diff options
Diffstat (limited to 'net')
62 files changed, 800 insertions, 371 deletions
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index c64050e839ac..1fffe2bed5b0 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -280,6 +280,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) diff --git a/net/atm/svc.c b/net/atm/svc.c index 4a02bcaad279..d83556d8beb9 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -28,6 +28,11 @@ #include "signaling.h" #include "addr.h" +#ifdef CONFIG_COMPAT +/* It actually takes struct sockaddr_atmsvc, not struct atm_iobuf */ +#define COMPAT_ATM_ADDPARTY _IOW('a', ATMIOC_SPECIAL + 4, struct compat_atm_iobuf) +#endif + static int svc_create(struct net *net, struct socket *sock, int protocol, int kern); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 17b946f9ba31..8455ba141ee6 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -68,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn) +static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -88,9 +88,28 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) params = hci_pend_le_action_lookup(&hdev->pend_le_conns, bdaddr, bdaddr_type); - if (!params || !params->explicit_connect) + if (!params) return; + if (params->conn) { + hci_conn_drop(params->conn); + hci_conn_put(params->conn); + params->conn = NULL; + } + + if (!params->explicit_connect) + return; + + /* If the status indicates successful cancellation of + * the attempt (i.e. Unknown Connection Id) there's no point of + * notifying failure since we'll go back to keep trying to + * connect. The only exception is explicit connect requests + * where a timeout + cancel does indicate an actual failure. + */ + if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other * autoconnect action, remove them completely. If they are, just unmark @@ -178,7 +197,7 @@ static void le_scan_cleanup(struct work_struct *work) rcu_read_unlock(); if (c == conn) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); hci_conn_cleanup(conn); } @@ -1049,6 +1068,17 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, return conn; } +static bool hci_conn_unlink(struct hci_conn *conn) +{ + if (!conn->link) + return false; + + conn->link->link = NULL; + conn->link = NULL; + + return true; +} + int hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1060,15 +1090,16 @@ int hci_conn_del(struct hci_conn *conn) cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - struct hci_conn *sco = conn->link; - if (sco) { - sco->link = NULL; + struct hci_conn *link = conn->link; + + if (link) { + hci_conn_unlink(conn); /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. */ - if (sco->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(sco); + if (link->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(link); } /* Unacked frames */ @@ -1084,7 +1115,7 @@ int hci_conn_del(struct hci_conn *conn) struct hci_conn *acl = conn->link; if (acl) { - acl->link = NULL; + hci_conn_unlink(conn); hci_conn_drop(acl); } @@ -1179,31 +1210,8 @@ EXPORT_SYMBOL(hci_get_route); static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; - struct hci_conn_params *params; - params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, - conn->dst_type); - if (params && params->conn) { - hci_conn_drop(params->conn); - hci_conn_put(params->conn); - params->conn = NULL; - } - - /* If the status indicates successful cancellation of - * the attempt (i.e. Unknown Connection Id) there's no point of - * notifying failure since we'll go back to keep trying to - * connect. The only exception is explicit connect requests - * where a timeout + cancel does indicate an actual failure. - */ - if (status != HCI_ERROR_UNKNOWN_CONN_ID || - (params && params->explicit_connect)) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, status); - - /* Since we may have temporarily stopped the background scanning in - * favor of connection establishment, we should restart it. - */ - hci_update_passive_scan(hdev); + hci_connect_le_scan_cleanup(conn, status); /* Enable advertising in case this was a failed connection * attempt as a peripheral. @@ -1237,15 +1245,15 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; + bt_dev_dbg(hdev, "err %d", err); + hci_dev_lock(hdev); if (!err) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); goto done; } - bt_dev_err(hdev, "request failed to create LE connection: err %d", err); - /* Check if connection is still pending */ if (conn != hci_lookup_le_connect(hdev)) goto done; @@ -2438,6 +2446,12 @@ void hci_conn_hash_flush(struct hci_dev *hdev) c->state = BT_CLOSED; hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + + /* Unlink before deleting otherwise it is possible that + * hci_conn_del removes the link which may cause the list to + * contain items already freed. + */ + hci_conn_unlink(c); hci_conn_del(c); } } @@ -2775,6 +2789,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) { int r = 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ad92a4be5851..e87c928c9e17 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2881,16 +2881,6 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, conn->resp_addr_type = peer_addr_type; bacpy(&conn->resp_addr, peer_addr); - - /* We don't want the connection attempt to stick around - * indefinitely since LE doesn't have a page timeout concept - * like BR/EDR. Set a timer for any connection that doesn't use - * the accept list for connecting. - */ - if (filter_policy == HCI_LE_USE_PEER_ADDR) - queue_delayed_work(conn->hdev->workqueue, - &conn->le_conn_timeout, - conn->conn_timeout); } static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) @@ -5902,6 +5892,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock; + /* Drop the connection if it has been aborted */ + if (test_bit(HCI_CONN_CANCEL, &conn->flags)) { + hci_conn_drop(conn); + goto unlock; + } + if (conn->dst_type == ADDR_LE_DEV_PUBLIC) addr_type = BDADDR_LE_PUBLIC; else @@ -6995,7 +6991,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.in.sdu = le16_to_cpu(ev->max_pdu); - hci_connect_cfm(bis, ev->status); + hci_iso_setup_path(bis); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5a6aa1627791..632be1267288 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -246,8 +246,9 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); if (IS_ERR(skb)) { - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, - PTR_ERR(skb)); + if (!event) + bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + PTR_ERR(skb)); return PTR_ERR(skb); } @@ -5126,8 +5127,11 @@ static int hci_le_connect_cancel_sync(struct hci_dev *hdev, if (test_bit(HCI_CONN_SCANNING, &conn->flags)) return 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, - 6, &conn->dst, HCI_CMD_TIMEOUT); + 0, NULL, HCI_CMD_TIMEOUT); } static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -6102,6 +6106,9 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) conn->conn_timeout, NULL); done: + if (err == -ETIMEDOUT) + hci_le_connect_cancel_sync(hdev, conn); + /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); return err; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index bed1a7b9205c..707f229f896a 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -433,7 +433,7 @@ static void hidp_set_timer(struct hidp_session *session) static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) - del_timer(&session->timer); + del_timer_sync(&session->timer); } static void hidp_process_report(struct hidp_session *session, int type, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 49926f59cc12..55a7226233f9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4652,33 +4652,27 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp); chan->ops->set_shutdown(chan); + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -4698,33 +4692,27 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; } + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1111da4e2f2b..cd1a27ac555d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -235,27 +235,41 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, return err; } -static int sco_connect(struct hci_dev *hdev, struct sock *sk) +static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; + struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); + hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); + if (!hdev) + return -EHOSTUNREACH; + + hci_dev_lock(hdev); + if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) - return -EOPNOTSUPP; + (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { + err = -EOPNOTSUPP; + goto unlock; + } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec); - if (IS_ERR(hcon)) - return PTR_ERR(hcon); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } + + hci_dev_unlock(hdev); + hci_dev_put(hdev); conn = sco_conn_add(hcon); if (!conn) { @@ -263,13 +277,15 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) return -ENOMEM; } - /* Update source addr of the socket */ - bacpy(&sco_pi(sk)->src, &hcon->src); - err = sco_chan_add(conn, sk, NULL); if (err) return err; + lock_sock(sk); + + /* Update source addr of the socket */ + bacpy(&sco_pi(sk)->src, &hcon->src); + if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; @@ -278,6 +294,13 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) sco_sock_set_timer(sk, sk->sk_sndtimeo); } + release_sock(sk); + + return err; + +unlock: + hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } @@ -565,7 +588,6 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; - struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); @@ -574,37 +596,26 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen addr->sa_family != AF_BLUETOOTH) return -EINVAL; - lock_sock(sk); - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { - err = -EBADFD; - goto done; - } + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) + return -EBADFD; - if (sk->sk_type != SOCK_SEQPACKET) { + if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; - goto done; - } - - hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); - if (!hdev) { - err = -EHOSTUNREACH; - goto done; - } - hci_dev_lock(hdev); + lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); + release_sock(sk); - err = sco_connect(hdev, sk); - hci_dev_unlock(hdev); - hci_dev_put(hdev); + err = sco_connect(sk); if (err) - goto done; + return err; + + lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); -done: release_sock(sk); return err; } @@ -1129,6 +1140,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, break; } + release_sock(sk); + /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { @@ -1146,15 +1159,13 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); - err = -ENOBUFS; - break; + return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); - err = -EFAULT; - break; + return -EFAULT; } ptr += sizeof(num_codecs); @@ -1194,12 +1205,14 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, ptr += len; } - if (!err && put_user(buf_len, optlen)) - err = -EFAULT; - hci_dev_unlock(hdev); hci_dev_put(hdev); + lock_sock(sk); + + if (!err && put_user(buf_len, optlen)) + err = -EFAULT; + break; default: diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 638a4d5359db..4bc6761517bb 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -868,12 +868,17 @@ static unsigned int ip_sabotage_in(void *priv, { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); - if (nf_bridge && !nf_bridge->in_prerouting && - !netif_is_l3_master(skb->dev) && - !netif_is_l3_slave(skb->dev)) { - nf_bridge_info_free(skb); - state->okfn(state->net, state->sk, skb); - return NF_STOLEN; + if (nf_bridge) { + if (nf_bridge->sabotage_in_done) + return NF_ACCEPT; + + if (!nf_bridge->in_prerouting && + !netif_is_l3_master(skb->dev) && + !netif_is_l3_slave(skb->dev)) { + nf_bridge->sabotage_in_done = 1; + state->okfn(state->net, state->sk, skb); + return NF_STOLEN; + } } return NF_ACCEPT; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index de18e9c1d7a7..ba95c4d74a60 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -148,6 +148,17 @@ br_switchdev_fdb_notify(struct net_bridge *br, if (test_bit(BR_FDB_LOCKED, &fdb->flags)) return; + /* Entries with these flags were created using ndm_state == NUD_REACHABLE, + * ndm_flags == NTF_MASTER( | NTF_STICKY), ext_flags == 0 by something + * equivalent to 'bridge fdb add ... master dynamic (sticky)'. + * Drivers don't know how to deal with these, so don't notify them to + * avoid confusing them. + */ + if (test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags) && + !test_bit(BR_FDB_STATIC, &fdb->flags) && + !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) + return; + br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { diff --git a/net/can/bcm.c b/net/can/bcm.c index 27706f6ace34..a962ec2b8ba5 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -941,6 +941,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); + if (err < 0) + goto free_op; if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) @@ -950,12 +952,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -EINVAL; } - if (err < 0) { - if (op->frames != &op->sframe) - kfree(op->frames); - kfree(op); - return err; - } + if (err < 0) + goto free_op; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ @@ -1026,6 +1024,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_tx_start_timer(op); return msg_head->nframes * op->cfsiz + MHSIZ; + +free_op: + if (op->frames != &op->sframe) + kfree(op->frames); + kfree(op); + return err; } /* diff --git a/net/can/isotp.c b/net/can/isotp.c index 9bc344851704..5761d4ab839d 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -119,7 +119,8 @@ enum { ISOTP_WAIT_FIRST_FC, ISOTP_WAIT_FC, ISOTP_WAIT_DATA, - ISOTP_SENDING + ISOTP_SENDING, + ISOTP_SHUTDOWN, }; struct tpcon { @@ -880,8 +881,8 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) txtimer); struct sock *sk = &so->sk; - /* don't handle timeouts in IDLE state */ - if (so->tx.state == ISOTP_IDLE) + /* don't handle timeouts in IDLE or SHUTDOWN state */ + if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) return HRTIMER_NORESTART; /* we did not get any flow control or echo frame in time */ @@ -918,7 +919,6 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); - u32 old_state = so->tx.state; struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; @@ -928,23 +928,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) int off; int err; - if (!so->bound) + if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; +wait_free_buffer: /* we do not support multiple buffers - for now */ - if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE || - wq_has_sleeper(&so->wait)) { - if (msg->msg_flags & MSG_DONTWAIT) { - err = -EAGAIN; - goto err_out; - } + if (wq_has_sleeper(&so->wait) && (msg->msg_flags & MSG_DONTWAIT)) + return -EAGAIN; - /* wait for complete transmission of current pdu */ - err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - if (err) - goto err_out; + /* wait for complete transmission of current pdu */ + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_event_drop; - so->tx.state = ISOTP_SENDING; + if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { + if (so->tx.state == ISOTP_SHUTDOWN) + return -EADDRNOTAVAIL; + + goto wait_free_buffer; } if (!size || size > MAX_MSG_LENGTH) { @@ -1074,7 +1075,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (wait_tx_done) { /* wait for complete transmission of current pdu */ - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_event_drop; if (sk->sk_err) return -sk->sk_err; @@ -1082,13 +1085,15 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return size; +err_event_drop: + /* got signal: force tx state machine to be idle */ + so->tx.state = ISOTP_IDLE; + hrtimer_cancel(&so->txfrtimer); + hrtimer_cancel(&so->txtimer); err_out_drop: /* drop this PDU and unlock a potential wait queue */ - old_state = ISOTP_IDLE; -err_out: - so->tx.state = old_state; - if (so->tx.state == ISOTP_IDLE) - wake_up_interruptible(&so->wait); + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); return err; } @@ -1120,7 +1125,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (ret < 0) goto out_err; - sock_recv_timestamp(msg, sk, skb); + sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(ISOTP_MIN_NAMELEN); @@ -1150,10 +1155,12 @@ static int isotp_release(struct socket *sock) net = sock_net(sk); /* wait for complete transmission of current pdu */ - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && + cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) + ; /* force state machines to be idle also when a signal occurred */ - so->tx.state = ISOTP_IDLE; + so->tx.state = ISOTP_SHUTDOWN; so->rx.state = ISOTP_IDLE; spin_lock(&isotp_notifier_lock); @@ -1608,6 +1615,21 @@ static int isotp_init(struct sock *sk) return 0; } +static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wait) +{ + struct sock *sk = sock->sk; + struct isotp_sock *so = isotp_sk(sk); + + __poll_t mask = datagram_poll(file, sock, wait); + poll_wait(file, &so->wait, wait); + + /* Check for false positives due to TX state */ + if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) + mask &= ~(EPOLLOUT | EPOLLWRNORM); + + return mask; +} + static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { @@ -1623,7 +1645,7 @@ static const struct proto_ops isotp_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = isotp_getname, - .poll = datagram_poll, + .poll = isotp_poll, .ioctl = isotp_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fce9b9ebf13f..fe3df23a2595 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -604,7 +604,10 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv, /* reserve CAN header */ skb_reserve(skb, offsetof(struct can_frame, data)); - memcpy(skb->cb, re_skcb, sizeof(skb->cb)); + /* skb->cb must be large enough to hold a j1939_sk_buff_cb structure */ + BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*re_skcb)); + + memcpy(skb->cb, re_skcb, sizeof(*re_skcb)); skcb = j1939_skb_to_cb(skb); if (swap_src_dst) j1939_skbcb_swap(skcb); @@ -1124,8 +1127,6 @@ static void __j1939_session_cancel(struct j1939_session *session, if (session->sk) j1939_sk_send_loop_abort(session->sk, session->err); - else - j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); } static void j1939_session_cancel(struct j1939_session *session, @@ -1140,6 +1141,9 @@ static void j1939_session_cancel(struct j1939_session *session, } j1939_session_list_unlock(session->priv); + + if (!session->sk) + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); } static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) @@ -1253,6 +1257,9 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer) __j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); } j1939_session_list_unlock(session->priv); + + if (!session->sk) + j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_ABORT); } j1939_session_put(session); diff --git a/net/core/dev.c b/net/core/dev.c index 253584777101..1488f700bf81 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3199,6 +3199,7 @@ static u16 skb_tx_hash(const struct net_device *dev, } if (skb_rx_queue_recorded(skb)) { + DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; @@ -10846,7 +10847,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, - portid, nlmsg_seq(nlh)); + portid, nlh); /* * Flush the unicast and multicast chains diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 7b69cf882b8e..3e3598cd49f2 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -20,6 +20,7 @@ #include <linux/sched/task.h> #include <linux/uidgid.h> #include <linux/cookie.h> +#include <linux/proc_fs.h> #include <net/sock.h> #include <net/netlink.h> @@ -676,21 +677,19 @@ EXPORT_SYMBOL_GPL(get_net_ns); struct net *get_net_ns_by_fd(int fd) { - struct file *file; - struct ns_common *ns; - struct net *net; + struct fd f = fdget(fd); + struct net *net = ERR_PTR(-EINVAL); - file = proc_ns_fget(fd); - if (IS_ERR(file)) - return ERR_CAST(file); + if (!f.file) + return ERR_PTR(-EBADF); - ns = get_proc_ns(file_inode(file)); - if (ns->ops == &netns_operations) - net = get_net(container_of(ns, struct net, ns)); - else - net = ERR_PTR(-EINVAL); + if (proc_ns_file(f.file)) { + struct ns_common *ns = get_proc_ns(file_inode(f.file)); + if (ns->ops == &netns_operations) + net = get_net(container_of(ns, struct net, ns)); + } + fdput(f); - fput(file); return net; } EXPORT_SYMBOL_GPL(get_net_ns_by_fd); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a089b704b986..e6a739b1afa9 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -137,6 +137,20 @@ static void queue_process(struct work_struct *work) } } +static int netif_local_xmit_active(struct net_device *dev) +{ + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + return 1; + } + + return 0; +} + static void poll_one_napi(struct napi_struct *napi) { int work; @@ -183,7 +197,10 @@ void netpoll_poll_dev(struct net_device *dev) if (!ni || down_trylock(&ni->dev_lock)) return; - if (!netif_running(dev)) { + /* Some drivers will take the same locks in poll and xmit, + * we can't poll if local CPU is already in xmit. + */ + if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5d8eb57867a9..6e44e92ebdf5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3972,16 +3972,23 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq) + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + u32 seq = 0; skb = nlmsg_new(if_nlmsg_size(dev, 0), flags); if (skb == NULL) goto errout; + if (nlmsg_report(nlh)) + seq = nlmsg_seq(nlh); + else + portid = 0; + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); @@ -4017,7 +4024,7 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex, portid, nlmsg_seq(nlh)); + new_ifindex, portid, nlh); if (skb) rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1a31815104d6..4c0879798eb8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5599,18 +5599,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* In general, avoid mixing slab allocated and page_pool allocated - * pages within the same SKB. However when @to is not pp_recycle and - * @from is cloned, we can transition frag pages from page_pool to - * reference counted. - * - * On the other hand, don't allow coalescing two pp_recycle SKBs if - * @from is cloned, in case the SKB is using page_pool fragment + /* In general, avoid mixing page_pool and non-page_pool allocated + * pages within the same SKB. Additionally avoid dealing with clones + * with page_pool pages, in case the SKB is using page_pool fragment * references (PP_FLAG_PAGE_FRAG). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. + * In theory we could take full references if @from is cloned and + * !@to->pp_recycle but its tricky (due to potential race with + * the clone disappearing) and rare, so not worth dealing with. */ - if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle || + (from->pp_recycle && skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 74842b453407..782273bb93c2 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -177,7 +177,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, if (orig_sock_table) { static_branch_dec(&rps_needed); static_branch_dec(&rfs_needed); - kvfree_rcu(orig_sock_table); + kvfree_rcu_mightsleep(orig_sock_table); } } } @@ -215,7 +215,7 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, lockdep_is_held(&flow_limit_update_mutex)); if (cur && !cpumask_test_cpu(i, mask)) { RCU_INIT_POINTER(sd->flow_limit, NULL); - kfree_rcu(cur); + kfree_rcu_mightsleep(cur); } else if (!cur && cpumask_test_cpu(i, mask)) { cur = kzalloc_node(len, GFP_KERNEL, cpu_to_node(i)); diff --git a/net/core/xdp.c b/net/core/xdp.c index 528d4b37983d..fb85aca81961 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -734,13 +734,21 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *tim * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. + * @rss_type: Return value pointer for RSS type. + * + * The RSS hash type (@rss_type) specifies what portion of packet headers NIC + * hardware used when calculating RSS hash value. The RSS type can be decoded + * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits + * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* + * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ -__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) +__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index cac17183589f..165bb2cb8431 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -57,6 +57,12 @@ struct dsa_standalone_event_work { u16 vid; }; +struct dsa_host_vlan_rx_filtering_ctx { + struct net_device *dev; + const unsigned char *addr; + enum dsa_standalone_event event; +}; + static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) { return ds->ops->port_fdb_add && ds->ops->port_fdb_del && @@ -155,18 +161,37 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, return 0; } +static int dsa_slave_host_vlan_rx_filtering(struct net_device *vdev, int vid, + void *arg) +{ + struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; + + return dsa_slave_schedule_standalone_work(ctx->dev, ctx->event, + ctx->addr, vid); +} + static int dsa_slave_sync_uc(struct net_device *dev, const unsigned char *addr) { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_UC_ADD, + }; + int err; dev_uc_add(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } static int dsa_slave_unsync_uc(struct net_device *dev, @@ -174,13 +199,23 @@ static int dsa_slave_unsync_uc(struct net_device *dev, { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_UC_DEL, + }; + int err; dev_uc_del(master, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } static int dsa_slave_sync_mc(struct net_device *dev, @@ -188,13 +223,23 @@ static int dsa_slave_sync_mc(struct net_device *dev, { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_MC_ADD, + }; + int err; dev_mc_add(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } static int dsa_slave_unsync_mc(struct net_device *dev, @@ -202,13 +247,23 @@ static int dsa_slave_unsync_mc(struct net_device *dev, { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_MC_DEL, + }; + int err; dev_mc_del(master, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, addr, 0); + err = dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, addr, 0); + if (err) + return err; + + return vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, &ctx); } void dsa_slave_sync_ha(struct net_device *dev) @@ -1702,6 +1757,8 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, .flags = 0, }; struct netlink_ext_ack extack = {0}; + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; int ret; /* User port... */ @@ -1721,6 +1778,30 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, return ret; } + if (!dsa_switch_supports_uc_filtering(ds) && + !dsa_switch_supports_mc_filtering(ds)) + return 0; + + netif_addr_lock_bh(dev); + + if (dsa_switch_supports_mc_filtering(ds)) { + netdev_for_each_synced_mc_addr(ha, dev) { + dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, + ha->addr, vid); + } + } + + if (dsa_switch_supports_uc_filtering(ds)) { + netdev_for_each_synced_uc_addr(ha, dev) { + dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, + ha->addr, vid); + } + } + + netif_addr_unlock_bh(dev); + + dsa_flush_workqueue(); + return 0; } @@ -1733,13 +1814,43 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, /* This API only allows programming tagged, non-PVID VIDs */ .flags = 0, }; + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; int err; err = dsa_port_vlan_del(dp, &vlan); if (err) return err; - return dsa_port_host_vlan_del(dp, &vlan); + err = dsa_port_host_vlan_del(dp, &vlan); + if (err) + return err; + + if (!dsa_switch_supports_uc_filtering(ds) && + !dsa_switch_supports_mc_filtering(ds)) + return 0; + + netif_addr_lock_bh(dev); + + if (dsa_switch_supports_mc_filtering(ds)) { + netdev_for_each_synced_mc_addr(ha, dev) { + dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, + ha->addr, vid); + } + } + + if (dsa_switch_supports_uc_filtering(ds)) { + netdev_for_each_synced_uc_addr(ha, dev) { + dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, + ha->addr, vid); + } + } + + netif_addr_unlock_bh(dev); + + dsa_flush_workqueue(); + + return 0; } static int dsa_slave_restore_vlan(struct net_device *vdev, int vid, void *arg) diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index fab66c169b9f..20165e07ef90 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -270,11 +270,12 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, "lanes configuration not supported by device"); return -EOPNOTSUPP; } - } else if (!lsettings->autoneg) { - /* If autoneg is off and lanes parameter is not passed from user, - * set the lanes parameter to 0. + } else if (!lsettings->autoneg && ksettings->lanes) { + /* If autoneg is off and lanes parameter is not passed from user but + * it was defined previously then set the lanes parameter to 0. */ ksettings->lanes = 0; + *mod = true; } ret = ethnl_update_bitset(ksettings->link_modes.advertising, diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index d8f4379d4fa6..832e3c50816c 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -2488,8 +2488,7 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) return -EOPNOTSUPP; - if (!info->attrs[NL802154_ATTR_SEC_LEVEL] || - llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], + if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 8cebb476b3ab..b8607763d113 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -749,6 +749,11 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); + /* Guard against tiny mtu. We need to include at least one + * IP network header for this message to make any sense. + */ + if (room <= (int)sizeof(struct iphdr)) + goto ende; icmp_param.data_len = skb_in->len - icmp_param.offset; if (icmp_param.data_len > room) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 409ec2a1f95b..5178a3f3cb53 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1089,13 +1089,13 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) } void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) - __acquires(RCU) + __acquires(ping_table.lock) { struct ping_iter_state *state = seq->private; state->bucket = 0; state->family = family; - rcu_read_lock(); + spin_lock(&ping_table.lock); return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1121,9 +1121,9 @@ void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(ping_seq_next); void ping_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) + __releases(ping_table.lock) { - rcu_read_unlock(); + spin_unlock(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_seq_stop); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 94df935ee0c5..8088a5011e7d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -91,12 +91,12 @@ EXPORT_SYMBOL_GPL(raw_v4_hashinfo); int raw_hash_sk(struct sock *sk) { struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; - struct hlist_nulls_head *hlist; + struct hlist_head *hlist; hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); - __sk_nulls_add_node_rcu(sk, hlist); + sk_add_node_rcu(sk, hlist); sock_set_flag(sk, SOCK_RCU_FREE); spin_unlock(&h->lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -110,7 +110,7 @@ void raw_unhash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; spin_lock(&h->lock); - if (__sk_nulls_del_node_init_rcu(sk)) + if (sk_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(&h->lock); } @@ -163,16 +163,15 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) static int raw_v4_input(struct net *net, struct sk_buff *skb, const struct iphdr *iph, int hash) { - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int sdif = inet_sdif(skb); + struct hlist_head *hlist; int dif = inet_iif(skb); int delivered = 0; struct sock *sk; hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; @@ -264,10 +263,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); + struct hlist_head *hlist; const struct iphdr *iph; struct sock *sk; int hash; @@ -276,7 +274,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { iph = (const struct iphdr *)skb->data; if (!raw_v4_match(net, sk, iph->protocol, iph->daddr, iph->saddr, dif, sdif)) @@ -950,14 +948,13 @@ static struct sock *raw_get_first(struct seq_file *seq, int bucket) { struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; for (state->bucket = bucket; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { hlist = &h->ht[state->bucket]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each(sk, hlist) { if (sock_net(sk) == seq_file_net(seq)) return sk; } @@ -970,7 +967,7 @@ static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) struct raw_iter_state *state = raw_seq_private(seq); do { - sk = sk_nulls_next(sk); + sk = sk_next(sk); } while (sk && sock_net(sk) != seq_file_net(seq)); if (!sk) @@ -989,9 +986,12 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) } void *raw_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) + __acquires(&h->lock) { - rcu_read_lock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_lock(&h->lock); + return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(raw_seq_start); @@ -1010,9 +1010,11 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) + __releases(&h->lock) { - rcu_read_unlock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_unlock(&h->lock); } EXPORT_SYMBOL_GPL(raw_seq_stop); diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 999321834b94..da3591a66a16 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -57,8 +57,7 @@ static bool raw_lookup(struct net *net, struct sock *sk, static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r) { struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int slot; @@ -68,7 +67,7 @@ static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 rcu_read_lock(); for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) { hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (raw_lookup(net, sk, r)) { /* * Grab it and keep until we fill @@ -142,9 +141,8 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); struct net *net = sock_net(skb->sk); struct inet_diag_dump_data *cb_data; - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int num, s_num, slot, s_slot; + struct hlist_head *hlist; struct sock *sk = NULL; struct nlattr *bc; @@ -161,7 +159,7 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num = 0; hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d0cc4ef2b85..40fe70fc2015 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -25,6 +25,7 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1198,6 +1199,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ea370afa70ed..b9d55277cb85 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2780,7 +2780,7 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { while (iter->cur_sk < iter->end_sk) - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, @@ -2941,7 +2941,7 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) * st->bucket. See tcp_seek_last_pos(). */ st->offset++; - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } if (iter->cur_sk < iter->end_sk) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c314fdde0097..95a55c6630ad 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1965,8 +1965,13 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + u8 icmp6_type; - ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + icmp6_type = fl6->fl6_icmp_type; + else + icmp6_type = icmp6_hdr(skb)->icmp6_type; + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bac9ba747bde..a327aa481df4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -141,10 +141,9 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister); static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; const struct in6_addr *saddr; const struct in6_addr *daddr; + struct hlist_head *hlist; struct sock *sk; bool delivered = false; __u8 hash; @@ -155,7 +154,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { int filtered; if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, @@ -333,15 +332,14 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int hash; hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index 488aec9e1a74..d1876f192225 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -32,7 +32,8 @@ static void *ipv6_rpl_segdata_pos(const struct ipv6_rpl_sr_hdr *hdr, int i) size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre) { - return (n * IPV6_PFXTAIL_LEN(cmpri)) + IPV6_PFXTAIL_LEN(cmpre); + return sizeof(struct ipv6_rpl_sr_hdr) + (n * IPV6_PFXTAIL_LEN(cmpri)) + + IPV6_PFXTAIL_LEN(cmpre); } void ipv6_rpl_srh_decompress(struct ipv6_rpl_sr_hdr *outhdr, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fb2f33ee3a7..a675acfb901d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1395,9 +1395,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 4db5a554bdbd..41a74fc84ca1 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -677,8 +677,8 @@ MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like - * enums +/* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, + * because __stringify doesn't like enums */ -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); -MODULE_ALIAS_NET_PF_PROTO(PF_INET, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 115, 2); +MODULE_ALIAS_NET_PF_PROTO(PF_INET, 115); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 2478aa60145f..5137ea1861ce 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -806,8 +806,8 @@ MODULE_AUTHOR("Chris Elston <celston@katalix.com>"); MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6"); MODULE_VERSION("1.0"); -/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like - * enums +/* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, + * because __stringify doesn't like enums */ -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP); -MODULE_ALIAS_NET_PF_PROTO(PF_INET6, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 115, 2); +MODULE_ALIAS_NET_PF_PROTO(PF_INET6, 115); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index e8de500eb9f3..af57616d2f1d 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2769,14 +2769,6 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta if (sdata->crypto_tx_tailroom_needed_cnt) tailroom = IEEE80211_ENCRYPT_TAILROOM; - if (!--mesh_hdr->ttl) { - if (multicast) - goto rx_accept; - - IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); - return RX_DROP_MONITOR; - } - if (mesh_hdr->flags & MESH_FLAGS_AE) { struct mesh_path *mppath; char *proxied_addr; @@ -2807,6 +2799,14 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta if (ether_addr_equal(sdata->vif.addr, eth->h_dest)) goto rx_accept; + if (!--mesh_hdr->ttl) { + if (multicast) + goto rx_accept; + + IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); + return RX_DROP_MONITOR; + } + if (!ifmsh->mshcfg.dot11MeshForwarding) { if (is_multicast_ether_addr(eth->h_dest)) goto rx_accept; @@ -2833,6 +2833,9 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta if (skb_cow_head(fwd_skb, hdrlen - sizeof(struct ethhdr))) return RX_DROP_UNUSABLE; + + if (skb_linearize(fwd_skb)) + return RX_DROP_UNUSABLE; } fwd_hdr = skb_push(fwd_skb, hdrlen - sizeof(struct ethhdr)); @@ -2847,7 +2850,7 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta hdrlen += ETH_ALEN; else fwd_skb->protocol = htons(fwd_skb->len - hdrlen); - skb_set_network_header(fwd_skb, hdrlen); + skb_set_network_header(fwd_skb, hdrlen + 2); info = IEEE80211_SKB_CB(fwd_skb); memset(info, 0, sizeof(*info)); @@ -2896,7 +2899,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; __le16 fc = hdr->frame_control; struct sk_buff_head frame_list; - static ieee80211_rx_result res; + ieee80211_rx_result res; struct ethhdr ethhdr; const u8 *check_da = ethhdr.h_dest, *check_sa = ethhdr.h_source; @@ -2930,7 +2933,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) data_offset, true)) return RX_DROP_UNUSABLE; - if (rx->sta && rx->sta->amsdu_mesh_control < 0) { + if (rx->sta->amsdu_mesh_control < 0) { bool valid_std = ieee80211_is_valid_amsdu(skb, true); bool valid_nonstd = ieee80211_is_valid_amsdu(skb, false); @@ -3006,7 +3009,7 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) } } - if (is_multicast_ether_addr(hdr->addr1)) + if (is_multicast_ether_addr(hdr->addr1) || !rx->sta) return RX_DROP_UNUSABLE; if (rx->key) { @@ -3037,7 +3040,7 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) struct net_device *dev = sdata->dev; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; __le16 fc = hdr->frame_control; - static ieee80211_rx_result res; + ieee80211_rx_result res; bool port_control; int err; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 7d68dbc872d7..941bda9141fa 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1264,7 +1264,8 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta) list_del_rcu(&sta->list); sta->removed = true; - drv_sta_pre_rcu_remove(local, sta->sdata, sta); + if (sta->uploaded) + drv_sta_pre_rcu_remove(local, sta->sdata, sta); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && rcu_access_pointer(sdata->u.vlan.sta) == sta) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3aceb3b731bf..8c397650b96f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -4906,7 +4906,7 @@ u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) &eht_cap->eht_cap_elem, is_ap); return 2 + 1 + - sizeof(he_cap->he_cap_elem) + n + + sizeof(eht_cap->eht_cap_elem) + n + ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], eht_cap->eht_cap_elem.phy_cap_info); return 0; diff --git a/net/mac802154/scan.c b/net/mac802154/scan.c index 9b0933a185eb..5c191bedd72c 100644 --- a/net/mac802154/scan.c +++ b/net/mac802154/scan.c @@ -52,7 +52,7 @@ static int mac802154_scan_cleanup_locked(struct ieee802154_local *local, request = rcu_replace_pointer(local->scan_req, NULL, 1); if (!request) return 0; - kfree_rcu(request); + kvfree_rcu_mightsleep(request); /* Advertize first, while we know the devices cannot be removed */ if (aborted) @@ -403,7 +403,7 @@ int mac802154_stop_beacons_locked(struct ieee802154_local *local, request = rcu_replace_pointer(local->beacon_req, NULL, 1); if (!request) return 0; - kfree_rcu(request); + kvfree_rcu_mightsleep(request); nl802154_beaconing_done(wpan_dev); diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index d237d142171c..bceaab8dd8e4 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -9,11 +9,18 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req) { - struct sock *ssk = subflow->tcp_sock; - struct sock *sk = subflow->conn; + struct sock *sk, *ssk; struct sk_buff *skb; struct tcp_sock *tp; + /* on early fallback the subflow context is deleted by + * subflow_syn_recv_sock() + */ + if (!subflow) + return; + + ssk = subflow->tcp_sock; + sk = subflow->conn; tp = tcp_sk(ssk); subflow->is_mptfo = 1; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b30cea2fbf3f..355f798d575a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1192,9 +1192,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && - mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) && - schedule_work(&msk->work)) - sock_hold(subflow->conn); + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64)) + mptcp_schedule_work((struct sock *)msk); return true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 60b23b2716c4..b998e9df53ce 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2315,7 +2315,26 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, unsigned int flags) { struct mptcp_sock *msk = mptcp_sk(sk); - bool need_push, dispose_it; + bool dispose_it, need_push = false; + + /* If the first subflow moved to a close state before accept, e.g. due + * to an incoming reset, mptcp either: + * - if either the subflow or the msk are dead, destroy the context + * (the subflow socket is deleted by inet_child_forget) and the msk + * - otherwise do nothing at the moment and take action at accept and/or + * listener shutdown - user-space must be able to accept() the closed + * socket. + */ + if (msk->in_accept_queue && msk->first == ssk) { + if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) + return; + + /* ensure later check in mptcp_worker() will dispose the msk */ + sock_set_flag(sk, SOCK_DEAD); + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + mptcp_subflow_drop_ctx(ssk); + goto out_release; + } dispose_it = !msk->subflow || ssk != msk->subflow->sk; if (dispose_it) @@ -2351,28 +2370,22 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (!inet_csk(ssk)->icsk_ulp_ops) { WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); - } else if (msk->in_accept_queue && msk->first == ssk) { - /* if the first subflow moved to a close state, e.g. due to - * incoming reset and we reach here before inet_child_forget() - * the TCP stack could later try to close it via - * inet_csk_listen_stop(), or deliver it to the user space via - * accept(). - * We can't delete the subflow - or risk a double free - nor let - * the msk survive - or will be leaked in the non accept scenario: - * fallback and let TCP cope with the subflow cleanup. - */ - WARN_ON_ONCE(sock_flag(ssk, SOCK_DEAD)); - mptcp_subflow_drop_ctx(ssk); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ - if (ssk->sk_state == TCP_LISTEN) + if (ssk->sk_state == TCP_LISTEN) { + tcp_set_state(ssk, TCP_CLOSE); + mptcp_subflow_queue_clean(sk, ssk); + inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); + } __tcp_close(ssk, 0); /* close acquired an extra ref */ __sock_put(ssk); } + +out_release: release_sock(ssk); sock_put(ssk); @@ -2427,21 +2440,14 @@ static void __mptcp_close_subflow(struct sock *sk) mptcp_close_ssk(sk, ssk, subflow); } - /* if the MPC subflow has been closed before the msk is accepted, - * msk will never be accept-ed, close it now - */ - if (!msk->first && msk->in_accept_queue) { - sock_set_flag(sk, SOCK_DEAD); - inet_sk_state_store(sk, TCP_CLOSE); - } } -static bool mptcp_check_close_timeout(const struct sock *sk) +static bool mptcp_should_close(const struct sock *sk) { s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp; struct mptcp_subflow_context *subflow; - if (delta >= TCP_TIMEWAIT_LEN) + if (delta >= TCP_TIMEWAIT_LEN || mptcp_sk(sk)->in_accept_queue) return true; /* if all subflows are in closed status don't bother with additional @@ -2626,7 +2632,7 @@ static void mptcp_worker(struct work_struct *work) lock_sock(sk); state = sk->sk_state; - if (unlikely(state == TCP_CLOSE)) + if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_data_fin_ack(sk); @@ -2649,7 +2655,7 @@ static void mptcp_worker(struct work_struct *work) * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_check_close_timeout(sk)) { + if (mptcp_should_close(sk)) { inet_sk_state_store(sk, TCP_CLOSE); mptcp_do_fastclose(sk); } @@ -2895,6 +2901,14 @@ static void __mptcp_destroy_sock(struct sock *sk) sock_put(sk); } +void __mptcp_unaccepted_force_close(struct sock *sk) +{ + sock_set_flag(sk, SOCK_DEAD); + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_do_fastclose(sk); + __mptcp_destroy_sock(sk); +} + static __poll_t mptcp_check_readable(struct mptcp_sock *msk) { /* Concurrent splices from sk_receive_queue into receive_queue will @@ -3733,6 +3747,18 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk->sk_socket) mptcp_sock_graft(ssk, newsock); } + + /* Do late cleanup for the first subflow as necessary. Also + * deal with bad peers not doing a complete shutdown. + */ + if (msk->first && + unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { + __mptcp_close_ssk(newsk, msk->first, + mptcp_subflow_ctx(msk->first), 0); + if (unlikely(list_empty(&msk->conn_list))) + inet_sk_state_store(newsk, TCP_CLOSE); + } + release_sock(newsk); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 339a6f072989..d6469b6ab38e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -629,10 +629,12 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); void __mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); +void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); void mptcp_cancel_work(struct sock *sk); +void __mptcp_unaccepted_force_close(struct sock *sk); void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a0041360ee9d..281c1cc8dc8d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -408,9 +408,8 @@ void mptcp_subflow_reset(struct sock *ssk) tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); - if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && - schedule_work(&mptcp_sk(sk)->work)) - return; /* worker will put sk for us */ + if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } @@ -724,9 +723,12 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) if (!ctx) return; - subflow_ulp_fallback(ssk, ctx); - if (ctx->conn) - sock_put(ctx->conn); + list_del(&mptcp_subflow_ctx(ssk)->node); + if (inet_csk(ssk)->icsk_ulp_ops) { + subflow_ulp_fallback(ssk, ctx); + if (ctx->conn) + sock_put(ctx->conn); + } kfree_rcu(ctx, rcu); } @@ -1118,8 +1120,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } else { - if (updated && schedule_work(&msk->work)) - sock_hold((struct sock *)msk); + if (updated) + mptcp_schedule_work((struct sock *)msk); return MAPPING_DATA_FIN; } @@ -1222,17 +1224,12 @@ 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) { - struct sock *sk = (struct sock *)msk; - if (likely(ssk->sk_state != TCP_CLOSE)) return; if (skb_queue_empty(&ssk->sk_receive_queue) && - !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) { - sock_hold(sk); - if (!schedule_work(&msk->work)) - sock_put(sk); - } + !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + mptcp_schedule_work((struct sock *)msk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) @@ -1825,6 +1822,77 @@ static void subflow_state_change(struct sock *sk) } } +void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) +{ + struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; + struct mptcp_sock *msk, *next, *head = NULL; + struct request_sock *req; + struct sock *sk; + + /* build a list of all unaccepted mptcp sockets */ + spin_lock_bh(&queue->rskq_lock); + for (req = queue->rskq_accept_head; req; req = req->dl_next) { + struct mptcp_subflow_context *subflow; + struct sock *ssk = req->sk; + + if (!sk_is_mptcp(ssk)) + continue; + + subflow = mptcp_subflow_ctx(ssk); + if (!subflow || !subflow->conn) + continue; + + /* skip if already in list */ + sk = subflow->conn; + msk = mptcp_sk(sk); + if (msk->dl_next || msk == head) + continue; + + sock_hold(sk); + msk->dl_next = head; + head = msk; + } + spin_unlock_bh(&queue->rskq_lock); + if (!head) + return; + + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (msk = head; msk; msk = next) { + sk = (struct sock *)msk; + + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); + next = msk->dl_next; + msk->dl_next = NULL; + + __mptcp_unaccepted_force_close(sk); + release_sock(sk); + + /* lockdep will report a false positive ABBA deadlock + * between cancel_work_sync and the listener socket. + * The involved locks belong to different sockets WRT + * the existing AB chain. + * Using a per socket key is problematic as key + * deregistration requires process context and must be + * performed at socket disposal time, in atomic + * context. + * Just tell lockdep to consider the listener socket + * released here. + */ + mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); + mptcp_cancel_work(sk); + mutex_acquire(&listener_sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + sock_put(sk); + } + + /* we are still under the listener msk socket lock */ + lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); +} + static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6004d4b24451..e48ab8dfb541 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3447,6 +3447,64 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) return 0; } +int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; + const struct nft_data *data; + int err; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) + return 0; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; + default: + break; + } + + return 0; +} + +struct nft_set_elem_catchall { + struct list_head list; + struct rcu_head rcu; + void *elem; +}; + +int nft_set_catchall_validate(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_elem elem; + 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; + + elem.priv = catchall->elem; + ret = nft_setelem_validate(ctx, set, NULL, &elem); + if (ret < 0) + return ret; + } + + return ret; +} + static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla); @@ -4759,12 +4817,6 @@ err_set_name: return err; } -struct nft_set_elem_catchall { - struct list_head list; - struct rcu_head rcu; - void *elem; -}; - static void nft_set_catchall_destroy(const struct nft_ctx *ctx, struct nft_set *set) { @@ -6056,7 +6108,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) + if (((flags & NFT_SET_ELEM_CATCHALL) && nla[NFTA_SET_ELEM_KEY]) || + (!(flags & NFT_SET_ELEM_CATCHALL) && !nla[NFTA_SET_ELEM_KEY])) return -EINVAL; if (flags != 0) { @@ -7052,7 +7105,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, } if (nla[NFTA_OBJ_USERDATA]) { - obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL); + obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL_ACCOUNT); if (obj->udata == NULL) goto err_userdata; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index cae5a6724163..cecf8ab90e58 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -199,37 +199,6 @@ nla_put_failure: return -1; } -static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_set_elem *elem) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); - struct nft_ctx *pctx = (struct nft_ctx *)ctx; - const struct nft_data *data; - int err; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - pctx->level++; - err = nft_chain_validate(ctx, data->verdict.chain); - if (err < 0) - return err; - pctx->level--; - break; - default: - break; - } - - return 0; -} - static int nft_lookup_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **d) @@ -245,9 +214,12 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, iter.skip = 0; iter.count = 0; iter.err = 0; - iter.fn = nft_lookup_validate_setelem; + iter.fn = nft_setelem_validate; priv->set->ops->walk(ctx, priv->set, &iter); + if (!iter.err) + iter.err = nft_set_catchall_validate(ctx, priv->set); + if (iter.err < 0) return iter.err; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c64277659753..f365dfdd672d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1952,7 +1952,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - size_t copied; + size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; @@ -1985,9 +1985,10 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, #endif /* Record the max length of recvmsg() calls for future allocations */ - nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); - nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, - SKB_WITH_OVERHEAD(32768)); + max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); + max_recvmsg_len = min_t(size_t, max_recvmsg_len, + SKB_WITH_OVERHEAD(32768)); + WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { @@ -2236,6 +2237,7 @@ static int netlink_dump(struct sock *sk) struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; + size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; @@ -2258,8 +2260,9 @@ static int netlink_dump(struct sock *sk) cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); - if (alloc_min_size < nlk->max_recvmsg_len) { - alloc_size = nlk->max_recvmsg_len; + max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); + if (alloc_min_size < max_recvmsg_len) { + alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ca3ebfdb3023..a8cf9a88758e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -913,7 +913,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport)) { + if (likely(vport && netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 5c2fb992803b..76f0434d3d06 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -393,10 +393,12 @@ static struct qrtr_node *qrtr_node_lookup(unsigned int nid) struct qrtr_node *node; unsigned long flags; + mutex_lock(&qrtr_node_lock); spin_lock_irqsave(&qrtr_nodes_lock, flags); node = radix_tree_lookup(&qrtr_nodes, nid); node = qrtr_node_acquire(node); spin_unlock_irqrestore(&qrtr_nodes_lock, flags); + mutex_unlock(&qrtr_node_lock); return node; } @@ -496,6 +498,11 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!size || len != ALIGN(size, 4) + hdrlen) goto err; + if ((cb->type == QRTR_TYPE_NEW_SERVER || + cb->type == QRTR_TYPE_RESUME_TX) && + size < sizeof(struct qrtr_ctrl_pkt)) + goto err; + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && cb->type != QRTR_TYPE_RESUME_TX) goto err; @@ -508,9 +515,6 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) /* Remote node endpoint can bridge other distant nodes */ const struct qrtr_ctrl_pkt *pkt; - if (size < sizeof(*pkt)) - goto err; - pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); } diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 722936f7dd98..0f25a386138c 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -274,7 +274,7 @@ err: return NULL; } -static int server_del(struct qrtr_node *node, unsigned int port) +static int server_del(struct qrtr_node *node, unsigned int port, bool bcast) { struct qrtr_lookup *lookup; struct qrtr_server *srv; @@ -287,7 +287,7 @@ static int server_del(struct qrtr_node *node, unsigned int port) radix_tree_delete(&node->servers, port); /* Broadcast the removal of local servers */ - if (srv->node == qrtr_ns.local_node) + if (srv->node == qrtr_ns.local_node && bcast) service_announce_del(&qrtr_ns.bcast_sq, srv); /* Announce the service's disappearance to observers */ @@ -373,7 +373,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) } slot = radix_tree_iter_resume(slot, &iter); rcu_read_unlock(); - server_del(node, srv->port); + server_del(node, srv->port, true); rcu_read_lock(); } rcu_read_unlock(); @@ -459,10 +459,13 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, kfree(lookup); } - /* Remove the server belonging to this port */ + /* Remove the server belonging to this port but don't broadcast + * DEL_SERVER. Neighbours would've already removed the server belonging + * to this port due to the DEL_CLIENT broadcast from qrtr_port_remove(). + */ node = node_get(node_id); if (node) - server_del(node, port); + server_del(node, port, false); /* Advertise the removal of this client to all local servers */ local_node = node_get(qrtr_ns.local_node); @@ -567,7 +570,7 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, if (!node) return -ENOENT; - return server_del(node, port); + return server_del(node, port, true); } static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 786dbfdad772..e9d1b2f2ff0a 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/mod_devicetable.h> #include <linux/rfkill.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/clk.h> #include <linux/slab.h> diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2a6b6be0811b..35785a36c802 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3235,6 +3235,9 @@ int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, err_miss_alloc: tcf_exts_destroy(exts); +#ifdef CONFIG_NET_CLS_ACT + exts->actions = NULL; +#endif return err; } EXPORT_SYMBOL(tcf_exts_init_ex); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index cf5ebe43b3b4..02098a02943e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -421,15 +421,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } else weight = 1; - if (tb[TCA_QFQ_LMAX]) { + if (tb[TCA_QFQ_LMAX]) lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - } else + else lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { + pr_notice("qfq: invalid max length %u\n", lmax); + return -EINVAL; + } + inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b91616f819de..218e0982c370 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1830,6 +1830,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) goto err; + if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { + err = -EINVAL; + goto err; + } } if (sctp_state(asoc, CLOSED)) { diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 94727feb07b3..b046b11200c9 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1154,7 +1154,8 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + (void *)pos <= (void *)chunk->subh.ifwdtsn_hdr->skip + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c6b4a62276f6..50c38b624f77 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3270,6 +3270,17 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, sk_common_release(sk); goto out; } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); } else { smc->clcsock = clcsock; } diff --git a/net/sunrpc/auth_gss/gss_krb5_test.c b/net/sunrpc/auth_gss/gss_krb5_test.c index ce0541e32fc9..95ca783795c5 100644 --- a/net/sunrpc/auth_gss/gss_krb5_test.c +++ b/net/sunrpc/auth_gss/gss_krb5_test.c @@ -73,7 +73,6 @@ static void checksum_case(struct kunit *test) { const struct gss_krb5_test_param *param = test->param_value; struct xdr_buf buf = { - .head[0].iov_base = param->plaintext->data, .head[0].iov_len = param->plaintext->len, .len = param->plaintext->len, }; @@ -99,6 +98,10 @@ static void checksum_case(struct kunit *test) err = crypto_ahash_setkey(tfm, Kc.data, Kc.len); KUNIT_ASSERT_EQ(test, err, 0); + buf.head[0].iov_base = kunit_kzalloc(test, buf.head[0].iov_len, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf.head[0].iov_base); + memcpy(buf.head[0].iov_base, param->plaintext->data, buf.head[0].iov_len); + checksum.len = gk5e->cksumlength; checksum.data = kunit_kzalloc(test, checksum.len, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, checksum.data); @@ -1327,6 +1330,7 @@ static void rfc6803_encrypt_case(struct kunit *test) if (!gk5e) kunit_skip(test, "Encryption type is not available"); + memset(usage_data, 0, sizeof(usage_data)); usage.data[3] = param->constant; Ke.len = gk5e->Ke_length; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 983c5891cb56..4246363cb095 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -416,14 +416,23 @@ static int unix_gid_hash(kuid_t uid) return hash_long(from_kuid(&init_user_ns, uid), GID_HASHBITS); } -static void unix_gid_put(struct kref *kref) +static void unix_gid_free(struct rcu_head *rcu) { - struct cache_head *item = container_of(kref, struct cache_head, ref); - struct unix_gid *ug = container_of(item, struct unix_gid, h); + struct unix_gid *ug = container_of(rcu, struct unix_gid, rcu); + struct cache_head *item = &ug->h; + if (test_bit(CACHE_VALID, &item->flags) && !test_bit(CACHE_NEGATIVE, &item->flags)) put_group_info(ug->gi); - kfree_rcu(ug, rcu); + kfree(ug); +} + +static void unix_gid_put(struct kref *kref) +{ + struct cache_head *item = container_of(kref, struct cache_head, ref); + struct unix_gid *ug = container_of(item, struct unix_gid, h); + + call_rcu(&ug->rcu, unix_gid_free); } static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index adcbedc244d6..6cacd70a15ff 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2158,6 +2158,7 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) switch (skst) { case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: + case TCP_LAST_ACK: break; case TCP_ESTABLISHED: case TCP_CLOSE_WAIT: diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 6564192e7f20..ee78b4082ef9 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -94,6 +94,11 @@ virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, info->op, info->flags); + if (info->vsk && !skb_set_owner_sk_safe(skb, sk_vsock(info->vsk))) { + WARN_ONCE(1, "failed to allocate skb on vsock socket with sk_refcnt == 0\n"); + goto out; + } + return skb; out: @@ -363,6 +368,13 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, u32 free_space; spin_lock_bh(&vvs->rx_lock); + + if (WARN_ONCE(skb_queue_empty(&vvs->rx_queue) && vvs->rx_bytes, + "rx_queue is empty, but rx_bytes is non-zero\n")) { + spin_unlock_bh(&vvs->rx_lock); + return err; + } + while (total < len && !skb_queue_empty(&vvs->rx_queue)) { skb = skb_peek(&vvs->rx_queue); @@ -1068,7 +1080,7 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, memcpy(skb_put(last_skb, skb->len), skb->data, skb->len); free_pkt = true; last_hdr->flags |= hdr->flags; - last_hdr->len = cpu_to_le32(last_skb->len); + le32_add_cpu(&last_hdr->len, len); goto out; } } @@ -1296,6 +1308,11 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, goto free_pkt; } + if (!skb_set_owner_sk_safe(skb, sk)) { + WARN_ONCE(1, "receiving vsock socket has sk_refcnt == 0\n"); + goto free_pkt; + } + vsk = vsock_sk(sk); lock_sock(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 36eb16a40745..95cc4d79ba29 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1842,7 +1842,13 @@ static ssize_t vmci_transport_stream_enqueue( struct msghdr *msg, size_t len) { - return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0); + ssize_t err; + + err = vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0); + if (err < 0) + err = -ENOMEM; + + return err; } static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk) diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 671e03240fc5..89905c092645 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -15,7 +15,6 @@ struct vsock_loopback { struct workqueue_struct *workqueue; - spinlock_t pkt_list_lock; /* protects pkt_list */ struct sk_buff_head pkt_queue; struct work_struct pkt_work; }; @@ -32,9 +31,7 @@ static int vsock_loopback_send_pkt(struct sk_buff *skb) struct vsock_loopback *vsock = &the_vsock_loopback; int len = skb->len; - spin_lock_bh(&vsock->pkt_list_lock); skb_queue_tail(&vsock->pkt_queue, skb); - spin_unlock_bh(&vsock->pkt_list_lock); queue_work(vsock->workqueue, &vsock->pkt_work); @@ -113,9 +110,9 @@ static void vsock_loopback_work(struct work_struct *work) skb_queue_head_init(&pkts); - spin_lock_bh(&vsock->pkt_list_lock); + spin_lock_bh(&vsock->pkt_queue.lock); skb_queue_splice_init(&vsock->pkt_queue, &pkts); - spin_unlock_bh(&vsock->pkt_list_lock); + spin_unlock_bh(&vsock->pkt_queue.lock); while ((skb = __skb_dequeue(&pkts))) { virtio_transport_deliver_tap_pkt(skb); @@ -132,7 +129,6 @@ static int __init vsock_loopback_init(void) if (!vsock->workqueue) return -ENOMEM; - spin_lock_init(&vsock->pkt_list_lock); skb_queue_head_init(&vsock->pkt_queue); INIT_WORK(&vsock->pkt_work, vsock_loopback_work); @@ -156,9 +152,7 @@ static void __exit vsock_loopback_exit(void) flush_work(&vsock->pkt_work); - spin_lock_bh(&vsock->pkt_list_lock); virtio_vsock_skb_queue_purge(&vsock->pkt_queue); - spin_unlock_bh(&vsock->pkt_list_lock); destroy_workqueue(vsock->workqueue); } |