (!smp) { smp = smp_chan_create(conn); - else - smp = chan->data; - - if (!smp) - return SMP_UNSPECIFIED; + if (!smp) + return SMP_UNSPECIFIED; + } /* We didn't start the pairing, so match remote */ auth = req->auth_req & AUTH_REQ_MASK(hdev); @@ -1946,7 +1946,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rsp)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_MASTER) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; skb_pull(skb, sizeof(*rsp)); @@ -2041,7 +2041,7 @@ static u8 sc_check_confirm(struct smp_chan *smp) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM); - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2063,7 +2063,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) u8 auth; /* The issue is only observed when we're in responder role */ - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_UNSPECIFIED; if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { @@ -2099,7 +2099,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_dev *hdev = hcon->hdev; bt_dev_dbg(hdev, "conn %p %s", conn, - hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2121,7 +2122,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) return ret; } - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2156,7 +2157,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (!test_bit(SMP_FLAG_SC, &smp->flags)) return smp_random(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { pkax = smp->local_pk; pkbx = smp->remote_pk; na = smp->prnd; @@ -2169,7 +2170,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); @@ -2180,7 +2181,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 cfm[16]; err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk, @@ -2221,7 +2222,7 @@ mackey_and_ltk: return SMP_UNSPECIFIED; if (smp->method == REQ_OOB) { - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } @@ -2295,10 +2296,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, return false; } +static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_pairing cp; + + if (smp->conn->hcon->type == ACL_LINK) + build_bredr_pairing_cmd(smp, &cp, NULL); + else + build_pairing_cmd(smp->conn, &cp, NULL, auth); + + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); + + smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + + set_bit(SMP_FLAG_INITIATOR, &smp->flags); +} + static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_security_req *rp = (void *) skb->data; - struct smp_cmd_pairing cp; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; struct smp_chan *smp; @@ -2347,16 +2365,20 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) skb_pull(skb, sizeof(*rp)); - memset(&cp, 0, sizeof(cp)); - build_pairing_cmd(conn, &cp, NULL, auth); + smp_send_pairing_req(smp, auth); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); + return 0; +} - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); +static void smp_send_security_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_security_req cp; - return 0; + cp.auth_req = auth; + smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); + + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); } int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) @@ -2427,23 +2449,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq |= SMP_AUTH_MITM; } - if (hcon->role == HCI_ROLE_MASTER) { - struct smp_cmd_pairing cp; - - build_pairing_cmd(conn, &cp, NULL, authreq); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); - } else { - struct smp_cmd_security_req cp; - cp.auth_req = authreq; - smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); - } + if (hcon->role == HCI_ROLE_MASTER) + smp_send_pairing_req(smp, authreq); + else + smp_send_security_req(smp, authreq); - set_bit(SMP_FLAG_INITIATOR, &smp->flags); ret = 0; unlock: @@ -2694,8 +2704,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) static u8 sc_select_method(struct smp_chan *smp) { - struct l2cap_conn *conn = smp->conn; - struct hci_conn *hcon = conn->hcon; struct smp_cmd_pairing *local, *remote; u8 local_mitm, remote_mitm, local_io, remote_io, method; @@ -2708,7 +2716,7 @@ static u8 sc_select_method(struct smp_chan *smp) * the "struct smp_cmd_pairing" from them we need to skip the * first byte which contains the opcode. */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local = (void *) &smp->preq[1]; remote = (void *) &smp->prsp[1]; } else { @@ -2777,7 +2785,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* Non-initiating device sends its public key after receiving * the key from the initiating device. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { err = sc_send_public_key(smp); if (err) return err; @@ -2839,7 +2847,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); @@ -2848,7 +2856,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); if (smp->method == REQ_PASSKEY) { @@ -2863,7 +2871,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* The Initiating device waits for the non-initiating device to * send the confirm value. */ - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd, @@ -2897,7 +2905,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->prsp[1], 3); @@ -2922,7 +2930,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED; - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) { set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags); return 0; @@ -2934,7 +2942,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) sc_add_ltk(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size); hcon->enc_key_size = smp->enc_key_size; } @@ -3083,7 +3091,6 @@ static void bredr_pairing(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - struct smp_cmd_pairing req; struct smp_chan *smp; bt_dev_dbg(hdev, "chan %p", chan); @@ -3135,14 +3142,7 @@ static void bredr_pairing(struct l2cap_chan *chan) bt_dev_dbg(hdev, "starting SMP over BR/EDR"); - /* Prepare and send the BR/EDR SMP Pairing Request */ - build_bredr_pairing_cmd(smp, &req, NULL); - - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &req, sizeof(req)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + smp_send_pairing_req(smp, 0x00); } static void smp_resume_cb(struct l2cap_chan *chan) diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index de33dc1b0daa..891cdf61c65a 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -79,6 +79,51 @@ static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args) args->args[3], args->args[4]); } +static const struct bpf_ctx_arg_aux *find_ctx_arg_info(struct bpf_prog_aux *aux, int offset) +{ + int i; + + for (i = 0; i < aux->ctx_arg_info_size; i++) + if (aux->ctx_arg_info[i].offset == offset) + return &aux->ctx_arg_info[i]; + + return NULL; +} + +/* There is only one check at the moment: + * - zero should not be passed for pointer parameters not marked as nullable. + */ +static int check_test_run_args(struct bpf_prog *prog, struct bpf_dummy_ops_test_args *args) +{ + const struct btf_type *func_proto = prog->aux->attach_func_proto; + + for (u32 arg_no = 0; arg_no < btf_type_vlen(func_proto) ; ++arg_no) { + const struct btf_param *param = &btf_params(func_proto)[arg_no]; + const struct bpf_ctx_arg_aux *info; + const struct btf_type *t; + int offset; + + if (args->args[arg_no] != 0) + continue; + + /* Program is validated already, so there is no need + * to check if t is NULL. + */ + t = btf_type_skip_modifiers(bpf_dummy_ops_btf, param->type, NULL); + if (!btf_type_is_ptr(t)) + continue; + + offset = btf_ctx_arg_offset(bpf_dummy_ops_btf, func_proto, arg_no); + info = find_ctx_arg_info(prog->aux, offset); + if (info && (info->reg_type & PTR_MAYBE_NULL)) + continue; + + return -EINVAL; + } + + return 0; +} + extern const struct bpf_link_ops bpf_struct_ops_link_lops; int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, @@ -87,7 +132,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops; const struct btf_type *func_proto; struct bpf_dummy_ops_test_args *args; - struct bpf_tramp_links *tlinks; + struct bpf_tramp_links *tlinks = NULL; struct bpf_tramp_link *link = NULL; void *image = NULL; unsigned int op_idx; @@ -109,6 +154,10 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, if (IS_ERR(args)) return PTR_ERR(args); + err = check_test_run_args(prog, args); + if (err) + goto out; + tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); if (!tlinks) { err = -ENOMEM; @@ -133,7 +182,9 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, if (err < 0) goto out; - arch_protect_bpf_trampoline(image, PAGE_SIZE); + err = arch_protect_bpf_trampoline(image, PAGE_SIZE); + if (err) + goto out; prog_ret = dummy_ops_call_op(image, args); err = dummy_ops_copy_args(args); @@ -230,7 +281,7 @@ static void bpf_dummy_unreg(void *kdata) { } -static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb) +static int bpf_dummy_ops__test_1(struct bpf_dummy_ops_state *cb__nullable) { return 0; } @@ -247,7 +298,7 @@ static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb) } static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { - .test_1 = bpf_dummy_test_1, + .test_1 = bpf_dummy_ops__test_1, .test_2 = bpf_dummy_test_2, .test_sleepable = bpf_dummy_test_sleepable, }; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 4cd29fb490f7..36ae54f57bf5 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -575,6 +575,13 @@ __bpf_kfunc int bpf_modify_return_test2(int a, int *b, short c, int d, return a + *b + c + d + (long)e + f + g; } +__bpf_kfunc int bpf_modify_return_test_tp(int nonce) +{ + trace_bpf_trigger_tp(nonce); + + return nonce; +} + int noinline bpf_fentry_shadow_test(int a) { return a + 1; @@ -622,6 +629,7 @@ __bpf_kfunc_end_defs(); BTF_KFUNCS_START(bpf_test_modify_return_ids) BTF_ID_FLAGS(func, bpf_modify_return_test) BTF_ID_FLAGS(func, bpf_modify_return_test2) +BTF_ID_FLAGS(func, bpf_modify_return_test_tp) BTF_ID_FLAGS(func, bpf_fentry_test1, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_test_modify_return_ids) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ecac7886988b..fb1115857e49 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -203,7 +203,7 @@ static int br_change_mtu(struct net_device *dev, int new_mtu) { struct net_bridge *br = netdev_priv(dev); - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); /* this flag will be cleared if the MTU was automatically adjusted */ br_opt_toggle(br, BROPT_MTU_SET_BY_USER, true); @@ -395,7 +395,7 @@ static int br_fill_forward_path(struct net_device_path_ctx *ctx, br_vlan_fill_forward_path_pvid(br, ctx, path); f = br_fdb_find_rcu(br, ctx->daddr, path->bridge.vlan_id); - if (!f || !f->dst) + if (!f) return -1; dst = READ_ONCE(f->dst); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index d97064d460dc..e19b583ff2c6 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -25,8 +25,8 @@ static inline int should_deliver(const struct net_bridge_port *p, vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) && - nbp_switchdev_allowed_egress(p, skb) && + (br_mst_is_enabled(p->br) || p->state == BR_STATE_FORWARDING) && + br_allowed_egress(vg, skb) && nbp_switchdev_allowed_egress(p, skb) && !br_skb_isolated(p, skb); } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 9a1cb5079a7a..b2ae0d2434d2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2045,16 +2045,14 @@ void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; - HLIST_HEAD(deleted_head); struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_find_del_pg(br, pg); - hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); - br_multicast_gc(&deleted_head); + flush_work(&br->mcast_gc_work); br_multicast_port_ctx_deinit(&port->multicast_ctx); free_percpu(port->mcast_stats); } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 22e35623c148..a9e1b56f854d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -399,7 +399,8 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ goto free_skb; rt = ip_route_output(net, iph->daddr, 0, - RT_TOS(iph->tos), 0); + RT_TOS(iph->tos), 0, + RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ @@ -618,8 +619,12 @@ static unsigned int br_nf_local_in(void *priv, if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT; + if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + WARN_ON_ONCE(skb_shared(skb)); - WARN_ON_ONCE(refcount_read(&nfct->use) != 1); /* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. @@ -1225,7 +1230,6 @@ static struct ctl_table brnf_table[] = { .mode = 0644, .proc_handler = brnf_sysctl_call_tables, }, - { } }; static inline void br_netfilter_sysctl_default(struct brnf_net *brnf) @@ -1274,7 +1278,7 @@ static int br_netfilter_sysctl_init_net(struct net *net) static void br_netfilter_sysctl_exit_net(struct net *net, struct brnf_net *brnet) { - struct ctl_table *table = brnet->ctl_hdr->ctl_table_arg; + const struct ctl_table *table = brnet->ctl_hdr->ctl_table_arg; unregister_net_sysctl_table(brnet->ctl_hdr); if (!net_eq(net, &init_net)) diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 81833ca7a2c7..a966a6ec8263 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -65,13 +65,14 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, { struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err; if (metadata) return -EEXIST; - metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, - key, 0); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, key, 0); if (!metadata) return -EINVAL; @@ -185,6 +186,7 @@ void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tunnel_dst; __be64 tunnel_id; int err; @@ -202,7 +204,8 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, return err; if (BR_INPUT_SKB_CB(skb)->backup_nhid) { - tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tunnel_dst = __ip_tun_set_dst(0, 0, 0, 0, 0, flags, tunnel_id, 0); if (!tunnel_dst) return -ENOMEM; diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 8480684f2762..20139fa1be1f 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -201,14 +201,14 @@ int cfctrl_linkup_request(struct cflayer *layer, struct cflayer *user_layer) { struct cfctrl *cfctrl = container_obj(layer); + struct cflayer *dn = cfctrl->serv.layer.dn; + char utility_name[UTILITY_NAME_LENGTH]; + struct cfctrl_request_info *req; + struct cfpkt *pkt; u32 tmp32; u16 tmp16; u8 tmp8; - struct cfctrl_request_info *req; int ret; - char utility_name[16]; - struct cfpkt *pkt; - struct cflayer *dn = cfctrl->serv.layer.dn; if (!dn) { pr_debug("not able to send linkup request\n"); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index a6fb89fa6278..7e8a20f2fc42 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -30,10 +30,6 @@ MODULE_ALIAS("can-proto-" __stringify(CAN_J1939)); /* CAN_HDR: #bytes before can_frame data part */ #define J1939_CAN_HDR (offsetof(struct can_frame, data)) -/* CAN_FTR: #bytes beyond data part */ -#define J1939_CAN_FTR (sizeof(struct can_frame) - J1939_CAN_HDR - \ - sizeof(((struct can_frame *)0)->data)) - /* lowest layer */ static void j1939_can_recv(struct sk_buff *iskb, void *data) { @@ -342,7 +338,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) memset(cf, 0, J1939_CAN_HDR); /* make it a full can frame again */ - skb_put(skb, J1939_CAN_FTR + (8 - dlc)); + skb_put_zero(skb, 8 - dlc); canid = CAN_EFF_FLAG | (skcb->priority << 26) | diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fe3df23a2595..4be73de5033c 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1593,8 +1593,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, struct j1939_sk_buff_cb skcb = *j1939_skb_to_cb(skb); struct j1939_session *session; const u8 *dat; + int len, ret; pgn_t pgn; - int len; netdev_dbg(priv->ndev, "%s\n", __func__); @@ -1653,7 +1653,22 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, session->tskey = priv->rx_tskey++; j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_RTS); - WARN_ON_ONCE(j1939_session_activate(session)); + ret = j1939_session_activate(session); + if (ret) { + /* Entering this scope indicates an issue with the J1939 bus. + * Possible scenarios include: + * - A time lapse occurred, and a new session was initiated + * due to another packet being sent correctly. This could + * have been caused by too long interrupt, debugger, or being + * out-scheduled by another task. + * - The bus is receiving numerous erroneous packets, either + * from a malfunctioning device or during a test scenario. + */ + netdev_alert(priv->ndev, "%s: 0x%p: concurrent session with same addr (%02x %02x) is already active.\n", + __func__, session, skcb.addr.sa, skcb.addr.da); + j1939_session_put(session); + return NULL; + } return session; } @@ -1681,6 +1696,8 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); + if (session->transmission) + j1939_session_deactivate_activate_next(session); return -EBUSY; } diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 1daf95e17d67..3a5bd1cd1e99 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -429,7 +429,10 @@ static int is_out(const struct crush_map *map, /** * crush_choose_firstn - choose numrep distinct items of given type * @map: the crush_map + * @work: working space initialized by crush_init_workspace() * @bucket: the bucket we are choose an item from + * @weight: weight vector (for map leaves) + * @weight_max: size of weight vector * @x: crush input value * @numrep: the number of items to choose * @type: the type of item to choose @@ -445,6 +448,7 @@ static int is_out(const struct crush_map *map, * @vary_r: pass r to recursive calls * @out2: second output vector for leaf items (if @recurse_to_leaf) * @parent_r: r value passed from the parent + * @choose_args: weights and ids for each known bucket */ static int crush_choose_firstn(const struct crush_map *map, struct crush_work *work, @@ -636,9 +640,8 @@ reject: } -/** +/* * crush_choose_indep: alternative breadth-first positionally stable mapping - * */ static void crush_choose_indep(const struct crush_map *map, struct crush_work *work, diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index f263f7e91a21..ab66b599ac47 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1085,13 +1085,19 @@ static void delayed_work(struct work_struct *work) struct ceph_mon_client *monc = container_of(work, struct ceph_mon_client, delayed_work.work); - dout("monc delayed_work\n"); mutex_lock(&monc->mutex); + dout("%s mon%d\n", __func__, monc->cur_mon); + if (monc->cur_mon < 0) { + goto out; + } + if (monc->hunting) { dout("%s continuing hunt\n", __func__); reopen_session(monc); } else { int is_auth = ceph_auth_is_authenticated(monc->auth); + + dout("%s is_authed %d\n", __func__, is_auth); if (ceph_con_keepalive_expired(&monc->con, CEPH_MONC_PING_TIMEOUT)) { dout("monc keepalive timeout\n"); @@ -1116,6 +1122,8 @@ static void delayed_work(struct work_struct *work) } } __schedule_delayed(monc); + +out: mutex_unlock(&monc->mutex); } @@ -1232,13 +1240,15 @@ EXPORT_SYMBOL(ceph_monc_init); void ceph_monc_stop(struct ceph_mon_client *monc) { dout("stop\n"); - cancel_delayed_work_sync(&monc->delayed_work); mutex_lock(&monc->mutex); __close_session(monc); + monc->hunting = false; monc->cur_mon = -1; mutex_unlock(&monc->mutex); + cancel_delayed_work_sync(&monc->delayed_work); + /* * flush msgr queue before we destroy ourselves to ensure that: * - any work that references our embedded con is finished. diff --git a/net/core/Makefile b/net/core/Makefile index 6e6548011fae..62be9aef2528 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o +obj-$(CONFIG_NET_IEEE8021Q_HELPERS) += ieee8021q_helpers.o obj-$(CONFIG_NET_SELFTESTS) += selftests.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o @@ -41,4 +42,4 @@ obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o -obj-$(CONFIG_NET_TEST) += gso_test.o +obj-$(CONFIG_NET_TEST) += net_test.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 6c4d90b24d46..bc01b3aa6b0f 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -496,27 +496,22 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) if (!bpf_capable()) return ERR_PTR(-EPERM); - nla_for_each_nested(nla, nla_stgs, rem) { - if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { - if (nla_len(nla) != sizeof(u32)) - return ERR_PTR(-EINVAL); - nr_maps++; - } + nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, + nla_stgs, rem) { + if (nla_len(nla) != sizeof(u32)) + return ERR_PTR(-EINVAL); + nr_maps++; } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); if (!diag) return ERR_PTR(-ENOMEM); - nla_for_each_nested(nla, nla_stgs, rem) { - struct bpf_map *map; - int map_fd; - - if (nla_type(nla) != SK_DIAG_BPF_STORAGE_REQ_MAP_FD) - continue; + nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, + nla_stgs, rem) { + int map_fd = nla_get_u32(nla); + struct bpf_map *map = bpf_map_get(map_fd); - map_fd = nla_get_u32(nla); - map = bpf_map_get(map_fd); if (IS_ERR(map)) { err = PTR_ERR(map); goto err_free; diff --git a/net/core/datagram.c b/net/core/datagram.c index a8b625abe242..e72dd78471a6 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -324,25 +324,6 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(skb_free_datagram); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) -{ - bool slow; - - if (!skb_unref(skb)) { - sk_peek_offset_bwd(sk, len); - return; - } - - slow = lock_sock_fast(sk); - sk_peek_offset_bwd(sk, len); - skb_orphan(skb); - unlock_sock_fast(sk, slow); - - /* skb is now orphaned, can be freed outside of locked section */ - __kfree_skb(skb); -} -EXPORT_SYMBOL(__skb_free_datagram_locked); - int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, @@ -435,15 +416,23 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { - struct page *page = skb_frag_page(frag); - u8 *vaddr = kmap(page); + u32 p_off, p_len, copied; + struct page *p; + u8 *vaddr; if (copy > len) copy = len; - n = INDIRECT_CALL_1(cb, simple_copy_to_iter, - vaddr + skb_frag_off(frag) + offset - start, - copy, data, to); - kunmap(page); + + n = 0; + skb_frag_foreach_page(frag, + skb_frag_off(frag) + offset - start, + copy, p, p_off, p_len, copied) { + vaddr = kmap_local_page(p); + n += INDIRECT_CALL_1(cb, simple_copy_to_iter, + vaddr + p_off, p_len, data, to); + kunmap_local(vaddr); + } + offset += n; if (n != copy) goto short_copy; diff --git a/net/core/dev.c b/net/core/dev.c index e8fb4ef8a85f..2b4819b610b8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -77,7 +77,9 @@ #include <linux/hash.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sched/isolation.h> #include <linux/sched/mm.h> +#include <linux/smpboot.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/string.h> @@ -197,35 +199,60 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } -static inline void rps_lock_irqsave(struct softnet_data *sd, - unsigned long *flags) +#ifndef CONFIG_PREEMPT_RT + +static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key); + +static int __init setup_backlog_napi_threads(char *arg) +{ + static_branch_enable(&use_backlog_threads_key); + return 0; +} +early_param("thread_backlog_napi", setup_backlog_napi_threads); + +static bool use_backlog_threads(void) +{ + return static_branch_unlikely(&use_backlog_threads_key); +} + +#else + +static bool use_backlog_threads(void) { - if (IS_ENABLED(CONFIG_RPS)) + return true; +} + +#endif + +static inline void backlog_lock_irq_save(struct softnet_data *sd, + unsigned long *flags) +{ + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_save(*flags); } -static inline void rps_lock_irq_disable(struct softnet_data *sd) +static inline void backlog_lock_irq_disable(struct softnet_data *sd) { - if (IS_ENABLED(CONFIG_RPS)) + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_disable(); } -static inline void rps_unlock_irq_restore(struct softnet_data *sd, - unsigned long *flags) +static inline void backlog_unlock_irq_restore(struct softnet_data *sd, + unsigned long *flags) { - if (IS_ENABLED(CONFIG_RPS)) + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } -static inline void rps_unlock_irq_enable(struct softnet_data *sd) +static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { - if (IS_ENABLED(CONFIG_RPS)) + if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_enable(); @@ -912,6 +939,18 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id) } EXPORT_SYMBOL(dev_get_by_napi_id); +static DEFINE_SEQLOCK(netdev_rename_lock); + +void netdev_copy_name(struct net_device *dev, char *name) +{ + unsigned int seq; + + do { + seq = read_seqbegin(&netdev_rename_lock); + strscpy(name, dev->name, IFNAMSIZ); + } while (read_seqretry(&netdev_rename_lock, seq)); +} + /** * netdev_get_name - get a netdevice name, knowing its ifindex. * @net: network namespace @@ -923,7 +962,6 @@ int netdev_get_name(struct net *net, char *name, int ifindex) struct net_device *dev; int ret; - down_read(&devnet_rename_sem); rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); @@ -932,12 +970,11 @@ int netdev_get_name(struct net *net, char *name, int ifindex) goto out; } - strcpy(name, dev->name); + netdev_copy_name(dev, name); ret = 0; out: rcu_read_unlock(); - up_read(&devnet_rename_sem); return ret; } @@ -1189,7 +1226,10 @@ int dev_change_name(struct net_device *dev, const char *newname) memcpy(oldname, dev->name, IFNAMSIZ); + write_seqlock_bh(&netdev_rename_lock); err = dev_get_valid_name(net, dev, newname); + write_sequnlock_bh(&netdev_rename_lock); + if (err < 0) { up_write(&devnet_rename_sem); return err; @@ -1229,7 +1269,9 @@ rollback: if (err >= 0) { err = ret; down_write(&devnet_rename_sem); + write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); + write_sequnlock_bh(&netdev_rename_lock); memcpy(oldname, newname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; @@ -2057,6 +2099,11 @@ void net_dec_egress_queue(void) EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif +#ifdef CONFIG_NET_CLS_ACT +DEFINE_STATIC_KEY_FALSE(tcf_bypass_check_needed_key); +EXPORT_SYMBOL(tcf_bypass_check_needed_key); +#endif + DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL @@ -3917,6 +3964,11 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, if (!miniq) return ret; + if (static_branch_unlikely(&tcf_bypass_check_needed_key)) { + if (tcf_block_bypass_sw(miniq->block)) + return ret; + } + tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; tcf_set_drop_reason(skb, *drop_reason); @@ -4410,8 +4462,8 @@ EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines *************************************************************************/ +static DEFINE_PER_CPU(struct task_struct *, backlog_napi); -unsigned int sysctl_skb_defer_max __read_mostly = 64; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ @@ -4433,18 +4485,16 @@ static inline void ____napi_schedule(struct softnet_data *sd, */ thread = READ_ONCE(napi->thread); if (thread) { - /* Avoid doing set_bit() if the thread is in - * INTERRUPTIBLE state, cause napi_thread_wait() - * makes sure to proceed with napi polling - * if the thread is explicitly woken from here. - */ - if (READ_ONCE(thread->__state) != TASK_INTERRUPTIBLE) - set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); + if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi)) + goto use_local_napi; + + set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } } +use_local_napi: list_add_tail(&napi->poll_list, &sd->poll_list); WRITE_ONCE(napi->list_owner, smp_processor_id()); /* If not called from net_rx_action() @@ -4466,12 +4516,13 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { if (next_cpu < nr_cpu_ids) { + u32 head; #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *old_rflow; - u32 flow_id; u16 rxq_index; + u32 flow_id; int rc; /* Should we steer this flow to a different hardware queue? */ @@ -4493,16 +4544,16 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb, goto out; old_rflow = rflow; rflow = &flow_table->flows[flow_id]; - rflow->filter = rc; - if (old_rflow->filter == rflow->filter) - old_rflow->filter = RPS_NO_FILTER; + WRITE_ONCE(rflow->filter, rc); + if (old_rflow->filter == rc) + WRITE_ONCE(old_rflow->filter, RPS_NO_FILTER); out: #endif - rflow->last_qtail = - per_cpu(softnet_data, next_cpu).input_queue_head; + head = READ_ONCE(per_cpu(softnet_data, next_cpu).input_queue_head); + rps_input_queue_tail_save(&rflow->last_qtail, head); } - rflow->cpu = next_cpu; + WRITE_ONCE(rflow->cpu, next_cpu); return rflow; } @@ -4581,7 +4632,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, */ if (unlikely(tcpu != next_cpu) && (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || - ((int)(per_cpu(softnet_data, tcpu).input_queue_head - + ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); @@ -4635,9 +4686,9 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; cpu = READ_ONCE(rflow->cpu); - if (rflow->filter == filter_id && cpu < nr_cpu_ids && - ((int)(per_cpu(softnet_data, cpu).input_queue_head - - rflow->last_qtail) < + if (READ_ONCE(rflow->filter) == filter_id && cpu < nr_cpu_ids && + ((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) - + READ_ONCE(rflow->last_qtail)) < (int)(10 * flow_table->mask))) expire = false; } @@ -4684,6 +4735,11 @@ static void napi_schedule_rps(struct softnet_data *sd) #ifdef CONFIG_RPS if (sd != mysd) { + if (use_backlog_threads()) { + __napi_schedule_irqoff(&sd->backlog); + return; + } + sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; @@ -4698,6 +4754,23 @@ static void napi_schedule_rps(struct softnet_data *sd) __napi_schedule_irqoff(&mysd->backlog); } +void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu) +{ + unsigned long flags; + + if (use_backlog_threads()) { + backlog_lock_irq_save(sd, &flags); + + if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) + __napi_schedule_irqoff(&sd->backlog); + + backlog_unlock_irq_restore(sd, &flags); + + } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) { + smp_call_function_single_async(cpu, &sd->defer_csd); + } +} + #ifdef CONFIG_NET_FLOW_LIMIT int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif @@ -4749,37 +4822,45 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, struct softnet_data *sd; unsigned long flags; unsigned int qlen; + int max_backlog; + u32 tail; - reason = SKB_DROP_REASON_NOT_SPECIFIED; + reason = SKB_DROP_REASON_DEV_READY; + if (!netif_running(skb->dev)) + goto bad_dev; + + reason = SKB_DROP_REASON_CPU_BACKLOG; sd = &per_cpu(softnet_data, cpu); - rps_lock_irqsave(sd, &flags); - if (!netif_running(skb->dev)) - goto drop; + qlen = skb_queue_len_lockless(&sd->input_pkt_queue); + max_backlog = READ_ONCE(net_hotdata.max_backlog); + if (unlikely(qlen > max_backlog)) + goto cpu_backlog_drop; + backlog_lock_irq_save(sd, &flags); qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= READ_ONCE(net_hotdata.max_backlog) && - !skb_flow_limit(skb, qlen)) { - if (qlen) { -enqueue: - __skb_queue_tail(&sd->input_pkt_queue, skb); - input_queue_tail_incr_save(sd, qtail); - rps_unlock_irq_restore(sd, &flags); - return NET_RX_SUCCESS; + if (qlen <= max_backlog && !skb_flow_limit(skb, qlen)) { + if (!qlen) { + /* Schedule NAPI for backlog device. We can use + * non atomic operation as we own the queue lock. + */ + if (!__test_and_set_bit(NAPI_STATE_SCHED, + &sd->backlog.state)) + napi_schedule_rps(sd); } + __skb_queue_tail(&sd->input_pkt_queue, skb); + tail = rps_input_queue_tail_incr(sd); + backlog_unlock_irq_restore(sd, &flags); - /* Schedule NAPI for backlog device - * We can use non atomic operation since we own the queue lock - */ - if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) - napi_schedule_rps(sd); - goto enqueue; + /* save the tail outside of the critical section */ + rps_input_queue_tail_save(qtail, tail); + return NET_RX_SUCCESS; } - reason = SKB_DROP_REASON_CPU_BACKLOG; -drop: - sd->dropped++; - rps_unlock_irq_restore(sd, &flags); + backlog_unlock_irq_restore(sd, &flags); +cpu_backlog_drop: + atomic_inc(&sd->dropped); +bad_dev: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); return NET_RX_DROP; @@ -5844,21 +5925,21 @@ static void flush_backlog(struct work_struct *work) local_bh_disable(); sd = this_cpu_ptr(&softnet_data); - rps_lock_irq_disable(sd); + backlog_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); dev_kfree_skb_irq(skb); - input_queue_head_incr(sd); + rps_input_queue_head_incr(sd); } } - rps_unlock_irq_enable(sd); + backlog_unlock_irq_enable(sd); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); - input_queue_head_incr(sd); + rps_input_queue_head_incr(sd); } } local_bh_enable(); @@ -5870,14 +5951,14 @@ static bool flush_required(int cpu) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; - rps_lock_irq_disable(sd); + backlog_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); - rps_unlock_irq_enable(sd); + backlog_unlock_irq_enable(sd); return do_flush; #endif @@ -5943,7 +6024,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) #ifdef CONFIG_RPS struct softnet_data *remsd = sd->rps_ipi_list; - if (remsd) { + if (!use_backlog_threads() && remsd) { sd->rps_ipi_list = NULL; local_irq_enable(); @@ -5958,7 +6039,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) { #ifdef CONFIG_RPS - return sd->rps_ipi_list != NULL; + return !use_backlog_threads() && sd->rps_ipi_list; #else return false; #endif @@ -5986,13 +6067,14 @@ static int process_backlog(struct napi_struct *napi, int quota) rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); - input_queue_head_incr(sd); - if (++work >= quota) + if (++work >= quota) { + rps_input_queue_head_add(sd, work); return work; + } } - rps_lock_irq_disable(sd); + backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). @@ -6002,15 +6084,17 @@ static int process_backlog(struct napi_struct *napi, int quota) * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ - napi->state = 0; + napi->state &= NAPIF_STATE_THREADED; again = false; } else { skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); } - rps_unlock_irq_enable(sd); + backlog_unlock_irq_enable(sd); } + if (work) + rps_input_queue_head_add(sd, work); return work; } @@ -6447,7 +6531,7 @@ int dev_set_threaded(struct net_device *dev, bool threaded) } } - dev->threaded = threaded; + WRITE_ONCE(dev->threaded, threaded); /* Make sure kthread is created before THREADED bit * is set. @@ -6538,7 +6622,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, * threaded mode will not be enabled in napi_enable(). */ if (dev->threaded && napi_kthread_create(napi)) - dev->threaded = 0; + dev->threaded = false; netif_napi_set_irq(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight); @@ -6716,8 +6800,6 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) static int napi_thread_wait(struct napi_struct *napi) { - bool woken = false; - set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { @@ -6726,15 +6808,13 @@ static int napi_thread_wait(struct napi_struct *napi) * Testing SCHED bit is not enough because SCHED bit might be * set by some other busy poll thread or by napi_disable(). */ - if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) { + if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); - /* woken being true indicates this thread owns this napi. */ - woken = true; set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); @@ -6742,43 +6822,48 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static int napi_threaded_poll(void *data) +static void napi_threaded_poll_loop(struct napi_struct *napi) { - struct napi_struct *napi = data; struct softnet_data *sd; - void *have; + unsigned long last_qs = jiffies; - while (!napi_thread_wait(napi)) { - unsigned long last_qs = jiffies; - - for (;;) { - bool repoll = false; + for (;;) { + bool repoll = false; + void *have; - local_bh_disable(); - sd = this_cpu_ptr(&softnet_data); - sd->in_napi_threaded_poll = true; + local_bh_disable(); + sd = this_cpu_ptr(&softnet_data); + sd->in_napi_threaded_poll = true; - have = netpoll_poll_lock(napi); - __napi_poll(napi, &repoll); - netpoll_poll_unlock(have); + have = netpoll_poll_lock(napi); + __napi_poll(napi, &repoll); + netpoll_poll_unlock(have); - sd->in_napi_threaded_poll = false; - barrier(); + sd->in_napi_threaded_poll = false; + barrier(); - if (sd_has_rps_ipi_waiting(sd)) { - local_irq_disable(); - net_rps_action_and_irq_enable(sd); - } - skb_defer_free_flush(sd); - local_bh_enable(); + if (sd_has_rps_ipi_waiting(sd)) { + local_irq_disable(); + net_rps_action_and_irq_enable(sd); + } + skb_defer_free_flush(sd); + local_bh_enable(); - if (!repoll) - break; + if (!repoll) + break; - rcu_softirq_qs_periodic(last_qs); - cond_resched(); - } + rcu_softirq_qs_periodic(last_qs); + cond_resched(); } +} + +static int napi_threaded_poll(void *data) +{ + struct napi_struct *napi = data; + + while (!napi_thread_wait(napi)) + napi_threaded_poll_loop(napi); + return 0; } @@ -8459,27 +8544,29 @@ static void dev_change_rx_flags(struct net_device *dev, int flags) static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags; + unsigned int promiscuity, flags; kuid_t uid; kgid_t gid; ASSERT_RTNL(); - dev->flags |= IFF_PROMISC; - dev->promiscuity += inc; - if (dev->promiscuity == 0) { + promiscuity = dev->promiscuity + inc; + if (promiscuity == 0) { /* * Avoid overflow. * If inc causes overflow, untouch promisc and return error. */ - if (inc < 0) - dev->flags &= ~IFF_PROMISC; - else { - dev->promiscuity -= inc; + if (unlikely(inc > 0)) { netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } + flags = old_flags & ~IFF_PROMISC; + } else { + flags = old_flags | IFF_PROMISC; } - if (dev->flags != old_flags) { + WRITE_ONCE(dev->promiscuity, promiscuity); + if (flags != old_flags) { + WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s promiscuous mode\n", dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { @@ -8530,25 +8617,27 @@ EXPORT_SYMBOL(dev_set_promiscuity); static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags, old_gflags = dev->gflags; + unsigned int allmulti, flags; ASSERT_RTNL(); - dev->flags |= IFF_ALLMULTI; - dev->allmulti += inc; - if (dev->allmulti == 0) { + allmulti = dev->allmulti + inc; + if (allmulti == 0) { /* * Avoid overflow. * If inc causes overflow, untouch allmulti and return error. */ - if (inc < 0) - dev->flags &= ~IFF_ALLMULTI; - else { - dev->allmulti -= inc; + if (unlikely(inc > 0)) { netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } + flags = old_flags & ~IFF_ALLMULTI; + } else { + flags = old_flags | IFF_ALLMULTI; } - if (dev->flags ^ old_flags) { + WRITE_ONCE(dev->allmulti, allmulti); + if (flags != old_flags) { + WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s allmulticast mode\n", dev->flags & IFF_ALLMULTI ? "entered" : "left"); dev_change_rx_flags(dev, IFF_ALLMULTI); @@ -8874,7 +8963,7 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) return -ERANGE; if (new_len != orig_len) { - dev->tx_queue_len = new_len; + WRITE_ONCE(dev->tx_queue_len, new_len); res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); if (res) @@ -8888,7 +8977,7 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) err_rollback: netdev_err(dev, "refused to change device tx_queue_len\n"); - dev->tx_queue_len = orig_len; + WRITE_ONCE(dev->tx_queue_len, orig_len); return res; } @@ -9134,7 +9223,7 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) netif_carrier_off(dev); else netif_carrier_on(dev); - dev->proto_down = proto_down; + WRITE_ONCE(dev->proto_down, proto_down); return 0; } @@ -9148,18 +9237,21 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down) void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value) { + u32 proto_down_reason; int b; if (!mask) { - dev->proto_down_reason = value; + proto_down_reason = value; } else { + proto_down_reason = dev->proto_down_reason; for_each_set_bit(b, &mask, 32) { if (value & (1 << b)) - dev->proto_down_reason |= BIT(b); + proto_down_reason |= BIT(b); else - dev->proto_down_reason &= ~BIT(b); + proto_down_reason &= ~BIT(b); } } + WRITE_ONCE(dev->proto_down_reason, proto_down_reason); } struct bpf_xdp_link { @@ -10349,25 +10441,12 @@ err_free_name: } EXPORT_SYMBOL(register_netdevice); -/** - * init_dummy_netdev - init a dummy network device for NAPI - * @dev: device to init - * - * This takes a network device structure and initialize the minimum - * amount of fields so it can be used to schedule NAPI polls without - * registering a full blown interface. This is to be used by drivers - * that need to tie several hardware interfaces to a single NAPI - * poll scheduler due to HW limitations. +/* Initialize the core of a dummy net device. + * This is useful if you are calling this function after alloc_netdev(), + * since it does not memset the net_device fields. */ -void init_dummy_netdev(struct net_device *dev) +static void init_dummy_netdev_core(struct net_device *dev) { - /* Clear everything. Note we don't initialize spinlocks - * are they aren't supposed to be taken by any of the - * NAPI code and this dummy netdev is supposed to be - * only ever used for NAPI polls - */ - memset(dev, 0, sizeof(struct net_device)); - /* make sure we BUG if trying to hit standard * register/unregister code path */ @@ -10388,8 +10467,28 @@ void init_dummy_netdev(struct net_device *dev) * its refcount. */ } -EXPORT_SYMBOL_GPL(init_dummy_netdev); +/** + * init_dummy_netdev - init a dummy network device for NAPI + * @dev: device to init + * + * This takes a network device structure and initializes the minimum + * amount of fields so it can be used to schedule NAPI polls without + * registering a full blown interface. This is to be used by drivers + * that need to tie several hardware interfaces to a single NAPI + * poll scheduler due to HW limitations. + */ +void init_dummy_netdev(struct net_device *dev) +{ + /* Clear everything. Note we don't initialize spinlocks + * as they aren't supposed to be taken by any of the + * NAPI code and this dummy netdev is supposed to be + * only ever used for NAPI polls + */ + memset(dev, 0, sizeof(struct net_device)); + init_dummy_netdev_core(dev); +} +EXPORT_SYMBOL_GPL(init_dummy_netdev); /** * register_netdev - register a network device @@ -10988,7 +11087,8 @@ void free_netdev(struct net_device *dev) dev->xdp_bulkq = NULL; /* Compatibility with error handling in drivers */ - if (dev->reg_state == NETREG_UNINITIALIZED) { + if (dev->reg_state == NETREG_UNINITIALIZED || + dev->reg_state == NETREG_DUMMY) { netdev_freemem(dev); return; } @@ -11002,6 +11102,19 @@ void free_netdev(struct net_device *dev) EXPORT_SYMBOL(free_netdev); /** + * alloc_netdev_dummy - Allocate and initialize a dummy net device. + * @sizeof_priv: size of private data to allocate space for + * + * Return: the allocated net_device on success, NULL otherwise + */ +struct net_device *alloc_netdev_dummy(int sizeof_priv) +{ + return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN, + init_dummy_netdev_core); +} +EXPORT_SYMBOL_GPL(alloc_netdev_dummy); + +/** * synchronize_net - Synchronize with packet receive processing * * Wait for packets currently being received to be done. @@ -11304,8 +11417,12 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, dev_net_set(dev, net); dev->ifindex = new_ifindex; - if (new_name[0]) /* Rename the netdev to prepared name */ + if (new_name[0]) { + /* Rename the netdev to prepared name */ + write_seqlock_bh(&netdev_rename_lock); strscpy(dev->name, new_name, IFNAMSIZ); + write_sequnlock_bh(&netdev_rename_lock); + } /* Fixup kobjects */ dev_set_uevent_suppress(&dev->dev, 1); @@ -11380,7 +11497,7 @@ static int dev_cpu_dead(unsigned int oldcpu) list_del_init(&napi->poll_list); if (napi->poll == process_backlog) - napi->state = 0; + napi->state &= NAPIF_STATE_THREADED; else ____napi_schedule(sd, napi); } @@ -11388,21 +11505,23 @@ static int dev_cpu_dead(unsigned int oldcpu) raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); + if (!use_backlog_threads()) { #ifdef CONFIG_RPS - remsd = oldsd->rps_ipi_list; - oldsd->rps_ipi_list = NULL; + remsd = oldsd->rps_ipi_list; + oldsd->rps_ipi_list = NULL; #endif - /* send out pending IPI's on offline CPU */ - net_rps_send_ipi(remsd); + /* send out pending IPI's on offline CPU */ + net_rps_send_ipi(remsd); + } /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx(skb); - input_queue_head_incr(oldsd); + rps_input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); - input_queue_head_incr(oldsd); + rps_input_queue_head_incr(oldsd); } return 0; @@ -11719,7 +11838,7 @@ static int net_page_pool_create(int cpuid) struct page_pool_params page_pool_params = { .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE, .flags = PP_FLAG_SYSTEM_POOL, - .nid = NUMA_NO_NODE, + .nid = cpu_to_mem(cpuid), }; struct page_pool *pp_ptr; @@ -11732,6 +11851,38 @@ static int net_page_pool_create(int cpuid) return 0; } +static int backlog_napi_should_run(unsigned int cpu) +{ + struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); + struct napi_struct *napi = &sd->backlog; + + return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state); +} + +static void run_backlog_napi(unsigned int cpu) +{ + struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); + + napi_threaded_poll_loop(&sd->backlog); +} + +static void backlog_napi_setup(unsigned int cpu) +{ + struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); + struct napi_struct *napi = &sd->backlog; + + napi->thread = this_cpu_read(backlog_napi); + set_bit(NAPI_STATE_THREADED, &napi->state); +} + +static struct smp_hotplug_thread backlog_threads = { + .store = &backlog_napi, + .thread_should_run = backlog_napi_should_run, + .thread_fn = run_backlog_napi, + .thread_comm = "backlog_napi/%u", + .setup = backlog_napi_setup, +}; + /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. @@ -11783,10 +11934,13 @@ static int __init net_dev_init(void) init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; + INIT_LIST_HEAD(&sd->backlog.poll_list); if (net_page_pool_create(i)) goto out; } + if (use_backlog_threads()) + smpboot_register_percpu_thread(&backlog_threads); dev_boot_phase = 0; @@ -11812,6 +11966,10 @@ static int __init net_dev_init(void) NULL, dev_cpu_dead); WARN_ON(rc < 0); rc = 0; + + /* avoid static key IPIs to isolated CPUs */ + if (housekeeping_enabled(HK_TYPE_MISC)) + net_enable_timestamp(); out: if (rc < 0) { for_each_possible_cpu(i) { diff --git a/net/core/dev.h b/net/core/dev.h index 2bcaf8eee50c..b7b518bc2be5 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -4,11 +4,9 @@ #include <linux/types.h> #include <linux/rwsem.h> +#include <linux/netdevice.h> struct net; -struct net_device; -struct netdev_bpf; -struct netdev_phys_item_id; struct netlink_ext_ack; struct cpumask; @@ -38,7 +36,6 @@ int dev_addr_init(struct net_device *dev); void dev_addr_check(struct net_device *dev); /* sysctls not referred to from outside net/core/ */ -extern unsigned int sysctl_skb_defer_max; extern int netdev_unregister_timeout_secs; extern int weight_p; extern int dev_weight_rx_bias; @@ -150,4 +147,23 @@ static inline void xdp_do_check_flushed(struct napi_struct *napi) { } #endif struct napi_struct *napi_by_id(unsigned int napi_id); +void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); + +#define XMIT_RECURSION_LIMIT 8 +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} + #endif diff --git a/net/core/dev_addr_lists_test.c b/net/core/dev_addr_lists_test.c index 4dbd0dc6aea2..8e1dba825e94 100644 --- a/net/core/dev_addr_lists_test.c +++ b/net/core/dev_addr_lists_test.c @@ -49,7 +49,6 @@ static int dev_addr_test_init(struct kunit *test) KUNIT_FAIL(test, "Can't register netdev %d", err); } - rtnl_lock(); return 0; } @@ -57,7 +56,6 @@ static void dev_addr_test_exit(struct kunit *test) { struct net_device *netdev = test->priv; - rtnl_unlock(); unregister_netdev(netdev); free_netdev(netdev); } @@ -67,6 +65,7 @@ static void dev_addr_test_basic(struct kunit *test) struct net_device *netdev = test->priv; u8 addr[ETH_ALEN]; + rtnl_lock(); KUNIT_EXPECT_TRUE(test, !!netdev->dev_addr); memset(addr, 2, sizeof(addr)); @@ -76,6 +75,7 @@ static void dev_addr_test_basic(struct kunit *test) memset(addr, 3, sizeof(addr)); dev_addr_set(netdev, addr); KUNIT_EXPECT_MEMEQ(test, netdev->dev_addr, addr, sizeof(addr)); + rtnl_unlock(); } static void dev_addr_test_sync_one(struct kunit *test) @@ -86,6 +86,7 @@ static void dev_addr_test_sync_one(struct kunit *test) datp = netdev_priv(netdev); + rtnl_lock(); memset(addr, 1, sizeof(addr)); eth_hw_addr_set(netdev, addr); @@ -103,6 +104,7 @@ static void dev_addr_test_sync_one(struct kunit *test) * considered synced and we overwrite in place. */ KUNIT_EXPECT_EQ(test, 0, datp->addr_seen); + rtnl_unlock(); } static void dev_addr_test_add_del(struct kunit *test) @@ -114,6 +116,7 @@ static void dev_addr_test_add_del(struct kunit *test) datp = netdev_priv(netdev); + rtnl_lock(); for (i = 1; i < 4; i++) { memset(addr, i, sizeof(addr)); KUNIT_EXPECT_EQ(test, 0, dev_addr_add(netdev, addr, @@ -143,6 +146,7 @@ static void dev_addr_test_add_del(struct kunit *test) __hw_addr_sync_dev(&netdev->dev_addrs, netdev, dev_addr_test_sync, dev_addr_test_unsync); KUNIT_EXPECT_EQ(test, 1, datp->addr_seen); + rtnl_unlock(); } static void dev_addr_test_del_main(struct kunit *test) @@ -150,6 +154,7 @@ static void dev_addr_test_del_main(struct kunit *test) struct net_device *netdev = test->priv; u8 addr[ETH_ALEN]; + rtnl_lock(); memset(addr, 1, sizeof(addr)); eth_hw_addr_set(netdev, addr); @@ -161,6 +166,7 @@ static void dev_addr_test_del_main(struct kunit *test) NETDEV_HW_ADDR_T_LAN)); KUNIT_EXPECT_EQ(test, -ENOENT, dev_addr_del(netdev, addr, NETDEV_HW_ADDR_T_LAN)); + rtnl_unlock(); } static void dev_addr_test_add_set(struct kunit *test) @@ -172,6 +178,7 @@ static void dev_addr_test_add_set(struct kunit *test) datp = netdev_priv(netdev); + rtnl_lock(); /* There is no external API like dev_addr_add_excl(), * so shuffle the tree a little bit and exploit aliasing. */ @@ -191,6 +198,7 @@ static void dev_addr_test_add_set(struct kunit *test) __hw_addr_sync_dev(&netdev->dev_addrs, netdev, dev_addr_test_sync, dev_addr_test_unsync); KUNIT_EXPECT_EQ(test, 0xffff, datp->addr_seen); + rtnl_unlock(); } static void dev_addr_test_add_excl(struct kunit *test) @@ -199,6 +207,7 @@ static void dev_addr_test_add_excl(struct kunit *test) u8 addr[ETH_ALEN]; int i; + rtnl_lock(); for (i = 0; i < 10; i++) { memset(addr, i, sizeof(addr)); KUNIT_EXPECT_EQ(test, 0, dev_uc_add_excl(netdev, addr)); @@ -213,6 +222,7 @@ static void dev_addr_test_add_excl(struct kunit *test) memset(addr, i, sizeof(addr)); KUNIT_EXPECT_EQ(test, -EEXIST, dev_uc_add_excl(netdev, addr)); } + rtnl_unlock(); } static struct kunit_case dev_addr_test_cases[] = { diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c index 0c0bdb058c5b..70c634b9e7b0 100644 --- a/net/core/dst_cache.c +++ b/net/core/dst_cache.c @@ -27,6 +27,7 @@ struct dst_cache_pcpu { static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, struct dst_entry *dst, u32 cookie) { + DEBUG_NET_WARN_ON_ONCE(!in_softirq()); dst_release(dst_cache->dst); if (dst) dst_hold(dst); @@ -40,6 +41,7 @@ static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, { struct dst_entry *dst; + DEBUG_NET_WARN_ON_ONCE(!in_softirq()); dst = idst->dst; if (!dst) goto fail; @@ -47,7 +49,8 @@ static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, /* the cache already hold a dst reference; it can't go away */ dst_hold(dst); - if (unlikely(!time_after(idst->refresh_ts, dst_cache->reset_ts) || + if (unlikely(!time_after(idst->refresh_ts, + READ_ONCE(dst_cache->reset_ts)) || (dst->obsolete && !dst->ops->check(dst, idst->cookie)))) { dst_cache_per_cpu_dst_set(idst, NULL, 0); dst_release(dst); @@ -111,7 +114,7 @@ void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, return; idst = this_cpu_ptr(dst_cache->cache); - dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst, + dst_cache_per_cpu_dst_set(idst, dst, rt6_get_cookie(dst_rt6_info(dst))); idst->in6_saddr = *saddr; } @@ -170,7 +173,7 @@ void dst_cache_reset_now(struct dst_cache *dst_cache) if (!dst_cache->cache) return; - dst_cache->reset_ts = jiffies; + dst_cache_reset(dst_cache); for_each_possible_cpu(i) { struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i); struct dst_entry *dst = idst->dst; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3f933ffcefc3..6ebffbc63236 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -1142,10 +1142,10 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct fib_rules_ops *ops; - int idx = 0, family; + int err, idx = 0, family; if (cb->strict_check) { - int err = fib_valid_dumprule_req(nlh, cb->extack); + err = fib_valid_dumprule_req(nlh, cb->extack); if (err < 0) return err; @@ -1158,17 +1158,17 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) if (ops == NULL) return -EAFNOSUPPORT; - dump_rules(skb, cb, ops); - - return skb->len; + return dump_rules(skb, cb, ops); } + err = 0; rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (idx < cb->args[0] || !try_module_get(ops->owner)) goto skip; - if (dump_rules(skb, cb, ops) < 0) + err = dump_rules(skb, cb, ops); + if (err < 0) break; cb->args[1] = 0; @@ -1178,7 +1178,7 @@ skip: rcu_read_unlock(); cb->args[0] = idx; - return skb->len; + return err; } static void notify_rule_change(int event, struct fib_rule *rule, @@ -1293,7 +1293,8 @@ static int __init fib_rules_init(void) int err; rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, 0); + rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, + RTNL_FLAG_DUMP_UNLOCKED); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) diff --git a/net/core/filter.c b/net/core/filter.c index ce255e0a2fbd..ab0455c64e49 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -87,6 +87,9 @@ #include "dev.h" +/* Keep the struct bpf_fib_lookup small so that it fits into a cacheline */ +static_assert(sizeof(struct bpf_fib_lookup) == 64, "struct bpf_fib_lookup size check"); + static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2276,12 +2279,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; @@ -2382,12 +2385,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; @@ -3541,13 +3544,20 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* Due to header grow, MSS needs to be downgraded. */ - if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) - skb_decrease_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; + + /* Due to header growth, MSS needs to be downgraded. + * There is a BUG_ON() when segmenting the frag_list with + * head_frag true, so linearize the skb after downgrading + * the MSS. + */ + if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { + skb_decrease_gso_size(shinfo, len_diff); + if (shinfo->frag_list) + return skb_linearize(skb); + } } return 0; @@ -4688,7 +4698,7 @@ set_compat: to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; if (flags & BPF_F_TUNINFO_FLAGS) - to->tunnel_flags = info->key.tun_flags; + to->tunnel_flags = ip_tunnel_flags_to_be16(info->key.tun_flags); else to->tunnel_ext = 0; @@ -4731,7 +4741,7 @@ BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) int err; if (unlikely(!info || - !(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))) { + !ip_tunnel_is_options_present(info->key.tun_flags))) { err = -ENOENT; goto err_clear; } @@ -4801,15 +4811,15 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; - info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; - if (flags & BPF_F_DONT_FRAGMENT) - info->key.tun_flags |= TUNNEL_DONT_FRAGMENT; - if (flags & BPF_F_ZERO_CSUM_TX) - info->key.tun_flags &= ~TUNNEL_CSUM; - if (flags & BPF_F_SEQ_NUMBER) - info->key.tun_flags |= TUNNEL_SEQ; - if (flags & BPF_F_NO_TUNNEL_KEY) - info->key.tun_flags &= ~TUNNEL_KEY; + __set_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); + __assign_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags, + flags & BPF_F_DONT_FRAGMENT); + __assign_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags, + !(flags & BPF_F_ZERO_CSUM_TX)); + __assign_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags, + flags & BPF_F_SEQ_NUMBER); + __assign_bit(IP_TUNNEL_KEY_BIT, info->key.tun_flags, + !(flags & BPF_F_NO_TUNNEL_KEY)); info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; @@ -4847,13 +4857,15 @@ BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); + IP_TUNNEL_DECLARE_FLAGS(present) = { }; if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; - ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT); + ip_tunnel_set_options_present(present); + ip_tunnel_info_opts_set(info, from, size, present); return 0; } @@ -5910,7 +5922,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { - fl4.flowi4_mark = 0; + if (flags & BPF_FIB_LOOKUP_MARK) + fl4.flowi4_mark = params->mark; + else + fl4.flowi4_mark = 0; fl4.flowi4_secid = 0; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); @@ -6053,7 +6068,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res, strict); } else { - fl6.flowi6_mark = 0; + if (flags & BPF_FIB_LOOKUP_MARK) + fl6.flowi6_mark = params->mark; + else + fl6.flowi6_mark = 0; fl6.flowi6_secid = 0; fl6.flowi6_tun_key.tun_id = 0; fl6.flowi6_uid = sock_net_uid(net, NULL); @@ -6131,7 +6149,7 @@ set_fwd_params: #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ - BPF_FIB_LOOKUP_SRC) + BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) @@ -8368,8 +8386,6 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_event_output_data_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 272f09251343..7b54f44f5372 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -455,17 +455,25 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + u32 val; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); - if (info->options_len) { - enc_opt->len = info->options_len; - ip_tunnel_info_opts_get(enc_opt->data, info); - enc_opt->dst_opt_type = info->key.tun_flags & - TUNNEL_OPTIONS_PRESENT; - } + if (!info->options_len) + return; + + enc_opt->len = info->options_len; + ip_tunnel_info_opts_get(enc_opt->data, info); + + ip_tunnel_set_options_present(flags); + ip_tunnel_flags_and(flags, info->key.tun_flags, flags); + + val = find_next_bit(flags, __IP_TUNNEL_FLAG_NUM, + IP_TUNNEL_GENEVE_OPT_BIT); + enc_opt->dst_opt_type = val < __IP_TUNNEL_FLAG_NUM ? val : 0; } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); @@ -1093,7 +1101,7 @@ bool __skb_flow_dissect(const struct net *net, } } - WARN_ON_ONCE(!net); + DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; diff --git a/net/core/gro.c b/net/core/gro.c index c7901253a1a8..b3b43de1a650 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -3,6 +3,7 @@ #include <net/dst_metadata.h> #include <net/busy_poll.h> #include <trace/events/net.h> +#include <linux/skbuff_ref.h> #define MAX_GRO_SKBS 8 @@ -230,6 +231,33 @@ done: return 0; } +int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) +{ + if (unlikely(p->len + skb->len >= 65536)) + return -E2BIG; + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + + skb_pull(skb, skb_gro_offset(skb)); + + NAPI_GRO_CB(p)->last = skb; + NAPI_GRO_CB(p)->count++; + p->data_len += skb->len; + + /* sk ownership - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; + skb->sk = NULL; + p->truesize += skb->truesize; + p->len += skb->len; + + NAPI_GRO_CB(skb)->same_flow = 1; + + return 0; +} + static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { @@ -330,8 +358,6 @@ static void gro_list_prepare(const struct list_head *head, list_for_each_entry(p, head, list) { unsigned long diffs; - NAPI_GRO_CB(p)->flush = 0; - if (hash != skb_get_hash_raw(p)) { NAPI_GRO_CB(p)->same_flow = 0; continue; @@ -471,7 +497,6 @@ found_ptype: sizeof(u32))); /* Avoid slow unaligned acc */ *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->is_atomic = 1; NAPI_GRO_CB(skb)->count = 1; if (unlikely(skb_is_gso(skb))) { NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; diff --git a/net/core/hotdata.c b/net/core/hotdata.c index c8a7a451c18a..d0aaaaa556f2 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-or-later -#include <net/hotdata.h> #include <linux/cache.h> #include <linux/jiffies.h> #include <linux/list.h> - +#include <net/hotdata.h> +#include <net/proto_memory.h> struct net_hotdata net_hotdata __cacheline_aligned = { .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base), @@ -18,5 +18,8 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .max_backlog = 1000, .dev_tx_weight = 64, .dev_rx_weight = 64, + .sysctl_max_skb_frags = MAX_SKB_FRAGS, + .sysctl_skb_defer_max = 64, + .sysctl_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE }; EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/ieee8021q_helpers.c b/net/core/ieee8021q_helpers.c new file mode 100644 index 000000000000..759a9b9f3f89 --- /dev/null +++ b/net/core/ieee8021q_helpers.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> + +#include <linux/array_size.h> +#include <linux/printk.h> +#include <linux/types.h> +#include <net/dscp.h> +#include <net/ieee8021q.h> + +/* The following arrays map Traffic Types (TT) to traffic classes (TC) for + * different number of queues as shown in the example provided by + * IEEE 802.1Q-2022 in Annex I "I.3 Traffic type to traffic class mapping" and + * Table I-1 "Traffic type to traffic class mapping". + */ +static const u8 ieee8021q_8queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, + [IEEE8021Q_TT_BE] = 1, + [IEEE8021Q_TT_EE] = 2, + [IEEE8021Q_TT_CA] = 3, + [IEEE8021Q_TT_VI] = 4, + [IEEE8021Q_TT_VO] = 5, + [IEEE8021Q_TT_IC] = 6, + [IEEE8021Q_TT_NC] = 7, +}; + +static const u8 ieee8021q_7queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, + [IEEE8021Q_TT_BE] = 1, + [IEEE8021Q_TT_EE] = 2, + [IEEE8021Q_TT_CA] = 3, + [IEEE8021Q_TT_VI] = 4, [IEEE8021Q_TT_VO] = 4, + [IEEE8021Q_TT_IC] = 5, + [IEEE8021Q_TT_NC] = 6, +}; + +static const u8 ieee8021q_6queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, + [IEEE8021Q_TT_BE] = 1, + [IEEE8021Q_TT_EE] = 2, [IEEE8021Q_TT_CA] = 2, + [IEEE8021Q_TT_VI] = 3, [IEEE8021Q_TT_VO] = 3, + [IEEE8021Q_TT_IC] = 4, + [IEEE8021Q_TT_NC] = 5, +}; + +static const u8 ieee8021q_5queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, [IEEE8021Q_TT_BE] = 0, + [IEEE8021Q_TT_EE] = 1, [IEEE8021Q_TT_CA] = 1, + [IEEE8021Q_TT_VI] = 2, [IEEE8021Q_TT_VO] = 2, + [IEEE8021Q_TT_IC] = 3, + [IEEE8021Q_TT_NC] = 4, +}; + +static const u8 ieee8021q_4queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, [IEEE8021Q_TT_BE] = 0, + [IEEE8021Q_TT_EE] = 1, [IEEE8021Q_TT_CA] = 1, + [IEEE8021Q_TT_VI] = 2, [IEEE8021Q_TT_VO] = 2, + [IEEE8021Q_TT_IC] = 3, [IEEE8021Q_TT_NC] = 3, +}; + +static const u8 ieee8021q_3queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, [IEEE8021Q_TT_BE] = 0, + [IEEE8021Q_TT_EE] = 0, [IEEE8021Q_TT_CA] = 0, + [IEEE8021Q_TT_VI] = 1, [IEEE8021Q_TT_VO] = 1, + [IEEE8021Q_TT_IC] = 2, [IEEE8021Q_TT_NC] = 2, +}; + +static const u8 ieee8021q_2queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, [IEEE8021Q_TT_BE] = 0, + [IEEE8021Q_TT_EE] = 0, [IEEE8021Q_TT_CA] = 0, + [IEEE8021Q_TT_VI] = 1, [IEEE8021Q_TT_VO] = 1, + [IEEE8021Q_TT_IC] = 1, [IEEE8021Q_TT_NC] = 1, +}; + +static const u8 ieee8021q_1queue_tt_tc_map[] = { + [IEEE8021Q_TT_BK] = 0, [IEEE8021Q_TT_BE] = 0, + [IEEE8021Q_TT_EE] = 0, [IEEE8021Q_TT_CA] = 0, + [IEEE8021Q_TT_VI] = 0, [IEEE8021Q_TT_VO] = 0, + [IEEE8021Q_TT_IC] = 0, [IEEE8021Q_TT_NC] = 0, +}; + +/** + * ieee8021q_tt_to_tc - Map IEEE 802.1Q Traffic Type to Traffic Class + * @tt: IEEE 802.1Q Traffic Type + * @num_queues: Number of queues + * + * This function maps an IEEE 802.1Q Traffic Type to a Traffic Class (TC) based + * on the number of queues configured on the NIC. The mapping is based on the + * example provided by IEEE 802.1Q-2022 in Annex I "I.3 Traffic type to traffic + * class mapping" and Table I-1 "Traffic type to traffic class mapping". + * + * Return: Traffic Class corresponding to the given Traffic Type or negative + * value in case of error. + */ +int ieee8021q_tt_to_tc(enum ieee8021q_traffic_type tt, unsigned int num_queues) +{ + if (tt < 0 || tt >= IEEE8021Q_TT_MAX) { + pr_err("Requested Traffic Type (%d) is out of range (%d)\n", tt, + IEEE8021Q_TT_MAX); + return -EINVAL; + } + + switch (num_queues) { + case 8: + compiletime_assert(ARRAY_SIZE(ieee8021q_8queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_8queue_tt_tc_map != max - 1"); + return ieee8021q_8queue_tt_tc_map[tt]; + case 7: + compiletime_assert(ARRAY_SIZE(ieee8021q_7queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_7queue_tt_tc_map != max - 1"); + + return ieee8021q_7queue_tt_tc_map[tt]; + case 6: + compiletime_assert(ARRAY_SIZE(ieee8021q_6queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_6queue_tt_tc_map != max - 1"); + + return ieee8021q_6queue_tt_tc_map[tt]; + case 5: + compiletime_assert(ARRAY_SIZE(ieee8021q_5queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_5queue_tt_tc_map != max - 1"); + + return ieee8021q_5queue_tt_tc_map[tt]; + case 4: + compiletime_assert(ARRAY_SIZE(ieee8021q_4queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_4queue_tt_tc_map != max - 1"); + + return ieee8021q_4queue_tt_tc_map[tt]; + case 3: + compiletime_assert(ARRAY_SIZE(ieee8021q_3queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_3queue_tt_tc_map != max - 1"); + + return ieee8021q_3queue_tt_tc_map[tt]; + case 2: + compiletime_assert(ARRAY_SIZE(ieee8021q_2queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_2queue_tt_tc_map != max - 1"); + + return ieee8021q_2queue_tt_tc_map[tt]; + case 1: + compiletime_assert(ARRAY_SIZE(ieee8021q_1queue_tt_tc_map) != + IEEE8021Q_TT_MAX - 1, + "ieee8021q_1queue_tt_tc_map != max - 1"); + + return ieee8021q_1queue_tt_tc_map[tt]; + } + + pr_err("Invalid number of queues %d\n", num_queues); + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(ieee8021q_tt_to_tc); + +/** + * ietf_dscp_to_ieee8021q_tt - Map IETF DSCP to IEEE 802.1Q Traffic Type + * @dscp: IETF DSCP value + * + * This function maps an IETF DSCP value to an IEEE 802.1Q Traffic Type (TT). + * Since there is no corresponding mapping between DSCP and IEEE 802.1Q Traffic + * Type, this function is inspired by the RFC8325 documentation which describe + * the mapping between DSCP and 802.11 User Priority (UP) values. + * + * Return: IEEE 802.1Q Traffic Type corresponding to the given DSCP value + */ +int ietf_dscp_to_ieee8021q_tt(u8 dscp) +{ + switch (dscp) { + case DSCP_CS0: + /* Comment from RFC8325: + * [RFC4594], Section 4.8, recommends High-Throughput Data be marked + * AF1x (that is, AF11, AF12, and AF13, according to the rules defined + * in [RFC2475]). + * + * By default (as described in Section 2.3), High-Throughput Data will + * map to UP 1 and, thus, to the Background Access Category (AC_BK), + * which is contrary to the intent expressed in [RFC4594]. + + * Unfortunately, there really is no corresponding fit for the High- + * Throughput Data service class within the constrained 4 Access + * Category [IEEE.802.11-2016] model. If the High-Throughput Data + * service class is assigned to the Best Effort Access Category (AC_BE), + * then it would contend with Low-Latency Data (while [RFC4594] + * recommends a distinction in servicing between these service classes) + * as well as with the default service class; alternatively, if it is + * assigned to the Background Access Category (AC_BK), then it would + * receive a less-then-best-effort service and contend with Low-Priority + * Data (as discussed in Section 4.2.10). + * + * As such, since there is no directly corresponding fit for the High- + * Throughout Data service class within the [IEEE.802.11-2016] model, it + * is generally RECOMMENDED to map High-Throughput Data to UP 0, thereby + * admitting it to the Best Effort Access Category (AC_BE). + * + * Note: The above text is from RFC8325 which is describing the mapping + * between DSCP and 802.11 User Priority (UP) values. The mapping + * between UP and IEEE 802.1Q Traffic Type is not defined in the RFC but + * the 802.11 AC_BK and AC_BE are closely related to the IEEE 802.1Q + * Traffic Types BE and BK. + */ + case DSCP_AF11: + case DSCP_AF12: + case DSCP_AF13: + return IEEE8021Q_TT_BE; + /* Comment from RFC8325: + * RFC3662 and RFC4594 both recommend Low-Priority Data be marked + * with DSCP CS1. The Low-Priority Data service class loosely + * corresponds to the [IEEE.802.11-2016] Background Access Category + */ + case DSCP_CS1: + return IEEE8021Q_TT_BK; + case DSCP_CS2: + case DSCP_AF21: + case DSCP_AF22: + case DSCP_AF23: + return IEEE8021Q_TT_EE; + case DSCP_CS3: + case DSCP_AF31: + case DSCP_AF32: + case DSCP_AF33: + return IEEE8021Q_TT_CA; + case DSCP_CS4: + case DSCP_AF41: + case DSCP_AF42: + case DSCP_AF43: + return IEEE8021Q_TT_VI; + case DSCP_CS5: + case DSCP_EF: + case DSCP_VOICE_ADMIT: + return IEEE8021Q_TT_VO; + case DSCP_CS6: + return IEEE8021Q_TT_IC; + case DSCP_CS7: + return IEEE8021Q_TT_NC; + } + + return SIMPLE_IETF_DSCP_TO_IEEE8021Q_TT(dscp); +} +EXPORT_SYMBOL_GPL(ietf_dscp_to_ieee8021q_tt); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 8ec35194bfcb..ab150641142a 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -148,9 +148,9 @@ static void linkwatch_schedule_work(int urgent) * override the existing timer. */ if (test_bit(LW_URGENT, &linkwatch_flags)) - mod_delayed_work(system_wq, &linkwatch_work, 0); + mod_delayed_work(system_unbound_wq, &linkwatch_work, 0); else - schedule_delayed_work(&linkwatch_work, delay); + queue_delayed_work(system_unbound_wq, &linkwatch_work, delay); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 552719c3bbc3..45fd88405b6b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -734,7 +734,9 @@ out_neigh_release: struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { - return ___neigh_create(tbl, pkey, dev, 0, false, want_ref); + bool exempt_from_gc = !!(dev->flags & IFF_LOOPBACK); + + return ___neigh_create(tbl, pkey, dev, 0, exempt_from_gc, want_ref); } EXPORT_SYMBOL(__neigh_create); @@ -1769,7 +1771,7 @@ static void neigh_parms_destroy(struct neigh_parms *parms) static struct lock_class_key neigh_table_proxy_queue_class; -static struct neigh_table *neigh_tables[NEIGH_NR_TABLES] __read_mostly; +static struct neigh_table __rcu *neigh_tables[NEIGH_NR_TABLES] __read_mostly; void neigh_table_init(int index, struct neigh_table *tbl) { @@ -1826,13 +1828,19 @@ void neigh_table_init(int index, struct neigh_table *tbl) tbl->last_flush = now; tbl->last_rand = now + tbl->parms.reachable_time * 20; - neigh_tables[index] = tbl; + rcu_assign_pointer(neigh_tables[index], tbl); } EXPORT_SYMBOL(neigh_table_init); +/* + * Only called from ndisc_cleanup(), which means this is dead code + * because we no longer can unload IPv6 module. + */ int neigh_table_clear(int index, struct neigh_table *tbl) { - neigh_tables[index] = NULL; + RCU_INIT_POINTER(neigh_tables[index], NULL); + synchronize_rcu(); + /* It is not clean... Fix it to unload IPv6 module safely */ cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); @@ -1864,10 +1872,10 @@ static struct neigh_table *neigh_find_table(int family) switch (family) { case AF_INET: - tbl = neigh_tables[NEIGH_ARP_TABLE]; + tbl = rcu_dereference_rtnl(neigh_tables[NEIGH_ARP_TABLE]); break; case AF_INET6: - tbl = neigh_tables[NEIGH_ND_TABLE]; + tbl = rcu_dereference_rtnl(neigh_tables[NEIGH_ND_TABLE]); break; } @@ -2331,7 +2339,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, ndtmsg = nlmsg_data(nlh); for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { - tbl = neigh_tables[tidx]; + tbl = rcu_dereference_rtnl(neigh_tables[tidx]); if (!tbl) continue; if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) @@ -2519,7 +2527,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { struct neigh_parms *p; - tbl = neigh_tables[tidx]; + tbl = rcu_dereference_rtnl(neigh_tables[tidx]); if (!tbl) continue; @@ -2674,7 +2682,7 @@ static bool neigh_master_filtered(struct net_device *dev, int master_idx) if (!master_idx) return false; - master = dev ? netdev_master_upper_dev_get(dev) : NULL; + master = dev ? netdev_master_upper_dev_get_rcu(dev) : NULL; /* 0 is already used to denote NDA_MASTER wasn't passed, therefore need another * invalid value for ifindex to denote "no master". @@ -2707,7 +2715,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, { struct net *net = sock_net(skb->sk); struct neighbour *n; - int rc, h, s_h = cb->args[1]; + int err = 0, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; unsigned int flags = NLM_F_MULTI; @@ -2715,7 +2723,6 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (filter->dev_idx || filter->master_idx) flags |= NLM_F_DUMP_FILTERED; - rcu_read_lock(); nht = rcu_dereference(tbl->nht); for (h = s_h; h < (1 << nht->hash_shift); h++) { @@ -2729,23 +2736,19 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || neigh_master_filtered(n->dev, filter->master_idx)) goto next; - if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, - flags) < 0) { - rc = -1; + err = neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, flags); + if (err < 0) goto out; - } next: idx++; } } - rc = skb->len; out: - rcu_read_unlock(); cb->args[1] = h; cb->args[2] = idx; - return rc; + return err; } static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, @@ -2754,7 +2757,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, { struct pneigh_entry *n; struct net *net = sock_net(skb->sk); - int rc, h, s_h = cb->args[3]; + int err = 0, h, s_h = cb->args[3]; int idx, s_idx = idx = cb->args[4]; unsigned int flags = NLM_F_MULTI; @@ -2772,11 +2775,11 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || neigh_master_filtered(n->dev, filter->master_idx)) goto next; - if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, flags, tbl) < 0) { + err = pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, flags, tbl); + if (err < 0) { read_unlock_bh(&tbl->lock); - rc = -1; goto out; } next: @@ -2785,12 +2788,10 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, } read_unlock_bh(&tbl->lock); - rc = skb->len; out: cb->args[3] = h; cb->args[4] = idx; - return rc; - + return err; } static int neigh_valid_dump_req(const struct nlmsghdr *nlh, @@ -2878,8 +2879,9 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; + rcu_read_lock(); for (t = 0; t < NEIGH_NR_TABLES; t++) { - tbl = neigh_tables[t]; + tbl = rcu_dereference(neigh_tables[t]); if (!tbl) continue; @@ -2895,9 +2897,10 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (err < 0) break; } + rcu_read_unlock(); cb->args[0] = t; - return skb->len; + return err; } static int neigh_valid_get_req(const struct nlmsghdr *nlh, @@ -3143,14 +3146,15 @@ int neigh_xmit(int index, struct net_device *dev, const void *addr, struct sk_buff *skb) { int err = -EAFNOSUPPORT; + if (likely(index < NEIGH_NR_TABLES)) { struct neigh_table *tbl; struct neighbour *neigh; - tbl = neigh_tables[index]; - if (!tbl) - goto out; rcu_read_lock(); + tbl = rcu_dereference(neigh_tables[index]); + if (!tbl) + goto out_unlock; if (index == NEIGH_ARP_TABLE) { u32 key = *((u32 *)addr); @@ -3166,6 +3170,7 @@ int neigh_xmit(int index, struct net_device *dev, goto out_kfree_skb; } err = READ_ONCE(neigh->output)(neigh, skb); +out_unlock: rcu_read_unlock(); } else if (index == NEIGH_LINK_TABLE) { @@ -3728,7 +3733,7 @@ static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; + struct ctl_table neigh_vars[NEIGH_VAR_MAX]; } neigh_sysctl_template __read_mostly = { .neigh_vars = { NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), @@ -3779,7 +3784,6 @@ static struct neigh_sysctl_table { .extra2 = SYSCTL_INT_MAX, .proc_handler = proc_dointvec_minmax, }, - {}, }, }; @@ -3807,8 +3811,6 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (dev) { dev_name_source = dev->name; /* Terminate the table early */ - memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, - sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); neigh_vars_size = NEIGH_VAR_BASE_REACHABLE_TIME_MS + 1; } else { struct neigh_table *tbl = p->tbl; @@ -3889,7 +3891,8 @@ static int __init neigh_init(void) { rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_GETNEIGH, neigh_get, neigh_dump_info, 0); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, neigh_get, neigh_dump_info, + RTNL_FLAG_DUMP_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, 0); diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index a97eceb84e61..fa6d3969734a 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -144,7 +144,8 @@ static int softnet_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x\n", - sd->processed, sd->dropped, sd->time_squeeze, 0, + sd->processed, atomic_read(&sd->dropped), + sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ sd->received_rps, flow_limit_count, diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e3d7a8cfa20b..dc91921da4ea 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -235,7 +235,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && netif_device_present(netdev)) { + if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) @@ -605,13 +605,13 @@ static ssize_t threaded_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; - if (!rtnl_trylock()) - return restart_syscall(); + rcu_read_lock(); if (dev_isalive(netdev)) - ret = sysfs_emit(buf, fmt_dec, netdev->threaded); + ret = sysfs_emit(buf, fmt_dec, READ_ONCE(netdev->threaded)); + + rcu_read_unlock(); - rtnl_unlock(); return ret; } @@ -1419,7 +1419,7 @@ static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; - return sprintf(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); + return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); } static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, @@ -1451,7 +1451,7 @@ static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) { - return sprintf(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); + return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); } static ssize_t bql_set_stall_max(struct netdev_queue *queue, @@ -1468,7 +1468,7 @@ static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; - return sprintf(buf, "%lu\n", dql->stall_cnt); + return sysfs_emit(buf, "%lu\n", dql->stall_cnt); } static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = @@ -2046,7 +2046,7 @@ static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid) net_ns_get_ownership(net, uid, gid); } -static struct class net_class __ro_after_init = { +static const struct class net_class = { .name = "net", .dev_release = netdev_release, .dev_groups = net_class_groups, diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b1dc84c4fda1..6a823ba906c6 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -1098,7 +1098,7 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) end: if (net_cb.fillargs.add_ref) put_net(net_cb.tgt_net); - return err < 0 ? err : skb->len; + return err; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, @@ -1213,7 +1213,8 @@ void __init net_ns_init(void) rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, - RTNL_FLAG_DOIT_UNLOCKED); + RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); } static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) diff --git a/net/core/gso_test.c b/net/core/net_test.c index 358c44680d91..9c3a590865d2 100644 --- a/net/core/gso_test.c +++ b/net/core/net_test.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-or-later #include <kunit/test.h> + +/* GSO */ + #include <linux/skbuff.h> static const char hdr[] = "abcdefgh"; @@ -258,17 +261,127 @@ free_gso_skb: consume_skb(skb); } -static struct kunit_case gso_test_cases[] = { - KUNIT_CASE_PARAM(gso_test_func, gso_test_gen_params), - {} +/* IP tunnel flags */ + +#include <net/ip_tunnels.h> + +struct ip_tunnel_flags_test { + const char *name; + + const u16 *src_bits; + const u16 *exp_bits; + u8 src_num; + u8 exp_num; + + __be16 exp_val; + bool exp_comp; +}; + +#define IP_TUNNEL_FLAGS_TEST(n, src, comp, eval, exp) { \ + .name = (n), \ + .src_bits = (src), \ + .src_num = ARRAY_SIZE(src), \ + .exp_comp = (comp), \ + .exp_val = (eval), \ + .exp_bits = (exp), \ + .exp_num = ARRAY_SIZE(exp), \ +} + +/* These are __be16-compatible and can be compared as is */ +static const u16 ip_tunnel_flags_1[] = { + IP_TUNNEL_KEY_BIT, + IP_TUNNEL_STRICT_BIT, + IP_TUNNEL_ERSPAN_OPT_BIT, +}; + +/* Due to the previous flags design limitation, setting either + * ``IP_TUNNEL_CSUM_BIT`` (on Big Endian) or ``IP_TUNNEL_DONT_FRAGMENT_BIT`` + * (on Little) also sets VTI/ISATAP bit. In the bitmap implementation, they + * correspond to ``BIT(16)``, which is bigger than ``U16_MAX``, but still is + * backward-compatible. + */ +#ifdef __LITTLE_ENDIAN +#define IP_TUNNEL_CONFLICT_BIT IP_TUNNEL_DONT_FRAGMENT_BIT +#else +#define IP_TUNNEL_CONFLICT_BIT IP_TUNNEL_CSUM_BIT +#endif + +static const u16 ip_tunnel_flags_2_src[] = { + IP_TUNNEL_CONFLICT_BIT, +}; + +static const u16 ip_tunnel_flags_2_exp[] = { + IP_TUNNEL_CONFLICT_BIT, + IP_TUNNEL_SIT_ISATAP_BIT, }; -static struct kunit_suite gso_test_suite = { - .name = "net_core_gso", - .test_cases = gso_test_cases, +/* Bits 17 and higher are not compatible with __be16 flags */ +static const u16 ip_tunnel_flags_3_src[] = { + IP_TUNNEL_VXLAN_OPT_BIT, + 17, + 18, + 20, }; -kunit_test_suite(gso_test_suite); +static const u16 ip_tunnel_flags_3_exp[] = { + IP_TUNNEL_VXLAN_OPT_BIT, +}; + +static const struct ip_tunnel_flags_test ip_tunnel_flags_test[] = { + IP_TUNNEL_FLAGS_TEST("compat", ip_tunnel_flags_1, true, + cpu_to_be16(BIT(IP_TUNNEL_KEY_BIT) | + BIT(IP_TUNNEL_STRICT_BIT) | + BIT(IP_TUNNEL_ERSPAN_OPT_BIT)), + ip_tunnel_flags_1), + IP_TUNNEL_FLAGS_TEST("conflict", ip_tunnel_flags_2_src, true, + VTI_ISVTI, ip_tunnel_flags_2_exp), + IP_TUNNEL_FLAGS_TEST("new", ip_tunnel_flags_3_src, false, + cpu_to_be16(BIT(IP_TUNNEL_VXLAN_OPT_BIT)), + ip_tunnel_flags_3_exp), +}; + +static void +ip_tunnel_flags_test_case_to_desc(const struct ip_tunnel_flags_test *t, + char *desc) +{ + strscpy(desc, t->name, KUNIT_PARAM_DESC_SIZE); +} +KUNIT_ARRAY_PARAM(ip_tunnel_flags_test, ip_tunnel_flags_test, + ip_tunnel_flags_test_case_to_desc); + +static void ip_tunnel_flags_test_run(struct kunit *test) +{ + const struct ip_tunnel_flags_test *t = test->param_value; + IP_TUNNEL_DECLARE_FLAGS(src) = { }; + IP_TUNNEL_DECLARE_FLAGS(exp) = { }; + IP_TUNNEL_DECLARE_FLAGS(out); + + for (u32 j = 0; j < t->src_num; j++) + __set_bit(t->src_bits[j], src); + for (u32 j = 0; j < t->exp_num; j++) + __set_bit(t->exp_bits[j], exp); + + KUNIT_ASSERT_EQ(test, t->exp_comp, + ip_tunnel_flags_is_be16_compat(src)); + KUNIT_ASSERT_EQ(test, (__force u16)t->exp_val, + (__force u16)ip_tunnel_flags_to_be16(src)); + + ip_tunnel_flags_from_be16(out, t->exp_val); + KUNIT_ASSERT_TRUE(test, __ipt_flag_op(bitmap_equal, exp, out)); +} + +static struct kunit_case net_test_cases[] = { + KUNIT_CASE_PARAM(gso_test_func, gso_test_gen_params), + KUNIT_CASE_PARAM(ip_tunnel_flags_test_run, + ip_tunnel_flags_test_gen_params), + { }, +}; + +static struct kunit_suite net_test_suite = { + .name = "net_core", + .test_cases = net_test_cases, +}; +kunit_test_suite(net_test_suite); +MODULE_DESCRIPTION("KUnit tests for networking core"); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("KUnit tests for segmentation offload"); diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 8d8ace9ef87f..8350a0afa9ec 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -70,6 +70,7 @@ static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFIN /* NETDEV_CMD_QSTATS_GET - dump */ static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE + 1] = { + [NETDEV_A_QSTATS_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), }; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 8c2d5a0bc208..05f9515d2c05 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -489,7 +489,17 @@ netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || - netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail)) + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, rx->hw_gro_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_BYTES, rx->hw_gro_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, rx->hw_gro_wire_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, rx->hw_gro_wire_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, rx->hw_drop_ratelimits)) return -EMSGSIZE; return 0; } @@ -498,7 +508,18 @@ static int netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) { if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || - netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes)) + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROPS, tx->hw_drops) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, tx->hw_drop_errors) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_CSUM_NONE, tx->csum_none) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_NEEDS_CSUM, tx->needs_csum) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, tx->hw_gso_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_BYTES, tx->hw_gso_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, tx->hw_gso_wire_packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, tx->hw_gso_wire_bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, tx->hw_drop_ratelimits) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_STOP, tx->stop) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_WAKE, tx->wake)) return -EMSGSIZE; return 0; } @@ -639,6 +660,24 @@ nla_put_failure: return -EMSGSIZE; } +static int +netdev_nl_qstats_get_dump_one(struct net_device *netdev, unsigned int scope, + struct sk_buff *skb, const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + if (!netdev->stat_ops) + return 0; + + switch (scope) { + case 0: + return netdev_nl_stats_by_netdev(netdev, skb, info); + case NETDEV_QSTATS_SCOPE_QUEUE: + return netdev_nl_stats_by_queue(netdev, skb, info, ctx); + } + + return -EINVAL; /* Should not happen, per netlink policy */ +} + int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { @@ -646,6 +685,7 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, const struct genl_info *info = genl_info_dump(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; + unsigned int ifindex; unsigned int scope; int err = 0; @@ -653,21 +693,28 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, if (info->attrs[NETDEV_A_QSTATS_SCOPE]) scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); - rtnl_lock(); - for_each_netdev_dump(net, netdev, ctx->ifindex) { - if (!netdev->stat_ops) - continue; + ifindex = 0; + if (info->attrs[NETDEV_A_QSTATS_IFINDEX]) + ifindex = nla_get_u32(info->attrs[NETDEV_A_QSTATS_IFINDEX]); - switch (scope) { - case 0: - err = netdev_nl_stats_by_netdev(netdev, skb, info); - break; - case NETDEV_QSTATS_SCOPE_QUEUE: - err = netdev_nl_stats_by_queue(netdev, skb, info, ctx); - break; + rtnl_lock(); + if (ifindex) { + netdev = __dev_get_by_index(net, ifindex); + if (netdev && netdev->stat_ops) { + err = netdev_nl_qstats_get_dump_one(netdev, scope, skb, + info, ctx); + } else { + NL_SET_BAD_ATTR(info->extack, + info->attrs[NETDEV_A_QSTATS_IFINDEX]); + err = netdev ? -EOPNOTSUPP : -ENODEV; + } + } else { + for_each_netdev_dump(net, netdev, ctx->ifindex) { + err = netdev_nl_qstats_get_dump_one(netdev, scope, skb, + info, ctx); + if (err < 0) + break; } - if (err < 0) - break; } rtnl_unlock(); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index dd364d738c00..3772eb63dcad 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -5,6 +5,7 @@ * Copyright (C) 2016 Red Hat, Inc. */ +#include <linux/error-injection.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -123,9 +124,9 @@ int page_pool_ethtool_stats_get_count(void) } EXPORT_SYMBOL(page_pool_ethtool_stats_get_count); -u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) +u64 *page_pool_ethtool_stats_get(u64 *data, const void *stats) { - struct page_pool_stats *pool_stats = stats; + const struct page_pool_stats *pool_stats = stats; *data++ = pool_stats->alloc_stats.fast; *data++ = pool_stats->alloc_stats.slow; @@ -172,19 +173,29 @@ static void page_pool_producer_unlock(struct page_pool *pool, spin_unlock_bh(&pool->ring.producer_lock); } +static void page_pool_struct_check(void) +{ + CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_users); + CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_page); + CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_offset); + CACHELINE_ASSERT_GROUP_SIZE(struct page_pool, frag, 4 * sizeof(long)); +} + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params, int cpuid) { unsigned int ring_qsize = 1024; /* Default */ + page_pool_struct_check(); + memcpy(&pool->p, ¶ms->fast, sizeof(pool->p)); memcpy(&pool->slow, ¶ms->slow, sizeof(pool->slow)); pool->cpuid = cpuid; /* Validate only known flags were used */ - if (pool->p.flags & ~(PP_FLAG_ALL)) + if (pool->slow.flags & ~PP_FLAG_ALL) return -EINVAL; if (pool->p.pool_size) @@ -198,22 +209,26 @@ static int page_pool_init(struct page_pool *pool, * DMA_BIDIRECTIONAL is for allowing page used for DMA sending, * which is the XDP_TX use-case. */ - if (pool->p.flags & PP_FLAG_DMA_MAP) { + if (pool->slow.flags & PP_FLAG_DMA_MAP) { if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; + + pool->dma_map = true; } - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) { + if (pool->slow.flags & PP_FLAG_DMA_SYNC_DEV) { /* In order to request DMA-sync-for-device the page * needs to be mapped */ - if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + if (!(pool->slow.flags & PP_FLAG_DMA_MAP)) return -EINVAL; if (!pool->p.max_len) return -EINVAL; + pool->dma_sync = true; + /* pool->p.offset has to be set according to the address * offset used by the DMA engine to start copying rx data */ @@ -222,7 +237,7 @@ static int page_pool_init(struct page_pool *pool, pool->has_init_callback = !!pool->slow.init_callback; #ifdef CONFIG_PAGE_POOL_STATS - if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) { + if (!(pool->slow.flags & PP_FLAG_SYSTEM_POOL)) { pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats); if (!pool->recycle_stats) return -ENOMEM; @@ -232,12 +247,13 @@ static int page_pool_init(struct page_pool *pool, * (also percpu) page pool instance. */ pool->recycle_stats = &pp_system_recycle_stats; + pool->system = true; } #endif if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) { #ifdef CONFIG_PAGE_POOL_STATS - if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) + if (!pool->system) free_percpu(pool->recycle_stats); #endif return -ENOMEM; @@ -248,7 +264,7 @@ static int page_pool_init(struct page_pool *pool, /* Driver calling page_pool_create() also call page_pool_destroy() */ refcount_set(&pool->user_cnt, 1); - if (pool->p.flags & PP_FLAG_DMA_MAP) + if (pool->dma_map) get_device(pool->p.dev); return 0; @@ -258,11 +274,11 @@ static void page_pool_uninit(struct page_pool *pool) { ptr_ring_cleanup(&pool->ring, NULL); - if (pool->p.flags & PP_FLAG_DMA_MAP) + if (pool->dma_map) put_device(pool->p.dev); #ifdef CONFIG_PAGE_POOL_STATS - if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) + if (!pool->system) free_percpu(pool->recycle_stats); #endif } @@ -383,16 +399,26 @@ static struct page *__page_pool_get_cached(struct page_pool *pool) return page; } -static void page_pool_dma_sync_for_device(struct page_pool *pool, - struct page *page, - unsigned int dma_sync_size) +static void __page_pool_dma_sync_for_device(const struct page_pool *pool, + const struct page *page, + u32 dma_sync_size) { +#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) dma_addr_t dma_addr = page_pool_get_dma_addr(page); dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, dma_addr, - pool->p.offset, dma_sync_size, - pool->p.dma_dir); + __dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset, + dma_sync_size, pool->p.dma_dir); +#endif +} + +static __always_inline void +page_pool_dma_sync_for_device(const struct page_pool *pool, + const struct page *page, + u32 dma_sync_size) +{ + if (pool->dma_sync && dma_dev_need_sync(pool->p.dev)) + __page_pool_dma_sync_for_device(pool, page, dma_sync_size); } static bool page_pool_dma_map(struct page_pool *pool, struct page *page) @@ -414,13 +440,12 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) if (page_pool_set_dma_addr(page, dma)) goto unmap_failed; - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) - page_pool_dma_sync_for_device(pool, page, pool->p.max_len); + page_pool_dma_sync_for_device(pool, page, pool->p.max_len); return true; unmap_failed: - WARN_ON_ONCE("unexpected DMA address, please report to netdev@"); + WARN_ONCE(1, "unexpected DMA address, please report to netdev@"); dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); @@ -460,8 +485,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, if (unlikely(!page)) return NULL; - if ((pool->p.flags & PP_FLAG_DMA_MAP) && - unlikely(!page_pool_dma_map(pool, page))) { + if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page))) { put_page(page); return NULL; } @@ -481,8 +505,8 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, gfp_t gfp) { const int bulk = PP_ALLOC_CACHE_REFILL; - unsigned int pp_flags = pool->p.flags; unsigned int pp_order = pool->p.order; + bool dma_map = pool->dma_map; struct page *page; int i, nr_pages; @@ -507,8 +531,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, */ for (i = 0; i < nr_pages; i++) { page = pool->alloc.cache[i]; - if ((pp_flags & PP_FLAG_DMA_MAP) && - unlikely(!page_pool_dma_map(pool, page))) { + if (dma_map && unlikely(!page_pool_dma_map(pool, page))) { put_page(page); continue; } @@ -550,6 +573,7 @@ struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) return page; } EXPORT_SYMBOL(page_pool_alloc_pages); +ALLOW_ERROR_INJECTION(page_pool_alloc_pages, NULL); /* Calculate distance between two u32 values, valid if distance is below 2^(31) * https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution @@ -580,7 +604,7 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) { dma_addr_t dma; - if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + if (!pool->dma_map) /* Always account for inflight pages, even if we didn't * map them */ @@ -663,7 +687,7 @@ static bool __page_pool_page_can_be_recycled(const struct page *page) } /* If the page refcnt == 1, this will try to recycle the page. - * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for + * If pool->dma_sync is set, we'll try to sync the DMA area for * the configured size min(dma_sync_size, pool->max_len). * If the page refcnt != 1, then the page will be returned to memory * subsystem. @@ -686,12 +710,9 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, if (likely(__page_pool_page_can_be_recycled(page))) { /* Read barrier done in page_ref_count / READ_ONCE */ - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) - page_pool_dma_sync_for_device(pool, page, - dma_sync_size); + page_pool_dma_sync_for_device(pool, page, dma_sync_size); - if (allow_direct && in_softirq() && - page_pool_recycle_in_cache(page, pool)) + if (allow_direct && page_pool_recycle_in_cache(page, pool)) return NULL; /* Page found as candidate for recycling */ @@ -716,9 +737,35 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, return NULL; } +static bool page_pool_napi_local(const struct page_pool *pool) +{ + const struct napi_struct *napi; + u32 cpuid; + + if (unlikely(!in_softirq())) + return false; + + /* Allow direct recycle if we have reasons to believe that we are + * in the same context as the consumer would run, so there's + * no possible race. + * __page_pool_put_page() makes sure we're not in hardirq context + * and interrupts are enabled prior to accessing the cache. + */ + cpuid = smp_processor_id(); + if (READ_ONCE(pool->cpuid) == cpuid) + return true; + + napi = READ_ONCE(pool->p.napi); + + return napi && READ_ONCE(napi->list_owner) == cpuid; +} + void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct) { + if (!allow_direct) + allow_direct = page_pool_napi_local(pool); + page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct); if (page && !page_pool_recycle_in_ring(pool, page)) { /* Cache full, fallback to free pages */ @@ -747,8 +794,11 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) { int i, bulk_len = 0; + bool allow_direct; bool in_softirq; + allow_direct = page_pool_napi_local(pool); + for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); @@ -756,13 +806,13 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, if (!page_pool_is_last_ref(page)) continue; - page = __page_pool_put_page(pool, page, -1, false); + page = __page_pool_put_page(pool, page, -1, allow_direct); /* Approved for bulk recycling in ptr_ring cache */ if (page) data[bulk_len++] = page; } - if (unlikely(!bulk_len)) + if (!bulk_len) return; /* Bulk producer into ptr_ring page_pool cache */ @@ -799,9 +849,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool, return NULL; if (__page_pool_page_can_be_recycled(page)) { - if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) - page_pool_dma_sync_for_device(pool, page, -1); - + page_pool_dma_sync_for_device(pool, page, -1); return page; } @@ -959,7 +1007,7 @@ static void page_pool_release_retry(struct work_struct *wq) } void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), - struct xdp_mem_info *mem) + const struct xdp_mem_info *mem) { refcount_inc(&pool->user_cnt); pool->disconnect = disconnect; @@ -969,7 +1017,7 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), static void page_pool_disable_direct_recycling(struct page_pool *pool) { /* Disable direct recycling based on pool->cpuid. - * Paired with READ_ONCE() in napi_pp_put_page(). + * Paired with READ_ONCE() in page_pool_napi_local(). */ WRITE_ONCE(pool->cpuid, -1); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index ea55a758a475..197a50ef8e2e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3654,7 +3654,7 @@ static int pktgen_thread_worker(void *arg) struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - WARN_ON(smp_processor_id() != cpu); + WARN_ON_ONCE(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); complete(&t->start_done); @@ -3989,6 +3989,7 @@ static int __net_init pg_net_init(struct net *net) goto remove; } + cpus_read_lock(); for_each_online_cpu(cpu) { int err; @@ -3997,6 +3998,7 @@ static int __net_init pg_net_init(struct net *net) pr_warn("Cannot create thread for cpu %d (%d)\n", cpu, err); } + cpus_read_unlock(); if (list_empty(&pn->pktgen_threads)) { pr_err("Initialization failed for all threads\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 74e6f9746fb3..5e589f0a62bc 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1036,8 +1036,8 @@ static size_t rtnl_proto_down_size(const struct net_device *dev) { size_t size = nla_total_size(1); - if (dev->proto_down_reason) - size += nla_total_size(0) + nla_total_size(4); + /* Assume dev->proto_down_reason is not zero. */ + size += nla_total_size(0) + nla_total_size(4); return size; } @@ -1477,13 +1477,15 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, static u32 rtnl_xdp_prog_skb(struct net_device *dev) { const struct bpf_prog *generic_xdp_prog; + u32 res = 0; - ASSERT_RTNL(); + rcu_read_lock(); + generic_xdp_prog = rcu_dereference(dev->xdp_prog); + if (generic_xdp_prog) + res = generic_xdp_prog->aux->id; + rcu_read_unlock(); - generic_xdp_prog = rtnl_dereference(dev->xdp_prog); - if (!generic_xdp_prog) - return 0; - return generic_xdp_prog->aux->id; + return res; } static u32 rtnl_xdp_prog_drv(struct net_device *dev) @@ -1603,7 +1605,8 @@ static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev) upper_dev = netdev_master_upper_dev_get_rcu(dev); if (upper_dev) - ret = nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex); + ret = nla_put_u32(skb, IFLA_MASTER, + READ_ONCE(upper_dev->ifindex)); rcu_read_unlock(); return ret; @@ -1736,10 +1739,10 @@ static int rtnl_fill_proto_down(struct sk_buff *skb, struct nlattr *pr; u32 preason; - if (nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) + if (nla_put_u8(skb, IFLA_PROTO_DOWN, READ_ONCE(dev->proto_down))) goto nla_put_failure; - preason = dev->proto_down_reason; + preason = READ_ONCE(dev->proto_down_reason); if (!preason) return 0; @@ -1812,6 +1815,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, u32 event, int *new_nsid, int new_ifindex, int tgt_netnsid, gfp_t gfp) { + char devname[IFNAMSIZ]; struct ifinfomsg *ifm; struct nlmsghdr *nlh; struct Qdisc *qdisc; @@ -1824,41 +1828,51 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, ifm = nlmsg_data(nlh); ifm->ifi_family = AF_UNSPEC; ifm->__ifi_pad = 0; - ifm->ifi_type = dev->type; - ifm->ifi_index = dev->ifindex; + ifm->ifi_type = READ_ONCE(dev->type); + ifm->ifi_index = READ_ONCE(dev->ifindex); ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) goto nla_put_failure; - qdisc = rtnl_dereference(dev->qdisc); - if (nla_put_string(skb, IFLA_IFNAME, dev->name) || - nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || + netdev_copy_name(dev, devname); + if (nla_put_string(skb, IFLA_IFNAME, devname)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_TXQLEN, READ_ONCE(dev->tx_queue_len)) || nla_put_u8(skb, IFLA_OPERSTATE, - netif_running(dev) ? dev->operstate : IF_OPER_DOWN) || - nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) || - nla_put_u32(skb, IFLA_MTU, dev->mtu) || - nla_put_u32(skb, IFLA_MIN_MTU, dev->min_mtu) || - nla_put_u32(skb, IFLA_MAX_MTU, dev->max_mtu) || - nla_put_u32(skb, IFLA_GROUP, dev->group) || - nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || - nla_put_u32(skb, IFLA_ALLMULTI, dev->allmulti) || - nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || - nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) || - nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || - nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) || - nla_put_u32(skb, IFLA_GSO_IPV4_MAX_SIZE, dev->gso_ipv4_max_size) || - nla_put_u32(skb, IFLA_GRO_IPV4_MAX_SIZE, dev->gro_ipv4_max_size) || - nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) || - nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) || + netif_running(dev) ? READ_ONCE(dev->operstate) : + IF_OPER_DOWN) || + nla_put_u8(skb, IFLA_LINKMODE, READ_ONCE(dev->link_mode)) || + nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) || + nla_put_u32(skb, IFLA_MIN_MTU, READ_ONCE(dev->min_mtu)) || + nla_put_u32(skb, IFLA_MAX_MTU, READ_ONCE(dev->max_mtu)) || + nla_put_u32(skb, IFLA_GROUP, READ_ONCE(dev->group)) || + nla_put_u32(skb, IFLA_PROMISCUITY, READ_ONCE(dev->promiscuity)) || + nla_put_u32(skb, IFLA_ALLMULTI, READ_ONCE(dev->allmulti)) || + nla_put_u32(skb, IFLA_NUM_TX_QUEUES, + READ_ONCE(dev->num_tx_queues)) || + nla_put_u32(skb, IFLA_GSO_MAX_SEGS, + READ_ONCE(dev->gso_max_segs)) || + nla_put_u32(skb, IFLA_GSO_MAX_SIZE, + READ_ONCE(dev->gso_max_size)) || + nla_put_u32(skb, IFLA_GRO_MAX_SIZE, + READ_ONCE(dev->gro_max_size)) || + nla_put_u32(skb, IFLA_GSO_IPV4_MAX_SIZE, + READ_ONCE(dev->gso_ipv4_max_size)) || + nla_put_u32(skb, IFLA_GRO_IPV4_MAX_SIZE, + READ_ONCE(dev->gro_ipv4_max_size)) || + nla_put_u32(skb, IFLA_TSO_MAX_SIZE, + READ_ONCE(dev->tso_max_size)) || + nla_put_u32(skb, IFLA_TSO_MAX_SEGS, + READ_ONCE(dev->tso_max_segs)) || #ifdef CONFIG_RPS - nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || + nla_put_u32(skb, IFLA_NUM_RX_QUEUES, + READ_ONCE(dev->num_rx_queues)) || #endif put_master_ifindex(skb, dev) || nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || - (qdisc && - nla_put_string(skb, IFLA_QDISC, qdisc->ops->id)) || nla_put_ifalias(skb, dev) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, atomic_read(&dev->carrier_up_count) + @@ -1909,9 +1923,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } - if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp)) - goto nla_put_failure; - if (new_nsid && nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) goto nla_put_failure; @@ -1924,6 +1935,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; rcu_read_lock(); + if (rtnl_fill_link_netnsid(skb, dev, src_net, GFP_ATOMIC)) + goto nla_put_failure_rcu; + qdisc = rcu_dereference(dev->qdisc); + if (qdisc && nla_put_string(skb, IFLA_QDISC, qdisc->ops->id)) + goto nla_put_failure_rcu; if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) goto nla_put_failure_rcu; if (rtnl_fill_link_ifmap(skb, dev)) @@ -3272,7 +3288,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) - dev = rtnl_dev_get(net, tb); + dev = rtnl_dev_get(tgt_net, tb); else if (tb[IFLA_GROUP]) err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP])); else @@ -5245,15 +5261,14 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { - nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { - if (nla_len(attr) < sizeof(flags)) - return -EINVAL; + nla_for_each_nested_type(attr, IFLA_BRIDGE_FLAGS, br_spec, + rem) { + if (nla_len(attr) < sizeof(flags)) + return -EINVAL; - have_flags = true; - flags = nla_get_u16(attr); - break; - } + have_flags = true; + flags = nla_get_u16(attr); + break; } } @@ -5962,19 +5977,17 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh, static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; - int h, s_h, err, s_idx, s_idxattr, s_prividx; struct rtnl_stats_dump_filters filters; struct net *net = sock_net(skb->sk); unsigned int flags = NLM_F_MULTI; struct if_stats_msg *ifsm; - struct hlist_head *head; + struct { + unsigned long ifindex; + int idxattr; + int prividx; + } *ctx = (void *)cb->ctx; struct net_device *dev; - int idx = 0; - - s_h = cb->args[0]; - s_idx = cb->args[1]; - s_idxattr = cb->args[2]; - s_prividx = cb->args[3]; + int err; cb->seq = net->dev_base_seq; @@ -5993,39 +6006,26 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - err = rtnl_fill_statsinfo(skb, dev, RTM_NEWSTATS, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - flags, &filters, - &s_idxattr, &s_prividx, - extack); - /* If we ran out of room on the first message, - * we're in trouble - */ - WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + for_each_netdev_dump(net, dev, ctx->ifindex) { + err = rtnl_fill_statsinfo(skb, dev, RTM_NEWSTATS, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + flags, &filters, + &ctx->idxattr, &ctx->prividx, + extack); + /* If we ran out of room on the first message, + * we're in trouble. + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); - if (err < 0) - goto out; - s_prividx = 0; - s_idxattr = 0; - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } + if (err < 0) + break; + ctx->prividx = 0; + ctx->idxattr = 0; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); } -out: - cb->args[3] = s_prividx; - cb->args[2] = s_idxattr; - cb->args[1] = idx; - cb->args[0] = h; - return skb->len; + return err; } void rtnl_offload_xstats_notify(struct net_device *dev) diff --git a/net/core/scm.c b/net/core/scm.c index 9cd4b0a01cd6..4f6a14babe5a 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -89,6 +89,12 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; +#if IS_ENABLED(CONFIG_UNIX) + fpl->inflight = false; + fpl->dead = false; + fpl->edges = NULL; + INIT_LIST_HEAD(&fpl->vertices); +#endif } fpp = &fpl->fp[fpl->count]; @@ -376,8 +382,14 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); + new_fpl->max = new_fpl->count; new_fpl->user = get_uid(fpl->user); +#if IS_ENABLED(CONFIG_UNIX) + new_fpl->inflight = false; + new_fpl->edges = NULL; + INIT_LIST_HEAD(&new_fpl->vertices); +#endif } return new_fpl; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4096e679f61c..466999a7515e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -51,6 +51,7 @@ #endif #include <linux/string.h> #include <linux/skbuff.h> +#include <linux/skbuff_ref.h> #include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> @@ -108,9 +109,6 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init; #define SKB_SMALL_HEAD_HEADROOM \ SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) -int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; -EXPORT_SYMBOL(sysctl_max_skb_frags); - /* kcm_write_msgs() relies on casting paged frags to bio_vec to use * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the * netmem is a page. @@ -775,10 +773,9 @@ skb_fail: EXPORT_SYMBOL(__netdev_alloc_skb); /** - * __napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance + * napi_alloc_skb - allocate skbuff for rx in a specific NAPI instance * @napi: napi instance this buffer was allocated for * @len: length to allocate - * @gfp_mask: get_free_pages mask, passed to alloc_skb and alloc_pages * * Allocate a new sk_buff for use in NAPI receive. This buffer will * attempt to allocate the head from a special reserved region used @@ -787,9 +784,9 @@ EXPORT_SYMBOL(__netdev_alloc_skb); * * %NULL is returned if there is no free memory. */ -struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, - gfp_t gfp_mask) +struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) { + gfp_t gfp_mask = GFP_ATOMIC | __GFP_NOWARN; struct napi_alloc_cache *nc; struct sk_buff *skb; bool pfmemalloc; @@ -860,7 +857,7 @@ skb_success: skb_fail: return skb; } -EXPORT_SYMBOL(__napi_alloc_skb); +EXPORT_SYMBOL(napi_alloc_skb); void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize) @@ -1005,11 +1002,8 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, EXPORT_SYMBOL(skb_cow_data_for_xdp); #if IS_ENABLED(CONFIG_PAGE_POOL) -bool napi_pp_put_page(struct page *page, bool napi_safe) +bool napi_pp_put_page(struct page *page) { - bool allow_direct = false; - struct page_pool *pp; - page = compound_head(page); /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation @@ -1022,39 +1016,18 @@ bool napi_pp_put_page(struct page *page, bool napi_safe) if (unlikely(!is_pp_page(page))) return false; - pp = page->pp; - - /* Allow direct recycle if we have reasons to believe that we are - * in the same context as the consumer would run, so there's - * no possible race. - * __page_pool_put_page() makes sure we're not in hardirq context - * and interrupts are enabled prior to accessing the cache. - */ - if (napi_safe || in_softirq()) { - const struct napi_struct *napi = READ_ONCE(pp->p.napi); - unsigned int cpuid = smp_processor_id(); - - allow_direct = napi && READ_ONCE(napi->list_owner) == cpuid; - allow_direct |= READ_ONCE(pp->cpuid) == cpuid; - } - - /* Driver set this to memory recycling info. Reset it on recycle. - * This will *not* work for NIC using a split-page memory model. - * The page will be returned to the pool here regardless of the - * 'flipped' fragment being in use or not. - */ - page_pool_put_full_page(pp, page, allow_direct); + page_pool_put_full_page(page->pp, page, false); return true; } EXPORT_SYMBOL(napi_pp_put_page); #endif -static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe) +static bool skb_pp_recycle(struct sk_buff *skb, void *data) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; - return napi_pp_put_page(virt_to_page(data), napi_safe); + return napi_pp_put_page(virt_to_page(data)); } /** @@ -1096,12 +1069,12 @@ static void skb_kfree_head(void *head, unsigned int end_offset) kfree(head); } -static void skb_free_head(struct sk_buff *skb, bool napi_safe) +static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; if (skb->head_frag) { - if (skb_pp_recycle(skb, head, napi_safe)) + if (skb_pp_recycle(skb, head)) return; skb_free_frag(head); } else { @@ -1109,8 +1082,7 @@ static void skb_free_head(struct sk_buff *skb, bool napi_safe) } } -static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason, - bool napi_safe) +static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason) { struct skb_shared_info *shinfo = skb_shinfo(skb); int i; @@ -1127,13 +1099,13 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason, } for (i = 0; i < shinfo->nr_frags; i++) - napi_frag_unref(&shinfo->frags[i], skb->pp_recycle, napi_safe); + __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); free_head: if (shinfo->frag_list) kfree_skb_list_reason(shinfo->frag_list, reason); - skb_free_head(skb, napi_safe); + skb_free_head(skb); exit: /* When we clone an SKB we copy the reycling bit. The pp_recycle * bit is only set on the head though, so in order to avoid races @@ -1194,12 +1166,11 @@ void skb_release_head_state(struct sk_buff *skb) } /* Free everything but the sk_buff shell. */ -static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason, - bool napi_safe) +static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_head_state(skb); if (likely(skb->head)) - skb_release_data(skb, reason, napi_safe); + skb_release_data(skb, reason); } /** @@ -1213,7 +1184,7 @@ static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason, void __kfree_skb(struct sk_buff *skb) { - skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED, false); + skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED); kfree_skbmem(skb); } EXPORT_SYMBOL(__kfree_skb); @@ -1270,7 +1241,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, return; } - skb_release_all(skb, reason, false); + skb_release_all(skb, reason); sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { @@ -1331,22 +1302,28 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) has_trans = skb_transport_header_was_set(skb); printk("%sskb len=%u headroom=%u headlen=%u tailroom=%u\n" - "mac=(%d,%d) net=(%d,%d) trans=%d\n" + "mac=(%d,%d) mac_len=%u net=(%d,%d) trans=%d\n" "shinfo(txflags=%u nr_frags=%u gso(size=%hu type=%u segs=%hu))\n" - "csum(0x%x ip_summed=%u complete_sw=%u valid=%u level=%u)\n" - "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n", + "csum(0x%x start=%u offset=%u ip_summed=%u complete_sw=%u valid=%u level=%u)\n" + "hash(0x%x sw=%u l4=%u) proto=0x%04x pkttype=%u iif=%d\n" + "priority=0x%x mark=0x%x alloc_cpu=%u vlan_all=0x%x\n" + "encapsulation=%d inner(proto=0x%04x, mac=%u, net=%u, trans=%u)\n", level, skb->len, headroom, skb_headlen(skb), tailroom, has_mac ? skb->mac_header : -1, has_mac ? skb_mac_header_len(skb) : -1, + skb->mac_len, skb->network_header, has_trans ? skb_network_header_len(skb) : -1, has_trans ? skb->transport_header : -1, sh->tx_flags, sh->nr_frags, sh->gso_size, sh->gso_type, sh->gso_segs, - skb->csum, skb->ip_summed, skb->csum_complete_sw, - skb->csum_valid, skb->csum_level, + skb->csum, skb->csum_start, skb->csum_offset, skb->ip_summed, + skb->csum_complete_sw, skb->csum_valid, skb->csum_level, skb->hash, skb->sw_hash, skb->l4_hash, - ntohs(skb->protocol), skb->pkt_type, skb->skb_iif); + ntohs(skb->protocol), skb->pkt_type, skb->skb_iif, + skb->priority, skb->mark, skb->alloc_cpu, skb->vlan_all, + skb->encapsulation, skb->inner_protocol, skb->inner_mac_header, + skb->inner_network_header, skb->inner_transport_header); if (dev) printk("%sdev name=%s feat=%pNF\n", @@ -1444,7 +1421,7 @@ EXPORT_SYMBOL(consume_skb); void __consume_stateless_skb(struct sk_buff *skb) { trace_consume_skb(skb, __builtin_return_address(0)); - skb_release_data(skb, SKB_CONSUMED, false); + skb_release_data(skb, SKB_CONSUMED); kfree_skbmem(skb); } @@ -1471,7 +1448,7 @@ static void napi_skb_cache_put(struct sk_buff *skb) void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason) { - skb_release_all(skb, reason, true); + skb_release_all(skb, reason); napi_skb_cache_put(skb); } @@ -1509,7 +1486,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget) return; } - skb_release_all(skb, SKB_CONSUMED, !!budget); + skb_release_all(skb, SKB_CONSUMED); napi_skb_cache_put(skb); } EXPORT_SYMBOL(napi_consume_skb); @@ -1640,7 +1617,7 @@ EXPORT_SYMBOL_GPL(alloc_skb_for_msg); */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { - skb_release_all(dst, SKB_CONSUMED, false); + skb_release_all(dst, SKB_CONSUMED); return __skb_clone(dst, src); } EXPORT_SYMBOL_GPL(skb_morph); @@ -1708,7 +1685,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) return NULL; } - uarg->ubuf.callback = msg_zerocopy_callback; + uarg->ubuf.ops = &msg_zerocopy_ubuf_ops; uarg->id = ((u32)atomic_inc_return(&sk->sk_zckey)) - 1; uarg->len = 1; uarg->bytelen = size; @@ -1734,7 +1711,7 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, u32 bytelen, next; /* there might be non MSG_ZEROCOPY users */ - if (uarg->callback != msg_zerocopy_callback) + if (uarg->ops != &msg_zerocopy_ubuf_ops) return NULL; /* realloc only when socket is locked (TCP, UDP cork), @@ -1845,8 +1822,8 @@ release: sock_put(sk); } -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success) +static void msg_zerocopy_complete(struct sk_buff *skb, struct ubuf_info *uarg, + bool success) { struct ubuf_info_msgzc *uarg_zc = uarg_to_msgzc(uarg); @@ -1855,7 +1832,6 @@ void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, if (refcount_dec_and_test(&uarg->refcnt)) __msg_zerocopy_callback(uarg_zc); } -EXPORT_SYMBOL_GPL(msg_zerocopy_callback); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) { @@ -1865,10 +1841,15 @@ void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref) uarg_to_msgzc(uarg)->len--; if (have_uref) - msg_zerocopy_callback(NULL, uarg, true); + msg_zerocopy_complete(NULL, uarg, true); } EXPORT_SYMBOL_GPL(msg_zerocopy_put_abort); +const struct ubuf_info_ops msg_zerocopy_ubuf_ops = { + .complete = msg_zerocopy_complete, +}; +EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops); + int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) @@ -1876,11 +1857,18 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct ubuf_info *orig_uarg = skb_zcopy(skb); int err, orig_len = skb->len; - /* An skb can only point to one uarg. This edge case happens when - * TCP appends to an skb, but zerocopy_realloc triggered a new alloc. - */ - if (orig_uarg && uarg != orig_uarg) - return -EEXIST; + if (uarg->ops->link_skb) { + err = uarg->ops->link_skb(skb, uarg); + if (err) + return err; + } else { + /* An skb can only point to one uarg. This edge case happens + * when TCP appends to an skb, but zerocopy_realloc triggered + * a new alloc. + */ + if (orig_uarg && uarg != orig_uarg) + return -EEXIST; + } err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { @@ -1894,7 +1882,8 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, return err; } - skb_zcopy_set(skb, uarg, NULL); + if (!uarg->ops->link_skb) + skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); @@ -2278,9 +2267,9 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - skb_release_data(skb, SKB_CONSUMED, false); + skb_release_data(skb, SKB_CONSUMED); } else { - skb_free_head(skb, false); + skb_free_head(skb); } off = (data + nhead) - skb->head; @@ -6586,12 +6575,12 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - skb_release_data(skb, SKB_CONSUMED, false); + skb_release_data(skb, SKB_CONSUMED); } else { /* we can reuse existing recount- all we did was * relocate values */ - skb_free_head(skb, false); + skb_free_head(skb); } skb->head = data; @@ -6726,7 +6715,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, skb_kfree_head(data, size); return -ENOMEM; } - skb_release_data(skb, SKB_CONSUMED, false); + skb_release_data(skb, SKB_CONSUMED); skb->head = data; skb->head_frag = 0; @@ -7006,6 +6995,19 @@ free_now: EXPORT_SYMBOL(__skb_ext_put); #endif /* CONFIG_SKB_EXTENSIONS */ +static void kfree_skb_napi_cache(struct sk_buff *skb) +{ + /* if SKB is a clone, don't handle this case */ + if (skb->fclone != SKB_FCLONE_UNAVAILABLE) { + __kfree_skb(skb); + return; + } + + local_bh_disable(); + __napi_kfree_skb(skb, SKB_CONSUMED); + local_bh_enable(); +} + /** * skb_attempt_defer_free - queue skb for remote freeing * @skb: buffer @@ -7021,10 +7023,10 @@ void skb_attempt_defer_free(struct sk_buff *skb) unsigned int defer_max; bool kick; - if (WARN_ON_ONCE(cpu >= nr_cpu_ids) || - !cpu_online(cpu) || - cpu == raw_smp_processor_id()) { -nodefer: __kfree_skb(skb); + if (cpu == raw_smp_processor_id() || + WARN_ON_ONCE(cpu >= nr_cpu_ids) || + !cpu_online(cpu)) { +nodefer: kfree_skb_napi_cache(skb); return; } @@ -7032,7 +7034,7 @@ nodefer: __kfree_skb(skb); DEBUG_NET_WARN_ON_ONCE(skb->destructor); sd = &per_cpu(softnet_data, cpu); - defer_max = READ_ONCE(sysctl_skb_defer_max); + defer_max = READ_ONCE(net_hotdata.sysctl_skb_defer_max); if (READ_ONCE(sd->defer_count) >= defer_max) goto nodefer; @@ -7050,8 +7052,8 @@ nodefer: __kfree_skb(skb); /* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU * if we are unlucky enough (this seems very unlikely). */ - if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) - smp_call_function_single_async(cpu, &sd->defer_csd); + if (unlikely(kick)) + kick_defer_list_purge(sd, cpu); } static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, @@ -7084,7 +7086,7 @@ static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize, gfp_t gfp) { - size_t frag_limit = READ_ONCE(sysctl_max_skb_frags); + size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags); struct page *pages[8], **ppages = pages; ssize_t spliced = 0, ret = 0; unsigned int i; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index fd20aae30be2..bbf40b999713 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -434,7 +434,8 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (copy) + copy = copy_page_to_iter(page, sge->offset, copy, iter); if (!copy) { copied = copied ? copied : -EFAULT; goto out; diff --git a/net/core/sock.c b/net/core/sock.c index 09eccc9c5020..100e975073ca 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -127,6 +127,7 @@ #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> +#include <net/proto_memory.h> #include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> @@ -283,7 +284,6 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; -int sysctl_mem_pcpu_rsv __read_mostly = SK_MEMORY_PCPU_RESERVE; int sysctl_tstamp_allow_data __read_mostly = 1; @@ -2526,13 +2526,12 @@ EXPORT_SYMBOL(skb_set_owner_w); static bool can_skb_orphan_partial(const struct sk_buff *skb) { -#ifdef CONFIG_TLS_DEVICE /* Drivers depend on in-order delivery for crypto offload, * partial orphan breaks out-of-order-OK logic. */ - if (skb->decrypted) + if (skb_is_decrypted(skb)) return false; -#endif + return (skb->destructor == sock_wfree || (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree)); } @@ -3242,8 +3241,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2) } EXPORT_SYMBOL(sock_no_socketpair); -int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +int sock_no_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { return -EOPNOTSUPP; } @@ -3338,7 +3337,7 @@ static void sock_def_error_report(struct sock *sk) wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLERR); - sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); + sk_wake_async_rcu(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } @@ -3353,7 +3352,7 @@ void sock_def_readable(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } @@ -3373,7 +3372,7 @@ static void sock_def_write_space(struct sock *sk) EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); @@ -3398,7 +3397,7 @@ static void sock_def_write_space_wfree(struct sock *sk) EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 01be07b485fa..d3dbb92153f2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -24,8 +24,16 @@ struct bpf_stab { #define SOCK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) +/* This mutex is used to + * - protect race between prog/link attach/detach and link prog update, and + * - protect race between releasing and accessing map in bpf_link. + * A single global mutex lock is used since it is expected contention is low. + */ +static DEFINE_MUTEX(sockmap_mutex); + static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which); + struct bpf_prog *old, struct bpf_link *link, + u32 which); static struct sk_psock_progs *sock_map_progs(struct bpf_map *map); static struct bpf_map *sock_map_alloc(union bpf_attr *attr) @@ -71,7 +79,9 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + mutex_lock(&sockmap_mutex); + ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type); + mutex_unlock(&sockmap_mutex); fdput(f); return ret; } @@ -103,7 +113,9 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) goto put_prog; } - ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); + mutex_lock(&sockmap_mutex); + ret = sock_map_prog_update(map, NULL, prog, NULL, attr->attach_type); + mutex_unlock(&sockmap_mutex); put_prog: bpf_prog_put(prog); put_map: @@ -411,9 +423,6 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -936,9 +945,6 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); @@ -1460,55 +1466,84 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) return NULL; } -static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog, - u32 which) +static int sock_map_prog_link_lookup(struct bpf_map *map, struct bpf_prog ***pprog, + struct bpf_link ***plink, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **cur_pprog; + struct bpf_link **cur_plink; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - *pprog = &progs->msg_parser; + cur_pprog = &progs->msg_parser; + cur_plink = &progs->msg_parser_link; break; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: - *pprog = &progs->stream_parser; + cur_pprog = &progs->stream_parser; + cur_plink = &progs->stream_parser_link; break; #endif case BPF_SK_SKB_STREAM_VERDICT: if (progs->skb_verdict) return -EBUSY; - *pprog = &progs->stream_verdict; + cur_pprog = &progs->stream_verdict; + cur_plink = &progs->stream_verdict_link; break; case BPF_SK_SKB_VERDICT: if (progs->stream_verdict) return -EBUSY; - *pprog = &progs->skb_verdict; + cur_pprog = &progs->skb_verdict; + cur_plink = &progs->skb_verdict_link; break; default: return -EOPNOTSUPP; } + *pprog = cur_pprog; + if (plink) + *plink = cur_plink; return 0; } +/* Handle the following four cases: + * prog_attach: prog != NULL, old == NULL, link == NULL + * prog_detach: prog == NULL, old != NULL, link == NULL + * link_attach: prog != NULL, old == NULL, link != NULL + * link_detach: prog == NULL, old != NULL, link != NULL + */ static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which) + struct bpf_prog *old, struct bpf_link *link, + u32 which) { struct bpf_prog **pprog; + struct bpf_link **plink; int ret; - ret = sock_map_prog_lookup(map, &pprog, which); + ret = sock_map_prog_link_lookup(map, &pprog, &plink, which); if (ret) return ret; - if (old) - return psock_replace_prog(pprog, prog, old); + /* for prog_attach/prog_detach/link_attach, return error if a bpf_link + * exists for that prog. + */ + if ((!link || prog) && *plink) + return -EBUSY; - psock_set_prog(pprog, prog); - return 0; + if (old) { + ret = psock_replace_prog(pprog, prog, old); + if (!ret) + *plink = NULL; + } else { + psock_set_prog(pprog, prog); + if (link) + *plink = link; + } + + return ret; } int sock_map_bpf_prog_query(const union bpf_attr *attr, @@ -1533,7 +1568,7 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr, rcu_read_lock(); - ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type); + ret = sock_map_prog_link_lookup(map, &pprog, NULL, attr->query.attach_type); if (ret) goto end; @@ -1667,6 +1702,196 @@ no_psock: } EXPORT_SYMBOL_GPL(sock_map_close); +struct sockmap_link { + struct bpf_link link; + struct bpf_map *map; + enum bpf_attach_type attach_type; +}; + +static void sock_map_link_release(struct bpf_link *link) +{ + struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + + mutex_lock(&sockmap_mutex); + if (!sockmap_link->map) + goto out; + + WARN_ON_ONCE(sock_map_prog_update(sockmap_link->map, NULL, link->prog, link, + sockmap_link->attach_type)); + + bpf_map_put_with_uref(sockmap_link->map); + sockmap_link->map = NULL; +out: + mutex_unlock(&sockmap_mutex); +} + +static int sock_map_link_detach(struct bpf_link *link) +{ + sock_map_link_release(link); + return 0; +} + +static void sock_map_link_dealloc(struct bpf_link *link) +{ + kfree(link); +} + +/* Handle the following two cases: + * case 1: link != NULL, prog != NULL, old != NULL + * case 2: link != NULL, prog != NULL, old == NULL + */ +static int sock_map_link_update_prog(struct bpf_link *link, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + struct bpf_prog **pprog, *old_link_prog; + struct bpf_link **plink; + int ret = 0; + + mutex_lock(&sockmap_mutex); + + /* If old prog is not NULL, ensure old prog is the same as link->prog. */ + if (old && link->prog != old) { + ret = -EPERM; + goto out; + } + /* Ensure link->prog has the same type/attach_type as the new prog. */ + if (link->prog->type != prog->type || + link->prog->expected_attach_type != prog->expected_attach_type) { + ret = -EINVAL; + goto out; + } + + ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink, + sockmap_link->attach_type); + if (ret) + goto out; + + /* return error if the stored bpf_link does not match the incoming bpf_link. */ + if (link != *plink) { + ret = -EBUSY; + goto out; + } + + if (old) { + ret = psock_replace_prog(pprog, prog, old); + if (ret) + goto out; + } else { + psock_set_prog(pprog, prog); + } + + bpf_prog_inc(prog); + old_link_prog = xchg(&link->prog, prog); + bpf_prog_put(old_link_prog); + +out: + mutex_unlock(&sockmap_mutex); + return ret; +} + +static u32 sock_map_link_get_map_id(const struct sockmap_link *sockmap_link) +{ + u32 map_id = 0; + + mutex_lock(&sockmap_mutex); + if (sockmap_link->map) + map_id = sockmap_link->map->id; + mutex_unlock(&sockmap_mutex); + return map_id; +} + +static int sock_map_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + u32 map_id = sock_map_link_get_map_id(sockmap_link); + + info->sockmap.map_id = map_id; + info->sockmap.attach_type = sockmap_link->attach_type; + return 0; +} + +static void sock_map_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + const struct sockmap_link *sockmap_link = container_of(link, struct sockmap_link, link); + u32 map_id = sock_map_link_get_map_id(sockmap_link); + + seq_printf(seq, "map_id:\t%u\n", map_id); + seq_printf(seq, "attach_type:\t%u\n", sockmap_link->attach_type); +} + +static const struct bpf_link_ops sock_map_link_ops = { + .release = sock_map_link_release, + .dealloc = sock_map_link_dealloc, + .detach = sock_map_link_detach, + .update_prog = sock_map_link_update_prog, + .fill_link_info = sock_map_link_fill_info, + .show_fdinfo = sock_map_link_show_fdinfo, +}; + +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct sockmap_link *sockmap_link; + enum bpf_attach_type attach_type; + struct bpf_map *map; + int ret; + + if (attr->link_create.flags) + return -EINVAL; + + map = bpf_map_get_with_uref(attr->link_create.target_fd); + if (IS_ERR(map)) + return PTR_ERR(map); + if (map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) { + ret = -EINVAL; + goto out; + } + + sockmap_link = kzalloc(sizeof(*sockmap_link), GFP_USER); + if (!sockmap_link) { + ret = -ENOMEM; + goto out; + } + + attach_type = attr->link_create.attach_type; + bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog); + sockmap_link->map = map; + sockmap_link->attach_type = attach_type; + + ret = bpf_link_prime(&sockmap_link->link, &link_primer); + if (ret) { + kfree(sockmap_link); + goto out; + } + + mutex_lock(&sockmap_mutex); + ret = sock_map_prog_update(map, prog, NULL, &sockmap_link->link, attach_type); + mutex_unlock(&sockmap_mutex); + if (ret) { + bpf_link_cleanup(&link_primer); + goto out; + } + + /* Increase refcnt for the prog since when old prog is replaced with + * psock_replace_prog() and psock_set_prog() its refcnt will be decreased. + * + * Actually, we do not need to increase refcnt for the prog since bpf_link + * will hold a reference. But in order to have less complexity w.r.t. + * replacing/setting prog, let us increase the refcnt to make things simpler. + */ + bpf_prog_inc(prog); + + return bpf_link_settle(&link_primer); + +out: + bpf_map_put_with_uref(map); + return ret; +} + static int sock_map_iter_attach_target(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 6973dda3abda..c9fb9ad87485 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -24,6 +24,7 @@ #include <net/busy_poll.h> #include <net/pkt_sched.h> #include <net/hotdata.h> +#include <net/proto_memory.h> #include <net/rps.h> #include "dev.h" @@ -415,7 +416,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "mem_pcpu_rsv", - .data = &sysctl_mem_pcpu_rsv, + .data = &net_hotdata.sysctl_mem_pcpu_rsv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -595,7 +596,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "max_skb_frags", - .data = &sysctl_max_skb_frags, + .data = &net_hotdata.sysctl_max_skb_frags, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -654,13 +655,12 @@ static struct ctl_table net_core_table[] = { }, { .procname = "skb_defer_max", - .data = &sysctl_skb_defer_max, + .data = &net_hotdata.sysctl_skb_defer_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, - { } }; static struct ctl_table netns_core_table[] = { @@ -697,7 +697,6 @@ static struct ctl_table netns_core_table[] = { .extra2 = SYSCTL_ONE, .proc_handler = proc_dou8vec_minmax, }, - { } }; static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str) @@ -715,20 +714,21 @@ __setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); static __net_init int sysctl_core_net_init(struct net *net) { - struct ctl_table *tbl, *tmp; + size_t table_size = ARRAY_SIZE(netns_core_table); + struct ctl_table *tbl; tbl = netns_core_table; if (!net_eq(net, &init_net)) { + int i; tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; - for (tmp = tbl; tmp->procname; tmp++) - tmp->data += (char *)net - (char *)&init_net; + for (i = 0; i < table_size; ++i) + tbl[i].data += (char *)net - (char *)&init_net; } - net->core.sysctl_hdr = register_net_sysctl_sz(net, "net/core", tbl, - ARRAY_SIZE(netns_core_table)); + net->core.sysctl_hdr = register_net_sysctl_sz(net, "net/core", tbl, table_size); if (net->core.sysctl_hdr == NULL) goto err_reg; @@ -743,7 +743,7 @@ err_dup: static __net_exit void sysctl_core_net_exit(struct net *net) { - struct ctl_table *tbl; + const struct ctl_table *tbl; tbl = net->core.sysctl_hdr->ctl_table_arg; unregister_net_sysctl_table(net->core.sysctl_hdr); diff --git a/net/core/xdp.c b/net/core/xdp.c index 41693154e426..bcc5551c6424 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -127,10 +127,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem) return; if (type == MEM_TYPE_PAGE_POOL) { - rcu_read_lock(); - xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); - rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); @@ -295,10 +293,8 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); - if (ret < 0) { - WARN_ON(1); + if (ret < 0) return ERR_PTR(ret); - } } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 4d9823d6dced..d6b30700af67 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -353,6 +353,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) /** * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm * @sk: socket to perform estimator on + * @mrtt: measured RTT * * This code is almost identical with TCP's tcp_rtt_estimator(), since * - it has a higher sampling frequency (recommended by RFC 1323), diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 44b033fe1ef6..5926159a6f20 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -24,6 +24,7 @@ #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/netns/generic.h> +#include <net/rstreason.h> #include "ackvec.h" #include "ccid.h" @@ -521,7 +522,8 @@ out: return err; } -static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) +static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb, + enum sk_rst_reason reason) { int err; const struct iphdr *rxiph; @@ -655,8 +657,11 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_v4_send_response(sk, req)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); - reqsk_put(req); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT))) + reqsk_free(req); + else + reqsk_put(req); + return 0; drop_and_free: @@ -706,7 +711,7 @@ int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; reset: - dccp_v4_ctl_send_reset(sk, skb); + dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); kfree_skb(skb); return 0; } @@ -869,7 +874,7 @@ lookup: if (nsk == sk) { reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { - dccp_v4_ctl_send_reset(sk, skb); + dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); goto discard_and_relse; } else { sock_put(sk); @@ -909,7 +914,7 @@ no_dccp_socket: if (dh->dccph_type != DCCP_PKT_RESET) { DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; - dccp_v4_ctl_send_reset(sk, skb); + dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); } discard_it: @@ -1039,7 +1044,7 @@ static void __net_exit dccp_v4_exit_net(struct net *net) static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) { - inet_twsk_purge(&dccp_hashinfo, AF_INET); + inet_twsk_purge(&dccp_hashinfo); } static struct pernet_operations dccp_v4_ops = { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ded07e09f813..da5dba120bc9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -29,6 +29,7 @@ #include <net/secure_seq.h> #include <net/netns/generic.h> #include <net/sock.h> +#include <net/rstreason.h> #include "dccp.h" #include "ipv6.h" @@ -256,7 +257,8 @@ static void dccp_v6_reqsk_destructor(struct request_sock *req) kfree_skb(inet_rsk(req)->pktopts); } -static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) +static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb, + enum sk_rst_reason reason) { const struct ipv6hdr *rxip6h; struct sk_buff *skb; @@ -398,8 +400,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_v6_send_response(sk, req)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); - reqsk_put(req); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT))) + reqsk_free(req); + else + reqsk_put(req); + return 0; drop_and_free: @@ -656,7 +661,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; reset: - dccp_v6_ctl_send_reset(sk, skb); + dccp_v6_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); discard: if (opt_skb != NULL) __kfree_skb(opt_skb); @@ -762,7 +767,7 @@ lookup: if (nsk == sk) { reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { - dccp_v6_ctl_send_reset(sk, skb); + dccp_v6_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); goto discard_and_relse; } else { sock_put(sk); @@ -801,7 +806,7 @@ no_dccp_socket: if (dh->dccph_type != DCCP_PKT_RESET) { DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; - dccp_v6_ctl_send_reset(sk, skb); + dccp_v6_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); } discard_it: @@ -1119,15 +1124,9 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } -static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&dccp_hashinfo, AF_INET6); -} - static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, - .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 64d805b27add..251a57cf5822 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -15,6 +15,7 @@ #include <net/sock.h> #include <net/xfrm.h> #include <net/inet_timewait_sock.h> +#include <net/rstreason.h> #include "ackvec.h" #include "ccid.h" @@ -202,7 +203,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) - req->rsk_ops->send_reset(sk, skb); + req->rsk_ops->send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); inet_csk_reqsk_queue_drop(sk, req); out: diff --git a/net/dccp/output.c b/net/dccp/output.c index fd2eb148d24d..5c2e24f3c39b 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -204,7 +204,7 @@ void dccp_write_space(struct sock *sk) wake_up_interruptible(&wq->wait); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index ee8d4f5afa72..3fc474d6e57d 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -90,8 +90,6 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, - - { } }; static struct ctl_table_header *dccp_table_header; diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 19dbf540748a..13c73f50da3d 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -1202,23 +1202,19 @@ static void __devlink_compat_running_version(struct devlink *devlink, if (err) goto free_msg; - nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + nla_for_each_attr_type(nlattr, DEVLINK_ATTR_INFO_VERSION_RUNNING, + (void *)msg->data, msg->len, rem) { const struct nlattr *kv; int rem_kv; - if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) - continue; - - nla_for_each_nested(kv, nlattr, rem_kv) { - if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) - continue; - + nla_for_each_nested_type(kv, DEVLINK_ATTR_INFO_VERSION_VALUE, + nlattr, rem_kv) { strlcat(buf, nla_data(kv), len); strlcat(buf, " ", len); } } free_msg: - nlmsg_free(msg); + nlmsg_consume(msg); } void devlink_compat_running_version(struct devlink *devlink, diff --git a/net/devlink/param.c b/net/devlink/param.c index 22bc3b500518..dcf0d1ccebba 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -158,11 +158,12 @@ static int devlink_param_get(struct devlink *devlink, static int devlink_param_set(struct devlink *devlink, const struct devlink_param *param, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { if (!param->set) return -EOPNOTSUPP; - return param->set(devlink, param->id, ctx); + return param->set(devlink, param->id, ctx, extack); } static int @@ -571,7 +572,7 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, return -EOPNOTSUPP; ctx.val = value; ctx.cmode = cmode; - err = devlink_param_set(devlink, param, &ctx); + err = devlink_param_set(devlink, param, &ctx, info->extack); if (err) return err; } diff --git a/net/devlink/port.c b/net/devlink/port.c index 118d130d2afd..be9158b4453c 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -16,6 +16,7 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ DEVLINK_PORT_FN_STATE_ACTIVE), [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), + [DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] = { .type = NLA_U32 }, }; #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ @@ -182,6 +183,30 @@ static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, return 0; } +static int devlink_port_fn_max_io_eqs_fill(struct devlink_port *port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + u32 max_io_eqs; + int err; + + if (!port->ops->port_fn_max_io_eqs_get) + return 0; + + err = port->ops->port_fn_max_io_eqs_get(port, &max_io_eqs, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + err = nla_put_u32(msg, DEVLINK_PORT_FN_ATTR_MAX_IO_EQS, max_io_eqs); + if (err) + return err; + *msg_updated = true; + return 0; +} + int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) { if (devlink_nl_put_handle(msg, devlink_port->devlink)) @@ -410,6 +435,18 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, } static int +devlink_port_fn_max_io_eqs_set(struct devlink_port *devlink_port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + u32 max_io_eqs; + + max_io_eqs = nla_get_u32(attr); + return devlink_port->ops->port_fn_max_io_eqs_set(devlink_port, + max_io_eqs, extack); +} + +static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { @@ -430,6 +467,9 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated); if (err) goto out; + err = devlink_port_fn_max_io_eqs_fill(port, msg, extack, &msg_updated); + if (err) + goto out; err = devlink_rel_devlink_handle_put(msg, port->devlink, port->rel_index, DEVLINK_PORT_FN_ATTR_DEVLINK, @@ -726,6 +766,12 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, } } } + if (tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS] && + !ops->port_fn_max_io_eqs_set) { + NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS], + "Function does not support max_io_eqs setting"); + return -EOPNOTSUPP; + } return 0; } @@ -761,6 +807,13 @@ static int devlink_port_function_set(struct devlink_port *port, return err; } + attr = tb[DEVLINK_PORT_FN_ATTR_MAX_IO_EQS]; + if (attr) { + err = devlink_port_fn_max_io_eqs_set(port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when * multiple port function attributes are set along with state, * Those can be applied first before activating the state. diff --git a/net/dsa/devlink.c b/net/dsa/devlink.c index 431bf52290a1..0aac887d0098 100644 --- a/net/dsa/devlink.c +++ b/net/dsa/devlink.c @@ -194,7 +194,8 @@ int dsa_devlink_param_get(struct devlink *dl, u32 id, EXPORT_SYMBOL_GPL(dsa_devlink_param_get); int dsa_devlink_param_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dsa_devlink_to_ds(dl); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 09d2f5d4b3dd..12521a7d4048 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1505,6 +1505,16 @@ static int dsa_switch_probe(struct dsa_switch *ds) if (!ds->num_ports) return -EINVAL; + if (ds->phylink_mac_ops) { + if (ds->ops->phylink_mac_select_pcs || + ds->ops->phylink_mac_prepare || + ds->ops->phylink_mac_config || + ds->ops->phylink_mac_finish || + ds->ops->phylink_mac_link_down || + ds->ops->phylink_mac_link_up) + return -EINVAL; + } + if (np) { err = dsa_switch_parse_of(ds, np); if (err) diff --git a/net/dsa/port.c b/net/dsa/port.c index c42dac87671b..9a249d4ac3a5 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1535,30 +1535,11 @@ void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, cpu_dp->tag_ops = tag_ops; } -static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) -{ - struct device_node *phy_dn; - struct phy_device *phydev; - - phy_dn = of_parse_phandle(dp->dn, "phy-handle", 0); - if (!phy_dn) - return NULL; - - phydev = of_phy_find_device(phy_dn); - if (!phydev) { - of_node_put(phy_dn); - return ERR_PTR(-EPROBE_DEFER); - } - - of_node_put(phy_dn); - return phydev; -} - static struct phylink_pcs * dsa_port_phylink_mac_select_pcs(struct phylink_config *config, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct phylink_pcs *pcs = ERR_PTR(-EOPNOTSUPP); struct dsa_switch *ds = dp->ds; @@ -1572,7 +1553,7 @@ static int dsa_port_phylink_mac_prepare(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; int err = 0; @@ -1587,7 +1568,7 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; if (!ds->ops->phylink_mac_config) @@ -1600,7 +1581,7 @@ static int dsa_port_phylink_mac_finish(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; int err = 0; @@ -1615,18 +1596,11 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct phy_device *phydev = NULL; + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; - if (dsa_port_is_user(dp)) - phydev = dp->user->phydev; - - if (!ds->ops->phylink_mac_link_down) { - if (ds->ops->adjust_link && phydev) - ds->ops->adjust_link(ds, dp->index, phydev); + if (!ds->ops->phylink_mac_link_down) return; - } ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); } @@ -1638,14 +1612,11 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; - if (!ds->ops->phylink_mac_link_up) { - if (ds->ops->adjust_link && phydev) - ds->ops->adjust_link(ds, dp->index, phydev); + if (!ds->ops->phylink_mac_link_up) return; - } ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev, speed, duplex, tx_pause, rx_pause); @@ -1662,6 +1633,7 @@ static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { int dsa_port_phylink_create(struct dsa_port *dp) { + const struct phylink_mac_ops *mac_ops; struct dsa_switch *ds = dp->ds; phy_interface_t mode; struct phylink *pl; @@ -1685,8 +1657,12 @@ int dsa_port_phylink_create(struct dsa_port *dp) } } - pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn), - mode, &dsa_port_phylink_mac_ops); + mac_ops = &dsa_port_phylink_mac_ops; + if (ds->phylink_mac_ops) + mac_ops = ds->phylink_mac_ops; + + pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn), mode, + mac_ops); if (IS_ERR(pl)) { pr_err("error creating PHYLINK: %ld\n", PTR_ERR(pl)); return PTR_ERR(pl); @@ -1703,78 +1679,6 @@ void dsa_port_phylink_destroy(struct dsa_port *dp) dp->pl = NULL; } -static int dsa_shared_port_setup_phy_of(struct dsa_port *dp, bool enable) -{ - struct dsa_switch *ds = dp->ds; - struct phy_device *phydev; - int port = dp->index; - int err = 0; - - phydev = dsa_port_get_phy_device(dp); - if (!phydev) - return 0; - - if (IS_ERR(phydev)) - return PTR_ERR(phydev); - - if (enable) { - err = genphy_resume(phydev); - if (err < 0) - goto err_put_dev; - - err = genphy_read_status(phydev); - if (err < 0) - goto err_put_dev; - } else { - err = genphy_suspend(phydev); - if (err < 0) - goto err_put_dev; - } - - if (ds->ops->adjust_link) - ds->ops->adjust_link(ds, port, phydev); - - dev_dbg(ds->dev, "enabled port's phy: %s", phydev_name(phydev)); - -err_put_dev: - put_device(&phydev->mdio.dev); - return err; -} - -static int dsa_shared_port_fixed_link_register_of(struct dsa_port *dp) -{ - struct device_node *dn = dp->dn; - struct dsa_switch *ds = dp->ds; - struct phy_device *phydev; - int port = dp->index; - phy_interface_t mode; - int err; - - err = of_phy_register_fixed_link(dn); - if (err) { - dev_err(ds->dev, - "failed to register the fixed PHY of port %d\n", - port); - return err; - } - - phydev = of_phy_find_device(dn); - - err = of_get_phy_mode(dn, &mode); - if (err) - mode = PHY_INTERFACE_MODE_NA; - phydev->interface = mode; - - genphy_read_status(phydev); - - if (ds->ops->adjust_link) - ds->ops->adjust_link(ds, port, phydev); - - put_device(&phydev->mdio.dev); - - return 0; -} - static int dsa_shared_port_phylink_register(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; @@ -1952,12 +1856,23 @@ static void dsa_shared_port_validate_of(struct dsa_port *dp, dn, dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); } +static void dsa_shared_port_link_down(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + + if (ds->phylink_mac_ops && ds->phylink_mac_ops->mac_link_down) + ds->phylink_mac_ops->mac_link_down(&dp->pl_config, MLO_AN_FIXED, + PHY_INTERFACE_MODE_NA); + else if (ds->ops->phylink_mac_link_down) + ds->ops->phylink_mac_link_down(ds, dp->index, MLO_AN_FIXED, + PHY_INTERFACE_MODE_NA); +} + int dsa_shared_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; bool missing_link_description; bool missing_phy_mode; - int port = dp->index; dsa_shared_port_validate_of(dp, &missing_phy_mode, &missing_link_description); @@ -1967,46 +1882,28 @@ int dsa_shared_port_link_register_of(struct dsa_port *dp) dsa_switches_apply_workarounds)) return -EINVAL; - if (!ds->ops->adjust_link) { - if (missing_link_description) { - dev_warn(ds->dev, - "Skipping phylink registration for %s port %d\n", - dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); - } else { - if (ds->ops->phylink_mac_link_down) - ds->ops->phylink_mac_link_down(ds, port, - MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); + if (missing_link_description) { + dev_warn(ds->dev, + "Skipping phylink registration for %s port %d\n", + dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); + } else { + dsa_shared_port_link_down(dp); - return dsa_shared_port_phylink_register(dp); - } - return 0; + return dsa_shared_port_phylink_register(dp); } - dev_warn(ds->dev, - "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n"); - - if (of_phy_is_fixed_link(dp->dn)) - return dsa_shared_port_fixed_link_register_of(dp); - else - return dsa_shared_port_setup_phy_of(dp, true); + return 0; } void dsa_shared_port_link_unregister_of(struct dsa_port *dp) { - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->adjust_link && dp->pl) { + if (dp->pl) { rtnl_lock(); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(dp); return; } - - if (of_phy_is_fixed_link(dp->dn)) - of_phy_deregister_fixed_link(dp->dn); - else - dsa_shared_port_setup_phy_of(dp, false); } int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr, diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville" -/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class; - ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; diff --git a/net/dsa/trace.h b/net/dsa/trace.h index 567f29a39707..83f3e5f78491 100644 --- a/net/dsa/trace.h +++ b/net/dsa/trace.h @@ -39,8 +39,8 @@ DECLARE_EVENT_CLASS(dsa_port_addr_op_hw, ), TP_fast_assign( - __assign_str(dev, dev_name(dp->ds->dev)); - __assign_str(kind, dsa_port_kind(dp)); + __assign_str(dev); + __assign_str(kind); __entry->port = dp->index; ether_addr_copy(__entry->addr, addr); __entry->vid = vid; @@ -98,8 +98,8 @@ DECLARE_EVENT_CLASS(dsa_port_addr_op_refcount, ), TP_fast_assign( - __assign_str(dev, dev_name(dp->ds->dev)); - __assign_str(kind, dsa_port_kind(dp)); + __assign_str(dev); + __assign_str(kind); __entry->port = dp->index; ether_addr_copy(__entry->addr, addr); __entry->vid = vid; @@ -157,8 +157,8 @@ DECLARE_EVENT_CLASS(dsa_port_addr_del_not_found, ), TP_fast_assign( - __assign_str(dev, dev_name(dp->ds->dev)); - __assign_str(kind, dsa_port_kind(dp)); + __assign_str(dev); + __assign_str(kind); __entry->port = dp->index; ether_addr_copy(__entry->addr, addr); __entry->vid = vid; @@ -199,7 +199,7 @@ TRACE_EVENT(dsa_lag_fdb_add_hw, ), TP_fast_assign( - __assign_str(dev, lag_dev->name); + __assign_str(dev); ether_addr_copy(__entry->addr, addr); __entry->vid = vid; dsa_db_print(db, __entry->db_buf); @@ -227,7 +227,7 @@ TRACE_EVENT(dsa_lag_fdb_add_bump, ), TP_fast_assign( - __assign_str(dev, lag_dev->name); + __assign_str(dev); ether_addr_copy(__entry->addr, addr); __entry->vid = vid; dsa_db_print(db, __entry->db_buf); @@ -255,7 +255,7 @@ TRACE_EVENT(dsa_lag_fdb_del_hw, ), TP_fast_assign( - __assign_str(dev, lag_dev->name); + __assign_str(dev); ether_addr_copy(__entry->addr, addr); __entry->vid = vid; dsa_db_print(db, __entry->db_buf); @@ -283,7 +283,7 @@ TRACE_EVENT(dsa_lag_fdb_del_drop, ), TP_fast_assign( - __assign_str(dev, lag_dev->name); + __assign_str(dev); ether_addr_copy(__entry->addr, addr); __entry->vid = vid; dsa_db_print(db, __entry->db_buf); @@ -310,7 +310,7 @@ TRACE_EVENT(dsa_lag_fdb_del_not_found, ), TP_fast_assign( - __assign_str(dev, lag_dev->name); + __assign_str(dev); ether_addr_copy(__entry->addr, addr); __entry->vid = vid; dsa_db_print(db, __entry->db_buf); @@ -338,8 +338,8 @@ DECLARE_EVENT_CLASS(dsa_vlan_op_hw, ), TP_fast_assign( - __assign_str(dev, dev_name(dp->ds->dev)); - __assign_str(kind, dsa_port_kind(dp)); + __assign_str(dev); + __assign_str(kind); __entry->port = dp->index; __entry->vid = vlan->vid; __entry->flags = vlan->flags; @@ -383,8 +383,8 @@ DECLARE_EVENT_CLASS(dsa_vlan_op_refcount, ), TP_fast_assign( - __assign_str(dev, dev_name(dp->ds->dev)); - __assign_str(kind, dsa_port_kind(dp)); + __assign_str(dev); + __assign_str(kind); __entry->port = dp->index; __entry->vid = vlan->vid; __entry->flags = vlan->flags; @@ -426,8 +426,8 @@ TRACE_EVENT(dsa_vlan_del_not_found, ), TP_fast_assign( - __assign_str(dev, dev_name(dp->ds->dev)); - __assign_str(kind, dsa_port_kind(dp)); + __assign_str(dev); + __assign_str(kind); __entry->port = dp->index; __entry->vid = vlan->vid; ), diff --git a/net/dsa/user.c b/net/dsa/user.c index 16d395bb1a1f..867c5fe9a4da 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -2120,7 +2120,7 @@ int dsa_user_change_mtu(struct net_device *dev, int new_mtu) if (err) goto out_port_failed; - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); dsa_bridge_mtu_normalization(dp); @@ -2137,6 +2137,32 @@ out_conduit_failed: } static int __maybe_unused +dsa_user_dcbnl_set_apptrust(struct net_device *dev, u8 *sel, int nsel) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->port_set_apptrust) + return -EOPNOTSUPP; + + return ds->ops->port_set_apptrust(ds, port, sel, nsel); +} + +static int __maybe_unused +dsa_user_dcbnl_get_apptrust(struct net_device *dev, u8 *sel, int *nsel) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->port_get_apptrust) + return -EOPNOTSUPP; + + return ds->ops->port_get_apptrust(ds, port, sel, nsel); +} + +static int __maybe_unused dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) { struct dsa_port *dp = dsa_user_to_port(dev); @@ -2163,6 +2189,58 @@ dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) return 0; } +/* Update the DSCP prio entries on all user ports of the switch in case + * the switch supports global DSCP prio instead of per port DSCP prios. + */ +static int dsa_user_dcbnl_ieee_global_dscp_setdel(struct net_device *dev, + struct dcb_app *app, bool del) +{ + int (*setdel)(struct net_device *dev, struct dcb_app *app); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + int err, restore_err; + + if (del) + setdel = dcb_ieee_delapp; + else + setdel = dcb_ieee_setapp; + + dsa_switch_for_each_user_port(other_dp, ds) { + struct net_device *user = other_dp->user; + + if (!user || user == dev) + continue; + + err = setdel(user, app); + if (err) + goto err_try_to_restore; + } + + return 0; + +err_try_to_restore: + + /* Revert logic to restore previous state of app entries */ + if (!del) + setdel = dcb_ieee_delapp; + else + setdel = dcb_ieee_setapp; + + dsa_switch_for_each_user_port_continue_reverse(other_dp, ds) { + struct net_device *user = other_dp->user; + + if (!user || user == dev) + continue; + + restore_err = setdel(user, app); + if (restore_err) + netdev_err(user, "Failed to restore DSCP prio entry configuration\n"); + } + + return err; +} + static int __maybe_unused dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) { @@ -2194,6 +2272,17 @@ dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) return err; } + if (!ds->dscp_prio_mapping_is_global) + return 0; + + err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, false); + if (err) { + if (ds->ops->port_del_dscp_prio) + ds->ops->port_del_dscp_prio(ds, port, dscp, new_prio); + dcb_ieee_delapp(dev, app); + return err; + } + return 0; } @@ -2264,6 +2353,18 @@ dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) return err; } + if (!ds->dscp_prio_mapping_is_global) + return 0; + + err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, true); + if (err) { + if (ds->ops->port_add_dscp_prio) + ds->ops->port_add_dscp_prio(ds, port, dscp, + app->priority); + dcb_ieee_setapp(dev, app); + return err; + } + return 0; } @@ -2376,6 +2477,8 @@ static const struct ethtool_ops dsa_user_ethtool_ops = { static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { .ieee_setapp = dsa_user_dcbnl_ieee_setapp, .ieee_delapp = dsa_user_dcbnl_ieee_delapp, + .dcbnl_setapptrust = dsa_user_dcbnl_set_apptrust, + .dcbnl_getapptrust = dsa_user_dcbnl_get_apptrust, }; static void dsa_user_get_stats64(struct net_device *dev, @@ -2445,7 +2548,7 @@ EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); static void dsa_user_phylink_fixed_state(struct phylink_config *config, struct phylink_link_state *state) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_port *dp = dsa_phylink_to_port(config); struct dsa_switch *ds = dp->ds; /* No need to check that this operation is valid, the callback would diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index e645d751a5e8..f99fd564d0ee 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -441,6 +441,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev, if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + memset(link_ksettings, 0, sizeof(*link_ksettings)); return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } @@ -1277,11 +1280,11 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); const struct ethtool_ops *ops = dev->ethtool_ops; u32 dev_indir_size = 0, dev_key_size = 0, i; + u32 user_indir_len = 0, indir_bytes = 0; struct ethtool_rxfh_param rxfh_dev = {}; struct netlink_ext_ack *extack = NULL; struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; - u32 indir_bytes = 0; u8 *rss_config; int ret; @@ -1306,7 +1309,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR && rxfh.input_xfrm != RXH_XFRM_NO_CHANGE) return -EINVAL; - if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && + if (rxfh.input_xfrm != RXH_XFRM_NO_CHANGE && + (rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && !ops->cap_rss_sym_xor_supported) return -EOPNOTSUPP; @@ -1341,6 +1345,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, */ if (rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { + user_indir_len = indir_bytes; rxfh_dev.indir = (u32 *)rss_config; rxfh_dev.indir_size = dev_indir_size; ret = ethtool_copy_validate_indir(rxfh_dev.indir, @@ -1367,7 +1372,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.key_size = dev_key_size; rxfh_dev.key = rss_config + indir_bytes; if (copy_from_user(rxfh_dev.key, - useraddr + rss_cfg_offset + indir_bytes, + useraddr + rss_cfg_offset + user_indir_len, rxfh.key_size)) { ret = -EFAULT; goto out; diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index b2de2108b356..34d76e87847d 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -37,6 +37,8 @@ static int linkstate_get_sqi(struct net_device *dev) mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi) ret = -EOPNOTSUPP; + else if (!phydev->link) + ret = -ENETDOWN; else ret = phydev->drv->get_sqi(phydev); mutex_unlock(&phydev->lock); @@ -55,6 +57,8 @@ static int linkstate_get_sqi_max(struct net_device *dev) mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi_max) ret = -EOPNOTSUPP; + else if (!phydev->link) + ret = -ENETDOWN; else ret = phydev->drv->get_sqi_max(phydev); mutex_unlock(&phydev->lock); @@ -62,6 +66,17 @@ static int linkstate_get_sqi_max(struct net_device *dev) return ret; }; +static bool linkstate_sqi_critical_error(int sqi) +{ + return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN; +} + +static bool linkstate_sqi_valid(struct linkstate_reply_data *data) +{ + return data->sqi >= 0 && data->sqi_max >= 0 && + data->sqi <= data->sqi_max; +} + static int linkstate_get_link_ext_state(struct net_device *dev, struct linkstate_reply_data *data) { @@ -93,12 +108,12 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, data->link = __ethtool_get_link(dev); ret = linkstate_get_sqi(dev); - if (ret < 0 && ret != -EOPNOTSUPP) + if (linkstate_sqi_critical_error(ret)) goto out; data->sqi = ret; ret = linkstate_get_sqi_max(dev); - if (ret < 0 && ret != -EOPNOTSUPP) + if (linkstate_sqi_critical_error(ret)) goto out; data->sqi_max = ret; @@ -136,11 +151,10 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + 0; - if (data->sqi != -EOPNOTSUPP) - len += nla_total_size(sizeof(u32)); - - if (data->sqi_max != -EOPNOTSUPP) - len += nla_total_size(sizeof(u32)); + if (linkstate_sqi_valid(data)) { + len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */ + len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */ + } if (data->link_ext_state_provided) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */ @@ -164,13 +178,14 @@ static int linkstate_fill_reply(struct sk_buff *skb, nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) return -EMSGSIZE; - if (data->sqi != -EOPNOTSUPP && - nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) - return -EMSGSIZE; + if (linkstate_sqi_valid(data)) { + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) + return -EMSGSIZE; - if (data->sqi_max != -EOPNOTSUPP && - nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max)) - return -EMSGSIZE; + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, + data->sqi_max)) + return -EMSGSIZE; + } if (data->link_ext_state_provided) { if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE, diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index cc478af77111..776ac96cdadc 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -82,6 +82,10 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, len += nla_total_size(sizeof(u32)); /* _PODL_PSE_ADMIN_STATE */ if (st->podl_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _PODL_PSE_PW_D_STATUS */ + if (st->c33_admin_state > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_ADMIN_STATE */ + if (st->c33_pw_status > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_D_STATUS */ return len; } @@ -103,6 +107,16 @@ static int pse_fill_reply(struct sk_buff *skb, st->podl_pw_status)) return -EMSGSIZE; + if (st->c33_admin_state > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_ADMIN_STATE, + st->c33_admin_state)) + return -EMSGSIZE; + + if (st->c33_pw_status > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_D_STATUS, + st->c33_pw_status)) + return -EMSGSIZE; + return 0; } @@ -113,25 +127,18 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { [ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED, ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED), + [ETHTOOL_A_C33_PSE_ADMIN_CONTROL] = + NLA_POLICY_RANGE(NLA_U32, ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED), }; static int ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) { - return !!info->attrs[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]; -} - -static int -ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) -{ struct net_device *dev = req_info->dev; - struct pse_control_config config = {}; struct nlattr **tb = info->attrs; struct phy_device *phydev; - /* this values are already validated by the ethnl_pse_set_policy */ - config.admin_cotrol = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); - phydev = dev->phydev; if (!phydev) { NL_SET_ERR_MSG(info->extack, "No PHY is attached"); @@ -143,7 +150,42 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) return -EOPNOTSUPP; } - /* Return errno directly - PSE has no notification */ + if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] && + !pse_has_podl(phydev->psec)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL], + "setting PoDL PSE admin control not supported"); + return -EOPNOTSUPP; + } + if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL] && + !pse_has_c33(phydev->psec)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL], + "setting C33 PSE admin control not supported"); + return -EOPNOTSUPP; + } + + return 1; +} + +static int +ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) +{ + struct net_device *dev = req_info->dev; + struct pse_control_config config = {}; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; + + phydev = dev->phydev; + /* These values are already validated by the ethnl_pse_set_policy */ + if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]) + config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); + if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) + config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); + + /* Return errno directly - PSE has no notification + * pse_ethtool_set_config() will do nothing if the config is null + */ return pse_ethtool_set_config(phydev->psec, info->extack, &config); } diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 71679137eff2..5c4c4505ab9a 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -111,7 +111,8 @@ rss_reply_size(const struct ethnl_req_info *req_base, const struct rss_reply_data *data = RSS_REPDATA(reply_base); int len; - len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */ + nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */ nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ nla_total_size(data->hkey_size); /* _RSS_HKEY */ @@ -124,6 +125,11 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + + if (request->rss_context && + nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) + return -EMSGSIZE; if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 9daed0aab162..57d496287e52 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -13,14 +13,18 @@ struct tsinfo_req_info { struct tsinfo_reply_data { struct ethnl_reply_data base; struct ethtool_ts_info ts_info; + struct ethtool_ts_stats stats; }; #define TSINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct tsinfo_reply_data, base) +#define ETHTOOL_TS_STAT_CNT \ + (__ETHTOOL_A_TS_STAT_CNT - (ETHTOOL_A_TS_STAT_UNSPEC + 1)) + const struct nla_policy ethnl_tsinfo_get_policy[] = { [ETHTOOL_A_TSINFO_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, @@ -34,6 +38,12 @@ static int tsinfo_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; + if (req_base->flags & ETHTOOL_FLAG_STATS) { + ethtool_stats_init((u64 *)&data->stats, + sizeof(data->stats) / sizeof(u64)); + if (dev->ethtool_ops->get_ts_stats) + dev->ethtool_ops->get_ts_stats(dev, &data->stats); + } ret = __ethtool_get_ts_info(dev, &data->ts_info); ethnl_ops_complete(dev); @@ -79,10 +89,47 @@ static int tsinfo_reply_size(const struct ethnl_req_info *req_base, } if (ts_info->phc_index >= 0) len += nla_total_size(sizeof(u32)); /* _TSINFO_PHC_INDEX */ + if (req_base->flags & ETHTOOL_FLAG_STATS) + len += nla_total_size(0) + /* _TSINFO_STATS */ + nla_total_size_64bit(sizeof(u64)) * ETHTOOL_TS_STAT_CNT; return len; } +static int tsinfo_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) +{ + if (val == ETHTOOL_STAT_NOT_SET) + return 0; + if (nla_put_uint(skb, attrtype, val)) + return -EMSGSIZE; + return 0; +} + +static int tsinfo_put_stats(struct sk_buff *skb, + const struct ethtool_ts_stats *stats) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_TSINFO_STATS); + if (!nest) + return -EMSGSIZE; + + if (tsinfo_put_stat(skb, stats->tx_stats.pkts, + ETHTOOL_A_TS_STAT_TX_PKTS) || + tsinfo_put_stat(skb, stats->tx_stats.lost, + ETHTOOL_A_TS_STAT_TX_LOST) || + tsinfo_put_stat(skb, stats->tx_stats.err, + ETHTOOL_A_TS_STAT_TX_ERR)) + goto err_cancel; + + nla_nest_end(skb, nest); + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int tsinfo_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) @@ -119,6 +166,9 @@ static int tsinfo_fill_reply(struct sk_buff *skb, if (ts_info->phc_index >= 0 && nla_put_u32(skb, ETHTOOL_A_TSINFO_PHC_INDEX, ts_info->phc_index)) return -EMSGSIZE; + if (req_base->flags & ETHTOOL_FLAG_STATS && + tsinfo_put_stats(skb, &data->stats)) + return -EMSGSIZE; return 0; } diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index d697f68c598c..d6f52839827e 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -213,7 +213,6 @@ static int tls_handshake_accept(struct handshake_req *req, if (!hdr) goto out_cancel; - ret = -EMSGSIZE; ret = nla_put_s32(msg, HANDSHAKE_A_ACCEPT_SOCKFD, fd); if (ret < 0) goto out_cancel; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 5afc450d0855..e6904288d40d 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -120,7 +120,7 @@ static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); return 0; } @@ -143,6 +143,9 @@ static int hsr_dev_open(struct net_device *dev) case HSR_PT_SLAVE_B: designation = "Slave B"; break; + case HSR_PT_INTERLINK: + designation = "Interlink"; + break; default: designation = "Unknown"; } @@ -282,6 +285,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, struct hsr_priv *hsr = master->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; + struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; @@ -321,6 +325,16 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); + if (hsr->redbox) { + hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); + hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; + hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); + + /* Payload: MacAddressRedBox */ + hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); + ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); + } + if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; @@ -402,6 +416,10 @@ void hsr_del_ports(struct hsr_priv *hsr) if (port) hsr_del_port(port); + port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); + if (port) + hsr_del_port(port); + port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); @@ -531,8 +549,8 @@ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], - unsigned char multicast_spec, u8 protocol_version, - struct netlink_ext_ack *extack) + struct net_device *interlink, unsigned char multicast_spec, + u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; @@ -541,6 +559,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); + INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); @@ -566,9 +585,11 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; + hsr->interlink_sequence_nr = HSR_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); + timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; @@ -601,6 +622,17 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], if (res) goto err_unregister; + if (interlink) { + res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); + if (res) + goto err_unregister; + + hsr->redbox = true; + ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); + mod_timer(&hsr->prune_proxy_timer, + jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); + } + hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index 9060c92168f9..655284095b78 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -16,8 +16,8 @@ void hsr_del_ports(struct hsr_priv *hsr); void hsr_dev_setup(struct net_device *dev); int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], - unsigned char multicast_spec, u8 protocol_version, - struct netlink_ext_ack *extack); + struct net_device *interlink, unsigned char multicast_spec, + u8 protocol_version, struct netlink_ext_ack *extack); void hsr_check_carrier_and_operstate(struct hsr_priv *hsr); int hsr_get_max_mtu(struct hsr_priv *hsr); #endif /* __HSR_DEVICE_H */ diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 5d68cb181695..05a61b8286ec 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -377,6 +377,15 @@ static int hsr_xmit(struct sk_buff *skb, struct hsr_port *port, */ ether_addr_copy(eth_hdr(skb)->h_source, port->dev->dev_addr); } + + /* When HSR node is used as RedBox - the frame received from HSR ring + * requires source MAC address (SA) replacement to one which can be + * recognized by SAN devices (otherwise, frames are dropped by switch) + */ + if (port->type == HSR_PT_INTERLINK) + ether_addr_copy(eth_hdr(skb)->h_source, + port->hsr->macaddress_redbox); + return dev_queue_xmit(skb); } @@ -390,9 +399,57 @@ bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) { + struct sk_buff *skb; + if (port->dev->features & NETIF_F_HW_HSR_FWD) return prp_drop_frame(frame, port); + /* RedBox specific frames dropping policies + * + * Do not send HSR supervisory frames to SAN devices + */ + if (frame->is_supervision && port->type == HSR_PT_INTERLINK) + return true; + + /* Do not forward to other HSR port (A or B) unicast frames which + * are addressed to interlink port (and are in the ProxyNodeTable). + */ + skb = frame->skb_hsr; + if (skb && prp_drop_frame(frame, port) && + is_unicast_ether_addr(eth_hdr(skb)->h_dest) && + hsr_is_node_in_db(&port->hsr->proxy_node_db, + eth_hdr(skb)->h_dest)) { + return true; + } + + /* Do not forward to port C (Interlink) frames from nodes A and B + * if DA is in NodeTable. + */ + if ((frame->port_rcv->type == HSR_PT_SLAVE_A || + frame->port_rcv->type == HSR_PT_SLAVE_B) && + port->type == HSR_PT_INTERLINK) { + skb = frame->skb_hsr; + if (skb && is_unicast_ether_addr(eth_hdr(skb)->h_dest) && + hsr_is_node_in_db(&port->hsr->node_db, + eth_hdr(skb)->h_dest)) { + return true; + } + } + + /* Do not forward to port A and B unicast frames received on the + * interlink port if it is addressed to one of nodes registered in + * the ProxyNodeTable. + */ + if ((port->type == HSR_PT_SLAVE_A || port->type == HSR_PT_SLAVE_B) && + frame->port_rcv->type == HSR_PT_INTERLINK) { + skb = frame->skb_std; + if (skb && is_unicast_ether_addr(eth_hdr(skb)->h_dest) && + hsr_is_node_in_db(&port->hsr->proxy_node_db, + eth_hdr(skb)->h_dest)) { + return true; + } + } + return false; } @@ -448,13 +505,14 @@ static void hsr_forward_do(struct hsr_frame_info *frame) } /* Check if frame is to be dropped. Eg. for PRP no forward - * between ports. + * between ports, or sending HSR supervision to RedBox. */ if (hsr->proto_ops->drop_frame && hsr->proto_ops->drop_frame(frame, port)) continue; - if (port->type != HSR_PT_MASTER) + if (port->type == HSR_PT_SLAVE_A || + port->type == HSR_PT_SLAVE_B) skb = hsr->proto_ops->create_tagged_frame(frame, port); else skb = hsr->proto_ops->get_untagged_frame(frame, port); @@ -469,7 +527,9 @@ static void hsr_forward_do(struct hsr_frame_info *frame) hsr_deliver_master(skb, port->dev, frame->node_src); } else { if (!hsr_xmit(skb, port, frame)) - sent = true; + if (port->type == HSR_PT_SLAVE_A || + port->type == HSR_PT_SLAVE_B) + sent = true; } } } @@ -503,10 +563,12 @@ static void handle_std_frame(struct sk_buff *skb, frame->skb_prp = NULL; frame->skb_std = skb; - if (port->type != HSR_PT_MASTER) { + if (port->type != HSR_PT_MASTER) frame->is_from_san = true; - } else { - /* Sequence nr for the master node */ + + if (port->type == HSR_PT_MASTER || + port->type == HSR_PT_INTERLINK) { + /* Sequence nr for the master/interlink node */ lockdep_assert_held(&hsr->seqnr_lock); frame->sequence_nr = hsr->sequence_nr; hsr->sequence_nr++; @@ -564,6 +626,7 @@ static int fill_frame_info(struct hsr_frame_info *frame, { struct hsr_priv *hsr = port->hsr; struct hsr_vlan_ethhdr *vlan_hdr; + struct list_head *n_db; struct ethhdr *ethhdr; __be16 proto; int ret; @@ -574,9 +637,13 @@ static int fill_frame_info(struct hsr_frame_info *frame, memset(frame, 0, sizeof(*frame)); frame->is_supervision = is_supervision_frame(port->hsr, skb); - frame->node_src = hsr_get_node(port, &hsr->node_db, skb, - frame->is_supervision, - port->type); + + n_db = &hsr->node_db; + if (port->type == HSR_PT_INTERLINK) + n_db = &hsr->proxy_node_db; + + frame->node_src = hsr_get_node(port, n_db, skb, + frame->is_supervision, port->type); if (!frame->node_src) return -1; /* Unknown node and !is_supervision, or no mem */ diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 26329db09210..614df9649794 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -71,6 +71,14 @@ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, return NULL; } +/* Check if node for a given MAC address is already present in data base + */ +bool hsr_is_node_in_db(struct list_head *node_db, + const unsigned char addr[ETH_ALEN]) +{ + return !!find_node_by_addr_A(node_db, addr); +} + /* Helper for device init; the self_node is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ @@ -223,6 +231,15 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, } } + /* Check if required node is not in proxy nodes table */ + list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { + if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { + if (hsr->proto_ops->update_san_info) + hsr->proto_ops->update_san_info(node, is_sup); + return node; + } + } + /* Everyone may create a node entry, connected node to a HSR/PRP * device. */ @@ -418,6 +435,10 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); + if (!node_dst && port->hsr->redbox) + node_dst = find_node_by_addr_A(&port->hsr->proxy_node_db, + eth_hdr(skb)->h_dest); + if (!node_dst) { if (port->hsr->prot_version != PRP_V1 && net_ratelimit()) netdev_err(skb->dev, "%s: Unknown node\n", __func__); @@ -561,6 +582,37 @@ void hsr_prune_nodes(struct timer_list *t) jiffies + msecs_to_jiffies(PRUNE_PERIOD)); } +void hsr_prune_proxy_nodes(struct timer_list *t) +{ + struct hsr_priv *hsr = from_timer(hsr, t, prune_proxy_timer); + unsigned long timestamp; + struct hsr_node *node; + struct hsr_node *tmp; + + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_safe(node, tmp, &hsr->proxy_node_db, mac_list) { + timestamp = node->time_in[HSR_PT_INTERLINK]; + + /* Prune old entries */ + if (time_is_before_jiffies(timestamp + + msecs_to_jiffies(HSR_PROXY_NODE_FORGET_TIME))) { + hsr_nl_nodedown(hsr, node->macaddress_A); + if (!node->removed) { + list_del_rcu(&node->mac_list); + node->removed = true; + /* Note that we need to free this entry later: */ + kfree_rcu(node, rcu_head); + } + } + } + + spin_unlock_bh(&hsr->list_lock); + + /* Restart timer */ + mod_timer(&hsr->prune_proxy_timer, + jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); +} + void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]) { diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index b23556251d62..7619e31c1d2d 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -46,6 +46,7 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, u16 sequence_nr); void hsr_prune_nodes(struct timer_list *t); +void hsr_prune_proxy_nodes(struct timer_list *t); int hsr_create_self_node(struct hsr_priv *hsr, const unsigned char addr_a[ETH_ALEN], @@ -67,6 +68,9 @@ void prp_handle_san_frame(bool san, enum hsr_port_type port, struct hsr_node *node); void prp_update_san_info(struct hsr_node *node, bool is_sup); +bool hsr_is_node_in_db(struct list_head *node_db, + const unsigned char addr[ETH_ALEN]); + struct hsr_node { struct list_head mac_list; /* Protect R/W access to seq_out */ diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 9756e657bab9..d7ae32473c41 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -96,7 +96,7 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, break; /* Handled in ndo_change_mtu() */ mtu_max = hsr_get_max_mtu(port->hsr); master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); - master->dev->mtu = mtu_max; + WRITE_ONCE(master->dev->mtu, mtu_max); break; case NETDEV_UNREGISTER: if (!is_hsr_master(dev)) { diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 18e01791ad79..23850b16d1ea 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -21,6 +21,7 @@ */ #define HSR_LIFE_CHECK_INTERVAL 2000 /* ms */ #define HSR_NODE_FORGET_TIME 60000 /* ms */ +#define HSR_PROXY_NODE_FORGET_TIME 60000 /* ms */ #define HSR_ANNOUNCE_INTERVAL 100 /* ms */ #define HSR_ENTRY_FORGET_TIME 400 /* ms */ @@ -35,6 +36,7 @@ * HSR_NODE_FORGET_TIME? */ #define PRUNE_PERIOD 3000 /* ms */ +#define PRUNE_PROXY_PERIOD 3000 /* ms */ #define HSR_TLV_EOT 0 /* End of TLVs */ #define HSR_TLV_ANNOUNCE 22 #define HSR_TLV_LIFE_CHECK 23 @@ -192,11 +194,14 @@ struct hsr_priv { struct rcu_head rcu_head; struct list_head ports; struct list_head node_db; /* Known HSR nodes */ + struct list_head proxy_node_db; /* RedBox HSR proxy nodes */ struct hsr_self_node __rcu *self_node; /* MACs of slaves */ struct timer_list announce_timer; /* Supervision frame dispatch */ struct timer_list prune_timer; + struct timer_list prune_proxy_timer; int announce_count; u16 sequence_nr; + u16 interlink_sequence_nr; /* Interlink port seq_nr */ u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ enum hsr_version prot_version; /* Indicate if HSRv0, HSRv1 or PRPv1 */ spinlock_t seqnr_lock; /* locking for sequence_nr */ @@ -209,6 +214,8 @@ struct hsr_priv { * of lan_id */ bool fwd_offloaded; /* Forwarding offloaded to HW */ + bool redbox; /* Device supports HSR RedBox */ + unsigned char macaddress_redbox[ETH_ALEN]; unsigned char sup_multicast_addr[ETH_ALEN] __aligned(sizeof(u16)); /* Align to u16 boundary to avoid unaligned access * in ether_addr_equal diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 78fe40eb9f01..898f18c6da53 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -23,6 +23,7 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { [IFLA_HSR_SUPERVISION_ADDR] = { .len = ETH_ALEN }, [IFLA_HSR_SEQ_NR] = { .type = NLA_U16 }, [IFLA_HSR_PROTOCOL] = { .type = NLA_U8 }, + [IFLA_HSR_INTERLINK] = { .type = NLA_U32 }, }; /* Here, it seems a netdevice has already been allocated for us, and the @@ -35,8 +36,8 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, enum hsr_version proto_version; unsigned char multicast_spec; u8 proto = HSR_PROTOCOL_HSR; - struct net_device *link[2]; + struct net_device *link[2], *interlink = NULL; if (!data) { NL_SET_ERR_MSG_MOD(extack, "No slave devices specified"); return -EINVAL; @@ -67,6 +68,20 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; } + if (data[IFLA_HSR_INTERLINK]) + interlink = __dev_get_by_index(src_net, + nla_get_u32(data[IFLA_HSR_INTERLINK])); + + if (interlink && interlink == link[0]) { + NL_SET_ERR_MSG_MOD(extack, "Interlink and Slave1 are the same"); + return -EINVAL; + } + + if (interlink && interlink == link[1]) { + NL_SET_ERR_MSG_MOD(extack, "Interlink and Slave2 are the same"); + return -EINVAL; + } + if (!data[IFLA_HSR_MULTICAST_SPEC]) multicast_spec = 0; else @@ -96,10 +111,17 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, } } - if (proto == HSR_PROTOCOL_PRP) + if (proto == HSR_PROTOCOL_PRP) { proto_version = PRP_V1; + if (interlink) { + NL_SET_ERR_MSG_MOD(extack, + "Interlink only works with HSR"); + return -EINVAL; + } + } - return hsr_dev_finalize(dev, link, multicast_spec, proto_version, extack); + return hsr_dev_finalize(dev, link, interlink, multicast_spec, + proto_version, extack); } static void hsr_dellink(struct net_device *dev, struct list_head *head) @@ -107,6 +129,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) struct hsr_priv *hsr = netdev_priv(dev); del_timer_sync(&hsr->prune_timer); + del_timer_sync(&hsr->prune_proxy_timer); del_timer_sync(&hsr->announce_timer); hsr_debugfs_term(hsr); @@ -114,6 +137,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) hsr_del_self_node(hsr); hsr_del_nodes(&hsr->node_db); + hsr_del_nodes(&hsr->proxy_node_db); unregister_netdevice_queue(dev, head); } diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 1b6457f357bd..af6cf64a00e0 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -55,6 +55,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) protocol = eth_hdr(skb)->h_proto; if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && + port->type != HSR_PT_INTERLINK && hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 6dd960ec558c..56ef873828f4 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -338,7 +338,6 @@ static struct ctl_table lowpan_frags_ns_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; /* secret interval has been deprecated */ @@ -351,7 +350,6 @@ static struct ctl_table lowpan_frags_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) @@ -370,10 +368,8 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) goto err_alloc; /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) { - table[0].procname = NULL; + if (net->user_ns != &init_user_ns) table_size = 0; - } } table[0].data = &ieee802154_lowpan->fqdir->high_thresh; @@ -399,7 +395,7 @@ err_alloc: static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h index 62aa6465253a..591ce0a16fc0 100644 --- a/net/ieee802154/trace.h +++ b/net/ieee802154/trace.h @@ -75,7 +75,7 @@ TRACE_EVENT(802154_rdev_add_virtual_intf, ), TP_fast_assign( WPAN_PHY_ASSIGN; - __assign_str(vir_intf_name, name ? name : "<noname>"); + __assign_str(vir_intf_name); __entry->type = type; __entry->extended_addr = extended_addr; ), diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5622ddd3bf55..b24d74616637 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -773,16 +773,16 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new * Accept a pending connection. The TCP layer now gives BSD semantics. */ -int inet_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +int inet_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *sk1 = sock->sk, *sk2; - int err = -EINVAL; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ - sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, flags, &err, kern); + arg->err = -EINVAL; + sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, arg); if (!sk2) - return err; + return arg->err; lock_sock(sk2); __inet_accept(sock, newsock, sk2); @@ -1074,6 +1074,7 @@ const struct proto_ops inet_stream_ops = { #endif .splice_eof = inet_splice_eof, .splice_read = tcp_splice_read, + .set_peek_off = sk_set_peek_off, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, @@ -1483,7 +1484,6 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) struct sk_buff *p; unsigned int hlen; unsigned int off; - unsigned int id; int flush = 1; int proto; @@ -1509,13 +1509,10 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) goto out; NAPI_GRO_CB(skb)->proto = proto; - id = ntohl(*(__be32 *)&iph->id); - flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); - id >>= 16; + flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (ntohl(*(__be32 *)&iph->id) & ~IP_DF)); list_for_each_entry(p, head, list) { struct iphdr *iph2; - u16 flush_id; if (!NAPI_GRO_CB(p)->same_flow) continue; @@ -1532,49 +1529,10 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) NAPI_GRO_CB(p)->same_flow = 0; continue; } - - /* All fields must match except length and checksum. */ - NAPI_GRO_CB(p)->flush |= - (iph->ttl ^ iph2->ttl) | - (iph->tos ^ iph2->tos) | - ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)); - - NAPI_GRO_CB(p)->flush |= flush; - - /* We need to store of the IP ID check to be included later - * when we can verify that this packet does in fact belong - * to a given flow. - */ - flush_id = (u16)(id - ntohs(iph2->id)); - - /* This bit of code makes it much easier for us to identify - * the cases where we are doing atomic vs non-atomic IP ID - * checks. Specifically an atomic check can return IP ID - * values 0 - 0xFFFF, while a non-atomic check can only - * return 0 or 0xFFFF. - */ - if (!NAPI_GRO_CB(p)->is_atomic || - !(iph->frag_off & htons(IP_DF))) { - flush_id ^= NAPI_GRO_CB(p)->count; - flush_id = flush_id ? 0xFFFF : 0; - } - - /* If the previous IP ID value was based on an atomic - * datagram we can overwrite the value and ignore it. - */ - if (NAPI_GRO_CB(skb)->is_atomic) - NAPI_GRO_CB(p)->flush_id = flush_id; - else - NAPI_GRO_CB(p)->flush_id |= flush_id; } - NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF)); NAPI_GRO_CB(skb)->flush |= flush; - skb_set_network_header(skb, off); - /* The above will be needed by the transport layer if there is one - * immediately following this IP hdr. - */ - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 0d0d725b46ad..11c1519b3699 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -456,7 +456,8 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) /*unsigned long now; */ struct net *net = dev_net(dev); - rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev)); + rt = ip_route_output(net, sip, tip, 0, l3mdev_master_ifindex_rcu(dev), + RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return 1; if (rt->dst.dev != dev) { @@ -1002,6 +1003,55 @@ out_of_mem: * User level interface (ioctl) */ +static struct net_device *arp_req_dev_by_name(struct net *net, struct arpreq *r, + bool getarp) +{ + struct net_device *dev; + + if (getarp) + dev = dev_get_by_name_rcu(net, r->arp_dev); + else + dev = __dev_get_by_name(net, r->arp_dev); + if (!dev) + return ERR_PTR(-ENODEV); + + /* Mmmm... It is wrong... ARPHRD_NETROM == 0 */ + if (!r->arp_ha.sa_family) + r->arp_ha.sa_family = dev->type; + + if ((r->arp_flags & ATF_COM) && r->arp_ha.sa_family != dev->type) + return ERR_PTR(-EINVAL); + + return dev; +} + +static struct net_device *arp_req_dev(struct net *net, struct arpreq *r) +{ + struct net_device *dev; + struct rtable *rt; + __be32 ip; + + if (r->arp_dev[0]) + return arp_req_dev_by_name(net, r, false); + + if (r->arp_flags & ATF_PUBL) + return NULL; + + ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; + + rt = ip_route_output(net, ip, 0, 0, 0, RT_SCOPE_LINK); + if (IS_ERR(rt)) + return ERR_CAST(rt); + + dev = rt->dst.dev; + ip_rt_put(rt); + + if (!dev) + return ERR_PTR(-EINVAL); + + return dev; +} + /* * Set (create) an ARP cache entry. */ @@ -1022,11 +1072,8 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { - __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; - if (mask && mask != htonl(0xFFFFFFFF)) - return -EINVAL; if (!dev && (r->arp_flags & ATF_COM)) { dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, r->arp_ha.sa_data); @@ -1034,6 +1081,8 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, return -ENODEV; } if (mask) { + __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; + if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1)) return -ENOBUFS; return 0; @@ -1042,29 +1091,20 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, return arp_req_set_proxy(net, dev, 1); } -static int arp_req_set(struct net *net, struct arpreq *r, - struct net_device *dev) +static int arp_req_set(struct net *net, struct arpreq *r) { - __be32 ip; struct neighbour *neigh; + struct net_device *dev; + __be32 ip; int err; + dev = arp_req_dev(net, r); + if (IS_ERR(dev)) + return PTR_ERR(dev); + if (r->arp_flags & ATF_PUBL) return arp_req_set_public(net, r, dev); - ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (r->arp_flags & ATF_PERM) - r->arp_flags |= ATF_COM; - if (!dev) { - struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); - - if (IS_ERR(rt)) - return PTR_ERR(rt); - dev = rt->dst.dev; - ip_rt_put(rt); - if (!dev) - return -EINVAL; - } switch (dev->type) { #if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: @@ -1086,12 +1126,18 @@ static int arp_req_set(struct net *net, struct arpreq *r, break; } + ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; + neigh = __neigh_lookup_errno(&arp_tbl, &ip, dev); err = PTR_ERR(neigh); if (!IS_ERR(neigh)) { unsigned int state = NUD_STALE; - if (r->arp_flags & ATF_PERM) + + if (r->arp_flags & ATF_PERM) { + r->arp_flags |= ATF_COM; state = NUD_PERMANENT; + } + err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? r->arp_ha.sa_data : NULL, state, NEIGH_UPDATE_F_OVERRIDE | @@ -1115,27 +1161,40 @@ static unsigned int arp_state_to_flags(struct neighbour *neigh) * Get an ARP cache entry. */ -static int arp_req_get(struct arpreq *r, struct net_device *dev) +static int arp_req_get(struct net *net, struct arpreq *r) { __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; struct neighbour *neigh; - int err = -ENXIO; + struct net_device *dev; + + if (!r->arp_dev[0]) + return -ENODEV; + + dev = arp_req_dev_by_name(net, r, true); + if (IS_ERR(dev)) + return PTR_ERR(dev); neigh = neigh_lookup(&arp_tbl, &ip, dev); - if (neigh) { - if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { - read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, - min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); - r->arp_flags = arp_state_to_flags(neigh); - read_unlock_bh(&neigh->lock); - r->arp_ha.sa_family = dev->type; - strscpy(r->arp_dev, dev->name, sizeof(r->arp_dev)); - err = 0; - } + if (!neigh) + return -ENXIO; + + if (READ_ONCE(neigh->nud_state) & NUD_NOARP) { neigh_release(neigh); + return -ENXIO; } - return err; + + read_lock_bh(&neigh->lock); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); + r->arp_flags = arp_state_to_flags(neigh); + read_unlock_bh(&neigh->lock); + + neigh_release(neigh); + + r->arp_ha.sa_family = dev->type; + netdev_copy_name(dev, r->arp_dev); + + return 0; } int arp_invalidate(struct net_device *dev, __be32 ip, bool force) @@ -1166,36 +1225,31 @@ int arp_invalidate(struct net_device *dev, __be32 ip, bool force) static int arp_req_delete_public(struct net *net, struct arpreq *r, struct net_device *dev) { - __be32 ip = ((struct sockaddr_in *) &r->arp_pa)->sin_addr.s_addr; __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; - if (mask == htonl(0xFFFFFFFF)) - return pneigh_delete(&arp_tbl, net, &ip, dev); + if (mask) { + __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (mask) - return -EINVAL; + return pneigh_delete(&arp_tbl, net, &ip, dev); + } return arp_req_set_proxy(net, dev, 0); } -static int arp_req_delete(struct net *net, struct arpreq *r, - struct net_device *dev) +static int arp_req_delete(struct net *net, struct arpreq *r) { + struct net_device *dev; __be32 ip; + dev = arp_req_dev(net, r); + if (IS_ERR(dev)) + return PTR_ERR(dev); + if (r->arp_flags & ATF_PUBL) return arp_req_delete_public(net, r, dev); ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (!dev) { - struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); - if (IS_ERR(rt)) - return PTR_ERR(rt); - dev = rt->dst.dev; - ip_rt_put(rt); - if (!dev) - return -EINVAL; - } + return arp_invalidate(dev, ip, true); } @@ -1205,9 +1259,9 @@ static int arp_req_delete(struct net *net, struct arpreq *r, int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) { - int err; struct arpreq r; - struct net_device *dev = NULL; + __be32 *netmask; + int err; switch (cmd) { case SIOCDARP: @@ -1230,42 +1284,34 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!(r.arp_flags & ATF_PUBL) && (r.arp_flags & (ATF_NETMASK | ATF_DONTPUB))) return -EINVAL; + + netmask = &((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr; if (!(r.arp_flags & ATF_NETMASK)) - ((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr = - htonl(0xFFFFFFFFUL); - rtnl_lock(); - if (r.arp_dev[0]) { - err = -ENODEV; - dev = __dev_get_by_name(net, r.arp_dev); - if (!dev) - goto out; - - /* Mmmm... It is wrong... ARPHRD_NETROM==0 */ - if (!r.arp_ha.sa_family) - r.arp_ha.sa_family = dev->type; - err = -EINVAL; - if ((r.arp_flags & ATF_COM) && r.arp_ha.sa_family != dev->type) - goto out; - } else if (cmd == SIOCGARP) { - err = -ENODEV; - goto out; - } + *netmask = htonl(0xFFFFFFFFUL); + else if (*netmask && *netmask != htonl(0xFFFFFFFFUL)) + return -EINVAL; switch (cmd) { case SIOCDARP: - err = arp_req_delete(net, &r, dev); + rtnl_lock(); + err = arp_req_delete(net, &r); + rtnl_unlock(); break; case SIOCSARP: - err = arp_req_set(net, &r, dev); + rtnl_lock(); + err = arp_req_set(net, &r); + rtnl_unlock(); break; case SIOCGARP: - err = arp_req_get(&r, dev); + rcu_read_lock(); + err = arp_req_get(net, &r); + rcu_read_unlock(); + + if (!err && copy_to_user(arg, &r, sizeof(r))) + err = -EFAULT; break; } -out: - rtnl_unlock(); - if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r))) - err = -EFAULT; + return err; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 7f518ea5f4ac..18227757ec0c 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -107,6 +107,9 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, case offsetof(struct tcp_sock, snd_cwnd_cnt): end = offsetofend(struct tcp_sock, snd_cwnd_cnt); break; + case offsetof(struct tcp_sock, snd_cwnd_stamp): + end = offsetofend(struct tcp_sock, snd_cwnd_stamp); + break; case offsetof(struct tcp_sock, snd_ssthresh): end = offsetofend(struct tcp_sock, snd_ssthresh); break; @@ -307,7 +310,8 @@ static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk) return 0; } -static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs) +static void bpf_tcp_ca_cong_control(struct sock *sk, u32 ack, int flag, + const struct rate_sample *rs) { } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 1eb98440c01e..e9cb27061c12 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1810,11 +1810,35 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, return CIPSO_V4_HDR_LEN + ret_val; } +static int cipso_v4_get_actual_opt_len(const unsigned char *data, int len) +{ + int iter = 0, optlen = 0; + + /* determining the new total option length is tricky because of + * the padding necessary, the only thing i can think to do at + * this point is walk the options one-by-one, skipping the + * padding at the end to determine the actual option size and + * from there we can determine the new total option length + */ + while (iter < len) { + if (data[iter] == IPOPT_END) { + break; + } else if (data[iter] == IPOPT_NOP) { + iter++; + } else { + iter += data[iter + 1]; + optlen = iter; + } + } + return optlen; +} + /** * cipso_v4_sock_setattr - Add a CIPSO option to a socket * @sk: the socket * @doi_def: the CIPSO DOI to use * @secattr: the specific security attributes of the socket + * @sk_locked: true if caller holds the socket lock * * Description: * Set the CIPSO option on the given socket using the DOI definition and @@ -1826,7 +1850,8 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, */ int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, - const struct netlbl_lsm_secattr *secattr) + const struct netlbl_lsm_secattr *secattr, + bool sk_locked) { int ret_val = -EPERM; unsigned char *buf = NULL; @@ -1876,8 +1901,7 @@ int cipso_v4_sock_setattr(struct sock *sk, sk_inet = inet_sk(sk); - old = rcu_dereference_protected(sk_inet->inet_opt, - lockdep_sock_is_held(sk)); + old = rcu_dereference_protected(sk_inet->inet_opt, sk_locked); if (inet_test_bit(IS_ICSK, sk)) { sk_conn = inet_csk(sk); if (old) @@ -1985,7 +2009,6 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) u8 cipso_len; u8 cipso_off; unsigned char *cipso_ptr; - int iter; int optlen_new; cipso_off = opt->opt.cipso - sizeof(struct iphdr); @@ -2005,23 +2028,8 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) memmove(cipso_ptr, cipso_ptr + cipso_len, opt->opt.optlen - cipso_off - cipso_len); - /* determining the new total option length is tricky because of - * the padding necessary, the only thing i can think to do at - * this point is walk the options one-by-one, skipping the - * padding at the end to determine the actual option size and - * from there we can determine the new total option length */ - iter = 0; - optlen_new = 0; - while (iter < opt->opt.optlen) { - if (opt->opt.__data[iter] == IPOPT_END) { - break; - } else if (opt->opt.__data[iter] == IPOPT_NOP) { - iter++; - } else { - iter += opt->opt.__data[iter + 1]; - optlen_new = iter; - } - } + optlen_new = cipso_v4_get_actual_opt_len(opt->opt.__data, + opt->opt.optlen); hdr_delta = opt->opt.optlen; opt->opt.optlen = (optlen_new + 3) & ~3; hdr_delta -= opt->opt.optlen; @@ -2241,7 +2249,8 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb, */ int cipso_v4_skbuff_delattr(struct sk_buff *skb) { - int ret_val; + int ret_val, cipso_len, hdr_len_actual, new_hdr_len_actual, new_hdr_len, + hdr_len_delta; struct iphdr *iph; struct ip_options *opt = &IPCB(skb)->opt; unsigned char *cipso_ptr; @@ -2254,16 +2263,37 @@ int cipso_v4_skbuff_delattr(struct sk_buff *skb) if (ret_val < 0) return ret_val; - /* the easiest thing to do is just replace the cipso option with noop - * options since we don't change the size of the packet, although we - * still need to recalculate the checksum */ - iph = ip_hdr(skb); cipso_ptr = (unsigned char *)iph + opt->cipso; - memset(cipso_ptr, IPOPT_NOOP, cipso_ptr[1]); + cipso_len = cipso_ptr[1]; + + hdr_len_actual = sizeof(struct iphdr) + + cipso_v4_get_actual_opt_len((unsigned char *)(iph + 1), + opt->optlen); + new_hdr_len_actual = hdr_len_actual - cipso_len; + new_hdr_len = (new_hdr_len_actual + 3) & ~3; + hdr_len_delta = (iph->ihl << 2) - new_hdr_len; + + /* 1. shift any options after CIPSO to the left */ + memmove(cipso_ptr, cipso_ptr + cipso_len, + new_hdr_len_actual - opt->cipso); + /* 2. move the whole IP header to its new place */ + memmove((unsigned char *)iph + hdr_len_delta, iph, new_hdr_len_actual); + /* 3. adjust the skb layout */ + skb_pull(skb, hdr_len_delta); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + /* 4. re-fill new padding with IPOPT_END (may now be longer) */ + memset((unsigned char *)iph + new_hdr_len_actual, IPOPT_END, + new_hdr_len - new_hdr_len_actual); + + opt->optlen -= hdr_len_delta; opt->cipso = 0; opt->is_changed = 1; - + if (hdr_len_delta != 0) { + iph->ihl = new_hdr_len >> 2; + iph_set_totlen(iph, skb->len); + } ip_send_check(iph); return 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 84b5d1ccf716..d09f557eaa77 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -224,6 +224,7 @@ static struct in_ifaddr *inet_alloc_ifa(void) static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); + if (ifa->ifa_dev) in_dev_put(ifa->ifa_dev); kfree(ifa); @@ -231,7 +232,11 @@ static void inet_rcu_free_ifa(struct rcu_head *head) static void inet_free_ifa(struct in_ifaddr *ifa) { - call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); + /* Our reference to ifa->ifa_dev must be freed ASAP + * to release the reference to the netdev the same way. + * in_dev_put() -> in_dev_finish_destroy() -> netdev_put() + */ + call_rcu_hurry(&ifa->rcu_head, inet_rcu_free_ifa); } static void in_dev_free_rcu(struct rcu_head *head) @@ -2523,7 +2528,7 @@ static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX]; + struct ctl_table devinet_vars[IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", @@ -2586,7 +2591,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, if (!t) goto out; - for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) { + for (i = 0; i < ARRAY_SIZE(t->devinet_vars); i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; @@ -2660,7 +2665,6 @@ static struct ctl_table ctl_forward_entry[] = { .extra1 = &ipv4_devconf, .extra2 = &init_net, }, - { }, }; #endif @@ -2757,7 +2761,7 @@ err_alloc_all: static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL - struct ctl_table *tbl; + const struct ctl_table *tbl; tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index d33d12421814..619a4df7be1e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -20,6 +20,7 @@ #include <net/udp.h> #include <net/tcp.h> #include <net/espintcp.h> +#include <linux/skbuff_ref.h> #include <linux/highmem.h> @@ -114,7 +115,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(skb, sg_page(sg), false); + skb_page_unref(sg_page(sg), skb->pp_recycle); } #ifdef CONFIG_INET_ESPINTCP @@ -238,8 +239,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) #else static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { - kfree_skb(skb); - + WARN_ON(1); return -EOPNOTSUPP; } #endif @@ -347,7 +347,6 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, __be16 dport) { struct udphdr *uh; - __be32 *udpdata32; unsigned int len; len = skb->len + esp->tailen - skb_transport_offset(skb); @@ -362,12 +361,6 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, *skb_mac_header(skb) = IPPROTO_UDP; - if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - return (struct ip_esp_hdr *)(udpdata32 + 2); - } - return (struct ip_esp_hdr *)(uh + 1); } @@ -423,7 +416,6 @@ static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb, switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport); break; case TCP_ENCAP_ESPINTCP: @@ -775,7 +767,6 @@ int esp_input_done2(struct sk_buff *skb, int err) source = th->source; break; case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: source = uh->source; break; default: @@ -1179,9 +1170,6 @@ static int esp_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); - break; #ifdef CONFIG_INET_ESPINTCP case TCP_ENCAP_ESPINTCP: /* only the length field, TCP encap is done by diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index b3271957ad9a..3f28ecbdcaef 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -56,6 +56,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, x = xfrm_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ip_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET); + + if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) { + /* non-offload path will record the error and audit log */ + xfrm_state_put(x); + x = NULL; + } + if (!x) goto out_reset; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 5eb1b8d302bb..8956026bc0a2 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -254,7 +254,7 @@ void free_fib_info(struct fib_info *fi) return; } - call_rcu(&fi->rcu, free_fib_info_rcu); + call_rcu_hurry(&fi->rcu, free_fib_info_rcu); } EXPORT_SYMBOL_GPL(free_fib_info); @@ -2270,6 +2270,15 @@ void fib_select_path(struct net *net, struct fib_result *res, fib_select_default(fl4, res); check_saddr: - if (!fl4->saddr) - fl4->saddr = fib_result_prefsrc(net, res); + if (!fl4->saddr) { + struct net_device *l3mdev; + + l3mdev = dev_get_by_index_rcu(net, fl4->flowi4_l3mdev); + + if (!l3mdev || + l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) == l3mdev) + fl4->saddr = fib_result_prefsrc(net, res); + else + fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK); + } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index f474106464d2..8f30e3f00b7f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1629,6 +1629,7 @@ set_result: res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; + res->dscp = fa->fa_dscp; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 06e5572f296f..54984f3170a8 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -64,7 +64,7 @@ __bpf_kfunc int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, info->encap.type = TUNNEL_ENCAP_NONE; } - if (info->key.tun_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)) info->encap.flags |= TUNNEL_ENCAP_FLAG_CSUM; info->encap.sport = encap->sport; diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index a8494f796dca..0abbc413e0fe 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -433,7 +433,7 @@ next_proto: offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); - if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) + if (!ops || !ops->callbacks.gro_receive) goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 3757fd93523f..6701a98d9a9f 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -73,7 +73,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; - tpi->flags = gre_flags_to_tnl_flags(greh->flags); + gre_flags_to_tnl_flags(tpi->flags, greh->flags); hdr_len = gre_calc_hlen(tpi->flags); if (!pskb_may_pull(skb, nhs + hdr_len)) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 207482d30dc7..ab6d0d98dbc3 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -93,6 +93,8 @@ #include <net/ip_fib.h> #include <net/l3mdev.h> #include <net/addrconf.h> +#define CREATE_TRACE_POINTS +#include <trace/events/icmp.h> /* * Build xmit assembly blocks @@ -770,6 +772,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (!fl4.saddr) fl4.saddr = htonl(INADDR_DUMMY); + trace_icmp_send(skb_in, type, code); + icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 717e97a389a8..9bf09de6a2e7 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1842,7 +1842,8 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, - 0, 0, 0); + 0, 0, 0, + RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 3b38610958ee..d4f0eff8b20f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -661,7 +661,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) /* * This will accept the next outstanding connection. */ -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) +struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; @@ -680,7 +680,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) /* Find already established connection */ if (reqsk_queue_empty(queue)) { - long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + long timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ error = -EAGAIN; @@ -692,6 +692,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) goto out_err; } req = reqsk_queue_remove(queue, sk); + arg->is_empty = reqsk_queue_empty(queue); newsk = req->sk; if (sk->sk_protocol == IPPROTO_TCP && @@ -745,7 +746,7 @@ out: out_err: newsk = NULL; req = NULL; - *err = error; + arg->err = error; goto out; } EXPORT_SYMBOL(inet_csk_accept); @@ -1121,25 +1122,34 @@ drop: inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } -static void reqsk_queue_hash_req(struct request_sock *req, +static bool reqsk_queue_hash_req(struct request_sock *req, unsigned long timeout) { + bool found_dup_sk = false; + + if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk)) + return false; + + /* The timer needs to be setup after a successful insertion. */ timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); refcount_set(&req->rsk_refcnt, 2 + 1); + return true; } -void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout) { - reqsk_queue_hash_req(req, timeout); + if (!reqsk_queue_hash_req(req, timeout)) + return false; + inet_csk_reqsk_queue_added(sk); + return true; } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 7adace541fe2..9712cdb8087c 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1383,6 +1383,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb, req.sdiag_family = AF_UNSPEC; /* compatibility */ req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type); req.idiag_ext = rc->idiag_ext; + req.pad = 0; req.idiag_states = rc->idiag_states; req.id = rc->id; @@ -1398,6 +1399,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, req.sdiag_family = rc->idiag_family; req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type); req.idiag_ext = rc->idiag_ext; + req.pad = 0; req.idiag_states = rc->idiag_states; req.id = rc->id; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c88c9034d630..faaec92a46ac 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -175,7 +175,7 @@ static void fqdir_free_fn(struct work_struct *work) } } -static DECLARE_WORK(fqdir_free_work, fqdir_free_fn); +static DECLARE_DELAYED_WORK(fqdir_free_work, fqdir_free_fn); static void fqdir_work_fn(struct work_struct *work) { @@ -184,7 +184,7 @@ static void fqdir_work_fn(struct work_struct *work) rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL); if (llist_add(&fqdir->free_list, &fqdir_free_list)) - queue_work(system_wq, &fqdir_free_work); + queue_delayed_work(system_wq, &fqdir_free_work, HZ); } int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index cf88eca5f1b4..48d0d494185b 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -565,7 +565,8 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, if (likely(inet_match(net, sk2, acookie, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); - if (twsk_unique(sk, sk2, twp)) + if (sk->sk_protocol == IPPROTO_TCP && + tcp_twsk_unique(sk, sk2, twp)) break; } goto not_unique; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index e8de45d34d56..e28075f0006e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -264,14 +264,18 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) EXPORT_SYMBOL_GPL(__inet_twsk_schedule); /* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) +void inet_twsk_purge(struct inet_hashinfo *hashinfo) { + struct inet_ehash_bucket *head = &hashinfo->ehash[0]; + unsigned int ehash_mask = hashinfo->ehash_mask; struct hlist_nulls_node *node; unsigned int slot; struct sock *sk; - for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { - struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; + for (slot = 0; slot <= ehash_mask; slot++, head++) { + if (hlist_nulls_empty(&head->chain)) + continue; + restart_rcu: cond_resched(); rcu_read_lock(); @@ -283,15 +287,13 @@ restart: TCPF_NEW_SYN_RECV)) continue; - if (sk->sk_family != family || - refcount_read(&sock_net(sk)->ns.count)) + if (refcount_read(&sock_net(sk)->ns.count)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely(sk->sk_family != family || - refcount_read(&sock_net(sk)->ns.count))) { + if (refcount_read(&sock_net(sk)->ns.count)) { sock_gen_put(sk); goto restart; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fb947d1613fe..08e2c92e25ab 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -580,7 +580,6 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &dist_min, }, - { } }; /* secret interval has been deprecated */ @@ -593,7 +592,6 @@ static struct ctl_table ip4_frags_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; static int __net_init ip4_frags_ns_ctl_register(struct net *net) @@ -632,7 +630,7 @@ err_alloc: static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->ipv4.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.frags_hdr); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 57ddcd8c62f6..ba205473522e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -265,6 +265,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; + IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -272,12 +273,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int ver; int len; + ip_tunnel_flags_copy(flags, tpi->flags); + itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, @@ -287,8 +290,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, - tpi->flags | TUNNEL_KEY, + __set_bit(IP_TUNNEL_KEY_BIT, flags); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } @@ -312,10 +315,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; - __be16 flags; - tpi->flags |= TUNNEL_KEY; - flags = tpi->flags; + __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, @@ -338,7 +340,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + info->key.tun_flags); info->options_len = sizeof(*md); } @@ -381,10 +384,13 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { - __be16 flags; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; - flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + ip_tunnel_flags_and(flags, tpi->flags, flags); + tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) @@ -464,12 +470,15 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags = tunnel->parms.o_flags; + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -483,10 +492,10 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; - __be16 flags; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -500,14 +509,19 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, goto err_free_skb; /* Push Tunnel header. */ - if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto err_free_skb; - flags = tun_info->key.tun_flags & - (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); + gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -521,6 +535,7 @@ err_free_skb: static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; @@ -536,7 +551,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; @@ -589,8 +604,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; } - gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + gre_build_header(skb, 8, flags, proto, 0, + htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -664,7 +680,8 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, tnl_params = &tunnel->parms.iph; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); @@ -706,7 +723,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); - tunnel->parms.o_flags &= ~TUNNEL_SEQ; + __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, @@ -721,7 +738,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; } - tunnel->parms.o_flags &= ~TUNNEL_KEY; + __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; @@ -744,7 +761,8 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } - if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) @@ -762,7 +780,6 @@ free_skb: static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); - __be16 flags; int len; len = tunnel->tun_hlen; @@ -776,12 +793,11 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) dev->needed_headroom += len; if (set_mtu) - dev->mtu = max_t(int, dev->mtu - len, 68); - - flags = tunnel->parms.o_flags; + WRITE_ONCE(dev->mtu, max_t(int, dev->mtu - len, 68)); - if (flags & TUNNEL_SEQ || - (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || + (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { @@ -790,20 +806,29 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) } } -static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, +static int ipgre_tunnel_ctl(struct net_device *dev, + struct ip_tunnel_parm_kern *p, int cmd) { + __be16 i_flags, o_flags; int err; + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + i_flags = ip_tunnel_flags_to_be16(p->i_flags); + o_flags = ip_tunnel_flags_to_be16(p->o_flags); + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || - ((p->i_flags | p->o_flags) & (GRE_VERSION | GRE_ROUTING))) + ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } - p->i_flags = gre_flags_to_tnl_flags(p->i_flags); - p->o_flags = gre_flags_to_tnl_flags(p->o_flags); + gre_flags_to_tnl_flags(p->i_flags, i_flags); + gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) @@ -812,15 +837,18 @@ static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); - t->parms.i_flags = p->i_flags; - t->parms.o_flags = p->o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } - p->i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); - p->o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); + ip_tunnel_flags_from_be16(p->i_flags, i_flags); + o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); + ip_tunnel_flags_from_be16(p->o_flags, o_flags); + return 0; } @@ -960,7 +988,6 @@ static void ipgre_tunnel_setup(struct net_device *dev) static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; - __be16 flags; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); @@ -972,14 +999,13 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= GRE_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE_FEATURES; - flags = tunnel->parms.o_flags; - /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ - if (flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; - if (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE) + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && + tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1136,7 +1162,7 @@ static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); @@ -1152,10 +1178,12 @@ static int ipgre_netlink_parms(struct net_device *dev, parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) - parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS])); + gre_flags_to_tnl_flags(parms->i_flags, + nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) - parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS])); + gre_flags_to_tnl_flags(parms->o_flags, + nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); @@ -1203,7 +1231,7 @@ static int ipgre_netlink_parms(struct net_device *dev, static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); @@ -1362,7 +1390,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1380,7 +1408,7 @@ static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1399,8 +1427,8 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); @@ -1415,8 +1443,8 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); @@ -1428,8 +1456,8 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); @@ -1444,8 +1472,8 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (err < 0) return err; - t->parms.i_flags = p.i_flags; - t->parms.o_flags = p.o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } @@ -1501,8 +1529,10 @@ static size_t ipgre_get_size(const struct net_device *dev) static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm *p = &t->parms; - __be16 o_flags = p->o_flags; + struct ip_tunnel_parm_kern *p = &t->parms; + IP_TUNNEL_DECLARE_FLAGS(o_flags); + + ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -1550,7 +1580,7 @@ static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) - t->parms.o_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 0e4bd528428e..bccef2fcf620 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -56,17 +56,13 @@ static unsigned int ip_tunnel_hash(__be32 key, __be32 remote) IP_TNL_HASH_BITS); } -static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, - __be16 flags, __be32 key) +static bool ip_tunnel_key_match(const struct ip_tunnel_parm_kern *p, + const unsigned long *flags, __be32 key) { - if (p->i_flags & TUNNEL_KEY) { - if (flags & TUNNEL_KEY) - return key == p->i_key; - else - /* key expected, none present */ - return false; - } else - return !(flags & TUNNEL_KEY); + if (!test_bit(IP_TUNNEL_KEY_BIT, flags)) + return !test_bit(IP_TUNNEL_KEY_BIT, p->i_flags); + + return test_bit(IP_TUNNEL_KEY_BIT, p->i_flags) && p->i_key == key; } /* Fallback tunnel: no source, no destination, no key, no options @@ -81,7 +77,7 @@ static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, Given src, dst and key, find appropriate for input tunnel. */ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, - int link, __be16 flags, + int link, const unsigned long *flags, __be32 remote, __be32 local, __be32 key) { @@ -143,7 +139,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, } hlist_for_each_entry_rcu(t, head, hash_node) { - if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) || + if ((!test_bit(IP_TUNNEL_NO_KEY_BIT, flags) && + t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) @@ -171,7 +168,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, EXPORT_SYMBOL_GPL(ip_tunnel_lookup); static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { unsigned int h; __be32 remote; @@ -182,7 +179,8 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, else remote = 0; - if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + if (!test_bit(IP_TUNNEL_KEY_BIT, parms->i_flags) && + test_bit(IP_TUNNEL_VTI_BIT, parms->i_flags)) i_key = 0; h = ip_tunnel_hash(i_key, remote); @@ -206,17 +204,19 @@ static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) } static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, int type) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; + IP_TUNNEL_DECLARE_FLAGS(flags); __be32 key = parms->i_key; - __be16 flags = parms->i_flags; int link = parms->link; struct ip_tunnel *t = NULL; struct hlist_head *head = ip_bucket(itn, parms); + ip_tunnel_flags_copy(flags, parms->i_flags); + hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && @@ -230,7 +230,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, static struct net_device *__ip_tunnel_create(struct net *net, const struct rtnl_link_ops *ops, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { int err; struct ip_tunnel *tunnel; @@ -326,7 +326,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) static struct ip_tunnel *ip_tunnel_create(struct net *net, struct ip_tunnel_net *itn, - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { struct ip_tunnel *nt; struct net_device *dev; @@ -386,15 +386,15 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, } #endif - if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || - ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != + test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } - if (tunnel->parms.i_flags&TUNNEL_SEQ) { - if (!(tpi->flags&TUNNEL_SEQ) || + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { + if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); @@ -638,7 +638,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) df = htons(IP_DF); if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, key->u.ipv4.dst, true)) { @@ -871,7 +871,7 @@ EXPORT_SYMBOL_GPL(ip_tunnel_xmit); static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel *t, struct net_device *dev, - struct ip_tunnel_parm *p, + struct ip_tunnel_parm_kern *p, bool set_mtu, __u32 fwmark) { @@ -897,13 +897,14 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) - dev->mtu = mtu; + WRITE_ONCE(dev->mtu, mtu); } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); } -int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd) { int err = 0; struct ip_tunnel *t = netdev_priv(dev); @@ -927,10 +928,10 @@ int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) goto done; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); - if (!(p->i_flags & VTI_ISVTI)) { - if (!(p->i_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_VTI_BIT, p->i_flags)) { + if (!test_bit(IP_TUNNEL_KEY_BIT, p->i_flags)) p->i_key = 0; - if (!(p->o_flags & TUNNEL_KEY)) + if (!test_bit(IP_TUNNEL_KEY_BIT, p->o_flags)) p->o_key = 0; } @@ -1005,16 +1006,58 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ctl); +bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp, + const void __user *data) +{ + struct ip_tunnel_parm p; + + if (copy_from_user(&p, data, sizeof(p))) + return false; + + strscpy(kp->name, p.name); + kp->link = p.link; + ip_tunnel_flags_from_be16(kp->i_flags, p.i_flags); + ip_tunnel_flags_from_be16(kp->o_flags, p.o_flags); + kp->i_key = p.i_key; + kp->o_key = p.o_key; + memcpy(&kp->iph, &p.iph, min(sizeof(kp->iph), sizeof(p.iph))); + + return true; +} +EXPORT_SYMBOL_GPL(ip_tunnel_parm_from_user); + +bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp) +{ + struct ip_tunnel_parm p; + + if (!ip_tunnel_flags_is_be16_compat(kp->i_flags) || + !ip_tunnel_flags_is_be16_compat(kp->o_flags)) + return false; + + memset(&p, 0, sizeof(p)); + + strscpy(p.name, kp->name); + p.link = kp->link; + p.i_flags = ip_tunnel_flags_to_be16(kp->i_flags); + p.o_flags = ip_tunnel_flags_to_be16(kp->o_flags); + p.i_key = kp->i_key; + p.o_key = kp->o_key; + memcpy(&p.iph, &kp->iph, min(sizeof(p.iph), sizeof(kp->iph))); + + return !copy_to_user(data, &p, sizeof(p)); +} +EXPORT_SYMBOL_GPL(ip_tunnel_parm_to_user); + int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { - struct ip_tunnel_parm p; + struct ip_tunnel_parm_kern p; int err; - if (copy_from_user(&p, data, sizeof(p))) + if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, cmd); - if (!err && copy_to_user(data, &p, sizeof(p))) + if (!err && !ip_tunnel_parm_to_user(data, &p)) return -EFAULT; return err; } @@ -1039,7 +1082,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) new_mtu = max_mtu; } - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); @@ -1077,7 +1120,7 @@ struct net *ip_tunnel_get_link_net(const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - return tunnel->net; + return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip_tunnel_get_link_net); @@ -1093,7 +1136,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname) { struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id); - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; unsigned int i; itn->rtnl_link_ops = ops; @@ -1171,7 +1214,7 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark) + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *nt; struct net *net = dev_net(dev); @@ -1225,7 +1268,7 @@ err_register_netdevice: EXPORT_SYMBOL_GPL(ip_tunnel_newlink); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm *p, __u32 fwmark) + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct ip_tunnel *t; struct ip_tunnel *tunnel = netdev_priv(dev); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 80ccd6661aa3..a3676155be78 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -125,6 +125,7 @@ EXPORT_SYMBOL_GPL(__iptunnel_pull_header); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags) { + IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; struct metadata_dst *res; struct ip_tunnel_info *dst, *src; @@ -144,10 +145,10 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, sizeof(struct in6_addr)); else dst->key.u.ipv4.dst = src->key.u.ipv4.src; - dst->key.tun_flags = src->key.tun_flags; + ip_tunnel_flags_copy(dst->key.tun_flags, src->key.tun_flags); dst->mode = src->mode | IP_TUNNEL_INFO_TX; ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src), - src->options_len, 0); + src->options_len, tun_flags); return res; } @@ -497,7 +498,7 @@ static int ip_tun_parse_opts_geneve(struct nlattr *attr, opt->opt_class = nla_get_be16(attr); attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE]; opt->type = nla_get_u8(attr); - info->key.tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); } return sizeof(struct geneve_opt) + data_len; @@ -525,7 +526,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr, attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; md->gbp = nla_get_u32(attr); md->gbp &= VXLAN_GBP_MASK; - info->key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct vxlan_metadata); @@ -574,7 +575,7 @@ static int ip_tun_parse_opts_erspan(struct nlattr *attr, set_hwid(&md->u.md2, nla_get_u8(attr)); } - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct erspan_metadata); @@ -585,7 +586,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, { int err, rem, opt_len, opts_len = 0; struct nlattr *nla; - __be16 type = 0; + u32 type = 0; if (!attr) return 0; @@ -598,7 +599,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) { switch (nla_type(nla)) { case LWTUNNEL_IP_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len, extack); @@ -607,7 +608,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, opts_len += opt_len; if (opts_len > IP_TUNNEL_OPTS_MAX) return -EINVAL; - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; case LWTUNNEL_IP_OPTS_VXLAN: if (type) @@ -617,7 +618,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case LWTUNNEL_IP_OPTS_ERSPAN: if (type) @@ -627,7 +628,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; default: return -EINVAL; @@ -705,10 +706,16 @@ static int ip_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); - if (tb[LWTUNNEL_IP_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + + ip_tunnel_flags_from_be16(flags, + nla_get_be16(tb[LWTUNNEL_IP_FLAGS])); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX; tun_info->options_len = opt_len; @@ -812,18 +819,18 @@ static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type, struct nlattr *nest; int err = 0; - if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(tun_info->key.tun_flags)) return 0; nest = nla_nest_start_noflag(skb, type); if (!nest) return -ENOMEM; - if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_geneve(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT) + else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_vxlan(skb, tun_info); - else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT) + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_erspan(skb, tun_info); if (err) { @@ -846,7 +853,8 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info)) return -ENOMEM; @@ -857,11 +865,11 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) { int opt_len; - if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + if (!ip_tunnel_is_options_present(info->key.tun_flags)) return 0; opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */ - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { struct geneve_opt *opt; int offset = 0; @@ -874,10 +882,10 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) /* OPT_GENEVE_DATA */ offset += sizeof(*opt) + opt->length * 4; } - } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_VXLAN */ + nla_total_size(4); /* OPT_VXLAN_GBP */ - } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { struct erspan_metadata *md = ip_tunnel_info_opts(info); opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_ERSPAN */ @@ -984,10 +992,17 @@ static int ip6_tun_build_state(struct net *net, struct nlattr *attr, if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); - if (tb[LWTUNNEL_IP6_FLAGS]) - tun_info->key.tun_flags |= - (nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) & - ~TUNNEL_OPTIONS_PRESENT); + if (tb[LWTUNNEL_IP6_FLAGS]) { + IP_TUNNEL_DECLARE_FLAGS(flags); + __be16 data; + + data = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]); + ip_tunnel_flags_from_be16(flags, data); + ip_tunnel_clear_options_present(flags); + + ip_tunnel_flags_or(tun_info->key.tun_flags, + tun_info->key.tun_flags, flags); + } tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; tun_info->options_len = opt_len; @@ -1008,7 +1023,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) || + nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, + ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info)) return -ENOMEM; @@ -1116,7 +1132,7 @@ bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], EXPORT_SYMBOL_GPL(ip_tunnel_netlink_encap_parms); void ip_tunnel_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms) + struct ip_tunnel_parm_kern *parms) { if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); @@ -1139,8 +1155,12 @@ void ip_tunnel_netlink_parms(struct nlattr *data[], if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); - if (data[IFLA_IPTUN_FLAGS]) - parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + if (data[IFLA_IPTUN_FLAGS]) { + __be16 flags; + + flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); + ip_tunnel_flags_from_be16(parms->i_flags, flags); + } if (data[IFLA_IPTUN_PROTO]) parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index ee587adb169f..14536da9f5dc 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -51,8 +51,11 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -167,7 +170,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parms = &tunnel->parms; + struct ip_tunnel_parm_kern *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int pkt_len = skb->len; @@ -322,8 +325,11 @@ static int vti4_err(struct sk_buff *skb, u32 info) const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; @@ -373,8 +379,9 @@ static int vti4_err(struct sk_buff *skb, u32 info) } static int -vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err = 0; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { @@ -383,20 +390,26 @@ vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) return -EINVAL; } - if (!(p->i_flags & GRE_KEY)) + if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || + !ip_tunnel_flags_is_be16_compat(p->o_flags)) + return -EOVERFLOW; + + if (!(ip_tunnel_flags_to_be16(p->i_flags) & GRE_KEY)) p->i_key = 0; - if (!(p->o_flags & GRE_KEY)) + if (!(ip_tunnel_flags_to_be16(p->o_flags) & GRE_KEY)) p->o_key = 0; - p->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, flags); + ip_tunnel_flags_copy(p->i_flags, flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p->i_flags |= GRE_KEY; - p->o_flags |= GRE_KEY; + ip_tunnel_flags_from_be16(flags, GRE_KEY); + ip_tunnel_flags_or(p->i_flags, p->i_flags, flags); + ip_tunnel_flags_or(p->o_flags, p->o_flags, flags); } return 0; } @@ -531,7 +544,7 @@ static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], } static void vti_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -541,7 +554,7 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; - parms->i_flags = VTI_ISVTI; + __set_bit(IP_TUNNEL_VTI_BIT, parms->i_flags); if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); @@ -566,7 +579,7 @@ static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip_tunnel_parm parms; + struct ip_tunnel_parm_kern parms; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); @@ -578,8 +591,8 @@ static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; - struct ip_tunnel_parm p; vti_netlink_parms(data, &p, &fwmark); return ip_tunnel_changelink(dev, tb, &p, fwmark); @@ -606,7 +619,7 @@ static size_t vti_get_size(const struct net_device *dev) static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm *p = &t->parms; + struct ip_tunnel_parm_kern *p = &t->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) || nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) || diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index f2696eaadbe6..923a2ef68c2f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -130,13 +130,16 @@ static int ipip_err(struct sk_buff *skb, u32 info) struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); const struct iphdr *iph = (const struct iphdr *)skb->data; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; int err = 0; - t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->daddr, iph->saddr, 0); + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + + t = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, + iph->saddr, 0); if (!t) { err = -ENOENT; goto out; @@ -213,13 +216,16 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; + __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); + iph = ip_hdr(skb); - tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, - iph->saddr, iph->daddr, 0); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, + iph->daddr, 0); if (tunnel) { const struct tnl_ptk_info *tpi; @@ -238,7 +244,9 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (tunnel->collect_md) { - tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); + ip_tunnel_flags_zero(flags); + + tun_dst = ip_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) return 0; ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info); @@ -330,7 +338,7 @@ static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto) } static int -ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || @@ -340,7 +348,8 @@ ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) } p->i_key = p->o_key = 0; - p->i_flags = p->o_flags = 0; + ip_tunnel_flags_zero(p->i_flags); + ip_tunnel_flags_zero(p->o_flags); return ip_tunnel_ctl(dev, p, cmd); } @@ -405,8 +414,8 @@ static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], } static void ipip_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, bool *collect_md, - __u32 *fwmark) + struct ip_tunnel_parm_kern *parms, + bool *collect_md, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -432,8 +441,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; __u32 fwmark = 0; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { @@ -452,8 +461,8 @@ static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; bool collect_md; __u32 fwmark = t->fwmark; @@ -510,7 +519,7 @@ static size_t ipip_get_size(const struct net_device *dev) static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parm = &tunnel->parms; + struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index fd5c01c8489f..6c750bd13dd8 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -441,7 +441,7 @@ static bool ipmr_init_vif_indev(const struct net_device *dev) static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { struct net_device *tunnel_dev, *new_dev; - struct ip_tunnel_parm p = { }; + struct ip_tunnel_parm_kern p = { }; int err; tunnel_dev = __dev_get_by_name(net, "tunl0"); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index b9062f4552ac..3ab908b74795 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -44,7 +44,7 @@ static int iptable_filter_table_init(struct net *net) return -ENOMEM; /* Entry 1 is the FORWARD hook */ ((struct ipt_standard *)repl->entries)[1].target.verdict = - forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; + forward ? -NF_ACCEPT - 1 : NF_DROP - 1; err = ipt_register_table(net, &packet_filter, repl, filter_ops); kfree(repl); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 4d42d0756fd7..a5db7c67d61b 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = { static int __init iptable_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv4_table, - iptable_nat_table_init); + int ret; + /* net->gen->ptr[iptable_nat_net_id] must be allocated + * before calling iptable_nat_table_init(). + */ + ret = register_pernet_subsys(&iptable_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&iptable_nat_net_ops); - if (ret < 0) { - xt_unregister_template(&nf_nat_ipv4_table); - return ret; - } + ret = xt_register_template(&nf_nat_ipv4_table, + iptable_nat_table_init); + if (ret < 0) + unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { - unregister_pernet_subsys(&iptable_nat_net_ops); xt_unregister_template(&nf_nat_ipv4_table); + unregister_pernet_subsys(&iptable_nat_net_ops); } module_init(iptable_nat_init); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 535856b0f0ed..6b9787ee8601 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -888,9 +888,10 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { - p->id = nhg->nh_entries[i].nh->id; - p->weight = nhg->nh_entries[i].weight - 1; - p += 1; + *p++ = (struct nexthop_grp) { + .id = nhg->nh_entries[i].nh->id, + .weight = nhg->nh_entries[i].weight - 1, + }; } if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 914bc9c35cc7..6c4664c681ca 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -33,6 +33,7 @@ #include <net/protocol.h> #include <net/tcp.h> #include <net/mptcp.h> +#include <net/proto_memory.h> #include <net/udp.h> #include <net/udplite.h> #include <linux/bottom_half.h> diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3fcf084fbda5..990912fa18e8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -106,9 +106,6 @@ #include "fib_lookup.h" -#define RT_FL_TOS(oldflp4) \ - ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) - #define RT_GC_TIMEOUT (300*HZ) #define DEFAULT_MIN_PMTU (512 + 20 + 20) @@ -499,15 +496,6 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) } EXPORT_SYMBOL(__ip_select_ident); -static void ip_rt_fix_tos(struct flowi4 *fl4) -{ - __u8 tos = RT_FL_TOS(fl4); - - fl4->flowi4_tos = tos & IPTOS_RT_MASK; - if (tos & RTO_ONLINK) - fl4->flowi4_scope = RT_SCOPE_LINK; -} - static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, __u8 tos, u8 prot, u32 mark, @@ -1275,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = RT_TOS(iph->tos), + .flowi4_tos = iph->tos & IPTOS_RT_MASK, .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, @@ -2631,7 +2619,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; - ip_rt_fix_tos(fl4); + fl4->flowi4_tos &= IPTOS_RT_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); @@ -2880,9 +2868,9 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, - struct rtable *rt, u32 table_id, struct flowi4 *fl4, - struct sk_buff *skb, u32 portid, u32 seq, - unsigned int flags) + struct rtable *rt, u32 table_id, dscp_t dscp, + struct flowi4 *fl4, struct sk_buff *skb, u32 portid, + u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; @@ -2898,7 +2886,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; - r->rtm_tos = fl4 ? fl4->flowi4_tos : 0; + r->rtm_tos = inet_dscp_to_dsfield(dscp); r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; @@ -3048,7 +3036,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, - table_id, NULL, skb, + table_id, 0, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) @@ -3344,7 +3332,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fri.tb_id = table_id; fri.dst = res.prefix; fri.dst_len = res.prefixlen; - fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos); + fri.dscp = res.dscp; fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; @@ -3371,8 +3359,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { - err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, + err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4, + skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) @@ -3502,7 +3490,6 @@ static struct ctl_table ipv4_route_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static const char ipv4_route_flush_procname[] = "flush"; @@ -3536,7 +3523,6 @@ static struct ctl_table ipv4_route_netns_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { }, }; static __net_init int sysctl_route_net_init(struct net *net) @@ -3554,16 +3540,14 @@ static __net_init int sysctl_route_net_init(struct net *net) /* Don't export non-whitelisted sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { - if (tbl[0].procname != ipv4_route_flush_procname) { - tbl[0].procname = NULL; + if (tbl[0].procname != ipv4_route_flush_procname) table_size = 0; - } } /* Update the variables to point into the current struct net * except for the first element flush */ - for (i = 1; i < ARRAY_SIZE(ipv4_route_netns_table) - 1; i++) + for (i = 1; i < table_size; i++) tbl[i].data += (void *)net - (void *)&init_net; } tbl[0].extra1 = net; @@ -3583,7 +3567,7 @@ err_dup: static __net_exit void sysctl_route_net_exit(struct net *net) { - struct ctl_table *tbl; + const struct ctl_table *tbl; tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 500f665f98cb..b61d36810fe3 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -462,7 +462,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) } /* Try to redo what tcp_v4_send_synack did. */ - req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? : + dst_metric(&rt->dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 7e4f16a7dcc1..162a0a3b6ba5 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -575,7 +575,6 @@ static struct ctl_table ipv4_table[] = { .extra1 = &sysctl_fib_sync_mem_min, .extra2 = &sysctl_fib_sync_mem_max, }, - { } }; static struct ctl_table ipv4_net_table[] = { @@ -1502,11 +1501,11 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, }, - { } }; static __net_init int ipv4_sysctl_init_net(struct net *net) { + size_t table_size = ARRAY_SIZE(ipv4_net_table); struct ctl_table *table; table = ipv4_net_table; @@ -1517,7 +1516,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!table) goto err_alloc; - for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { + for (i = 0; i < table_size; i++) { if (table[i].data) { /* Update the variables to point into * the current struct net @@ -1533,7 +1532,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) } net->ipv4.ipv4_hdr = register_net_sysctl_sz(net, "net/ipv4", table, - ARRAY_SIZE(ipv4_net_table)); + table_size); if (!net->ipv4.ipv4_hdr) goto err_reg; @@ -1554,7 +1553,7 @@ err_alloc: static __net_exit void ipv4_sysctl_exit_net(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; kfree(net->ipv4.sysctl_local_reserved_ports); table = net->ipv4.ipv4_hdr->ctl_table_arg; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77ee1eda3fd8..2edbd5b181e2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -272,13 +272,16 @@ #include <net/inet_common.h> #include <net/tcp.h> #include <net/mptcp.h> +#include <net/proto_memory.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> +#include <net/rstreason.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> +#include <net/hotdata.h> #include <net/rps.h> /* Track pending CMSGs. */ @@ -290,6 +293,9 @@ enum { DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); +DEFINE_PER_CPU(u32, tcp_tw_isn); +EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); + long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); @@ -592,7 +598,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask |= EPOLLOUT | EPOLLWRNORM; } - /* This barrier is coupled with smp_wmb() in tcp_reset() */ + /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) @@ -1187,7 +1193,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i >= READ_ONCE(sysctl_max_skb_frags)) { + if (i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1419,8 +1425,6 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) struct sk_buff *skb; int copied = 0, err = 0; - /* XXX -- need to support SO_PEEK_OFF */ - skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) @@ -1724,7 +1728,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); - tcp_sk(sk)->window_clamp = val; + WRITE_ONCE(tcp_sk(sk)->window_clamp, val); } return 0; } @@ -2331,6 +2335,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; + u32 peek_offset = 0; u32 urg_hole = 0; err = -ENOTCONN; @@ -2364,7 +2369,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, seq = &tp->copied_seq; if (flags & MSG_PEEK) { - peek_seq = tp->copied_seq; + peek_offset = max(sk_peek_offset(sk, flags), 0); + peek_seq = tp->copied_seq + peek_offset; seq = &peek_seq; } @@ -2467,11 +2473,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, } if ((flags & MSG_PEEK) && - (peek_seq - copied - urg_hole != tp->copied_seq)) { + (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); - peek_seq = tp->copied_seq; + peek_seq = tp->copied_seq + peek_offset; } continue; @@ -2512,7 +2518,10 @@ found_ok_skb: WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; - + if (flags & MSG_PEEK) + sk_peek_offset_fwd(sk, used); + else + sk_peek_offset_bwd(sk, used); tcp_rcv_space_adjust(sk); skip_copy: @@ -2751,7 +2760,15 @@ static bool tcp_too_many_orphans(int shift) READ_ONCE(sysctl_tcp_max_orphans); } -bool tcp_check_oom(struct sock *sk, int shift) +static bool tcp_out_of_memory(const struct sock *sk) +{ + if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && + sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) + return true; + return false; +} + +bool tcp_check_oom(const struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; @@ -2812,7 +2829,8 @@ void __tcp_close(struct sock *sk, long timeout) /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, sk->sk_allocation); + tcp_send_active_reset(sk, sk->sk_allocation, + SK_RST_REASON_NOT_SPECIFIED); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -2886,7 +2904,8 @@ adjudge_to_death: struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { @@ -2904,7 +2923,8 @@ adjudge_to_death: if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { @@ -3008,7 +3028,7 @@ int tcp_disconnect(struct sock *sk, int flags) /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any()); + tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_NOT_SPECIFIED); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); @@ -3017,6 +3037,7 @@ int tcp_disconnect(struct sock *sk, int flags) __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); + sk_set_peek_off(sk, -1); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); @@ -3386,7 +3407,7 @@ int tcp_set_window_clamp(struct sock *sk, int val) if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; - tp->window_clamp = 0; + WRITE_ONCE(tp->window_clamp, 0); } else { u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? @@ -3395,7 +3416,7 @@ int tcp_set_window_clamp(struct sock *sk, int val) if (new_window_clamp == old_window_clamp) return 0; - tp->window_clamp = new_window_clamp; + WRITE_ONCE(tp->window_clamp, new_window_clamp); if (new_window_clamp < old_window_clamp) { /* need to apply the reserved mem provisioning only * when shrinking the window clamp @@ -4064,7 +4085,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: - val = tp->window_clamp; + val = READ_ONCE(tp->window_clamp); break; case TCP_INFO: { struct tcp_info info; @@ -4349,6 +4370,9 @@ zerocopy_rcv_out: return err; } + case TCP_IS_MPTCP: + val = 0; + break; default: return -ENOPROTOOPT; } @@ -4549,6 +4573,13 @@ int tcp_abort(struct sock *sk, int err) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); + /* Avoid closing the same socket twice. */ + if (sk->sk_state == TCP_CLOSE) { + if (!has_current_bpf_ctx()) + release_sock(sk); + return -ENOENT; + } + if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); @@ -4558,19 +4589,13 @@ int tcp_abort(struct sock *sk, int err) local_bh_disable(); bh_lock_sock(sk); - if (!sock_flag(sk, SOCK_DEAD)) { - WRITE_ONCE(sk->sk_err, err); - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - sk_error_report(sk); - if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC); - tcp_done(sk); - } + if (tcp_need_reset(sk->sk_state)) + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); + tcp_done_with_error(sk, err); bh_unlock_sock(sk); local_bh_enable(); - tcp_write_queue_purge(sk); if (!has_current_bpf_ctx()) release_sock(sk); return 0; @@ -4655,16 +4680,16 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); - CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache); - CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 105); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_clock_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); @@ -4677,7 +4702,11 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76); + + /* 32bit arches with 8byte alignment on u64 fields might need padding + * before tcp_clock_cache. + */ + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4); /* RX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 09c0fa6756b7..9171e1066808 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -266,32 +266,49 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head) kfree_sensitive(key); } -void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +static void tcp_ao_info_free_rcu(struct rcu_head *head) { - struct tcp_ao_info *ao; + struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu); struct tcp_ao_key *key; struct hlist_node *n; + hlist_for_each_entry_safe(key, n, &ao->head, node) { + hlist_del(&key->node); + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); + } + kfree(ao); + static_branch_slow_dec_deferred(&tcp_ao_needed); +} + +static void tcp_ao_sk_omem_free(struct sock *sk, struct tcp_ao_info *ao) +{ + size_t total_ao_sk_mem = 0; + struct tcp_ao_key *key; + + hlist_for_each_entry(key, &ao->head, node) + total_ao_sk_mem += tcp_ao_sizeof_key(key); + atomic_sub(total_ao_sk_mem, &sk->sk_omem_alloc); +} + +void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +{ + struct tcp_ao_info *ao; + if (twsk) { ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1); - tcp_twsk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_twsk(sk)->ao_info, NULL); } else { ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1); - tcp_sk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_sk(sk)->ao_info, NULL); } if (!ao || !refcount_dec_and_test(&ao->refcnt)) return; - hlist_for_each_entry_safe(key, n, &ao->head, node) { - hlist_del_rcu(&key->node); - if (!twsk) - atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); - call_rcu(&key->rcu, tcp_ao_key_free_rcu); - } - - kfree_rcu(ao, rcu); - static_branch_slow_dec_deferred(&tcp_ao_needed); + if (!twsk) + tcp_ao_sk_omem_free(sk, ao); + call_rcu(&ao->rcu, tcp_ao_info_free_rcu); } void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp) diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 05dc2d05bc7c..760941e55153 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1024,7 +1024,7 @@ static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) bbr_update_gains(sk); } -__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs) +__bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw; @@ -1156,8 +1156,6 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { }; BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, bbr_init) BTF_ID_FLAGS(func, bbr_main) BTF_ID_FLAGS(func, bbr_sndbuf_expand) @@ -1166,8 +1164,6 @@ BTF_ID_FLAGS(func, bbr_cwnd_event) BTF_ID_FLAGS(func, bbr_ssthresh) BTF_ID_FLAGS(func, bbr_min_tso_segs) BTF_ID_FLAGS(func, bbr_set_state) -#endif -#endif BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 44869ea089e3..5dbed91c6178 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -486,16 +486,12 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { }; BTF_KFUNCS_START(tcp_cubic_check_kfunc_ids) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, cubictcp_init) BTF_ID_FLAGS(func, cubictcp_recalc_ssthresh) BTF_ID_FLAGS(func, cubictcp_cong_avoid) BTF_ID_FLAGS(func, cubictcp_state) BTF_ID_FLAGS(func, cubictcp_cwnd_event) BTF_ID_FLAGS(func, cubictcp_acked) -#endif -#endif BTF_KFUNCS_END(tcp_cubic_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index b004280855f8..8a45a4aea933 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -272,16 +272,12 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { }; BTF_KFUNCS_START(tcp_dctcp_check_kfunc_ids) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, dctcp_init) BTF_ID_FLAGS(func, dctcp_update_alpha) BTF_ID_FLAGS(func, dctcp_cwnd_event) BTF_ID_FLAGS(func, dctcp_ssthresh) BTF_ID_FLAGS(func, dctcp_cwnd_undo) BTF_ID_FLAGS(func, dctcp_state) -#endif -#endif BTF_KFUNCS_END(tcp_dctcp_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1054a440332d..2c52f6dcbd29 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -72,6 +72,7 @@ #include <linux/prefetch.h> #include <net/dst.h> #include <net/tcp.h> +#include <net/proto_memory.h> #include <net/inet_common.h> #include <linux/ipsec.h> #include <asm/unaligned.h> @@ -237,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ if (unlikely(len != icsk->icsk_ack.rcv_mss)) { u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + u8 old_ratio = tcp_sk(sk)->scaling_ratio; do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; + + if (old_ratio != tcp_sk(sk)->scaling_ratio) + WRITE_ONCE(tcp_sk(sk)->window_clamp, + tcp_win_from_space(sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -563,19 +569,20 @@ static void tcp_init_buffer_space(struct sock *sk) maxwin = tcp_full_space(sk); if (tp->window_clamp >= maxwin) { - tp->window_clamp = maxwin; + WRITE_ONCE(tp->window_clamp, maxwin); if (tcp_app_win && maxwin > 4 * tp->advmss) - tp->window_clamp = max(maxwin - - (maxwin >> tcp_app_win), - 4 * tp->advmss); + WRITE_ONCE(tp->window_clamp, + max(maxwin - (maxwin >> tcp_app_win), + 4 * tp->advmss)); } /* Force reservation of one segment. */ if (tcp_app_win && tp->window_clamp > 2 * tp->advmss && tp->window_clamp + tp->advmss > maxwin) - tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss); + WRITE_ONCE(tp->window_clamp, + max(2 * tp->advmss, maxwin - tp->advmss)); tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; @@ -773,7 +780,8 @@ void tcp_rcv_space_adjust(struct sock *sk) WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */ - tp->window_clamp = tcp_win_from_space(sk, rcvbuf); + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); } } tp->rcvq_space.space = copied; @@ -911,7 +919,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->rtt_seq = tp->snd_nxt; tp->mdev_max_us = tcp_rto_min_us(sk); - tcp_bpf_rtt(sk); + tcp_bpf_rtt(sk, mrtt_us, srtt); } } else { /* no previous measure. */ @@ -921,7 +929,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; - tcp_bpf_rtt(sk); + tcp_bpf_rtt(sk, mrtt_us, srtt); } tp->srtt_us = max(1U, srtt); } @@ -2126,8 +2134,16 @@ void tcp_clear_retrans(struct tcp_sock *tp) static inline void tcp_init_undo(struct tcp_sock *tp) { tp->undo_marker = tp->snd_una; + /* Retransmission still in flight may cause DSACKs later. */ - tp->undo_retrans = tp->retrans_out ? : -1; + /* First, account for regular retransmits in flight: */ + tp->undo_retrans = tp->retrans_out; + /* Next, account for TLP retransmits in flight: */ + if (tp->tlp_high_seq && tp->tlp_retrans) + tp->undo_retrans++; + /* Finally, avoid 0, because undo_retrans==0 means "can undo now": */ + if (!tp->undo_retrans) + tp->undo_retrans = -1; } static bool tcp_is_rack(const struct sock *sk) @@ -2206,6 +2222,7 @@ void tcp_enter_loss(struct sock *sk) tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; + tp->tlp_high_seq = 0; tcp_ecn_queue_cwr(tp); /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous @@ -2779,13 +2796,37 @@ static void tcp_mtup_probe_success(struct sock *sk) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } +/* Sometimes we deduce that packets have been dropped due to reasons other than + * congestion, like path MTU reductions or failed client TFO attempts. In these + * cases we call this function to retransmit as many packets as cwnd allows, + * without reducing cwnd. Given that retransmits will set retrans_stamp to a + * non-zero value (and may do so in a later calling context due to TSQ), we + * also enter CA_Loss so that we track when all retransmitted packets are ACKed + * and clear retrans_stamp when that happens (to ensure later recurring RTOs + * are using the correct retrans_stamp and don't declare ETIMEDOUT + * prematurely). + */ +static void tcp_non_congestion_loss_retransmit(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (icsk->icsk_ca_state != TCP_CA_Loss) { + tp->high_seq = tp->snd_nxt; + tp->snd_ssthresh = tcp_current_ssthresh(sk); + tp->prior_ssthresh = 0; + tp->undo_marker = 0; + tcp_set_ca_state(sk, TCP_CA_Loss); + } + tcp_xmit_retransmit_queue(sk); +} + /* Do a simple retransmit without using the backoff mechanisms in * tcp_timer. This is used for path mtu discovery. * The socket is already locked here. */ void tcp_simple_retransmit(struct sock *sk) { - const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int mss; @@ -2825,14 +2866,7 @@ void tcp_simple_retransmit(struct sock *sk) * in network, but units changed and effective * cwnd/ssthresh really reduced now. */ - if (icsk->icsk_ca_state != TCP_CA_Loss) { - tp->high_seq = tp->snd_nxt; - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->prior_ssthresh = 0; - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Loss); - } - tcp_xmit_retransmit_queue(sk); + tcp_non_congestion_loss_retransmit(sk); } EXPORT_SYMBOL(tcp_simple_retransmit); @@ -3057,7 +3091,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, return; if (tcp_try_undo_dsack(sk)) - tcp_try_keep_open(sk); + tcp_try_to_open(sk, flag); tcp_identify_packet_loss(sk, ack_flag); if (icsk->icsk_ca_state != TCP_CA_Recovery) { @@ -3539,7 +3573,7 @@ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked, const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cong_control) { - icsk->icsk_ca_ops->cong_control(sk, rs); + icsk->icsk_ca_ops->cong_control(sk, ack, flag, rs); return; } @@ -4204,6 +4238,13 @@ void tcp_parse_options(const struct net *net, */ break; #endif +#ifdef CONFIG_TCP_AO + case TCPOPT_AO: + /* TCP AO has already been checked + * (see tcp_inbound_ao_hash()). + */ + break; +#endif case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -4433,9 +4474,26 @@ static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp, return SKB_NOT_DROPPED_YET; } + +void tcp_done_with_error(struct sock *sk, int err) +{ + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + WRITE_ONCE(sk->sk_err, err); + smp_wmb(); + + tcp_write_queue_purge(sk); + tcp_done(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); +} +EXPORT_SYMBOL(tcp_done_with_error); + /* When we get a reset we do this. */ void tcp_reset(struct sock *sk, struct sk_buff *skb) { + int err; + trace_tcp_receive_reset(sk); /* mptcp can't tell us to ignore reset pkts, @@ -4447,24 +4505,17 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) /* We want the right error as BSD sees it (and indeed as we do). */ switch (sk->sk_state) { case TCP_SYN_SENT: - WRITE_ONCE(sk->sk_err, ECONNREFUSED); + err = ECONNREFUSED; break; case TCP_CLOSE_WAIT: - WRITE_ONCE(sk->sk_err, EPIPE); + err = EPIPE; break; case TCP_CLOSE: return; default: - WRITE_ONCE(sk->sk_err, ECONNRESET); + err = ECONNRESET; } - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - - tcp_write_queue_purge(sk); - tcp_done(sk); - - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); + tcp_done_with_error(sk, err); } /* @@ -4803,10 +4854,8 @@ static bool tcp_try_coalesce(struct sock *sk, if (!mptcp_skb_can_collapse(to, from)) return false; -#ifdef CONFIG_TLS_DEVICE - if (from->decrypted != to->decrypted) + if (skb_cmp_decrypted(from, to)) return false; -#endif if (!skb_try_coalesce(to, from, fragstolen, &delta)) return false; @@ -5174,6 +5223,16 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { if (tcp_receive_window(tp) == 0) { + /* Some stacks are known to send bare FIN packets + * in a loop even if we send RWIN 0 in our ACK. + * Accepting this FIN does not hurt memory pressure + * because the FIN flag will simply be merged to the + * receive queue tail skb in most cases. + */ + if (!skb->len && + (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) + goto queue_and_out; + reason = SKB_DROP_REASON_TCP_ZEROWINDOW; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; @@ -5188,7 +5247,7 @@ queue_and_out: inet_csk_schedule_ack(sk); sk->sk_data_ready(sk); - if (skb_queue_len(&sk->sk_receive_queue)) { + if (skb_queue_len(&sk->sk_receive_queue) && skb->len) { reason = SKB_DROP_REASON_PROTO_MEM; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); goto drop; @@ -5375,9 +5434,7 @@ restart: break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); -#ifdef CONFIG_TLS_DEVICE - nskb->decrypted = skb->decrypted; -#endif + skb_copy_decrypted(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; if (list) __skb_queue_before(list, skb, nskb); @@ -5407,10 +5464,8 @@ restart: !mptcp_skb_can_collapse(nskb, skb) || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) goto end; -#ifdef CONFIG_TLS_DEVICE - if (skb->decrypted != nskb->decrypted) + if (skb_cmp_decrypted(skb, nskb)) goto end; -#endif } } } @@ -6288,8 +6343,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tp->fastopen_client_fail = TFO_DATA_NOT_ACKED; skb_rbtree_walk_from(data) tcp_mark_skb_lost(sk, data); - tcp_xmit_retransmit_queue(sk); - tp->retrans_stamp = 0; + tcp_non_congestion_loss_retransmit(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; @@ -6427,7 +6481,8 @@ consume: if (!tp->rx_opt.wscale_ok) { tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0; - tp->window_clamp = min(tp->window_clamp, 65535U); + WRITE_ONCE(tp->window_clamp, + min(tp->window_clamp, 65535U)); } if (tp->rx_opt.saw_tstamp) { @@ -7002,7 +7057,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) +static bool tcp_syn_flood_action(struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; @@ -7103,7 +7158,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct sock *sk, struct sk_buff *skb) { struct tcp_fastopen_cookie foc = { .len = -1 }; - __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); @@ -7113,21 +7167,28 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct dst_entry *dst; struct flowi fl; u8 syncookies; + u32 isn; #ifdef CONFIG_TCP_AO const struct tcp_ao_hdr *aoh; #endif - syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); + isn = __this_cpu_read(tcp_tw_isn); + if (isn) { + /* TW buckets are converted to open requests without + * limitations, they conserve resources and peer is + * evidently real one. + */ + __this_cpu_write(tcp_tw_isn, 0); + } else { + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); - /* TW buckets are converted to open requests without - * limitations, they conserve resources and peer is - * evidently real one. - */ - if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); - if (!want_cookie) - goto drop; + if (syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) { + want_cookie = tcp_syn_flood_action(sk, + rsk_ops->slab_name); + if (!want_cookie) + goto drop; + } } if (sk_acceptq_is_full(sk)) { @@ -7166,7 +7227,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb); - dst = af_ops->route_req(sk, skb, &fl, req); + dst = af_ops->route_req(sk, skb, &fl, req, isn); if (!dst) goto drop_and_free; @@ -7243,7 +7304,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->tfo_listener = false; if (!want_cookie) { req->timeout = tcp_timeout_init((struct sock *)req); - inet_csk_reqsk_queue_hash_add(sk, req, req->timeout); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, + req->timeout))) { + reqsk_free(req); + return 0; + } + } af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 92511b7fd524..8f8f93716ff8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -70,6 +70,7 @@ #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/busy_poll.h> +#include <net/rstreason.h> #include <linux/inet.h> #include <linux/ipv6.h> @@ -94,6 +95,8 @@ EXPORT_SYMBOL(tcp_hashinfo); static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); +static DEFINE_MUTEX(tcp_exit_batch_mutex); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -610,15 +613,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); - if (!sock_owned_by_user(sk)) { - WRITE_ONCE(sk->sk_err, err); - - sk_error_report(sk); - - tcp_done(sk); - } else { + if (!sock_owned_by_user(sk)) + tcp_done_with_error(sk, err); + else WRITE_ONCE(sk->sk_err_soft, err); - } goto out; } @@ -729,7 +727,8 @@ out: * Exception: precedence violation. We do not implement it in any case. */ -static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) +static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, + enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct { @@ -872,11 +871,10 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. */ - if (sk) { + if (sk) arg.bound_dev_if = sk->sk_bound_dev_if; - if (sk_fullsock(sk)) - trace_tcp_send_reset(sk, skb); - } + + trace_tcp_send_reset(sk, skb, reason); BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); @@ -1143,14 +1141,9 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, #endif } - /* 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(sk, skb, seq, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), 0, &key, @@ -1673,7 +1666,8 @@ static void tcp_v4_init_req(struct request_sock *req, static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req) + struct request_sock *req, + u32 tw_isn) { tcp_v4_init_req(req, sk, skb); @@ -1940,7 +1934,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; reset: - tcp_v4_send_reset(rsk, skb); + tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason)); discard: kfree_skb_reason(skb, reason); /* Be careful here. If this function gets more complicated and @@ -2052,10 +2046,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || -#ifdef CONFIG_TLS_DEVICE - tail->decrypted != skb->decrypted || -#endif !mptcp_skb_can_collapse(tail, skb) || + skb_cmp_decrypted(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; @@ -2163,7 +2155,6 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); - TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = @@ -2185,6 +2176,7 @@ int tcp_v4_rcv(struct sk_buff *skb) bool refcounted; struct sock *sk; int ret; + u32 isn; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) @@ -2222,7 +2214,6 @@ lookup: if (!sk) goto no_tcp_socket; -process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; @@ -2294,7 +2285,10 @@ process: } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { - tcp_v4_send_reset(nsk, skb); + enum sk_rst_reason rst_reason; + + rst_reason = sk_rst_convert_drop_reason(drop_reason); + tcp_v4_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); @@ -2302,6 +2296,7 @@ process: } } +process: if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ if (unlikely(iph->ttl < READ_ONCE(inet_sk(sk)->min_ttl))) { @@ -2372,7 +2367,7 @@ csum_error: bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { - tcp_v4_send_reset(NULL, skb); + tcp_v4_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: @@ -2400,7 +2395,7 @@ do_time_wait: inet_twsk_put(inet_twsk(sk)); goto csum_error; } - switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { + switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, @@ -2414,6 +2409,7 @@ do_time_wait: sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; + __this_cpu_write(tcp_tw_isn, isn); goto process; } } @@ -2423,7 +2419,7 @@ do_time_wait: tcp_v4_timewait_ack(sk, skb); break; case TCP_TW_RST: - tcp_v4_send_reset(sk, skb); + tcp_v4_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS:; @@ -2433,7 +2429,6 @@ do_time_wait: static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), - .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, }; @@ -3516,13 +3511,25 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; - tcp_twsk_purge(net_exit_list, AF_INET); + /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work + * and failed setup_net error unwinding path are serialized. + * + * tcp_twsk_purge() handles twsk in any dead netns, not just those in + * net_exit_list, the thread that dismantles a particular twsk must + * do so without other thread progressing to refcount_dec_and_test() of + * tcp_death_row.tw_refcount. + */ + mutex_lock(&tcp_exit_batch_mutex); + + tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { inet_pernet_hashinfo_free(net->ipv4.tcp_death_row.hashinfo); WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } + + mutex_unlock(&tcp_exit_batch_mutex); } static struct pernet_operations __net_initdata tcp_sk_ops = { diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c2a925538542..b01eb6d94413 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -619,6 +619,7 @@ static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr), }, + [TCP_METRICS_ATTR_SADDR_IPV4] = { .type = NLA_U32, }, /* Following attributes are not received for GET/DEL, * we keep them for reference */ @@ -766,6 +767,7 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb, unsigned int max_rows = 1U << tcp_metrics_hash_log; unsigned int row, s_row = cb->args[0]; int s_col = cb->args[1], col = s_col; + int res = 0; for (row = s_row; row < max_rows; row++, s_col = 0) { struct tcp_metrics_block *tm; @@ -778,7 +780,8 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb, continue; if (col < s_col) continue; - if (tcp_metrics_dump_info(skb, cb, tm) < 0) { + res = tcp_metrics_dump_info(skb, cb, tm); + if (res < 0) { rcu_read_unlock(); goto done; } @@ -789,7 +792,7 @@ static int tcp_metrics_nl_dump(struct sk_buff *skb, done: cb->args[0] = row; cb->args[1] = col; - return skb->len; + return res; } static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, @@ -986,6 +989,7 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = { .maxattr = TCP_METRICS_ATTR_MAX, .policy = tcp_metrics_nl_policy, .netnsok = true, + .parallel_ops = true, .module = THIS_MODULE, .small_ops = tcp_metrics_nl_ops, .n_small_ops = ARRAY_SIZE(tcp_metrics_nl_ops), diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f0761f060a83..0fbebf6266e9 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -22,6 +22,7 @@ #include <net/tcp.h> #include <net/xfrm.h> #include <net/busy_poll.h> +#include <net/rstreason.h> static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { @@ -95,7 +96,7 @@ static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq) */ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, - const struct tcphdr *th) + const struct tcphdr *th, u32 *tw_isn) { struct tcp_options_received tmp_opt; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); @@ -228,7 +229,7 @@ kill: u32 isn = tcptw->tw_snd_nxt + 65535 + 2; if (isn == 0) isn++; - TCP_SKB_CB(skb)->tcp_tw_isn = isn; + *tw_isn = isn; return TCP_TW_SYN; } @@ -388,7 +389,7 @@ void tcp_twsk_destructor(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); -void tcp_twsk_purge(struct list_head *net_exit_list, int family) +void tcp_twsk_purge(struct list_head *net_exit_list) { bool purged_once = false; struct net *net; @@ -396,14 +397,13 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family) list_for_each_entry(net, net_exit_list, exit_list) { if (net->ipv4.tcp_death_row.hashinfo->pernet) { /* Even if tw_refcount == 1, we must clean up kernel reqsk */ - inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family); + inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo); } else if (!purged_once) { - inet_twsk_purge(&tcp_hashinfo, family); + inet_twsk_purge(&tcp_hashinfo); purged_once = true; } } } -EXPORT_SYMBOL_GPL(tcp_twsk_purge); /* Warning : This function is called without sk_listener being locked. * Be sure to read socket fields once, as their value could change under us. @@ -515,9 +515,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, const struct tcp_sock *oldtp; struct tcp_sock *newtp; u32 seq; -#ifdef CONFIG_TCP_AO - struct tcp_ao_key *ao_key; -#endif if (!newsk) return NULL; @@ -608,10 +605,14 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, #endif #ifdef CONFIG_TCP_AO newtp->ao_info = NULL; - ao_key = treq->af_specific->ao_lookup(sk, req, - tcp_rsk(req)->ao_keyid, -1); - if (ao_key) - newtp->tcp_header_len += tcp_ao_len_aligned(ao_key); + + if (tcp_rsk_used_ao(req)) { + struct tcp_ao_key *ao_key; + + ao_key = treq->af_specific->ao_lookup(sk, req, tcp_rsk(req)->ao_keyid, -1); + if (ao_key) + newtp->tcp_header_len += tcp_ao_len_aligned(ao_key); + } #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; @@ -783,8 +784,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ - if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { + if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + tcp_rsk(req)->rcv_nxt, + tcp_rsk(req)->rcv_nxt + + tcp_synack_window(req))) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST) && !tcp_oow_rate_limited(sock_net(sk), skb, @@ -879,7 +883,7 @@ embryonic_reset: * avoid becoming vulnerable to outside attack aiming at * resetting legit local connections. */ - req->rsk_ops->send_reset(sk, skb); + req->rsk_ops->send_reset(sk, skb, SK_RST_REASON_INVALID_SYN); } else if (fastopen) { /* received a valid RST pkt */ reqsk_fastopen_remove(sk, req, true); tcp_reset(sk, skb); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index ebe4722bb020..e4ad3311e148 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -28,6 +28,70 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, } } +static void __tcpv4_gso_segment_csum(struct sk_buff *seg, + __be32 *oldip, __be32 newip, + __be16 *oldport, __be16 newport) +{ + struct tcphdr *th; + struct iphdr *iph; + + if (*oldip == newip && *oldport == newport) + return; + + th = tcp_hdr(seg); + iph = ip_hdr(seg); + + inet_proto_csum_replace4(&th->check, seg, *oldip, newip, true); + inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false); + *oldport = newport; + + csum_replace4(&iph->check, *oldip, newip); + *oldip = newip; +} + +static struct sk_buff *__tcpv4_gso_segment_list_csum(struct sk_buff *segs) +{ + const struct tcphdr *th; + const struct iphdr *iph; + struct sk_buff *seg; + struct tcphdr *th2; + struct iphdr *iph2; + + seg = segs; + th = tcp_hdr(seg); + iph = ip_hdr(seg); + th2 = tcp_hdr(seg->next); + iph2 = ip_hdr(seg->next); + + if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) && + iph->daddr == iph2->daddr && iph->saddr == iph2->saddr) + return segs; + + while ((seg = seg->next)) { + th2 = tcp_hdr(seg); + iph2 = ip_hdr(seg); + + __tcpv4_gso_segment_csum(seg, + &iph2->saddr, iph->saddr, + &th2->source, th->source); + __tcpv4_gso_segment_csum(seg, + &iph2->daddr, iph->daddr, + &th2->dest, th->dest); + } + + return segs; +} + +static struct sk_buff *__tcp4_gso_segment_list(struct sk_buff *skb, + netdev_features_t features) +{ + skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); + if (IS_ERR(skb)) + return skb; + + return __tcpv4_gso_segment_list_csum(skb); +} + static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { @@ -37,6 +101,9 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL); + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) + return __tcp4_gso_segment_list(skb, features); + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); @@ -73,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; @@ -178,63 +248,76 @@ out: return segs; } -struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) +struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th) { - struct sk_buff *pp = NULL; + struct tcphdr *th2; struct sk_buff *p; + + list_for_each_entry(p, head, list) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + th2 = tcp_hdr(p); + if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + return p; + } + + return NULL; +} + +struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb) +{ + unsigned int thlen, hlen, off; struct tcphdr *th; - struct tcphdr *th2; - unsigned int len; - unsigned int thlen; - __be32 flags; - unsigned int mss = 1; - unsigned int hlen; - unsigned int off; - int flush = 1; - int i; off = skb_gro_offset(skb); hlen = off + sizeof(*th); th = skb_gro_header(skb, hlen, off); if (unlikely(!th)) - goto out; + return NULL; thlen = th->doff * 4; if (thlen < sizeof(*th)) - goto out; + return NULL; hlen = off + thlen; if (!skb_gro_may_pull(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) - goto out; + return NULL; } skb_gro_pull(skb, thlen); - len = skb_gro_len(skb); - flags = tcp_flag_word(th); - - list_for_each_entry(p, head, list) { - if (!NAPI_GRO_CB(p)->same_flow) - continue; + return th; +} - th2 = tcp_hdr(p); +struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th) +{ + unsigned int thlen = th->doff * 4; + struct sk_buff *pp = NULL; + struct sk_buff *p; + struct tcphdr *th2; + unsigned int len; + __be32 flags; + unsigned int mss = 1; + int flush = 1; + int i; - if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } + len = skb_gro_len(skb); + flags = tcp_flag_word(th); - goto found; - } - p = NULL; - goto out_check_final; + p = tcp_gro_lookup(head, th); + if (!p) + goto out_check_final; -found: - /* Include the IP ID check below from the inner most IP hdr */ - flush = NAPI_GRO_CB(p)->flush; - flush |= (__force int)(flags & TCP_FLAG_CWR); + th2 = tcp_hdr(p); + flush = (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); @@ -242,16 +325,7 @@ found: flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); - /* When we receive our second frame we can made a decision on if we - * continue this flow as an atomic flow with a fixed ID or if we use - * an incrementing ID. - */ - if (NAPI_GRO_CB(p)->flush_id != 1 || - NAPI_GRO_CB(p)->count != 1 || - !NAPI_GRO_CB(p)->is_atomic) - flush |= NAPI_GRO_CB(p)->flush_id; - else - NAPI_GRO_CB(p)->is_atomic = false; + flush |= gro_receive_network_flush(th, th2, p); mss = skb_shinfo(p)->gso_size; @@ -265,9 +339,19 @@ found: flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); -#ifdef CONFIG_TLS_DEVICE - flush |= p->decrypted ^ skb->decrypted; -#endif + flush |= skb_cmp_decrypted(p, skb); + + if (unlikely(NAPI_GRO_CB(p)->is_flist)) { + flush |= (__force int)(flags ^ tcp_flag_word(th2)); + flush |= skb->ip_summed != p->ip_summed; + flush |= skb->csum_level != p->csum_level; + flush |= NAPI_GRO_CB(p)->count >= 64; + + if (flush || skb_gro_receive_list(p, skb)) + mss = 1; + + goto out_check_final; + } if (flush || skb_gro_receive(p, skb)) { mss = 1; @@ -290,7 +374,6 @@ out_check_final: if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) pp = p; -out: NAPI_GRO_CB(skb)->flush |= (flush != 0); return pp; @@ -316,30 +399,80 @@ void tcp_gro_complete(struct sk_buff *skb) } EXPORT_SYMBOL(tcp_gro_complete); +static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th) +{ + const struct iphdr *iph; + struct sk_buff *p; + struct sock *sk; + struct net *net; + int iif, sdif; + + if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) + return; + + p = tcp_gro_lookup(head, th); + if (p) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + inet_get_iif_sdif(skb, &iif, &sdif); + iph = skb_gro_network_header(skb); + net = dev_net(skb->dev); + sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, + iph->saddr, th->source, + iph->daddr, ntohs(th->dest), + iif, sdif); + NAPI_GRO_CB(skb)->is_flist = !sk; + if (sk) + sock_put(sk); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { + struct tcphdr *th; + /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, - inet_gro_compute_pseudo)) { - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - } + inet_gro_compute_pseudo)) + goto flush; + + th = tcp_gro_pull_header(skb); + if (!th) + goto flush; - return tcp_gro_receive(head, skb); + tcp4_check_fraglist_gro(head, skb, th); + + return tcp_gro_receive(head, skb, th); + +flush: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; } INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) { - const struct iphdr *iph = ip_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct tcphdr *th = tcp_hdr(skb); + if (unlikely(NAPI_GRO_CB(skb)->is_flist)) { + skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV4; + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + __skb_incr_checksum_unnecessary(skb); + + return 0; + } + th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 | - (NAPI_GRO_CB(skb)->is_atomic * SKB_GSO_TCP_FIXEDID); + (NAPI_GRO_CB(skb)->ip_fixedid * SKB_GSO_TCP_FIXEDID); tcp_gro_complete(skb); return 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 02caeb7bcf63..95618d0e78e4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -39,11 +39,13 @@ #include <net/tcp.h> #include <net/mptcp.h> +#include <net/proto_memory.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> +#include <linux/skbuff_ref.h> #include <trace/events/tcp.h> @@ -203,16 +205,17 @@ static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) * This MUST be enforced by all callers. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, - __u32 *rcv_wnd, __u32 *window_clamp, + __u32 *rcv_wnd, __u32 *__window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); + u32 window_clamp = READ_ONCE(*__window_clamp); /* If no clamp set the clamp to the max possible scaled window */ - if (*window_clamp == 0) - (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); - space = min(*window_clamp, space); + if (window_clamp == 0) + window_clamp = (U16_MAX << TCP_MAX_WSCALE); + space = min(window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) @@ -229,7 +232,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else - (*rcv_wnd) = min_t(u32, space, U16_MAX); + (*rcv_wnd) = space; if (init_rcv_wnd) *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); @@ -239,12 +242,13 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); - space = min_t(u32, space, *window_clamp); + space = min_t(u32, space, window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); } /* Set the clamp no higher than max representable value */ - (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); + WRITE_ONCE(*__window_clamp, + min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp)); } EXPORT_SYMBOL(tcp_select_initial_window); @@ -1499,18 +1503,22 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) } /* Initialize TSO segments for a packet. */ -static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) +static int tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { + int tso_segs; + if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ - tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->tcp_gso_size = 0; - } else { - tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now)); - TCP_SKB_CB(skb)->tcp_gso_size = mss_now; + tcp_skb_pcount_set(skb, 1); + return 1; } + TCP_SKB_CB(skb)->tcp_gso_size = mss_now; + tso_segs = DIV_ROUND_UP(skb->len, mss_now); + tcp_skb_pcount_set(skb, tso_segs); + return tso_segs; } /* Pcount in the middle of the write queue got changed, we need to do various @@ -2070,16 +2078,10 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ -static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, - const struct sk_buff *skb) +static u32 tcp_cwnd_test(const struct tcp_sock *tp) { u32 in_flight, cwnd, halfcwnd; - /* Don't be strict about the congestion window for the final FIN. */ - if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && - tcp_skb_pcount(skb) == 1) - return 1; - in_flight = tcp_packets_in_flight(tp); cwnd = tcp_snd_cwnd(tp); if (in_flight >= cwnd) @@ -2100,10 +2102,9 @@ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); - if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { - tcp_set_skb_tso_segs(skb, mss_now); - tso_segs = tcp_skb_pcount(skb); - } + if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) + return tcp_set_skb_tso_segs(skb, mss_now); + return tso_segs; } @@ -2403,6 +2404,21 @@ commit: return 0; } +/* tcp_mtu_probe() and tcp_grow_skb() can both eat an skb (src) if + * all its payload was moved to another one (dst). + * Make sure to transfer tcp_flags, eor, and tstamp. + */ +static void tcp_eat_one_skb(struct sock *sk, + struct sk_buff *dst, + struct sk_buff *src) +{ + TCP_SKB_CB(dst)->tcp_flags |= TCP_SKB_CB(src)->tcp_flags; + TCP_SKB_CB(dst)->eor = TCP_SKB_CB(src)->eor; + tcp_skb_collapse_tstamp(dst, src); + tcp_unlink_write_queue(src, sk); + tcp_wmem_free_skb(sk, src); +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -2508,16 +2524,7 @@ static int tcp_mtu_probe(struct sock *sk) copy = min_t(int, skb->len, probe_size - len); if (skb->len <= copy) { - /* We've eaten all the data from this skb. - * Throw it away. */ - TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; - /* If this is the last SKB we copy and eor is set - * we need to propagate it to the new skb. - */ - TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; - tcp_skb_collapse_tstamp(nskb, skb); - tcp_unlink_write_queue(skb, sk); - tcp_wmem_free_skb(sk, skb); + tcp_eat_one_skb(sk, nskb, skb); } else { TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); @@ -2683,6 +2690,35 @@ void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); } +/* First skb in the write queue is smaller than ideal packet size. + * Check if we can move payload from the second skb in the queue. + */ +static void tcp_grow_skb(struct sock *sk, struct sk_buff *skb, int amount) +{ + struct sk_buff *next_skb = skb->next; + unsigned int nlen; + + if (tcp_skb_is_last(sk, skb)) + return; + + if (!tcp_skb_can_collapse(skb, next_skb)) + return; + + nlen = min_t(u32, amount, next_skb->len); + if (!nlen || !skb_shift(skb, next_skb, nlen)) + return; + + TCP_SKB_CB(skb)->end_seq += nlen; + TCP_SKB_CB(next_skb)->seq += nlen; + + if (!next_skb->len) { + /* In case FIN is set, we need to update end_seq */ + TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; + + tcp_eat_one_skb(sk, skb, next_skb); + } +} + /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. @@ -2703,10 +2739,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; - int cwnd_quota; + u32 cwnd_quota, max_segs; int result; bool is_cwnd_limited = false, is_rwnd_limited = false; - u32 max_segs; sent_pkts = 0; @@ -2724,6 +2759,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; + int missing_bytes; if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ @@ -2737,10 +2773,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_pacing_check(sk)) break; - tso_segs = tcp_init_tso_segs(skb, mss_now); - BUG_ON(!tso_segs); - - cwnd_quota = tcp_cwnd_test(tp, skb); + cwnd_quota = tcp_cwnd_test(tp); if (!cwnd_quota) { if (push_one == 2) /* Force out a loss probe pkt. */ @@ -2748,6 +2781,12 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, else break; } + cwnd_quota = min(cwnd_quota, max_segs); + missing_bytes = cwnd_quota * mss_now - skb->len; + if (missing_bytes > 0) + tcp_grow_skb(sk, skb, missing_bytes); + + tso_segs = tcp_set_skb_tso_segs(skb, mss_now); if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) { is_rwnd_limited = true; @@ -2769,9 +2808,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, - min_t(unsigned int, - cwnd_quota, - max_segs), + cwnd_quota, nonagle); if (skb->len > limit && @@ -3387,11 +3424,6 @@ start: err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } - /* To avoid taking spuriously low RTT samples based on a timestamp - * for a transmit that never happened, always mark EVER_RETRANS - */ - TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; - if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); @@ -3401,6 +3433,12 @@ start: } else if (err != -EBUSY) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } + + /* To avoid taking spuriously low RTT samples based on a timestamp + * for a transmit that never happened, always mark EVER_RETRANS + */ + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + return err; } @@ -3585,7 +3623,8 @@ void tcp_send_fin(struct sock *sk) * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ -void tcp_send_active_reset(struct sock *sk, gfp_t priority) +void tcp_send_active_reset(struct sock *sk, gfp_t priority, + enum sk_rst_reason reason) { struct sk_buff *skb; @@ -3610,7 +3649,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ - trace_tcp_send_reset(sk, NULL); + trace_tcp_send_reset(sk, NULL, SK_RST_REASON_NOT_SPECIFIED); } /* Send a crossed SYN-ACK during socket establishment. @@ -3857,7 +3896,7 @@ static void tcp_connect_init(struct sock *sk) tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) - tp->window_clamp = dst_metric(dst, RTAX_WINDOW); + WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW)); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); @@ -3865,7 +3904,7 @@ static void tcp_connect_init(struct sock *sk) /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) - tp->window_clamp = tcp_full_space(sk); + WRITE_ONCE(tp->window_clamp, tcp_full_space(sk)); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index f96f68cf7961..4d40615dc8fc 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,10 +22,11 @@ #include <linux/module.h> #include <linux/gfp.h> #include <net/tcp.h> +#include <net/rstreason.h> static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); u32 elapsed, user_timeout; s32 remaining; @@ -47,7 +48,7 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); u32 remaining, user_timeout; s32 elapsed; @@ -73,11 +74,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) static void tcp_write_err(struct sock *sk) { - WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); - sk_error_report(sk); - - tcp_write_queue_purge(sk); - tcp_done(sk); + tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } @@ -127,7 +124,8 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; @@ -481,15 +479,26 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb, u32 rtx_delta) { + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); - const int timeout = TCP_RTO_MAX * 2; + int timeout = TCP_RTO_MAX * 2; s32 rcv_delta; + if (user_timeout) { + /* If user application specified a TCP_USER_TIMEOUT, + * it does not want win 0 packets to 'reset the timer' + * while retransmits are not making progress. + */ + if (rtx_delta > user_timeout) + return true; + timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); + } /* Note: timer interrupt might have been delayed by at least one jiffy, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ - rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; @@ -534,8 +543,6 @@ void tcp_retransmit_timer(struct sock *sk) if (WARN_ON_ONCE(!skb)) return; - tp->tlp_high_seq = 0; - if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { /* Receiver dastardly shrinks window. Our retransmits @@ -772,7 +779,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_NOT_SPECIFIED); goto death; } @@ -799,7 +806,8 @@ static void tcp_keepalive_timer (struct timer_list *t) icsk->icsk_probes_out > 0) || (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_NOT_SPECIFIED); tcp_write_err(sk); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 72d3bf136810..578668878a85 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -326,6 +326,8 @@ found: goto fail_unlock; } + sock_set_flag(sk, SOCK_RCU_FREE); + sk_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -342,7 +344,7 @@ found: hslot2->count++; spin_unlock(&hslot2->lock); } - sock_set_flag(sk, SOCK_RCU_FREE); + error = 0; fail_unlock: spin_unlock_bh(&hslot->lock); @@ -1512,13 +1514,15 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) struct sk_buff_head *list = &sk->sk_receive_queue; int rmem, err = -ENOMEM; spinlock_t *busy = NULL; - int size; + bool becomes_readable; + int size, rcvbuf; - /* try to avoid the costly atomic add/sub pair when the receive - * queue is full; always allow at least a packet + /* Immediately drop when the receive queue is full. + * Always allow at least one packet. */ rmem = atomic_read(&sk->sk_rmem_alloc); - if (rmem > sk->sk_rcvbuf) + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + if (rmem > rcvbuf) goto drop; /* Under mem pressure, it might be helpful to help udp_recvmsg() @@ -1527,7 +1531,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * - Less cache line misses at copyout() time * - Less work at consume_skb() (less alien page frag freeing) */ - if (rmem > (sk->sk_rcvbuf >> 1)) { + if (rmem > (rcvbuf >> 1)) { skb_condense(skb); busy = busylock_acquire(sk); @@ -1535,12 +1539,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) size = skb->truesize; udp_set_dev_scratch(skb); - /* we drop only if the receive buf is full and the receive - * queue contains some other skb - */ - rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) - goto uncharge_drop; + atomic_add(size, &sk->sk_rmem_alloc); spin_lock(&list->lock); err = udp_rmem_schedule(sk, size); @@ -1556,12 +1555,19 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) */ sock_skb_set_dropcount(sk, skb); + becomes_readable = skb_queue_empty(list); __skb_queue_tail(list, skb); spin_unlock(&list->lock); - if (!sock_flag(sk, SOCK_DEAD)) - INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk); - + if (!sock_flag(sk, SOCK_DEAD)) { + if (becomes_readable || + sk->sk_data_ready != sock_def_readable || + READ_ONCE(sk->sk_peek_off) >= 0) + INDIRECT_CALL_1(sk->sk_data_ready, + sock_def_readable, sk); + else + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); + } busylock_release(busy); return 0; @@ -2069,8 +2075,8 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) drop_reason = SKB_DROP_REASON_PROTO_MEM; } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); kfree_skb_reason(skb, drop_reason); - trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -2708,8 +2714,6 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: set_xfrm_gro_udp_encap_rcv(val, sk->sk_family, sk); - fallthrough; - case UDP_ENCAP_ESPINUDP_NON_IKE: #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) WRITE_ONCE(up->encap_rcv, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 8721fe5beca2..5b54f4f32b1c 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,11 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) + return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), @@ -433,33 +438,6 @@ out: return segs; } -static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) -{ - if (unlikely(p->len + skb->len >= 65536)) - return -E2BIG; - - if (NAPI_GRO_CB(p)->last == p) - skb_shinfo(p)->frag_list = skb; - else - NAPI_GRO_CB(p)->last->next = skb; - - skb_pull(skb, skb_gro_offset(skb)); - - NAPI_GRO_CB(p)->last = skb; - NAPI_GRO_CB(p)->count++; - p->data_len += skb->len; - - /* sk ownership - if any - completely transferred to the aggregated packet */ - skb->destructor = NULL; - skb->sk = NULL; - p->truesize += skb->truesize; - p->len += skb->len; - - NAPI_GRO_CB(skb)->same_flow = 1; - - return 0; -} - #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, @@ -505,14 +483,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return p; } - flush = NAPI_GRO_CB(p)->flush; - - if (NAPI_GRO_CB(p)->flush_id != 1 || - NAPI_GRO_CB(p)->count != 1 || - !NAPI_GRO_CB(p)->is_atomic) - flush |= NAPI_GRO_CB(p)->flush_id; - else - NAPI_GRO_CB(p)->is_atomic = false; + flush = gro_receive_network_flush(uh, uh2, p); /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 860aff5f8599..e4e0fa869fa4 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -183,7 +183,8 @@ void udp_tunnel_sock_release(struct socket *sock) EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, - __be16 flags, __be64 tunnel_id, int md_size) + const unsigned long *flags, + __be64 tunnel_id, int md_size) { struct metadata_dst *tun_dst; struct ip_tunnel_info *info; @@ -199,7 +200,7 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, info->key.tp_src = udp_hdr(skb)->source; info->key.tp_dst = udp_hdr(skb)->dest; if (udp_hdr(skb)->check) - info->key.tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); return tun_dst; } EXPORT_SYMBOL_GPL(udp_tun_rx_dst); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 86382e08140e..a620618cc568 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -117,19 +117,6 @@ static int __xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull /* Must be an IKE packet.. pass it through */ return 1; break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - /* Check if this is a keepalive packet. If so, eat it. */ - if (len == 1 && udpdata[0] == 0xff) { - return -EINVAL; - } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && - udpdata32[0] == 0 && udpdata32[1] == 0) { - - /* ESP Packet with Non-IKE marker */ - len = sizeof(struct udphdr) + 2 * sizeof(u32); - } else - /* Must be an IKE packet.. pass it through */ - return 1; - break; } /* At this point we are sure that this is an ESPinUDP packet, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 1853a8415d9f..0294fef577fa 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -152,7 +152,6 @@ static struct ctl_table xfrm4_policy_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static __net_init int xfrm4_net_sysctl_init(struct net *net) @@ -186,7 +185,7 @@ err_alloc: static __net_exit void xfrm4_net_sysctl_exit(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; if (!net->ipv4.xfrm4_hdr) return; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 779aa6ecdd49..4f2c5cc31015 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -63,6 +63,7 @@ #include <linux/string.h> #include <linux/hash.h> +#include <net/ip_tunnels.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> @@ -1872,7 +1873,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, master, &dst, scores, hiscore_idx); - if (scores[hiscore_idx].ifa) + if (scores[hiscore_idx].ifa && + scores[hiscore_idx].scopedist >= 0) goto out; } @@ -2918,7 +2920,7 @@ put: static int addrconf_set_sit_dstaddr(struct net *net, struct net_device *dev, struct in6_ifreq *ireq) { - struct ip_tunnel_parm p = { }; + struct ip_tunnel_parm_kern p = { }; int err; if (!(ipv6_addr_type(&ireq->ifr6_addr) & IPV6_ADDR_COMPATv4)) @@ -7183,14 +7185,12 @@ static const struct ctl_table addrconf_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, - { - /* sentinel */ - } }; static int __addrconf_sysctl_register(struct net *net, char *dev_name, struct inet6_dev *idev, struct ipv6_devconf *p) { + size_t table_size = ARRAY_SIZE(addrconf_sysctl); int i, ifindex; struct ctl_table *table; char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; @@ -7199,7 +7199,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, if (!table) goto out; - for (i = 0; table[i].data; i++) { + for (i = 0; i < table_size; i++) { table[i].data += (char *)p - (char *)&ipv6_devconf; /* If one of these is already set, then it is not safe to * overwrite either of them: this makes proc_dointvec_minmax @@ -7214,7 +7214,7 @@ static int __addrconf_sysctl_register(struct net *net, char *dev_name, snprintf(path, sizeof(path), "net/ipv6/conf/%s", dev_name); p->sysctl_header = register_net_sysctl_sz(net, path, table, - ARRAY_SIZE(addrconf_sysctl)); + table_size); if (!p->sysctl_header) goto free; @@ -7237,7 +7237,7 @@ out: static void __addrconf_sysctl_unregister(struct net *net, struct ipv6_devconf *p, int ifindex) { - struct ctl_table *table; + const struct ctl_table *table; if (!p->sysctl_header) return; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 17ac45aa7194..acd70b5992a7 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -234,7 +234,8 @@ static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head); out: if (!ret) - net->ipv6.ip6addrlbl_table.seq++; + WRITE_ONCE(net->ipv6.ip6addrlbl_table.seq, + net->ipv6.ip6addrlbl_table.seq + 1); return ret; } @@ -445,7 +446,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, }; static int ip6addrlbl_fill(struct sk_buff *skb, - struct ip6addrlbl_entry *p, + const struct ip6addrlbl_entry *p, u32 lseq, u32 portid, u32 seq, int event, unsigned int flags) @@ -498,7 +499,8 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); struct ip6addrlbl_entry *p; int idx = 0, s_idx = cb->args[0]; - int err; + int err = 0; + u32 lseq; if (cb->strict_check) { err = ip6addrlbl_valid_dump_req(nlh, cb->extack); @@ -507,10 +509,11 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) } rcu_read_lock(); + lseq = READ_ONCE(net->ipv6.ip6addrlbl_table.seq); hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { if (idx >= s_idx) { err = ip6addrlbl_fill(skb, p, - net->ipv6.ip6addrlbl_table.seq, + lseq, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWADDRLABEL, @@ -522,7 +525,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) } rcu_read_unlock(); cb->args[0] = idx; - return skb->len; + return err; } static inline int ip6addrlbl_msgsize(void) @@ -614,7 +617,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, rcu_read_lock(); p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - lseq = net->ipv6.ip6addrlbl_table.seq; + lseq = READ_ONCE(net->ipv6.ip6addrlbl_table.seq); if (p) err = ip6addrlbl_fill(skb, p, lseq, NETLINK_CB(in_skb).portid, @@ -647,6 +650,7 @@ int __init ipv6_addr_label_rtnl_register(void) return ret; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, - ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED); + ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); return ret; } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 0f2506e35359..0627c4c18d1a 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -252,9 +252,8 @@ static void aca_free_rcu(struct rcu_head *h) static void aca_put(struct ifacaddr6 *ac) { - if (refcount_dec_and_test(&ac->aca_refcnt)) { - call_rcu(&ac->rcu, aca_free_rcu); - } + if (refcount_dec_and_test(&ac->aca_refcnt)) + call_rcu_hurry(&ac->rcu, aca_free_rcu); } static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 7371886d4f9f..3920e8aa1031 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -36,6 +36,7 @@ #include <net/tcp.h> #include <net/espintcp.h> #include <net/inet6_hashtables.h> +#include <linux/skbuff_ref.h> #include <linux/highmem.h> @@ -131,7 +132,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(skb, sg_page(sg), false); + skb_page_unref(sg_page(sg), skb->pp_recycle); } #ifdef CONFIG_INET6_ESPINTCP @@ -255,8 +256,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) #else static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { - kfree_skb(skb); - + WARN_ON(1); return -EOPNOTSUPP; } #endif @@ -383,7 +383,6 @@ static struct ip_esp_hdr *esp6_output_udp_encap(struct sk_buff *skb, __be16 dport) { struct udphdr *uh; - __be32 *udpdata32; unsigned int len; len = skb->len + esp->tailen - skb_transport_offset(skb); @@ -398,12 +397,6 @@ static struct ip_esp_hdr *esp6_output_udp_encap(struct sk_buff *skb, *skb_mac_header(skb) = IPPROTO_UDP; - if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - return (struct ip_esp_hdr *)(udpdata32 + 2); - } - return (struct ip_esp_hdr *)(uh + 1); } @@ -459,7 +452,6 @@ static int esp6_output_encap(struct xfrm_state *x, struct sk_buff *skb, switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: esph = esp6_output_udp_encap(skb, encap_type, esp, sport, dport); break; case TCP_ENCAP_ESPINTCP: @@ -822,7 +814,6 @@ int esp6_input_done2(struct sk_buff *skb, int err) source = th->source; break; case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: source = uh->source; break; default: @@ -1232,9 +1223,6 @@ static int esp6_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); - break; #ifdef CONFIG_INET6_ESPINTCP case TCP_ENCAP_ESPINTCP: /* only the length field, TCP encap is done by diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 527b7caddbc6..919ebfabbe4e 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -83,6 +83,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, x = xfrm_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ipv6_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET6); + + if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) { + /* non-offload path will record the error and audit log */ + xfrm_state_put(x); + x = NULL; + } + if (!x) goto out_reset; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index d285c1f6f1a6..7b31674644ef 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -1206,7 +1206,6 @@ static struct ctl_table ipv6_icmp_table_template[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - { }, }; struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 0601bad79822..ff7e734e335b 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -58,7 +58,9 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) return orig_dst->lwtstate->orig_output(net, sk, skb); } + local_bh_disable(); dst = dst_cache_get(&ilwt->dst_cache); + local_bh_enable(); if (unlikely(!dst)) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct flowi6 fl6; @@ -86,8 +88,11 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; } - if (ilwt->connected) + if (ilwt->connected) { + local_bh_disable(); dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr); + local_bh_enable(); + } } skb_dst_set(skb, dst); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 2e81383b663b..6db71bb1cd30 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -21,6 +21,7 @@ #include <net/secure_seq.h> #include <net/ip.h> #include <net/sock_reuseport.h> +#include <net/tcp.h> u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, @@ -289,7 +290,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); - if (twsk_unique(sk, sk2, twp)) + if (sk->sk_protocol == IPPROTO_TCP && + tcp_twsk_unique(sk, sk2, twp)) break; } goto not_unique; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1ace4ac3ee04..83e4f9855ae1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -623,23 +623,22 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, .filter.dump_routes = true, - .filter.rtnl_held = true, + .filter.rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - unsigned int h, s_h; unsigned int e = 0, s_e; + struct hlist_head *head; struct fib6_walker *w; struct fib6_table *tb; - struct hlist_head *head; - int res = 0; + unsigned int h, s_h; + int err = 0; + rcu_read_lock(); if (cb->strict_check) { - int err; - err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb); if (err < 0) - return err; + goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); @@ -654,8 +653,10 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); - if (!w) - return -ENOMEM; + if (!w) { + err = -ENOMEM; + goto unlock; + } w->func = fib6_dump_node; cb->args[2] = (long)w; @@ -675,46 +676,46 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET6) - goto out; + goto unlock; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); - return -ENOENT; + err = -ENOENT; + goto unlock; } if (!cb->args[0]) { - res = fib6_dump_table(tb, skb, cb); - if (!res) + err = fib6_dump_table(tb, skb, cb); + if (!err) cb->args[0] = 1; } - goto out; + goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; - rcu_read_lock(); for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; - res = fib6_dump_table(tb, skb, cb); - if (res != 0) - goto out_unlock; + err = fib6_dump_table(tb, skb, cb); + if (err != 0) + goto out; next: e++; } } -out_unlock: - rcu_read_unlock(); +out: cb->args[1] = e; cb->args[0] = h; -out: - res = res < 0 ? res : skb->len; - if (res <= 0) + +unlock: + rcu_read_unlock(); + if (err <= 0) fib6_dump_end(cb); - return res; + return err; } void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) @@ -2513,7 +2514,8 @@ int __init fib6_init(void) goto out_kmem_cache_create; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL, - inet6_dump_fib, 0); + inet6_dump_fib, RTNL_FLAG_DUMP_UNLOCKED | + RTNL_FLAG_DUMP_SPLIT_NLM_DONE); if (ret) goto out_unregister_subsys; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c89aef524df9..3942bd2ade78 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -496,11 +496,11 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) tpi->proto); if (tunnel) { if (tunnel->parms.collect_md) { + IP_TUNNEL_DECLARE_FLAGS(flags); struct metadata_dst *tun_dst; __be64 tun_id; - __be16 flags; - flags = tpi->flags; + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, 0); @@ -551,14 +551,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, if (tunnel->parms.collect_md) { struct erspan_metadata *pkt_md, *md; + IP_TUNNEL_DECLARE_FLAGS(flags); struct metadata_dst *tun_dst; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; - __be16 flags; - tpi->flags |= TUNNEL_KEY; - flags = tpi->flags; + __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); + ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, @@ -580,7 +580,8 @@ static int ip6erspan_rcv(struct sk_buff *skb, md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + info->key.tun_flags); info->options_len = sizeof(*md); ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); @@ -748,8 +749,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, __u32 *pmtu, __be16 proto) { struct ip6_tnl *tunnel = netdev_priv(dev); + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 protocol; - __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -781,8 +782,11 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, fl6->fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; - flags = key->tun_flags & - (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); + ip_tunnel_flags_zero(flags); + __set_bit(IP_TUNNEL_CSUM_BIT, flags); + __set_bit(IP_TUNNEL_KEY_BIT, flags); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + ip_tunnel_flags_and(flags, flags, key->tun_flags); tun_hlen = gre_calc_hlen(flags); if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) @@ -791,19 +795,21 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) - : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : + 0); } else { if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) return -ENOMEM; - flags = tunnel->parms.o_flags; + ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) - : 0); + test_bit(IP_TUNNEL_SEQ_BIT, flags) ? + htonl(atomic_fetch_inc(&tunnel->o_seqno)) : + 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -825,7 +831,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_ipv4(skb, dev, &fl6, &dsfield, &encap_limit); - err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); + err = gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags)); if (err) return -1; @@ -859,7 +866,8 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; - if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM))) + if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags))) return -1; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, @@ -886,7 +894,8 @@ static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) prepare_ip6gre_xmit_other(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; - err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); + err = gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, + t->parms.o_flags)); if (err) return err; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, skb->protocol); @@ -939,6 +948,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; bool truncate = false; int encap_limit = -1; __u8 dsfield = false; @@ -982,7 +992,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; - t->parms.o_flags &= ~TUNNEL_KEY; + __clear_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); IPCB(skb)->flags = 0; /* For collect_md mode, derive fl6 from the tunnel key, @@ -1007,7 +1017,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, fl6.fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; - if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) + if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_info->key.tun_flags)) goto tx_err; if (tun_info->options_len < sizeof(*md)) goto tx_err; @@ -1068,7 +1079,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, } /* Push GRE header. */ - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); + __set_bit(IP_TUNNEL_SEQ_BIT, flags); + gre_build_header(skb, 8, flags, proto, 0, + htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) @@ -1211,8 +1224,8 @@ static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t, t->parms.proto = p->proto; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; - t->parms.i_flags = p->i_flags; - t->parms.o_flags = p->o_flags; + ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); + ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); t->parms.fwmark = p->fwmark; t->parms.erspan_ver = p->erspan_ver; t->parms.index = p->index; @@ -1241,8 +1254,8 @@ static void ip6gre_tnl_parm_from_user(struct __ip6_tnl_parm *p, p->link = u->link; p->i_key = u->i_key; p->o_key = u->o_key; - p->i_flags = gre_flags_to_tnl_flags(u->i_flags); - p->o_flags = gre_flags_to_tnl_flags(u->o_flags); + gre_flags_to_tnl_flags(p->i_flags, u->i_flags); + gre_flags_to_tnl_flags(p->o_flags, u->o_flags); memcpy(p->name, u->name, sizeof(u->name)); } @@ -1394,7 +1407,7 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, ipv6h->daddr = t->parms.raddr; p = (__be16 *)(ipv6h + 1); - p[0] = t->parms.o_flags; + p[0] = ip_tunnel_flags_to_be16(t->parms.o_flags); p[1] = htons(type); /* @@ -1421,7 +1434,6 @@ static const struct net_device_ops ip6gre_netdev_ops = { .ndo_start_xmit = ip6gre_tunnel_xmit, .ndo_siocdevprivate = ip6gre_tunnel_siocdevprivate, .ndo_change_mtu = ip6_tnl_change_mtu, - .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; @@ -1431,7 +1443,6 @@ static void ip6gre_dev_free(struct net_device *dev) gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); - free_percpu(dev->tstats); } static void ip6gre_tunnel_setup(struct net_device *dev) @@ -1440,6 +1451,7 @@ static void ip6gre_tunnel_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->type = ARPHRD_IP6GRE; dev->flags |= IFF_NOARP; @@ -1458,19 +1470,17 @@ static void ip6gre_tunnel_setup(struct net_device *dev) static void ip6gre_tnl_init_features(struct net_device *dev) { struct ip6_tnl *nt = netdev_priv(dev); - __be16 flags; dev->features |= GRE6_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE6_FEATURES; - flags = nt->parms.o_flags; - /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ - if (flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, nt->parms.o_flags)) return; - if (flags & TUNNEL_CSUM && nt->encap.type != TUNNEL_ENCAP_NONE) + if (test_bit(IP_TUNNEL_CSUM_BIT, nt->parms.o_flags) && + nt->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; @@ -1489,13 +1499,9 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (ret) - goto cleanup_alloc_pcpu_stats; + return ret; ret = gro_cells_init(&tunnel->gro_cells, dev); if (ret) @@ -1519,9 +1525,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) cleanup_dst_cache_init: dst_cache_destroy(&tunnel->dst_cache); -cleanup_alloc_pcpu_stats: - free_percpu(dev->tstats); - dev->tstats = NULL; return ret; } @@ -1795,12 +1798,12 @@ static void ip6gre_netlink_parms(struct nlattr *data[], parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) - parms->i_flags = gre_flags_to_tnl_flags( - nla_get_be16(data[IFLA_GRE_IFLAGS])); + gre_flags_to_tnl_flags(parms->i_flags, + nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) - parms->o_flags = gre_flags_to_tnl_flags( - nla_get_be16(data[IFLA_GRE_OFLAGS])); + gre_flags_to_tnl_flags(parms->o_flags, + nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); @@ -1853,7 +1856,6 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip6_tnl_change_mtu, - .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; @@ -1882,13 +1884,9 @@ static int ip6erspan_tap_init(struct net_device *dev) tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (ret) - goto cleanup_alloc_pcpu_stats; + return ret; ret = gro_cells_init(&tunnel->gro_cells, dev); if (ret) @@ -1910,9 +1908,6 @@ static int ip6erspan_tap_init(struct net_device *dev) cleanup_dst_cache_init: dst_cache_destroy(&tunnel->dst_cache); -cleanup_alloc_pcpu_stats: - free_percpu(dev->tstats); - dev->tstats = NULL; return ret; } @@ -1923,7 +1918,6 @@ static const struct net_device_ops ip6erspan_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip6_tnl_change_mtu, - .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; @@ -1937,6 +1931,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); @@ -2147,11 +2142,13 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; - __be16 o_flags = p->o_flags; + IP_TUNNEL_DECLARE_FLAGS(o_flags); + + ip_tunnel_flags_copy(o_flags, p->o_flags); if (p->erspan_ver == 1 || p->erspan_ver == 2) { if (!p->collect_md) - o_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) goto nla_put_failure; @@ -2237,6 +2234,7 @@ static void ip6erspan_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index c8b909a9904f..9822163428b0 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -67,7 +67,7 @@ static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto) off += len; } - skb_gro_pull(skb, off - skb_network_offset(skb)); + skb_gro_pull(skb, off - skb_gro_receive_network_offset(skb)); return proto; } @@ -236,8 +236,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, if (unlikely(!iph)) goto out; - skb_set_network_header(skb, off); - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; flush += ntohs(iph->payload_len) != skb->len - hlen; @@ -260,7 +259,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, NAPI_GRO_CB(skb)->proto = proto; flush--; - nlen = skb_network_header_len(skb); + nlen = skb_gro_offset(skb) - off; list_for_each_entry(p, head, list) { const struct ipv6hdr *iph2; @@ -291,19 +290,8 @@ not_same_flow: nlen - sizeof(struct ipv6hdr))) goto not_same_flow; } - /* flush if Traffic Class fields are different */ - NAPI_GRO_CB(p)->flush |= !!((first_word & htonl(0x0FF00000)) | - (__force __be32)(iph->hop_limit ^ iph2->hop_limit)); - NAPI_GRO_CB(p)->flush |= flush; - - /* If the previous IP ID value was based on an atomic - * datagram we can overwrite the value and ignore it. - */ - if (NAPI_GRO_CB(skb)->is_atomic) - NAPI_GRO_CB(p)->flush_id = 0; } - NAPI_GRO_CB(skb)->is_atomic = true; NAPI_GRO_CB(skb)->flush |= flush; skb_gro_postpull_rcsum(skb, iph, nlen); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 27d8725445e3..c49344d8311a 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOMEM; } + rcu_read_unlock(); } hdr = ipv6_hdr(skb); @@ -283,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOBUFS; } + rcu_read_unlock(); } if (opt) { @@ -1124,6 +1132,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, from = rt ? rcu_dereference(rt->from) : NULL; err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0, + fl6->flowi6_l3mdev, &fl6->saddr); rcu_read_unlock(); @@ -1952,6 +1961,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; + rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) @@ -1961,6 +1971,7 @@ int ip6_send_skb(struct sk_buff *skb) IPSTATS_MIB_OUTDISCARDS); } + rcu_read_unlock(); return err; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index e9cc315832cb..87dfb565a9f8 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -798,17 +798,15 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, const struct ipv6hdr *ipv6h; int nh, err; - if ((!(tpi->flags & TUNNEL_CSUM) && - (tunnel->parms.i_flags & TUNNEL_CSUM)) || - ((tpi->flags & TUNNEL_CSUM) && - !(tunnel->parms.i_flags & TUNNEL_CSUM))) { + if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != + test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } - if (tunnel->parms.i_flags & TUNNEL_SEQ) { - if (!(tpi->flags & TUNNEL_SEQ) || + if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { + if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); @@ -946,7 +944,9 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (t->parms.collect_md) { - tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0); + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; + + tun_dst = ipv6_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) goto drop; } @@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { - dev->hard_header_len = tdev->hard_header_len + t_hlen; + dev->needed_headroom = tdev->hard_header_len + + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; @@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); + int t_hlen; + t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; @@ -1740,13 +1743,13 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { - if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { - if (new_mtu > IP_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(ip6_tnl_change_mtu); @@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; + dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); @@ -2146,7 +2148,7 @@ struct net *ip6_tnl_get_link_net(const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); - return tunnel->net; + return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip6_tnl_get_link_net); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 7f4f976aa24a..590737c27537 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -174,11 +174,6 @@ vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t) } } -static void vti6_dev_free(struct net_device *dev) -{ - free_percpu(dev->tstats); -} - static int vti6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); @@ -671,7 +666,8 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) dev->flags &= ~IFF_POINTOPOINT; if (keep_mtu && dev->mtu) { - dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu); + WRITE_ONCE(dev->mtu, + clamp(dev->mtu, dev->min_mtu, dev->max_mtu)); return; } @@ -892,7 +888,6 @@ static const struct net_device_ops vti6_netdev_ops = { .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_siocdevprivate = vti6_siocdevprivate, - .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; @@ -908,8 +903,8 @@ static void vti6_dev_setup(struct net_device *dev) dev->netdev_ops = &vti6_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; - dev->priv_destructor = vti6_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->type = ARPHRD_TUNNEL6; dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); @@ -931,9 +926,6 @@ static inline int vti6_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d914b23256ce..0282d1572509 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { + bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; @@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, break; #endif default: - if (ndisc_is_useropt(dev, nd_opt)) { - ndopts->nd_useropts_end = nd_opt; - if (!ndopts->nd_useropts) - ndopts->nd_useropts = nd_opt; - } else { - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the - * protocol. - */ - ND_PRINTK(2, notice, - "%s: ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, - nd_opt->nd_opt_len); - } + unknown = true; + } + if (ndisc_is_useropt(dev, nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else if (unknown) { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); } next_opt: opt_len -= l; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 53d255838e6a..5d989d803009 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -36,6 +36,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, .saddr = iph->saddr, + .flowlabel = ip6_flowinfo(iph), }; int err; diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index df785ebda0ca..e8992693e14a 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -43,7 +43,7 @@ static int ip6table_filter_table_init(struct net *net) return -ENOMEM; /* Entry 1 is the FORWARD hook */ ((struct ip6t_standard *)repl->entries)[1].target.verdict = - forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; + forward ? -NF_ACCEPT - 1 : NF_DROP - 1; err = ip6t_register_table(net, &packet_filter, repl, filter_ops); kfree(repl); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 52cf104e3478..e119d4f090cc 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = { static int __init ip6table_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv6_table, - ip6table_nat_table_init); + int ret; + /* net->gen->ptr[ip6table_nat_net_id] must be allocated + * before calling ip6t_nat_register_lookups(). + */ + ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&ip6table_nat_net_ops); + ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); if (ret) - xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { - unregister_pernet_subsys(&ip6table_nat_net_ops); xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index d0dcbaca1994..3e9779ed7dae 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -62,7 +62,6 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, - { } }; static int nf_ct_frag6_sysctl_register(struct net *net) @@ -105,7 +104,7 @@ err_alloc: static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { struct nft_ct_frag6_pernet *nf_frag = nf_frag_pernet(net); - struct ctl_table *table; + const struct ctl_table *table; table = nf_frag->nf_frag_frags_hdr->ctl_table_arg; unregister_net_sysctl_table(nf_frag->nf_frag_frags_hdr); @@ -155,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q; + if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0; + q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 148bf9e3131a..327caca64257 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -436,7 +436,6 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; /* secret interval has been deprecated */ @@ -449,7 +448,6 @@ static struct ctl_table ip6_frags_ctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; static int __net_init ip6_frags_ns_sysctl_register(struct net *net) @@ -487,7 +485,7 @@ err_alloc: static void __net_exit ip6_frags_ns_sysctl_unregister(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->ipv6.sysctl.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.frags_hdr); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d7a5ca012a8f..c9a9506b714d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5689,7 +5689,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } else if (dest) { struct in6_addr saddr_buf; - if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 && + if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } @@ -6435,7 +6435,6 @@ static struct ctl_table ipv6_route_table_template[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - { } }; struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) @@ -6459,10 +6458,6 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down; - - /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) - table[1].procname = NULL; } return table; diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index a013b92cbb86..2c83b7586422 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -212,9 +212,9 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(err)) goto drop; - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&rlwt->cache); - preempt_enable(); + local_bh_enable(); if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -234,9 +234,9 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; } - preempt_disable(); + local_bh_disable(); dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr); - preempt_enable(); + local_bh_enable(); } skb_dst_drop(skb); @@ -268,23 +268,21 @@ static int rpl_input(struct sk_buff *skb) return err; } - preempt_disable(); + local_bh_disable(); dst = dst_cache_get(&rlwt->cache); - preempt_enable(); if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); if (!dst->error) { - preempt_disable(); dst_cache_set_ip6(&rlwt->cache, dst, &ipv6_hdr(skb)->saddr); - preempt_enable(); } } else { skb_dst_drop(skb); skb_dst_set(skb, dst); } + local_bh_enable(); err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 655c9b1a19b8..83b195f09561 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -132,8 +132,8 @@ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, return NULL; } -static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn, - struct ip_tunnel_parm *parms) +static struct ip_tunnel __rcu ** +__ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm_kern *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; @@ -207,7 +207,7 @@ static int ipip6_tunnel_create(struct net_device *dev) __dev_addr_set(dev, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); - if ((__force u16)t->parms.i_flags & SIT_ISATAP) + if (test_bit(IP_TUNNEL_SIT_ISATAP_BIT, t->parms.i_flags)) dev->priv_flags |= IFF_ISATAP; dev->rtnl_link_ops = &sit_link_ops; @@ -226,7 +226,8 @@ out: } static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, - struct ip_tunnel_parm *parms, int create) + struct ip_tunnel_parm_kern *parms, + int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; @@ -1135,7 +1136,8 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) dev->needed_headroom = t_hlen + hlen; } -static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, +static void ipip6_tunnel_update(struct ip_tunnel *t, + struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct net *net = t->net; @@ -1196,11 +1198,11 @@ static int ipip6_tunnel_get6rd(struct net_device *dev, struct ip_tunnel_parm __user *data) { struct ip_tunnel *t = netdev_priv(dev); + struct ip_tunnel_parm_kern p; struct ip_tunnel_6rd ip6rd; - struct ip_tunnel_parm p; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { - if (copy_from_user(&p, data, sizeof(p))) + if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; t = ipip6_tunnel_locate(t->net, &p, 0); } @@ -1251,7 +1253,7 @@ static bool ipip6_valid_ip_proto(u8 ipproto) } static int -__ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm *p) +__ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm_kern *p) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1268,7 +1270,7 @@ __ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); @@ -1281,7 +1283,7 @@ ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; @@ -1297,7 +1299,7 @@ ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; @@ -1328,7 +1330,7 @@ ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm *p) +ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); @@ -1348,7 +1350,8 @@ ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm *p) } static int -ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) +ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, + int cmd) { switch (cmd) { case SIOCGETTUNNEL: @@ -1490,7 +1493,7 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], } static void ipip6_netlink_parms(struct nlattr *data[], - struct ip_tunnel_parm *parms, + struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); @@ -1599,8 +1602,8 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; + struct ip_tunnel_parm_kern p; struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD @@ -1687,7 +1690,7 @@ static size_t ipip6_get_size(const struct net_device *dev) static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct ip_tunnel_parm *parm = &tunnel->parms; + struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || @@ -1697,7 +1700,8 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || - nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags) || + nla_put_be16(skb, IFLA_IPTUN_FLAGS, + ip_tunnel_flags_to_be16(parm->i_flags)) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 6d8286c299c9..bfad1e89b6a6 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -246,7 +246,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } } - req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); + req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? :dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 888676163e90..c060285ff47f 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -213,7 +213,6 @@ static struct ctl_table ipv6_table_template[] = { .proc_handler = proc_doulongvec_minmax, .extra2 = &ioam6_id_wide_max, }, - { } }; static struct ctl_table ipv6_rotable[] = { @@ -248,11 +247,11 @@ static struct ctl_table ipv6_rotable[] = { .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ - { } }; static int __net_init ipv6_sysctl_net_init(struct net *net) { + size_t table_size = ARRAY_SIZE(ipv6_table_template); struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; @@ -264,7 +263,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) if (!ipv6_table) goto out; /* Update the variables to point into the current struct net */ - for (i = 0; i < ARRAY_SIZE(ipv6_table_template) - 1; i++) + for (i = 0; i < table_size; i++) ipv6_table[i].data += (void *)net - (void *)&init_net; ipv6_route_table = ipv6_route_sysctl_init(net); @@ -276,8 +275,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) goto out_ipv6_route_table; net->ipv6.sysctl.hdr = register_net_sysctl_sz(net, "net/ipv6", - ipv6_table, - ARRAY_SIZE(ipv6_table_template)); + ipv6_table, table_size); if (!net->ipv6.sysctl.hdr) goto out_ipv6_icmp_table; @@ -313,9 +311,9 @@ out_ipv6_table: static void __net_exit ipv6_sysctl_net_exit(struct net *net) { - struct ctl_table *ipv6_table; - struct ctl_table *ipv6_route_table; - struct ctl_table *ipv6_icmp_table; + const struct ctl_table *ipv6_table; + const struct ctl_table *ipv6_route_table; + const struct ctl_table *ipv6_icmp_table; ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2b2eda5a2894..3385faf1d5dc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -60,6 +60,7 @@ #include <net/secure_seq.h> #include <net/hotdata.h> #include <net/busy_poll.h> +#include <net/rstreason.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -69,7 +70,8 @@ #include <trace/events/tcp.h> -static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb); +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, + enum sk_rst_reason reason); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); @@ -488,14 +490,10 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); - if (!sock_owned_by_user(sk)) { - WRITE_ONCE(sk->sk_err, err); - sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ - - tcp_done(sk); - } else { + if (!sock_owned_by_user(sk)) + tcp_done_with_error(sk, err); + else WRITE_ONCE(sk->sk_err_soft, err); - } goto out; case TCP_LISTEN: break; @@ -791,7 +789,8 @@ clear_hash_nostart: static void tcp_v6_init_req(struct request_sock *req, const struct sock *sk_listener, - struct sk_buff *skb) + struct sk_buff *skb, + u32 tw_isn) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); struct inet_request_sock *ireq = inet_rsk(req); @@ -805,7 +804,7 @@ static void tcp_v6_init_req(struct request_sock *req, ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); - if (!TCP_SKB_CB(skb)->tcp_tw_isn && + if (!tw_isn && (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || @@ -818,9 +817,10 @@ static void tcp_v6_init_req(struct request_sock *req, static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req) + struct request_sock *req, + u32 tw_isn) { - tcp_v6_init_req(req, sk, skb); + tcp_v6_init_req(req, sk, skb, tw_isn); if (security_inet_conn_request(sk, skb, req)) return NULL; @@ -1004,7 +1004,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 kfree_skb(buff); } -static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, + enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); @@ -1111,7 +1112,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) if (sk) { oif = sk->sk_bound_dev_if; if (sk_fullsock(sk)) { - trace_tcp_send_reset(sk, skb); if (inet6_test_bit(REPFLOW, sk)) label = ip6_flowlabel(ipv6h); priority = READ_ONCE(sk->sk_priority); @@ -1127,6 +1127,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) label = ip6_flowlabel(ipv6h); } + trace_tcp_send_reset(sk, skb, reason); + tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1, ipv6_get_dsfield(ipv6h), label, priority, txhash, &key); @@ -1266,15 +1268,10 @@ 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 >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, &key, ipv6_get_dsfield(ipv6_hdr(skb)), 0, @@ -1673,7 +1670,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; reset: - tcp_v6_send_reset(sk, skb); + tcp_v6_send_reset(sk, skb, sk_rst_convert_drop_reason(reason)); discard: if (opt_skb) __kfree_skb(opt_skb); @@ -1737,7 +1734,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); - TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = @@ -1754,6 +1750,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) bool refcounted; struct sock *sk; int ret; + u32 isn; struct net *net = dev_net(skb->dev); drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; @@ -1790,7 +1787,6 @@ lookup: if (!sk) goto no_tcp_socket; -process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; @@ -1859,7 +1855,10 @@ process: } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { - tcp_v6_send_reset(nsk, skb); + enum sk_rst_reason rst_reason; + + rst_reason = sk_rst_convert_drop_reason(drop_reason); + tcp_v6_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); @@ -1867,6 +1866,7 @@ process: } } +process: if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (unlikely(hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount))) { @@ -1935,7 +1935,7 @@ csum_error: bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { - tcp_v6_send_reset(NULL, skb); + tcp_v6_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: @@ -1963,7 +1963,7 @@ do_time_wait: goto csum_error; } - switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { + switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) { case TCP_TW_SYN: { struct sock *sk2; @@ -1981,6 +1981,7 @@ do_time_wait: sk = sk2; tcp_v6_restore_cb(skb); refcounted = false; + __this_cpu_write(tcp_tw_isn, isn); goto process; } } @@ -1990,7 +1991,7 @@ do_time_wait: tcp_v6_timewait_ack(sk, skb); break; case TCP_TW_RST: - tcp_v6_send_reset(sk, skb); + tcp_v6_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS: @@ -2040,7 +2041,6 @@ void tcp_v6_early_demux(struct sk_buff *skb) static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), - .twsk_unique = tcp_twsk_unique, .twsk_destructor = tcp_twsk_destructor, }; @@ -2388,15 +2388,9 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } -static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) -{ - tcp_twsk_purge(net_exit_list, AF_INET6); -} - static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, - .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 4b07d1e6c952..23971903e66d 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -7,31 +7,84 @@ */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> +#include <net/inet6_hashtables.h> #include <net/gro.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" +static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb, + struct tcphdr *th) +{ +#if IS_ENABLED(CONFIG_IPV6) + const struct ipv6hdr *hdr; + struct sk_buff *p; + struct sock *sk; + struct net *net; + int iif, sdif; + + if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST))) + return; + + p = tcp_gro_lookup(head, th); + if (p) { + NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist; + return; + } + + inet6_get_iif_sdif(skb, &iif, &sdif); + hdr = skb_gro_network_header(skb); + net = dev_net(skb->dev); + sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, + &hdr->saddr, th->source, + &hdr->daddr, ntohs(th->dest), + iif, sdif); + NAPI_GRO_CB(skb)->is_flist = !sk; + if (sk) + sock_put(sk); +#endif /* IS_ENABLED(CONFIG_IPV6) */ +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb) { + struct tcphdr *th; + /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, - ip6_gro_compute_pseudo)) { - NAPI_GRO_CB(skb)->flush = 1; - return NULL; - } + ip6_gro_compute_pseudo)) + goto flush; - return tcp_gro_receive(head, skb); + th = tcp_gro_pull_header(skb); + if (!th) + goto flush; + + tcp6_check_fraglist_gro(head, skb, th); + + return tcp_gro_receive(head, skb, th); + +flush: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; } INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff) { - const struct ipv6hdr *iph = ipv6_hdr(skb); + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset); struct tcphdr *th = tcp_hdr(skb); + if (unlikely(NAPI_GRO_CB(skb)->is_flist)) { + skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV6; + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + __skb_incr_checksum_unnecessary(skb); + + return 0; + } + th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; @@ -40,6 +93,61 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff) return 0; } +static void __tcpv6_gso_segment_csum(struct sk_buff *seg, + __be16 *oldport, __be16 newport) +{ + struct tcphdr *th; + + if (*oldport == newport) + return; + + th = tcp_hdr(seg); + inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false); + *oldport = newport; +} + +static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs) +{ + const struct tcphdr *th; + const struct ipv6hdr *iph; + struct sk_buff *seg; + struct tcphdr *th2; + struct ipv6hdr *iph2; + + seg = segs; + th = tcp_hdr(seg); + iph = ipv6_hdr(seg); + th2 = tcp_hdr(seg->next); + iph2 = ipv6_hdr(seg->next); + + if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) && + ipv6_addr_equal(&iph->saddr, &iph2->saddr) && + ipv6_addr_equal(&iph->daddr, &iph2->daddr)) + return segs; + + while ((seg = seg->next)) { + th2 = tcp_hdr(seg); + iph2 = ipv6_hdr(seg); + + iph2->saddr = iph->saddr; + iph2->daddr = iph->daddr; + __tcpv6_gso_segment_csum(seg, &th2->source, th->source); + __tcpv6_gso_segment_csum(seg, &th2->dest, th->dest); + } + + return segs; +} + +static struct sk_buff *__tcp6_gso_segment_list(struct sk_buff *skb, + netdev_features_t features) +{ + skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); + if (IS_ERR(skb)) + return skb; + + return __tcpv6_gso_segment_list_csum(skb); +} + static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, netdev_features_t features) { @@ -51,6 +159,9 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL); + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) + return __tcp6_gso_segment_list(skb, features); + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index acafa0cdf74a..c81a07ac0463 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/indirect_call_wrapper.h> +#include <trace/events/udp.h> #include <net/addrconf.h> #include <net/ndisc.h> @@ -671,8 +672,8 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) drop_reason = SKB_DROP_REASON_PROTO_MEM; } UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); kfree_skb_reason(skb, drop_reason); - trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index c6b8e132e10a..4abc5e9d6322 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -113,19 +113,6 @@ static int __xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb, bool pull /* Must be an IKE packet.. pass it through */ return 1; break; - case UDP_ENCAP_ESPINUDP_NON_IKE: - /* Check if this is a keepalive packet. If so, eat it. */ - if (len == 1 && udpdata[0] == 0xff) { - return -EINVAL; - } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && - udpdata32[0] == 0 && udpdata32[1] == 0) { - - /* ESP Packet with Non-IKE marker */ - len = sizeof(struct udphdr) + 2 * sizeof(u32); - } else - /* Must be an IKE packet.. pass it through */ - return 1; - break; } /* At this point we are sure that this is an ESPinUDP packet, @@ -283,6 +270,13 @@ int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, if (!x) continue; + if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); + xfrm_state_put(x); + x = NULL; + continue; + } + spin_lock(&x->lock); if ((!i || (x->props.flags & XFRM_STATE_WILDRECV)) && diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 4332d4b82b1d..2f1ea5f999a2 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -190,7 +190,6 @@ static struct ctl_table xfrm6_policy_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static int __net_init xfrm6_net_sysctl_init(struct net *net) @@ -224,7 +223,7 @@ err_alloc: static void __net_exit xfrm6_net_sysctl_exit(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; if (!net->ipv6.sysctl.xfrm6_hdr) return; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 7c8c3adcac6e..c00323fa9eb6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -184,7 +184,7 @@ static void iucv_sock_wake_msglim(struct sock *sk) wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_all(&wq->wait); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } @@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) struct iucv_sock *iucv = iucv_sk(sk); struct iucv_path *path = iucv->path; - if (iucv->path) { - iucv->path = NULL; + /* Whoever resets the path pointer, must sever and free it. */ + if (xchg(&iucv->path, NULL)) { if (with_user_data) { low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); @@ -795,7 +795,7 @@ done: /* Accept a pending connection */ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *nsk; @@ -809,7 +809,7 @@ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, goto done; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); /* Wait for an incoming connection */ add_wait_queue_exclusive(sk_sleep(sk), &wait); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index a4ab615ca3e3..123530702007 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -73,8 +73,44 @@ const struct bus_type iucv_bus = { }; EXPORT_SYMBOL(iucv_bus); -struct device *iucv_root; -EXPORT_SYMBOL(iucv_root); +static struct device *iucv_root; + +static void iucv_release_device(struct device *device) +{ + kfree(device); +} + +struct device *iucv_alloc_device(const struct attribute_group **attrs, + struct device_driver *driver, + void *priv, const char *fmt, ...) +{ + struct device *dev; + va_list vargs; + char buf[20]; + int rc; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + goto out_error; + va_start(vargs, fmt); + vsnprintf(buf, sizeof(buf), fmt, vargs); + rc = dev_set_name(dev, "%s", buf); + va_end(vargs); + if (rc) + goto out_error; + dev->bus = &iucv_bus; + dev->parent = iucv_root; + dev->driver = driver; + dev->groups = attrs; + dev->release = iucv_release_device; + dev_set_drvdata(dev, priv); + return dev; + +out_error: + kfree(dev); + return NULL; +} +EXPORT_SYMBOL(iucv_alloc_device); static int iucv_available; @@ -520,7 +556,7 @@ static void iucv_setmask_mp(void) */ static void iucv_setmask_up(void) { - cpumask_t cpumask; + static cpumask_t cpumask; int cpu; /* Disable all cpu but the first in cpu_irq_cpumask. */ @@ -628,23 +664,33 @@ static int iucv_cpu_online(unsigned int cpu) static int iucv_cpu_down_prep(unsigned int cpu) { - cpumask_t cpumask; + cpumask_var_t cpumask; + int ret = 0; if (!iucv_path_table) return 0; - cpumask_copy(&cpumask, &iucv_buffer_cpumask); - cpumask_clear_cpu(cpu, &cpumask); - if (cpumask_empty(&cpumask)) + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_copy(cpumask, &iucv_buffer_cpumask); + cpumask_clear_cpu(cpu, cpumask); + if (cpumask_empty(cpumask)) { /* Can't offline last IUCV enabled cpu. */ - return -EINVAL; + ret = -EINVAL; + goto __free_cpumask; + } iucv_retrieve_cpu(NULL); if (!cpumask_empty(&iucv_irq_cpumask)) - return 0; + goto __free_cpumask; + smp_call_function_single(cpumask_first(&iucv_buffer_cpumask), iucv_allow_cpu, NULL, 1); - return 0; + +__free_cpumask: + free_cpumask_var(cpumask); + return ret; } /** diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2f191e50d4fc..d4118c796290 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -926,6 +927,7 @@ partial_message: KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -951,6 +953,7 @@ out_error: sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 4a0fb8731eee..7ea4adf81d85 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -88,6 +88,11 @@ /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 +#define L2TP_DEPTH_NESTING 2 +#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING +#error "L2TP requires its own lockdep subclass" +#endif + /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { @@ -794,6 +799,7 @@ static void l2tp_session_queue_purge(struct l2tp_session *session) static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) { struct l2tp_session *session = NULL; + struct l2tp_tunnel *orig_tunnel = tunnel; unsigned char *ptr, *optr; u16 hdrflags; u32 tunnel_id, session_id; @@ -819,13 +825,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Get L2TP header flags */ hdrflags = ntohs(*(__be16 *)ptr); - /* Check protocol version */ + /* Get protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; - if (version != tunnel->version) { - pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); - goto invalid; - } /* Get length of L2TP packet */ length = skb->len; @@ -837,7 +838,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Skip flags */ ptr += 2; - if (tunnel->version == L2TP_HDR_VER_2) { + if (version == L2TP_HDR_VER_2) { /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; @@ -845,6 +846,20 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; + + if (tunnel_id != tunnel->tunnel_id) { + /* We are receiving trafic for another tunnel, probably + * because we have several tunnels between the same + * IP/port quadruple, look it up. + */ + struct l2tp_tunnel *alt_tunnel; + + alt_tunnel = l2tp_tunnel_get(tunnel->l2tp_net, tunnel_id); + if (!alt_tunnel) + goto pass; + tunnel = alt_tunnel; + } + session_id = ntohs(*(__be16 *)ptr); ptr += 2; } else { @@ -854,6 +869,13 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) ptr += 4; } + /* Check protocol version */ + if (version != tunnel->version) { + pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); + goto invalid; + } + /* Find the session context */ session = l2tp_tunnel_get_session(tunnel, session_id); if (!session || !session->recv_skb) { @@ -875,6 +897,9 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); + if (tunnel != orig_tunnel) + l2tp_tunnel_dec_refcount(tunnel); + return 0; invalid: @@ -884,6 +909,9 @@ pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); + if (tunnel != orig_tunnel) + l2tp_tunnel_dec_refcount(tunnel); + return 1; } @@ -1062,7 +1090,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); - bh_lock_sock_nested(sk); + /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by + * nested socket calls on the same lockdep socket class. This can + * happen when data from a user socket is routed over l2tp, which uses + * another userspace socket. + */ + spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); + if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1114,7 +1148,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: - bh_unlock_sock(sk); + spin_unlock(&sk->sk_lock.slock); return ret; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index fde1140d899e..4eb52add7103 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -688,14 +688,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) * llc_ui_accept - accept a new incoming connection. * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. - * @flags: User specified operational flags. - * @kern: If the socket is kernel internal + * @arg: User specified arguments * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ -static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int llc_ui_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c index 8443a6d841b0..72e101135f8c 100644 --- a/net/llc/sysctl_net_llc.c +++ b/net/llc/sysctl_net_llc.c @@ -44,11 +44,6 @@ static struct ctl_table llc2_timeout_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { }, -}; - -static struct ctl_table llc_station_table[] = { - { }, }; static struct ctl_table_header *llc2_timeout_header; @@ -56,8 +51,9 @@ static struct ctl_table_header *llc_station_header; int __init llc_sysctl_init(void) { + struct ctl_table empty[1] = {}; llc2_timeout_header = register_net_sysctl(&init_net, "net/llc/llc2/timeout", llc2_timeout_table); - llc_station_header = register_net_sysctl(&init_net, "net/llc/station", llc_station_table); + llc_station_header = register_net_sysctl_sz(&init_net, "net/llc/station", empty, 0); if (!llc2_timeout_header || !llc_station_header) { llc_sysctl_exit(); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 21d55dc539f6..677bbbac9f16 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -616,7 +616,9 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, return -EINVAL; if (!pubsta->deflink.ht_cap.ht_supported && - sta->sdata->vif.bss_conf.chanreq.oper.chan->band != NL80211_BAND_6GHZ) + !pubsta->deflink.vht_cap.vht_supported && + !pubsta->deflink.he_cap.has_he && + !pubsta->deflink.eht_cap.has_eht) return -EINVAL; if (WARN_ON_ONCE(!local->ops->ampdu_action)) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 51dc2d9dd6b8..87a7b569cc77 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, /* apply all changes now - no failures allowed */ - if (monitor_sdata) + if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { @@ -1486,7 +1486,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(link->u.ap.beacon, NULL); - sdata->u.ap.active = false; + + if (ieee80211_num_beaconing_links(sdata) == 0) + sdata->u.ap.active = false; + goto error; } @@ -1619,11 +1622,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_off(vlan->dev); - if (ieee80211_num_beaconing_links(sdata) <= 1) + if (ieee80211_num_beaconing_links(sdata) <= 1) { netif_carrier_off(dev); + sdata->u.ap.active = false; + } /* remove beacon and probe response */ - sdata->u.ap.active = false; RCU_INIT_POINTER(link->u.ap.beacon, NULL); RCU_INIT_POINTER(link->u.ap.probe_resp, NULL); RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); @@ -2954,8 +2958,9 @@ static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev, memcpy(sdata->vif.bss_conf.mcast_rate, rate, sizeof(int) * NUM_NL80211_BANDS); - ieee80211_link_info_change_notify(sdata, &sdata->deflink, - BSS_CHANGED_MCAST_RATE); + if (ieee80211_sdata_running(sdata)) + ieee80211_link_info_change_notify(sdata, &sdata->deflink, + BSS_CHANGED_MCAST_RATE); return 0; } @@ -3033,6 +3038,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return -EOPNOTSUPP; + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) @@ -3095,7 +3103,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; @@ -3914,13 +3922,13 @@ static int ieee80211_set_csa_beacon(struct ieee80211_link_data *link_data, return 0; } -static void ieee80211_color_change_abort(struct ieee80211_sub_if_data *sdata) +static void ieee80211_color_change_abort(struct ieee80211_link_data *link) { - sdata->vif.bss_conf.color_change_active = false; + link->conf->color_change_active = false; - ieee80211_free_next_beacon(&sdata->deflink); + ieee80211_free_next_beacon(link); - cfg80211_color_change_aborted_notify(sdata->dev); + cfg80211_color_change_aborted_notify(link->sdata->dev, link->link_id); } static int @@ -4004,7 +4012,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, /* if there is a color change in progress, abort it */ if (link_conf->color_change_active) - ieee80211_color_change_abort(sdata); + ieee80211_color_change_abort(link_data); err = ieee80211_set_csa_beacon(link_data, params, &changed); if (err) { @@ -4662,20 +4670,22 @@ static int ieee80211_set_sar_specs(struct wiphy *wiphy, } static int -ieee80211_set_after_color_change_beacon(struct ieee80211_sub_if_data *sdata, +ieee80211_set_after_color_change_beacon(struct ieee80211_link_data *link, u64 *changed) { + struct ieee80211_sub_if_data *sdata = link->sdata; + switch (sdata->vif.type) { case NL80211_IFTYPE_AP: { int ret; - if (!sdata->deflink.u.ap.next_beacon) + if (!link->u.ap.next_beacon) return -EINVAL; - ret = ieee80211_assign_beacon(sdata, &sdata->deflink, - sdata->deflink.u.ap.next_beacon, + ret = ieee80211_assign_beacon(sdata, link, + link->u.ap.next_beacon, NULL, NULL, changed); - ieee80211_free_next_beacon(&sdata->deflink); + ieee80211_free_next_beacon(link); if (ret < 0) return ret; @@ -4691,18 +4701,19 @@ ieee80211_set_after_color_change_beacon(struct ieee80211_sub_if_data *sdata, } static int -ieee80211_set_color_change_beacon(struct ieee80211_sub_if_data *sdata, +ieee80211_set_color_change_beacon(struct ieee80211_link_data *link, struct cfg80211_color_change_settings *params, u64 *changed) { + struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_color_change_settings color_change = {}; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: - sdata->deflink.u.ap.next_beacon = + link->u.ap.next_beacon = cfg80211_beacon_dup(¶ms->beacon_next); - if (!sdata->deflink.u.ap.next_beacon) + if (!link->u.ap.next_beacon) return -ENOMEM; if (params->count <= 1) @@ -4714,11 +4725,11 @@ ieee80211_set_color_change_beacon(struct ieee80211_sub_if_data *sdata, params->counter_offset_presp; color_change.count = params->count; - err = ieee80211_assign_beacon(sdata, &sdata->deflink, + err = ieee80211_assign_beacon(sdata, link, ¶ms->beacon_color_change, NULL, &color_change, changed); if (err < 0) { - ieee80211_free_next_beacon(&sdata->deflink); + ieee80211_free_next_beacon(link); return err; } break; @@ -4730,16 +4741,18 @@ ieee80211_set_color_change_beacon(struct ieee80211_sub_if_data *sdata, } static void -ieee80211_color_change_bss_config_notify(struct ieee80211_sub_if_data *sdata, +ieee80211_color_change_bss_config_notify(struct ieee80211_link_data *link, u8 color, int enable, u64 changed) { + struct ieee80211_sub_if_data *sdata = link->sdata; + lockdep_assert_wiphy(sdata->local->hw.wiphy); - sdata->vif.bss_conf.he_bss_color.color = color; - sdata->vif.bss_conf.he_bss_color.enabled = enable; + link->conf->he_bss_color.color = color; + link->conf->he_bss_color.enabled = enable; changed |= BSS_CHANGED_HE_BSS_COLOR; - ieee80211_link_info_change_notify(sdata, &sdata->deflink, changed); + ieee80211_link_info_change_notify(sdata, link, changed); if (!sdata->vif.bss_conf.nontransmitted && sdata->vif.mbssid_tx_vif) { struct ieee80211_sub_if_data *child; @@ -4756,26 +4769,27 @@ ieee80211_color_change_bss_config_notify(struct ieee80211_sub_if_data *sdata, } } -static int ieee80211_color_change_finalize(struct ieee80211_sub_if_data *sdata) +static int ieee80211_color_change_finalize(struct ieee80211_link_data *link) { + struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); - sdata->vif.bss_conf.color_change_active = false; + link->conf->color_change_active = false; - err = ieee80211_set_after_color_change_beacon(sdata, &changed); + err = ieee80211_set_after_color_change_beacon(link, &changed); if (err) { - cfg80211_color_change_aborted_notify(sdata->dev); + cfg80211_color_change_aborted_notify(sdata->dev, link->link_id); return err; } - ieee80211_color_change_bss_config_notify(sdata, - sdata->vif.bss_conf.color_change_color, + ieee80211_color_change_bss_config_notify(link, + link->conf->color_change_color, 1, changed); - cfg80211_color_change_notify(sdata->dev); + cfg80211_color_change_notify(sdata->dev, link->link_id); return 0; } @@ -4783,21 +4797,23 @@ static int ieee80211_color_change_finalize(struct ieee80211_sub_if_data *sdata) void ieee80211_color_change_finalize_work(struct wiphy *wiphy, struct wiphy_work *work) { - struct ieee80211_sub_if_data *sdata = - container_of(work, struct ieee80211_sub_if_data, - deflink.color_change_finalize_work); + struct ieee80211_link_data *link = + container_of(work, struct ieee80211_link_data, + color_change_finalize_work); + struct ieee80211_sub_if_data *sdata = link->sdata; + struct ieee80211_bss_conf *link_conf = link->conf; struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); /* AP might have been stopped while waiting for the lock. */ - if (!sdata->vif.bss_conf.color_change_active) + if (!link_conf->color_change_active) return; if (!ieee80211_sdata_running(sdata)) return; - ieee80211_color_change_finalize(sdata); + ieee80211_color_change_finalize(link); } void ieee80211_color_collision_detection_work(struct work_struct *work) @@ -4808,30 +4824,60 @@ void ieee80211_color_collision_detection_work(struct work_struct *work) color_collision_detect_work); struct ieee80211_sub_if_data *sdata = link->sdata; - cfg80211_obss_color_collision_notify(sdata->dev, link->color_bitmap); + cfg80211_obss_color_collision_notify(sdata->dev, link->color_bitmap, + link->link_id); } -void ieee80211_color_change_finish(struct ieee80211_vif *vif) +void ieee80211_color_change_finish(struct ieee80211_vif *vif, u8 link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_link_data *link; + + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return; + + rcu_read_lock(); + + link = rcu_dereference(sdata->link[link_id]); + if (WARN_ON(!link)) { + rcu_read_unlock(); + return; + } wiphy_work_queue(sdata->local->hw.wiphy, - &sdata->deflink.color_change_finalize_work); + &link->color_change_finalize_work); + + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); void ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap) + u64 color_bitmap, u8 link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - struct ieee80211_link_data *link = &sdata->deflink; + struct ieee80211_link_data *link; + + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return; + + rcu_read_lock(); - if (sdata->vif.bss_conf.color_change_active || sdata->vif.bss_conf.csa_active) + link = rcu_dereference(sdata->link[link_id]); + if (WARN_ON(!link)) { + rcu_read_unlock(); return; + } - if (delayed_work_pending(&link->color_collision_detect_work)) + if (link->conf->color_change_active || link->conf->csa_active) { + rcu_read_unlock(); return; + } + + if (delayed_work_pending(&link->color_collision_detect_work)) { + rcu_read_unlock(); + return; + } link->color_bitmap = color_bitmap; /* queue the color collision detection event every 500 ms in order to @@ -4840,6 +4886,8 @@ ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, ieee80211_queue_delayed_work(&sdata->local->hw, &link->color_collision_detect_work, msecs_to_jiffies(500)); + + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_obss_color_collision_notify); @@ -4849,36 +4897,48 @@ ieee80211_color_change(struct wiphy *wiphy, struct net_device *dev, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; + struct ieee80211_bss_conf *link_conf; + struct ieee80211_link_data *link; + u8 link_id = params->link_id; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); - if (sdata->vif.bss_conf.nontransmitted) + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return -EINVAL; + + link = wiphy_dereference(wiphy, sdata->link[link_id]); + if (!link) + return -ENOLINK; + + link_conf = link->conf; + + if (link_conf->nontransmitted) return -EINVAL; /* don't allow another color change if one is already active or if csa * is active */ - if (sdata->vif.bss_conf.color_change_active || sdata->vif.bss_conf.csa_active) { + if (link_conf->color_change_active || link_conf->csa_active) { err = -EBUSY; goto out; } - err = ieee80211_set_color_change_beacon(sdata, params, &changed); + err = ieee80211_set_color_change_beacon(link, params, &changed); if (err) goto out; - sdata->vif.bss_conf.color_change_active = true; - sdata->vif.bss_conf.color_change_color = params->color; + link_conf->color_change_active = true; + link_conf->color_change_color = params->color; - cfg80211_color_change_started_notify(sdata->dev, params->count); + cfg80211_color_change_started_notify(sdata->dev, params->count, link_id); if (changed) - ieee80211_color_change_bss_config_notify(sdata, 0, 0, changed); + ieee80211_color_change_bss_config_notify(link, 0, 0, changed); else /* if the beacon didn't change, we can finalize immediately */ - ieee80211_color_change_finalize(sdata); + ieee80211_color_change_finalize(link); out: diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index ccacaed32817..e6a7ff6ca679 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -547,8 +547,10 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, _ieee80211_change_chanctx(local, ctx, old_ctx, chanreq, NULL); } +/* Note: if successful, the returned chanctx is reserved for the link */ static struct ieee80211_chanctx * ieee80211_find_chanctx(struct ieee80211_local *local, + struct ieee80211_link_data *link, const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode) { @@ -560,6 +562,9 @@ ieee80211_find_chanctx(struct ieee80211_local *local, if (mode == IEEE80211_CHANCTX_EXCLUSIVE) return NULL; + if (WARN_ON(link->reserved_chanctx)) + return NULL; + list_for_each_entry(ctx, &local->chanctx_list, list) { const struct ieee80211_chan_req *compat; @@ -578,6 +583,16 @@ ieee80211_find_chanctx(struct ieee80211_local *local, if (!compat) continue; + /* + * Reserve the chanctx temporarily, as the driver might change + * active links during callbacks we make into it below and/or + * later during assignment, which could (otherwise) cause the + * context to actually be removed. + */ + link->reserved_chanctx = ctx; + list_add(&link->reserved_chanctx_list, + &ctx->reserved_links); + ieee80211_change_chanctx(local, ctx, ctx, compat); return ctx; @@ -673,7 +688,8 @@ static int ieee80211_add_chanctx(struct ieee80211_local *local, static struct ieee80211_chanctx * ieee80211_new_chanctx(struct ieee80211_local *local, const struct ieee80211_chan_req *chanreq, - enum ieee80211_chanctx_mode mode) + enum ieee80211_chanctx_mode mode, + bool assign_on_failure) { struct ieee80211_chanctx *ctx; int err; @@ -685,36 +701,41 @@ ieee80211_new_chanctx(struct ieee80211_local *local, return ERR_PTR(-ENOMEM); err = ieee80211_add_chanctx(local, ctx); - if (err) { + if (!assign_on_failure && err) { kfree(ctx); return ERR_PTR(err); } + /* We ignored a driver error, see _ieee80211_set_active_links */ + WARN_ON_ONCE(err && !local->in_reconfig); list_add_rcu(&ctx->list, &local->chanctx_list); return ctx; } static void ieee80211_del_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) + struct ieee80211_chanctx *ctx, + bool skip_idle_recalc) { lockdep_assert_wiphy(local->hw.wiphy); drv_remove_chanctx(local, ctx); - ieee80211_recalc_idle(local); + if (!skip_idle_recalc) + ieee80211_recalc_idle(local); ieee80211_remove_wbrf(local, &ctx->conf.def); } static void ieee80211_free_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) + struct ieee80211_chanctx *ctx, + bool skip_idle_recalc) { lockdep_assert_wiphy(local->hw.wiphy); WARN_ON_ONCE(ieee80211_chanctx_refcount(local, ctx) != 0); list_del_rcu(&ctx->list); - ieee80211_del_chanctx(local, ctx); + ieee80211_del_chanctx(local, ctx, skip_idle_recalc); kfree_rcu(ctx, rcu_head); } @@ -754,13 +775,24 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, /* TDLS peers can sometimes affect the chandef width */ list_for_each_entry(sta, &local->sta_list, list) { + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_chan_req tdls_chanreq = {}; + int tdls_link_id; + if (!sta->uploaded || !test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) || !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->tdls_chandef.chan) continue; + tdls_link_id = ieee80211_tdls_sta_link_id(sta); + link = sdata_dereference(sdata->link[tdls_link_id], sdata); + if (!link) + continue; + + if (rcu_access_pointer(link->conf->chanctx_conf) != conf) + continue; + tdls_chanreq.oper = sta->tdls_chandef; /* note this always fills and returns &tmp if compat */ @@ -791,14 +823,15 @@ static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, } static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, - struct ieee80211_chanctx *new_ctx) + struct ieee80211_chanctx *new_ctx, + bool assign_on_failure) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *curr_ctx = NULL; bool new_idle; - int ret = 0; + int ret; if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_NAN)) return -EOPNOTSUPP; @@ -819,15 +852,20 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, ieee80211_recalc_chanctx_min_def(local, new_ctx, link); ret = drv_assign_vif_chanctx(local, sdata, link->conf, new_ctx); - if (ret) - goto out; - - conf = &new_ctx->conf; - list_add(&link->assigned_chanctx_list, - &new_ctx->assigned_links); + if (assign_on_failure || !ret) { + /* Need to continue, see _ieee80211_set_active_links */ + WARN_ON_ONCE(ret && !local->in_reconfig); + ret = 0; + + /* succeeded, so commit it to the data structures */ + conf = &new_ctx->conf; + list_add(&link->assigned_chanctx_list, + &new_ctx->assigned_links); + } + } else { + ret = 0; } -out: rcu_assign_pointer(link->conf->chanctx_conf, conf); if (curr_ctx && ieee80211_chanctx_num_assigned(local, curr_ctx) > 0) { @@ -1019,7 +1057,7 @@ int ieee80211_link_unreserve_chanctx(struct ieee80211_link_data *link) list_del_rcu(&ctx->list); kfree_rcu(ctx, rcu_head); } else { - ieee80211_free_chanctx(sdata->local, ctx); + ieee80211_free_chanctx(sdata->local, ctx, false); } } @@ -1044,7 +1082,8 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, new_ctx = ieee80211_find_reservation_chanctx(local, chanreq, mode); if (!new_ctx) { if (ieee80211_can_create_new_chanctx(local)) { - new_ctx = ieee80211_new_chanctx(local, chanreq, mode); + new_ctx = ieee80211_new_chanctx(local, chanreq, mode, + false); if (IS_ERR(new_ctx)) return PTR_ERR(new_ctx); } else { @@ -1235,7 +1274,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) CHANCTX_SWMODE_REASSIGN_VIF); if (err) { if (ieee80211_chanctx_refcount(local, new_ctx) == 0) - ieee80211_free_chanctx(local, new_ctx); + ieee80211_free_chanctx(local, new_ctx, false); goto out; } @@ -1249,7 +1288,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) ieee80211_check_fast_xmit_iface(sdata); if (ieee80211_chanctx_refcount(local, old_ctx) == 0) - ieee80211_free_chanctx(local, old_ctx); + ieee80211_free_chanctx(local, old_ctx, false); ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); ieee80211_recalc_smps_chanctx(local, new_ctx); @@ -1300,10 +1339,10 @@ ieee80211_link_use_reserved_assign(struct ieee80211_link_data *link) list_del(&link->reserved_chanctx_list); link->reserved_chanctx = NULL; - err = ieee80211_assign_link_chanctx(link, new_ctx); + err = ieee80211_assign_link_chanctx(link, new_ctx, false); if (err) { if (ieee80211_chanctx_refcount(local, new_ctx) == 0) - ieee80211_free_chanctx(local, new_ctx); + ieee80211_free_chanctx(local, new_ctx, false); goto out; } @@ -1400,7 +1439,7 @@ static int ieee80211_chsw_switch_ctxs(struct ieee80211_local *local) if (!list_empty(&ctx->replace_ctx->assigned_links)) continue; - ieee80211_del_chanctx(local, ctx->replace_ctx); + ieee80211_del_chanctx(local, ctx->replace_ctx, false); err = ieee80211_add_chanctx(local, ctx); if (err) goto err; @@ -1417,7 +1456,7 @@ err: if (!list_empty(&ctx->replace_ctx->assigned_links)) continue; - ieee80211_del_chanctx(local, ctx); + ieee80211_del_chanctx(local, ctx, false); WARN_ON(ieee80211_add_chanctx(local, ctx->replace_ctx)); } @@ -1669,7 +1708,8 @@ err: return err; } -static void __ieee80211_link_release_channel(struct ieee80211_link_data *link) +void __ieee80211_link_release_channel(struct ieee80211_link_data *link, + bool skip_idle_recalc) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_bss_conf *link_conf = link->conf; @@ -1695,9 +1735,9 @@ static void __ieee80211_link_release_channel(struct ieee80211_link_data *link) ieee80211_link_unreserve_chanctx(link); } - ieee80211_assign_link_chanctx(link, NULL); + ieee80211_assign_link_chanctx(link, NULL, false); if (ieee80211_chanctx_refcount(local, ctx) == 0) - ieee80211_free_chanctx(local, ctx); + ieee80211_free_chanctx(local, ctx, skip_idle_recalc); link->radar_required = false; @@ -1706,14 +1746,16 @@ static void __ieee80211_link_release_channel(struct ieee80211_link_data *link) ieee80211_vif_use_reserved_switch(local); } -int ieee80211_link_use_channel(struct ieee80211_link_data *link, - const struct ieee80211_chan_req *chanreq, - enum ieee80211_chanctx_mode mode) +int _ieee80211_link_use_channel(struct ieee80211_link_data *link, + const struct ieee80211_chan_req *chanreq, + enum ieee80211_chanctx_mode mode, + bool assign_on_failure) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx *ctx; u8 radar_detect_width = 0; + bool reserved = false; int ret; lockdep_assert_wiphy(local->hw.wiphy); @@ -1738,11 +1780,15 @@ int ieee80211_link_use_channel(struct ieee80211_link_data *link, if (ret < 0) goto out; - __ieee80211_link_release_channel(link); + __ieee80211_link_release_channel(link, false); - ctx = ieee80211_find_chanctx(local, chanreq, mode); - if (!ctx) - ctx = ieee80211_new_chanctx(local, chanreq, mode); + ctx = ieee80211_find_chanctx(local, link, chanreq, mode); + /* Note: context is now reserved */ + if (ctx) + reserved = true; + else + ctx = ieee80211_new_chanctx(local, chanreq, mode, + assign_on_failure); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); goto out; @@ -1750,11 +1796,19 @@ int ieee80211_link_use_channel(struct ieee80211_link_data *link, ieee80211_link_update_chanreq(link, chanreq); - ret = ieee80211_assign_link_chanctx(link, ctx); + ret = ieee80211_assign_link_chanctx(link, ctx, assign_on_failure); + + if (reserved) { + /* remove reservation */ + WARN_ON(link->reserved_chanctx != ctx); + link->reserved_chanctx = NULL; + list_del(&link->reserved_chanctx_list); + } + if (ret) { /* if assign fails refcount stays the same */ if (ieee80211_chanctx_refcount(local, ctx) == 0) - ieee80211_free_chanctx(local, ctx); + ieee80211_free_chanctx(local, ctx, false); goto out; } @@ -1947,7 +2001,7 @@ void ieee80211_link_release_channel(struct ieee80211_link_data *link) lockdep_assert_wiphy(sdata->local->hw.wiphy); if (rcu_access_pointer(link->conf->chanctx_conf)) - __ieee80211_link_release_channel(link); + __ieee80211_link_release_channel(link, false); } void ieee80211_link_vlan_copy_chanctx(struct ieee80211_link_data *link) diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 2f68e92a7404..98310188f330 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -498,6 +498,7 @@ static const char *hw_flag_names[] = { FLAG(DETECTS_COLOR_COLLISION), FLAG(MLO_MCAST_MULTI_LINK_TX), FLAG(DISALLOW_PUNCTURING), + FLAG(DISALLOW_PUNCTURING_5GHZ), FLAG(HANDLES_QUIET_CSA), #undef FLAG }; diff --git a/net/mac80211/drop.h b/net/mac80211/drop.h index 12a6f0e9eca6..59e3ec4dc960 100644 --- a/net/mac80211/drop.h +++ b/net/mac80211/drop.h @@ -2,7 +2,7 @@ /* * mac80211 drop reason list * - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation */ #ifndef MAC80211_DROP_H @@ -66,6 +66,7 @@ typedef unsigned int __bitwise ieee80211_rx_result; R(RX_DROP_U_UNEXPECTED_STA_4ADDR) \ R(RX_DROP_U_UNEXPECTED_VLAN_MCAST) \ R(RX_DROP_U_NOT_PORT_CONTROL) \ + R(RX_DROP_U_UNKNOWN_ACTION_REJECTED) \ /* this line for the trailing \ - add before this */ /* having two enums allows for checking ieee80211_rx_result use with sparse */ diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index c3330aea4da3..d7e8cf8e48b7 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -580,7 +580,7 @@ int ieee80211_send_smps_action(struct ieee80211_sub_if_data *sdata, /* we'll do more on status of this frame */ info = IEEE80211_SKB_CB(skb); info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; - /* we have 12 bits, and need 6: link_id 4, smps 2 */ + /* we have 13 bits, and need 6: link_id 4, smps 2 */ info->status_data = IEEE80211_STATUS_TYPE_SMPS | u16_encode_bits(status_link_id << 2 | smps, IEEE80211_STATUS_SUBDATA_MASK); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 70c67c860e99..3cedfdc9099b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -89,7 +89,8 @@ enum ieee80211_status_data { IEEE80211_STATUS_TYPE_MASK = 0x00f, IEEE80211_STATUS_TYPE_INVALID = 0, IEEE80211_STATUS_TYPE_SMPS = 1, - IEEE80211_STATUS_SUBDATA_MASK = 0xff0, + IEEE80211_STATUS_TYPE_NEG_TTLM = 2, + IEEE80211_STATUS_SUBDATA_MASK = 0x1ff0, }; static inline bool @@ -595,6 +596,7 @@ struct ieee80211_if_managed { /* TID-to-link mapping support */ struct wiphy_delayed_work ttlm_work; struct ieee80211_adv_ttlm_info ttlm_info; + struct wiphy_work teardown_ttlm_work; /* dialog token enumerator for neg TTLM request */ u8 dialog_token_alloc; @@ -684,7 +686,7 @@ struct mesh_csa_settings { }; /** - * struct mesh_table + * struct mesh_table - mesh hash table * * @known_gates: list of known mesh gates and their mpaths by the station. The * gate's mpath may or may not be resolved and active. @@ -1160,6 +1162,8 @@ struct ieee80211_sub_if_data { struct wiphy_work activate_links_work; u16 desired_active_links; + u16 restart_active_links; + #ifdef CONFIG_MAC80211_DEBUGFS struct { struct dentry *subdir_stations; @@ -1841,6 +1845,8 @@ void ieee80211_link_info_change_notify(struct ieee80211_sub_if_data *sdata, void ieee80211_configure_filter(struct ieee80211_local *local); u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata); +void ieee80211_handle_queued_frames(struct ieee80211_local *local); + u64 ieee80211_mgmt_tx_cookie(struct ieee80211_local *local); int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb, u64 *cookie, gfp_t gfp); @@ -2550,9 +2556,19 @@ bool ieee80211_chanreq_identical(const struct ieee80211_chan_req *a, const struct ieee80211_chan_req *b); int __must_check +_ieee80211_link_use_channel(struct ieee80211_link_data *link, + const struct ieee80211_chan_req *req, + enum ieee80211_chanctx_mode mode, + bool assign_on_failure); + +static inline int __must_check ieee80211_link_use_channel(struct ieee80211_link_data *link, const struct ieee80211_chan_req *req, - enum ieee80211_chanctx_mode mode); + enum ieee80211_chanctx_mode mode) +{ + return _ieee80211_link_use_channel(link, req, mode, false); +} + int __must_check ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, const struct ieee80211_chan_req *req, @@ -2566,6 +2582,8 @@ int __must_check ieee80211_link_change_chanreq(struct ieee80211_link_data *link, const struct ieee80211_chan_req *req, u64 *changed); +void __ieee80211_link_release_channel(struct ieee80211_link_data *link, + bool skip_idle_recalc); void ieee80211_link_release_channel(struct ieee80211_link_data *link); void ieee80211_link_vlan_copy_chanctx(struct ieee80211_link_data *link); void ieee80211_link_copy_chanctx_to_vlans(struct ieee80211_link_data *link, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7c8a421f0901..b935bb5d8ed1 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1697,8 +1697,13 @@ static void ieee80211_activate_links_work(struct wiphy *wiphy, struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, activate_links_work); + struct ieee80211_local *local = wiphy_priv(wiphy); + + if (local->in_reconfig) + return; ieee80211_set_active_links(&sdata->vif, sdata->desired_active_links); + sdata->desired_active_links = 0; } /* diff --git a/net/mac80211/link.c b/net/mac80211/link.c index 685ec66b4264..af0321408a97 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -358,7 +358,7 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, ieee80211_teardown_tdls_peers(link); - ieee80211_link_release_channel(link); + __ieee80211_link_release_channel(link, true); } list_for_each_entry(sta, &local->sta_list, list) { @@ -404,9 +404,24 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, link = sdata_dereference(sdata->link[link_id], sdata); - ret = ieee80211_link_use_channel(link, - &link->conf->chanreq, - IEEE80211_CHANCTX_SHARED); + /* + * This call really should not fail. Unfortunately, it appears + * that this may happen occasionally with some drivers. Should + * it happen, we are stuck in a bad place as going backwards is + * not really feasible. + * + * So lets just tell link_use_channel that it must not fail to + * assign the channel context (from mac80211's perspective) and + * assume the driver is going to trigger a recovery flow if it + * had a failure. + * That really is not great nor guaranteed to work. But at least + * the internal mac80211 state remains consistent and there is + * a chance that we can recover. + */ + ret = _ieee80211_link_use_channel(link, + &link->conf->chanreq, + IEEE80211_CHANCTX_SHARED, + true); WARN_ON_ONCE(ret); ieee80211_mgd_set_link_qos_params(link); @@ -450,10 +465,13 @@ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links) if (WARN_ON(!active_links)) return -EINVAL; + old_active = sdata->vif.active_links; + if (old_active == active_links) + return 0; + if (!drv_can_activate_links(local, sdata, active_links)) return -EINVAL; - old_active = sdata->vif.active_links; if (old_active & active_links) { /* * if there's at least one link that stays active across diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4eaea0a9975b..7ba329ebdda9 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -148,7 +148,7 @@ static u32 ieee80211_calc_hw_conf_chan(struct ieee80211_local *local, offchannel_flag ^= local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; /* force it also for scanning, since drivers might config differently */ - if (offchannel_flag || local->scanning || + if (offchannel_flag || local->scanning || local->in_reconfig || !cfg80211_chandef_identical(&local->hw.conf.chandef, &chandef)) { local->hw.conf.chandef = chandef; changed |= IEEE80211_CONF_CHANGE_CHANNEL; @@ -423,9 +423,9 @@ u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata) BSS_CHANGED_ERP_SLOT; } -static void ieee80211_tasklet_handler(struct tasklet_struct *t) +/* context: requires softirqs disabled */ +void ieee80211_handle_queued_frames(struct ieee80211_local *local) { - struct ieee80211_local *local = from_tasklet(local, t, tasklet); struct sk_buff *skb; while ((skb = skb_dequeue(&local->skb_queue)) || @@ -450,6 +450,13 @@ static void ieee80211_tasklet_handler(struct tasklet_struct *t) } } +static void ieee80211_tasklet_handler(struct tasklet_struct *t) +{ + struct ieee80211_local *local = from_tasklet(local, t, tasklet); + + ieee80211_handle_queued_frames(local); +} + static void ieee80211_restart_work(struct work_struct *work) { struct ieee80211_local *local = diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index cbc9b5e40cb3..6d4510221c98 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1776,6 +1776,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) ifmsh->last_preq = jiffies; ifmsh->next_perr = jiffies; ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE; + ifmsh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; /* Allocate all mesh structures when creating the first mesh interface. */ if (!mesh_allocated) ieee80211s_init(); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 497677e3d8b2..ad2ce9c92ba8 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -599,6 +599,10 @@ static bool ieee80211_chandef_usable(struct ieee80211_sub_if_data *sdata, ieee80211_hw_check(&sdata->local->hw, DISALLOW_PUNCTURING)) return false; + if (chandef->punctured && chandef->chan->band == NL80211_BAND_5GHZ && + ieee80211_hw_check(&sdata->local->hw, DISALLOW_PUNCTURING_5GHZ)) + return false; + return true; } @@ -3283,8 +3287,17 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sizeof(sdata->u.mgd.ttlm_info)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->neg_ttlm_timeout_work); + + sdata->u.mgd.removed_links = 0; + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &sdata->u.mgd.ml_reconf_work); + + wiphy_work_cancel(sdata->local->hw.wiphy, + &ifmgd->teardown_ttlm_work); + ieee80211_vif_set_links(sdata, 0, 0); ifmgd->mcast_seq_last = IEEE80211_SN_MODULO; @@ -4455,9 +4468,11 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, switch (u8_get_bits(he_6ghz_oper->control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: bss_conf->power_type = IEEE80211_REG_LPI_AP; break; case IEEE80211_6GHZ_CTRL_REG_SP_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: bss_conf->power_type = IEEE80211_REG_SP_AP; break; case IEEE80211_6GHZ_CTRL_REG_VLP_AP: @@ -6822,6 +6837,60 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, __ieee80211_disconnect(sdata); } +static void ieee80211_teardown_ttlm_work(struct wiphy *wiphy, + struct wiphy_work *work) +{ + u16 new_dormant_links; + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + u.mgd.teardown_ttlm_work); + + if (!sdata->vif.neg_ttlm.valid) + return; + + memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm)); + new_dormant_links = + sdata->vif.dormant_links & ~sdata->vif.suspended_links; + sdata->vif.suspended_links = 0; + ieee80211_vif_set_links(sdata, sdata->vif.valid_links, + new_dormant_links); + ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_MLD_TTLM | + BSS_CHANGED_MLD_VALID_LINKS); +} + +void ieee80211_send_teardown_neg_ttlm(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgmt *mgmt; + struct sk_buff *skb; + int frame_len = offsetofend(struct ieee80211_mgmt, + u.action.u.ttlm_tear_down); + struct ieee80211_tx_info *info; + + skb = dev_alloc_skb(local->hw.extra_tx_headroom + frame_len); + if (!skb) + return; + + skb_reserve(skb, local->hw.extra_tx_headroom); + mgmt = skb_put_zero(skb, frame_len); + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + memcpy(mgmt->da, sdata->vif.cfg.ap_addr, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); + + mgmt->u.action.category = WLAN_CATEGORY_PROTECTED_EHT; + mgmt->u.action.u.ttlm_tear_down.action_code = + WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN; + + info = IEEE80211_SKB_CB(skb); + info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; + info->status_data = IEEE80211_STATUS_TYPE_NEG_TTLM; + ieee80211_tx_skb(sdata, skb); +} +EXPORT_SYMBOL(ieee80211_send_teardown_neg_ttlm); + void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { @@ -7453,6 +7522,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) ieee80211_tid_to_link_map_work); wiphy_delayed_work_init(&ifmgd->neg_ttlm_timeout_work, ieee80211_neg_ttlm_timeout_work); + wiphy_work_init(&ifmgd->teardown_ttlm_work, + ieee80211_teardown_ttlm_work); ifmgd->flags = 0; ifmgd->powersave = sdata->wdev.ps; @@ -8239,6 +8310,14 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (req->ap_mld_addr) { uapsd_supported = true; + if (req->flags & (ASSOC_REQ_DISABLE_HT | + ASSOC_REQ_DISABLE_VHT | + ASSOC_REQ_DISABLE_HE | + ASSOC_REQ_DISABLE_EHT)) { + err = -EINVAL; + goto err_free; + } + for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { struct ieee80211_supported_band *sband; struct cfg80211_bss *link_cbss = req->links[i].bss; @@ -8251,19 +8330,13 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (!bss->wmm_used) { err = -EINVAL; - goto err_free; - } - - if (req->flags & (ASSOC_REQ_DISABLE_HT | - ASSOC_REQ_DISABLE_VHT | - ASSOC_REQ_DISABLE_HE | - ASSOC_REQ_DISABLE_EHT)) { - err = -EINVAL; + req->links[i].error = err; goto err_free; } if (link_cbss->channel->band == NL80211_BAND_S1GHZ) { err = -EINVAL; + req->links[i].error = err; goto err_free; } @@ -8642,8 +8715,6 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) &ifmgd->csa_connection_drop_work); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->tdls_peer_del_work); - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, - &ifmgd->ml_reconf_work); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->neg_ttlm_timeout_work); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 221695d841fd..65e1e9e971fd 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -897,8 +897,18 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, break; } - if (ether_addr_equal(conf->addr, mgmt->sa)) + if (ether_addr_equal(conf->addr, mgmt->sa)) { + /* If userspace requested Tx on a specific link + * use the same link id if the link bss is matching + * the requested chan. + */ + if (sdata->vif.valid_links && + params->link_id >= 0 && params->link_id == i && + params->chan == chanctx_conf->def.chan) + link_id = i; + break; + } chanctx_conf = NULL; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6e24864f9a40..4914692750e5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3368,7 +3368,7 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) if (ieee80211_hw_check(&rx->local->hw, DETECTS_COLOR_COLLISION)) return; - if (rx->sdata->vif.bss_conf.csa_active) + if (rx->link->conf->csa_active) return; baselen = mgmt->u.beacon.variable - rx->skb->data; @@ -3380,7 +3380,7 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) rx->skb->len - baselen); if (ie && ie->datalen >= sizeof(struct ieee80211_he_operation) && ie->datalen >= ieee80211_he_oper_size(ie->data + 1)) { - struct ieee80211_bss_conf *bss_conf = &rx->sdata->vif.bss_conf; + struct ieee80211_bss_conf *bss_conf = rx->link->conf; const struct ieee80211_he_operation *he_oper; u8 color; @@ -3393,7 +3393,8 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) IEEE80211_HE_OPERATION_BSS_COLOR_MASK); if (color == bss_conf->he_bss_color.color) ieee80211_obss_color_collision_notify(&rx->sdata->vif, - BIT_ULL(color)); + BIT_ULL(color), + bss_conf->link_id); } } @@ -3969,8 +3970,8 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) __ieee80211_tx_skb_tid_band(rx->sdata, nskb, 7, -1, status->band); } - dev_kfree_skb(rx->skb); - return RX_QUEUED; + + return RX_DROP_U_UNKNOWN_ACTION_REJECTED; } static ieee80211_rx_result debug_noinline diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 3da1c5c45035..b5f2df61c7f6 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -358,7 +358,8 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) struct cfg80211_scan_request *req; struct cfg80211_chan_def chandef; u8 bands_used = 0; - int i, ielen, n_chans; + int i, ielen; + u32 *n_chans; u32 flags = 0; req = rcu_dereference_protected(local->scan_req, @@ -368,34 +369,34 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) return false; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { + local->hw_scan_req->req.n_channels = req->n_channels; + for (i = 0; i < req->n_channels; i++) { local->hw_scan_req->req.channels[i] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } - - n_chans = req->n_channels; } else { do { if (local->hw_scan_band == NUM_NL80211_BANDS) return false; - n_chans = 0; + n_chans = &local->hw_scan_req->req.n_channels; + *n_chans = 0; for (i = 0; i < req->n_channels; i++) { if (req->channels[i]->band != local->hw_scan_band) continue; - local->hw_scan_req->req.channels[n_chans] = + local->hw_scan_req->req.channels[(*n_chans)++] = req->channels[i]; - n_chans++; + bands_used |= BIT(req->channels[i]->band); } local->hw_scan_band++; - } while (!n_chans); + } while (!*n_chans); } - local->hw_scan_req->req.n_channels = n_chans; ieee80211_prepare_scan_chandef(&chandef); if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) @@ -744,15 +745,21 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, local->hw_scan_ies_bufsize *= n_bands; } - local->hw_scan_req = kmalloc( - sizeof(*local->hw_scan_req) + - req->n_channels * sizeof(req->channels[0]) + - local->hw_scan_ies_bufsize, GFP_KERNEL); + local->hw_scan_req = kmalloc(struct_size(local->hw_scan_req, + req.channels, + req->n_channels) + + local->hw_scan_ies_bufsize, + GFP_KERNEL); if (!local->hw_scan_req) return -ENOMEM; local->hw_scan_req->req.ssids = req->ssids; local->hw_scan_req->req.n_ssids = req->n_ssids; + /* None of the channels are actually set + * up but let UBSAN know the boundaries. + */ + local->hw_scan_req->req.n_channels = req->n_channels; + ies = (u8 *)local->hw_scan_req + sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]); diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 327c74e296e2..b2de4c6fb808 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -155,6 +155,7 @@ validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata, struct ieee80211_eht_operation _oper; struct ieee80211_eht_operation_info _oper_info; } __packed eht; + const struct ieee80211_eht_operation *eht_oper; if (conn->mode < IEEE80211_CONN_MODE_HE) { chandef->chan = NULL; @@ -203,19 +204,18 @@ validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata, } if (conn->mode < IEEE80211_CONN_MODE_EHT) { - if (!ieee80211_chandef_he_6ghz_oper(local, &he._oper, - NULL, chandef)) - chandef->chan = NULL; + eht_oper = NULL; } else { eht._oper.params = IEEE80211_EHT_OPER_INFO_PRESENT; eht._oper_info.control = he._6ghz_oper.control; eht._oper_info.ccfs0 = he._6ghz_oper.ccfs0; eht._oper_info.ccfs1 = he._6ghz_oper.ccfs1; - - if (!ieee80211_chandef_he_6ghz_oper(local, &he._oper, - &eht._oper, chandef)) - chandef->chan = NULL; + eht_oper = &eht._oper; } + + if (!ieee80211_chandef_he_6ghz_oper(local, &he._oper, + eht_oper, chandef)) + chandef->chan = NULL; } int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, @@ -348,6 +348,10 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, new_chandef = csa_ie->chanreq.oper; /* and update the width accordingly */ ieee80211_chandef_eht_oper(&bwi->info, &new_chandef); + + if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT) + new_chandef.punctured = + get_unaligned_le16(bwi->info.optional); } else if (!wide_bw_chansw_ie || !wbcs_elem_to_chandef(wide_bw_chansw_ie, &new_chandef)) { if (!ieee80211_operating_class_to_chandef(new_op_class, new_chan, diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index a52fb76386d0..9195d5a2de0a 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -727,6 +727,12 @@ struct sta_info { struct ieee80211_sta sta; }; +static inline int ieee80211_tdls_sta_link_id(struct sta_info *sta) +{ + /* TDLS STA can only have a single link */ + return sta->sta.valid_links ? __ffs(sta->sta.valid_links) : 0; +} + static inline enum nl80211_plink_state sta_plink_state(struct sta_info *sta) { #ifdef CONFIG_MAC80211_MESH @@ -886,7 +892,7 @@ void sta_info_stop(struct ieee80211_local *local); /** * __sta_info_flush - flush matching STA entries from the STA table * - * Returns the number of removed STA entries. + * Return: the number of removed STA entries. * * @sdata: sdata to remove all stations from * @vlans: if the given interface is an AP interface, also flush VLANs @@ -900,7 +906,7 @@ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, /** * sta_info_flush - flush matching STA entries from the STA table * - * Returns the number of removed STA entries. + * Return: the number of removed STA entries. * * @sdata: sdata to remove all stations from * @link_id: if given (>=0), all those STA entries using @link_id only diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 1708b33cdc5e..dd8f857a1fbc 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2008-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2021-2023 Intel Corporation + * Copyright 2021-2024 Intel Corporation */ #include <linux/export.h> @@ -696,6 +696,23 @@ static void ieee80211_handle_smps_status(struct ieee80211_sub_if_data *sdata, wiphy_work_queue(sdata->local->hw.wiphy, &link->u.mgd.recalc_smps); } +static void +ieee80211_handle_teardown_ttlm_status(struct ieee80211_sub_if_data *sdata, + bool acked) +{ + if (!sdata || !ieee80211_sdata_running(sdata)) + return; + + if (!acked) + return; + + if (sdata->vif.type != NL80211_IFTYPE_STATION) + return; + + wiphy_work_queue(sdata->local->hw.wiphy, + &sdata->u.mgd.teardown_ttlm_work); +} + static void ieee80211_report_used_skb(struct ieee80211_local *local, struct sk_buff *skb, bool dropped, ktime_t ack_hwtstamp) @@ -773,6 +790,9 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, ieee80211_handle_smps_status(sdata, acked, info->status_data); break; + case IEEE80211_STATUS_TYPE_NEG_TTLM: + ieee80211_handle_teardown_ttlm_status(sdata, acked); + break; } rcu_read_unlock(); } diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 8e758b5074bd..b26aacfbc622 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -33,7 +33,7 @@ __string(vif_name, sdata->name) #define VIF_ASSIGN __entry->vif_type = sdata->vif.type; __entry->sdata = sdata; \ __entry->p2p = sdata->vif.p2p; \ - __assign_str(vif_name, sdata->name) + __assign_str(vif_name) #define VIF_PR_FMT " vif:%s(%d%s)" #define VIF_PR_ARG __get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : "" diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index cfd0a62d0152..edba4a31844f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1609,8 +1609,8 @@ int ieee80211_txq_setup_flows(struct ieee80211_local *local) local->cparams.target = MS2TIME(20); local->cparams.ecn = true; - local->cvars = kcalloc(fq->flows_cnt, sizeof(local->cvars[0]), - GFP_KERNEL); + local->cvars = kvcalloc(fq->flows_cnt, sizeof(local->cvars[0]), + GFP_KERNEL); if (!local->cvars) { spin_lock_bh(&fq->lock); fq_reset(fq, fq_skb_free_func); @@ -1630,7 +1630,7 @@ void ieee80211_txq_teardown_flows(struct ieee80211_local *local) { struct fq *fq = &local->fq; - kfree(local->cvars); + kvfree(local->cvars); local->cvars = NULL; spin_lock_bh(&fq->lock); @@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local, break; } sdata = rcu_dereference(local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; @@ -2774,8 +2774,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, if (tdls_peer) { /* For TDLS only one link can be valid with peer STA */ - int tdls_link_id = sta->sta.valid_links ? - __ffs(sta->sta.valid_links) : 0; + int tdls_link_id = ieee80211_tdls_sta_link_id(sta); struct ieee80211_link_data *link; /* DA SA BSSID */ @@ -3101,8 +3100,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) case NL80211_IFTYPE_STATION: if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { /* For TDLS only one link can be valid with peer STA */ - int tdls_link_id = sta->sta.valid_links ? - __ffs(sta->sta.valid_links) : 0; + int tdls_link_id = ieee80211_tdls_sta_link_id(sta); struct ieee80211_link_data *link; /* DA SA BSSID */ @@ -3959,7 +3957,8 @@ begin: break; } tx.sdata = rcu_dereference(local->monitor_sdata); - if (tx.sdata) { + if (tx.sdata && + ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &tx.sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 0da5f6082d15..c11dbe82ae1b 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -776,7 +776,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || lockdep_is_held(&local->hw.wiphy->mtx)); - if (sdata && + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); @@ -1567,6 +1567,10 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, void ieee80211_stop_device(struct ieee80211_local *local) { + local_bh_disable(); + ieee80211_handle_queued_frames(local); + local_bh_enable(); + ieee80211_led_radio(local, false); ieee80211_mod_tpt_led_trig(local, 0, IEEE80211_TPT_LEDTRIG_FL_RADIO); @@ -1932,6 +1936,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) old); } + sdata->restart_active_links = active_links; + for (link_id = 0; link_id < ARRAY_SIZE(sdata->vif.link_conf); link_id++) { @@ -2059,9 +2065,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN_ON(1); break; } - - if (active_links) - ieee80211_set_active_links(&sdata->vif, active_links); } ieee80211_recalc_ps(local); @@ -2102,6 +2105,20 @@ int ieee80211_reconfig(struct ieee80211_local *local) list_for_each_entry(sdata, &local->interfaces, list) ieee80211_reenable_keys(sdata); + /* re-enable multi-link for client interfaces */ + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata->restart_active_links) + ieee80211_set_active_links(&sdata->vif, + sdata->restart_active_links); + /* + * If a link switch was scheduled before the restart, and ran + * before reconfig, it will do nothing, so re-schedule. + */ + if (sdata->desired_active_links) + wiphy_work_queue(sdata->local->hw.wiphy, + &sdata->activate_links_work); + } + /* Reconfigure sched scan if it was interrupted by FW restart */ sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); @@ -3136,6 +3153,8 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_local *local, } else { ieee80211_chandef_eht_oper((const void *)eht_oper->optional, &he_chandef); + he_chandef.punctured = + ieee80211_eht_oper_dis_subchan_bitmap(eht_oper); } if (!cfg80211_chandef_valid(&he_chandef)) diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index e40529b8c5c9..047a33797020 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -895,7 +895,8 @@ ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx) info = IEEE80211_SKB_CB(skb); - if (info->control.hw_key) + if (info->control.hw_key && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIE)) return TX_CONTINUE; if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) @@ -911,6 +912,9 @@ ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx) bip_ipn_set64(mmie->sequence_number, pn64); + if (info->control.hw_key) + return TX_CONTINUE; + bip_aad(skb, aad); /* MIC = AES-256-CMAC(IGTK, AAD || Management Frame Body || MMIE, 128) @@ -1040,7 +1044,8 @@ ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx) info = IEEE80211_SKB_CB(skb); - if (info->control.hw_key) + if (info->control.hw_key && + !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIE)) return TX_CONTINUE; if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie))) @@ -1056,6 +1061,9 @@ ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx) bip_ipn_set64(mmie->sequence_number, pn64); + if (info->control.hw_key) + return TX_CONTINUE; + bip_aad(skb, aad); hdr = (struct ieee80211_hdr *)skb->data; diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 9ab7396668d2..21b7c3b280b4 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -161,8 +161,10 @@ void ieee802154_configure_durations(struct wpan_phy *phy, } phy->symbol_duration = duration; - phy->lifs_period = (IEEE802154_LIFS_PERIOD * phy->symbol_duration) / NSEC_PER_SEC; - phy->sifs_period = (IEEE802154_SIFS_PERIOD * phy->symbol_duration) / NSEC_PER_SEC; + phy->lifs_period = + (IEEE802154_LIFS_PERIOD * phy->symbol_duration) / NSEC_PER_USEC; + phy->sifs_period = + (IEEE802154_SIFS_PERIOD * phy->symbol_duration) / NSEC_PER_USEC; } EXPORT_SYMBOL(ieee802154_configure_durations); @@ -184,10 +186,10 @@ static void ieee802154_setup_wpan_phy_pib(struct wpan_phy *wpan_phy) * Should be done when all drivers sets this value. */ - wpan_phy->lifs_period = - (IEEE802154_LIFS_PERIOD * wpan_phy->symbol_duration) / 1000; - wpan_phy->sifs_period = - (IEEE802154_SIFS_PERIOD * wpan_phy->symbol_duration) / 1000; + wpan_phy->lifs_period = (IEEE802154_LIFS_PERIOD * + wpan_phy->symbol_duration) / NSEC_PER_USEC; + wpan_phy->sifs_period = (IEEE802154_SIFS_PERIOD * + wpan_phy->symbol_duration) / NSEC_PER_USEC; } int ieee802154_register_hw(struct ieee802154_hw *hw) diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 2a6f1ed763c9..6fbed5bb5c3e 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -34,8 +34,8 @@ void ieee802154_xmit_sync_worker(struct work_struct *work) if (res) goto err_tx; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + DEV_STATS_INC(dev, tx_packets); + DEV_STATS_ADD(dev, tx_bytes, skb->len); ieee802154_xmit_complete(&local->hw, skb, false); @@ -90,8 +90,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) if (ret) goto err_wake_netif_queue; - dev->stats.tx_packets++; - dev->stats.tx_bytes += len; + DEV_STATS_INC(dev, tx_packets); + DEV_STATS_ADD(dev, tx_bytes, len); } else { local->tx_skb = skb; queue_work(local->workqueue, &local->sync_tx_work); diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 77e5dd422258..8551dab1d1e6 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test) skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2); - KUNIT_EXPECT_EQ(test, skb->len, 1); + KUNIT_EXPECT_EQ(test, skb2->len, 1); skb_free_datagram(sock->sk, skb2); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 6dab883a08dd..2dc7a908a6bb 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -594,7 +594,7 @@ static struct net_device *inet_fib_lookup_dev(struct net *net, struct in_addr daddr; memcpy(&daddr, addr, sizeof(struct in_addr)); - rt = ip_route_output(net, daddr.s_addr, 0, 0, 0); + rt = ip_route_output(net, daddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return ERR_CAST(rt); @@ -1154,7 +1154,7 @@ static int mpls_netconf_fill_devconf(struct sk_buff *skb, struct mpls_dev *mdev, if ((all || type == NETCONFA_INPUT) && nla_put_s32(skb, NETCONFA_INPUT, - mdev->input_enabled) < 0) + READ_ONCE(mdev->input_enabled)) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); @@ -1303,11 +1303,12 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb, { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - struct hlist_head *head; + struct { + unsigned long ifindex; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct mpls_dev *mdev; - int idx, s_idx; - int h, s_h; + int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; @@ -1324,40 +1325,23 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb, } } - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = net->dev_base_seq; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - mdev = mpls_dev_get(dev); - if (!mdev) - goto cont; - if (mpls_netconf_fill_devconf(skb, mdev, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, - NLM_F_MULTI, - NETCONFA_ALL) < 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - rcu_read_unlock(); + rcu_read_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + mdev = mpls_dev_get(dev); + if (!mdev) + continue; + err = mpls_netconf_fill_devconf(skb, mdev, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, + NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) + break; } -done: - cb->args[0] = h; - cb->args[1] = idx; + rcu_read_unlock(); - return skb->len; + return err; } #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ @@ -1393,13 +1377,13 @@ static const struct ctl_table mpls_dev_table[] = { .proc_handler = mpls_conf_proc, .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), }, - { } }; static int mpls_dev_sysctl_register(struct net_device *dev, struct mpls_dev *mdev) { char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; + size_t table_size = ARRAY_SIZE(mpls_dev_table); struct net *net = dev_net(dev); struct ctl_table *table; int i; @@ -1411,7 +1395,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ - for (i = 0; i < ARRAY_SIZE(mpls_dev_table); i++) { + for (i = 0; i < table_size; i++) { table[i].data = (char *)mdev + (uintptr_t)table[i].data; table[i].extra1 = mdev; table[i].extra2 = net; @@ -1419,8 +1403,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); - mdev->sysctl = register_net_sysctl_sz(net, path, table, - ARRAY_SIZE(mpls_dev_table)); + mdev->sysctl = register_net_sysctl_sz(net, path, table, table_size); if (!mdev->sysctl) goto free; @@ -1438,7 +1421,7 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev, struct mpls_dev *mdev) { struct net *net = dev_net(dev); - struct ctl_table *table; + const struct ctl_table *table; if (!mdev->sysctl) return; @@ -2669,11 +2652,11 @@ static const struct ctl_table mpls_table[] = { .extra1 = SYSCTL_ONE, .extra2 = &ttl_max, }, - { } }; static int mpls_net_init(struct net *net) { + size_t table_size = ARRAY_SIZE(mpls_table); struct ctl_table *table; int i; @@ -2689,11 +2672,11 @@ static int mpls_net_init(struct net *net) /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ - for (i = 0; i < ARRAY_SIZE(mpls_table) - 1; i++) + for (i = 0; i < table_size; i++) table[i].data = (char *)net + (uintptr_t)table[i].data; net->mpls.ctl = register_net_sysctl_sz(net, "net/mpls", table, - ARRAY_SIZE(mpls_table)); + table_size); if (net->mpls.ctl == NULL) { kfree(table); return -ENOMEM; @@ -2706,7 +2689,7 @@ static void mpls_net_exit(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; - struct ctl_table *table; + const struct ctl_table *table; unsigned int index; table = net->mpls.ctl->ctl_table_arg; @@ -2773,7 +2756,8 @@ static int __init mpls_init(void) mpls_getroute, mpls_dump_routes, 0); rtnl_register_module(THIS_MODULE, PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, - mpls_netconf_dump_devconf, 0); + mpls_netconf_dump_devconf, + RTNL_FLAG_DUMP_UNLOCKED); err = ipgre_tunnel_encap_add_mpls_ops(); if (err) pr_err("Can't add mpls over gre tunnel ops\n"); diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 2963ba84e2ee..98b1dd498ff6 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -92,7 +92,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) pernet->allow_join_initial_addr_port = 1; pernet->stale_loss_cnt = 4; pernet->pm_type = MPTCP_PM_TYPE_KERNEL; - strcpy(pernet->scheduler, "default"); + strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler)); } #ifdef CONFIG_SYSCTL @@ -133,6 +133,24 @@ static int proc_scheduler(struct ctl_table *ctl, int write, return ret; } +static int proc_available_schedulers(struct ctl_table *ctl, + int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tbl = { .maxlen = MPTCP_SCHED_BUF_MAX, }; + int ret; + + tbl.data = kmalloc(tbl.maxlen, GFP_USER); + if (!tbl.data) + return -ENOMEM; + + mptcp_get_available_schedulers(tbl.data, MPTCP_SCHED_BUF_MAX); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + kfree(tbl.data); + + return ret; +} + static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", @@ -188,12 +206,17 @@ static struct ctl_table mptcp_sysctl_table[] = { .proc_handler = proc_scheduler, }, { + .procname = "available_schedulers", + .maxlen = MPTCP_SCHED_BUF_MAX, + .mode = 0644, + .proc_handler = proc_available_schedulers, + }, + { .procname = "close_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - {} }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) @@ -215,7 +238,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[4].data = &pernet->stale_loss_cnt; table[5].data = &pernet->pm_type; table[6].data = &pernet->scheduler; - table[7].data = &pernet->close_timeout; + /* table[7] is for available_schedulers which is read-only info */ + table[8].data = &pernet->close_timeout; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); @@ -235,7 +259,7 @@ err_alloc: static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) { - struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg; + const struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg; unregister_net_sysctl_table(pernet->ctl_table_hdr); diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 3ae46b545d2c..2d3efb405437 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */ diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index ad28da655f8b..a29ff901df75 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -68,12 +68,12 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo skb = skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); - pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk, + pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk, MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq, MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq); MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq; MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq; } - pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); + pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq); } diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index c30405e76833..7884217f33eb 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), + SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), + SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index dd7fd1f246b5..66aa67f49d03 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ +#include <net/inet_common.h> + enum linux_mptcp_mib_field { MPTCP_MIB_NUM = 0, MPTCP_MIB_MPCAPABLEPASSIVE, /* Received SYN with MP_CAPABLE */ @@ -12,7 +14,9 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 27ca42c77b02..370c3836b771 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -117,7 +117,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } - pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", + pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u\n", version, flags, opsize, mp_opt->sndr_key, mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum); break; @@ -131,7 +131,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 4; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; - pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u", + pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u\n", mp_opt->backup, mp_opt->join_id, mp_opt->token, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) { @@ -142,19 +142,19 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 8; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; - pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u", + pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u\n", mp_opt->backup, mp_opt->join_id, mp_opt->thmac, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK; ptr += 2; memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); - pr_debug("MP_JOIN hmac"); + pr_debug("MP_JOIN hmac\n"); } break; case MPTCPOPT_DSS: - pr_debug("DSS"); + pr_debug("DSS\n"); ptr++; /* we must clear 'mpc_map' be able to detect MP_CAPABLE @@ -169,7 +169,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0; mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK); - pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d", + pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n", mp_opt->data_fin, mp_opt->dsn64, mp_opt->use_map, mp_opt->ack64, mp_opt->use_ack); @@ -207,7 +207,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 4; } - pr_debug("data_ack=%llu", mp_opt->data_ack); + pr_debug("data_ack=%llu\n", mp_opt->data_ack); } if (mp_opt->use_map) { @@ -231,7 +231,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; } - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n", mp_opt->data_seq, mp_opt->subflow_seq, mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD), mp_opt->csum); @@ -293,7 +293,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->ahmac = get_unaligned_be64(ptr); ptr += 8; } - pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d", + pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d\n", (mp_opt->addr.family == AF_INET6) ? "6" : "", mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port)); break; @@ -309,7 +309,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE; for (i = 0; i < mp_opt->rm_list.nr; i++) mp_opt->rm_list.ids[i] = *ptr++; - pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr); + pr_debug("RM_ADDR: rm_list_nr=%d\n", mp_opt->rm_list.nr); break; case MPTCPOPT_MP_PRIO: @@ -318,7 +318,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_PRIO; mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP; - pr_debug("MP_PRIO: prio=%d", mp_opt->backup); + pr_debug("MP_PRIO: prio=%d\n", mp_opt->backup); break; case MPTCPOPT_MP_FASTCLOSE: @@ -329,7 +329,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE; - pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key); + pr_debug("MP_FASTCLOSE: recv_key=%llu\n", mp_opt->rcvr_key); break; case MPTCPOPT_RST: @@ -343,7 +343,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; - pr_debug("MP_RST: transient=%u reason=%u", + pr_debug("MP_RST: transient=%u reason=%u\n", mp_opt->reset_transient, mp_opt->reset_reason); break; @@ -354,7 +354,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; mp_opt->suboptions |= OPTION_MPTCP_FAIL; mp_opt->fail_seq = get_unaligned_be64(ptr); - pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq); + pr_debug("MP_FAIL: data_seq=%llu\n", mp_opt->fail_seq); break; default: @@ -417,7 +417,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { - pr_debug("remote_token=%u, nonce=%u", subflow->remote_token, + pr_debug("remote_token=%u, nonce=%u\n", subflow->remote_token, subflow->local_nonce); opts->suboptions = OPTION_MPTCP_MPJ_SYN; opts->join_id = subflow->local_id; @@ -500,7 +500,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPC_ACK; } - pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", + pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d\n", subflow, subflow->local_key, subflow->remote_key, data_len); @@ -509,7 +509,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, opts->suboptions = OPTION_MPTCP_MPJ_ACK; memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN); *size = TCPOLEN_MPTCP_MPJ_ACK; - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); /* we can use the full delegate action helper only from BH context * If we are in process context - sk is flushing the backlog at @@ -675,7 +675,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * *size = len; if (drop_other_suboptions) { - pr_debug("drop other suboptions"); + pr_debug("drop other suboptions\n"); opts->suboptions = 0; /* note that e.g. DSS could have written into the memory @@ -695,7 +695,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * } else { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); } - pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d", + pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); return true; @@ -726,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk, opts->rm_list = rm_list; for (i = 0; i < opts->rm_list.nr; i++) - pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]); + pr_debug("rm_list_ids[%d]=%d\n", i, opts->rm_list.ids[i]); MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr); return true; } @@ -752,7 +752,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, opts->suboptions |= OPTION_MPTCP_PRIO; opts->backup = subflow->request_bkup; - pr_debug("prio=%d", opts->backup); + pr_debug("prio=%d\n", opts->backup); return true; } @@ -794,7 +794,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk, opts->suboptions |= OPTION_MPTCP_FASTCLOSE; opts->rcvr_key = READ_ONCE(msk->remote_key); - pr_debug("FASTCLOSE key=%llu", opts->rcvr_key); + pr_debug("FASTCLOSE key=%llu\n", opts->rcvr_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); return true; } @@ -816,7 +816,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk, opts->suboptions |= OPTION_MPTCP_FAIL; opts->fail_seq = subflow->map_seq; - pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); + pr_debug("MP_FAIL fail_seq=%llu\n", opts->fail_seq); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); return true; @@ -904,16 +904,16 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, opts->csum_reqd = subflow_req->csum_reqd; opts->allow_join_id0 = subflow_req->allow_join_id0; *size = TCPOLEN_MPTCP_MPC_SYNACK; - pr_debug("subflow_req=%p, local_key=%llu", + pr_debug("subflow_req=%p, local_key=%llu\n", subflow_req, subflow_req->local_key); return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; - opts->backup = subflow_req->backup; + opts->backup = subflow_req->request_bkup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; - pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u", + pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u\n", subflow_req, opts->backup, opts->join_id, opts->thmac, opts->nonce); *size = TCPOLEN_MPTCP_MPJ_SYNACK; @@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (subflow->remote_key_valid && (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || - ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) { + ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && + (!mp_opt->echo || subflow->mp_join)))) { /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ @@ -1068,6 +1069,7 @@ static void ack_update_msk(struct mptcp_sock *msk, __mptcp_snd_una_update(msk, new_snd_una); __mptcp_data_acked(sk); } + msk->last_ack_recv = tcp_jiffies32; mptcp_data_unlock(sk); trace_ack_update_msk(mp_opt->data_ack, diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 55406720c607..37f6dbcd8434 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -19,7 +19,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, { u8 add_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, local_id=%d, echo=%d", msk, addr->id, echo); + pr_debug("msk=%p, local_id=%d, echo=%d\n", msk, addr->id, echo); lockdep_assert_held(&msk->pm.lock); @@ -45,7 +45,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ { u8 rm_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); + pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr); if (rm_addr) { MPTCP_ADD_STATS(sock_net((struct sock *)msk), @@ -60,23 +60,13 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ return 0; } -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) -{ - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); - - spin_lock_bh(&msk->pm.lock); - mptcp_pm_nl_rm_subflow_received(msk, rm_list); - spin_unlock_bh(&msk->pm.lock); - return 0; -} - /* path manager event handlers */ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side); + pr_debug("msk=%p, token=%u side=%d\n", msk, READ_ONCE(msk->token), server_side); WRITE_ONCE(pm->server_side, server_side); mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC); @@ -100,7 +90,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) subflows_max = mptcp_pm_get_subflows_max(msk); - pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows, + pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows, subflows_max, READ_ONCE(pm->accept_subflow)); /* try to avoid acquiring the lock below */ @@ -124,7 +114,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) static bool mptcp_pm_schedule_work(struct mptcp_sock *msk, enum mptcp_pm_status new_status) { - pr_debug("msk=%p status=%x new=%lx", msk, msk->pm.status, + pr_debug("msk=%p status=%x new=%lx\n", msk, msk->pm.status, BIT(new_status)); if (msk->pm.status & BIT(new_status)) return false; @@ -139,7 +129,7 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk) struct mptcp_pm_data *pm = &msk->pm; bool announce = false; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); @@ -163,14 +153,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk) void mptcp_pm_connection_closed(struct mptcp_sock *msk) { - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); } void mptcp_pm_subflow_established(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (!READ_ONCE(pm->work_pending)) return; @@ -222,7 +212,7 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id, + pr_debug("msk=%p remote_id=%d accept=%d\n", msk, addr->id, READ_ONCE(pm->accept_addr)); mptcp_event_addr_announced(ssk, addr); @@ -236,7 +226,9 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, } else { __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP); } - } else if (!READ_ONCE(pm->accept_addr)) { + /* id0 should not have a different address */ + } else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) || + (addr->id > 0 && !READ_ONCE(pm->accept_addr))) { mptcp_pm_announce_addr(msk, addr, true); mptcp_pm_add_addr_send_ack(msk); } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) { @@ -253,7 +245,7 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); @@ -277,7 +269,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, struct mptcp_pm_data *pm = &msk->pm; u8 i; - pr_debug("msk=%p remote_ids_nr=%d", msk, rm_list->nr); + pr_debug("msk=%p remote_ids_nr=%d\n", msk, rm_list->nr); for (i = 0; i < rm_list->nr; i++) mptcp_event_addr_removed(msk, rm_list->ids[i]); @@ -309,19 +301,19 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - pr_debug("fail_seq=%llu", fail_seq); + pr_debug("fail_seq=%llu\n", fail_seq); if (!READ_ONCE(msk->allow_infinite_fallback)) return; if (!subflow->fail_tout) { - pr_debug("send MP_FAIL response and infinite map"); + pr_debug("send MP_FAIL response and infinite map\n"); subflow->send_mp_fail = 1; subflow->send_infinite_map = 1; tcp_send_ack(sk); } else { - pr_debug("MP_FAIL response received"); + pr_debug("MP_FAIL response received\n"); WRITE_ONCE(subflow->fail_tout, 0); } } @@ -426,15 +418,24 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, &skc_local); } +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) +{ + struct mptcp_addr_info skc_local; + + mptcp_local_address((struct sock_common *)skc, &skc_local); + + if (mptcp_pm_is_userspace(msk)) + return mptcp_userspace_pm_is_backup(msk, &skc_local); + + return mptcp_pm_nl_is_backup(msk, &skc_local); +} + int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) { *flags = 0; *ifindex = 0; - if (!id) - return 0; - if (mptcp_pm_is_userspace(msk)) return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 8bf7ed6d63d1..f891bc714668 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -14,6 +14,7 @@ #include "protocol.h" #include "mib.h" +#include "mptcp_pm_gen.h" static int pm_nl_pernet_id; @@ -129,12 +130,15 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; - struct sock_common *skc; list_for_each_entry(subflow, list, node) { - skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - remote_address(skc, &cur); + if (!((1 << inet_sk_state_load(ssk)) & + (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV))) + continue; + + remote_address((struct sock_common *)ssk, &cur); if (mptcp_addresses_equal(&cur, daddr, daddr->port)) return true; } @@ -142,11 +146,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, return false; } -static struct mptcp_pm_addr_entry * +static bool select_local_address(const struct pm_nl_pernet *pernet, - const struct mptcp_sock *msk) + const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; msk_owned_by_me(msk); @@ -158,17 +164,21 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } -static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) +static bool +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; rcu_read_lock(); /* do not keep any additional per socket state, just signal @@ -183,11 +193,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) @@ -278,7 +290,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (!msk) return; @@ -297,7 +309,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) spin_lock_bh(&msk->pm.lock); if (!mptcp_pm_should_add_signal_addr(msk)) { - pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id); + pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id); mptcp_pm_announce_addr(msk, &entry->addr, false); mptcp_pm_add_addr_send_ack(msk); entry->retrans_times++; @@ -347,7 +359,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (add_entry) { - if (mptcp_pm_is_kernel(msk)) + if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; sk_reset_timer(sk, &add_entry->add_timer, @@ -378,7 +390,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) struct sock *sk = (struct sock *)msk; LIST_HEAD(free_list); - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&msk->pm.lock); list_splice_init(&msk->pm.anno_list, &free_list); @@ -464,13 +476,12 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow; - pr_debug("send ack for %s", + pr_debug("send ack for %s\n", prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr")); slow = lock_sock_fast(ssk); if (prio) { subflow->send_mp_prio = 1; - subflow->backup = backup; subflow->request_bkup = backup; } @@ -513,8 +524,9 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - struct mptcp_pm_addr_entry *local; + struct mptcp_pm_addr_entry local; unsigned int add_addr_signal_max; + bool signal_and_subflow = false; unsigned int local_addr_max; struct pm_nl_pernet *pernet; unsigned int subflows_max; @@ -555,8 +567,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check first for announce */ if (msk->pm.add_addr_signaled < add_addr_signal_max) { - local = select_signal_address(pernet, msk); - /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the @@ -567,16 +577,30 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; - if (local) { - if (mptcp_pm_alloc_anno_list(msk, &local->addr)) { - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); - mptcp_pm_nl_addr_send_ack(msk); - } - } + if (!select_signal_address(pernet, msk, &local)) + goto subflow; + + /* If the alloc fails, we are on memory pressure, not worth + * continuing, and trying to create subflows. + */ + if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) + return; + + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled++; + + /* Special case for ID0: set the correct ID */ + if (local.addr.id == msk->mpc_endpoint_id) + local.addr.id = 0; + + mptcp_pm_announce_addr(msk, &local.addr, false); + mptcp_pm_nl_addr_send_ack(msk); + + if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = true; } +subflow: /* check if should create a new subflow */ while (msk->pm.local_addr_used < local_addr_max && msk->pm.subflows < subflows_max) { @@ -584,21 +608,28 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) bool fullmesh; int i, nr; - local = select_local_address(pernet, msk); - if (!local) + if (signal_and_subflow) + signal_and_subflow = false; + else if (!select_local_address(pernet, msk, &local)) break; - fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + + /* Special case for ID0: set the correct ID */ + if (local.addr.id == msk->mpc_endpoint_id) + local.addr.id = 0; + else /* local_addr_used is not decr for ID 0 */ + msk->pm.local_addr_used++; - msk->pm.local_addr_used++; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); + nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs); if (nr == 0) continue; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); + __mptcp_subflow_connect(sk, &local.addr, &addrs[i]); spin_lock_bh(&msk->pm.lock); } mptcp_pm_nl_check_work_pending(msk); @@ -623,6 +654,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; + struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; @@ -630,6 +662,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk); + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) @@ -640,7 +674,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, if (msk->pm.subflows < subflows_max) { msk->pm.subflows++; - addrs[i++] = entry->addr; + addrs[i] = entry->addr; + + /* Special case for ID0: set the correct ID */ + if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port)) + addrs[i].id = 0; + + i++; } } rcu_read_unlock(); @@ -682,7 +722,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); subflows_max = mptcp_pm_get_subflows_max(msk); - pr_debug("accepted %d:%d remote family %d", + pr_debug("accepted %d:%d remote family %d\n", msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family); @@ -711,13 +751,24 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) spin_lock_bh(&msk->pm.lock); if (sf_created) { - msk->pm.add_addr_accepted++; + /* add_addr_accepted is not decr for ID 0 */ + if (remote.id) + msk->pm.add_addr_accepted++; if (msk->pm.add_addr_accepted >= add_addr_accept_max || msk->pm.subflows >= subflows_max) WRITE_ONCE(msk->pm.accept_addr, false); } } +bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *remote) +{ + struct mptcp_addr_info mpc_remote; + + remote_address((struct sock_common *)msk, &mpc_remote); + return mptcp_addresses_equal(&mpc_remote, remote, remote->port); +} + void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; @@ -729,9 +780,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) !mptcp_pm_should_rm_signal(msk)) return; - subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node); - if (subflow) - mptcp_pm_send_ack(msk, subflow, false, false); + mptcp_for_each_subflow(msk, subflow) { + if (__mptcp_subflow_active(subflow)) { + mptcp_pm_send_ack(msk, subflow, false, false); + break; + } + } } int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, @@ -741,7 +795,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, { struct mptcp_subflow_context *subflow; - pr_debug("bkup=%d", bkup); + pr_debug("bkup=%d\n", bkup); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -764,11 +818,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, return -EINVAL; } -static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id) -{ - return local_id == id || (!local_id && msk->mpc_endpoint_id == id); -} - static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list, enum linux_mptcp_mib_field rm_type) @@ -777,7 +826,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, struct sock *sk = (struct sock *)msk; u8 i; - pr_debug("%s rm_list_nr %d", + pr_debug("%s rm_list_nr %d\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr); msk_owned_by_me(msk); @@ -801,12 +850,14 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, int how = RCV_SHUTDOWN | SEND_SHUTDOWN; u8 id = subflow_get_local_id(subflow); + if (inet_sk_state_load(ssk) == TCP_CLOSE) + continue; if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; - if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) + if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id) continue; - pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", + pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); @@ -816,25 +867,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); - removed = true; + removed |= subflow->request_join; if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } - if (rm_type == MPTCP_MIB_RMSUBFLOW) - __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); - else if (rm_type == MPTCP_MIB_RMADDR) + + if (rm_type == MPTCP_MIB_RMADDR) __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (!removed) continue; if (!mptcp_pm_is_kernel(msk)) continue; - if (rm_type == MPTCP_MIB_RMADDR) { - msk->pm.add_addr_accepted--; - WRITE_ONCE(msk->pm.accept_addr, true); - } else if (rm_type == MPTCP_MIB_RMSUBFLOW) { - msk->pm.local_addr_used--; + if (rm_type == MPTCP_MIB_RMADDR && rm_id && + !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + /* Note: if the subflow has been closed before, this + * add_addr_accepted counter will not be decremented. + */ + if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk)) + WRITE_ONCE(msk->pm.accept_addr, true); } } } @@ -844,8 +897,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR); } -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list) +static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW); } @@ -861,7 +914,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk) spin_lock_bh(&msk->pm.lock); - pr_debug("msk=%p status=%x", msk, pm->status); + pr_debug("msk=%p status=%x\n", msk, pm->status); if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); mptcp_pm_nl_add_addr_received(msk); @@ -1101,6 +1154,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc return ret; } +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) +{ + struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + rcu_read_unlock(); + + return backup; +} + #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 @@ -1261,20 +1332,27 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) return pm_nl_get_pernet(genl_info_net(info)); } -static int mptcp_nl_add_subflow_or_signal_addr(struct net *net) +static int mptcp_nl_add_subflow_or_signal_addr(struct net *net, + struct mptcp_addr_info *addr) { struct mptcp_sock *msk; long s_slot = 0, s_num = 0; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; + struct mptcp_addr_info mpc_addr; if (!READ_ONCE(msk->fully_established) || mptcp_pm_is_userspace(msk)) goto next; + /* if the endp linked to the init sf is re-added with a != ID */ + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + lock_sock(sk); spin_lock_bh(&msk->pm.lock); + if (mptcp_addresses_equal(addr, &mpc_addr, addr->port)) + msk->mpc_endpoint_id = addr->id; mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1310,8 +1388,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; - if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - GENL_SET_ERR_MSG(info, "flags must have signal when using port"); + if (addr.addr.port && !address_use_port(&addr)) { + GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port"); return -EINVAL; } @@ -1347,7 +1425,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } - mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk)); + mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr); return 0; out_free: @@ -1362,6 +1440,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + /* No entries with ID 0 */ + if (id == 0) + return 0; + rcu_read_lock(); entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); if (entry) { @@ -1388,6 +1470,12 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, return false; } +static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) +{ + return msk->mpc_endpoint_id == addr->id ? 0 : addr->id; +} + static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool force) @@ -1395,28 +1483,38 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, struct mptcp_rm_list list = { .nr = 0 }; bool ret; - list.ids[list.nr++] = addr->id; + list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); + if (ret) { + __set_bit(addr->id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled--; + } mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } return ret; } +static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) +{ + /* If it was marked as used, and not ID 0, decrement local_addr_used */ + if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && + id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) + msk->pm.local_addr_used--; +} + static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { const struct mptcp_addr_info *addr = &entry->addr; - struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_rm_list list = { .nr = 1 }; long s_slot = 0, s_num = 0; struct mptcp_sock *msk; - pr_debug("remove_id=%d", addr->id); - - list.ids[list.nr++] = addr->id; + pr_debug("remove_id=%d\n", addr->id); while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; @@ -1434,8 +1532,22 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); - if (remove_subflow) - mptcp_pm_remove_subflow(msk, &list); + + list.ids[0] = mptcp_endp_get_local_id(msk, addr); + if (remove_subflow) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_nl_rm_subflow_received(msk, &list); + spin_unlock_bh(&msk->pm.lock); + } + + if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + spin_lock_bh(&msk->pm.lock); + __mark_subflow_endp_available(msk, list.ids[0]); + spin_unlock_bh(&msk->pm.lock); + } + + if (msk->mpc_endpoint_id == entry->addr.id) + msk->mpc_endpoint_id = 0; release_sock(sk); next: @@ -1470,6 +1582,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1529,25 +1642,36 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) return ret; } +/* Called from the userspace PM only */ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; + int anno_nr = 0; list_for_each_entry(entry, rm_list, list) { - if ((remove_anno_list_by_saddr(msk, &entry->addr) || - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr >= MPTCP_RM_IDS_MAX) + break; + + /* only delete if either announced or matching a subflow */ + if (remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!lookup_subflow_by_saddr(&msk->conn_list, + &entry->addr)) + continue; + + alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= anno_nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } } +/* Called from the in-kernel PM only */ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list) { @@ -1555,22 +1679,26 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && - slist.nr < MPTCP_RM_IDS_MAX) - slist.ids[slist.nr++] = entry->addr.id; + if (slist.nr < MPTCP_RM_IDS_MAX && + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) + slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); - if (remove_anno_list_by_saddr(msk, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr < MPTCP_RM_IDS_MAX && + remove_anno_list_by_saddr(msk, &entry->addr)) + alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); } + spin_lock_bh(&msk->pm.lock); if (alist.nr) { - spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); - spin_unlock_bh(&msk->pm.lock); } if (slist.nr) - mptcp_pm_remove_subflow(msk, &slist); + mptcp_pm_nl_rm_subflow_received(msk, &slist); + /* Reset counters: maybe some subflows have been removed before */ + bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + msk->pm.local_addr_used = 0; + spin_unlock_bh(&msk->pm.lock); } static void mptcp_nl_remove_addrs_list(struct net *net, @@ -1854,10 +1982,11 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, { struct mptcp_rm_list list = { .nr = 0 }; - list.ids[list.nr++] = addr->id; + list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 9f5d422d5ef6..8eaa9fbe3e34 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -6,6 +6,7 @@ #include "protocol.h" #include "mib.h" +#include "mptcp_pm_gen.h" void mptcp_free_local_addr_list(struct mptcp_sock *msk) { @@ -164,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, + struct mptcp_addr_info *skc) +{ + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, false)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + spin_unlock_bh(&msk->pm.lock); + + return backup; +} + int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 68e4c086483a..4c8c21d3c3f7 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -20,6 +20,7 @@ #include <net/transp_v6.h> #endif #include <net/mptcp.h> +#include <net/hotdata.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include "protocol.h" @@ -138,7 +139,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; - pr_debug("colesced seq %llx into %llx new len %d new end seq %llx", + pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n", MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; @@ -216,7 +217,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) end_seq = MPTCP_SKB_CB(skb)->end_seq; max_seq = atomic64_read(&msk->rcv_wnd_sent); - pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq, + pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq, RB_EMPTY_ROOT(&msk->out_of_order_queue)); if (after64(end_seq, max_seq)) { /* out of window */ @@ -349,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_orphan(skb); /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) + if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; + } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -640,7 +643,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } - pr_debug("msk=%p ssk=%p", msk, ssk); + pr_debug("msk=%p ssk=%p\n", msk, ssk); tp = tcp_sk(ssk); do { u32 map_remaining, offset; @@ -706,6 +709,8 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } while (more_data_avail); + if (moved > 0) + msk->last_data_recv = tcp_jiffies32; *bytes += moved; return done; } @@ -719,7 +724,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) u64 end_seq; p = rb_first(&msk->out_of_order_queue); - pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); + pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); while (p) { skb = rb_to_skb(p); if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) @@ -741,7 +746,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; /* skip overlapping data, if any */ - pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d", + pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n", MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, delta); MPTCP_SKB_CB(skb)->offset += delta; @@ -841,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + if (__mptcp_rmem(sk) > sk_rbuf) return; - } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1237,7 +1240,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, size_t copy; int i; - pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u", + pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n", msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent); if (WARN_ON_ONCE(info->sent > info->limit || @@ -1270,7 +1273,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); - if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { + if (!can_coalesce && i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } @@ -1338,7 +1341,7 @@ alloc_skb: mpext->use_map = 1; mpext->dsn64 = 1; - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d", + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n", mpext->data_seq, mpext->subflow_seq, mpext->data_len, mpext->dsn64); @@ -1419,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); - nr_active += !subflow->backup; + nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ @@ -1436,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (linger_time < send_info[subflow->backup].linger_time) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].linger_time = linger_time; + if (linger_time < send_info[backup].linger_time) { + send_info[backup].ssk = ssk; + send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); @@ -1556,6 +1561,8 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk, err = copied; out: + if (err > 0) + msk->last_data_sent = tcp_jiffies32; return err; } @@ -1885,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!msk->first_pending) WRITE_ONCE(msk->first_pending, dfrag); } - pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk, + pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, !dfrag_collapsed); @@ -2056,7 +2063,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); - tcp_sk(ssk)->window_clamp = window_clamp; + WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp); tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); } @@ -2241,7 +2248,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - pr_debug("block timeout %ld", timeo); + pr_debug("block timeout %ld\n", timeo); sk_wait_data(sk, &timeo, NULL); } @@ -2257,7 +2264,7 @@ out_err: } } - pr_debug("msk=%p rx queue empty=%d:%d copied=%d", + pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n", msk, skb_queue_empty_lockless(&sk->sk_receive_queue), skb_queue_empty(&msk->receive_queue), copied); if (!(flags & MSG_PEEK)) @@ -2319,7 +2326,7 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) continue; } - if (subflow->backup) { + if (subflow->backup || subflow->request_bkup) { if (!backup) backup = ssk; continue; @@ -2501,6 +2508,12 @@ out: void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { + /* The first subflow can already be closed and still in the list */ + if (subflow->close_event_done) + return; + + subflow->close_event_done = true; + if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); @@ -2526,8 +2539,11 @@ static void __mptcp_close_subflow(struct sock *sk) mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int ssk_state = inet_sk_state_load(ssk); - if (inet_sk_state_load(ssk) != TCP_CLOSE) + if (ssk_state != TCP_CLOSE && + (ssk_state != TCP_CLOSE_WAIT || + inet_sk_state_load(sk) != TCP_ESTABLISHED)) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ @@ -2565,7 +2581,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { - tcp_send_active_reset(tcp_sk, GFP_ATOMIC); + mptcp_send_active_reset_reason(tcp_sk); tcp_set_state(tcp_sk, TCP_CLOSE); } unlock_sock_fast(tcp_sk, slow); @@ -2707,7 +2723,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) if (!ssk) return; - pr_debug("MP_FAIL doesn't respond, reset the subflow"); + pr_debug("MP_FAIL doesn't respond, reset the subflow\n"); slow = lock_sock_fast(ssk); mptcp_subflow_reset(ssk); @@ -2793,6 +2809,9 @@ static void __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; msk->subflow_id = 1; + msk->last_data_sent = tcp_jiffies32; + msk->last_data_recv = tcp_jiffies32; + msk->last_ack_recv = tcp_jiffies32; mptcp_pm_data_init(msk); @@ -2806,7 +2825,8 @@ static void mptcp_ca_reset(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); tcp_assign_congestion_control(sk); - strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name); + strscpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name, + sizeof(mptcp_sk(sk)->ca_name)); /* no need to keep a reference to the ops, the name will suffice */ tcp_cleanup_congestion_control(sk); @@ -2877,7 +2897,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) break; default: if (__mptcp_check_fallback(mptcp_sk(sk))) { - pr_debug("Fallback"); + pr_debug("Fallback\n"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); @@ -2887,7 +2907,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); mptcp_schedule_work(sk); } else { - pr_debug("Sending DATA_FIN on subflow %p", ssk); + pr_debug("Sending DATA_FIN on subflow %p\n", ssk); tcp_send_ack(ssk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); @@ -2953,7 +2973,7 @@ static void mptcp_check_send_data_fin(struct sock *sk) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu", + pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n", msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk), msk->snd_nxt, msk->write_seq); @@ -2977,7 +2997,7 @@ static void __mptcp_wr_shutdown(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d", + pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n", msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state, !!mptcp_send_head(sk)); @@ -2992,7 +3012,7 @@ static void __mptcp_destroy_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); might_sleep(); @@ -3100,7 +3120,7 @@ cleanup: mptcp_set_state(sk, TCP_CLOSE); sock_hold(sk); - pr_debug("msk=%p state=%d", sk, sk->sk_state); + pr_debug("msk=%p state=%d\n", sk, sk->sk_state); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); @@ -3532,7 +3552,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p, ssk=%p", msk, msk->first); + pr_debug("msk=%p, ssk=%p\n", msk, msk->first); if (WARN_ON_ONCE(!msk->first)) return -EINVAL; @@ -3549,7 +3569,7 @@ void mptcp_finish_connect(struct sock *ssk) sk = subflow->conn; msk = mptcp_sk(sk); - pr_debug("msk=%p, token=%u", sk, subflow->token); + pr_debug("msk=%p, token=%u\n", sk, subflow->token); subflow->map_seq = subflow->iasn; subflow->map_subflow_seq = 1; @@ -3578,7 +3598,7 @@ bool mptcp_finish_join(struct sock *ssk) struct sock *parent = (void *)msk; bool ret = true; - pr_debug("msk=%p, subflow=%p", msk, subflow); + pr_debug("msk=%p, subflow=%p\n", msk, subflow); /* mptcp socket already closing? */ if (!mptcp_is_fully_established(parent)) { @@ -3624,7 +3644,7 @@ err_prohibited: static void mptcp_shutdown(struct sock *sk, int how) { - pr_debug("sk=%p, how=%d", sk, how); + pr_debug("sk=%p, how=%d\n", sk, how); if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk)) __mptcp_wr_shutdown(sk); @@ -3845,7 +3865,7 @@ static int mptcp_listen(struct socket *sock, int backlog) struct sock *ssk; int err; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); lock_sock(sk); @@ -3879,13 +3899,12 @@ unlock: } static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *newsk; - int err; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. @@ -3894,12 +3913,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk) return -EINVAL; - pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); - newsk = inet_csk_accept(ssk, flags, &err, kern); + pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk)); + newsk = inet_csk_accept(ssk, arg); if (!newsk) - return err; + return arg->err; - pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); + pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; @@ -3918,7 +3937,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); - newsk->sk_kern_sock = kern; + newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); @@ -3947,7 +3966,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, } } else { tcpfallback: - newsk->sk_kern_sock = kern; + newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); /* we are being invoked after accepting a non-mp-capable @@ -3992,7 +4011,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); - pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); + pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags); if (state == TCP_LISTEN) { struct sock *ssk = READ_ONCE(msk->first); @@ -4167,7 +4186,7 @@ int __init mptcp_proto_v6_init(void) int err; mptcp_v6_prot = mptcp_prot; - strcpy(mptcp_v6_prot.name, "MPTCPv6"); + strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name)); mptcp_v6_prot.slab = NULL; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9d1ee199490b..0241b0dbab3c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -12,8 +12,7 @@ #include <net/inet_connection_sock.h> #include <uapi/linux/mptcp.h> #include <net/genetlink.h> - -#include "mptcp_pm_gen.h" +#include <net/rstreason.h> #define MPTCP_SUPPORTED_VERSION 1 @@ -282,6 +281,9 @@ struct mptcp_sock { u64 bytes_acked; u64 snd_una; u64 wnd_end; + u32 last_data_sent; + u32 last_data_recv; + u32 last_ack_recv; unsigned long timer_ival; u32 token; int rmem_released; @@ -441,6 +443,7 @@ struct mptcp_subflow_request_sock { u16 mp_capable : 1, mp_join : 1, backup : 1, + request_bkup : 1, csum_reqd : 1, allow_join_id0 : 1; u8 local_id; @@ -516,7 +519,8 @@ struct mptcp_subflow_context { stale : 1, /* unable to snd/rcv data, do not use for xmit */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 10; + close_event_done : 1, /* has done the post-closed part */ + __unused : 9; bool data_avail; bool scheduled; u32 remote_nonce; @@ -561,7 +565,7 @@ struct mptcp_subflow_context { static inline struct mptcp_subflow_context * mptcp_subflow_ctx(const struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); /* Use RCU on icsk_ulp_data only for sock diag code */ return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data; @@ -581,6 +585,43 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) WRITE_ONCE(subflow->local_id, -1); } +/* Convert reset reasons in MPTCP to enum sk_rst_reason type */ +static inline enum sk_rst_reason +sk_rst_convert_mptcp_reason(u32 reason) +{ + switch (reason) { + case MPTCP_RST_EUNSPEC: + return SK_RST_REASON_MPTCP_RST_EUNSPEC; + case MPTCP_RST_EMPTCP: + return SK_RST_REASON_MPTCP_RST_EMPTCP; + case MPTCP_RST_ERESOURCE: + return SK_RST_REASON_MPTCP_RST_ERESOURCE; + case MPTCP_RST_EPROHIBIT: + return SK_RST_REASON_MPTCP_RST_EPROHIBIT; + case MPTCP_RST_EWQ2BIG: + return SK_RST_REASON_MPTCP_RST_EWQ2BIG; + case MPTCP_RST_EBADPERF: + return SK_RST_REASON_MPTCP_RST_EBADPERF; + case MPTCP_RST_EMIDDLEBOX: + return SK_RST_REASON_MPTCP_RST_EMIDDLEBOX; + default: + /* It should not happen, or else errors may occur + * in MPTCP layer + */ + return SK_RST_REASON_ERROR; + } +} + +static inline void +mptcp_send_active_reset_reason(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + enum sk_rst_reason reason; + + reason = sk_rst_convert_mptcp_reason(subflow->reset_reason); + tcp_send_active_reset(sk, GFP_ATOMIC, reason); +} + static inline u64 mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow) { @@ -645,6 +686,7 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net); unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); +void mptcp_get_available_schedulers(char *buf, size_t maxlen); void __mptcp_subflow_fully_established(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt); @@ -946,6 +988,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk); +bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *remote); void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); @@ -980,7 +1024,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -1063,6 +1106,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc); +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); @@ -1084,8 +1130,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list); unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); @@ -1131,7 +1175,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk) static inline void __mptcp_do_fallback(struct mptcp_sock *msk) { if (__mptcp_check_fallback(msk)) { - pr_debug("TCP fallback already done (msk=%p)", msk); + pr_debug("TCP fallback already done (msk=%p)\n", msk); return; } set_bit(MPTCP_FALLBACK_DONE, &msk->flags); @@ -1167,7 +1211,7 @@ static inline void mptcp_do_fallback(struct sock *ssk) } } -#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a) +#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a) static inline bool mptcp_check_infinite_map(struct sk_buff *skb) { diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c index 4ab0693c069c..78ed508ebc1b 100644 --- a/net/mptcp/sched.c +++ b/net/mptcp/sched.c @@ -51,6 +51,28 @@ struct mptcp_sched_ops *mptcp_sched_find(const char *name) return ret; } +/* Build string with list of available scheduler values. + * Similar to tcp_get_available_congestion_control() + */ +void mptcp_get_available_schedulers(char *buf, size_t maxlen) +{ + struct mptcp_sched_ops *sched; + size_t offs = 0; + + rcu_read_lock(); + spin_lock(&mptcp_sched_list_lock); + list_for_each_entry_rcu(sched, &mptcp_sched_list, list) { + offs += snprintf(buf + offs, maxlen - offs, + "%s%s", + offs == 0 ? "" : " ", sched->name); + + if (WARN_ON_ONCE(offs >= maxlen)) + break; + } + spin_unlock(&mptcp_sched_list_lock); + rcu_read_unlock(); +} + int mptcp_register_scheduler(struct mptcp_sched_ops *sched) { if (!sched->get_subflow) @@ -64,7 +86,7 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched) list_add_tail_rcu(&sched->list, &mptcp_sched_list); spin_unlock(&mptcp_sched_list_lock); - pr_debug("%s registered", sched->name); + pr_debug("%s registered\n", sched->name); return 0; } @@ -96,7 +118,7 @@ int mptcp_init_sched(struct mptcp_sock *msk, if (msk->sched->init) msk->sched->init(msk); - pr_debug("sched=%s", msk->sched->name); + pr_debug("sched=%s\n", msk->sched->name); return 0; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 19ee684f9e40..499bd002ceb8 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -616,7 +616,7 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t } if (ret == 0) - strcpy(msk->ca_name, name); + strscpy(msk->ca_name, name, sizeof(msk->ca_name)); release_sock(sk); return ret; @@ -873,7 +873,7 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (level == SOL_SOCKET) return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); @@ -937,6 +937,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) struct sock *sk = (struct sock *)msk; u32 flags = 0; bool slow; + u32 now; memset(info, 0, sizeof(*info)); @@ -965,11 +966,6 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; info->mptcpi_flags = flags; - mptcp_data_lock(sk); - info->mptcpi_snd_una = msk->snd_una; - info->mptcpi_rcv_nxt = msk->ack_seq; - info->mptcpi_bytes_acked = msk->bytes_acked; - mptcp_data_unlock(sk); slow = lock_sock_fast(sk); info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); @@ -981,7 +977,17 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_bytes_retrans = msk->bytes_retrans; info->mptcpi_subflows_total = info->mptcpi_subflows + __mptcp_has_initial_subflow(msk); + now = tcp_jiffies32; + info->mptcpi_last_data_sent = jiffies_to_msecs(now - msk->last_data_sent); + info->mptcpi_last_data_recv = jiffies_to_msecs(now - msk->last_data_recv); unlock_sock_fast(sk, slow); + + mptcp_data_lock(sk); + info->mptcpi_last_ack_recv = jiffies_to_msecs(now - msk->last_ack_recv); + info->mptcpi_snd_una = msk->snd_una; + info->mptcpi_rcv_nxt = msk->ack_seq; + info->mptcpi_bytes_acked = msk->bytes_acked; + mptcp_data_unlock(sk); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); @@ -993,6 +999,10 @@ static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, in if (get_user(len, optlen)) return -EFAULT; + /* When used only to check if a fallback to TCP happened. */ + if (len == 0) + return 0; + len = min_t(unsigned int, len, sizeof(struct mptcp_info)); mptcp_diag_fill_info(msk, &m_info); @@ -1395,6 +1405,8 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes)); case TCP_NOTSENT_LOWAT: return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); + case TCP_IS_MPTCP: + return mptcp_put_int_option(msk, optval, optlen, 1); } return -EOPNOTSUPP; } @@ -1441,7 +1453,7 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the @@ -1579,7 +1591,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val) slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, space); - tcp_sk(ssk)->window_clamp = val; + WRITE_ONCE(tcp_sk(ssk)->window_clamp, val); unlock_sock_fast(ssk, slow); } return 0; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6042a47da61b..fc813d538a5a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -20,6 +20,7 @@ #include <net/transp_v6.h> #endif #include <net/mptcp.h> + #include "protocol.h" #include "mib.h" @@ -38,7 +39,7 @@ static void subflow_req_destructor(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - pr_debug("subflow_req=%p", subflow_req); + pr_debug("subflow_req=%p\n", subflow_req); if (subflow_req->msk) sock_put((struct sock *)subflow_req->msk); @@ -99,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) return NULL; } subflow_req->local_id = local_id; + subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req); return msk; } @@ -144,14 +146,16 @@ static int subflow_check_req(struct request_sock *req, struct mptcp_options_received mp_opt; bool opt_mp_capable, opt_mp_join; - pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); + pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ - if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) + if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info)) { + subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP); return -EINVAL; + } #endif mptcp_get_options(skb, &mp_opt); @@ -165,6 +169,9 @@ static int subflow_check_req(struct request_sock *req, return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); + + if (mp_opt.backup) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (opt_mp_capable && listener->request_mptcp) { @@ -214,11 +221,12 @@ again: } if (subflow_use_different_sport(subflow_req->msk, sk_listener)) { - pr_debug("syn inet_sport=%d %d", + pr_debug("syn inet_sport=%d %d\n", ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); return -EPERM; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX); @@ -227,13 +235,15 @@ again: subflow_req_create_thmac(subflow_req); if (unlikely(req->syncookie)) { - if (mptcp_can_accept_new_subflow(subflow_req->msk)) - subflow_init_req_cookie_join_save(subflow_req, skb); - else + if (!mptcp_can_accept_new_subflow(subflow_req->msk)) { + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); return -EPERM; + } + + subflow_init_req_cookie_join_save(subflow_req, skb); } - pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, + pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token, subflow_req->remote_nonce, subflow_req->msk); } @@ -281,10 +291,21 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, } EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req); +static enum sk_rst_reason mptcp_get_rst_reason(const struct sk_buff *skb) +{ + const struct mptcp_ext *mpext = mptcp_get_ext(skb); + + if (!mpext) + return SK_RST_REASON_NOT_SPECIFIED; + + return sk_rst_convert_mptcp_reason(mpext->reset_reason); +} + static struct dst_entry *subflow_v4_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req) + struct request_sock *req, + u32 tw_isn) { struct dst_entry *dst; int err; @@ -292,7 +313,7 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk, tcp_rsk(req)->is_mptcp = 1; subflow_init_req(req, sk); - dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req); + dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req, tw_isn); if (!dst) return NULL; @@ -302,7 +323,8 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk, dst_release(dst); if (!req->syncookie) - tcp_request_sock_ops.send_reset(sk, skb); + tcp_request_sock_ops.send_reset(sk, skb, + mptcp_get_rst_reason(skb)); return NULL; } @@ -351,7 +373,8 @@ static int subflow_v6_send_synack(const struct sock *sk, struct dst_entry *dst, static struct dst_entry *subflow_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct request_sock *req) + struct request_sock *req, + u32 tw_isn) { struct dst_entry *dst; int err; @@ -359,7 +382,7 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk, tcp_rsk(req)->is_mptcp = 1; subflow_init_req(req, sk); - dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req); + dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req, tw_isn); if (!dst) return NULL; @@ -369,7 +392,8 @@ static struct dst_entry *subflow_v6_route_req(const struct sock *sk, dst_release(dst); if (!req->syncookie) - tcp6_request_sock_ops.send_reset(sk, skb); + tcp6_request_sock_ops.send_reset(sk, skb, + mptcp_get_rst_reason(skb)); return NULL; } #endif @@ -405,7 +429,7 @@ void mptcp_subflow_reset(struct sock *ssk) /* must hold: tcp_done() could drop last reference on parent */ sock_hold(sk); - tcp_send_active_reset(ssk, GFP_ATOMIC); + mptcp_send_active_reset_reason(ssk); tcp_done(ssk); if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) mptcp_schedule_work(sk); @@ -503,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; - pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); + pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset); mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { @@ -535,7 +559,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; WRITE_ONCE(subflow->remote_id, mp_opt.join_id); - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", + pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -557,8 +581,11 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + if (subflow->backup) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); + if (subflow_use_different_dport(msk, sk)) { - pr_debug("synack inet_dport=%d %d", + pr_debug("synack inet_dport=%d %d\n", ntohs(inet_sk(sk)->inet_dport), ntohs(inet_sk(parent)->inet_dport)); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX); @@ -594,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk) return err; subflow_set_local_id(subflow, err); + subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk); + return 0; } @@ -626,7 +655,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); /* Never answer to SYNs sent to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -657,7 +686,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); if (skb->protocol == htons(ETH_P_IP)) return subflow_v4_conn_request(sk, skb); @@ -774,10 +803,11 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_subflow_request_sock *subflow_req; struct mptcp_options_received mp_opt; bool fallback, fallback_is_fatal; + enum sk_rst_reason reason; struct mptcp_sock *owner; struct sock *child; - pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); + pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn); /* After child creation we must look for MPC even when options * are not parsed @@ -868,18 +898,23 @@ create_child: ctx->conn = (struct sock *)owner; if (subflow_use_different_sport(owner, sk)) { - pr_debug("ack inet_sport=%d %d", + pr_debug("ack inet_sport=%d %d\n", ntohs(inet_sk(sk)->inet_sport), ntohs(inet_sk((struct sock *)owner)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(owner, sk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); goto dispose_child; } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX); } - if (!mptcp_finish_join(child)) + if (!mptcp_finish_join(child)) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(child); + + subflow_add_reset_reason(skb, subflow->reset_reason); goto dispose_child; + } SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX); tcp_rsk(req)->drop_req = true; @@ -887,7 +922,7 @@ create_child: } /* check for expected invariant - should never trigger, just help - * catching eariler subtle bugs + * catching earlier subtle bugs */ WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp && (!mptcp_subflow_ctx(child) || @@ -899,7 +934,8 @@ dispose_child: tcp_rsk(req)->drop_req = true; inet_csk_prepare_for_destroy_sock(child); tcp_done(child); - req->rsk_ops->send_reset(sk, skb); + reason = mptcp_get_rst_reason(skb); + req->rsk_ops->send_reset(sk, skb, reason); /* The last child reference will be released by the caller */ return child; @@ -925,7 +961,7 @@ enum mapping_status { static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n", ssn, subflow->map_subflow_seq, subflow->map_data_len); } @@ -1085,17 +1121,19 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len = mpext->data_len; if (data_len == 0) { - pr_debug("infinite mapping received"); + pr_debug("infinite mapping received\n"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); subflow->map_data_len = 0; return MAPPING_INVALID; } if (mpext->data_fin == 1) { + u64 data_fin_seq; + if (data_len == 1) { bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq, mpext->dsn64); - pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq); + pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS * option before the previous mapping @@ -1104,26 +1142,26 @@ static enum mapping_status get_mapping_status(struct sock *ssk, */ skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; - } else { - if (updated) - mptcp_schedule_work((struct sock *)msk); - - return MAPPING_DATA_FIN; } - } else { - u64 data_fin_seq = mpext->data_seq + data_len - 1; - /* If mpext->data_seq is a 32-bit value, data_fin_seq - * must also be limited to 32 bits. - */ - if (!mpext->dsn64) - data_fin_seq &= GENMASK_ULL(31, 0); + if (updated) + mptcp_schedule_work((struct sock *)msk); - mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); - pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d", - data_fin_seq, mpext->dsn64); + return MAPPING_DATA_FIN; } + data_fin_seq = mpext->data_seq + data_len - 1; + + /* If mpext->data_seq is a 32-bit value, data_fin_seq must also + * be limited to 32 bits. + */ + if (!mpext->dsn64) + data_fin_seq &= GENMASK_ULL(31, 0); + + mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); + pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n", + data_fin_seq, mpext->dsn64); + /* Adjust for DATA_FIN using 1 byte of sequence space */ data_len--; } @@ -1167,7 +1205,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (unlikely(subflow->map_csum_reqd != csum_reqd)) return MAPPING_INVALID; - pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", + pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n", subflow->map_seq, subflow->map_subflow_seq, subflow->map_data_len, subflow->map_csum_reqd, subflow->map_data_csum); @@ -1192,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - u32 incr; + struct tcp_sock *tp = tcp_sk(ssk); + u32 offset, incr, avail_len; + + offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(offset > skb->len)) + goto out; - incr = limit >= skb->len ? skb->len + fin : limit; + avail_len = skb->len - offset; + incr = limit >= avail_len ? avail_len + fin : limit; - pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, - subflow->map_subflow_seq); + pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len, + offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; + +out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) @@ -1209,12 +1255,16 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { - if (likely(ssk->sk_state != TCP_CLOSE)) + struct sock *sk = (struct sock *)msk; + + if (likely(ssk->sk_state != TCP_CLOSE && + (ssk->sk_state != TCP_CLOSE_WAIT || + inet_sk_state_load(sk) != TCP_ESTABLISHED))) return; if (skb_queue_empty(&ssk->sk_receive_queue) && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) - mptcp_schedule_work((struct sock *)msk); + mptcp_schedule_work(sk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) @@ -1234,7 +1284,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); unsigned long fail_tout; - /* greceful failure can happen only on the MPC subflow */ + /* graceful failure can happen only on the MPC subflow */ if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first))) return; @@ -1291,7 +1341,7 @@ static bool subflow_check_data_avail(struct sock *ssk) old_ack = READ_ONCE(msk->ack_seq); ack_seq = mptcp_subflow_get_mapped_dsn(subflow); - pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, + pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack, ack_seq); if (unlikely(before64(ack_seq, old_ack))) { mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); @@ -1336,7 +1386,7 @@ reset: tcp_set_state(ssk, TCP_CLOSE); while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); - tcp_send_active_reset(ssk, GFP_ATOMIC); + mptcp_send_active_reset_reason(ssk); WRITE_ONCE(subflow->data_avail, false); return false; } @@ -1363,7 +1413,7 @@ bool mptcp_subflow_data_available(struct sock *sk) subflow->map_valid = 0; WRITE_ONCE(subflow->data_avail, false); - pr_debug("Done with mapping: seq=%u data_len=%u", + pr_debug("Done with mapping: seq=%u data_len=%u\n", subflow->map_subflow_seq, subflow->map_data_len); } @@ -1473,7 +1523,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); - pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d", + pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n", subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped); if (likely(icsk->icsk_af_ops == target)) @@ -1566,7 +1616,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, goto failed; mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL); - pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, + pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; WRITE_ONCE(subflow->remote_id, remote_id); @@ -1701,7 +1751,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid; subflow = mptcp_subflow_ctx(sf->sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); *new_sock = sf; sock_hold(sk); @@ -1730,7 +1780,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, INIT_LIST_HEAD(&ctx->node); INIT_LIST_HEAD(&ctx->delegated_node); - pr_debug("subflow=%p", ctx); + pr_debug("subflow=%p\n", ctx); ctx->tcp_sock = sk; WRITE_ONCE(ctx->local_id, -1); @@ -1881,7 +1931,7 @@ static int subflow_ulp_init(struct sock *sk) goto out; } - pr_debug("subflow=%p, family=%d", ctx, sk->sk_family); + pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family); tp->is_mptcp = 1; ctx->icsk_af_ops = icsk->icsk_af_ops; @@ -1976,6 +2026,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; + new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index a2c16b501087..c7a8a08b7308 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1550,6 +1550,7 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(flags); __be16 type; /* Only support version 0 and C (csum) */ @@ -1560,7 +1561,10 @@ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; - return gre_calc_hlen(gre_flags_to_tnl_flags(greh->flags)); + + gre_flags_to_tnl_flags(flags, greh->flags); + + return gre_calc_hlen(flags); } unk: diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 143a341bbc0a..f4384e147ee1 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -94,6 +94,7 @@ static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; int availmem; + int amemthresh; int nomem; int to_change = -1; @@ -105,7 +106,8 @@ static void update_defense_level(struct netns_ipvs *ipvs) /* si_swapinfo(&i); */ /* availmem = availmem - (i.totalswap - i.freeswap); */ - nomem = (availmem < ipvs->sysctl_amemthresh); + amemthresh = max(READ_ONCE(ipvs->sysctl_amemthresh), 0); + nomem = (availmem < amemthresh); local_bh_disable(); @@ -145,9 +147,8 @@ static void update_defense_level(struct netns_ipvs *ipvs) break; case 1: if (nomem) { - ipvs->drop_rate = ipvs->drop_counter - = ipvs->sysctl_amemthresh / - (ipvs->sysctl_amemthresh-availmem); + ipvs->drop_counter = amemthresh / (amemthresh - availmem); + ipvs->drop_rate = ipvs->drop_counter; ipvs->sysctl_drop_packet = 2; } else { ipvs->drop_rate = 0; @@ -155,9 +156,8 @@ static void update_defense_level(struct netns_ipvs *ipvs) break; case 2: if (nomem) { - ipvs->drop_rate = ipvs->drop_counter - = ipvs->sysctl_amemthresh / - (ipvs->sysctl_amemthresh-availmem); + ipvs->drop_counter = amemthresh / (amemthresh - availmem); + ipvs->drop_rate = ipvs->drop_counter; } else { ipvs->drop_rate = 0; ipvs->sysctl_drop_packet = 1; @@ -1459,18 +1459,18 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, if (ret < 0) goto out_err; - /* Bind the ct retriever */ - RCU_INIT_POINTER(svc->pe, pe); - pe = NULL; - /* Update the virtual service counters */ if (svc->port == FTPPORT) atomic_inc(&ipvs->ftpsvc_counter); else if (svc->port == 0) atomic_inc(&ipvs->nullsvc_counter); - if (svc->pe && svc->pe->conn_out) + if (pe && pe->conn_out) atomic_inc(&ipvs->conn_out_counter); + /* Bind the ct retriever */ + RCU_INIT_POINTER(svc->pe, pe); + pe = NULL; + /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) ipvs->num_services++; @@ -2263,7 +2263,6 @@ static struct ctl_table vs_vars[] = { .proc_handler = proc_dointvec, }, #endif - { } }; #endif @@ -4270,6 +4269,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) struct ctl_table *tbl; int idx, ret; size_t ctl_table_size = ARRAY_SIZE(vs_vars); + bool unpriv = net->user_ns != &init_user_ns; atomic_set(&ipvs->dropentry, 0); spin_lock_init(&ipvs->dropentry_lock); @@ -4284,12 +4284,6 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); if (tbl == NULL) return -ENOMEM; - - /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) { - tbl[0].procname = NULL; - ctl_table_size = 0; - } } else tbl = vs_vars; /* Initialize sysctl defaults */ @@ -4315,10 +4309,17 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) ipvs->sysctl_sync_ports = 1; tbl[idx++].data = &ipvs->sysctl_sync_ports; tbl[idx++].data = &ipvs->sysctl_sync_persist_mode; + ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32; + if (unpriv) + tbl[idx].mode = 0444; tbl[idx++].data = &ipvs->sysctl_sync_qlen_max; + ipvs->sysctl_sync_sock_size = 0; + if (unpriv) + tbl[idx].mode = 0444; tbl[idx++].data = &ipvs->sysctl_sync_sock_size; + tbl[idx++].data = &ipvs->sysctl_cache_bypass; tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn; tbl[idx++].data = &ipvs->sysctl_sloppy_tcp; @@ -4341,15 +4342,22 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; + ipvs->sysctl_run_estimation = 1; + if (unpriv) + tbl[idx].mode = 0444; tbl[idx].extra2 = ipvs; tbl[idx++].data = &ipvs->sysctl_run_estimation; ipvs->est_cpulist_valid = 0; + if (unpriv) + tbl[idx].mode = 0444; tbl[idx].extra2 = ipvs; tbl[idx++].data = &ipvs->sysctl_est_cpulist; ipvs->sysctl_est_nice = IPVS_EST_NICE; + if (unpriv) + tbl[idx].mode = 0444; tbl[idx].extra2 = ipvs; tbl[idx++].data = &ipvs->sysctl_est_nice; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 8ceec7a2fa8f..2423513d701d 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -123,7 +123,6 @@ static struct ctl_table vs_vars_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; #endif @@ -563,10 +562,8 @@ static int __net_init __ip_vs_lblc_init(struct net *net) return -ENOMEM; /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) { - ipvs->lblc_ctl_table[0].procname = NULL; + if (net->user_ns != &init_user_ns) vars_table_size = 0; - } } else ipvs->lblc_ctl_table = vs_vars_table; diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 0fb64707213f..cdb1d4bf6761 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -294,7 +294,6 @@ static struct ctl_table vs_vars_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { } }; #endif @@ -749,10 +748,8 @@ static int __net_init __ip_vs_lblcr_init(struct net *net) return -ENOMEM; /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) { - ipvs->lblcr_ctl_table[0].procname = NULL; + if (net->user_ns != &init_user_ns) vars_table_size = 0; - } } else ipvs->lblcr_ctl_table = vs_vars_table; ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1e689c714127..83e452916403 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -175,7 +175,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index e1f17392f58c..3313bceb6cc9 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -390,10 +390,10 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, skb->ip_summed == CHECKSUM_PARTIAL) mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); mtu -= gre_calc_hlen(tflags); } if (mtu < 68) { @@ -553,10 +553,10 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, skb->ip_summed == CHECKSUM_PARTIAL) mtu -= GUE_PLEN_REMCSUM + GUE_LEN_PRIV; } else if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; if (dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); mtu -= gre_calc_hlen(tflags); } if (mtu < IPV6_MIN_MTU) { @@ -1082,11 +1082,11 @@ ipvs_gre_encap(struct net *net, struct sk_buff *skb, { __be16 proto = *next_protocol == IPPROTO_IPIP ? htons(ETH_P_IP) : htons(ETH_P_IPV6); - __be16 tflags = 0; + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t hdrlen; if (cp->dest->tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); hdrlen = gre_calc_hlen(tflags); gre_build_header(skb, hdrlen, tflags, proto, 0, 0); @@ -1165,11 +1165,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom += sizeof(struct udphdr) + gue_hdrlen; } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t gre_hdrlen; - __be16 tflags = 0; if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); gre_hdrlen = gre_calc_hlen(tflags); max_headroom += gre_hdrlen; @@ -1310,11 +1310,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, max_headroom += sizeof(struct udphdr) + gue_hdrlen; } else if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { + IP_TUNNEL_DECLARE_FLAGS(tflags) = { }; size_t gre_hdrlen; - __be16 tflags = 0; if (tun_flags & IP_VS_TUNNEL_ENCAP_FLAG_CSUM) - tflags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tflags); gre_hdrlen = gre_calc_hlen(tflags); max_headroom += gre_hdrlen; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c63868666bd9..7ac20750c127 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1440,8 +1440,6 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) const struct nf_conntrack_l4proto *l4proto; u8 protonum = nf_ct_protonum(ct); - if (test_bit(IPS_OFFLOAD_BIT, &ct->status) && protonum != IPPROTO_UDP) - return false; if (!test_bit(IPS_ASSURED_BIT, &ct->status)) return true; @@ -2024,7 +2022,7 @@ repeat: goto repeat; NF_CT_STAT_INC_ATOMIC(state->net, invalid); - if (ret == -NF_DROP) + if (ret == NF_DROP) NF_CT_STAT_INC_ATOMIC(state->net, drop); ret = -ret; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 3b846cbdc050..4cbf71d0786b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3420,7 +3420,8 @@ static int ctnetlink_del_expect(struct sk_buff *skb, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index e2db1f4ec2df..ebc4f733bb2e 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -525,7 +525,7 @@ int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh); if (!dh) - return NF_DROP; + return -NF_ACCEPT; if (dccp_error(dh, skb, dataoff, state)) return -NF_ACCEPT; @@ -533,7 +533,7 @@ int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, /* pull again, including possible 48 bit sequences and subtype header */ dh = dccp_header_pointer(skb, dataoff, dh, &_dh); if (!dh) - return NF_DROP; + return -NF_ACCEPT; type = dh->dccph_type; if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state)) diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 1020d67600a9..327b8059025d 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -62,7 +62,9 @@ static const u_int8_t noct_valid_new[] = { [NDISC_ROUTER_ADVERTISEMENT - 130] = 1, [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1, [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1, - [ICMPV6_MLD2_REPORT - 130] = 1 + [ICMPV6_MLD2_REPORT - 130] = 1, + [ICMPV6_MRDISC_ADV - 130] = 1, + [ICMPV6_MRDISC_SOL - 130] = 1 }; bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 559665467b04..6c40bdf8b05a 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -610,11 +610,9 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif - __NF_SYSCTL_CT_LAST_SYSCTL, + NF_SYSCTL_CT_LAST_SYSCTL, }; -#define NF_SYSCTL_CT_LAST_SYSCTL (__NF_SYSCTL_CT_LAST_SYSCTL + 1) - static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_MAX] = { .procname = "nf_conntrack_max", @@ -942,7 +940,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, #endif - {} }; static struct ctl_table nf_ct_netfilter_table[] = { @@ -953,7 +950,6 @@ static struct ctl_table nf_ct_netfilter_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, @@ -1107,7 +1103,7 @@ out_unregister_netfilter: static void nf_conntrack_standalone_fini_sysctl(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); - struct ctl_table *table; + const struct ctl_table *table; table = cnet->sysctl_header->ctl_table_arg; unregister_net_sysctl_table(cnet->sysctl_header); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 6eef15648b7b..b0f199171932 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return NF_ACCEPT; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); proto = veth->h_vlan_encapsulated_proto; break; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index c2c005234dcd..98edcaa37b38 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return false; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); if (veth->h_vlan_encapsulated_proto == proto) { *offset += VLAN_HLEN; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index a010b25076ca..3d46372b538e 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, struct list_head *block_cb_list) { struct flow_cls_offload cls_flow = {}; + struct netlink_ext_ack extack = {}; struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0; diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c index 7cdb59bb4459..d8ebebc9775d 100644 --- a/net/netfilter/nf_hooks_lwtunnel.c +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -117,4 +117,7 @@ void netfilter_lwtunnel_fini(void) { unregister_pernet_subsys(&nf_lwtunnel_net_ops); } +#else +int __init netfilter_lwtunnel_init(void) { return 0; } +void netfilter_lwtunnel_fini(void) {} #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 370f8231385c..769fd7680fac 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -395,7 +395,7 @@ static const struct seq_operations nflog_seq_ops = { #ifdef CONFIG_SYSCTL static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; -static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; +static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO]; static struct ctl_table_header *nf_log_sysctl_fhdr; static struct ctl_table nf_log_sysctl_ftable[] = { @@ -406,7 +406,6 @@ static struct ctl_table nf_log_sysctl_ftable[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static int nf_log_proc_dostring(struct ctl_table *table, int write, @@ -514,7 +513,7 @@ err_alloc: static void netfilter_log_sysctl_exit(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->nf.nf_log_dir_header->ctl_table_arg; unregister_net_sysctl_table(net->nf.nf_log_dir_header); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 167074283ea9..41d7faeb101c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3333,7 +3333,7 @@ err_expr_parse: return ERR_PTR(err); } -int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) +int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src, gfp_t gfp) { int err; @@ -3341,7 +3341,7 @@ int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src) return -EINVAL; dst->ops = src->ops; - err = src->ops->clone(dst, src); + err = src->ops->clone(dst, src, gfp); if (err < 0) return err; @@ -3823,6 +3823,15 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r nf_tables_rule_destroy(ctx, rule); } +/** nft_chain_validate - loop detection and hook validation + * + * @ctx: context containing call depth and base chain + * @chain: chain to validate + * + * Walk through the rules of the given chain and chase all jumps/gotos + * and set lookups until either the jump limit is hit or all reachable + * chains have been validated. + */ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) { struct nft_expr *expr, *last; @@ -3844,6 +3853,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (!expr->ops->validate) continue; + /* This may call nft_chain_validate() recursively, + * callers that do so must increment ctx->level. + */ err = expr->ops->validate(ctx, expr, &data); if (err < 0) return err; @@ -5740,8 +5752,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), - set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, - set->dlen) < 0) + nft_set_datatype(set), set->dlen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && @@ -6525,7 +6536,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, if (!expr) goto err_expr; - err = nft_expr_clone(expr, set->exprs[i]); + err = nft_expr_clone(expr, set->exprs[i], GFP_KERNEL_ACCOUNT); if (err < 0) { kfree(expr); goto err_expr; @@ -6564,7 +6575,7 @@ static int nft_set_elem_expr_setup(struct nft_ctx *ctx, for (i = 0; i < num_exprs; i++) { expr = nft_setelem_expr_at(elem_expr, elem_expr->size); - err = nft_expr_clone(expr, expr_array[i]); + err = nft_expr_clone(expr, expr_array[i], GFP_KERNEL_ACCOUNT); if (err < 0) goto err_elem_expr_setup; @@ -7776,6 +7787,9 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (WARN_ON_ONCE(!type)) return -ENOENT; + if (!obj->ops->update) + return 0; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); @@ -7963,6 +7977,19 @@ cont: return skb->len; } +static int nf_tables_dumpreset_obj(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_obj(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -7979,12 +8006,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb) if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - ctx->reset = true; - return 0; } +static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb) +{ + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_obj_start(cb); +} + static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -7995,8 +8028,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); @@ -8005,72 +8039,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; - bool reset = false; u32 objtype; int err; - if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start = nf_tables_dump_obj_start, - .dump = nf_tables_dump_obj, - .done = nf_tables_dump_obj_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) - return -EINVAL; + return ERR_PTR(-EINVAL); table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); - return PTR_ERR(obj); + return ERR_CAST(obj); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; + err = nf_tables_fill_obj_info(skb2, net, portid, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj, reset); + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } - if (reset) { - const struct nftables_pernet *nft_net; - char *buf; + return skb2; +} - nft_net = nft_pernet(net); - buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + u32 portid = NETLINK_CB(skb).portid; + struct sk_buff *skb2; - audit_log_nfcfg(buf, - family, - 1, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, + .dump = nf_tables_dump_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj, reset); - if (err < 0) - goto err_fill_obj_info; + skb2 = nf_tables_getobj_single(portid, info, nla, false); + if (IS_ERR(skb2)) + return PTR_ERR(skb2); - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, info->net, portid); +} -err_fill_obj_info: - kfree_skb(skb2); - return err; +static int nf_tables_getobj_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dumpreset_obj_start, + .dump = nf_tables_dumpreset_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getobj_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_OBJ_TABLE]), + (char *)nla_data(nla[NFTA_OBJ_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); + + return nfnetlink_unicast(skb2, net, portid); } static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) @@ -9353,7 +9424,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, @@ -9467,9 +9538,10 @@ static void nft_obj_commit_update(struct nft_trans *trans) obj = nft_trans_obj(trans); newobj = nft_trans_obj_newobj(trans); - if (obj->ops->update) - obj->ops->update(obj, newobj); + if (WARN_ON_ONCE(!obj->ops->update)) + return; + obj->ops->update(obj, newobj); nft_obj_destroy(&trans->ctx, newobj); } @@ -10806,150 +10878,6 @@ int nft_chain_validate_hooks(const struct nft_chain *chain, } EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); -/* - * Loop detection - walk through the ruleset beginning at the destination chain - * of a new jump until either the source chain is reached (loop) or all - * reachable chains have been traversed. - * - * The loop check is performed whenever a new jump verdict is added to an - * expression or verdict map or a verdict map is bound to a new chain. - */ - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain); - -static int nft_check_loops(const struct nft_ctx *ctx, - const struct nft_set_ext *ext) -{ - const struct nft_data *data; - int ret; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - ret = nf_tables_check_loops(ctx, data->verdict.chain); - break; - default: - ret = 0; - break; - } - - return ret; -} - -static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_elem_priv *elem_priv) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); - - if (!nft_set_elem_active(ext, iter->genmask)) - return 0; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - return nft_check_loops(ctx, ext); -} - -static int nft_set_catchall_loops(const struct nft_ctx *ctx, - struct nft_set *set) -{ - u8 genmask = nft_genmask_next(ctx->net); - struct nft_set_elem_catchall *catchall; - struct nft_set_ext *ext; - int ret = 0; - - list_for_each_entry_rcu(catchall, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) - continue; - - ret = nft_check_loops(ctx, ext); - if (ret < 0) - return ret; - } - - return ret; -} - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain) -{ - const struct nft_rule *rule; - const struct nft_expr *expr, *last; - struct nft_set *set; - struct nft_set_binding *binding; - struct nft_set_iter iter; - - if (ctx->chain == chain) - return -ELOOP; - - if (fatal_signal_pending(current)) - return -EINTR; - - list_for_each_entry(rule, &chain->rules, list) { - nft_rule_for_each_expr(expr, last, rule) { - struct nft_immediate_expr *priv; - const struct nft_data *data; - int err; - - if (strcmp(expr->ops->type->name, "immediate")) - continue; - - priv = nft_expr_priv(expr); - if (priv->dreg != NFT_REG_VERDICT) - continue; - - data = &priv->data; - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - err = nf_tables_check_loops(ctx, - data->verdict.chain); - if (err < 0) - return err; - break; - default: - break; - } - } - } - - list_for_each_entry(set, &ctx->table->sets, list) { - if (!nft_is_active_next(ctx->net, set)) - continue; - if (!(set->flags & NFT_SET_MAP) || - set->dtype != NFT_DATA_VERDICT) - continue; - - list_for_each_entry(binding, &set->bindings, list) { - if (!(binding->flags & NFT_SET_MAP) || - binding->chain != chain) - continue; - - iter.genmask = nft_genmask_next(ctx->net); - iter.type = NFT_ITER_UPDATE; - iter.skip = 0; - iter.count = 0; - iter.err = 0; - iter.fn = nf_tables_loop_check_setelem; - - set->ops->walk(ctx, set, &iter); - if (!iter.err) - iter.err = nft_set_catchall_loops(ctx, set); - - if (iter.err < 0) - return iter.err; - } - } - - return 0; -} - /** * nft_parse_u32_check - fetch u32 attribute and check for maximum value * @@ -11062,13 +10990,16 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, if (data != NULL && (data->verdict.code == NFT_GOTO || data->verdict.code == NFT_JUMP)) { - err = nf_tables_check_loops(ctx, data->verdict.chain); + err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; } return 0; default: + if (type != NFT_DATA_VALUE) + return -EINVAL; + if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) @@ -11077,8 +11008,6 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, sizeof_field(struct nft_regs, data)) return -ERANGE; - if (data != NULL && type != NFT_DATA_VALUE) - return -EINVAL; return 0; } } @@ -11479,8 +11408,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nf_tables_destroy_list)) - nf_tables_trans_destroy_flush_work(); + nf_tables_trans_destroy_flush_work(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index c9fbe0f707b5..932b3ddb34f1 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -427,6 +427,11 @@ replay_abort: nfnl_unlock(subsys_id); + if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); + nfnl_err_add(&err_list, nlh, 0, &extack); + } + while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -573,6 +578,9 @@ done: } else if (err) { ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); + } else if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); + nfnl_err_add(&err_list, nlh, 0, &extack); } } else { enum nfnl_abort_action abort_action; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f1c31757e496..e0716da256bf 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -325,7 +325,7 @@ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) hooks = nf_hook_entries_head(net, pf, entry->state.hook); i = entry->hook_index; - if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { + if (!hooks || i >= hooks->num_hook_entries) { kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); nf_queue_entry_free(entry); return; @@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - const struct nf_conn *ct = (void *)skb_nfct(entry->skb); + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + unsigned long status; + unsigned int use; - if (ct && ((ct->status & flags) == IPS_DYING)) + if (!ct) + return false; + + status = READ_ONCE(ct->status); + if ((status & flags) == IPS_DYING) return true; + + if (status & IPS_CONFIRMED) + return false; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * We can't be solved with serialization here because one clone could + * have been queued for local delivery. + */ + use = refcount_read(&ct->ct_general.use); + if (likely(use == 1)) + return false; + + /* Can't decrement further? Exclusive ownership. */ + if (!refcount_dec_not_one(&ct->ct_general.use)) + return false; + + skb_set_nfct(entry->skb, 0); + /* No nf_ct_put(): we already decremented .use and it cannot + * drop down to 0. + */ + return true; #endif return false; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index d170758a1eb5..7010541fcca6 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -325,9 +325,6 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, struct nft_hook *hook, *found = NULL; int n = 0; - if (event != NETDEV_UNREGISTER) - return; - list_for_each_entry(hook, &basechain->hook_list, list) { if (hook->ops.dev == dev) found = hook; @@ -367,8 +364,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, .net = dev_net(dev), }; - if (event != NETDEV_UNREGISTER && - event != NETDEV_CHANGENAME) + if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(ctx.net); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index de9d1980df69..92b984fa8175 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -210,12 +210,12 @@ static void nft_connlimit_destroy(const struct nft_ctx *ctx, nft_connlimit_do_destroy(ctx, priv); } -static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp) { struct nft_connlimit *priv_dst = nft_expr_priv(dst); struct nft_connlimit *priv_src = nft_expr_priv(src); - priv_dst->list = kmalloc(sizeof(*priv_dst->list), GFP_ATOMIC); + priv_dst->list = kmalloc(sizeof(*priv_dst->list), gfp); if (!priv_dst->list) return -ENOMEM; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index dccc68a5135a..eab0dc66bee6 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv, struct nft_counter *total) { struct nft_counter *this_cpu; + seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); + myseq = this_cpu_ptr(&nft_counter_seq); + + write_seqcount_begin(myseq); this_cpu->packets -= total->packets; this_cpu->bytes -= total->bytes; + write_seqcount_end(myseq); local_bh_enable(); } @@ -226,7 +231,7 @@ static void nft_counter_destroy(const struct nft_ctx *ctx, nft_counter_do_destroy(priv); } -static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp) { struct nft_counter_percpu_priv *priv = nft_expr_priv(src); struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst); @@ -236,7 +241,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) nft_counter_fetch(priv, &total); - cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_ATOMIC); + cpu_stats = alloc_percpu_gfp(struct nft_counter, gfp); if (cpu_stats == NULL) return -ENOMEM; @@ -265,7 +270,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, struct nft_counter *this_cpu; seqcount_t *myseq; - preempt_disable(); + local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); myseq = this_cpu_ptr(&nft_counter_seq); @@ -273,7 +278,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, this_cpu->packets += stats->pkts; this_cpu->bytes += stats->bytes; write_seqcount_end(myseq); - preempt_enable(); + local_bh_enable(); } void nft_counter_init_seqcount(void) diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index c09dba57354c..b4ada3ab2167 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -35,7 +35,7 @@ static int nft_dynset_expr_setup(const struct nft_dynset *priv, for (i = 0; i < priv->num_exprs; i++) { expr = nft_setelem_expr_at(elem_expr, elem_expr->size); - if (nft_expr_clone(expr, priv->expr_array[i]) < 0) + if (nft_expr_clone(expr, priv->expr_array[i], GFP_ATOMIC) < 0) return -1; elem_expr->size += priv->expr_array[i]->ops->size; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 8e6d7eaf9dc8..de1b6066bfa8 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -102,12 +102,12 @@ static void nft_last_destroy(const struct nft_ctx *ctx, kfree(priv->last); } -static int nft_last_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_last_clone(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp) { struct nft_last_priv *priv_dst = nft_expr_priv(dst); struct nft_last_priv *priv_src = nft_expr_priv(src); - priv_dst->last = kzalloc(sizeof(*priv_dst->last), GFP_ATOMIC); + priv_dst->last = kzalloc(sizeof(*priv_dst->last), gfp); if (!priv_dst->last) return -ENOMEM; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index cefa25e0dbb0..21d26b79b460 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -150,7 +150,7 @@ static void nft_limit_destroy(const struct nft_ctx *ctx, } static int nft_limit_clone(struct nft_limit_priv *priv_dst, - const struct nft_limit_priv *priv_src) + const struct nft_limit_priv *priv_src, gfp_t gfp) { priv_dst->tokens_max = priv_src->tokens_max; priv_dst->rate = priv_src->rate; @@ -158,7 +158,7 @@ static int nft_limit_clone(struct nft_limit_priv *priv_dst, priv_dst->burst = priv_src->burst; priv_dst->invert = priv_src->invert; - priv_dst->limit = kmalloc(sizeof(*priv_dst->limit), GFP_ATOMIC); + priv_dst->limit = kmalloc(sizeof(*priv_dst->limit), gfp); if (!priv_dst->limit) return -ENOMEM; @@ -223,14 +223,15 @@ static void nft_limit_pkts_destroy(const struct nft_ctx *ctx, nft_limit_destroy(ctx, &priv->limit); } -static int nft_limit_pkts_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_limit_pkts_clone(struct nft_expr *dst, const struct nft_expr *src, + gfp_t gfp) { struct nft_limit_priv_pkts *priv_dst = nft_expr_priv(dst); struct nft_limit_priv_pkts *priv_src = nft_expr_priv(src); priv_dst->cost = priv_src->cost; - return nft_limit_clone(&priv_dst->limit, &priv_src->limit); + return nft_limit_clone(&priv_dst->limit, &priv_src->limit, gfp); } static struct nft_expr_type nft_limit_type; @@ -281,12 +282,13 @@ static void nft_limit_bytes_destroy(const struct nft_ctx *ctx, nft_limit_destroy(ctx, priv); } -static int nft_limit_bytes_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_limit_bytes_clone(struct nft_expr *dst, const struct nft_expr *src, + gfp_t gfp) { struct nft_limit_priv *priv_dst = nft_expr_priv(dst); struct nft_limit_priv *priv_src = nft_expr_priv(src); - return nft_limit_clone(priv_dst, priv_src); + return nft_limit_clone(priv_dst, priv_src, gfp); } static const struct nft_expr_ops nft_limit_bytes_ops = { diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b314ca728a29..f3080fa1b226 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -132,7 +132,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return -EINVAL; err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG], - &priv->dreg, NULL, set->dtype, + &priv->dreg, NULL, + nft_set_datatype(set), set->dlen); if (err < 0) return err; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 3ba12a7471b0..9b2d7463d3d3 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -233,7 +233,7 @@ static void nft_quota_destroy(const struct nft_ctx *ctx, return nft_quota_do_destroy(ctx, priv); } -static int nft_quota_clone(struct nft_expr *dst, const struct nft_expr *src) +static int nft_quota_clone(struct nft_expr *dst, const struct nft_expr *src, gfp_t gfp) { struct nft_quota *priv_dst = nft_expr_priv(dst); struct nft_quota *priv_src = nft_expr_priv(src); @@ -241,7 +241,7 @@ static int nft_quota_clone(struct nft_expr *dst, const struct nft_expr *src) priv_dst->quota = priv_src->quota; priv_dst->flags = priv_src->flags; - priv_dst->consumed = kmalloc(sizeof(*priv_dst->consumed), GFP_ATOMIC); + priv_dst->consumed = kmalloc(sizeof(*priv_dst->consumed), gfp); if (!priv_dst->consumed) return -ENOMEM; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 187138afac45..eb4c4a4ac7ac 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -434,7 +434,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, res_map = scratch->map + (map_index ? m->bsize_max : 0); fill_map = scratch->map + (map_index ? 0 : m->bsize_max); - memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); + pipapo_resmap_init(m, res_map); nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1; @@ -504,6 +504,7 @@ out: * pipapo_get() - Get matching element reference given key data * @net: Network namespace * @set: nftables API set representation + * @m: storage containing active/existing elements * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask * @tstamp: timestamp to check for expired elements @@ -517,17 +518,15 @@ out: */ static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, + const struct nft_pipapo_match *m, const u8 *data, u8 genmask, u64 tstamp, gfp_t gfp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); - struct nft_pipapo *priv = nft_set_priv(set); unsigned long *res_map, *fill_map = NULL; - const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; int i; - m = priv->clone; if (m->bsize_max == 0) return ret; @@ -543,7 +542,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; } - memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); + pipapo_resmap_init(m, res_map); nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1; @@ -612,9 +611,11 @@ static struct nft_elem_priv * nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m = rcu_dereference(priv->match); struct nft_pipapo_elem *e; - e = pipapo_get(net, set, (const u8 *)elem->key.val.data, + e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data, nft_genmask_cur(net), get_jiffies_64(), GFP_ATOMIC); if (IS_ERR(e)) @@ -1247,6 +1248,40 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, return 0; } +static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set) +{ +#ifdef CONFIG_PROVE_LOCKING + const struct net *net = read_pnet(&set->net); + + return lockdep_is_held(&nft_pernet(net)->commit_mutex); +#else + return true; +#endif +} + +static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old); + +/** + * pipapo_maybe_clone() - Build clone for pending data changes, if not existing + * @set: nftables API set representation + * + * Return: newly created or existing clone, if any. NULL on allocation failure + */ +static struct nft_pipapo_match *pipapo_maybe_clone(const struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_match *m; + + if (priv->clone) + return priv->clone; + + m = rcu_dereference_protected(priv->match, + nft_pipapo_transaction_mutex_held(set)); + priv->clone = pipapo_clone(m); + + return priv->clone; +} + /** * nft_pipapo_insert() - Validate and insert ranged elements * @net: Network namespace @@ -1263,8 +1298,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const u8 *start = (const u8 *)elem->key.val.data, *end; - struct nft_pipapo *priv = nft_set_priv(set); - struct nft_pipapo_match *m = priv->clone; + struct nft_pipapo_match *m = pipapo_maybe_clone(set); u8 genmask = nft_genmask_next(net); struct nft_pipapo_elem *e, *dup; u64 tstamp = nft_net_tstamp(net); @@ -1272,12 +1306,15 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, const u8 *start_p, *end_p; int i, bsize_max, err = 0; + if (!m) + return -ENOMEM; + if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) end = (const u8 *)nft_set_ext_key_end(ext)->data; else end = start; - dup = pipapo_get(net, set, start, genmask, tstamp, GFP_KERNEL); + dup = pipapo_get(net, set, m, start, genmask, tstamp, GFP_KERNEL); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1299,7 +1336,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp, + dup = pipapo_get(net, set, m, end, nft_genmask_next(net), tstamp, GFP_KERNEL); } @@ -1332,8 +1369,6 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, } /* Insert */ - priv->dirty = true; - bsize_max = m->bsize_max; nft_pipapo_for_each_field(f, i, m) { @@ -1384,7 +1419,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, * pipapo_clone() - Clone matching data to create new working copy * @old: Existing matching data * - * Return: copy of matching data passed as 'old', error pointer on failure + * Return: copy of matching data passed as 'old' or NULL. */ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) { @@ -1394,7 +1429,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL); if (!new) - return ERR_PTR(-ENOMEM); + return NULL; new->field_count = old->field_count; new->bsize_max = old->bsize_max; @@ -1466,7 +1501,7 @@ out_scratch: free_percpu(new->scratch); kfree(new); - return ERR_PTR(-ENOMEM); + return NULL; } /** @@ -1698,8 +1733,6 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) * NFT_SET_ELEM_DEAD_BIT. */ if (__nft_set_elem_expired(&e->ext, tstamp)) { - priv->dirty = true; - gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) return; @@ -1777,57 +1810,30 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) static void nft_pipapo_commit(struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); - struct nft_pipapo_match *new_clone, *old; - - if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) - pipapo_gc(set, priv->clone); + struct nft_pipapo_match *old; - if (!priv->dirty) + if (!priv->clone) return; - new_clone = pipapo_clone(priv->clone); - if (IS_ERR(new_clone)) - return; + if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) + pipapo_gc(set, priv->clone); - priv->dirty = false; + old = rcu_replace_pointer(priv->match, priv->clone, + nft_pipapo_transaction_mutex_held(set)); + priv->clone = NULL; - old = rcu_access_pointer(priv->match); - rcu_assign_pointer(priv->match, priv->clone); if (old) call_rcu(&old->rcu, pipapo_reclaim_match); - - priv->clone = new_clone; -} - -static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set) -{ -#ifdef CONFIG_PROVE_LOCKING - const struct net *net = read_pnet(&set->net); - - return lockdep_is_held(&nft_pernet(net)->commit_mutex); -#else - return true; -#endif } static void nft_pipapo_abort(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); - struct nft_pipapo_match *new_clone, *m; - - if (!priv->dirty) - return; - - m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set)); - new_clone = pipapo_clone(m); - if (IS_ERR(new_clone)) + if (!priv->clone) return; - - priv->dirty = false; - pipapo_free_match(priv->clone); - priv->clone = new_clone; + priv->clone = NULL; } /** @@ -1851,52 +1857,38 @@ static void nft_pipapo_activate(const struct net *net, } /** - * pipapo_deactivate() - Check that element is in set, mark as inactive + * nft_pipapo_deactivate() - Search for element and make it inactive * @net: Network namespace * @set: nftables API set representation - * @data: Input key data - * @ext: nftables API extension pointer, used to check for end element - * - * This is a convenience function that can be called from both - * nft_pipapo_deactivate() and nft_pipapo_flush(), as they are in fact the same - * operation. + * @elem: nftables API element representation containing key data * * Return: deactivated element if found, NULL otherwise. */ -static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, - const u8 *data, const struct nft_set_ext *ext) +static struct nft_elem_priv * +nft_pipapo_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { + struct nft_pipapo_match *m = pipapo_maybe_clone(set); struct nft_pipapo_elem *e; - e = pipapo_get(net, set, data, nft_genmask_next(net), - nft_net_tstamp(net), GFP_KERNEL); + /* removal must occur on priv->clone, if we are low on memory + * we have no choice and must fail the removal request. + */ + if (!m) + return NULL; + + e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data, + nft_genmask_next(net), nft_net_tstamp(net), GFP_KERNEL); if (IS_ERR(e)) return NULL; nft_set_elem_change_active(net, set, &e->ext); - return e; -} - -/** - * nft_pipapo_deactivate() - Call pipapo_deactivate() to make element inactive - * @net: Network namespace - * @set: nftables API set representation - * @elem: nftables API element representation containing key data - * - * Return: deactivated element if found, NULL otherwise. - */ -static struct nft_elem_priv * -nft_pipapo_deactivate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - - return pipapo_deactivate(net, set, (const u8 *)elem->key.val.data, ext); + return &e->priv; } /** - * nft_pipapo_flush() - Call pipapo_deactivate() to make element inactive + * nft_pipapo_flush() - make element inactive * @net: Network namespace * @set: nftables API set representation * @elem_priv: nftables API element representation containing key data @@ -2093,7 +2085,6 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); if (last && f->mt[rulemap[i].to].e == e) { - priv->dirty = true; pipapo_drop(m, rulemap); return; } @@ -2106,35 +2097,23 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, } /** - * nft_pipapo_walk() - Walk over elements + * nft_pipapo_do_walk() - Walk over elements in m * @ctx: nftables API context * @set: nftables API set representation + * @m: matching data pointing to key mapping array * @iter: Iterator * * As elements are referenced in the mapping array for the last field, directly * scan that array: there's no need to follow rule mappings from the first - * field. + * field. @m is protected either by RCU read lock or by transaction mutex. */ -static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_iter *iter) +static void nft_pipapo_do_walk(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_pipapo_match *m, + struct nft_set_iter *iter) { - struct nft_pipapo *priv = nft_set_priv(set); - const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; unsigned int i, r; - WARN_ON_ONCE(iter->type != NFT_ITER_READ && - iter->type != NFT_ITER_UPDATE); - - rcu_read_lock(); - if (iter->type == NFT_ITER_READ) - m = rcu_dereference(priv->match); - else - m = priv->clone; - - if (unlikely(!m)) - goto out; - for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) ; @@ -2151,14 +2130,49 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) - goto out; + return; cont: iter->count++; } +} -out: - rcu_read_unlock(); +/** + * nft_pipapo_walk() - Walk over elements + * @ctx: nftables API context + * @set: nftables API set representation + * @iter: Iterator + * + * Test if destructive action is needed or not, clone active backend if needed + * and call the real function to work on the data. + */ +static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, + struct nft_set_iter *iter) +{ + struct nft_pipapo *priv = nft_set_priv(set); + const struct nft_pipapo_match *m; + + switch (iter->type) { + case NFT_ITER_UPDATE: + m = pipapo_maybe_clone(set); + if (!m) { + iter->err = -ENOMEM; + return; + } + + nft_pipapo_do_walk(ctx, set, m, iter); + break; + case NFT_ITER_READ: + rcu_read_lock(); + m = rcu_dereference(priv->match); + nft_pipapo_do_walk(ctx, set, m, iter); + rcu_read_unlock(); + break; + default: + iter->err = -EINVAL; + WARN_ON_ONCE(1); + break; + } } /** @@ -2267,21 +2281,10 @@ static int nft_pipapo_init(const struct nft_set *set, f->mt = NULL; } - /* Create an initial clone of matching data for next insertion */ - priv->clone = pipapo_clone(m); - if (IS_ERR(priv->clone)) { - err = PTR_ERR(priv->clone); - goto out_free; - } - - priv->dirty = false; - rcu_assign_pointer(priv->match, m); return 0; -out_free: - free_percpu(m->scratch); out_scratch: kfree(m); @@ -2326,33 +2329,18 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; - int cpu; m = rcu_dereference_protected(priv->match, true); - if (m) { - rcu_barrier(); - - for_each_possible_cpu(cpu) - pipapo_free_scratch(m, cpu); - free_percpu(m->scratch); - pipapo_free_fields(m); - kfree(m); - priv->match = NULL; - } if (priv->clone) { - m = priv->clone; - - nft_set_pipapo_match_destroy(ctx, set, m); - - for_each_possible_cpu(cpu) - pipapo_free_scratch(priv->clone, cpu); - free_percpu(priv->clone->scratch); - - pipapo_free_fields(priv->clone); - kfree(priv->clone); + nft_set_pipapo_match_destroy(ctx, set, priv->clone); + pipapo_free_match(priv->clone); priv->clone = NULL; + } else { + nft_set_pipapo_match_destroy(ctx, set, m); } + + pipapo_free_match(m); } /** diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 24cd1ff73f98..4a2ff85ce1c4 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -155,14 +155,12 @@ struct nft_pipapo_match { * @match: Currently in-use matching data * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding - * @dirty: Working copy has pending insertions or deletions * @last_gc: Timestamp of last garbage collection run, jiffies */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; - bool dirty; unsigned long last_gc; }; @@ -280,4 +278,25 @@ static u64 pipapo_estimate_size(const struct nft_set_desc *desc) return size; } +/** + * pipapo_resmap_init() - Initialise result map before first use + * @m: Matching data, including mapping table + * @res_map: Result map + * + * Initialize all bits covered by the first field to one, so that after + * the first step, only the matching bits of the first bit group remain. + * + * If other fields have a large bitmap, set remainder of res_map to 0. + */ +static inline void pipapo_resmap_init(const struct nft_pipapo_match *m, unsigned long *res_map) +{ + const struct nft_pipapo_field *f = m->f; + int i; + + for (i = 0; i < f->bsize; i++) + res_map[i] = ULONG_MAX; + + for (i = f->bsize; i < m->bsize_max; i++) + res_map[i] = 0ul; +} #endif /* _NFT_SET_PIPAPO_H */ diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index d08407d589ea..b8d3c3213efe 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1036,6 +1036,7 @@ nothing: /** * nft_pipapo_avx2_lookup_slow() - Fallback function for uncommon field sizes + * @mdata: Matching data, including mapping table * @map: Previous match result, used as initial bitmap * @fill: Destination bitmap to be filled with current match result * @f: Field, containing lookup and mapping tables @@ -1051,7 +1052,8 @@ nothing: * Return: -1 on no match, rule index of match if @last, otherwise first long * word index to be checked next (i.e. first filled word). */ -static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill, +static int nft_pipapo_avx2_lookup_slow(const struct nft_pipapo_match *mdata, + unsigned long *map, unsigned long *fill, const struct nft_pipapo_field *f, int offset, const u8 *pkt, bool first, bool last) @@ -1060,7 +1062,7 @@ static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill, int i, ret = -1, b; if (first) - memset(map, 0xff, bsize * sizeof(*map)); + pipapo_resmap_init(mdata, map); for (i = offset; i < bsize; i++) { if (f->bb == 8) @@ -1137,8 +1139,14 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, bool map_index; int i, ret = 0; - if (unlikely(!irq_fpu_usable())) - return nft_pipapo_lookup(net, set, key, ext); + local_bh_disable(); + + if (unlikely(!irq_fpu_usable())) { + bool fallback_res = nft_pipapo_lookup(net, set, key, ext); + + local_bh_enable(); + return fallback_res; + } m = rcu_dereference(priv->match); @@ -1153,6 +1161,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); + local_bh_enable(); return false; } @@ -1186,7 +1195,7 @@ next_match: } else if (f->groups == 16) { NFT_SET_PIPAPO_AVX2_LOOKUP(8, 16); } else { - ret = nft_pipapo_avx2_lookup_slow(res, fill, f, + ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f, ret, rp, first, last); } @@ -1202,7 +1211,7 @@ next_match: } else if (f->groups == 32) { NFT_SET_PIPAPO_AVX2_LOOKUP(4, 32); } else { - ret = nft_pipapo_avx2_lookup_slow(res, fill, f, + ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f, ret, rp, first, last); } @@ -1233,6 +1242,7 @@ out: if (i % 2) scratch->map_index = !map_index; kernel_fpu_end(); + local_bh_enable(); return ret >= 0; } diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index f735d79d8be5..60a76e6e348e 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -174,8 +174,8 @@ struct nft_tunnel_opts { struct erspan_metadata erspan; u8 data[IP_TUNNEL_OPTS_MAX]; } u; + IP_TUNNEL_DECLARE_FLAGS(flags); u32 len; - __be16 flags; }; struct nft_tunnel_obj { @@ -271,7 +271,8 @@ static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, opts->u.vxlan.gbp = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_VXLAN_GBP])); opts->len = sizeof(struct vxlan_metadata); - opts->flags = TUNNEL_VXLAN_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, opts->flags); return 0; } @@ -325,7 +326,8 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, opts->u.erspan.version = version; opts->len = sizeof(struct erspan_metadata); - opts->flags = TUNNEL_ERSPAN_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, opts->flags); return 0; } @@ -366,7 +368,8 @@ static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, opt->length = data_len / 4; opt->opt_class = nla_get_be16(tb[NFTA_TUNNEL_KEY_GENEVE_CLASS]); opt->type = nla_get_u8(tb[NFTA_TUNNEL_KEY_GENEVE_TYPE]); - opts->flags = TUNNEL_GENEVE_OPT; + ip_tunnel_flags_zero(opts->flags); + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, opts->flags); return 0; } @@ -385,8 +388,8 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, struct nft_tunnel_opts *opts) { struct nlattr *nla; - __be16 type = 0; int err, rem; + u32 type = 0; err = nla_validate_nested_deprecated(attr, NFTA_TUNNEL_KEY_OPTS_MAX, nft_tunnel_opts_policy, NULL); @@ -401,7 +404,7 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, err = nft_tunnel_obj_vxlan_init(nla, opts); if (err) return err; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case NFTA_TUNNEL_KEY_OPTS_ERSPAN: if (type) @@ -409,15 +412,15 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx, err = nft_tunnel_obj_erspan_init(nla, opts); if (err) return err; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; case NFTA_TUNNEL_KEY_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; err = nft_tunnel_obj_geneve_init(nla, opts); if (err) return err; - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; default: return -EOPNOTSUPP; @@ -454,7 +457,9 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, memset(&info, 0, sizeof(info)); info.mode = IP_TUNNEL_INFO_TX; info.key.tun_id = key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID])); - info.key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; + __set_bit(IP_TUNNEL_KEY_BIT, info.key.tun_flags); + __set_bit(IP_TUNNEL_CSUM_BIT, info.key.tun_flags); + __set_bit(IP_TUNNEL_NOCACHE_BIT, info.key.tun_flags); if (tb[NFTA_TUNNEL_KEY_IP]) { err = nft_tunnel_obj_ip_init(ctx, tb[NFTA_TUNNEL_KEY_IP], &info); @@ -483,11 +488,12 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; if (tun_flags & NFT_TUNNEL_F_ZERO_CSUM_TX) - info.key.tun_flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, info.key.tun_flags); if (tun_flags & NFT_TUNNEL_F_DONT_FRAGMENT) - info.key.tun_flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, + info.key.tun_flags); if (tun_flags & NFT_TUNNEL_F_SEQ_NUMBER) - info.key.tun_flags |= TUNNEL_SEQ; + __set_bit(IP_TUNNEL_SEQ_BIT, info.key.tun_flags); } if (tb[NFTA_TUNNEL_KEY_TOS]) info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]); @@ -583,7 +589,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, if (!nest) return -1; - if (opts->flags & TUNNEL_VXLAN_OPT) { + if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, opts->flags)) { inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_VXLAN); if (!inner) goto failure; @@ -591,7 +597,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, htonl(opts->u.vxlan.gbp))) goto inner_failure; nla_nest_end(skb, inner); - } else if (opts->flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, opts->flags)) { inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_ERSPAN); if (!inner) goto failure; @@ -613,7 +619,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, break; } nla_nest_end(skb, inner); - } else if (opts->flags & TUNNEL_GENEVE_OPT) { + } else if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, opts->flags)) { struct geneve_opt *opt; int offset = 0; @@ -658,11 +664,11 @@ static int nft_tunnel_flags_dump(struct sk_buff *skb, { u32 flags = 0; - if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_DONT_FRAGMENT; - if (!(info->key.tun_flags & TUNNEL_CSUM)) + if (!test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_ZERO_CSUM_TX; - if (info->key.tun_flags & TUNNEL_SEQ) + if (test_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags)) flags |= NFT_TUNNEL_F_SEQ_NUMBER; if (nla_put_be32(skb, NFTA_TUNNEL_KEY_FLAGS, htonl(flags)) < 0) diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 1ba4f58e1d35..cd9160bbc919 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -965,6 +965,7 @@ int netlbl_enabled(void) * @sk: the socket to label * @family: protocol family * @secattr: the security attributes + * @sk_locked: true if caller holds the socket lock * * Description: * Attach the correct label to the given socket using the security attributes @@ -977,7 +978,8 @@ int netlbl_enabled(void) */ int netlbl_sock_setattr(struct sock *sk, u16 family, - const struct netlbl_lsm_secattr *secattr) + const struct netlbl_lsm_secattr *secattr, + bool sk_locked) { int ret_val; struct netlbl_dom_map *dom_entry; @@ -997,7 +999,7 @@ int netlbl_sock_setattr(struct sock *sk, case NETLBL_NLTYPE_CIPSOV4: ret_val = cipso_v4_sock_setattr(sk, dom_entry->def.cipso, - secattr); + secattr, sk_locked); break; case NETLBL_NLTYPE_UNLABELED: ret_val = 0; @@ -1091,6 +1093,28 @@ int netlbl_sock_getattr(struct sock *sk, } /** + * netlbl_sk_lock_check - Check if the socket lock has been acquired. + * @sk: the socket to be checked + * + * Return: true if socket @sk is locked or if lock debugging is disabled at + * runtime or compile-time; false otherwise + * + */ +#ifdef CONFIG_LOCKDEP +bool netlbl_sk_lock_check(struct sock *sk) +{ + if (debug_locks) + return lockdep_sock_is_held(sk); + return true; +} +#else +bool netlbl_sk_lock_check(struct sock *sk) +{ + return true; +} +#endif + +/** * netlbl_conn_setattr - Label a connected socket using the correct protocol * @sk: the socket to label * @addr: the destination address @@ -1126,7 +1150,8 @@ int netlbl_conn_setattr(struct sock *sk, switch (entry->type) { case NETLBL_NLTYPE_CIPSOV4: ret_val = cipso_v4_sock_setattr(sk, - entry->cipso, secattr); + entry->cipso, secattr, + netlbl_sk_lock_check(sk)); break; case NETLBL_NLTYPE_UNLABELED: /* just delete the protocols we support for right now diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7554803218a2..fa9c090cf629 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -59,7 +59,6 @@ #include <linux/rhashtable.h> #include <asm/cacheflush.h> #include <linux/hash.h> -#include <linux/genetlink.h> #include <linux/net_namespace.h> #include <linux/nospec.h> #include <linux/btf_ids.h> @@ -73,6 +72,7 @@ #include <trace/events/netlink.h> #include "af_netlink.h" +#include "genetlink.h" struct listeners { struct rcu_head rcu; @@ -2165,6 +2165,69 @@ __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int fla } EXPORT_SYMBOL(__nlmsg_put); +static size_t +netlink_ack_tlv_len(struct netlink_sock *nlk, int err, + const struct netlink_ext_ack *extack) +{ + size_t tlvlen; + + if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) + return 0; + + tlvlen = 0; + if (extack->_msg) + tlvlen += nla_total_size(strlen(extack->_msg) + 1); + if (extack->cookie_len) + tlvlen += nla_total_size(extack->cookie_len); + + /* Following attributes are only reported as error (not warning) */ + if (!err) + return tlvlen; + + if (extack->bad_attr) + tlvlen += nla_total_size(sizeof(u32)); + if (extack->policy) + tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); + if (extack->miss_type) + tlvlen += nla_total_size(sizeof(u32)); + if (extack->miss_nest) + tlvlen += nla_total_size(sizeof(u32)); + + return tlvlen; +} + +static void +netlink_ack_tlv_fill(struct sk_buff *in_skb, struct sk_buff *skb, + const struct nlmsghdr *nlh, int err, + const struct netlink_ext_ack *extack) +{ + if (extack->_msg) + WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); + if (extack->cookie_len) + WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, + extack->cookie_len, extack->cookie)); + + if (!err) + return; + + if (extack->bad_attr && + !WARN_ON((u8 *)extack->bad_attr < in_skb->data || + (u8 *)extack->bad_attr >= in_skb->data + in_skb->len)) + WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, + (u8 *)extack->bad_attr - (const u8 *)nlh)); + if (extack->policy) + netlink_policy_dump_write_attr(skb, extack->policy, + NLMSGERR_ATTR_POLICY); + if (extack->miss_type) + WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE, + extack->miss_type)); + if (extack->miss_nest && + !WARN_ON((u8 *)extack->miss_nest < in_skb->data || + (u8 *)extack->miss_nest > in_skb->data + in_skb->len)) + WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST, + (u8 *)extack->miss_nest - (const u8 *)nlh)); +} + /* * It looks a bit ugly. * It would be better to create kernel thread. @@ -2175,6 +2238,7 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, struct netlink_ext_ack *extack) { struct nlmsghdr *nlh; + size_t extack_len; nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), NLM_F_MULTI | cb->answer_flags); @@ -2184,10 +2248,14 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); - if (extack->_msg && test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) { + extack_len = netlink_ack_tlv_len(nlk, nlk->dump_done_errno, extack); + if (extack_len) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; - if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)) + if (skb_tailroom(skb) >= extack_len) { + netlink_ack_tlv_fill(cb->skb, skb, cb->nlh, + nlk->dump_done_errno, extack); nlmsg_end(skb, nlh); + } } return 0; @@ -2406,69 +2474,6 @@ error_free: } EXPORT_SYMBOL(__netlink_dump_start); -static size_t -netlink_ack_tlv_len(struct netlink_sock *nlk, int err, - const struct netlink_ext_ack *extack) -{ - size_t tlvlen; - - if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) - return 0; - - tlvlen = 0; - if (extack->_msg) - tlvlen += nla_total_size(strlen(extack->_msg) + 1); - if (extack->cookie_len) - tlvlen += nla_total_size(extack->cookie_len); - - /* Following attributes are only reported as error (not warning) */ - if (!err) - return tlvlen; - - if (extack->bad_attr) - tlvlen += nla_total_size(sizeof(u32)); - if (extack->policy) - tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); - if (extack->miss_type) - tlvlen += nla_total_size(sizeof(u32)); - if (extack->miss_nest) - tlvlen += nla_total_size(sizeof(u32)); - - return tlvlen; -} - -static void -netlink_ack_tlv_fill(struct sk_buff *in_skb, struct sk_buff *skb, - struct nlmsghdr *nlh, int err, - const struct netlink_ext_ack *extack) -{ - if (extack->_msg) - WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); - if (extack->cookie_len) - WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, - extack->cookie_len, extack->cookie)); - - if (!err) - return; - - if (extack->bad_attr && - !WARN_ON((u8 *)extack->bad_attr < in_skb->data || - (u8 *)extack->bad_attr >= in_skb->data + in_skb->len)) - WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, - (u8 *)extack->bad_attr - (u8 *)nlh)); - if (extack->policy) - netlink_policy_dump_write_attr(skb, extack->policy, - NLMSGERR_ATTR_POLICY); - if (extack->miss_type) - WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE, - extack->miss_type)); - if (extack->miss_nest && - !WARN_ON((u8 *)extack->miss_nest < in_skb->data || - (u8 *)extack->miss_nest > in_skb->data + in_skb->len)) - WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST, - (u8 *)extack->miss_nest - (u8 *)nlh)); -} - void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 3b7666944b11..feb54c63a116 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -22,6 +22,8 @@ #include <net/sock.h> #include <net/genetlink.h> +#include "genetlink.h" + static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); diff --git a/net/netlink/genetlink.h b/net/netlink/genetlink.h new file mode 100644 index 000000000000..89bd9d2631c3 --- /dev/null +++ b/net/netlink/genetlink.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_GENETLINK_H +#define __NET_GENETLINK_H + +#include <linux/wait.h> + +/* for synchronisation between af_netlink and genetlink */ +extern atomic_t genl_sk_destructing_cnt; +extern wait_queue_head_t genl_sk_destructing_waitq; + +#endif /* __LINUX_GENERIC_NETLINK_H */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 104a80b75477..6ee148f0e6d0 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -772,8 +772,8 @@ out_release: return err; } -static int nr_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int nr_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sk_buff *skb; struct sock *newsk; @@ -805,7 +805,7 @@ static int nr_accept(struct socket *sock, struct socket *newsock, int flags, if (skb) break; - if (flags & O_NONBLOCK) { + if (arg->flags & O_NONBLOCK) { err = -EWOULDBLOCK; break; } diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c index 79fb2d3f477b..7dc0fa628f2e 100644 --- a/net/netrom/sysctl_net_netrom.c +++ b/net/netrom/sysctl_net_netrom.c @@ -140,7 +140,6 @@ static struct ctl_table nr_table[] = { .extra1 = &min_reset, .extra2 = &max_reset }, - { } }; int __init nr_register_sysctl(void) diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index d5344563e525..57a2f97004e1 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -447,7 +447,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent, } static int llcp_sock_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *new_sk; @@ -463,7 +463,7 @@ static int llcp_sock_accept(struct socket *sock, struct socket *newsock, goto error; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); /* Wait for an incoming connection. */ add_wait_queue_exclusive(sk_sleep(sk), &wait); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index aa1dbf654c3e..dd2ce73a24fb 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -969,8 +969,7 @@ static int nfc_genl_dep_link_down(struct sk_buff *skb, struct genl_info *info) int rc; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || - !info->attrs[NFC_ATTR_TARGET_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); @@ -1018,8 +1017,7 @@ static int nfc_genl_llc_get_params(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg = NULL; u32 idx; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || - !info->attrs[NFC_ATTR_FIRMWARE_NAME]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 2928c142a2dd..3b980bf2770b 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -168,8 +168,13 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct) static void ovs_ct_get_labels(const struct nf_conn *ct, struct ovs_key_ct_labels *labels) { - struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; + struct nf_conn_labels *cl = NULL; + if (ct) { + if (ct->master && !nf_ct_is_confirmed(ct)) + ct = ct->master; + cl = nf_ct_labels_find(ct); + } if (cl) memcpy(labels, cl->bits, OVS_CT_LABELS_LEN); else diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 11c69415c605..78d9961fcd44 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -15,7 +15,6 @@ #include <linux/delay.h> #include <linux/time.h> #include <linux/etherdevice.h> -#include <linux/genetlink.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/mutex.h> @@ -2707,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = { }; static const char * const ovs_drop_reasons[] = { -#define S(x) (#x), +#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x), OVS_DROP_REASONS(S) #undef S }; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ebc5728aab4e..f224d9bcea5e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -152,6 +152,13 @@ static void update_range(struct sw_flow_match *match, sizeof((match)->key->field)); \ } while (0) +#define SW_FLOW_KEY_BITMAP_COPY(match, field, value_p, nbits, is_mask) ({ \ + update_range(match, offsetof(struct sw_flow_key, field), \ + bitmap_size(nbits), is_mask); \ + bitmap_copy(is_mask ? (match)->mask->key.field : (match)->key->field, \ + value_p, nbits); \ +}) + static bool match_validate(const struct sw_flow_match *match, u64 key_attrs, u64 mask_attrs, bool log) { @@ -670,8 +677,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, bool log) { bool ttl = false, ipv4 = false, ipv6 = false; + IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; bool info_bridge_mode = false; - __be16 tun_flags = 0; int opts_type = 0; struct nlattr *a; int rem; @@ -697,7 +704,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_ID: SW_FLOW_KEY_PUT(match, tun_key.tun_id, nla_get_be64(a), is_mask); - tun_flags |= TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, @@ -729,10 +736,10 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, ttl = true; break; case OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT: - tun_flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_CSUM: - tun_flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_TP_SRC: SW_FLOW_KEY_PUT(match, tun_key.tp_src, @@ -743,7 +750,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, nla_get_be16(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_OAM: - tun_flags |= TUNNEL_OAM; + __set_bit(IP_TUNNEL_OAM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: if (opts_type) { @@ -755,7 +762,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: @@ -768,7 +775,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_PAD: @@ -784,7 +791,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, if (err) return err; - tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE: @@ -798,7 +805,8 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, } } - SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask); + SW_FLOW_KEY_BITMAP_COPY(match, tun_key.tun_flags, tun_flags, + __IP_TUNNEL_FLAG_NUM, is_mask); if (is_mask) SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true); else @@ -823,13 +831,15 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, } if (ipv4) { if (info_bridge_mode) { + __clear_bit(IP_TUNNEL_KEY_BIT, tun_flags); + if (match->key->tun_key.u.ipv4.src || match->key->tun_key.u.ipv4.dst || match->key->tun_key.tp_src || match->key->tun_key.tp_dst || match->key->tun_key.ttl || match->key->tun_key.tos || - tun_flags & ~TUNNEL_KEY) { + !ip_tunnel_flags_empty(tun_flags)) { OVS_NLERR(log, "IPv4 tun info is not correct"); return -EINVAL; } @@ -874,7 +884,7 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, const void *tun_opts, int swkey_tun_opts_len, unsigned short tun_proto, u8 mode) { - if (output->tun_flags & TUNNEL_KEY && + if (test_bit(IP_TUNNEL_KEY_BIT, output->tun_flags) && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id, OVS_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; @@ -910,10 +920,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, return -EMSGSIZE; if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ttl)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) && + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_CSUM) && + if (test_bit(IP_TUNNEL_CSUM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) return -EMSGSIZE; if (output->tp_src && @@ -922,18 +932,20 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, if (output->tp_dst && nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst)) return -EMSGSIZE; - if ((output->tun_flags & TUNNEL_OAM) && + if (test_bit(IP_TUNNEL_OAM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; if (swkey_tun_opts_len) { - if (output->tun_flags & TUNNEL_GENEVE_OPT && + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_VXLAN_OPT && + else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, + output->tun_flags) && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_ERSPAN_OPT && + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; @@ -2029,7 +2041,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if ((swkey->tun_proto || is_mask)) { const void *opts = NULL; - if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) + if (ip_tunnel_is_options_present(output->tun_key.tun_flags)) opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); if (ip_tun_to_nlattr(skb, &output->tun_key, opts, @@ -2752,7 +2764,8 @@ static int validate_geneve_opts(struct sw_flow_key *key) opts_len -= len; } - key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + if (crit_opt) + __set_bit(IP_TUNNEL_CRIT_OPT_BIT, key->tun_key.tun_flags); return 0; } @@ -2760,6 +2773,7 @@ static int validate_geneve_opts(struct sw_flow_key *key) static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_actions **sfa, bool log) { + IP_TUNNEL_DECLARE_FLAGS(dst_opt_type) = { }; struct sw_flow_match match; struct sw_flow_key key; struct metadata_dst *tun_dst; @@ -2767,9 +2781,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; - __be16 dst_opt_type; - dst_opt_type = 0; ovs_match_init(&match, &key, true, NULL); opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) @@ -2781,13 +2793,14 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, err = validate_geneve_opts(&key); if (err < 0) return err; - dst_opt_type = TUNNEL_GENEVE_OPT; + + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: - dst_opt_type = TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - dst_opt_type = TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, dst_opt_type); break; } } diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h index ed11cd12b512..8bbf983cd244 100644 --- a/net/openvswitch/meter.h +++ b/net/openvswitch/meter.h @@ -11,7 +11,6 @@ #include <linux/kernel.h> #include <linux/netlink.h> #include <linux/openvswitch.h> -#include <linux/genetlink.h> #include <linux/skbuff.h> #include <linux/bits.h> diff --git a/net/openvswitch/openvswitch_trace.h b/net/openvswitch/openvswitch_trace.h index 3eb35d9eb700..74d75aaebef4 100644 --- a/net/openvswitch/openvswitch_trace.h +++ b/net/openvswitch/openvswitch_trace.h @@ -43,8 +43,8 @@ TRACE_EVENT(ovs_do_execute_action, TP_fast_assign( __entry->dpaddr = dp; - __assign_str(dp_name, ovs_dp_name(dp)); - __assign_str(dev_name, skb->dev->name); + __assign_str(dp_name); + __assign_str(dev_name); __entry->skbaddr = skb; __entry->len = skb->len; __entry->data_len = skb->data_len; @@ -113,8 +113,8 @@ TRACE_EVENT(ovs_dp_upcall, TP_fast_assign( __entry->dpaddr = dp; - __assign_str(dp_name, ovs_dp_name(dp)); - __assign_str(dev_name, skb->dev->name); + __assign_str(dp_name); + __assign_str(dev_name); __entry->skbaddr = skb; __entry->len = skb->len; __entry->data_len = skb->data_len; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 903537a5da22..91a11067e458 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -82,6 +82,13 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name) err = -ENODEV; goto error_free_vport; } + /* Ensure that the device exists and that the provided + * name is not one of its aliases. + */ + if (strcmp(name, ovs_vport_name(vport))) { + err = -ENODEV; + goto error_put; + } netdev_tracker_alloc(vport->dev, &vport->dev_tracker, GFP_KERNEL); if (vport->dev->flags & IFF_LOOPBACK || (vport->dev->type != ARPHRD_ETHER && diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ea3ebc160e25..4692a9ef110b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,6 +538,61 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } +static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +{ + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + struct vlan_hdr vhdr, *vh; + unsigned int header_len; + + if (!dev) + return 0; + + /* In the SOCK_DGRAM scenario, skb data starts at the network + * protocol, which is after the VLAN headers. The outer VLAN + * header is at the hard_header_len offset in non-variable + * length link layer headers. If it's a VLAN device, the + * min_header_len should be used to exclude the VLAN header + * size. + */ + if (dev->min_header_len == dev->hard_header_len) + header_len = dev->hard_header_len; + else if (is_vlan_dev(dev)) + header_len = dev->min_header_len; + else + return 0; + + skb_push(skb, skb->data - skb_mac_header(skb)); + vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + if (unlikely(!vh)) + return 0; + + return ntohs(vh->h_vlan_TCI); +} + +static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +{ + __be16 proto = skb->protocol; + + if (unlikely(eth_type_vlan(proto))) { + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + + skb_push(skb, skb->data - skb_mac_header(skb)); + proto = __vlan_get_protocol(skb, proto, NULL); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + } + + return proto; +} + static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); @@ -1007,10 +1062,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { + struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); + if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { + ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); + ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); + ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; @@ -2428,6 +2489,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); + h.h2->tp_vlan_tpid = ntohs(skb->protocol); + status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; @@ -2457,7 +2522,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; @@ -3482,7 +3548,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sock->type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); @@ -3539,6 +3606,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); + if (dev) { + aux.tp_vlan_tci = vlan_get_tci(skb, dev); + aux.tp_vlan_tpid = ntohs(skb->protocol); + aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else { + aux.tp_vlan_tci = 0; + aux.tp_vlan_tpid = 0; + } + rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 3dd5f52bc1b5..53a858478e22 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -759,8 +759,8 @@ static void pep_sock_close(struct sock *sk, long timeout) sock_put(sk); } -static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, - bool kern) +static struct sock *pep_sock_accept(struct sock *sk, + struct proto_accept_arg *arg) { struct pep_sock *pn = pep_sk(sk), *newpn; struct sock *newsk = NULL; @@ -772,8 +772,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, u8 pipe_handle, enabled, n_sb; u8 aligned = 0; - skb = skb_recv_datagram(sk, (flags & O_NONBLOCK) ? MSG_DONTWAIT : 0, - errp); + skb = skb_recv_datagram(sk, (arg->flags & O_NONBLOCK) ? MSG_DONTWAIT : 0, + &arg->err); if (!skb) return NULL; @@ -836,7 +836,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, /* Create a new to-be-accepted sock */ newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, - kern); + arg->kern); if (!newsk) { pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL); err = -ENOBUFS; @@ -878,7 +878,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, drop: release_sock(sk); kfree_skb(skb); - *errp = err; + arg->err = err; return newsk; } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index dd4c7e9a634f..7008d402499d 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -178,7 +178,7 @@ static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst, rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; if (nla_put_u8(skb, RTA_DST, dst) || - nla_put_u32(skb, RTA_OIF, dev->ifindex)) + nla_put_u32(skb, RTA_OIF, READ_ONCE(dev->ifindex))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -263,6 +263,7 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh, static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + int err = 0; u8 addr; rcu_read_lock(); @@ -272,16 +273,16 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (!dev) continue; - if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWROUTE) < 0) - goto out; + err = fill_route(skb, dev, addr << 2, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE); + if (err < 0) + break; } - -out: rcu_read_unlock(); cb->args[0] = addr; - return skb->len; + return err; } int __init phonet_netlink_register(void) @@ -301,6 +302,6 @@ int __init phonet_netlink_register(void) rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_DELROUTE, route_doit, NULL, 0); rtnl_register_module(THIS_MODULE, PF_PHONET, RTM_GETROUTE, - NULL, route_dumpit, 0); + NULL, route_dumpit, RTNL_FLAG_DUMP_UNLOCKED); return 0; } diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 1018340d89a7..5ce0b3ee5def 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -292,18 +292,17 @@ out: } static int pn_socket_accept(struct socket *sock, struct socket *newsock, - int flags, bool kern) + struct proto_accept_arg *arg) { struct sock *sk = sock->sk; struct sock *newsk; - int err; if (unlikely(sk->sk_state != TCP_LISTEN)) return -EINVAL; - newsk = sk->sk_prot->accept(sk, flags, &err, kern); + newsk = sk->sk_prot->accept(sk, arg); if (!newsk) - return err; + return arg->err; lock_sock(newsk); sock_graft(newsk, newsock); diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index 0d0bf41381c2..82fc22467a09 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -81,7 +81,6 @@ static struct ctl_table phonet_table[] = { .mode = 0644, .proc_handler = proc_local_port_range, }, - { } }; int __init phonet_sysctl_init(void) diff --git a/net/psample/psample.c b/net/psample/psample.c index ddd211a151d0..a5d9b8446f77 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -221,7 +221,7 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, const struct ip_tunnel_key *tun_key = &tun_info->key; int tun_opts_len = tun_info->options_len; - if (tun_key->tun_flags & TUNNEL_KEY && + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags) && nla_put_be64(skb, PSAMPLE_TUNNEL_KEY_ATTR_ID, tun_key->tun_id, PSAMPLE_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; @@ -257,10 +257,10 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, return -EMSGSIZE; if (nla_put_u8(skb, PSAMPLE_TUNNEL_KEY_ATTR_TTL, tun_key->ttl)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) && + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_CSUM) && + if (test_bit(IP_TUNNEL_CSUM_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_CSUM)) return -EMSGSIZE; if (tun_key->tp_src && @@ -269,15 +269,16 @@ static int __psample_ip_tun_to_nlattr(struct sk_buff *skb, if (tun_key->tp_dst && nla_put_be16(skb, PSAMPLE_TUNNEL_KEY_ATTR_TP_DST, tun_key->tp_dst)) return -EMSGSIZE; - if ((tun_key->tun_flags & TUNNEL_OAM) && + if (test_bit(IP_TUNNEL_OAM_BIT, tun_key->tun_flags) && nla_put_flag(skb, PSAMPLE_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; if (tun_opts_len) { - if (tun_key->tun_flags & TUNNEL_GENEVE_OPT && + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_key->tun_flags) && nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_GENEVE_OPTS, tun_opts_len, tun_opts)) return -EMSGSIZE; - else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT && + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_key->tun_flags) && nla_put(skb, PSAMPLE_TUNNEL_KEY_ATTR_ERSPAN_OPTS, tun_opts_len, tun_opts)) return -EMSGSIZE; @@ -314,7 +315,7 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) int tun_opts_len = tun_info->options_len; int sum = nla_total_size(0); /* PSAMPLE_ATTR_TUNNEL */ - if (tun_key->tun_flags & TUNNEL_KEY) + if (test_bit(IP_TUNNEL_KEY_BIT, tun_key->tun_flags)) sum += nla_total_size_64bit(sizeof(u64)); if (tun_info->mode & IP_TUNNEL_INFO_BRIDGE) @@ -337,20 +338,21 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) if (tun_key->tos) sum += nla_total_size(sizeof(u8)); sum += nla_total_size(sizeof(u8)); /* TTL */ - if (tun_key->tun_flags & TUNNEL_DONT_FRAGMENT) + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_key->tun_flags)) sum += nla_total_size(0); - if (tun_key->tun_flags & TUNNEL_CSUM) + if (test_bit(IP_TUNNEL_CSUM_BIT, tun_key->tun_flags)) sum += nla_total_size(0); if (tun_key->tp_src) sum += nla_total_size(sizeof(u16)); if (tun_key->tp_dst) sum += nla_total_size(sizeof(u16)); - if (tun_key->tun_flags & TUNNEL_OAM) + if (test_bit(IP_TUNNEL_OAM_BIT, tun_key->tun_flags)) sum += nla_total_size(0); if (tun_opts_len) { - if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_key->tun_flags)) sum += nla_total_size(tun_opts_len); - else if (tun_key->tun_flags & TUNNEL_ERSPAN_OPT) + else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, + tun_key->tun_flags)) sum += nla_total_size(tun_opts_len); } diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index 9ced13c0627a..69f53625a049 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -118,6 +118,51 @@ static const struct mhi_device_id qcom_mhi_qrtr_id_table[] = { }; MODULE_DEVICE_TABLE(mhi, qcom_mhi_qrtr_id_table); +static int __maybe_unused qcom_mhi_qrtr_pm_suspend_late(struct device *dev) +{ + struct mhi_device *mhi_dev = container_of(dev, struct mhi_device, dev); + enum mhi_state state; + + state = mhi_get_mhi_state(mhi_dev->mhi_cntrl); + /* + * If the device is in suspend state, then no need for the + * client driver to unprepare the channels. + */ + if (state == MHI_STATE_M3) + return 0; + + mhi_unprepare_from_transfer(mhi_dev); + + return 0; +} + +static int __maybe_unused qcom_mhi_qrtr_pm_resume_early(struct device *dev) +{ + struct mhi_device *mhi_dev = container_of(dev, struct mhi_device, dev); + enum mhi_state state; + int rc; + + state = mhi_get_mhi_state(mhi_dev->mhi_cntrl); + /* + * If the device is in suspend state, we won't unprepare channels + * in suspend callback, therefore no need to prepare channels when + * resume. + */ + if (state == MHI_STATE_M3) + return 0; + + rc = mhi_prepare_for_transfer_autoqueue(mhi_dev); + if (rc) + dev_err(dev, "failed to prepare for autoqueue transfer %d\n", rc); + + return rc; +} + +static const struct dev_pm_ops qcom_mhi_qrtr_pm_ops = { + SET_LATE_SYSTEM_SLEEP_PM_OPS(qcom_mhi_qrtr_pm_suspend_late, + qcom_mhi_qrtr_pm_resume_early) +}; + static struct mhi_driver qcom_mhi_qrtr_driver = { .probe = qcom_mhi_qrtr_probe, .remove = qcom_mhi_qrtr_remove, @@ -126,6 +171,7 @@ static struct mhi_driver qcom_mhi_qrtr_driver = { .id_table = qcom_mhi_qrtr_id_table, .driver = { .name = "qcom_mhi_qrtr", + .pm = &qcom_mhi_qrtr_pm_ops, }, }; diff --git a/net/rds/ib_sysctl.c b/net/rds/ib_sysctl.c index e4e41b3afce7..2af678e71e3c 100644 --- a/net/rds/ib_sysctl.c +++ b/net/rds/ib_sysctl.c @@ -103,7 +103,6 @@ static struct ctl_table rds_ib_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; void rds_ib_sysctl_exit(void) diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c index e381bbcd9cc1..025f518a4349 100644 --- a/net/rds/sysctl.c +++ b/net/rds/sysctl.c @@ -89,7 +89,6 @@ static struct ctl_table rds_sysctl_rds_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; void rds_sysctl_exit(void) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 2dba7505b414..d8111ac83bb6 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -86,7 +86,6 @@ static struct ctl_table rds_tcp_sysctl_table[] = { .proc_handler = rds_tcp_skbuf_handler, .extra1 = &rds_tcp_min_rcvbuf, }, - { } }; u32 rds_tcp_write_seq(struct rds_tcp_connection *tc) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 05008ce5c421..d89bd8d0c354 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -105,6 +105,10 @@ int rds_tcp_accept_one(struct socket *sock) int conn_state; struct rds_conn_path *cp; struct in6_addr *my_addr, *peer_addr; + struct proto_accept_arg arg = { + .flags = O_NONBLOCK, + .kern = true, + }; #if !IS_ENABLED(CONFIG_IPV6) struct in6_addr saddr, daddr; #endif @@ -119,7 +123,7 @@ int rds_tcp_accept_one(struct socket *sock) if (ret) goto out; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); + ret = sock->ops->accept(sock, new_sock, &arg); if (ret < 0) goto out; diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 4e32d659524e..84529886c2e6 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -156,14 +156,12 @@ err_destroy: return ret; } -static int rfkill_gpio_remove(struct platform_device *pdev) +static void rfkill_gpio_remove(struct platform_device *pdev) { struct rfkill_gpio_data *rfkill = platform_get_drvdata(pdev); rfkill_unregister(rfkill->rfkill_dev); rfkill_destroy(rfkill->rfkill_dev); - - return 0; } #ifdef CONFIG_ACPI @@ -183,7 +181,7 @@ MODULE_DEVICE_TABLE(of, rfkill_of_match); static struct platform_driver rfkill_gpio_driver = { .probe = rfkill_gpio_probe, - .remove = rfkill_gpio_remove, + .remove_new = rfkill_gpio_remove, .driver = { .name = "rfkill_gpio", .acpi_match_table = ACPI_PTR(rfkill_acpi_match), diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index ef81d019b20f..59050caab65c 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -919,8 +919,8 @@ out_release: return err; } -static int rose_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int rose_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sk_buff *skb; struct sock *newsk; @@ -953,7 +953,7 @@ static int rose_accept(struct socket *sock, struct socket *newsock, int flags, if (skb) break; - if (flags & O_NONBLOCK) { + if (arg->flags & O_NONBLOCK) { err = -EWOULDBLOCK; break; } diff --git a/net/rose/sysctl_net_rose.c b/net/rose/sysctl_net_rose.c index d391d7758f52..d801315b7083 100644 --- a/net/rose/sysctl_net_rose.c +++ b/net/rose/sysctl_net_rose.c @@ -112,7 +112,6 @@ static struct ctl_table rose_table[] = { .extra1 = &min_window, .extra2 = &max_window }, - { } }; void __init rose_register_sysctl(void) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 5222bc97d192..f4844683e120 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -65,7 +65,7 @@ static void rxrpc_write_space(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible(&wq->wait); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index c9bedd0e2d86..9bf9a1f6e4cb 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -127,7 +127,6 @@ static struct ctl_table rxrpc_sysctl_table[] = { .extra1 = (void *)SYSCTL_ONE, .extra2 = (void *)&four, }, - { } }; int __init rxrpc_sysctl_init(void) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 2a96d9c1db65..9d451d77d54e 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -44,6 +44,8 @@ static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; + /* Note : pad[] must be the last field. */ + u8 pad[]; }; struct tcf_ct_flow_table { @@ -60,7 +62,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = sizeof_field(struct tcf_ct_flow_table, key), + .key_len = offsetof(struct zones_ht_key, pad), .automatic_shrinking = true, }; @@ -1077,6 +1079,14 @@ do_nat: */ if (nf_conntrack_confirm(skb) != NF_ACCEPT) goto drop; + + /* The ct may be dropped if a clash has been resolved, + * so it's necessary to retrieve it from skb again to + * prevent UAF. + */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + skip_add = true; } if (!skip_add) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 1536f8b16f1b..af7c99845948 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -230,7 +230,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, nla_for_each_attr(attr, head, len, rem) { switch (nla_type(attr)) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: - if (type && type != TUNNEL_GENEVE_OPT) { + if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } @@ -247,7 +247,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, dst_len -= opt_len; dst += opt_len; } - type = TUNNEL_GENEVE_OPT; + type = IP_TUNNEL_GENEVE_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: if (type) { @@ -259,7 +259,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_VXLAN_OPT; + type = IP_TUNNEL_VXLAN_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: if (type) { @@ -271,7 +271,7 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; - type = TUNNEL_ERSPAN_OPT; + type = IP_TUNNEL_ERSPAN_OPT_BIT; break; } } @@ -302,7 +302,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, switch (nla_type(nla_data(nla))) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_GENEVE_OPT; + __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -310,7 +310,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, #endif case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_VXLAN_OPT; + __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -318,7 +318,7 @@ static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, #endif case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: #if IS_ENABLED(CONFIG_INET) - info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else @@ -363,6 +363,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; struct tcf_tunnel_key_params *params_new; + IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *metadata = NULL; struct tcf_chain *goto_ch = NULL; struct tc_tunnel_key *parm; @@ -371,7 +372,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, __be16 dst_port = 0; __be64 key_id = 0; int opts_len = 0; - __be16 flags = 0; u8 tos, ttl; int ret = 0; u32 index; @@ -412,16 +412,16 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]); key_id = key32_to_tunnel_id(key32); - flags = TUNNEL_KEY; + __set_bit(IP_TUNNEL_KEY_BIT, flags); } - flags |= TUNNEL_CSUM; + __set_bit(IP_TUNNEL_CSUM_BIT, flags); if (tb[TCA_TUNNEL_KEY_NO_CSUM] && nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) - flags &= ~TUNNEL_CSUM; + __clear_bit(IP_TUNNEL_CSUM_BIT, flags); if (nla_get_flag(tb[TCA_TUNNEL_KEY_NO_FRAG])) - flags |= TUNNEL_DONT_FRAGMENT; + __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, flags); if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); @@ -663,15 +663,15 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (!start) return -EMSGSIZE; - if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) goto err_out; - } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_vxlan_opts_dump(skb, info); if (err) goto err_out; - } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_erspan_opts_dump(skb, info); if (err) goto err_out; @@ -741,7 +741,7 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); - if (((key->tun_flags & TUNNEL_KEY) && + if ((test_bit(IP_TUNNEL_KEY_BIT, key->tun_flags) && nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || @@ -749,8 +749,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst)) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, - !(key->tun_flags & TUNNEL_CSUM)) || - ((key->tun_flags & TUNNEL_DONT_FRAGMENT) && + !test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) || + (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) && nla_put_flag(skb, TCA_TUNNEL_KEY_NO_FRAG)) || tunnel_key_opts_dump(skb, info)) goto nla_put_failure; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ca5676b2668e..17d97bbe890f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -410,12 +410,48 @@ static void tcf_proto_get(struct tcf_proto *tp) refcount_inc(&tp->refcnt); } +static void tcf_maintain_bypass(struct tcf_block *block) +{ + int filtercnt = atomic_read(&block->filtercnt); + int skipswcnt = atomic_read(&block->skipswcnt); + bool bypass_wanted = filtercnt > 0 && filtercnt == skipswcnt; + + if (bypass_wanted != block->bypass_wanted) { +#ifdef CONFIG_NET_CLS_ACT + if (bypass_wanted) + static_branch_inc(&tcf_bypass_check_needed_key); + else + static_branch_dec(&tcf_bypass_check_needed_key); +#endif + block->bypass_wanted = bypass_wanted; + } +} + +static void tcf_block_filter_cnt_update(struct tcf_block *block, bool *counted, bool add) +{ + lockdep_assert_not_held(&block->cb_lock); + + down_write(&block->cb_lock); + if (*counted != add) { + if (add) { + atomic_inc(&block->filtercnt); + *counted = true; + } else { + atomic_dec(&block->filtercnt); + *counted = false; + } + } + tcf_maintain_bypass(block); + up_write(&block->cb_lock); +} + static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, bool sig_destroy, struct netlink_ext_ack *extack) { tp->ops->destroy(tp, rtnl_held, extack); + tcf_block_filter_cnt_update(tp->chain->block, &tp->counted, false); if (sig_destroy) tcf_proto_signal_destroyed(tp->chain, tp); tcf_chain_put(tp->chain); @@ -2367,6 +2403,7 @@ replay: tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false, rtnl_held, extack); tfilter_put(tp, fh); + tcf_block_filter_cnt_update(block, &tp->counted, true); /* q pointer is NULL for shared blocks */ if (q) q->flags &= ~TCQ_F_CAN_BYPASS; @@ -3483,6 +3520,8 @@ static void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) if (*flags & TCA_CLS_FLAGS_IN_HW) return; *flags |= TCA_CLS_FLAGS_IN_HW; + if (tc_skip_sw(*flags)) + atomic_inc(&block->skipswcnt); atomic_inc(&block->offloadcnt); } @@ -3491,6 +3530,8 @@ static void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) if (!(*flags & TCA_CLS_FLAGS_IN_HW)) return; *flags &= ~TCA_CLS_FLAGS_IN_HW; + if (tc_skip_sw(*flags)) + atomic_dec(&block->skipswcnt); atomic_dec(&block->offloadcnt); } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e1314674b4a9..fd9a6f20b60b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -28,6 +28,7 @@ #include <net/vxlan.h> #include <net/erspan.h> #include <net/gtp.h> +#include <net/pfcp.h> #include <net/tc_wrapper.h> #include <net/dst.h> @@ -741,6 +742,7 @@ enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_GTP] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_OPTS_PFCP] = { .type = NLA_NESTED }, }; static const struct nla_policy @@ -771,6 +773,12 @@ gtp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GTP_MAX + 1] = { }; static const struct nla_policy +pfcp_opt_policy[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1] = { + [TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE] = { .type = NLA_U8 }, + [TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID] = { .type = NLA_U64 }, +}; + +static const struct nla_policy mpls_stack_entry_policy[TCA_FLOWER_KEY_MPLS_OPT_LSE_MAX + 1] = { [TCA_FLOWER_KEY_MPLS_OPT_LSE_DEPTH] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_MPLS_OPT_LSE_TTL] = { .type = NLA_U8 }, @@ -1419,6 +1427,44 @@ static int fl_set_gtp_opt(const struct nlattr *nla, struct fl_flow_key *key, return sizeof(*sinfo); } +static int fl_set_pfcp_opt(const struct nlattr *nla, struct fl_flow_key *key, + int depth, int option_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX + 1]; + struct pfcp_metadata *md; + int err; + + md = (struct pfcp_metadata *)&key->enc_opts.data[key->enc_opts.len]; + memset(md, 0xff, sizeof(*md)); + + if (!depth) + return sizeof(*md); + + if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_PFCP) { + NL_SET_ERR_MSG_MOD(extack, "Non-pfcp option type for mask"); + return -EINVAL; + } + + err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_PFCP_MAX, nla, + pfcp_opt_policy, extack); + if (err < 0) + return err; + + if (!option_len && !tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing tunnel key pfcp option type"); + return -EINVAL; + } + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]) + md->type = nla_get_u8(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE]); + + if (tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]) + md->seid = nla_get_be64(tb[TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID]); + + return sizeof(*md); +} + static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct fl_flow_key *mask, struct netlink_ext_ack *extack) @@ -1454,12 +1500,13 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, switch (nla_type(nla_opt_key)) { case TCA_FLOWER_KEY_ENC_OPTS_GENEVE: if (key->enc_opts.dst_opt_type && - key->enc_opts.dst_opt_type != TUNNEL_GENEVE_OPT) { + key->enc_opts.dst_opt_type != + IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; option_len = fl_set_geneve_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1470,7 +1517,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_GENEVE_OPT_BIT; option_len = fl_set_geneve_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1489,7 +1536,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; option_len = fl_set_vxlan_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1500,7 +1547,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_VXLAN_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_VXLAN_OPT_BIT; option_len = fl_set_vxlan_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1519,7 +1566,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; option_len = fl_set_erspan_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1530,7 +1577,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_ERSPAN_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_ERSPAN_OPT_BIT; option_len = fl_set_erspan_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1550,7 +1597,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } option_len = 0; - key->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + key->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; option_len = fl_set_gtp_opt(nla_opt_key, key, key_depth, option_len, extack); @@ -1561,7 +1608,7 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, /* At the same time we need to parse through the mask * in order to verify exact and mask attribute lengths. */ - mask->enc_opts.dst_opt_type = TUNNEL_GTP_OPT; + mask->enc_opts.dst_opt_type = IP_TUNNEL_GTP_OPT_BIT; option_len = fl_set_gtp_opt(nla_opt_msk, mask, msk_depth, option_len, extack); @@ -1575,6 +1622,36 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, return -EINVAL; } break; + case TCA_FLOWER_KEY_ENC_OPTS_PFCP: + if (key->enc_opts.dst_opt_type) { + NL_SET_ERR_MSG_MOD(extack, "Duplicate type for pfcp options"); + return -EINVAL; + } + option_len = 0; + key->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_key, key, + key_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + key->enc_opts.len += option_len; + /* At the same time we need to parse through the mask + * in order to verify exact and mask attribute lengths. + */ + mask->enc_opts.dst_opt_type = IP_TUNNEL_PFCP_OPT_BIT; + option_len = fl_set_pfcp_opt(nla_opt_msk, mask, + msk_depth, option_len, + extack); + if (option_len < 0) + return option_len; + + mask->enc_opts.len += option_len; + if (key->enc_opts.len != mask->enc_opts.len) { + NL_SET_ERR_MSG_MOD(extack, "Key and mask miss aligned"); + return -EINVAL; + } + break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel option type"); return -EINVAL; @@ -3117,6 +3194,32 @@ nla_put_failure: return -EMSGSIZE; } +static int fl_dump_key_pfcp_opt(struct sk_buff *skb, + struct flow_dissector_key_enc_opts *enc_opts) +{ + struct pfcp_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_PFCP); + if (!nest) + goto nla_put_failure; + + md = (struct pfcp_metadata *)&enc_opts->data[0]; + if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_TYPE, md->type)) + goto nla_put_failure; + + if (nla_put_be64(skb, TCA_FLOWER_KEY_ENC_OPT_PFCP_SEID, + md->seid, 0)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int fl_dump_key_ct(struct sk_buff *skb, struct flow_dissector_key_ct *key, struct flow_dissector_key_ct *mask) @@ -3202,26 +3305,31 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type, goto nla_put_failure; switch (enc_opts->dst_opt_type) { - case TUNNEL_GENEVE_OPT: + case IP_TUNNEL_GENEVE_OPT_BIT: err = fl_dump_key_geneve_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_VXLAN_OPT: + case IP_TUNNEL_VXLAN_OPT_BIT: err = fl_dump_key_vxlan_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_ERSPAN_OPT: + case IP_TUNNEL_ERSPAN_OPT_BIT: err = fl_dump_key_erspan_opt(skb, enc_opts); if (err) goto nla_put_failure; break; - case TUNNEL_GTP_OPT: + case IP_TUNNEL_GTP_OPT_BIT: err = fl_dump_key_gtp_opt(skb, enc_opts); if (err) goto nla_put_failure; break; + case IP_TUNNEL_PFCP_OPT_BIT: + err = fl_dump_key_pfcp_opt(skb, enc_opts); + if (err) + goto nla_put_failure; + break; default: goto nla_put_failure; } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 6292d6d73b72..74afc210527d 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1334,7 +1334,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, * before again attaching a qdisc. */ if ((dev->priv_flags & IFF_NO_QUEUE) && (dev->tx_queue_len == 0)) { - dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; + WRITE_ONCE(dev->tx_queue_len, DEFAULT_TX_QUEUE_LEN); netdev_info(dev, "Caught tx_queue_len zero misconfig\n"); } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index edee926ccde8..9602dafe32e6 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1512,7 +1512,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) if (!q->overflow_timeout) { int i; /* Build fresh max-heap */ - for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2; i >= 0; i--) + for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2 - 1; i >= 0; i--) cake_heapify(q, i); } q->overflow_timeout = 65535; @@ -2572,6 +2572,8 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CAKE_MAX + 1]; + u16 rate_flags; + u8 flow_mode; int err; err = nla_parse_nested_deprecated(tb, TCA_CAKE_MAX, opt, cake_policy, @@ -2579,10 +2581,11 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, if (err < 0) return err; + flow_mode = q->flow_mode; if (tb[TCA_CAKE_NAT]) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) - q->flow_mode &= ~CAKE_FLOW_NAT_FLAG; - q->flow_mode |= CAKE_FLOW_NAT_FLAG * + flow_mode &= ~CAKE_FLOW_NAT_FLAG; + flow_mode |= CAKE_FLOW_NAT_FLAG * !!nla_get_u32(tb[TCA_CAKE_NAT]); #else NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT], @@ -2592,29 +2595,34 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, } if (tb[TCA_CAKE_BASE_RATE64]) - q->rate_bps = nla_get_u64(tb[TCA_CAKE_BASE_RATE64]); + WRITE_ONCE(q->rate_bps, + nla_get_u64(tb[TCA_CAKE_BASE_RATE64])); if (tb[TCA_CAKE_DIFFSERV_MODE]) - q->tin_mode = nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE]); + WRITE_ONCE(q->tin_mode, + nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE])); + rate_flags = q->rate_flags; if (tb[TCA_CAKE_WASH]) { if (!!nla_get_u32(tb[TCA_CAKE_WASH])) - q->rate_flags |= CAKE_FLAG_WASH; + rate_flags |= CAKE_FLAG_WASH; else - q->rate_flags &= ~CAKE_FLAG_WASH; + rate_flags &= ~CAKE_FLAG_WASH; } if (tb[TCA_CAKE_FLOW_MODE]) - q->flow_mode = ((q->flow_mode & CAKE_FLOW_NAT_FLAG) | + flow_mode = ((flow_mode & CAKE_FLOW_NAT_FLAG) | (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) & CAKE_FLOW_MASK)); if (tb[TCA_CAKE_ATM]) - q->atm_mode = nla_get_u32(tb[TCA_CAKE_ATM]); + WRITE_ONCE(q->atm_mode, + nla_get_u32(tb[TCA_CAKE_ATM])); if (tb[TCA_CAKE_OVERHEAD]) { - q->rate_overhead = nla_get_s32(tb[TCA_CAKE_OVERHEAD]); - q->rate_flags |= CAKE_FLAG_OVERHEAD; + WRITE_ONCE(q->rate_overhead, + nla_get_s32(tb[TCA_CAKE_OVERHEAD])); + rate_flags |= CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; @@ -2623,7 +2631,7 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, } if (tb[TCA_CAKE_RAW]) { - q->rate_flags &= ~CAKE_FLAG_OVERHEAD; + rate_flags &= ~CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; @@ -2632,54 +2640,58 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, } if (tb[TCA_CAKE_MPU]) - q->rate_mpu = nla_get_u32(tb[TCA_CAKE_MPU]); + WRITE_ONCE(q->rate_mpu, + nla_get_u32(tb[TCA_CAKE_MPU])); if (tb[TCA_CAKE_RTT]) { - q->interval = nla_get_u32(tb[TCA_CAKE_RTT]); + u32 interval = nla_get_u32(tb[TCA_CAKE_RTT]); - if (!q->interval) - q->interval = 1; + WRITE_ONCE(q->interval, max(interval, 1U)); } if (tb[TCA_CAKE_TARGET]) { - q->target = nla_get_u32(tb[TCA_CAKE_TARGET]); + u32 target = nla_get_u32(tb[TCA_CAKE_TARGET]); - if (!q->target) - q->target = 1; + WRITE_ONCE(q->target, max(target, 1U)); } if (tb[TCA_CAKE_AUTORATE]) { if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE])) - q->rate_flags |= CAKE_FLAG_AUTORATE_INGRESS; + rate_flags |= CAKE_FLAG_AUTORATE_INGRESS; else - q->rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS; + rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS; } if (tb[TCA_CAKE_INGRESS]) { if (!!nla_get_u32(tb[TCA_CAKE_INGRESS])) - q->rate_flags |= CAKE_FLAG_INGRESS; + rate_flags |= CAKE_FLAG_INGRESS; else - q->rate_flags &= ~CAKE_FLAG_INGRESS; + rate_flags &= ~CAKE_FLAG_INGRESS; } if (tb[TCA_CAKE_ACK_FILTER]) - q->ack_filter = nla_get_u32(tb[TCA_CAKE_ACK_FILTER]); + WRITE_ONCE(q->ack_filter, + nla_get_u32(tb[TCA_CAKE_ACK_FILTER])); if (tb[TCA_CAKE_MEMORY]) - q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]); + WRITE_ONCE(q->buffer_config_limit, + nla_get_u32(tb[TCA_CAKE_MEMORY])); if (tb[TCA_CAKE_SPLIT_GSO]) { if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO])) - q->rate_flags |= CAKE_FLAG_SPLIT_GSO; + rate_flags |= CAKE_FLAG_SPLIT_GSO; else - q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO; + rate_flags &= ~CAKE_FLAG_SPLIT_GSO; } if (tb[TCA_CAKE_FWMARK]) { - q->fwmark_mask = nla_get_u32(tb[TCA_CAKE_FWMARK]); - q->fwmark_shft = q->fwmark_mask ? __ffs(q->fwmark_mask) : 0; + WRITE_ONCE(q->fwmark_mask, nla_get_u32(tb[TCA_CAKE_FWMARK])); + WRITE_ONCE(q->fwmark_shft, + q->fwmark_mask ? __ffs(q->fwmark_mask) : 0); } + WRITE_ONCE(q->rate_flags, rate_flags); + WRITE_ONCE(q->flow_mode, flow_mode); if (q->tins) { sch_tree_lock(sch); cake_reconfigure(sch); @@ -2774,68 +2786,72 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *opts; + u16 rate_flags; + u8 flow_mode; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!opts) goto nla_put_failure; - if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, q->rate_bps, - TCA_CAKE_PAD)) + if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, + READ_ONCE(q->rate_bps), TCA_CAKE_PAD)) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, - q->flow_mode & CAKE_FLOW_MASK)) + flow_mode = READ_ONCE(q->flow_mode); + if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, flow_mode & CAKE_FLOW_MASK)) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_RTT, q->interval)) + if (nla_put_u32(skb, TCA_CAKE_RTT, READ_ONCE(q->interval))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_TARGET, q->target)) + if (nla_put_u32(skb, TCA_CAKE_TARGET, READ_ONCE(q->target))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_MEMORY, q->buffer_config_limit)) + if (nla_put_u32(skb, TCA_CAKE_MEMORY, + READ_ONCE(q->buffer_config_limit))) goto nla_put_failure; + rate_flags = READ_ONCE(q->rate_flags); if (nla_put_u32(skb, TCA_CAKE_AUTORATE, - !!(q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS))) + !!(rate_flags & CAKE_FLAG_AUTORATE_INGRESS))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_INGRESS, - !!(q->rate_flags & CAKE_FLAG_INGRESS))) + !!(rate_flags & CAKE_FLAG_INGRESS))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, q->ack_filter)) + if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, READ_ONCE(q->ack_filter))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_NAT, - !!(q->flow_mode & CAKE_FLOW_NAT_FLAG))) + !!(flow_mode & CAKE_FLOW_NAT_FLAG))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, q->tin_mode)) + if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, READ_ONCE(q->tin_mode))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_WASH, - !!(q->rate_flags & CAKE_FLAG_WASH))) + !!(rate_flags & CAKE_FLAG_WASH))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, q->rate_overhead)) + if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, READ_ONCE(q->rate_overhead))) goto nla_put_failure; - if (!(q->rate_flags & CAKE_FLAG_OVERHEAD)) + if (!(rate_flags & CAKE_FLAG_OVERHEAD)) if (nla_put_u32(skb, TCA_CAKE_RAW, 0)) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_ATM, q->atm_mode)) + if (nla_put_u32(skb, TCA_CAKE_ATM, READ_ONCE(q->atm_mode))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_MPU, q->rate_mpu)) + if (nla_put_u32(skb, TCA_CAKE_MPU, READ_ONCE(q->rate_mpu))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO, - !!(q->rate_flags & CAKE_FLAG_SPLIT_GSO))) + !!(rate_flags & CAKE_FLAG_SPLIT_GSO))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_FWMARK, q->fwmark_mask)) + if (nla_put_u32(skb, TCA_CAKE_FWMARK, READ_ONCE(q->fwmark_mask))) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 69001eff0315..939425da1895 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -389,11 +389,11 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt, } /* Everything went OK, save the parameters used. */ - q->hicredit = qopt->hicredit; - q->locredit = qopt->locredit; - q->idleslope = qopt->idleslope * BYTES_PER_KBIT; - q->sendslope = qopt->sendslope * BYTES_PER_KBIT; - q->offload = qopt->offload; + WRITE_ONCE(q->hicredit, qopt->hicredit); + WRITE_ONCE(q->locredit, qopt->locredit); + WRITE_ONCE(q->idleslope, qopt->idleslope * BYTES_PER_KBIT); + WRITE_ONCE(q->sendslope, qopt->sendslope * BYTES_PER_KBIT); + WRITE_ONCE(q->offload, qopt->offload); return 0; } @@ -459,11 +459,11 @@ static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) if (!nest) goto nla_put_failure; - opt.hicredit = q->hicredit; - opt.locredit = q->locredit; - opt.sendslope = div64_s64(q->sendslope, BYTES_PER_KBIT); - opt.idleslope = div64_s64(q->idleslope, BYTES_PER_KBIT); - opt.offload = q->offload; + opt.hicredit = READ_ONCE(q->hicredit); + opt.locredit = READ_ONCE(q->locredit); + opt.sendslope = div64_s64(READ_ONCE(q->sendslope), BYTES_PER_KBIT); + opt.idleslope = div64_s64(READ_ONCE(q->idleslope), BYTES_PER_KBIT); + opt.offload = READ_ONCE(q->offload); if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index ea108030c6b4..91072010923d 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -405,8 +405,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, } else sch_tree_lock(sch); - q->flags = ctl->flags; - q->limit = ctl->limit; + WRITE_ONCE(q->flags, ctl->flags); + WRITE_ONCE(q->limit, ctl->limit); red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, @@ -431,15 +431,16 @@ static int choke_init(struct Qdisc *sch, struct nlattr *opt, static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) { struct choke_sched_data *q = qdisc_priv(sch); + u8 Wlog = READ_ONCE(q->parms.Wlog); struct nlattr *opts = NULL; struct tc_red_qopt opt = { - .limit = q->limit, - .flags = q->flags, - .qth_min = q->parms.qth_min >> q->parms.Wlog, - .qth_max = q->parms.qth_max >> q->parms.Wlog, - .Wlog = q->parms.Wlog, - .Plog = q->parms.Plog, - .Scell_log = q->parms.Scell_log, + .limit = READ_ONCE(q->limit), + .flags = READ_ONCE(q->flags), + .qth_min = READ_ONCE(q->parms.qth_min) >> Wlog, + .qth_max = READ_ONCE(q->parms.qth_max) >> Wlog, + .Wlog = Wlog, + .Plog = READ_ONCE(q->parms.Plog), + .Scell_log = READ_ONCE(q->parms.Scell_log), }; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); @@ -447,7 +448,7 @@ static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) || - nla_put_u32(skb, TCA_CHOKE_MAX_P, q->parms.max_P)) + nla_put_u32(skb, TCA_CHOKE_MAX_P, READ_ONCE(q->parms.max_P))) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index ecb3f164bb25..3e8d4fe4d91e 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -118,26 +118,31 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_CODEL_TARGET]) { u32 target = nla_get_u32(tb[TCA_CODEL_TARGET]); - q->params.target = ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->params.target, + ((u64)target * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_CE_THRESHOLD]) { u64 val = nla_get_u32(tb[TCA_CODEL_CE_THRESHOLD]); - q->params.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->params.ce_threshold, + (val * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_INTERVAL]) { u32 interval = nla_get_u32(tb[TCA_CODEL_INTERVAL]); - q->params.interval = ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->params.interval, + ((u64)interval * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_CODEL_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_CODEL_LIMIT]); + WRITE_ONCE(sch->limit, + nla_get_u32(tb[TCA_CODEL_LIMIT])); if (tb[TCA_CODEL_ECN]) - q->params.ecn = !!nla_get_u32(tb[TCA_CODEL_ECN]); + WRITE_ONCE(q->params.ecn, + !!nla_get_u32(tb[TCA_CODEL_ECN])); qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { @@ -183,6 +188,7 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt, static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) { struct codel_sched_data *q = qdisc_priv(sch); + codel_time_t ce_threshold; struct nlattr *opts; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); @@ -190,17 +196,18 @@ static int codel_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; if (nla_put_u32(skb, TCA_CODEL_TARGET, - codel_time_to_us(q->params.target)) || + codel_time_to_us(READ_ONCE(q->params.target))) || nla_put_u32(skb, TCA_CODEL_LIMIT, - sch->limit) || + READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_CODEL_INTERVAL, - codel_time_to_us(q->params.interval)) || + codel_time_to_us(READ_ONCE(q->params.interval))) || nla_put_u32(skb, TCA_CODEL_ECN, - q->params.ecn)) + READ_ONCE(q->params.ecn))) goto nla_put_failure; - if (q->params.ce_threshold != CODEL_DISABLED_THRESHOLD && + ce_threshold = READ_ONCE(q->params.ce_threshold); + if (ce_threshold != CODEL_DISABLED_THRESHOLD && nla_put_u32(skb, TCA_CODEL_CE_THRESHOLD, - codel_time_to_us(q->params.ce_threshold))) + codel_time_to_us(ce_threshold))) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index 2e4bef713b6a..c74d778c32a1 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -467,15 +467,15 @@ static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) if (!nest) goto nla_put_failure; - opt.delta = q->delta; - opt.clockid = q->clockid; - if (q->offload) + opt.delta = READ_ONCE(q->delta); + opt.clockid = READ_ONCE(q->clockid); + if (READ_ONCE(q->offload)) opt.flags |= TC_ETF_OFFLOAD_ON; - if (q->deadline_mode) + if (READ_ONCE(q->deadline_mode)) opt.flags |= TC_ETF_DEADLINE_MODE_ON; - if (q->skip_sock_check) + if (READ_ONCE(q->skip_sock_check)) opt.flags |= TC_ETF_SKIP_SOCK_CHECK; if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt)) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 835b4460b448..f80bc05d4c5a 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -646,7 +646,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); - q->nbands = nbands; + WRITE_ONCE(q->nbands, nbands); for (i = nstrict; i < q->nstrict; i++) { if (q->classes[i].qdisc->q.qlen) { list_add_tail(&q->classes[i].alist, &q->active); @@ -658,11 +658,11 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, list_del(&q->classes[i].alist); qdisc_tree_flush_backlog(q->classes[i].qdisc); } - q->nstrict = nstrict; + WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); for (i = 0; i < q->nbands; i++) - q->classes[i].quantum = quanta[i]; + WRITE_ONCE(q->classes[i].quantum, quanta[i]); for (i = oldbands; i < q->nbands; i++) { q->classes[i].qdisc = queues[i]; @@ -676,7 +676,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, for (i = q->nbands; i < oldbands; i++) { qdisc_put(q->classes[i].qdisc); q->classes[i].qdisc = NULL; - q->classes[i].quantum = 0; + WRITE_ONCE(q->classes[i].quantum, 0); q->classes[i].deficit = 0; gnet_stats_basic_sync_init(&q->classes[i].bstats); memset(&q->classes[i].qstats, 0, sizeof(q->classes[i].qstats)); @@ -733,6 +733,7 @@ static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb) struct ets_sched *q = qdisc_priv(sch); struct nlattr *opts; struct nlattr *nest; + u8 nbands, nstrict; int band; int prio; int err; @@ -745,21 +746,22 @@ static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb) if (!opts) goto nla_err; - if (nla_put_u8(skb, TCA_ETS_NBANDS, q->nbands)) + nbands = READ_ONCE(q->nbands); + if (nla_put_u8(skb, TCA_ETS_NBANDS, nbands)) goto nla_err; - if (q->nstrict && - nla_put_u8(skb, TCA_ETS_NSTRICT, q->nstrict)) + nstrict = READ_ONCE(q->nstrict); + if (nstrict && nla_put_u8(skb, TCA_ETS_NSTRICT, nstrict)) goto nla_err; - if (q->nbands > q->nstrict) { + if (nbands > nstrict) { nest = nla_nest_start(skb, TCA_ETS_QUANTA); if (!nest) goto nla_err; - for (band = q->nstrict; band < q->nbands; band++) { + for (band = nstrict; band < nbands; band++) { if (nla_put_u32(skb, TCA_ETS_QUANTA_BAND, - q->classes[band].quantum)) + READ_ONCE(q->classes[band].quantum))) goto nla_err; } @@ -771,7 +773,8 @@ static int ets_qdisc_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_err; for (prio = 0; prio <= TC_PRIO_MAX; prio++) { - if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND, q->prio2band[prio])) + if (nla_put_u8(skb, TCA_ETS_PRIOMAP_BAND, + READ_ONCE(q->prio2band[prio]))) goto nla_err; } diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 450f5c67ac49..b50b2c2cc09b 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -19,7 +19,8 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) + if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= + READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); @@ -28,7 +29,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { - if (likely(sch->q.qlen < sch->limit)) + if (likely(sch->q.qlen < READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); @@ -39,7 +40,7 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, { unsigned int prev_backlog; - if (likely(sch->q.qlen < sch->limit)) + if (likely(sch->q.qlen < READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); prev_backlog = sch->qstats.backlog; @@ -105,14 +106,14 @@ static int __fifo_init(struct Qdisc *sch, struct nlattr *opt, if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); - sch->limit = limit; + WRITE_ONCE(sch->limit, limit); } else { struct tc_fifo_qopt *ctl = nla_data(opt); if (nla_len(opt) < sizeof(*ctl)) return -EINVAL; - sch->limit = ctl->limit; + WRITE_ONCE(sch->limit, ctl->limit); } if (is_bfifo) @@ -154,7 +155,7 @@ static void fifo_destroy(struct Qdisc *sch) static int __fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { - struct tc_fifo_qopt opt = { .limit = sch->limit }; + struct tc_fifo_qopt opt = { .limit = READ_ONCE(sch->limit) }; if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index cdf23ff16f40..19a49af5a9e5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -106,6 +106,8 @@ struct fq_perband_flows { int quantum; /* based on band nr : 576KB, 192KB, 64KB */ }; +#define FQ_PRIO2BAND_CRUMB_SIZE ((TC_PRIO_MAX + 1) >> 2) + struct fq_sched_data { /* Read mostly cache line */ @@ -122,7 +124,7 @@ struct fq_sched_data { u8 rate_enable; u8 fq_trees_log; u8 horizon_drop; - u8 prio2band[(TC_PRIO_MAX + 1) >> 2]; + u8 prio2band[FQ_PRIO2BAND_CRUMB_SIZE]; u32 timer_slack; /* hrtimer slack in ns */ /* Read/Write fields. */ @@ -159,7 +161,7 @@ struct fq_sched_data { /* return the i-th 2-bit value ("crumb") */ static u8 fq_prio2band(const u8 *prio2band, unsigned int prio) { - return (prio2band[prio / 4] >> (2 * (prio & 0x3))) & 0x3; + return (READ_ONCE(prio2band[prio / 4]) >> (2 * (prio & 0x3))) & 0x3; } /* @@ -661,7 +663,9 @@ begin: pband = &q->band_flows[q->band_nr]; pband->credit = min(pband->credit + pband->quantum, pband->quantum); - goto begin; + if (pband->credit > 0) + goto begin; + retry = 0; } if (q->time_next_delayed_flow != ~0ULL) qdisc_watchdog_schedule_range_ns(&q->watchdog, @@ -888,7 +892,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) fq_rehash(q, old_fq_root, q->fq_trees_log, array, log); q->fq_root = array; - q->fq_trees_log = log; + WRITE_ONCE(q->fq_trees_log, log); sch_tree_unlock(sch); @@ -927,11 +931,15 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { static void fq_prio2band_compress_crumb(const u8 *in, u8 *out) { const int num_elems = TC_PRIO_MAX + 1; + u8 tmp[FQ_PRIO2BAND_CRUMB_SIZE]; int i; - memset(out, 0, num_elems / 4); + memset(tmp, 0, sizeof(tmp)); for (i = 0; i < num_elems; i++) - out[i / 4] |= in[i] << (2 * (i & 0x3)); + tmp[i / 4] |= in[i] << (2 * (i & 0x3)); + + for (i = 0; i < FQ_PRIO2BAND_CRUMB_SIZE; i++) + WRITE_ONCE(out[i], tmp[i]); } static void fq_prio2band_decompress_crumb(const u8 *in, u8 *out) @@ -958,7 +966,7 @@ static int fq_load_weights(struct fq_sched_data *q, } } for (i = 0; i < FQ_BANDS; i++) - q->band_flows[i].quantum = weights[i]; + WRITE_ONCE(q->band_flows[i].quantum, weights[i]); return 0; } @@ -1011,16 +1019,18 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, err = -EINVAL; } if (tb[TCA_FQ_PLIMIT]) - sch->limit = nla_get_u32(tb[TCA_FQ_PLIMIT]); + WRITE_ONCE(sch->limit, + nla_get_u32(tb[TCA_FQ_PLIMIT])); if (tb[TCA_FQ_FLOW_PLIMIT]) - q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]); + WRITE_ONCE(q->flow_plimit, + nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT])); if (tb[TCA_FQ_QUANTUM]) { u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); if (quantum > 0 && quantum <= (1 << 20)) { - q->quantum = quantum; + WRITE_ONCE(q->quantum, quantum); } else { NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); err = -EINVAL; @@ -1028,7 +1038,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, } if (tb[TCA_FQ_INITIAL_QUANTUM]) - q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); + WRITE_ONCE(q->initial_quantum, + nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM])); if (tb[TCA_FQ_FLOW_DEFAULT_RATE]) pr_warn_ratelimited("sch_fq: defrate %u ignored.\n", @@ -1037,17 +1048,19 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_FLOW_MAX_RATE]) { u32 rate = nla_get_u32(tb[TCA_FQ_FLOW_MAX_RATE]); - q->flow_max_rate = (rate == ~0U) ? ~0UL : rate; + WRITE_ONCE(q->flow_max_rate, + (rate == ~0U) ? ~0UL : rate); } if (tb[TCA_FQ_LOW_RATE_THRESHOLD]) - q->low_rate_threshold = - nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD]); + WRITE_ONCE(q->low_rate_threshold, + nla_get_u32(tb[TCA_FQ_LOW_RATE_THRESHOLD])); if (tb[TCA_FQ_RATE_ENABLE]) { u32 enable = nla_get_u32(tb[TCA_FQ_RATE_ENABLE]); if (enable <= 1) - q->rate_enable = enable; + WRITE_ONCE(q->rate_enable, + enable); else err = -EINVAL; } @@ -1055,7 +1068,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_FLOW_REFILL_DELAY]) { u32 usecs_delay = nla_get_u32(tb[TCA_FQ_FLOW_REFILL_DELAY]) ; - q->flow_refill_delay = usecs_to_jiffies(usecs_delay); + WRITE_ONCE(q->flow_refill_delay, + usecs_to_jiffies(usecs_delay)); } if (!err && tb[TCA_FQ_PRIOMAP]) @@ -1065,21 +1079,26 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, err = fq_load_weights(q, tb[TCA_FQ_WEIGHTS], extack); if (tb[TCA_FQ_ORPHAN_MASK]) - q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]); + WRITE_ONCE(q->orphan_mask, + nla_get_u32(tb[TCA_FQ_ORPHAN_MASK])); if (tb[TCA_FQ_CE_THRESHOLD]) - q->ce_threshold = (u64)NSEC_PER_USEC * - nla_get_u32(tb[TCA_FQ_CE_THRESHOLD]); + WRITE_ONCE(q->ce_threshold, + (u64)NSEC_PER_USEC * + nla_get_u32(tb[TCA_FQ_CE_THRESHOLD])); if (tb[TCA_FQ_TIMER_SLACK]) - q->timer_slack = nla_get_u32(tb[TCA_FQ_TIMER_SLACK]); + WRITE_ONCE(q->timer_slack, + nla_get_u32(tb[TCA_FQ_TIMER_SLACK])); if (tb[TCA_FQ_HORIZON]) - q->horizon = (u64)NSEC_PER_USEC * - nla_get_u32(tb[TCA_FQ_HORIZON]); + WRITE_ONCE(q->horizon, + (u64)NSEC_PER_USEC * + nla_get_u32(tb[TCA_FQ_HORIZON])); if (tb[TCA_FQ_HORIZON_DROP]) - q->horizon_drop = nla_get_u8(tb[TCA_FQ_HORIZON_DROP]); + WRITE_ONCE(q->horizon_drop, + nla_get_u8(tb[TCA_FQ_HORIZON_DROP])); if (!err) { @@ -1160,13 +1179,13 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt, static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_sched_data *q = qdisc_priv(sch); - u64 ce_threshold = q->ce_threshold; struct tc_prio_qopt prio = { .bands = FQ_BANDS, }; - u64 horizon = q->horizon; struct nlattr *opts; + u64 ce_threshold; s32 weights[3]; + u64 horizon; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (opts == NULL) @@ -1174,35 +1193,48 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore */ + ce_threshold = READ_ONCE(q->ce_threshold); do_div(ce_threshold, NSEC_PER_USEC); + + horizon = READ_ONCE(q->horizon); do_div(horizon, NSEC_PER_USEC); - if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || - nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || - nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) || - nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) || - nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) || + if (nla_put_u32(skb, TCA_FQ_PLIMIT, + READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, + READ_ONCE(q->flow_plimit)) || + nla_put_u32(skb, TCA_FQ_QUANTUM, + READ_ONCE(q->quantum)) || + nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, + READ_ONCE(q->initial_quantum)) || + nla_put_u32(skb, TCA_FQ_RATE_ENABLE, + READ_ONCE(q->rate_enable)) || nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, - min_t(unsigned long, q->flow_max_rate, ~0U)) || + min_t(unsigned long, + READ_ONCE(q->flow_max_rate), ~0U)) || nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY, - jiffies_to_usecs(q->flow_refill_delay)) || - nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) || + jiffies_to_usecs(READ_ONCE(q->flow_refill_delay))) || + nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, + READ_ONCE(q->orphan_mask)) || nla_put_u32(skb, TCA_FQ_LOW_RATE_THRESHOLD, - q->low_rate_threshold) || + READ_ONCE(q->low_rate_threshold)) || nla_put_u32(skb, TCA_FQ_CE_THRESHOLD, (u32)ce_threshold) || - nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log) || - nla_put_u32(skb, TCA_FQ_TIMER_SLACK, q->timer_slack) || + nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, + READ_ONCE(q->fq_trees_log)) || + nla_put_u32(skb, TCA_FQ_TIMER_SLACK, + READ_ONCE(q->timer_slack)) || nla_put_u32(skb, TCA_FQ_HORIZON, (u32)horizon) || - nla_put_u8(skb, TCA_FQ_HORIZON_DROP, q->horizon_drop)) + nla_put_u8(skb, TCA_FQ_HORIZON_DROP, + READ_ONCE(q->horizon_drop))) goto nla_put_failure; fq_prio2band_decompress_crumb(q->prio2band, prio.priomap); if (nla_put(skb, TCA_FQ_PRIOMAP, sizeof(prio), &prio)) goto nla_put_failure; - weights[0] = q->band_flows[0].quantum; - weights[1] = q->band_flows[1].quantum; - weights[2] = q->band_flows[2].quantum; + weights[0] = READ_ONCE(q->band_flows[0].quantum); + weights[1] = READ_ONCE(q->band_flows[1].quantum); + weights[2] = READ_ONCE(q->band_flows[2].quantum); if (nla_put(skb, TCA_FQ_WEIGHTS, sizeof(weights), &weights)) goto nla_put_failure; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 79f9d6de6c85..4f908c11ba95 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -396,40 +396,49 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_CODEL_TARGET]) { u64 target = nla_get_u32(tb[TCA_FQ_CODEL_TARGET]); - q->cparams.target = (target * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->cparams.target, + (target * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_FQ_CODEL_CE_THRESHOLD]) { u64 val = nla_get_u32(tb[TCA_FQ_CODEL_CE_THRESHOLD]); - q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->cparams.ce_threshold, + (val * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]) - q->cparams.ce_threshold_selector = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]); + WRITE_ONCE(q->cparams.ce_threshold_selector, + nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR])); if (tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]) - q->cparams.ce_threshold_mask = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]); + WRITE_ONCE(q->cparams.ce_threshold_mask, + nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK])); if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); - q->cparams.interval = (interval * NSEC_PER_USEC) >> CODEL_SHIFT; + WRITE_ONCE(q->cparams.interval, + (interval * NSEC_PER_USEC) >> CODEL_SHIFT); } if (tb[TCA_FQ_CODEL_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_FQ_CODEL_LIMIT]); + WRITE_ONCE(sch->limit, + nla_get_u32(tb[TCA_FQ_CODEL_LIMIT])); if (tb[TCA_FQ_CODEL_ECN]) - q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]); + WRITE_ONCE(q->cparams.ecn, + !!nla_get_u32(tb[TCA_FQ_CODEL_ECN])); if (quantum) - q->quantum = quantum; + WRITE_ONCE(q->quantum, quantum); if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + WRITE_ONCE(q->drop_batch_size, + max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]))); if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) - q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); + WRITE_ONCE(q->memory_limit, + min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT]))); while (sch->q.qlen > sch->limit || q->memory_usage > q->memory_limit) { @@ -522,6 +531,7 @@ init_failure: static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) { struct fq_codel_sched_data *q = qdisc_priv(sch); + codel_time_t ce_threshold; struct nlattr *opts; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); @@ -529,30 +539,33 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; if (nla_put_u32(skb, TCA_FQ_CODEL_TARGET, - codel_time_to_us(q->cparams.target)) || + codel_time_to_us(READ_ONCE(q->cparams.target))) || nla_put_u32(skb, TCA_FQ_CODEL_LIMIT, - sch->limit) || + READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_FQ_CODEL_INTERVAL, - codel_time_to_us(q->cparams.interval)) || + codel_time_to_us(READ_ONCE(q->cparams.interval))) || nla_put_u32(skb, TCA_FQ_CODEL_ECN, - q->cparams.ecn) || + READ_ONCE(q->cparams.ecn)) || nla_put_u32(skb, TCA_FQ_CODEL_QUANTUM, - q->quantum) || + READ_ONCE(q->quantum)) || nla_put_u32(skb, TCA_FQ_CODEL_DROP_BATCH_SIZE, - q->drop_batch_size) || + READ_ONCE(q->drop_batch_size)) || nla_put_u32(skb, TCA_FQ_CODEL_MEMORY_LIMIT, - q->memory_limit) || + READ_ONCE(q->memory_limit)) || nla_put_u32(skb, TCA_FQ_CODEL_FLOWS, - q->flows_cnt)) + READ_ONCE(q->flows_cnt))) goto nla_put_failure; - if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD) { + ce_threshold = READ_ONCE(q->cparams.ce_threshold); + if (ce_threshold != CODEL_DISABLED_THRESHOLD) { if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, - codel_time_to_us(q->cparams.ce_threshold))) + codel_time_to_us(ce_threshold))) goto nla_put_failure; - if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, q->cparams.ce_threshold_selector)) + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, + READ_ONCE(q->cparams.ce_threshold_selector))) goto nla_put_failure; - if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_MASK, q->cparams.ce_threshold_mask)) + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_MASK, + READ_ONCE(q->cparams.ce_threshold_mask))) goto nla_put_failure; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 358cf304f4c9..c38f33ff80bd 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -299,8 +299,8 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_PIE_LIMIT]) { u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]); - q->p_params.limit = limit; - sch->limit = limit; + WRITE_ONCE(q->p_params.limit, limit); + WRITE_ONCE(sch->limit, limit); } if (tb[TCA_FQ_PIE_FLOWS]) { if (q->flows) { @@ -322,39 +322,45 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]); /* convert to pschedtime */ - q->p_params.target = - PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC); + WRITE_ONCE(q->p_params.target, + PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC)); } /* tupdate is in jiffies */ if (tb[TCA_FQ_PIE_TUPDATE]) - q->p_params.tupdate = - usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE])); + WRITE_ONCE(q->p_params.tupdate, + usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE]))); if (tb[TCA_FQ_PIE_ALPHA]) - q->p_params.alpha = nla_get_u32(tb[TCA_FQ_PIE_ALPHA]); + WRITE_ONCE(q->p_params.alpha, + nla_get_u32(tb[TCA_FQ_PIE_ALPHA])); if (tb[TCA_FQ_PIE_BETA]) - q->p_params.beta = nla_get_u32(tb[TCA_FQ_PIE_BETA]); + WRITE_ONCE(q->p_params.beta, + nla_get_u32(tb[TCA_FQ_PIE_BETA])); if (tb[TCA_FQ_PIE_QUANTUM]) - q->quantum = nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]); + WRITE_ONCE(q->quantum, nla_get_u32(tb[TCA_FQ_PIE_QUANTUM])); if (tb[TCA_FQ_PIE_MEMORY_LIMIT]) - q->memory_limit = nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT]); + WRITE_ONCE(q->memory_limit, + nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT])); if (tb[TCA_FQ_PIE_ECN_PROB]) - q->ecn_prob = nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB]); + WRITE_ONCE(q->ecn_prob, + nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB])); if (tb[TCA_FQ_PIE_ECN]) - q->p_params.ecn = nla_get_u32(tb[TCA_FQ_PIE_ECN]); + WRITE_ONCE(q->p_params.ecn, + nla_get_u32(tb[TCA_FQ_PIE_ECN])); if (tb[TCA_FQ_PIE_BYTEMODE]) - q->p_params.bytemode = nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE]); + WRITE_ONCE(q->p_params.bytemode, + nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE])); if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]) - q->p_params.dq_rate_estimator = - nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]); + WRITE_ONCE(q->p_params.dq_rate_estimator, + nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ while (sch->q.qlen > sch->limit) { @@ -471,22 +477,23 @@ static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb) return -EMSGSIZE; /* convert target from pschedtime to us */ - if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, sch->limit) || - nla_put_u32(skb, TCA_FQ_PIE_FLOWS, q->flows_cnt) || + if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_FQ_PIE_FLOWS, READ_ONCE(q->flows_cnt)) || nla_put_u32(skb, TCA_FQ_PIE_TARGET, - ((u32)PSCHED_TICKS2NS(q->p_params.target)) / + ((u32)PSCHED_TICKS2NS(READ_ONCE(q->p_params.target))) / NSEC_PER_USEC) || nla_put_u32(skb, TCA_FQ_PIE_TUPDATE, - jiffies_to_usecs(q->p_params.tupdate)) || - nla_put_u32(skb, TCA_FQ_PIE_ALPHA, q->p_params.alpha) || - nla_put_u32(skb, TCA_FQ_PIE_BETA, q->p_params.beta) || - nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, q->quantum) || - nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, q->memory_limit) || - nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, q->ecn_prob) || - nla_put_u32(skb, TCA_FQ_PIE_ECN, q->p_params.ecn) || - nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, q->p_params.bytemode) || + jiffies_to_usecs(READ_ONCE(q->p_params.tupdate))) || + nla_put_u32(skb, TCA_FQ_PIE_ALPHA, READ_ONCE(q->p_params.alpha)) || + nla_put_u32(skb, TCA_FQ_PIE_BETA, READ_ONCE(q->p_params.beta)) || + nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, READ_ONCE(q->quantum)) || + nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, + READ_ONCE(q->memory_limit)) || + nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, READ_ONCE(q->ecn_prob)) || + nla_put_u32(skb, TCA_FQ_PIE_ECN, READ_ONCE(q->p_params.ecn)) || + nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, READ_ONCE(q->p_params.bytemode)) || nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR, - q->p_params.dq_rate_estimator)) + READ_ONCE(q->p_params.dq_rate_estimator))) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index fb32984d7a16..e22ff003d52e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -506,19 +506,22 @@ static void dev_watchdog(struct timer_list *t) unsigned int timedout_ms = 0; unsigned int i; unsigned long trans_start; + unsigned long oldest_start = jiffies; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); trans_start = READ_ONCE(txq->trans_start); - if (netif_xmit_stopped(txq) && - time_after(jiffies, (trans_start + - dev->watchdog_timeo))) { + if (!netif_xmit_stopped(txq)) + continue; + if (time_after(jiffies, trans_start + dev->watchdog_timeo)) { timedout_ms = jiffies_to_msecs(jiffies - trans_start); atomic_long_inc(&txq->trans_timeout); break; } + if (time_after(oldest_start, trans_start)) + oldest_start = trans_start; } if (unlikely(timedout_ms)) { @@ -531,7 +534,7 @@ static void dev_watchdog(struct timer_list *t) netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, - round_jiffies(jiffies + + round_jiffies(oldest_start + dev->watchdog_timeo))) release = false; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 4e626df742d7..c287bf8423b4 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1174,7 +1174,8 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) } /* classification failed, try default class */ - cl = hfsc_find_class(TC_H_MAKE(TC_H_MAJ(sch->handle), q->defcls), sch); + cl = hfsc_find_class(TC_H_MAKE(TC_H_MAJ(sch->handle), + READ_ONCE(q->defcls)), sch); if (cl == NULL || cl->level > 0) return NULL; @@ -1443,9 +1444,7 @@ hfsc_change_qdisc(struct Qdisc *sch, struct nlattr *opt, return -EINVAL; qopt = nla_data(opt); - sch_tree_lock(sch); - q->defcls = qopt->defcls; - sch_tree_unlock(sch); + WRITE_ONCE(q->defcls, qopt->defcls); return 0; } @@ -1525,7 +1524,7 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) unsigned char *b = skb_tail_pointer(skb); struct tc_hfsc_qopt qopt; - qopt.defcls = q->defcls; + qopt.defcls = READ_ONCE(q->defcls); if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; return skb->len; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 3f906df1435b..44d9efe1a96a 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -534,27 +534,31 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); if (tb[TCA_HHF_BACKLOG_LIMIT]) - sch->limit = nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT]); + WRITE_ONCE(sch->limit, nla_get_u32(tb[TCA_HHF_BACKLOG_LIMIT])); - q->quantum = new_quantum; - q->hhf_non_hh_weight = new_hhf_non_hh_weight; + WRITE_ONCE(q->quantum, new_quantum); + WRITE_ONCE(q->hhf_non_hh_weight, new_hhf_non_hh_weight); if (tb[TCA_HHF_HH_FLOWS_LIMIT]) - q->hh_flows_limit = nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT]); + WRITE_ONCE(q->hh_flows_limit, + nla_get_u32(tb[TCA_HHF_HH_FLOWS_LIMIT])); if (tb[TCA_HHF_RESET_TIMEOUT]) { u32 us = nla_get_u32(tb[TCA_HHF_RESET_TIMEOUT]); - q->hhf_reset_timeout = usecs_to_jiffies(us); + WRITE_ONCE(q->hhf_reset_timeout, + usecs_to_jiffies(us)); } if (tb[TCA_HHF_ADMIT_BYTES]) - q->hhf_admit_bytes = nla_get_u32(tb[TCA_HHF_ADMIT_BYTES]); + WRITE_ONCE(q->hhf_admit_bytes, + nla_get_u32(tb[TCA_HHF_ADMIT_BYTES])); if (tb[TCA_HHF_EVICT_TIMEOUT]) { u32 us = nla_get_u32(tb[TCA_HHF_EVICT_TIMEOUT]); - q->hhf_evict_timeout = usecs_to_jiffies(us); + WRITE_ONCE(q->hhf_evict_timeout, + usecs_to_jiffies(us)); } qlen = sch->q.qlen; @@ -657,15 +661,18 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) if (opts == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_HHF_BACKLOG_LIMIT, sch->limit) || - nla_put_u32(skb, TCA_HHF_QUANTUM, q->quantum) || - nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, q->hh_flows_limit) || + if (nla_put_u32(skb, TCA_HHF_BACKLOG_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_HHF_QUANTUM, READ_ONCE(q->quantum)) || + nla_put_u32(skb, TCA_HHF_HH_FLOWS_LIMIT, + READ_ONCE(q->hh_flows_limit)) || nla_put_u32(skb, TCA_HHF_RESET_TIMEOUT, - jiffies_to_usecs(q->hhf_reset_timeout)) || - nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, q->hhf_admit_bytes) || + jiffies_to_usecs(READ_ONCE(q->hhf_reset_timeout))) || + nla_put_u32(skb, TCA_HHF_ADMIT_BYTES, + READ_ONCE(q->hhf_admit_bytes)) || nla_put_u32(skb, TCA_HHF_EVICT_TIMEOUT, - jiffies_to_usecs(q->hhf_evict_timeout)) || - nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight)) + jiffies_to_usecs(READ_ONCE(q->hhf_evict_timeout))) || + nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, + READ_ONCE(q->hhf_non_hh_weight))) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index c2ef9dcf91d2..cc6051d4f2ef 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -91,7 +91,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, true, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, true); @@ -121,7 +121,7 @@ static void ingress_destroy(struct Qdisc *sch) tcf_block_put_ext(q->block, sch, &q->block_info); if (entry) { - tcx_miniq_set_active(entry, false); + tcx_miniq_dec(entry); if (!tcx_entry_is_active(entry)) { tcx_entry_update(dev, NULL, true); tcx_entry_free(entry); @@ -257,7 +257,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, true, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, true); @@ -276,7 +276,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, false, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, false); @@ -302,7 +302,7 @@ static void clsact_destroy(struct Qdisc *sch) tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); if (ingress_entry) { - tcx_miniq_set_active(ingress_entry, false); + tcx_miniq_dec(ingress_entry); if (!tcx_entry_is_active(ingress_entry)) { tcx_entry_update(dev, NULL, true); tcx_entry_free(ingress_entry); @@ -310,7 +310,7 @@ static void clsact_destroy(struct Qdisc *sch) } if (egress_entry) { - tcx_miniq_set_active(egress_entry, false); + tcx_miniq_dec(egress_entry); if (!tcx_entry_is_active(egress_entry)) { tcx_entry_update(dev, NULL, false); tcx_entry_free(egress_entry); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 225353fbb3f1..51d4013b6121 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -215,10 +215,8 @@ static int mqprio_parse_tc_entries(struct Qdisc *sch, struct nlattr *nlattr_opt, for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) fp[tc] = priv->fp[tc]; - nla_for_each_attr(n, nlattr_opt, nlattr_opt_len, rem) { - if (nla_type(n) != TCA_MQPRIO_TC_ENTRY) - continue; - + nla_for_each_attr_type(n, TCA_MQPRIO_TC_ENTRY, nlattr_opt, + nlattr_opt_len, rem) { err = mqprio_parse_tc_entry(fp, n, &seen_tcs, extack); if (err) goto out; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edc72962ae63..0f8d581438c3 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; - int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb); /* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root_bh(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - rc_drop = NET_XMIT_SUCCESS; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. @@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) - return rc_drop; + goto finish_segs; + segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); - return rc_drop; + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); @@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { unsigned int len, last_len; - int nb; + int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 1764059b0635..b3dcb845b327 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -156,36 +156,38 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, u32 target = nla_get_u32(tb[TCA_PIE_TARGET]); /* convert to pschedtime */ - q->params.target = PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC); + WRITE_ONCE(q->params.target, + PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC)); } /* tupdate is in jiffies */ if (tb[TCA_PIE_TUPDATE]) - q->params.tupdate = - usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE])); + WRITE_ONCE(q->params.tupdate, + usecs_to_jiffies(nla_get_u32(tb[TCA_PIE_TUPDATE]))); if (tb[TCA_PIE_LIMIT]) { u32 limit = nla_get_u32(tb[TCA_PIE_LIMIT]); - q->params.limit = limit; - sch->limit = limit; + WRITE_ONCE(q->params.limit, limit); + WRITE_ONCE(sch->limit, limit); } if (tb[TCA_PIE_ALPHA]) - q->params.alpha = nla_get_u32(tb[TCA_PIE_ALPHA]); + WRITE_ONCE(q->params.alpha, nla_get_u32(tb[TCA_PIE_ALPHA])); if (tb[TCA_PIE_BETA]) - q->params.beta = nla_get_u32(tb[TCA_PIE_BETA]); + WRITE_ONCE(q->params.beta, nla_get_u32(tb[TCA_PIE_BETA])); if (tb[TCA_PIE_ECN]) - q->params.ecn = nla_get_u32(tb[TCA_PIE_ECN]); + WRITE_ONCE(q->params.ecn, nla_get_u32(tb[TCA_PIE_ECN])); if (tb[TCA_PIE_BYTEMODE]) - q->params.bytemode = nla_get_u32(tb[TCA_PIE_BYTEMODE]); + WRITE_ONCE(q->params.bytemode, + nla_get_u32(tb[TCA_PIE_BYTEMODE])); if (tb[TCA_PIE_DQ_RATE_ESTIMATOR]) - q->params.dq_rate_estimator = - nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR]); + WRITE_ONCE(q->params.dq_rate_estimator, + nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; @@ -469,17 +471,18 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb) /* convert target from pschedtime to us */ if (nla_put_u32(skb, TCA_PIE_TARGET, - ((u32)PSCHED_TICKS2NS(q->params.target)) / + ((u32)PSCHED_TICKS2NS(READ_ONCE(q->params.target))) / NSEC_PER_USEC) || - nla_put_u32(skb, TCA_PIE_LIMIT, sch->limit) || + nla_put_u32(skb, TCA_PIE_LIMIT, READ_ONCE(sch->limit)) || nla_put_u32(skb, TCA_PIE_TUPDATE, - jiffies_to_usecs(q->params.tupdate)) || - nla_put_u32(skb, TCA_PIE_ALPHA, q->params.alpha) || - nla_put_u32(skb, TCA_PIE_BETA, q->params.beta) || + jiffies_to_usecs(READ_ONCE(q->params.tupdate))) || + nla_put_u32(skb, TCA_PIE_ALPHA, READ_ONCE(q->params.alpha)) || + nla_put_u32(skb, TCA_PIE_BETA, READ_ONCE(q->params.beta)) || nla_put_u32(skb, TCA_PIE_ECN, q->params.ecn) || - nla_put_u32(skb, TCA_PIE_BYTEMODE, q->params.bytemode) || + nla_put_u32(skb, TCA_PIE_BYTEMODE, + READ_ONCE(q->params.bytemode)) || nla_put_u32(skb, TCA_PIE_DQ_RATE_ESTIMATOR, - q->params.dq_rate_estimator)) + READ_ONCE(q->params.dq_rate_estimator))) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index e66f4afb920d..3b9245a3c767 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -608,6 +608,7 @@ static void sfq_perturbation(struct timer_list *t) struct Qdisc *sch = q->sch; spinlock_t *root_lock; siphash_key_t nkey; + int period; get_random_bytes(&nkey, sizeof(nkey)); rcu_read_lock(); @@ -618,8 +619,12 @@ static void sfq_perturbation(struct timer_list *t) sfq_rehash(sch); spin_unlock(root_lock); - if (q->perturb_period) - mod_timer(&q->perturb_timer, jiffies + q->perturb_period); + /* q->perturb_period can change under us from + * sfq_change() and sfq_destroy(). + */ + period = READ_ONCE(q->perturb_period); + if (period) + mod_timer(&q->perturb_timer, jiffies + period); rcu_read_unlock(); } @@ -662,7 +667,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) q->quantum = ctl->quantum; q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); } - q->perturb_period = ctl->perturb_period * HZ; + WRITE_ONCE(q->perturb_period, ctl->perturb_period * HZ); if (ctl->flows) q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) { @@ -724,7 +729,7 @@ static void sfq_destroy(struct Qdisc *sch) struct sfq_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); - q->perturb_period = 0; + WRITE_ONCE(q->perturb_period, 0); del_timer_sync(&q->perturb_timer); sfq_free(q->ht); sfq_free(q->slots); diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index b4dd626c309c..20ff7386b74b 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -79,7 +79,9 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, prio = min(skb->priority, max_priority); qdisc = &q->qdiscs[prio]; - if (sch->q.qlen < sch->limit) { + + /* sch->limit can change under us from skbprio_change() */ + if (sch->q.qlen < READ_ONCE(sch->limit)) { __skb_queue_tail(qdisc, skb); qdisc_qstats_backlog_inc(sch, skb); q->qstats[prio].backlog += qdisc_pkt_len(skb); @@ -172,7 +174,7 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, if (opt->nla_len != nla_attr_size(sizeof(*ctl))) return -EINVAL; - sch->limit = ctl->limit; + WRITE_ONCE(sch->limit, ctl->limit); return 0; } @@ -200,7 +202,7 @@ static int skbprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct tc_skbprio_qopt opt; - opt.limit = sch->limit; + opt.limit = READ_ONCE(sch->limit); if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) return -1; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 0b150b13bee7..b284a06b5a75 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1749,10 +1749,7 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, fp[tc] = q->fp[tc]; } - nla_for_each_nested(n, opt, rem) { - if (nla_type(n) != TCA_TAPRIO_ATTR_TC_ENTRY) - continue; - + nla_for_each_nested_type(n, TCA_TAPRIO_ATTR_TC_ENTRY, opt, rem) { err = taprio_parse_tc_entry(sch, n, max_sdu, fp, &seen_tcs, extack); if (err) diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 59304611dc00..8badec6d82a2 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -78,7 +78,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) struct net_device *dev = qdisc_dev(sch); struct teql_sched_data *q = qdisc_priv(sch); - if (q->q.qlen < dev->tx_queue_len) { + if (q->q.qlen < READ_ONCE(dev->tx_queue_len)) { __skb_queue_tail(&q->q, skb); return NET_XMIT_SUCCESS; } @@ -424,7 +424,7 @@ static int teql_master_mtu(struct net_device *dev, int new_mtu) } while ((q = NEXT_SLAVE(q)) != m->slaves); } - dev->mtu = new_mtu; + WRITE_ONCE(dev->mtu, new_mtu); return 0; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 17fcaa9b0df9..a8a254a5008e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; + int err = 0; ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; - int cnt = 0, err = 1; + int cnt = 0; + + err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; @@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) - return err; + goto out; break; } else if (err < 0) { - return err; + goto out; } } if (err) { err = reuseport_alloc(sk, any); if (err) - return err; + goto out; } } - write_lock(&head->lock); hlist_add_head(&ep->node, &head->chain); +out: write_unlock(&head->lock); - return 0; + return err; } /* Add an endpoint to the hash. Local BH-safe. */ @@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - - write_lock(&head->lock); hlist_del_init(&ep->node); write_unlock(&head->lock); } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 08fdf1251f46..7d315a18612b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -38,6 +38,7 @@ #include <linux/inet.h> #include <linux/slab.h> #include <net/sock.h> +#include <net/proto_memory.h> #include <net/inet_ecn.h> #include <linux/skbuff.h> #include <net/sctp/sctp.h> @@ -2259,12 +2260,6 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } } - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; @@ -2273,6 +2268,22 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( */ action = sctp_tietags_compare(new_asoc, asoc); + /* In cases C and E the association doesn't enter the ESTABLISHED + * state, so there is no need to call security_sctp_assoc_request(). + */ + switch (action) { + case 'A': /* Association restart. */ + case 'B': /* Collision case B. */ + case 'D': /* Collision case D. */ + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request((struct sctp_association *)asoc, + chunk->head_skb ?: chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + break; + } + switch (action) { case 'A': /* Association restart. */ retval = sctp_sf_do_dupcook_a(net, ep, asoc, chunk, commands, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c67679a41044..c009383369b2 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4847,7 +4847,7 @@ static int sctp_disconnect(struct sock *sk, int flags) * descriptor will be returned from accept() to represent the newly * formed association. */ -static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) +static struct sock *sctp_accept(struct sock *sk, struct proto_accept_arg *arg) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -4871,7 +4871,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) goto out; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); error = sctp_wait_for_accept(sk, timeo); if (error) @@ -4882,7 +4882,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) */ asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); - newsk = sp->pf->create_accept_sk(sk, asoc, kern); + newsk = sp->pf->create_accept_sk(sk, asoc, arg->kern); if (!newsk) { error = -ENOMEM; goto out; @@ -4899,7 +4899,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) out: release_sock(sk); - *err = error; + arg->err = error; return newsk; } @@ -7119,6 +7119,7 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_assoc_ids *ids; + size_t ids_size; u32 num = 0; if (sctp_style(sk, TCP)) @@ -7131,11 +7132,11 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, num++; } - if (len < sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num) + ids_size = struct_size(ids, gaids_assoc_id, num); + if (len < ids_size) return -EINVAL; - len = sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num; - + len = ids_size; ids = kmalloc(len, GFP_USER | __GFP_NOWARN); if (unlikely(!ids)) return -ENOMEM; @@ -9276,7 +9277,7 @@ void sctp_data_ready(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index f65d6f92afcb..61c6f3027e7f 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -80,8 +80,6 @@ static struct ctl_table sctp_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - - { /* sentinel */ } }; /* The following index defines are used in sctp_sysctl_net_register(). @@ -384,8 +382,6 @@ static struct ctl_table sctp_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = &pf_expose_max, }, - - { /* sentinel */ } }; static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, @@ -597,6 +593,7 @@ static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, int sctp_sysctl_net_register(struct net *net) { + size_t table_size = ARRAY_SIZE(sctp_net_table); struct ctl_table *table; int i; @@ -604,7 +601,7 @@ int sctp_sysctl_net_register(struct net *net) if (!table) return -ENOMEM; - for (i = 0; table[i].data; i++) + for (i = 0; i < table_size; i++) table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; table[SCTP_RTO_MIN_IDX].extra2 = &net->sctp.rto_max; @@ -613,8 +610,7 @@ int sctp_sysctl_net_register(struct net *net) table[SCTP_PS_RETRANS_IDX].extra1 = &net->sctp.pf_retrans; net->sctp.sysctl_header = register_net_sysctl_sz(net, "net/sctp", - table, - ARRAY_SIZE(sctp_net_table)); + table, table_size); if (net->sctp.sysctl_header == NULL) { kfree(table); return -ENOMEM; @@ -624,7 +620,7 @@ int sctp_sysctl_net_register(struct net *net) void sctp_sysctl_net_unregister(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->sctp.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->sctp.sysctl_header); diff --git a/net/smc/Kconfig b/net/smc/Kconfig index 746be3996768..ba5e6a2dd2fd 100644 --- a/net/smc/Kconfig +++ b/net/smc/Kconfig @@ -20,3 +20,16 @@ config SMC_DIAG smcss. if unsure, say Y. + +config SMC_LO + bool "SMC intra-OS shortcut with loopback-ism" + depends on SMC + default n + help + SMC_LO enables the creation of an Emulated-ISM device named + loopback-ism in SMC and makes use of it for transferring data + when communication occurs within the same OS. This helps in + convenient testing of SMC-D since loopback-ism is independent + of architecture or hardware. + + if unsure, say N. diff --git a/net/smc/Makefile b/net/smc/Makefile index 875efcd126a2..2c510d543058 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -6,3 +6,4 @@ smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o smc-y += smc_tracepoint.o smc-$(CONFIG_SYSCTL) += smc_sysctl.o +smc-$(CONFIG_SMC_LO) += smc_loopback.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5f9f3d4c1df5..c5f98c6b2561 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -53,6 +53,7 @@ #include "smc_stats.h" #include "smc_tracepoint.h" #include "smc_sysctl.h" +#include "smc_loopback.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -177,7 +178,7 @@ static struct smc_hashinfo smc_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock), }; -int smc_hash_sk(struct sock *sk) +static int smc_hash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; struct hlist_head *head; @@ -191,9 +192,8 @@ int smc_hash_sk(struct sock *sk) return 0; } -EXPORT_SYMBOL_GPL(smc_hash_sk); -void smc_unhash_sk(struct sock *sk) +static void smc_unhash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; @@ -202,7 +202,6 @@ void smc_unhash_sk(struct sock *sk) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); write_unlock_bh(&h->lock); } -EXPORT_SYMBOL_GPL(smc_unhash_sk); /* This will be called before user really release sock_lock. So do the * work which we didn't do because of user hold the sock_lock in the @@ -1419,6 +1418,14 @@ static int smc_connect_ism(struct smc_sock *smc, } smc_conn_save_peer_info(smc, aclc); + + if (smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd)) { + rc = smcd_buf_attach(smc); + if (rc) { + rc = SMC_CLC_DECL_MEM; /* try to fallback */ + goto connect_abort; + } + } smc_close_init(smc); smc_rx_init(smc); smc_tx_init(smc); @@ -2523,6 +2530,14 @@ static void smc_listen_work(struct work_struct *work) mutex_unlock(&smc_server_lgr_pending); } smc_conn_save_peer_info(new_smc, cclc); + + if (ini->is_smcd && + smc_ism_support_dmb_nocopy(new_smc->conn.lgr->smcd)) { + rc = smcd_buf_attach(new_smc); + if (rc) + goto out_decl; + } + smc_listen_out_connected(new_smc); SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); goto out_free; @@ -2656,7 +2671,7 @@ out: } static int smc_accept(struct socket *sock, struct socket *new_sock, - int flags, bool kern) + struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); @@ -2675,7 +2690,7 @@ static int smc_accept(struct socket *sock, struct socket *new_sock, } /* Wait for an incoming connection */ - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); add_wait_queue_exclusive(sk_sleep(sk), &wait); while (!(nsk = smc_accept_dequeue(sk, new_sock))) { set_current_state(TASK_INTERRUPTIBLE); @@ -2702,7 +2717,7 @@ static int smc_accept(struct socket *sock, struct socket *new_sock, if (rc) goto out; - if (lsmc->sockopt_defer_accept && !(flags & O_NONBLOCK)) { + if (lsmc->sockopt_defer_accept && !(arg->flags & O_NONBLOCK)) { /* wait till data arrives on the socket */ timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept * MSEC_PER_SEC); @@ -3539,15 +3554,23 @@ static int __init smc_init(void) goto out_sock; } + rc = smc_loopback_init(); + if (rc) { + pr_err("%s: smc_loopback_init fails with %d\n", __func__, rc); + goto out_ib; + } + rc = tcp_register_ulp(&smc_ulp_ops); if (rc) { pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); - goto out_ib; + goto out_lo; } static_branch_enable(&tcp_have_smc); return 0; +out_lo: + smc_loopback_exit(); out_ib: smc_ib_unregister_client(); out_sock: @@ -3585,6 +3608,7 @@ static void __exit smc_exit(void) tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); + smc_loopback_exit(); smc_ib_unregister_client(); smc_ism_exit(); destroy_workqueue(smc_close_wq); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 3c06625ceb20..619b3bab3824 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -18,6 +18,7 @@ #include "smc_tx.h" #include "smc_rx.h" #include "smc_close.h" +#include "smc_ism.h" /********************************** send *************************************/ @@ -255,6 +256,14 @@ int smcd_cdc_msg_send(struct smc_connection *conn) return rc; smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn); conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0; + + if (smc_ism_support_dmb_nocopy(conn->lgr->smcd)) + /* if local sndbuf shares the same memory region with + * peer DMB, then don't update the tx_curs_fin + * and sndbuf_space until peer has consumed the data. + */ + return 0; + /* Calculate transmitted data and increment free send buffer space */ diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin, &conn->tx_curs_sent); @@ -266,7 +275,7 @@ int smcd_cdc_msg_send(struct smc_connection *conn) smc_curs_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn); smc_tx_sndbuf_nonfull(smc); - return rc; + return 0; } /********************************* receive ***********************************/ @@ -323,7 +332,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, { union smc_host_cursor cons_old, prod_old; struct smc_connection *conn = &smc->conn; - int diff_cons, diff_prod; + int diff_cons, diff_prod, diff_tx; smc_curs_copy(&prod_old, &conn->local_rx_ctrl.prod, conn); smc_curs_copy(&cons_old, &conn->local_rx_ctrl.cons, conn); @@ -339,6 +348,29 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, atomic_add(diff_cons, &conn->peer_rmbe_space); /* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */ smp_mb__after_atomic(); + + /* if local sndbuf shares the same memory region with + * peer RMB, then update tx_curs_fin and sndbuf_space + * here since peer has already consumed the data. + */ + if (conn->lgr->is_smcd && + smc_ism_support_dmb_nocopy(conn->lgr->smcd)) { + /* Calculate consumed data and + * increment free send buffer space. + */ + diff_tx = smc_curs_diff(conn->sndbuf_desc->len, + &conn->tx_curs_fin, + &conn->local_rx_ctrl.cons); + /* increase local sndbuf space and fin_curs */ + smp_mb__before_atomic(); + atomic_add(diff_tx, &conn->sndbuf_space); + /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ + smp_mb__after_atomic(); + smc_curs_copy(&conn->tx_curs_fin, + &conn->local_rx_ctrl.cons, conn); + + smc_tx_sndbuf_nonfull(smc); + } } diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old, diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index e55026c7529c..33fa787c28eb 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -853,8 +853,10 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) pclc_smcd = &pclc->pclc_smcd; pclc_prfx = &pclc->pclc_prfx; ipv6_prfx = pclc->pclc_prfx_ipv6; - v2_ext = &pclc->pclc_v2_ext; - smcd_v2_ext = &pclc->pclc_smcd_v2_ext; + v2_ext = container_of(&pclc->pclc_v2_ext, + struct smc_clc_v2_extension, fixed); + smcd_v2_ext = container_of(&pclc->pclc_smcd_v2_ext, + struct smc_clc_smcd_v2_extension, fixed); gidchids = pclc->pclc_gidchids; trl = &pclc->pclc_trl; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 7cc7070b9772..467effb50cd6 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -134,12 +134,15 @@ struct smc_clc_smcd_gid_chid { */ struct smc_clc_v2_extension { - struct smc_clnt_opts_area_hdr hdr; - u8 roce[16]; /* RoCEv2 GID */ - u8 max_conns; - u8 max_links; - __be16 feature_mask; - u8 reserved[12]; + /* New members must be added within the struct_group() macro below. */ + struct_group_tagged(smc_clc_v2_extension_fixed, fixed, + struct smc_clnt_opts_area_hdr hdr; + u8 roce[16]; /* RoCEv2 GID */ + u8 max_conns; + u8 max_links; + __be16 feature_mask; + u8 reserved[12]; + ); u8 user_eids[][SMC_MAX_EID_LEN]; }; @@ -159,8 +162,11 @@ struct smc_clc_msg_smcd { /* SMC-D GID information */ }; struct smc_clc_smcd_v2_extension { - u8 system_eid[SMC_MAX_EID_LEN]; - u8 reserved[16]; + /* New members must be added within the struct_group() macro below. */ + struct_group_tagged(smc_clc_smcd_v2_extension_fixed, fixed, + u8 system_eid[SMC_MAX_EID_LEN]; + u8 reserved[16]; + ); struct smc_clc_smcd_gid_chid gidchid[]; }; @@ -183,9 +189,9 @@ struct smc_clc_msg_proposal_area { struct smc_clc_msg_smcd pclc_smcd; struct smc_clc_msg_proposal_prefix pclc_prfx; struct smc_clc_ipv6_prefix pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX]; - struct smc_clc_v2_extension pclc_v2_ext; + struct smc_clc_v2_extension_fixed pclc_v2_ext; u8 user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN]; - struct smc_clc_smcd_v2_extension pclc_smcd_v2_ext; + struct smc_clc_smcd_v2_extension_fixed pclc_smcd_v2_ext; struct smc_clc_smcd_gid_chid pclc_gidchids[SMCD_CLC_MAX_V2_GID_ENTRIES]; struct smc_clc_msg_trail pclc_trl; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 9b84d5897aa5..acca3b1a068f 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1149,6 +1149,20 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, } } +static void smcd_buf_detach(struct smc_connection *conn) +{ + struct smcd_dev *smcd = conn->lgr->smcd; + u64 peer_token = conn->peer_token; + + if (!conn->sndbuf_desc) + return; + + smc_ism_detach_dmb(smcd, peer_token); + + kfree(conn->sndbuf_desc); + conn->sndbuf_desc = NULL; +} + static void smc_buf_unuse(struct smc_connection *conn, struct smc_link_group *lgr) { @@ -1192,6 +1206,8 @@ void smc_conn_free(struct smc_connection *conn) if (lgr->is_smcd) { if (!list_empty(&lgr->list)) smc_ism_unset_conn(conn); + if (smc_ism_support_dmb_nocopy(lgr->smcd)) + smcd_buf_detach(conn); tasklet_kill(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); @@ -1445,6 +1461,8 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft) smc_sk_wake_ups(smc); if (conn->lgr->is_smcd) { smc_ism_unset_conn(conn); + if (smc_ism_support_dmb_nocopy(conn->lgr->smcd)) + smcd_buf_detach(conn); if (soft) tasklet_kill(&conn->rx_tsklet); else @@ -1997,7 +2015,6 @@ out: */ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { - const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE; u8 compressed; if (size <= SMC_BUF_MIN_SIZE) @@ -2007,9 +2024,11 @@ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) compressed = min_t(u8, ilog2(size) + 1, is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); +#ifdef CONFIG_ARCH_NO_SG_CHAIN if (!is_smcd && is_rmb) /* RMBs are backed by & limited to max size of scatterlists */ - compressed = min_t(u8, compressed, ilog2(max_scat >> 14)); + compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14)); +#endif return compressed; } @@ -2464,12 +2483,18 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) int rc; /* create send buffer */ + if (is_smcd && + smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd)) + goto create_rmb; + rc = __smc_buf_create(smc, is_smcd, false); if (rc) return rc; + +create_rmb: /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); - if (rc) { + if (rc && smc->conn.sndbuf_desc) { down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); up_write(&smc->conn.lgr->sndbufs_lock); @@ -2479,6 +2504,41 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) return rc; } +int smcd_buf_attach(struct smc_sock *smc) +{ + struct smc_connection *conn = &smc->conn; + struct smcd_dev *smcd = conn->lgr->smcd; + u64 peer_token = conn->peer_token; + struct smc_buf_desc *buf_desc; + int rc; + + buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); + if (!buf_desc) + return -ENOMEM; + + /* The ghost sndbuf_desc describes the same memory region as + * peer RMB. Its lifecycle is consistent with the connection's + * and it will be freed with the connections instead of the + * link group. + */ + rc = smc_ism_attach_dmb(smcd, peer_token, buf_desc); + if (rc) + goto free; + + smc->sk.sk_sndbuf = buf_desc->len; + buf_desc->cpu_addr = + (u8 *)buf_desc->cpu_addr + sizeof(struct smcd_cdc_msg); + buf_desc->len -= sizeof(struct smcd_cdc_msg); + conn->sndbuf_desc = buf_desc; + conn->sndbuf_desc->used = 1; + atomic_set(&conn->sndbuf_space, conn->sndbuf_desc->len); + return 0; + +free: + kfree(buf_desc); + return rc; +} + static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr) { int i; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 1f175376037b..d93cf51dbd7c 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -557,6 +557,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, void smc_smcd_terminate_all(struct smcd_dev *dev); void smc_smcr_terminate_all(struct smc_ib_device *smcibdev); int smc_buf_create(struct smc_sock *smc, bool is_smcd); +int smcd_buf_attach(struct smc_sock *smc); int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *link, struct smc_clc_msg_accept_confirm *clc); diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index ac88de2a06a0..84f98e18c7db 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -91,6 +91,11 @@ bool smc_ism_is_v2_capable(void) return smc_ism_v2_capable; } +void smc_ism_set_v2_capable(void) +{ + smc_ism_v2_capable = true; +} + /* Set a connection using this DMBE. */ void smc_ism_set_conn(struct smc_connection *conn) { @@ -126,6 +131,8 @@ int smc_ism_get_vlan(struct smcd_dev *smcd, unsigned short vlanid) if (!vlanid) /* No valid vlan id */ return -EINVAL; + if (!smcd->ops->add_vlan_id) + return -EOPNOTSUPP; /* create new vlan entry, in case we need it */ new_vlan = kzalloc(sizeof(*new_vlan), GFP_KERNEL); @@ -171,6 +178,8 @@ int smc_ism_put_vlan(struct smcd_dev *smcd, unsigned short vlanid) if (!vlanid) /* No valid vlan id */ return -EINVAL; + if (!smcd->ops->del_vlan_id) + return -EOPNOTSUPP; spin_lock_irqsave(&smcd->lock, flags); list_for_each_entry(vlan, &smcd->vlan, list) { @@ -222,7 +231,6 @@ int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc) int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, struct smc_buf_desc *dmb_desc) { -#if IS_ENABLED(CONFIG_ISM) struct smcd_dmb dmb; int rc; @@ -231,7 +239,7 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, dmb.sba_idx = dmb_desc->sba_idx; dmb.vlan_id = lgr->vlan_id; dmb.rgid = lgr->peer_gid.gid; - rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb, &smc_ism_client); + rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb, lgr->smcd->client); if (!rc) { dmb_desc->sba_idx = dmb.sba_idx; dmb_desc->token = dmb.dmb_tok; @@ -240,9 +248,46 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, dmb_desc->len = dmb.dmb_len; } return rc; -#else - return 0; -#endif +} + +bool smc_ism_support_dmb_nocopy(struct smcd_dev *smcd) +{ + /* for now only loopback-ism supports + * merging sndbuf with peer DMB to avoid + * data copies between them. + */ + return (smcd->ops->support_dmb_nocopy && + smcd->ops->support_dmb_nocopy(smcd)); +} + +int smc_ism_attach_dmb(struct smcd_dev *dev, u64 token, + struct smc_buf_desc *dmb_desc) +{ + struct smcd_dmb dmb; + int rc = 0; + + if (!dev->ops->attach_dmb) + return -EINVAL; + + memset(&dmb, 0, sizeof(dmb)); + dmb.dmb_tok = token; + rc = dev->ops->attach_dmb(dev, &dmb); + if (!rc) { + dmb_desc->sba_idx = dmb.sba_idx; + dmb_desc->token = dmb.dmb_tok; + dmb_desc->cpu_addr = dmb.cpu_addr; + dmb_desc->dma_addr = dmb.dma_addr; + dmb_desc->len = dmb.dmb_len; + } + return rc; +} + +int smc_ism_detach_dmb(struct smcd_dev *dev, u64 token) +{ + if (!dev->ops->detach_dmb) + return -EINVAL; + + return dev->ops->detach_dmb(dev, token); } static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd, @@ -322,6 +367,8 @@ static void smc_nl_prep_smcd_dev(struct smcd_dev_list *dev_list, list_for_each_entry(smcd, &dev_list->list, list) { if (num < snum) goto next; + if (smc_ism_is_loopback(smcd)) + goto next; if (smc_nl_handle_smcd_dev(smcd, skb, cb)) goto errout; next: @@ -372,7 +419,8 @@ static void smcd_handle_sw_event(struct smc_ism_event_work *wrk) smc_smcd_terminate(wrk->smcd, &peer_gid, ev_info.vlan_id); break; case ISM_EVENT_CODE_TESTLINK: /* Activity timer */ - if (ev_info.code == ISM_EVENT_REQUEST) { + if (ev_info.code == ISM_EVENT_REQUEST && + wrk->smcd->ops->signal_event) { ev_info.code = ISM_EVENT_RESPONSE; wrk->smcd->ops->signal_event(wrk->smcd, &peer_gid, @@ -436,7 +484,7 @@ static struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, static void smcd_register_dev(struct ism_dev *ism) { const struct smcd_ops *ops = ism_get_smcd_ops(); - struct smcd_dev *smcd; + struct smcd_dev *smcd, *fentry; if (!ops) return; @@ -446,20 +494,28 @@ static void smcd_register_dev(struct ism_dev *ism) if (!smcd) return; smcd->priv = ism; + smcd->client = &smc_ism_client; ism_set_priv(ism, &smc_ism_client, smcd); if (smc_pnetid_by_dev_port(&ism->pdev->dev, 0, smcd->pnetid)) smc_pnetid_by_table_smcd(smcd); + if (smcd->ops->supports_v2()) + smc_ism_set_v2_capable(); mutex_lock(&smcd_dev_list.mutex); - if (list_empty(&smcd_dev_list.list)) { - if (smcd->ops->supports_v2()) - smc_ism_v2_capable = true; - } - /* sort list: devices without pnetid before devices with pnetid */ - if (smcd->pnetid[0]) + /* sort list: + * - devices without pnetid before devices with pnetid; + * - loopback-ism always at the very beginning; + */ + if (!smcd->pnetid[0]) { + fentry = list_first_entry_or_null(&smcd_dev_list.list, + struct smcd_dev, list); + if (fentry && smc_ism_is_loopback(fentry)) + list_add(&smcd->list, &fentry->list); + else + list_add(&smcd->list, &smcd_dev_list.list); + } else { list_add_tail(&smcd->list, &smcd_dev_list.list); - else - list_add(&smcd->list, &smcd_dev_list.list); + } mutex_unlock(&smcd_dev_list.mutex); pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n", @@ -541,6 +597,8 @@ int smc_ism_signal_shutdown(struct smc_link_group *lgr) if (lgr->peer_shutdown) return 0; + if (!lgr->smcd->ops->signal_event) + return 0; memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE); ev_info.vlan_id = lgr->vlan_id; diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 165cd013404b..6763133dd8d0 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -48,10 +48,15 @@ int smc_ism_put_vlan(struct smcd_dev *dev, unsigned short vlan_id); int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size, struct smc_buf_desc *dmb_desc); int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); +bool smc_ism_support_dmb_nocopy(struct smcd_dev *smcd); +int smc_ism_attach_dmb(struct smcd_dev *dev, u64 token, + struct smc_buf_desc *dmb_desc); +int smc_ism_detach_dmb(struct smcd_dev *dev, u64 token); int smc_ism_signal_shutdown(struct smc_link_group *lgr); void smc_ism_get_system_eid(u8 **eid); u16 smc_ism_get_chid(struct smcd_dev *dev); bool smc_ism_is_v2_capable(void); +void smc_ism_set_v2_capable(void); int smc_ism_init(void); void smc_ism_exit(void); int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); @@ -84,4 +89,9 @@ static inline bool smc_ism_is_emulated(struct smcd_dev *smcd) return __smc_ism_is_emulated(chid); } +static inline bool smc_ism_is_loopback(struct smcd_dev *smcd) +{ + return (smcd->ops->get_chid(smcd) == 0xFFFF); +} + #endif diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c new file mode 100644 index 000000000000..3c5f64ca4115 --- /dev/null +++ b/net/smc/smc_loopback.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shared Memory Communications Direct over loopback-ism device. + * + * Functions for loopback-ism device. + * + * Copyright (c) 2024, Alibaba Inc. + * + * Author: Wen Gu <guwen@linux.alibaba.com> + * Tony Lu <tonylu@linux.alibaba.com> + * + */ + +#include <linux/device.h> +#include <linux/types.h> +#include <net/smc.h> + +#include "smc_cdc.h" +#include "smc_ism.h" +#include "smc_loopback.h" + +#define SMC_LO_V2_CAPABLE 0x1 /* loopback-ism acts as ISMv2 */ +#define SMC_LO_SUPPORT_NOCOPY 0x1 +#define SMC_DMA_ADDR_INVALID (~(dma_addr_t)0) + +static const char smc_lo_dev_name[] = "loopback-ism"; +static struct smc_lo_dev *lo_dev; + +static void smc_lo_generate_ids(struct smc_lo_dev *ldev) +{ + struct smcd_gid *lgid = &ldev->local_gid; + uuid_t uuid; + + uuid_gen(&uuid); + memcpy(&lgid->gid, &uuid, sizeof(lgid->gid)); + memcpy(&lgid->gid_ext, (u8 *)&uuid + sizeof(lgid->gid), + sizeof(lgid->gid_ext)); + + ldev->chid = SMC_LO_RESERVED_CHID; +} + +static int smc_lo_query_rgid(struct smcd_dev *smcd, struct smcd_gid *rgid, + u32 vid_valid, u32 vid) +{ + struct smc_lo_dev *ldev = smcd->priv; + + /* rgid should be the same as lgid */ + if (!ldev || rgid->gid != ldev->local_gid.gid || + rgid->gid_ext != ldev->local_gid.gid_ext) + return -ENETUNREACH; + return 0; +} + +static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, + void *client_priv) +{ + struct smc_lo_dmb_node *dmb_node, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + int sba_idx, rc; + + /* check space for new dmb */ + for_each_clear_bit(sba_idx, ldev->sba_idx_mask, SMC_LO_MAX_DMBS) { + if (!test_and_set_bit(sba_idx, ldev->sba_idx_mask)) + break; + } + if (sba_idx == SMC_LO_MAX_DMBS) + return -ENOSPC; + + dmb_node = kzalloc(sizeof(*dmb_node), GFP_KERNEL); + if (!dmb_node) { + rc = -ENOMEM; + goto err_bit; + } + + dmb_node->sba_idx = sba_idx; + dmb_node->len = dmb->dmb_len; + dmb_node->cpu_addr = kzalloc(dmb_node->len, GFP_KERNEL | + __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC); + if (!dmb_node->cpu_addr) { + rc = -ENOMEM; + goto err_node; + } + dmb_node->dma_addr = SMC_DMA_ADDR_INVALID; + refcount_set(&dmb_node->refcnt, 1); + +again: + /* add new dmb into hash table */ + get_random_bytes(&dmb_node->token, sizeof(dmb_node->token)); + write_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_node->token) { + if (tmp_node->token == dmb_node->token) { + write_unlock_bh(&ldev->dmb_ht_lock); + goto again; + } + } + hash_add(ldev->dmb_ht, &dmb_node->list, dmb_node->token); + write_unlock_bh(&ldev->dmb_ht_lock); + atomic_inc(&ldev->dmb_cnt); + + dmb->sba_idx = dmb_node->sba_idx; + dmb->dmb_tok = dmb_node->token; + dmb->cpu_addr = dmb_node->cpu_addr; + dmb->dma_addr = dmb_node->dma_addr; + dmb->dmb_len = dmb_node->len; + + return 0; + +err_node: + kfree(dmb_node); +err_bit: + clear_bit(sba_idx, ldev->sba_idx_mask); + return rc; +} + +static void __smc_lo_unregister_dmb(struct smc_lo_dev *ldev, + struct smc_lo_dmb_node *dmb_node) +{ + /* remove dmb from hash table */ + write_lock_bh(&ldev->dmb_ht_lock); + hash_del(&dmb_node->list); + write_unlock_bh(&ldev->dmb_ht_lock); + + clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask); + kvfree(dmb_node->cpu_addr); + kfree(dmb_node); + + if (atomic_dec_and_test(&ldev->dmb_cnt)) + wake_up(&ldev->ldev_release); +} + +static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) +{ + struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + + /* find dmb from hash table */ + read_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) { + if (tmp_node->token == dmb->dmb_tok) { + dmb_node = tmp_node; + break; + } + } + if (!dmb_node) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + read_unlock_bh(&ldev->dmb_ht_lock); + + if (refcount_dec_and_test(&dmb_node->refcnt)) + __smc_lo_unregister_dmb(ldev, dmb_node); + return 0; +} + +static int smc_lo_support_dmb_nocopy(struct smcd_dev *smcd) +{ + return SMC_LO_SUPPORT_NOCOPY; +} + +static int smc_lo_attach_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) +{ + struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + + /* find dmb_node according to dmb->dmb_tok */ + read_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) { + if (tmp_node->token == dmb->dmb_tok) { + dmb_node = tmp_node; + break; + } + } + if (!dmb_node) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + read_unlock_bh(&ldev->dmb_ht_lock); + + if (!refcount_inc_not_zero(&dmb_node->refcnt)) + /* the dmb is being unregistered, but has + * not been removed from the hash table. + */ + return -EINVAL; + + /* provide dmb information */ + dmb->sba_idx = dmb_node->sba_idx; + dmb->dmb_tok = dmb_node->token; + dmb->cpu_addr = dmb_node->cpu_addr; + dmb->dma_addr = dmb_node->dma_addr; + dmb->dmb_len = dmb_node->len; + return 0; +} + +static int smc_lo_detach_dmb(struct smcd_dev *smcd, u64 token) +{ + struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + + /* find dmb_node according to dmb->dmb_tok */ + read_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, token) { + if (tmp_node->token == token) { + dmb_node = tmp_node; + break; + } + } + if (!dmb_node) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + read_unlock_bh(&ldev->dmb_ht_lock); + + if (refcount_dec_and_test(&dmb_node->refcnt)) + __smc_lo_unregister_dmb(ldev, dmb_node); + return 0; +} + +static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, + unsigned int idx, bool sf, unsigned int offset, + void *data, unsigned int size) +{ + struct smc_lo_dmb_node *rmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + struct smc_connection *conn; + + if (!sf) + /* since sndbuf is merged with peer DMB, there is + * no need to copy data from sndbuf to peer DMB. + */ + return 0; + + read_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_tok) { + if (tmp_node->token == dmb_tok) { + rmb_node = tmp_node; + break; + } + } + if (!rmb_node) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + memcpy((char *)rmb_node->cpu_addr + offset, data, size); + read_unlock_bh(&ldev->dmb_ht_lock); + + conn = smcd->conn[rmb_node->sba_idx]; + if (!conn || conn->killed) + return -EPIPE; + tasklet_schedule(&conn->rx_tsklet); + return 0; +} + +static int smc_lo_supports_v2(void) +{ + return SMC_LO_V2_CAPABLE; +} + +static void smc_lo_get_local_gid(struct smcd_dev *smcd, + struct smcd_gid *smcd_gid) +{ + struct smc_lo_dev *ldev = smcd->priv; + + smcd_gid->gid = ldev->local_gid.gid; + smcd_gid->gid_ext = ldev->local_gid.gid_ext; +} + +static u16 smc_lo_get_chid(struct smcd_dev *smcd) +{ + return ((struct smc_lo_dev *)smcd->priv)->chid; +} + +static struct device *smc_lo_get_dev(struct smcd_dev *smcd) +{ + return &((struct smc_lo_dev *)smcd->priv)->dev; +} + +static const struct smcd_ops lo_ops = { + .query_remote_gid = smc_lo_query_rgid, + .register_dmb = smc_lo_register_dmb, + .unregister_dmb = smc_lo_unregister_dmb, + .support_dmb_nocopy = smc_lo_support_dmb_nocopy, + .attach_dmb = smc_lo_attach_dmb, + .detach_dmb = smc_lo_detach_dmb, + .add_vlan_id = NULL, + .del_vlan_id = NULL, + .set_vlan_required = NULL, + .reset_vlan_required = NULL, + .signal_event = NULL, + .move_data = smc_lo_move_data, + .supports_v2 = smc_lo_supports_v2, + .get_local_gid = smc_lo_get_local_gid, + .get_chid = smc_lo_get_chid, + .get_dev = smc_lo_get_dev, +}; + +static struct smcd_dev *smcd_lo_alloc_dev(const struct smcd_ops *ops, + int max_dmbs) +{ + struct smcd_dev *smcd; + + smcd = kzalloc(sizeof(*smcd), GFP_KERNEL); + if (!smcd) + return NULL; + + smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *), + GFP_KERNEL); + if (!smcd->conn) + goto out_smcd; + + smcd->ops = ops; + + spin_lock_init(&smcd->lock); + spin_lock_init(&smcd->lgr_lock); + INIT_LIST_HEAD(&smcd->vlan); + INIT_LIST_HEAD(&smcd->lgr_list); + init_waitqueue_head(&smcd->lgrs_deleted); + return smcd; + +out_smcd: + kfree(smcd); + return NULL; +} + +static int smcd_lo_register_dev(struct smc_lo_dev *ldev) +{ + struct smcd_dev *smcd; + + smcd = smcd_lo_alloc_dev(&lo_ops, SMC_LO_MAX_DMBS); + if (!smcd) + return -ENOMEM; + ldev->smcd = smcd; + smcd->priv = ldev; + smc_ism_set_v2_capable(); + mutex_lock(&smcd_dev_list.mutex); + list_add(&smcd->list, &smcd_dev_list.list); + mutex_unlock(&smcd_dev_list.mutex); + pr_warn_ratelimited("smc: adding smcd device %s\n", + dev_name(&ldev->dev)); + return 0; +} + +static void smcd_lo_unregister_dev(struct smc_lo_dev *ldev) +{ + struct smcd_dev *smcd = ldev->smcd; + + pr_warn_ratelimited("smc: removing smcd device %s\n", + dev_name(&ldev->dev)); + smcd->going_away = 1; + smc_smcd_terminate_all(smcd); + mutex_lock(&smcd_dev_list.mutex); + list_del_init(&smcd->list); + mutex_unlock(&smcd_dev_list.mutex); + kfree(smcd->conn); + kfree(smcd); +} + +static int smc_lo_dev_init(struct smc_lo_dev *ldev) +{ + smc_lo_generate_ids(ldev); + rwlock_init(&ldev->dmb_ht_lock); + hash_init(ldev->dmb_ht); + atomic_set(&ldev->dmb_cnt, 0); + init_waitqueue_head(&ldev->ldev_release); + + return smcd_lo_register_dev(ldev); +} + +static void smc_lo_dev_exit(struct smc_lo_dev *ldev) +{ + smcd_lo_unregister_dev(ldev); + if (atomic_read(&ldev->dmb_cnt)) + wait_event(ldev->ldev_release, !atomic_read(&ldev->dmb_cnt)); +} + +static void smc_lo_dev_release(struct device *dev) +{ + struct smc_lo_dev *ldev = + container_of(dev, struct smc_lo_dev, dev); + + kfree(ldev); +} + +static int smc_lo_dev_probe(void) +{ + struct smc_lo_dev *ldev; + int ret; + + ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); + if (!ldev) + return -ENOMEM; + + ldev->dev.parent = NULL; + ldev->dev.release = smc_lo_dev_release; + device_initialize(&ldev->dev); + dev_set_name(&ldev->dev, smc_lo_dev_name); + + ret = smc_lo_dev_init(ldev); + if (ret) + goto free_dev; + + lo_dev = ldev; /* global loopback device */ + return 0; + +free_dev: + put_device(&ldev->dev); + return ret; +} + +static void smc_lo_dev_remove(void) +{ + if (!lo_dev) + return; + + smc_lo_dev_exit(lo_dev); + put_device(&lo_dev->dev); /* device_initialize in smc_lo_dev_probe */ +} + +int smc_loopback_init(void) +{ + return smc_lo_dev_probe(); +} + +void smc_loopback_exit(void) +{ + smc_lo_dev_remove(); +} diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h new file mode 100644 index 000000000000..6dd4292dae56 --- /dev/null +++ b/net/smc/smc_loopback.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications Direct over loopback-ism device. + * + * SMC-D loopback-ism device structure definitions. + * + * Copyright (c) 2024, Alibaba Inc. + * + * Author: Wen Gu <guwen@linux.alibaba.com> + * Tony Lu <tonylu@linux.alibaba.com> + * + */ + +#ifndef _SMC_LOOPBACK_H +#define _SMC_LOOPBACK_H + +#include <linux/device.h> +#include <linux/err.h> +#include <net/smc.h> + +#if IS_ENABLED(CONFIG_SMC_LO) +#define SMC_LO_MAX_DMBS 5000 +#define SMC_LO_DMBS_HASH_BITS 12 +#define SMC_LO_RESERVED_CHID 0xFFFF + +struct smc_lo_dmb_node { + struct hlist_node list; + u64 token; + u32 len; + u32 sba_idx; + void *cpu_addr; + dma_addr_t dma_addr; + refcount_t refcnt; +}; + +struct smc_lo_dev { + struct smcd_dev *smcd; + struct device dev; + u16 chid; + struct smcd_gid local_gid; + atomic_t dmb_cnt; + rwlock_t dmb_ht_lock; + DECLARE_BITMAP(sba_idx_mask, SMC_LO_MAX_DMBS); + DECLARE_HASHTABLE(dmb_ht, SMC_LO_DMBS_HASH_BITS); + wait_queue_head_t ldev_release; +}; + +int smc_loopback_init(void); +void smc_loopback_exit(void); +#else +static inline int smc_loopback_init(void) +{ + return 0; +} + +static inline void smc_loopback_exit(void) +{ +} +#endif + +#endif /* _SMC_LOOPBACK_H */ diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 9a2f3638d161..f0cbe77a80b4 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -42,10 +42,10 @@ static void smc_rx_wake_up(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN); if ((sk->sk_shutdown == SHUTDOWN_MASK) || (sk->sk_state == SMC_CLOSED)) - sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); + sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_HUP); rcu_read_unlock(); } diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index 9d32058db2b5..e19177ce4092 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -19,7 +19,7 @@ #include "smc_clc.h" -#define SMC_MAX_FBACK_RSN_CNT 30 +#define SMC_MAX_FBACK_RSN_CNT 36 enum { SMC_BUF_8K, diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index a5946d1b9d60..13f2bc092db1 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -90,11 +90,11 @@ static struct ctl_table smc_table[] = { .extra1 = &conns_per_lgr_min, .extra2 = &conns_per_lgr_max, }, - { } }; int __net_init smc_sysctl_net_init(struct net *net) { + size_t table_size = ARRAY_SIZE(smc_table); struct ctl_table *table; table = smc_table; @@ -105,12 +105,12 @@ int __net_init smc_sysctl_net_init(struct net *net) if (!table) goto err_alloc; - for (i = 0; i < ARRAY_SIZE(smc_table) - 1; i++) + for (i = 0; i < table_size; i++) table[i].data += (void *)net - (void *)&init_net; } net->smc.smc_hdr = register_net_sysctl_sz(net, "net/smc", table, - ARRAY_SIZE(smc_table)); + table_size); if (!net->smc.smc_hdr) goto err_reg; @@ -133,7 +133,7 @@ err_alloc: void __net_exit smc_sysctl_net_exit(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->smc.smc_hdr->ctl_table_arg; unregister_net_sysctl_table(net->smc.smc_hdr); diff --git a/net/smc/smc_tracepoint.h b/net/smc/smc_tracepoint.h index 9fc5e586d24a..a9a6e3c1113a 100644 --- a/net/smc/smc_tracepoint.h +++ b/net/smc/smc_tracepoint.h @@ -60,7 +60,7 @@ DECLARE_EVENT_CLASS(smc_msg_event, __entry->smc = smc; __entry->net_cookie = sock_net(sk)->net_cookie; __entry->len = len; - __assign_str(name, smc->conn.lnk->ibname); + __assign_str(name); ), TP_printk("smc=%p net=%llu len=%zu dev=%s", @@ -104,7 +104,7 @@ TRACE_EVENT(smcr_link_down, __entry->lgr = lgr; __entry->net_cookie = lgr->net->net_cookie; __entry->state = lnk->state; - __assign_str(name, lnk->ibname); + __assign_str(name); __entry->location = location; ), diff --git a/net/socket.c b/net/socket.c index e5f3af49a8b6..e416920e9399 100644 --- a/net/socket.c +++ b/net/socket.c @@ -88,7 +88,7 @@ #include <linux/xattr.h> #include <linux/nospec.h> #include <linux/indirect_call_wrapper.h> -#include <linux/io_uring.h> +#include <linux/io_uring/net.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -1890,7 +1890,7 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -struct file *do_accept(struct file *file, unsigned file_flags, +struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { @@ -1926,8 +1926,8 @@ struct file *do_accept(struct file *file, unsigned file_flags, if (err) goto out_fd; - err = ops->accept(sock, newsock, sock->file->f_flags | file_flags, - false); + arg->flags |= sock->file->f_flags; + err = ops->accept(sock, newsock, arg); if (err < 0) goto out_fd; @@ -1953,6 +1953,7 @@ out_fd: static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { + struct proto_accept_arg arg = { }; struct file *newfile; int newfd; @@ -1966,7 +1967,7 @@ static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_s if (unlikely(newfd < 0)) return newfd; - newfile = do_accept(file, 0, upeer_sockaddr, upeer_addrlen, + newfile = do_accept(file, &arg, upeer_sockaddr, upeer_addrlen, flags); if (IS_ERR(newfile)) { put_unused_fd(newfd); @@ -3580,6 +3581,10 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; const struct proto_ops *ops = READ_ONCE(sock->ops); + struct proto_accept_arg arg = { + .flags = flags, + .kern = true, + }; int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, @@ -3587,7 +3592,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) if (err < 0) goto done; - err = ops->accept(sock, *newsock, flags, true); + err = ops->accept(sock, *newsock, &arg); if (err < 0) { sock_release(*newsock); *newsock = NULL; diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h index c53b329092d4..4ebc1b7043d9 100644 --- a/net/sunrpc/auth_gss/auth_gss_internal.h +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -23,7 +23,7 @@ simple_get_bytes(const void *p, const void *end, void *res, size_t len) } static inline const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) +simple_get_netobj_noprof(const void *p, const void *end, struct xdr_netobj *dest) { const void *q; unsigned int len; @@ -35,7 +35,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); if (len) { - dest->data = kmemdup(p, len, GFP_KERNEL); + dest->data = kmemdup_noprof(p, len, GFP_KERNEL); if (unlikely(dest->data == NULL)) return ERR_PTR(-ENOMEM); } else @@ -43,3 +43,5 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) dest->len = len; return q; } + +#define simple_get_netobj(...) alloc_hooks(simple_get_netobj_noprof(__VA_ARGS__)) diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 06d8ee0db000..4eb19c3a54c7 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -168,7 +168,7 @@ static int krb5_DK(const struct gss_krb5_enctype *gk5e, goto err_return; blocksize = crypto_sync_skcipher_blocksize(cipher); if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len)) - goto err_return; + goto err_free_cipher; ret = -ENOMEM; inblockdata = kmalloc(blocksize, gfp_mask); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 59b2fbd88e5e..09f29a95f2bc 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2326,12 +2326,13 @@ call_transmit_status(struct rpc_task *task) task->tk_action = call_transmit; task->tk_status = 0; break; - case -ECONNREFUSED: case -EHOSTDOWN: case -ENETDOWN: case -EHOSTUNREACH: case -ENETUNREACH: case -EPERM: + break; + case -ECONNREFUSED: if (RPC_IS_SOFTCONN(task)) { if (!task->tk_msg.rpc_proc->p_proc) trace_xprt_ping(task->tk_xprt, @@ -2699,8 +2700,19 @@ rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr) goto out_msg_denied; error = rpcauth_checkverf(task, xdr); - if (error) + if (error) { + struct rpc_cred *cred = task->tk_rqstp->rq_cred; + + if (!test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags)) { + rpcauth_invalcred(task); + if (!task->tk_cred_retry) + goto out_err; + task->tk_cred_retry--; + trace_rpc__stale_creds(task); + return -EKEYREJECTED; + } goto out_verifier; + } p = xdr_inline_decode(xdr, sizeof(*p)); if (!p) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6debf4fd42d4..cef623ea1506 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -369,8 +369,10 @@ static void rpc_make_runnable(struct workqueue_struct *wq, if (RPC_IS_ASYNC(task)) { INIT_WORK(&task->u.tk_work, rpc_async_schedule); queue_work(wq, &task->u.tk_work); - } else + } else { + smp_mb__after_atomic(); wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED); + } } /* diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 2b4b1276d4e8..d9cda1e53a01 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1557,9 +1557,11 @@ out_drop: */ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) { + struct rpc_timeout timeout = { + .to_increment = 0, + }; struct rpc_task *task; int proc_error; - struct rpc_timeout timeout; /* Build the svc_rqst used by the common processing routine */ rqstp->rq_xid = req->rq_xid; @@ -1612,6 +1614,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) timeout.to_initval = req->rq_xprt->timeout->to_initval; timeout.to_retries = req->rq_xprt->timeout->to_retries; } + timeout.to_maxval = timeout.to_initval; memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); task = rpc_run_bc_task(req, &timeout); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b4a85a227bd7..dd86d7f1e97e 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -46,7 +46,6 @@ static LIST_HEAD(svc_xprt_class_list); /* SMP locking strategy: * - * svc_pool->sp_lock protects most of the fields of that pool. * svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt. * when both need to be taken (rare), svc_serv->sv_lock is first. * The "service mutex" protects svc_serv->sv_nrthread. @@ -211,51 +210,6 @@ void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl, } EXPORT_SYMBOL_GPL(svc_xprt_init); -static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, - struct svc_serv *serv, - struct net *net, - const int family, - const unsigned short port, - int flags) -{ - struct sockaddr_in sin = { - .sin_family = AF_INET, - .sin_addr.s_addr = htonl(INADDR_ANY), - .sin_port = htons(port), - }; -#if IS_ENABLED(CONFIG_IPV6) - struct sockaddr_in6 sin6 = { - .sin6_family = AF_INET6, - .sin6_addr = IN6ADDR_ANY_INIT, - .sin6_port = htons(port), - }; -#endif - struct svc_xprt *xprt; - struct sockaddr *sap; - size_t len; - - switch (family) { - case PF_INET: - sap = (struct sockaddr *)&sin; - len = sizeof(sin); - break; -#if IS_ENABLED(CONFIG_IPV6) - case PF_INET6: - sap = (struct sockaddr *)&sin6; - len = sizeof(sin6); - break; -#endif - default: - return ERR_PTR(-EAFNOSUPPORT); - } - - xprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags); - if (IS_ERR(xprt)) - trace_svc_xprt_create_err(serv->sv_program->pg_name, - xcl->xcl_name, sap, len, xprt); - return xprt; -} - /** * svc_xprt_received - start next receiver thread * @xprt: controlling transport @@ -294,9 +248,8 @@ void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new) } static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, - struct net *net, const int family, - const unsigned short port, int flags, - const struct cred *cred) + struct net *net, struct sockaddr *sap, + size_t len, int flags, const struct cred *cred) { struct svc_xprt_class *xcl; @@ -312,8 +265,11 @@ static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, goto err; spin_unlock(&svc_xprt_class_lock); - newxprt = __svc_xpo_create(xcl, serv, net, family, port, flags); + newxprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags); if (IS_ERR(newxprt)) { + trace_svc_xprt_create_err(serv->sv_program->pg_name, + xcl->xcl_name, sap, len, + newxprt); module_put(xcl->xcl_owner); return PTR_ERR(newxprt); } @@ -330,6 +286,48 @@ static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, } /** + * svc_xprt_create_from_sa - Add a new listener to @serv from socket address + * @serv: target RPC service + * @xprt_name: transport class name + * @net: network namespace + * @sap: socket address pointer + * @flags: SVC_SOCK flags + * @cred: credential to bind to this transport + * + * Return local xprt port on success or %-EPROTONOSUPPORT on failure + */ +int svc_xprt_create_from_sa(struct svc_serv *serv, const char *xprt_name, + struct net *net, struct sockaddr *sap, + int flags, const struct cred *cred) +{ + size_t len; + int err; + + switch (sap->sa_family) { + case AF_INET: + len = sizeof(struct sockaddr_in); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + len = sizeof(struct sockaddr_in6); + break; +#endif + default: + return -EAFNOSUPPORT; + } + + err = _svc_xprt_create(serv, xprt_name, net, sap, len, flags, cred); + if (err == -EPROTONOSUPPORT) { + request_module("svc%s", xprt_name); + err = _svc_xprt_create(serv, xprt_name, net, sap, len, flags, + cred); + } + + return err; +} +EXPORT_SYMBOL_GPL(svc_xprt_create_from_sa); + +/** * svc_xprt_create - Add a new listener to @serv * @serv: target RPC service * @xprt_name: transport class name @@ -339,23 +337,41 @@ static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, * @flags: SVC_SOCK flags * @cred: credential to bind to this transport * - * Return values: - * %0: New listener added successfully - * %-EPROTONOSUPPORT: Requested transport type not supported + * Return local xprt port on success or %-EPROTONOSUPPORT on failure */ int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, struct net *net, const int family, const unsigned short port, int flags, const struct cred *cred) { - int err; + struct sockaddr_in sin = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_ANY), + .sin_port = htons(port), + }; +#if IS_ENABLED(CONFIG_IPV6) + struct sockaddr_in6 sin6 = { + .sin6_family = AF_INET6, + .sin6_addr = IN6ADDR_ANY_INIT, + .sin6_port = htons(port), + }; +#endif + struct sockaddr *sap; - err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred); - if (err == -EPROTONOSUPPORT) { - request_module("svc%s", xprt_name); - err = _svc_xprt_create(serv, xprt_name, net, family, port, flags, cred); + switch (family) { + case PF_INET: + sap = (struct sockaddr *)&sin; + break; +#if IS_ENABLED(CONFIG_IPV6) + case PF_INET6: + sap = (struct sockaddr *)&sin6; + break; +#endif + default: + return -EAFNOSUPPORT; } - return err; + + return svc_xprt_create_from_sa(serv, xprt_name, net, sap, flags, cred); } EXPORT_SYMBOL_GPL(svc_xprt_create); @@ -1260,6 +1276,40 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) } /** + * svc_find_listener - find an RPC transport instance + * @serv: pointer to svc_serv to search + * @xcl_name: C string containing transport's class name + * @net: owner net pointer + * @sa: sockaddr containing address + * + * Return the transport instance pointer for the endpoint accepting + * connections/peer traffic from the specified transport class, + * and matching sockaddr. + */ +struct svc_xprt *svc_find_listener(struct svc_serv *serv, const char *xcl_name, + struct net *net, const struct sockaddr *sa) +{ + struct svc_xprt *xprt; + struct svc_xprt *found = NULL; + + spin_lock_bh(&serv->sv_lock); + list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) { + if (xprt->xpt_net != net) + continue; + if (strcmp(xprt->xpt_class->xcl_name, xcl_name)) + continue; + if (!rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local)) + continue; + found = xprt; + svc_xprt_get(xprt); + break; + } + spin_unlock_bh(&serv->sv_lock); + return found; +} +EXPORT_SYMBOL_GPL(svc_find_listener); + +/** * svc_find_xprt - find an RPC transport instance * @serv: pointer to svc_serv to search * @xcl_name: C string containing transport's class name diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 93941ab12549..5f3170a1c9bb 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -160,7 +160,6 @@ static struct ctl_table debug_table[] = { .mode = 0444, .proc_handler = proc_do_xprt, }, - { } }; void diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index ffbf99894970..47f33bb7bff8 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -92,7 +92,8 @@ static void frwr_mr_put(struct rpcrdma_mr *mr) rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs); } -/* frwr_reset - Place MRs back on the free list +/** + * frwr_reset - Place MRs back on @req's free list * @req: request to reset * * Used after a failed marshal. For FRWR, this means the MRs diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index f86970733eb0..474f7a98fe9e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -209,7 +209,6 @@ static struct ctl_table svcrdma_parm_table[] = { .extra1 = &zero, .extra2 = &zero, }, - { }, }; static void svc_rdma_proc_cleanup(void) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 29b0562d62e7..9a8ce5df83ca 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -137,7 +137,6 @@ static struct ctl_table xr_tunables_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { }, }; #endif diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 432557a553e7..a0b071089e15 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -897,6 +897,8 @@ static int rpcrdma_reqs_setup(struct rpcrdma_xprt *r_xprt) static void rpcrdma_req_reset(struct rpcrdma_req *req) { + struct rpcrdma_mr *mr; + /* Credits are valid for only one connection */ req->rl_slot.rq_cong = 0; @@ -906,7 +908,19 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req) rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); rpcrdma_regbuf_dma_unmap(req->rl_recvbuf); - frwr_reset(req); + /* The verbs consumer can't know the state of an MR on the + * req->rl_registered list unless a successful completion + * has occurred, so they cannot be re-used. + */ + while ((mr = rpcrdma_mr_pop(&req->rl_registered))) { + struct rpcrdma_buffer *buf = &mr->mr_xprt->rx_buf; + + spin_lock(&buf->rb_lock); + list_del(&mr->mr_all); + spin_unlock(&buf->rb_lock); + + frwr_mr_release(mr); + } } /* ASSUMPTION: the rb_allreqs list is stable for the duration, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ce18716491c8..0e1691316f42 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -160,7 +160,6 @@ static struct ctl_table xs_tunables_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { }, }; /* @@ -2442,6 +2441,13 @@ static void xs_tcp_setup_socket(struct work_struct *work) transport->srcport = 0; status = -EAGAIN; break; + case -EPERM: + /* Happens, for instance, if a BPF program is preventing + * the connect. Remap the error so upper layers can better + * deal with it. + */ + status = -ECONNREFUSED; + fallthrough; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index c9189a970eec..6488ead9e464 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -244,6 +244,99 @@ static int switchdev_port_obj_notify(enum switchdev_notifier_type nt, return 0; } +static void switchdev_obj_id_to_helpful_msg(struct net_device *dev, + enum switchdev_obj_id obj_id, + int err, bool add) +{ + const char *action = add ? "add" : "del"; + const char *reason = ""; + const char *problem; + const char *obj_str; + + switch (obj_id) { + case SWITCHDEV_OBJ_ID_UNDEFINED: + obj_str = "Undefined object"; + problem = "Attempted operation is undefined, indicating a possible programming\n" + "error.\n"; + break; + case SWITCHDEV_OBJ_ID_PORT_VLAN: + obj_str = "VLAN entry"; + problem = "Failure in VLAN settings on this port might disrupt network\n" + "segmentation or traffic isolation, affecting network partitioning.\n"; + break; + case SWITCHDEV_OBJ_ID_PORT_MDB: + obj_str = "Port Multicast Database entry"; + problem = "Failure in updating the port's Multicast Database could lead to\n" + "multicast forwarding issues.\n"; + break; + case SWITCHDEV_OBJ_ID_HOST_MDB: + obj_str = "Host Multicast Database entry"; + problem = "Failure in updating the host's Multicast Database may impact multicast\n" + "group memberships or traffic delivery, affecting multicast\n" + "communication.\n"; + break; + case SWITCHDEV_OBJ_ID_MRP: + obj_str = "Media Redundancy Protocol configuration for port"; + problem = "Failure to set MRP ring ID on this port prevents communication with\n" + "the specified redundancy ring, resulting in an inability to engage\n" + "in MRP-based network operations.\n"; + break; + case SWITCHDEV_OBJ_ID_RING_TEST_MRP: + obj_str = "MRP Test Frame Operations for port"; + problem = "Failure to generate/monitor MRP test frames may lead to inability to\n" + "assess the ring's operational integrity and fault response, hindering\n" + "proactive network management.\n"; + break; + case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: + obj_str = "MRP Ring Role Configuration"; + problem = "Improper MRP ring role configuration may create conflicts in the ring,\n" + "disrupting communication for all participants, or isolate the local\n" + "system from the ring, hindering its ability to communicate with other\n" + "participants.\n"; + break; + case SWITCHDEV_OBJ_ID_RING_STATE_MRP: + obj_str = "MRP Ring State Configuration"; + problem = "Failure to correctly set the MRP ring state can result in network\n" + "loops or leave segments without communication. In a Closed state,\n" + "it maintains loop prevention by blocking one MRM port, while an Open\n" + "state activates in response to failures, changing port states to\n" + "preserve network connectivity.\n"; + break; + case SWITCHDEV_OBJ_ID_IN_TEST_MRP: + obj_str = "MRP_InTest Frame Generation Configuration"; + problem = "Failure in managing MRP_InTest frame generation can misjudge the\n" + "interconnection ring's state, leading to incorrect blocking or\n" + "unblocking of the I/C port. This misconfiguration might result\n" + "in unintended network loops or isolate critical network segments,\n" + "compromising network integrity and reliability.\n"; + break; + case SWITCHDEV_OBJ_ID_IN_ROLE_MRP: + obj_str = "Interconnection Ring Role Configuration"; + problem = "Failure in incorrect assignment of interconnection ring roles\n" + "(MIM/MIC) can impair the formation of the interconnection rings.\n"; + break; + case SWITCHDEV_OBJ_ID_IN_STATE_MRP: + obj_str = "Interconnection Ring State Configuration"; + problem = "Failure in updating the interconnection ring state can lead in\n" + "case of Open state to incorrect blocking or unblocking of the\n" + "I/C port, resulting in unintended network loops or isolation\n" + "of critical network\n"; + break; + default: + obj_str = "Unknown object"; + problem = "Indicating a possible programming error.\n"; + } + + switch (err) { + case -ENOSPC: + reason = "Current HW/SW setup lacks sufficient resources.\n"; + break; + } + + netdev_err(dev, "Failed to %s %s (object id=%d) with error: %pe (%d).\n%s%s\n", + action, obj_str, obj_id, ERR_PTR(err), err, problem, reason); +} + static void switchdev_port_obj_add_deferred(struct net_device *dev, const void *data) { @@ -254,8 +347,7 @@ static void switchdev_port_obj_add_deferred(struct net_device *dev, err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD, dev, obj, NULL); if (err && err != -EOPNOTSUPP) - netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", - err, obj->id); + switchdev_obj_id_to_helpful_msg(dev, obj->id, err, true); if (obj->complete) obj->complete(dev, err, obj->complete_priv); } @@ -304,8 +396,7 @@ static void switchdev_port_obj_del_deferred(struct net_device *dev, err = switchdev_port_obj_del_now(dev, obj); if (err && err != -EOPNOTSUPP) - netdev_err(dev, "failed (err=%d) to del object (id=%d)\n", - err, obj->id); + switchdev_obj_id_to_helpful_msg(dev, obj->id, err, false); if (obj->complete) obj->complete(dev, err, obj->complete_priv); } diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 051ed5f6fc93..f5017012a049 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -40,7 +40,7 @@ static int is_seen(struct ctl_table_set *set) /* Return standard mode bits for table entry. */ static int net_ctl_permissions(struct ctl_table_header *head, - struct ctl_table *table) + const struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); @@ -54,7 +54,6 @@ static int net_ctl_permissions(struct ctl_table_header *head, } static void net_ctl_set_ownership(struct ctl_table_header *head, - struct ctl_table *table, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 7e4135db5816..2d58ecae4e21 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -146,8 +146,6 @@ static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); static int tipc_release(struct socket *sock); -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, - bool kern); static void tipc_sk_timeout(struct timer_list *t); static int tipc_sk_publish(struct tipc_sock *tsk, struct tipc_uaddr *ua); static int tipc_sk_withdraw(struct tipc_sock *tsk, struct tipc_uaddr *ua); @@ -2711,13 +2709,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * tipc_accept - wait for connection request * @sock: listening socket * @new_sock: new socket that is to be connected - * @flags: file-related flags associated with socket - * @kern: caused by kernel or by userspace? + * @arg: arguments for accept * * Return: 0 on success, errno otherwise */ -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, - bool kern) +static int tipc_accept(struct socket *sock, struct socket *new_sock, + struct proto_accept_arg *arg) { struct sock *new_sk, *sk = sock->sk; struct tipc_sock *new_tsock; @@ -2733,14 +2730,14 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, res = -EINVAL; goto exit; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); + timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); res = tipc_wait_for_accept(sock, timeo); if (res) goto exit; buf = skb_peek(&sk->sk_receive_queue); - res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern); + res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, arg->kern); if (res) goto exit; security_sk_clone(sock->sk, new_sock->sk); @@ -3565,11 +3562,8 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, rhashtable_walk_start(iter); while ((tsk = rhashtable_walk_next(iter)) != NULL) { if (IS_ERR(tsk)) { - err = PTR_ERR(tsk); - if (err == -EAGAIN) { - err = 0; + if (PTR_ERR(tsk) == -EAGAIN) continue; - } break; } diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c index 9fb65c988f7f..30d2e06e3d8c 100644 --- a/net/tipc/sysctl.c +++ b/net/tipc/sysctl.c @@ -91,7 +91,6 @@ static struct ctl_table tipc_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, - {} }; int tipc_register_sysctl(void) diff --git a/net/tipc/trace.h b/net/tipc/trace.h index 04af83f0500c..865142ed0ab4 100644 --- a/net/tipc/trace.h +++ b/net/tipc/trace.h @@ -145,7 +145,7 @@ DECLARE_EVENT_CLASS(tipc_skb_class, ), TP_fast_assign( - __assign_str(header, header); + __assign_str(header); tipc_skb_dump(skb, more, __get_str(buf)); ), @@ -172,7 +172,7 @@ DECLARE_EVENT_CLASS(tipc_list_class, ), TP_fast_assign( - __assign_str(header, header); + __assign_str(header); tipc_list_dump(list, more, __get_str(buf)); ), @@ -200,7 +200,7 @@ DECLARE_EVENT_CLASS(tipc_sk_class, ), TP_fast_assign( - __assign_str(header, header); + __assign_str(header); __entry->portid = tipc_sock_get_portid(sk); tipc_sk_dump(sk, dqueues, __get_str(buf)); if (skb) @@ -254,7 +254,7 @@ DECLARE_EVENT_CLASS(tipc_link_class, ), TP_fast_assign( - __assign_str(header, header); + __assign_str(header); memcpy(__entry->name, tipc_link_name(l), TIPC_MAX_LINK_NAME); tipc_link_dump(l, dqueues, __get_str(buf)); ), @@ -337,7 +337,7 @@ DECLARE_EVENT_CLASS(tipc_node_class, ), TP_fast_assign( - __assign_str(header, header); + __assign_str(header); __entry->addr = tipc_node_get_addr(n); tipc_node_dump(n, more, __get_str(buf)); ), @@ -374,7 +374,7 @@ DECLARE_EVENT_CLASS(tipc_fsm_class, ), TP_fast_assign( - __assign_str(name, name); + __assign_str(name); __entry->os = os; __entry->ns = ns; __entry->evt = evt; @@ -409,8 +409,8 @@ TRACE_EVENT(tipc_l2_device_event, ), TP_fast_assign( - __assign_str(dev_name, dev->name); - __assign_str(b_name, b->name); + __assign_str(dev_name); + __assign_str(b_name); __entry->evt = evt; __entry->b_up = test_bit(0, &b->up); __entry->carrier = netif_carrier_ok(dev); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b849a3d133a0..439f75539977 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -135,8 +135,11 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size) snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port)); else if (ntohs(ua->proto) == ETH_P_IPV6) snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port)); - else + else { pr_err("Invalid UDP media address\n"); + return 1; + } + return 0; } diff --git a/net/tls/Kconfig b/net/tls/Kconfig index 0cdc1f7b6b08..ce8d56a19187 100644 --- a/net/tls/Kconfig +++ b/net/tls/Kconfig @@ -20,6 +20,7 @@ config TLS config TLS_DEVICE bool "Transport Layer Security HW offload" depends on TLS + select SKB_DECRYPTED select SOCK_VALIDATE_XMIT select SOCK_RX_QUEUE_MAPPING default n diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bf8ed36b1ad6..ab6e694f7bc2 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -37,6 +37,7 @@ #include <net/inet_connection_sock.h> #include <net/tcp.h> #include <net/tls.h> +#include <linux/skbuff_ref.h> #include "tls.h" #include "trace.h" diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 4e7228f275fa..f9e3d3d90dcf 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -33,6 +33,7 @@ #include <crypto/aead.h> #include <crypto/scatterwalk.h> #include <net/ip6_checksum.h> +#include <linux/skbuff_ref.h> #include "tls.h" diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 5df08d848b5c..77e33e1e340e 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -2,6 +2,7 @@ /* Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #include <linux/skbuff.h> +#include <linux/skbuff_ref.h> #include <linux/workqueue.h> #include <net/strparser.h> #include <net/tcp.h> diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index b783231668c6..305a412785f5 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2147,7 +2147,6 @@ recv_end: if (ret) { if (err >= 0 || err == -EINPROGRESS) err = ret; - decrypted = 0; goto end; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 68a58bc07cf2..be5266007b48 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -540,7 +540,7 @@ static void unix_write_space(struct sock *sk) if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); - sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); + sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } @@ -749,7 +749,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int); static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); -static int unix_accept(struct socket *, struct socket *, int, bool); +static int unix_accept(struct socket *, struct socket *, struct proto_accept_arg *arg); static int unix_getname(struct socket *, struct sockaddr *, int); static __poll_t unix_poll(struct file *, struct socket *, poll_table *); static __poll_t unix_dgram_poll(struct file *, struct socket *, @@ -973,11 +973,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; u = unix_sk(sk); - u->inflight = 0; + u->listener = NULL; + u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); @@ -1473,6 +1473,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, struct unix_sock *u = unix_sk(sk), *newu, *otheru; struct net *net = sock_net(sk); struct sk_buff *skb = NULL; + unsigned char state; long timeo; int err; @@ -1523,7 +1524,6 @@ restart: goto out; } - /* Latch state of peer */ unix_state_lock(other); /* Apparently VFS overslept socket death. Retry. */ @@ -1553,37 +1553,21 @@ restart: goto restart; } - /* Latch our state. - - It is tricky place. We need to grab our state lock and cannot - drop lock on peer. It is dangerous because deadlock is - possible. Connect to self case and simultaneous - attempt to connect are eliminated by checking socket - state. other is TCP_LISTEN, if sk is TCP_LISTEN we - check this before attempt to grab lock. - - Well, and we have to recheck the state after socket locked. + /* self connect and simultaneous connect are eliminated + * by rejecting TCP_LISTEN socket to avoid deadlock. */ - switch (READ_ONCE(sk->sk_state)) { - case TCP_CLOSE: - /* This is ok... continue with connect */ - break; - case TCP_ESTABLISHED: - /* Socket is already connected */ - err = -EISCONN; - goto out_unlock; - default: - err = -EINVAL; + state = READ_ONCE(sk->sk_state); + if (unlikely(state != TCP_CLOSE)) { + err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; goto out_unlock; } unix_state_lock_nested(sk, U_LOCK_SECOND); - if (sk->sk_state != TCP_CLOSE) { + if (unlikely(sk->sk_state != TCP_CLOSE)) { + err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; unix_state_unlock(sk); - unix_state_unlock(other); - sock_put(other); - goto restart; + goto out_unlock; } err = security_unix_stream_connect(sk, other, newsk); @@ -1600,6 +1584,7 @@ restart: newsk->sk_type = sk->sk_type; init_peercred(newsk); newu = unix_sk(newsk); + newu->listener = other; RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); @@ -1691,19 +1676,18 @@ static void unix_sock_inherit_flags(const struct socket *old, set_bit(SOCK_PASSSEC, &new->flags); } -static int unix_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int unix_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk; - struct sock *tsk; struct sk_buff *skb; - int err; + struct sock *tsk; - err = -EOPNOTSUPP; + arg->err = -EOPNOTSUPP; if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto out; - err = -EINVAL; + arg->err = -EINVAL; if (READ_ONCE(sk->sk_state) != TCP_LISTEN) goto out; @@ -1711,12 +1695,12 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, * so that no locks are necessary. */ - skb = skb_recv_datagram(sk, (flags & O_NONBLOCK) ? MSG_DONTWAIT : 0, - &err); + skb = skb_recv_datagram(sk, (arg->flags & O_NONBLOCK) ? MSG_DONTWAIT : 0, + &arg->err); if (!skb) { /* This means receive shutdown. */ - if (err == 0) - err = -EINVAL; + if (arg->err == 0) + arg->err = -EINVAL; goto out; } @@ -1726,6 +1710,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, /* attach accepted sock to socket */ unix_state_lock(tsk); + unix_update_edges(unix_sk(tsk)); newsock->state = SS_CONNECTED; unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); @@ -1733,7 +1718,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, return 0; out: - return err; + return arg->err; } @@ -1792,81 +1777,29 @@ static inline bool too_many_unix_fds(struct task_struct *p) static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) { - int i; - if (too_many_unix_fds(current)) return -ETOOMANYREFS; - /* Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; + UNIXCB(skb).fp = scm->fp; + scm->fp = NULL; - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); + if (unix_prepare_fpl(UNIXCB(skb).fp)) + return -ENOMEM; return 0; } static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) { - int i; - scm->fp = UNIXCB(skb).fp; UNIXCB(skb).fp = NULL; - for (i = scm->fp->count - 1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); + unix_destroy_fpl(scm->fp); } static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); - - /* - * Garbage collection of unix sockets starts by selecting a set of - * candidate sockets which have reference only from being in flight - * (total_refs == inflight_refs). This condition is checked once during - * the candidate collection phase, and candidates are marked as such, so - * that non-candidates can later be ignored. While inflight_refs is - * protected by unix_gc_lock, total_refs (file count) is not, hence this - * is an instantaneous decision. - * - * Once a candidate, however, the socket must not be reinstalled into a - * file descriptor while the garbage collection is in progress. - * - * If the above conditions are met, then the directed graph of - * candidates (*) does not change while unix_gc_lock is held. - * - * Any operations that changes the file count through file descriptors - * (dup, close, sendmsg) does not change the graph since candidates are - * not installed in fds. - * - * Dequeing a candidate via recvmsg would install it into an fd, but - * that takes unix_gc_lock to decrement the inflight count, so it's - * serialized with garbage collection. - * - * MSG_PEEK is special in that it does not change the inflight count, - * yet does install the socket into an fd. The following lock/unlock - * pair is to ensure serialization with garbage collection. It must be - * done between incrementing the file count and installing the file into - * an fd. - * - * If garbage collection starts after the barrier provided by the - * lock/unlock, then it will see the elevated refcount and not mark this - * as a candidate. If a garbage collection is already in progress - * before the file count was incremented, then the lock/unlock pair will - * ensure that garbage collection is finished before progressing to - * installing the fd. - * - * (*) A -> B where B is on the queue of A or B is on the queue of C - * which is on the queue of listening socket A. - */ - spin_lock(&unix_gc_lock); - spin_unlock(&unix_gc_lock); } static void unix_destruct_scm(struct sk_buff *skb) @@ -1940,8 +1873,10 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_add(fp->count, &u->scm_stat.nr_fds); + unix_add_edges(fp, u); + } } static void scm_stat_del(struct sock *sk, struct sk_buff *skb) @@ -1949,8 +1884,10 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_sub(fp->count, &u->scm_stat.nr_fds); + unix_del_edges(fp); + } } /* @@ -2660,10 +2597,24 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, { struct unix_sock *u = unix_sk(sk); - if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) { - skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); - skb = NULL; + if (!unix_skb_len(skb)) { + struct sk_buff *unlinked_skb = NULL; + + spin_lock(&sk->sk_receive_queue.lock); + + if (copied && (!u->oob_skb || skb == u->oob_skb)) { + skb = NULL; + } else if (flags & MSG_PEEK) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); + } else { + unlinked_skb = skb; + skb = skb_peek_next(skb, &sk->sk_receive_queue); + __skb_unlink(unlinked_skb, &sk->sk_receive_queue); + } + + spin_unlock(&sk->sk_receive_queue.lock); + + consume_skb(unlinked_skb); } else { struct sk_buff *unlinked_skb = NULL; @@ -2700,10 +2651,49 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { + struct unix_sock *u = unix_sk(sk); + struct sk_buff *skb; + int err; + if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) return -ENOTCONN; - return unix_read_skb(sk, recv_actor); + mutex_lock(&u->iolock); + skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); + mutex_unlock(&u->iolock); + if (!skb) + return err; + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (unlikely(skb == READ_ONCE(u->oob_skb))) { + bool drop = false; + + unix_state_lock(sk); + + if (sock_flag(sk, SOCK_DEAD)) { + unix_state_unlock(sk); + kfree_skb(skb); + return -ECONNRESET; + } + + spin_lock(&sk->sk_receive_queue.lock); + if (likely(skb == u->oob_skb)) { + WRITE_ONCE(u->oob_skb, NULL); + drop = true; + } + spin_unlock(&sk->sk_receive_queue.lock); + + unix_state_unlock(sk); + + if (drop) { + WARN_ON_ONCE(skb_unref(skb)); + kfree_skb(skb); + return -EAGAIN; + } + } +#endif + + return recv_actor(sk, skb); } static int unix_stream_read_generic(struct unix_stream_read_state *state, @@ -3140,12 +3130,23 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) case SIOCATMARK: { + struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; int answ = 0; + mutex_lock(&u->iolock); + skb = skb_peek(&sk->sk_receive_queue); - if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb)) - answ = 1; + if (skb) { + struct sk_buff *oob_skb = READ_ONCE(u->oob_skb); + + if (skb == oob_skb || + (!oob_skb && !unix_skb_len(skb))) + answ = 1; + } + + mutex_unlock(&u->iolock); + err = put_user(answ, (int __user *)arg); } break; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 0104be9d4704..23efb78fe9ef 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -101,277 +101,499 @@ struct unix_sock *unix_get_socket(struct file *filp) return NULL; } -DEFINE_SPINLOCK(unix_gc_lock); +static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) +{ + /* If an embryo socket has a fd, + * the listener indirectly holds the fd's refcnt. + */ + if (edge->successor->listener) + return unix_sk(edge->successor->listener)->vertex; + + return edge->successor->vertex; +} + +static bool unix_graph_maybe_cyclic; +static bool unix_graph_grouped; + +static void unix_update_graph(struct unix_vertex *vertex) +{ + /* If the receiver socket is not inflight, no cyclic + * reference could be formed. + */ + if (!vertex) + return; + + unix_graph_maybe_cyclic = true; + unix_graph_grouped = false; +} + +static LIST_HEAD(unix_unvisited_vertices); + +enum unix_vertex_index { + UNIX_VERTEX_INDEX_MARK1, + UNIX_VERTEX_INDEX_MARK2, + UNIX_VERTEX_INDEX_START, +}; + +static unsigned long unix_vertex_unvisited_index = UNIX_VERTEX_INDEX_MARK1; + +static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) +{ + struct unix_vertex *vertex = edge->predecessor->vertex; + + if (!vertex) { + vertex = list_first_entry(&fpl->vertices, typeof(*vertex), entry); + vertex->index = unix_vertex_unvisited_index; + vertex->out_degree = 0; + INIT_LIST_HEAD(&vertex->edges); + INIT_LIST_HEAD(&vertex->scc_entry); + + list_move_tail(&vertex->entry, &unix_unvisited_vertices); + edge->predecessor->vertex = vertex; + } + + vertex->out_degree++; + list_add_tail(&edge->vertex_entry, &vertex->edges); + + unix_update_graph(unix_edge_successor(edge)); +} + +static void unix_del_edge(struct scm_fp_list *fpl, struct unix_edge *edge) +{ + struct unix_vertex *vertex = edge->predecessor->vertex; + + if (!fpl->dead) + unix_update_graph(unix_edge_successor(edge)); + + list_del(&edge->vertex_entry); + vertex->out_degree--; + + if (!vertex->out_degree) { + edge->predecessor->vertex = NULL; + list_move_tail(&vertex->entry, &fpl->vertices); + } +} + +static void unix_free_vertices(struct scm_fp_list *fpl) +{ + struct unix_vertex *vertex, *next_vertex; + + list_for_each_entry_safe(vertex, next_vertex, &fpl->vertices, entry) { + list_del(&vertex->entry); + kfree(vertex); + } +} + +static DEFINE_SPINLOCK(unix_gc_lock); unsigned int unix_tot_inflight; -static LIST_HEAD(gc_candidates); -static LIST_HEAD(gc_inflight_list); -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ -void unix_inflight(struct user_struct *user, struct file *filp) +void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) { - struct unix_sock *u = unix_get_socket(filp); + int i = 0, j = 0; spin_lock(&unix_gc_lock); - if (u) { - if (!u->inflight) { - WARN_ON_ONCE(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - WARN_ON_ONCE(list_empty(&u->link)); - } - u->inflight++; + if (!fpl->count_unix) + goto out; - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); - } + do { + struct unix_sock *inflight = unix_get_socket(fpl->fp[j++]); + struct unix_edge *edge; + + if (!inflight) + continue; + + edge = fpl->edges + i++; + edge->predecessor = inflight; + edge->successor = receiver; - WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); + unix_add_edge(fpl, edge); + } while (i < fpl->count_unix); + + receiver->scm_stat.nr_unix_fds += fpl->count_unix; + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); spin_unlock(&unix_gc_lock); + + fpl->inflight = true; + + unix_free_vertices(fpl); } -void unix_notinflight(struct user_struct *user, struct file *filp) +void unix_del_edges(struct scm_fp_list *fpl) { - struct unix_sock *u = unix_get_socket(filp); + struct unix_sock *receiver; + int i = 0; spin_lock(&unix_gc_lock); - if (u) { - WARN_ON_ONCE(!u->inflight); - WARN_ON_ONCE(list_empty(&u->link)); + if (!fpl->count_unix) + goto out; - u->inflight--; - if (!u->inflight) - list_del_init(&u->link); + do { + struct unix_edge *edge = fpl->edges + i++; - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); - } + unix_del_edge(fpl, edge); + } while (i < fpl->count_unix); - WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); + if (!fpl->dead) { + receiver = fpl->edges[0].successor; + receiver->scm_stat.nr_unix_fds -= fpl->count_unix; + } + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); spin_unlock(&unix_gc_lock); + + fpl->inflight = false; } -static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) +void unix_update_edges(struct unix_sock *receiver) { - struct sk_buff *skb; - struct sk_buff *next; - - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - /* Do we have file descriptors ? */ - if (UNIXCB(skb).fp) { - bool hit = false; - /* Process the descriptors of this socket */ - int nfd = UNIXCB(skb).fp->count; - struct file **fp = UNIXCB(skb).fp->fp; - - while (nfd--) { - /* Get the socket the fd matches if it indeed does so */ - struct unix_sock *u = unix_get_socket(*fp++); - - /* Ignore non-candidates, they could have been added - * to the queues after starting the garbage collection - */ - if (u && test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { - hit = true; - - func(u); - } - } - if (hit && hitlist != NULL) { - __skb_unlink(skb, &x->sk_receive_queue); - __skb_queue_tail(hitlist, skb); - } - } + /* nr_unix_fds is only updated under unix_state_lock(). + * If it's 0 here, the embryo socket is not part of the + * inflight graph, and GC will not see it, so no lock needed. + */ + if (!receiver->scm_stat.nr_unix_fds) { + receiver->listener = NULL; + } else { + spin_lock(&unix_gc_lock); + unix_update_graph(unix_sk(receiver->listener)->vertex); + receiver->listener = NULL; + spin_unlock(&unix_gc_lock); } - spin_unlock(&x->sk_receive_queue.lock); } -static void scan_children(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) +int unix_prepare_fpl(struct scm_fp_list *fpl) { - if (x->sk_state != TCP_LISTEN) { - scan_inflight(x, func, hitlist); - } else { - struct sk_buff *skb; - struct sk_buff *next; - struct unix_sock *u; - LIST_HEAD(embryos); + struct unix_vertex *vertex; + int i; - /* For a listening socket collect the queued embryos - * and perform a scan on them as well. - */ - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - u = unix_sk(skb->sk); + if (!fpl->count_unix) + return 0; - /* An embryo cannot be in-flight, so it's safe - * to use the list link. - */ - WARN_ON_ONCE(!list_empty(&u->link)); - list_add_tail(&u->link, &embryos); - } - spin_unlock(&x->sk_receive_queue.lock); + for (i = 0; i < fpl->count_unix; i++) { + vertex = kmalloc(sizeof(*vertex), GFP_KERNEL); + if (!vertex) + goto err; - while (!list_empty(&embryos)) { - u = list_entry(embryos.next, struct unix_sock, link); - scan_inflight(&u->sk, func, hitlist); - list_del_init(&u->link); - } + list_add(&vertex->entry, &fpl->vertices); } + + fpl->edges = kvmalloc_array(fpl->count_unix, sizeof(*fpl->edges), + GFP_KERNEL_ACCOUNT); + if (!fpl->edges) + goto err; + + return 0; + +err: + unix_free_vertices(fpl); + return -ENOMEM; } -static void dec_inflight(struct unix_sock *usk) +void unix_destroy_fpl(struct scm_fp_list *fpl) { - usk->inflight--; + if (fpl->inflight) + unix_del_edges(fpl); + + kvfree(fpl->edges); + unix_free_vertices(fpl); } -static void inc_inflight(struct unix_sock *usk) +static bool unix_vertex_dead(struct unix_vertex *vertex) { - usk->inflight++; + struct unix_edge *edge; + struct unix_sock *u; + long total_ref; + + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); + + /* The vertex's fd can be received by a non-inflight socket. */ + if (!next_vertex) + return false; + + /* The vertex's fd can be received by an inflight socket in + * another SCC. + */ + if (next_vertex->scc_index != vertex->scc_index) + return false; + } + + /* No receiver exists out of the same SCC. */ + + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + total_ref = file_count(u->sk.sk_socket->file); + + /* If not close()d, total_ref > out_degree. */ + if (total_ref != vertex->out_degree) + return false; + + return true; } -static void inc_inflight_move_tail(struct unix_sock *u) +enum unix_recv_queue_lock_class { + U_RECVQ_LOCK_NORMAL, + U_RECVQ_LOCK_EMBRYO, +}; + +static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist) { - u->inflight++; + skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist); - /* If this still might be part of a cycle, move it to the end - * of the list, so that it's checked even if it was already - * passed over - */ - if (test_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags)) - list_move_tail(&u->link, &gc_candidates); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + WARN_ON_ONCE(skb_unref(u->oob_skb)); + u->oob_skb = NULL; + } +#endif } -static bool gc_in_progress; - -static void __unix_gc(struct work_struct *work) +static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) { - struct sk_buff_head hitlist; - struct unix_sock *u, *next; - LIST_HEAD(not_cycle_list); - struct list_head cursor; + struct unix_vertex *vertex; - spin_lock(&unix_gc_lock); + list_for_each_entry_reverse(vertex, scc, scc_entry) { + struct sk_buff_head *queue; + struct unix_edge *edge; + struct unix_sock *u; - /* First, select candidates for garbage collection. Only - * in-flight sockets are considered, and from those only ones - * which don't have any external reference. - * - * Holding unix_gc_lock will protect these candidates from - * being detached, and hence from gaining an external - * reference. Since there are no possible receivers, all - * buffers currently on the candidates' queues stay there - * during the garbage collection. - * - * We also know that no new candidate can be added onto the - * receive queues. Other, non candidate sockets _can_ be - * added to queue, so we must make sure only to touch - * candidates. - * - * Embryos, though never candidates themselves, affect which - * candidates are reachable by the garbage collector. Before - * being added to a listener's queue, an embryo may already - * receive data carrying SCM_RIGHTS, potentially making the - * passed socket a candidate that is not yet reachable by the - * collector. It becomes reachable once the embryo is - * enqueued. Therefore, we must ensure that no SCM-laden - * embryo appears in a (candidate) listener's queue between - * consecutive scan_children() calls. - */ - list_for_each_entry_safe(u, next, &gc_inflight_list, link) { - struct sock *sk = &u->sk; - long total_refs; - - total_refs = file_count(sk->sk_socket->file); - - WARN_ON_ONCE(!u->inflight); - WARN_ON_ONCE(total_refs < u->inflight); - if (total_refs == u->inflight) { - list_move_tail(&u->link, &gc_candidates); - __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - - if (sk->sk_state == TCP_LISTEN) { - unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); - unix_state_unlock(sk); + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + queue = &u->sk.sk_receive_queue; + + spin_lock(&queue->lock); + + if (u->sk.sk_state == TCP_LISTEN) { + struct sk_buff *skb; + + skb_queue_walk(queue, skb) { + struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; + + /* listener -> embryo order, the inversion never happens. */ + spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO); + unix_collect_queue(unix_sk(skb->sk), hitlist); + spin_unlock(&embryo_queue->lock); } + } else { + unix_collect_queue(u, hitlist); } + + spin_unlock(&queue->lock); } +} - /* Now remove all internal in-flight reference to children of - * the candidates. - */ - list_for_each_entry(u, &gc_candidates, link) - scan_children(&u->sk, dec_inflight, NULL); +static bool unix_scc_cyclic(struct list_head *scc) +{ + struct unix_vertex *vertex; + struct unix_edge *edge; - /* Restore the references for children of all candidates, - * which have remaining references. Do this recursively, so - * only those remain, which form cyclic references. - * - * Use a "cursor" link, to make the list traversal safe, even - * though elements might be moved about. + /* SCC containing multiple vertices ? */ + if (!list_is_singular(scc)) + return true; + + vertex = list_first_entry(scc, typeof(*vertex), scc_entry); + + /* Self-reference or a embryo-listener circle ? */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + if (unix_edge_successor(edge) == vertex) + return true; + } + + return false; +} + +static LIST_HEAD(unix_visited_vertices); +static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; + +static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, + struct sk_buff_head *hitlist) +{ + LIST_HEAD(vertex_stack); + struct unix_edge *edge; + LIST_HEAD(edge_stack); + +next_vertex: + /* Push vertex to vertex_stack and mark it as on-stack + * (index >= UNIX_VERTEX_INDEX_START). + * The vertex will be popped when finalising SCC later. */ - list_add(&cursor, &gc_candidates); - while (cursor.next != &gc_candidates) { - u = list_entry(cursor.next, struct unix_sock, link); + list_add(&vertex->scc_entry, &vertex_stack); + + vertex->index = *last_index; + vertex->scc_index = *last_index; + (*last_index)++; + + /* Explore neighbour vertices (receivers of the current vertex's fd). */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); + + if (!next_vertex) + continue; + + if (next_vertex->index == unix_vertex_unvisited_index) { + /* Iterative deepening depth first search + * + * 1. Push a forward edge to edge_stack and set + * the successor to vertex for the next iteration. + */ + list_add(&edge->stack_entry, &edge_stack); + + vertex = next_vertex; + goto next_vertex; - /* Move cursor to after the current position. */ - list_move(&cursor, &u->link); + /* 2. Pop the edge directed to the current vertex + * and restore the ancestor for backtracking. + */ +prev_vertex: + edge = list_first_entry(&edge_stack, typeof(*edge), stack_entry); + list_del_init(&edge->stack_entry); + + next_vertex = vertex; + vertex = edge->predecessor->vertex; - if (u->inflight) { - list_move_tail(&u->link, ¬_cycle_list); - __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - scan_children(&u->sk, inc_inflight_move_tail, NULL); + /* If the successor has a smaller scc_index, two vertices + * are in the same SCC, so propagate the smaller scc_index + * to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else if (next_vertex->index != unix_vertex_grouped_index) { + /* Loop detected by a back/cross edge. + * + * The successor is on vertex_stack, so two vertices are in + * the same SCC. If the successor has a smaller *scc_index*, + * propagate it to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else { + /* The successor was already grouped as another SCC */ } } - list_del(&cursor); - /* Now gc_candidates contains only garbage. Restore original - * inflight counters for these as well, and remove the skbuffs - * which are creating the cycle(s). - */ - skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) { - scan_children(&u->sk, inc_inflight, &hitlist); + if (vertex->index == vertex->scc_index) { + struct unix_vertex *v; + struct list_head scc; + bool scc_dead = true; -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; + /* SCC finalised. + * + * If the scc_index was not updated, all the vertices above on + * vertex_stack are in the same SCC. Group them using scc_entry. + */ + __list_cut_position(&scc, &vertex_stack, &vertex->scc_entry); + + list_for_each_entry_reverse(v, &scc, scc_entry) { + /* Don't restart DFS from this vertex in unix_walk_scc(). */ + list_move_tail(&v->entry, &unix_visited_vertices); + + /* Mark vertex as off-stack. */ + v->index = unix_vertex_grouped_index; + + if (scc_dead) + scc_dead = unix_vertex_dead(v); } -#endif + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); } - /* not_cycle_list contains those sockets which do not make up a - * cycle. Restore these to the inflight list. + /* Need backtracking ? */ + if (!list_empty(&edge_stack)) + goto prev_vertex; +} + +static void unix_walk_scc(struct sk_buff_head *hitlist) +{ + unsigned long last_index = UNIX_VERTEX_INDEX_START; + + unix_graph_maybe_cyclic = false; + + /* Visit every vertex exactly once. + * __unix_walk_scc() moves visited vertices to unix_visited_vertices. */ - while (!list_empty(¬_cycle_list)) { - u = list_entry(not_cycle_list.next, struct unix_sock, link); - __clear_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - list_move_tail(&u->link, &gc_inflight_list); + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + __unix_walk_scc(vertex, &last_index, hitlist); } - spin_unlock(&unix_gc_lock); + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); + swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); - /* Here we are. Hitlist is filled. Die. */ - __skb_queue_purge(&hitlist); + unix_graph_grouped = true; +} + +static void unix_walk_scc_fast(struct sk_buff_head *hitlist) +{ + unix_graph_maybe_cyclic = false; + + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + struct list_head scc; + bool scc_dead = true; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + list_add(&scc, &vertex->scc_entry); + + list_for_each_entry_reverse(vertex, &scc, scc_entry) { + list_move_tail(&vertex->entry, &unix_visited_vertices); + + if (scc_dead) + scc_dead = unix_vertex_dead(vertex); + } + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); + } + + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); +} + +static bool gc_in_progress; + +static void __unix_gc(struct work_struct *work) +{ + struct sk_buff_head hitlist; + struct sk_buff *skb; spin_lock(&unix_gc_lock); - /* All candidates should have been detached by now. */ - WARN_ON_ONCE(!list_empty(&gc_candidates)); + if (!unix_graph_maybe_cyclic) { + spin_unlock(&unix_gc_lock); + goto skip_gc; + } - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ - WRITE_ONCE(gc_in_progress, false); + __skb_queue_head_init(&hitlist); + + if (unix_graph_grouped) + unix_walk_scc_fast(&hitlist); + else + unix_walk_scc(&hitlist); spin_unlock(&unix_gc_lock); + + skb_queue_walk(&hitlist, skb) { + if (UNIXCB(skb).fp) + UNIXCB(skb).fp->dead = true; + } + + __skb_queue_purge(&hitlist); +skip_gc: + WRITE_ONCE(gc_in_progress, false); } static DECLARE_WORK(unix_gc_work, __unix_gc); diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c index 3e84b31c355a..357b3e5f3847 100644 --- a/net/unix/sysctl_net_unix.c +++ b/net/unix/sysctl_net_unix.c @@ -19,7 +19,6 @@ static struct ctl_table unix_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { } }; int __net_init unix_sysctl_register(struct net *net) @@ -52,7 +51,7 @@ err_alloc: void unix_sysctl_unregister(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->unx.ctl->ctl_table_arg; unregister_net_sysctl_table(net->unx.ctl); diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index bd84785bf8d6..bca2d86ba97d 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, struct sk_psock *psock; int copied; + if (flags & MSG_OOB) + return -EOPNOTSUPP; + if (!len) return 0; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 54ba7316f808..0ff9b2dd86ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ out: return err; } +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk; - sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif - return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); @@ -1500,8 +1503,8 @@ out: return err; } -static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int vsock_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *listener; int err; @@ -1528,7 +1531,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, /* Wait for children sockets to appear; these are the new sockets * created upon connection establishment. */ - timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK); + timeout = sock_rcvtimeo(listener, arg->flags & O_NONBLOCK); prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); while ((connected = vsock_dequeue_accept(listener)) == NULL && @@ -2174,15 +2177,12 @@ out: } int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err; sk = sock->sk; @@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } -#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2242,22 @@ out: release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index ee5d306a96d0..43d405298857 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -859,7 +859,6 @@ 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, diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 72074fd36df4..1d49cc8b6da1 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -25,7 +25,7 @@ ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) cfg80211-y += extra-certs.o endif -$(obj)/shipped-certs.c: $(sort $(wildcard $(srctree)/$(src)/certs/*.hex)) +$(obj)/shipped-certs.c: $(sort $(wildcard $(src)/certs/*.hex)) @$(kecho) " GEN $@" $(Q)(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 65c416e8d25e..c2829d673bc7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -468,6 +468,10 @@ static const struct netlink_range_validation nl80211_punct_bitmap_range = { .max = 0xffff, }; +static const struct netlink_range_validation q_range = { + .max = INT_MAX, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -754,7 +758,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, - [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, + [NL80211_ATTR_TXQ_QUANTUM] = NLA_POLICY_FULL_RANGE(NLA_U32, &q_range), [NL80211_ATTR_HE_CAPABILITY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_he_capa, NL80211_HE_MAX_CAPABILITY_LEN), @@ -1204,6 +1208,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_CAN_MONITOR) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_CAN_MONITOR)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -3415,6 +3422,33 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, if (chandef.chan != cur_chan) return -EBUSY; + /* only allow this for regular channel widths */ + switch (wdev->links[link_id].ap.chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_40: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_320: + break; + default: + return -EINVAL; + } + + switch (chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_40: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_320: + break; + default: + return -EINVAL; + } + result = rdev_set_ap_chanwidth(rdev, dev, link_id, &chandef); if (result) @@ -4451,10 +4485,7 @@ static void get_key_callback(void *c, struct key_params *params) struct nlattr *key; struct get_key_cookie *cookie = c; - if ((params->key && - nla_put(cookie->msg, NL80211_ATTR_KEY_DATA, - params->key_len, params->key)) || - (params->seq && + if ((params->seq && nla_put(cookie->msg, NL80211_ATTR_KEY_SEQ, params->seq_len, params->seq)) || (params->cipher && @@ -4466,10 +4497,7 @@ static void get_key_callback(void *c, struct key_params *params) if (!key) goto nla_put_failure; - if ((params->key && - nla_put(cookie->msg, NL80211_KEY_DATA, - params->key_len, params->key)) || - (params->seq && + if ((params->seq && nla_put(cookie->msg, NL80211_KEY_SEQ, params->seq_len, params->seq)) || (params->cipher && @@ -8116,7 +8144,8 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) is_indoor = true; } - return regulatory_hint_indoor(is_indoor, owner_nlportid); + regulatory_hint_indoor(is_indoor, owner_nlportid); + return 0; default: return -EINVAL; } @@ -16031,6 +16060,7 @@ static int nl80211_color_change(struct sk_buff *skb, struct genl_info *info) params.counter_offset_presp = offset; } + params.link_id = nl80211_link_id(info->attrs); err = rdev_color_change(rdev, dev, ¶ms); out: @@ -17433,7 +17463,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_color_change, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_SET_FILS_AAD, @@ -19455,7 +19486,7 @@ EXPORT_SYMBOL(cfg80211_ch_switch_started_notify); int cfg80211_bss_color_notify(struct net_device *dev, enum nl80211_commands cmd, u8 count, - u64 color_bitmap) + u64 color_bitmap, u8 link_id) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; @@ -19478,6 +19509,10 @@ int cfg80211_bss_color_notify(struct net_device *dev, if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; + if (wdev->valid_links && + nla_put_u8(msg, NL80211_ATTR_MLO_LINK_ID, link_id)) + goto nla_put_failure; + if (cmd == NL80211_CMD_COLOR_CHANGE_STARTED && nla_put_u32(msg, NL80211_ATTR_COLOR_CHANGE_COUNT, count)) goto nla_put_failure; diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 43897a5269b6..755af47b88b9 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -2,7 +2,7 @@ /* * Portions of this file * Copyright(c) 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2018, 2021-2023 Intel Corporation + * Copyright (C) 2018, 2021-2024 Intel Corporation */ #ifndef __CFG80211_RDEV_OPS #define __CFG80211_RDEV_OPS @@ -458,6 +458,10 @@ static inline int rdev_scan(struct cfg80211_registered_device *rdev, struct cfg80211_scan_request *request) { int ret; + + if (WARN_ON_ONCE(!request->n_ssids && request->ssids)) + return -EINVAL; + trace_rdev_scan(&rdev->wiphy, request); ret = rdev->ops->scan(&rdev->wiphy, request); trace_rdev_return_int(&rdev->wiphy, ret); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 753f8e9aa4b1..3cef0021a3db 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3284,7 +3284,7 @@ int regulatory_hint_user(const char *alpha2, return 0; } -int regulatory_hint_indoor(bool is_indoor, u32 portid) +void regulatory_hint_indoor(bool is_indoor, u32 portid) { spin_lock(®_indoor_lock); @@ -3307,8 +3307,6 @@ int regulatory_hint_indoor(bool is_indoor, u32 portid) if (!is_indoor) reg_check_channels(); - - return 0; } void regulatory_netlink_notify(u32 portid) @@ -3666,9 +3664,9 @@ static bool pending_reg_beacon(struct ieee80211_channel *beacon_chan) return false; } -int regulatory_hint_found_beacon(struct wiphy *wiphy, - struct ieee80211_channel *beacon_chan, - gfp_t gfp) +void regulatory_hint_found_beacon(struct wiphy *wiphy, + struct ieee80211_channel *beacon_chan, + gfp_t gfp) { struct reg_beacon *reg_beacon; bool processing; @@ -3677,18 +3675,18 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy, beacon_chan->flags & IEEE80211_CHAN_RADAR || (beacon_chan->band == NL80211_BAND_2GHZ && !freq_is_chan_12_13_14(beacon_chan->center_freq))) - return 0; + return; spin_lock_bh(®_pending_beacons_lock); processing = pending_reg_beacon(beacon_chan); spin_unlock_bh(®_pending_beacons_lock); if (processing) - return 0; + return; reg_beacon = kzalloc(sizeof(struct reg_beacon), gfp); if (!reg_beacon) - return -ENOMEM; + return; pr_debug("Found new beacon on frequency: %d.%03d MHz (Ch %d) on %s\n", beacon_chan->center_freq, beacon_chan->freq_offset, @@ -3708,8 +3706,6 @@ int regulatory_hint_found_beacon(struct wiphy *wiphy, spin_unlock_bh(®_pending_beacons_lock); schedule_work(®_work); - - return 0; } static void print_rd_rules(const struct ieee80211_regdomain *rd) diff --git a/net/wireless/reg.h b/net/wireless/reg.h index a02ef5609f52..e1b211c4f75c 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -42,7 +42,7 @@ int regulatory_hint_user(const char *alpha2, * device is operating in an indoor environment. * @portid: the netlink port ID on which the hint was given. */ -int regulatory_hint_indoor(bool is_indoor, u32 portid); +void regulatory_hint_indoor(bool is_indoor, u32 portid); /** * regulatory_netlink_notify - notify on released netlink socket @@ -82,9 +82,9 @@ bool reg_last_request_cell_base(void); * on a newly found BSS. If you cannot make use of this feature you can * set the wiphy->disable_beacon_hints to true. */ -int regulatory_hint_found_beacon(struct wiphy *wiphy, - struct ieee80211_channel *beacon_chan, - gfp_t gfp); +void regulatory_hint_found_beacon(struct wiphy *wiphy, + struct ieee80211_channel *beacon_chan, + gfp_t gfp); /** * regulatory_hint_country_ie - hints a country IE as a regulatory domain @@ -137,13 +137,14 @@ void regulatory_hint_disconnect(void); * Get a value specifying the U-NII band frequency belongs to. * U-NII bands are defined by the FCC in C.F.R 47 part 15. * - * Returns -EINVAL if freq is invalid, 0 for UNII-1, 1 for UNII-2A, + * Return: -EINVAL if freq is invalid, 0 for UNII-1, 1 for UNII-2A, * 2 for UNII-2B, 3 for UNII-2C and 4 for UNII-3. */ int cfg80211_get_unii(int freq); /** * regulatory_indoor_allowed - is indoor operation allowed + * Return: %true if indoor operation is allowed, %false otherwise */ bool regulatory_indoor_allowed(void); @@ -173,11 +174,13 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy, * reg_dfs_domain_same - Checks if both wiphy have same DFS domain configured * @wiphy1: wiphy it's dfs_region to be checked against that of wiphy2 * @wiphy2: wiphy it's dfs_region to be checked against that of wiphy1 + * Return: %true if both wiphys have the same DFS domain, %false otherwise */ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2); /** * reg_reload_regdb - reload the regulatory.db firmware file + * Return: 0 for success, an error code otherwise */ int reg_reload_regdb(void); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index ecea8c08e270..292b530a6dd3 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -812,6 +812,7 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) LIST_HEAD(coloc_ap_list); bool need_scan_psc = true; const struct ieee80211_sband_iftype_data *iftd; + size_t size, offs_ssids, offs_6ghz_params, offs_ies; rdev_req->scan_6ghz = true; @@ -877,10 +878,15 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) spin_unlock_bh(&rdev->bss_lock); } - request = kzalloc(struct_size(request, channels, n_channels) + - sizeof(*request->scan_6ghz_params) * count + - sizeof(*request->ssids) * rdev_req->n_ssids, - GFP_KERNEL); + size = struct_size(request, channels, n_channels); + offs_ssids = size; + size += sizeof(*request->ssids) * rdev_req->n_ssids; + offs_6ghz_params = size; + size += sizeof(*request->scan_6ghz_params) * count; + offs_ies = size; + size += rdev_req->ie_len; + + request = kzalloc(size, GFP_KERNEL); if (!request) { cfg80211_free_coloc_ap_list(&coloc_ap_list); return -ENOMEM; @@ -888,8 +894,26 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) *request = *rdev_req; request->n_channels = 0; - request->scan_6ghz_params = - (void *)&request->channels[n_channels]; + request->n_6ghz_params = 0; + if (rdev_req->n_ssids) { + /* + * Add the ssids from the parent scan request to the new + * scan request, so the driver would be able to use them + * in its probe requests to discover hidden APs on PSC + * channels. + */ + request->ssids = (void *)request + offs_ssids; + memcpy(request->ssids, rdev_req->ssids, + sizeof(*request->ssids) * request->n_ssids); + } + request->scan_6ghz_params = (void *)request + offs_6ghz_params; + + if (rdev_req->ie_len) { + void *ie = (void *)request + offs_ies; + + memcpy(ie, rdev_req->ie, rdev_req->ie_len); + request->ie = ie; + } /* * PSC channels should not be scanned in case of direct scan with 1 SSID @@ -978,17 +1002,8 @@ skip: if (request->n_channels) { struct cfg80211_scan_request *old = rdev->int_scan_req; - rdev->int_scan_req = request; - /* - * Add the ssids from the parent scan request to the new scan - * request, so the driver would be able to use them in its - * probe requests to discover hidden APs on PSC channels. - */ - request->ssids = (void *)&request->channels[request->n_channels]; - request->n_ssids = rdev_req->n_ssids; - memcpy(request->ssids, rdev_req->ssids, sizeof(*request->ssids) * - request->n_ssids); + rdev->int_scan_req = request; /* * If this scan follows a previous scan, save the scan start @@ -2141,11 +2156,15 @@ static bool cfg80211_6ghz_power_type_valid(const u8 *ie, size_t ielen, switch (u8_get_bits(he_6ghz_oper->control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: return true; case IEEE80211_6GHZ_CTRL_REG_SP_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: return !(flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT); case IEEE80211_6GHZ_CTRL_REG_VLP_AP: return !(flags & IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT); + default: + return false; } } return false; @@ -2449,7 +2468,8 @@ cfg80211_parse_mbssid_data(struct wiphy *wiphy, profile, profile_len); if (!mbssid_index_ie || mbssid_index_ie[1] < 1 || mbssid_index_ie[2] == 0 || - mbssid_index_ie[2] > 46) { + mbssid_index_ie[2] > 46 || + mbssid_index_ie[2] >= (1 << elem->data[0])) { /* No valid Multiple BSSID-Index element */ continue; } @@ -3116,8 +3136,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, gfp_t gfp) { - size_t min_hdr_len = offsetof(struct ieee80211_mgmt, - u.probe_resp.variable); + size_t min_hdr_len; struct ieee80211_ext *ext = NULL; enum cfg80211_bss_frame_type ftype; u16 beacon_interval; @@ -3140,10 +3159,16 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { ext = (void *) mgmt; - min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon); if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon.variable); + } else { + /* same for beacons */ + min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); } if (WARN_ON(len < min_hdr_len)) @@ -3396,10 +3421,14 @@ int cfg80211_wext_siwscan(struct net_device *dev, wiphy = &rdev->wiphy; /* Determine number of channels, needed to allocate creq */ - if (wreq && wreq->num_channels) + if (wreq && wreq->num_channels) { + /* Passed from userspace so should be checked */ + if (unlikely(wreq->num_channels > IW_MAX_FREQUENCIES)) + return -EINVAL; n_channels = wreq->num_channels; - else + } else { n_channels = ieee80211_get_num_supported_channels(wiphy); + } creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) + n_channels * sizeof(void *), @@ -3473,8 +3502,10 @@ int cfg80211_wext_siwscan(struct net_device *dev, memcpy(creq->ssids[0].ssid, wreq->essid, wreq->essid_len); creq->ssids[0].ssid_len = wreq->essid_len; } - if (wreq->scan_type == IW_SCAN_TYPE_PASSIVE) + if (wreq->scan_type == IW_SCAN_TYPE_PASSIVE) { + creq->ssids = NULL; creq->n_ssids = 0; + } } for (i = 0; i < NUM_NL80211_BANDS; i++) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 82e3ce42206c..1cfe673bc52f 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1045,6 +1045,7 @@ void cfg80211_connect_done(struct net_device *dev, cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; + ev->cr.links[link].status = params->links[link].status; if (params->links[link].addr) { ev->cr.links[link].addr = next; @@ -1353,6 +1354,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, return; cfg80211_wdev_release_bsses(wdev); + wdev->valid_links = 0; wdev->connected = false; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index df013c98b80d..87986170d1b1 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -372,7 +372,7 @@ TRACE_EVENT(rdev_add_virtual_intf, ), TP_fast_assign( WIPHY_ASSIGN; - __assign_str(vir_intf_name, name ? name : "<noname>"); + __assign_str(vir_intf_name); __entry->type = type; ), TP_printk(WIPHY_PR_FMT ", virtual intf name: %s, type: %d", @@ -2842,6 +2842,7 @@ TRACE_EVENT(rdev_color_change, __field(u8, count) __field(u16, bcn_ofs) __field(u16, pres_ofs) + __field(u8, link_id) ), TP_fast_assign( WIPHY_ASSIGN; @@ -2849,11 +2850,12 @@ TRACE_EVENT(rdev_color_change, __entry->count = params->count; __entry->bcn_ofs = params->counter_offset_beacon; __entry->pres_ofs = params->counter_offset_presp; + __entry->link_id = params->link_id; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT - ", count: %u", + ", count: %u, link_id: %d", WIPHY_PR_ARG, NETDEV_PR_ARG, - __entry->count) + __entry->count, __entry->link_id) ); TRACE_EVENT(rdev_set_radar_background, diff --git a/net/wireless/util.c b/net/wireless/util.c index 082c6f9c5416..af6ec719567f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1504,7 +1504,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) 5120, /* 0.833333... */ }; u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; - u32 rates_969[3] = { 480388888, 453700000, 408333333 }; + u32 rates_996[3] = { 480388888, 453700000, 408333333 }; u32 rates_484[3] = { 229411111, 216666666, 195000000 }; u32 rates_242[3] = { 114711111, 108333333, 97500000 }; u32 rates_106[3] = { 40000000, 37777777, 34000000 }; @@ -1524,12 +1524,14 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; - if (rate->bw == RATE_INFO_BW_160) + if (rate->bw == RATE_INFO_BW_160 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) - result = rates_969[rate->he_gi]; + result = rates_996[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index d18d51412cc0..8dda4178497c 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -871,8 +871,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout) return rc; } -static int x25_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) +static int x25_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk; struct sock *newsk; diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c index e9802afa43d0..643f50874dfe 100644 --- a/net/x25/sysctl_net_x25.c +++ b/net/x25/sysctl_net_x25.c @@ -71,7 +71,6 @@ static struct ctl_table x25_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { }, }; int __init x25_register_sysctl(void) diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index caa340134b0e..9f76ca591d54 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) #define XDP_UMEM_FLAGS_VALID ( \ XDP_UMEM_UNALIGNED_CHUNK_FLAG | \ XDP_UMEM_TX_SW_CSUM | \ + XDP_UMEM_TX_METADATA_LEN | \ 0) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) @@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; - if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) - return -EINVAL; + if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { + if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) + return -EINVAL; + umem->tx_metadata_len = mr->tx_metadata_len; + } umem->size = size; umem->headroom = headroom; @@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - umem->tx_metadata_len = mr->tx_metadata_len; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index ce60ecd48a4d..c0e0204b9630 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -338,7 +338,6 @@ static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_devi dma_map->netdev = netdev; dma_map->dev = dev; - dma_map->dma_need_sync = false; dma_map->dma_pages_cnt = nr_pages; refcount_set(&dma_map->users, 1); list_add(&dma_map->list, &umem->xsk_dma_list); @@ -424,7 +423,6 @@ static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_ pool->dev = dma_map->dev; pool->dma_pages_cnt = dma_map->dma_pages_cnt; - pool->dma_need_sync = dma_map->dma_need_sync; memcpy(pool->dma_pages, dma_map->dma_pages, pool->dma_pages_cnt * sizeof(*pool->dma_pages)); @@ -460,8 +458,6 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, __xp_dma_unmap(dma_map, attrs); return -ENOMEM; } - if (dma_need_sync(dev, dma)) - dma_map->dma_need_sync = true; dma_map->dma_pages[i] = dma; } @@ -557,11 +553,9 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) xskb->xdp.data_meta = xskb->xdp.data; xskb->xdp.flags = 0; - if (pool->dma_need_sync) { - dma_sync_single_range_for_device(pool->dev, xskb->dma, 0, - pool->frame_len, - DMA_BIDIRECTIONAL); - } + if (pool->dev) + xp_dma_sync_for_device(pool, xskb->dma, pool->frame_len); + return &xskb->xdp; } EXPORT_SYMBOL(xp_alloc); @@ -633,7 +627,7 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) { u32 nb_entries1 = 0, nb_entries2; - if (unlikely(pool->dma_need_sync)) { + if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) { struct xdp_buff *buff; /* Slow path */ @@ -693,18 +687,3 @@ dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr) (addr & ~PAGE_MASK); } EXPORT_SYMBOL(xp_raw_get_dma); - -void xp_dma_sync_for_cpu_slow(struct xdp_buff_xsk *xskb) -{ - dma_sync_single_range_for_cpu(xskb->pool->dev, xskb->dma, 0, - xskb->pool->frame_len, DMA_BIDIRECTIONAL); -} -EXPORT_SYMBOL(xp_dma_sync_for_cpu_slow); - -void xp_dma_sync_for_device_slow(struct xsk_buff_pool *pool, dma_addr_t dma, - size_t size) -{ - dma_sync_single_range_for_device(pool->dev, dma, 0, - size, DMA_BIDIRECTIONAL); -} -EXPORT_SYMBOL(xp_dma_sync_for_device_slow); diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 655fe4ff8621..703d4172c7d7 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -98,6 +98,7 @@ static const int compat_msg_min[XFRM_NR_MSGTYPES] = { }; static const struct nla_policy compat_policy[XFRMA_MAX+1] = { + [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = XMSGSIZE(compat_xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = XMSGSIZE(compat_xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, @@ -129,6 +130,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, + [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, @@ -277,9 +279,10 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_SET_MARK_MASK: case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: + case XFRMA_SA_DIR: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -434,7 +437,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err; if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_MTIMER_THRESH); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 6346690d5c69..2455a76a1cff 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -253,6 +253,12 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, return -EINVAL; } + if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || + (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { + NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); + return -EINVAL; + } + is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support UDP encapsulation and TFC padding. */ diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 3a2982a72a6b..e95462b982b0 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -579,6 +579,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } + if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { + secpath_reset(skb); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); + xfrm_audit_state_notfound(skb, family, spi, seq); + xfrm_state_put(x); + x = NULL; + goto drop; + } + skb->mark = xfrm_smark_get(skb->mark, x); sp->xvec[sp->len++] = x; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 4df5c06e3ece..e50e4bf993fa 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -926,7 +926,7 @@ static struct net *xfrmi_get_link_net(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - return xi->net; + return READ_ONCE(xi->net); } static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d154597728d5..56b88ad88db6 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -452,6 +452,8 @@ EXPORT_SYMBOL(xfrm_policy_destroy); static void xfrm_policy_kill(struct xfrm_policy *policy) { + xfrm_dev_policy_delete(policy); + write_lock_bh(&policy->lock); policy->walk.dead = 1; write_unlock_bh(&policy->lock); @@ -1850,7 +1852,6 @@ again: __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); - xfrm_dev_policy_delete(pol); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); @@ -1891,7 +1892,6 @@ again: __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); - xfrm_dev_policy_delete(pol); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); @@ -2342,7 +2342,6 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir) pol = __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { - xfrm_dev_policy_delete(pol); xfrm_policy_kill(pol); return 0; } @@ -2489,6 +2488,12 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family, policy->if_id); + if (x && x->dir && x->dir != XFRM_SA_DIR_OUT) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEDIRERROR); + xfrm_state_put(x); + error = -EINVAL; + goto fail; + } if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 5f9bf8e5c933..eeb984be03a7 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -41,6 +41,8 @@ static const struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_ITEM("XfrmFwdHdrError", LINUX_MIB_XFRMFWDHDRERROR), SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID), SNMP_MIB_ITEM("XfrmAcquireError", LINUX_MIB_XFRMACQUIREERROR), + SNMP_MIB_ITEM("XfrmOutStateDirError", LINUX_MIB_XFRMOUTSTATEDIRERROR), + SNMP_MIB_ITEM("XfrmInStateDirError", LINUX_MIB_XFRMINSTATEDIRERROR), SNMP_MIB_SENTINEL }; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index ce56d659c55a..bc56c6305725 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -778,7 +778,8 @@ int xfrm_init_replay(struct xfrm_state *x, struct netlink_ext_ack *extack) } if (x->props.flags & XFRM_STATE_ESN) { - if (replay_esn->replay_window == 0) { + if (replay_esn->replay_window == 0 && + (!x->dir || x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "ESN replay window must be > 0"); return -EINVAL; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 0c306473a79d..67b2a399a48a 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -49,6 +49,7 @@ static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); +static HLIST_HEAD(xfrm_state_dev_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) { @@ -214,6 +215,7 @@ static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); +static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); @@ -683,6 +685,41 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc); +#ifdef CONFIG_XFRM_OFFLOAD +void xfrm_dev_state_delete(struct xfrm_state *x) +{ + struct xfrm_dev_offload *xso = &x->xso; + struct net_device *dev = READ_ONCE(xso->dev); + + if (dev) { + dev->xfrmdev_ops->xdo_dev_state_delete(x); + spin_lock_bh(&xfrm_state_dev_gc_lock); + hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list); + spin_unlock_bh(&xfrm_state_dev_gc_lock); + } +} +EXPORT_SYMBOL_GPL(xfrm_dev_state_delete); + +void xfrm_dev_state_free(struct xfrm_state *x) +{ + struct xfrm_dev_offload *xso = &x->xso; + struct net_device *dev = READ_ONCE(xso->dev); + + if (dev && dev->xfrmdev_ops) { + spin_lock_bh(&xfrm_state_dev_gc_lock); + if (!hlist_unhashed(&x->dev_gclist)) + hlist_del(&x->dev_gclist); + spin_unlock_bh(&xfrm_state_dev_gc_lock); + + if (dev->xfrmdev_ops->xdo_dev_state_free) + dev->xfrmdev_ops->xdo_dev_state_free(x); + WRITE_ONCE(xso->dev, NULL); + xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; + netdev_put(dev, &xso->dev_tracker); + } +} +#endif + void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); @@ -848,6 +885,9 @@ EXPORT_SYMBOL(xfrm_state_flush); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid) { + struct xfrm_state *x; + struct hlist_node *tmp; + struct xfrm_dev_offload *xso; int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); @@ -857,8 +897,6 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct xfrm_state *x; - struct xfrm_dev_offload *xso; restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; @@ -868,6 +906,8 @@ restart: spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); + xfrm_dev_state_free(x); + xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); @@ -884,6 +924,24 @@ restart: out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); + + spin_lock_bh(&xfrm_state_dev_gc_lock); +restart_gc: + hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) { + xso = &x->xso; + + if (xso->dev == dev) { + spin_unlock_bh(&xfrm_state_dev_gc_lock); + xfrm_dev_state_free(x); + spin_lock_bh(&xfrm_state_dev_gc_lock); + goto restart_gc; + } + + } + spin_unlock_bh(&xfrm_state_dev_gc_lock); + + xfrm_flush_gc(); + return err; } EXPORT_SYMBOL(xfrm_dev_state_flush); @@ -1273,8 +1331,7 @@ found: xso->dev = xdo->dev; xso->real_dev = xdo->real_dev; xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ; - netdev_tracker_alloc(xso->dev, &xso->dev_tracker, - GFP_ATOMIC); + netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC); error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL); if (error) { xso->dir = 0; @@ -1292,6 +1349,7 @@ found: if (km_query(x, tmpl, pol) == 0) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; + x->dir = XFRM_SA_DIR_OUT; list_add(&x->km.all, &net->xfrm.state_all); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, @@ -1744,6 +1802,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; + x->dir = orig->dir; return x; @@ -1864,8 +1923,14 @@ int xfrm_state_update(struct xfrm_state *x) } if (x1->km.state == XFRM_STATE_ACQ) { + if (x->dir && x1->dir != x->dir) + goto out; + __xfrm_state_insert(x); x = NULL; + } else { + if (x1->dir != x->dir) + goto out; } err = 0; diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c index 7fdeafc838a7..ca003e8a0376 100644 --- a/net/xfrm/xfrm_sysctl.c +++ b/net/xfrm/xfrm_sysctl.c @@ -38,7 +38,6 @@ static struct ctl_table xfrm_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - {} }; int __net_init xfrm_sysctl_init(struct net *net) @@ -57,10 +56,8 @@ int __net_init xfrm_sysctl_init(struct net *net) table[3].data = &net->xfrm.sysctl_acq_expires; /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) { - table[0].procname = NULL; + if (net->user_ns != &init_user_ns) table_size = 0; - } net->xfrm.sysctl_hdr = register_net_sysctl_sz(net, "net/core", table, table_size); @@ -76,7 +73,7 @@ out_kmemdup: void __net_exit xfrm_sysctl_fini(struct net *net) { - struct ctl_table *table; + const struct ctl_table *table; table = net->xfrm.sysctl_hdr->ctl_table_arg; unregister_net_sysctl_table(net->xfrm.sysctl_hdr); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 810b520493f3..77355422ce82 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -130,7 +130,7 @@ static inline int verify_sec_ctx_len(struct nlattr **attrs, struct netlink_ext_a } static inline int verify_replay(struct xfrm_usersa_info *p, - struct nlattr **attrs, + struct nlattr **attrs, u8 sa_dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; @@ -168,6 +168,30 @@ static inline int verify_replay(struct xfrm_usersa_info *p, return -EINVAL; } + if (sa_dir == XFRM_SA_DIR_OUT) { + if (rs->replay_window) { + NL_SET_ERR_MSG(extack, "Replay window should be 0 for output SA"); + return -EINVAL; + } + if (rs->seq || rs->seq_hi) { + NL_SET_ERR_MSG(extack, + "Replay seq and seq_hi should be 0 for output SA"); + return -EINVAL; + } + if (rs->bmp_len) { + NL_SET_ERR_MSG(extack, "Replay bmp_len should 0 for output SA"); + return -EINVAL; + } + } + + if (sa_dir == XFRM_SA_DIR_IN) { + if (rs->oseq || rs->oseq_hi) { + NL_SET_ERR_MSG(extack, + "Replay oseq and oseq_hi should be 0 for input SA"); + return -EINVAL; + } + } + return 0; } @@ -176,6 +200,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, struct netlink_ext_ack *extack) { int err; + u8 sa_dir = attrs[XFRMA_SA_DIR] ? nla_get_u8(attrs[XFRMA_SA_DIR]) : 0; err = -EINVAL; switch (p->family) { @@ -334,7 +359,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, goto out; if ((err = verify_sec_ctx_len(attrs, extack))) goto out; - if ((err = verify_replay(p, attrs, extack))) + if ((err = verify_replay(p, attrs, sa_dir, extack))) goto out; err = -EINVAL; @@ -358,6 +383,77 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, err = -EINVAL; goto out; } + + if (sa_dir == XFRM_SA_DIR_OUT) { + NL_SET_ERR_MSG(extack, + "MTIMER_THRESH attribute should not be set on output SA"); + err = -EINVAL; + goto out; + } + } + + if (sa_dir == XFRM_SA_DIR_OUT) { + if (p->flags & XFRM_STATE_DECAP_DSCP) { + NL_SET_ERR_MSG(extack, "Flag DECAP_DSCP should not be set for output SA"); + err = -EINVAL; + goto out; + } + + if (p->flags & XFRM_STATE_ICMP) { + NL_SET_ERR_MSG(extack, "Flag ICMP should not be set for output SA"); + err = -EINVAL; + goto out; + } + + if (p->flags & XFRM_STATE_WILDRECV) { + NL_SET_ERR_MSG(extack, "Flag WILDRECV should not be set for output SA"); + err = -EINVAL; + goto out; + } + + if (p->replay_window) { + NL_SET_ERR_MSG(extack, "Replay window should be 0 for output SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_REPLAY_VAL]) { + struct xfrm_replay_state *replay; + + replay = nla_data(attrs[XFRMA_REPLAY_VAL]); + + if (replay->seq || replay->bitmap) { + NL_SET_ERR_MSG(extack, + "Replay seq and bitmap should be 0 for output SA"); + err = -EINVAL; + goto out; + } + } + } + + if (sa_dir == XFRM_SA_DIR_IN) { + if (p->flags & XFRM_STATE_NOPMTUDISC) { + NL_SET_ERR_MSG(extack, "Flag NOPMTUDISC should not be set for input SA"); + err = -EINVAL; + goto out; + } + + if (attrs[XFRMA_SA_EXTRA_FLAGS]) { + u32 xflags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); + + if (xflags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP) { + NL_SET_ERR_MSG(extack, "Flag DONT_ENCAP_DSCP should not be set for input SA"); + err = -EINVAL; + goto out; + } + + if (xflags & XFRM_SA_XFLAG_OSEQ_MAY_WRAP) { + NL_SET_ERR_MSG(extack, "Flag OSEQ_MAY_WRAP should not be set for input SA"); + err = -EINVAL; + goto out; + } + + } } out: @@ -734,6 +830,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_IF_ID]) x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (attrs[XFRMA_SA_DIR]) + x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); + err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV], extack); if (err) goto error; @@ -1182,8 +1281,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x, if (ret) goto out; } - if (x->mapping_maxage) + if (x->mapping_maxage) { ret = nla_put_u32(skb, XFRMA_MTIMER_THRESH, x->mapping_maxage); + if (ret) + goto out; + } + if (x->dir) + ret = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); out: return ret; } @@ -1618,6 +1722,9 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) goto out; + if (attrs[XFRMA_SA_DIR]) + x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); + resp_skb = xfrm_state_netlink(skb, x, nlh->nlmsg_seq); if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); @@ -2348,7 +2455,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, NETLINK_CB(skb).portid); } } else { - xfrm_dev_policy_delete(xp); xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err != 0) @@ -2402,7 +2508,8 @@ static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x) + nla_total_size_64bit(sizeof(struct xfrm_lifetime_cur)) + nla_total_size(sizeof(struct xfrm_mark)) + nla_total_size(4) /* XFRM_AE_RTHR */ - + nla_total_size(4); /* XFRM_AE_ETHR */ + + nla_total_size(4) /* XFRM_AE_ETHR */ + + nla_total_size(sizeof(x->dir)); /* XFRMA_SA_DIR */ } static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) @@ -2459,6 +2566,12 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) goto out_cancel; + if (x->dir) { + err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); + if (err) + goto out_cancel; + } + nlmsg_end(skb, nlh); return 0; @@ -3018,6 +3131,7 @@ EXPORT_SYMBOL_GPL(xfrm_msg_min); #undef XMSGSIZE const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { + [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = sizeof(struct xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = sizeof(struct xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, @@ -3049,6 +3163,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, + [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), }; EXPORT_SYMBOL_GPL(xfrma_policy); @@ -3097,6 +3212,24 @@ static const struct xfrm_link { [XFRM_MSG_GETDEFAULT - XFRM_MSG_BASE] = { .doit = xfrm_get_default }, }; +static int xfrm_reject_unused_attr(int type, struct nlattr **attrs, + struct netlink_ext_ack *extack) +{ + if (attrs[XFRMA_SA_DIR]) { + switch (type) { + case XFRM_MSG_NEWSA: + case XFRM_MSG_UPDSA: + case XFRM_MSG_ALLOCSPI: + break; + default: + NL_SET_ERR_MSG(extack, "Invalid attribute SA_DIR"); + return -EINVAL; + } + } + + return 0; +} + static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -3156,6 +3289,12 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto err; + if (!link->nla_pol || link->nla_pol == xfrma_policy) { + err = xfrm_reject_unused_attr((type + XFRM_MSG_BASE), attrs, extack); + if (err < 0) + goto err; + } + if (link->doit == NULL) { err = -EINVAL; goto err; @@ -3189,8 +3328,9 @@ static void xfrm_netlink_rcv(struct sk_buff *skb) static inline unsigned int xfrm_expire_msgsize(void) { - return NLMSG_ALIGN(sizeof(struct xfrm_user_expire)) - + nla_total_size(sizeof(struct xfrm_mark)); + return NLMSG_ALIGN(sizeof(struct xfrm_user_expire)) + + nla_total_size(sizeof(struct xfrm_mark)) + + nla_total_size(sizeof_field(struct xfrm_state, dir)); } static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) @@ -3217,6 +3357,12 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) return err; + if (x->dir) { + err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); + if (err) + return err; + } + nlmsg_end(skb, nlh); return 0; } @@ -3324,6 +3470,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) if (x->mapping_maxage) l += nla_total_size(sizeof(x->mapping_maxage)); + if (x->dir) + l += nla_total_size(sizeof(x->dir)); + return l; } |