diff options
Diffstat (limited to 'net')
116 files changed, 1451 insertions, 812 deletions
diff --git a/net/ax25/Kconfig b/net/ax25/Kconfig index d3a9843a043d..fdb666607f10 100644 --- a/net/ax25/Kconfig +++ b/net/ax25/Kconfig @@ -10,7 +10,7 @@ menuconfig HAMRADIO If you want to connect your Linux box to an amateur radio, answer Y here. You want to read <https://www.tapr.org/> and more specifically about AX.25 on Linux - <http://www.linux-ax25.org/>. + <https://linux-ax25.in-berlin.de>. Note that the answer to this question won't directly affect the kernel: saying N will just cause the configurator to skip all @@ -61,7 +61,7 @@ config AX25_DAMA_SLAVE configuration. Linux cannot yet act as a DAMA server. This option only compiles DAMA slave support into the kernel. It still needs to be enabled at runtime. For more about DAMA see - <http://www.linux-ax25.org>. If unsure, say Y. + <https://linux-ax25.in-berlin.de>. If unsure, say Y. # placeholder until implemented config AX25_DAMA_MASTER @@ -87,9 +87,9 @@ config NETROM A comprehensive listing of all the software for Linux amateur radio users as well as information about how to configure an AX.25 port is contained in the Linux Ham Wiki, available from - <http://www.linux-ax25.org>. You also might want to check out the - file <file:Documentation/networking/ax25.rst>. More information about - digital amateur radio in general is on the WWW at + <https://linux-ax25.in-berlin.de>. You also might want to check out + the file <file:Documentation/networking/ax25.rst>. More information + about digital amateur radio in general is on the WWW at <https://www.tapr.org/>. To compile this driver as a module, choose M here: the @@ -106,9 +106,9 @@ config ROSE A comprehensive listing of all the software for Linux amateur radio users as well as information about how to configure an AX.25 port is contained in the Linux Ham Wiki, available from - <http://www.linux-ax25.org>. You also might want to check out the - file <file:Documentation/networking/ax25.rst>. More information about - digital amateur radio in general is on the WWW at + <https://linux-ax25.in-berlin.de>. You also might want to check out + the file <file:Documentation/networking/ax25.rst>. More information + about digital amateur radio in general is on the WWW at <https://www.tapr.org/>. To compile this driver as a module, choose M here: the diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 9d5057cef30a..73470cc3518a 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1627,6 +1627,15 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-EOPNOTSUPP); } + /* Reject outgoing connection to device with same BD ADDR against + * CVE-2020-26555 + */ + if (!bacmp(&hdev->bdaddr, dst)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + dst); + return ERR_PTR(-ECONNREFUSED); + } + acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); @@ -2413,34 +2422,41 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, if (!test_bit(HCI_CONN_AUTH, &conn->flags)) goto auth; - /* An authenticated FIPS approved combination key has sufficient - * security for security level 4. */ - if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256 && - sec_level == BT_SECURITY_FIPS) - goto encrypt; - - /* An authenticated combination key has sufficient security for - security level 3. */ - if ((conn->key_type == HCI_LK_AUTH_COMBINATION_P192 || - conn->key_type == HCI_LK_AUTH_COMBINATION_P256) && - sec_level == BT_SECURITY_HIGH) - goto encrypt; - - /* An unauthenticated combination key has sufficient security for - security level 1 and 2. */ - if ((conn->key_type == HCI_LK_UNAUTH_COMBINATION_P192 || - conn->key_type == HCI_LK_UNAUTH_COMBINATION_P256) && - (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW)) - goto encrypt; - - /* A combination key has always sufficient security for the security - levels 1 or 2. High security level requires the combination key - is generated using maximum PIN code length (16). - For pre 2.1 units. */ - if (conn->key_type == HCI_LK_COMBINATION && - (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW || - conn->pin_length == 16)) - goto encrypt; + switch (conn->key_type) { + case HCI_LK_AUTH_COMBINATION_P256: + /* An authenticated FIPS approved combination key has + * sufficient security for security level 4 or lower. + */ + if (sec_level <= BT_SECURITY_FIPS) + goto encrypt; + break; + case HCI_LK_AUTH_COMBINATION_P192: + /* An authenticated combination key has sufficient security for + * security level 3 or lower. + */ + if (sec_level <= BT_SECURITY_HIGH) + goto encrypt; + break; + case HCI_LK_UNAUTH_COMBINATION_P192: + case HCI_LK_UNAUTH_COMBINATION_P256: + /* An unauthenticated combination key has sufficient security + * for security level 2 or lower. + */ + if (sec_level <= BT_SECURITY_MEDIUM) + goto encrypt; + break; + case HCI_LK_COMBINATION: + /* A combination key has always sufficient security for the + * security levels 2 or lower. High security level requires the + * combination key is generated using maximum PIN code length + * (16). For pre 2.1 units. + */ + if (sec_level <= BT_SECURITY_MEDIUM || conn->pin_length == 16) + goto encrypt; + break; + default: + break; + } auth: if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a5992f1b3c9b..195aea2198a9 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2617,7 +2617,11 @@ int hci_register_dev(struct hci_dev *hdev) if (id < 0) return id; - snprintf(hdev->name, sizeof(hdev->name), "hci%d", id); + error = dev_set_name(&hdev->dev, "hci%u", id); + if (error) + return error; + + hdev->name = dev_name(&hdev->dev); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); @@ -2639,8 +2643,6 @@ int hci_register_dev(struct hci_dev *hdev) if (!IS_ERR_OR_NULL(bt_debugfs)) hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs); - dev_set_name(&hdev->dev, "%s", hdev->name); - error = device_add(&hdev->dev); if (error < 0) goto err_wqueue; @@ -2784,6 +2786,7 @@ void hci_release_dev(struct hci_dev *hdev) hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); + hci_codec_list_clear(&hdev->local_codecs); hci_dev_unlock(hdev); ida_simple_remove(&hci_index_ida, hdev->id); @@ -3418,7 +3421,12 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) if (c->type == type && c->sent) { bt_dev_err(hdev, "killing stalled connection %pMR", &c->dst); + /* hci_disconnect might sleep, so, we have to release + * the RCU read lock before calling it. + */ + rcu_read_unlock(); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); + rcu_read_lock(); } } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 35f251041eeb..1e1c9147356c 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -26,6 +26,8 @@ /* Bluetooth HCI event handling. */ #include <asm/unaligned.h> +#include <linux/crypto.h> +#include <crypto/algapi.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -33,6 +35,7 @@ #include "hci_request.h" #include "hci_debugfs.h" +#include "hci_codec.h" #include "a2mp.h" #include "amp.h" #include "smp.h" @@ -3267,6 +3270,16 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type); + /* Reject incoming connection from device with same BD ADDR against + * CVE-2020-26555 + */ + if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + &ev->bdaddr); + hci_reject_conn(hdev, &ev->bdaddr); + return; + } + mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type, &flags); @@ -4741,6 +4754,15 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, void *data, if (!conn) goto unlock; + /* Ignore NULL link key against CVE-2020-26555 */ + if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) { + bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR", + &ev->bdaddr); + hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_drop(conn); + goto unlock; + } + hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; hci_conn_drop(conn); @@ -5273,8 +5295,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * available, then do not declare that OOB data is * present. */ - if (!memcmp(data->rand256, ZERO_KEY, 16) || - !memcmp(data->hash256, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand256, ZERO_KEY, 16) || + !crypto_memneq(data->hash256, ZERO_KEY, 16)) return 0x00; return 0x02; @@ -5284,8 +5306,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * not supported by the hardware, then check that if * P-192 data values are present. */ - if (!memcmp(data->rand192, ZERO_KEY, 16) || - !memcmp(data->hash192, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand192, ZERO_KEY, 16) || + !crypto_memneq(data->hash192, ZERO_KEY, 16)) return 0x00; return 0x01; @@ -5302,7 +5324,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; hci_conn_hold(conn); @@ -5549,7 +5571,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; /* Reset the authentication requirement to unknown */ @@ -7020,6 +7042,14 @@ unlock: hci_dev_unlock(hdev); } +static int hci_iso_term_big_sync(struct hci_dev *hdev, void *data) +{ + u8 handle = PTR_UINT(data); + + return hci_le_terminate_big_sync(hdev, handle, + HCI_ERROR_LOCAL_HOST_TERM); +} + static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -7064,16 +7094,17 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, rcu_read_lock(); } + rcu_read_unlock(); + if (!ev->status && !i) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections * have been closed before the BIG creation * has completed. */ - hci_le_terminate_big_sync(hdev, ev->handle, - HCI_ERROR_LOCAL_HOST_TERM); + hci_cmd_sync_queue(hdev, hci_iso_term_big_sync, + UINT_PTR(ev->handle), NULL); - rcu_read_unlock(); hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h index b9c5a9823837..0be75cf0efed 100644 --- a/net/bluetooth/hci_request.h +++ b/net/bluetooth/hci_request.h @@ -71,7 +71,5 @@ struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn); void hci_req_add_le_passive_scan(struct hci_request *req); -void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next); - void hci_request_setup(struct hci_dev *hdev); void hci_request_cancel_all(struct hci_dev *hdev); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 5e4f718073b7..3e7cd330d731 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -488,7 +488,8 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) ni->type = hdev->dev_type; ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); - memcpy(ni->name, hdev->name, 8); + memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name, + strnlen(hdev->name, sizeof(ni->name)), '\0'); opcode = cpu_to_le16(HCI_MON_NEW_INDEX); break; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 9b93653c6197..a15ab0b874a9 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -413,11 +413,6 @@ static int hci_le_scan_restart_sync(struct hci_dev *hdev) LE_SCAN_FILTER_DUP_ENABLE); } -static int le_scan_restart_sync(struct hci_dev *hdev, void *data) -{ - return hci_le_scan_restart_sync(hdev); -} - static void le_scan_restart(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -427,15 +422,15 @@ static void le_scan_restart(struct work_struct *work) bt_dev_dbg(hdev, ""); - hci_dev_lock(hdev); - - status = hci_cmd_sync_queue(hdev, le_scan_restart_sync, NULL, NULL); + status = hci_le_scan_restart_sync(hdev); if (status) { bt_dev_err(hdev, "failed to restart LE scan: status %d", status); - goto unlock; + return; } + hci_dev_lock(hdev); + if (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) || !hdev->discovery.scan_start) goto unlock; @@ -5079,6 +5074,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); bacpy(&hdev->random_addr, BDADDR_ANY); + hci_codec_list_clear(&hdev->local_codecs); hci_dev_put(hdev); return err; @@ -5373,6 +5369,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { int err = 0; u16 handle = conn->handle; + bool disconnect = false; struct hci_conn *c; switch (conn->state) { @@ -5403,24 +5400,15 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) hci_dev_unlock(hdev); return 0; case BT_BOUND: - hci_dev_lock(hdev); - hci_conn_failed(conn, reason); - hci_dev_unlock(hdev); - return 0; + break; default: - hci_dev_lock(hdev); - conn->state = BT_CLOSED; - hci_disconn_cfm(conn, reason); - hci_conn_del(conn); - hci_dev_unlock(hdev); - return 0; + disconnect = true; + break; } hci_dev_lock(hdev); - /* Check if the connection hasn't been cleanup while waiting - * commands to complete. - */ + /* Check if the connection has been cleaned up concurrently */ c = hci_conn_hash_lookup_handle(hdev, handle); if (!c || c != conn) { err = 0; @@ -5432,7 +5420,13 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) * or in case of LE it was still scanning so it can be cleanup * safely. */ - hci_conn_failed(conn, reason); + if (disconnect) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, reason); + hci_conn_del(conn); + } else { + hci_conn_failed(conn, reason); + } unlock: hci_dev_unlock(hdev); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 16da946f5881..71248163ce9a 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -502,7 +502,7 @@ drop: } /* -------- Socket interface ---------- */ -static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *ba) +static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *src, bdaddr_t *dst) { struct sock *sk; @@ -510,7 +510,10 @@ static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *ba) if (sk->sk_state != BT_LISTEN) continue; - if (!bacmp(&iso_pi(sk)->src, ba)) + if (bacmp(&iso_pi(sk)->dst, dst)) + continue; + + if (!bacmp(&iso_pi(sk)->src, src)) return sk; } @@ -952,7 +955,7 @@ static int iso_listen_cis(struct sock *sk) write_lock(&iso_sk_list.lock); - if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src)) + if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src, &iso_pi(sk)->dst)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 9d7bc8b96b53..7431f89e897b 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -124,7 +124,7 @@ static int deliver_clone(const struct net_bridge_port *prev, skb = skb_clone(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return -ENOMEM; } @@ -268,7 +268,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, skb = skb_copy(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index c34a0b0901b0..c729528b5e85 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -181,12 +181,12 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if ((mdst && mdst->host_joined) || br_multicast_is_router(brmctx, skb)) { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } mcast_hit = true; } else { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } break; case BR_PKT_UNICAST: diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 15186247b59a..033034d68f1f 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -294,7 +294,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ /* tell br_dev_xmit to continue with forwarding */ nf_bridge->bridged_dnat = 1; /* FIXME Need to refragment */ - ret = neigh->output(neigh, skb); + ret = READ_ONCE(neigh->output)(neigh, skb); } neigh_release(neigh); return ret; diff --git a/net/can/isotp.c b/net/can/isotp.c index f02b5d3e4733..d1c6f206f429 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -948,21 +948,18 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; -wait_free_buffer: - /* we do not support multiple buffers - for now */ - if (wq_has_sleeper(&so->wait) && (msg->msg_flags & MSG_DONTWAIT)) - return -EAGAIN; + while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { + /* we do not support multiple buffers - for now */ + if (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_event_drop; - - if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { if (so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; - goto wait_free_buffer; + /* wait for complete transmission of current pdu */ + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_event_drop; } /* PDU size > default => try max_pdu_size */ diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 10a41cd9c523..3c8b78d9c4d1 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -459,8 +459,8 @@ int ceph_tcp_connect(struct ceph_connection *con) set_sock_callbacks(sock, con); con_sock_state_connecting(con); - ret = sock->ops->connect(sock, (struct sockaddr *)&ss, sizeof(ss), - O_NONBLOCK); + ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss), + O_NONBLOCK); if (ret == -EINPROGRESS) { dout("connect %s EINPROGRESS sk_state = %u\n", ceph_pr_addr(&con->peer_addr), diff --git a/net/core/datagram.c b/net/core/datagram.c index 176eb5834746..103d46fa0eeb 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -50,7 +50,7 @@ #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/pagemap.h> -#include <linux/uio.h> +#include <linux/iov_iter.h> #include <linux/indirect_call_wrapper.h> #include <net/protocol.h> @@ -61,6 +61,7 @@ #include <net/tcp_states.h> #include <trace/events/skb.h> #include <net/busy_poll.h> +#include <crypto/hash.h> /* * Is a socket 'connection oriented' ? @@ -489,6 +490,24 @@ short_copy: return 0; } +static size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, + struct iov_iter *i) +{ +#ifdef CONFIG_CRYPTO_HASH + struct ahash_request *hash = hashp; + struct scatterlist sg; + size_t copied; + + copied = copy_to_iter(addr, bytes, i); + sg_init_one(&sg, addr, copied); + ahash_request_set_crypt(hash, &sg, NULL, copied); + crypto_ahash_update(hash); + return copied; +#else + return 0; +#endif +} + /** * skb_copy_and_hash_datagram_iter - Copy datagram to an iovec iterator * and update a hash. @@ -716,6 +735,60 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) } EXPORT_SYMBOL(zerocopy_sg_from_iter); +static __always_inline +size_t copy_to_user_iter_csum(void __user *iter_to, size_t progress, + size_t len, void *from, void *priv2) +{ + __wsum next, *csum = priv2; + + next = csum_and_copy_to_user(from + progress, iter_to, len); + *csum = csum_block_add(*csum, next, progress); + return next ? 0 : len; +} + +static __always_inline +size_t memcpy_to_iter_csum(void *iter_to, size_t progress, + size_t len, void *from, void *priv2) +{ + __wsum *csum = priv2; + __wsum next = csum_partial_copy_nocheck(from, iter_to, len); + + *csum = csum_block_add(*csum, next, progress); + return 0; +} + +struct csum_state { + __wsum csum; + size_t off; +}; + +static size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, + struct iov_iter *i) +{ + struct csum_state *csstate = _csstate; + __wsum sum; + + if (WARN_ON_ONCE(i->data_source)) + return 0; + if (unlikely(iov_iter_is_discard(i))) { + // can't use csum_memcpy() for that one - data is not copied + csstate->csum = csum_block_add(csstate->csum, + csum_partial(addr, bytes, 0), + csstate->off); + csstate->off += bytes; + return bytes; + } + + sum = csum_shift(csstate->csum, csstate->off); + + bytes = iterate_and_advance2(i, bytes, (void *)addr, &sum, + copy_to_user_iter_csum, + memcpy_to_iter_csum); + csstate->csum = csum_shift(sum, csstate->off); + csstate->off += bytes; + return bytes; +} + /** * skb_copy_and_csum_datagram - Copy datagram to an iovec iterator * and update a checksum. diff --git a/net/core/dev.c b/net/core/dev.c index ccff2b6ef958..9f3f8930c691 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -69,7 +69,7 @@ */ #include <linux/uaccess.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/types.h> @@ -345,7 +345,6 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { list_del(&name_node->list); - netdev_name_node_del(name_node); kfree(name_node->name); netdev_name_node_free(name_node); } @@ -364,6 +363,8 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; + netdev_name_node_del(name_node); + synchronize_rcu(); __netdev_name_node_alt_destroy(name_node); return 0; @@ -380,6 +381,7 @@ static void netdev_name_node_alt_flush(struct net_device *dev) /* Device list insertion */ static void list_netdevice(struct net_device *dev) { + struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); @@ -390,6 +392,10 @@ static void list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock(&dev_base_lock); + + netdev_for_each_altname(dev, name_node) + netdev_name_node_add(net, name_node); + /* We reserved the ifindex, this can't fail */ WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); @@ -401,12 +407,16 @@ static void list_netdevice(struct net_device *dev) */ static void unlist_netdevice(struct net_device *dev, bool lock) { + struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); xa_erase(&net->dev_by_index, dev->ifindex); + netdev_for_each_altname(dev, name_node) + netdev_name_node_del(name_node); + /* Unlink dev from the device chain */ if (lock) write_lock(&dev_base_lock); @@ -1080,13 +1090,14 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -EINVAL; /* Use one page as a bit array of possible slots */ - inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC); + inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); if (!inuse) return -ENOMEM; for_each_netdev(net, d) { struct netdev_name_node *name_node; - list_for_each_entry(name_node, &d->name_node->list, list) { + + netdev_for_each_altname(d, name_node) { if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) @@ -1109,7 +1120,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } i = find_first_zero_bit(inuse, max_netdevices); - free_page((unsigned long) inuse); + bitmap_free(inuse); } snprintf(buf, IFNAMSIZ, name, i); @@ -1123,6 +1134,26 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -ENFILE; } +static int dev_prep_valid_name(struct net *net, struct net_device *dev, + const char *want_name, char *out_name) +{ + int ret; + + if (!dev_valid_name(want_name)) + return -EINVAL; + + if (strchr(want_name, '%')) { + ret = __dev_alloc_name(net, want_name, out_name); + return ret < 0 ? ret : 0; + } else if (netdev_name_in_use(net, want_name)) { + return -EEXIST; + } else if (out_name != want_name) { + strscpy(out_name, want_name, IFNAMSIZ); + } + + return 0; +} + static int dev_alloc_name_ns(struct net *net, struct net_device *dev, const char *name) @@ -1160,19 +1191,13 @@ EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { - BUG_ON(!net); - - if (!dev_valid_name(name)) - return -EINVAL; - - if (strchr(name, '%')) - return dev_alloc_name_ns(net, dev, name); - else if (netdev_name_in_use(net, name)) - return -EEXIST; - else if (dev->name != name) - strscpy(dev->name, name, IFNAMSIZ); + char buf[IFNAMSIZ]; + int ret; - return 0; + ret = dev_prep_valid_name(net, dev, name, buf); + if (ret >= 0) + strscpy(dev->name, buf, IFNAMSIZ); + return ret; } /** @@ -3292,15 +3317,19 @@ int skb_checksum_help(struct sk_buff *skb) offset = skb_checksum_start_offset(skb); ret = -EINVAL; - if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { + if (unlikely(offset >= skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); + WARN_ONCE(true, "offset (%d) >= skb_headlen() (%u)\n", + offset, skb_headlen(skb)); goto out; } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; - if (WARN_ON_ONCE(offset + sizeof(__sum16) > skb_headlen(skb))) { + if (unlikely(offset + sizeof(__sum16) > skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); + WARN_ONCE(true, "offset+2 (%zu) > skb_headlen() (%u)\n", + offset + sizeof(__sum16), skb_headlen(skb)); goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); @@ -11033,7 +11062,9 @@ EXPORT_SYMBOL(unregister_netdev); int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex) { + struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); + char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); @@ -11060,10 +11091,15 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, /* We get here if we can't use the current device name */ if (!pat) goto out; - err = dev_get_valid_name(net, dev, pat); + err = dev_prep_valid_name(net, dev, pat, new_name); if (err < 0) goto out; } + /* Check that none of the altnames conflicts. */ + err = -EEXIST; + netdev_for_each_altname(dev, name_node) + if (netdev_name_in_use(net, name_node->name)) + goto out; /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { @@ -11131,6 +11167,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); + if (new_name[0]) /* Rename the netdev to prepared name */ + strscpy(dev->name, new_name, IFNAMSIZ); + /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); WARN_ON(err); diff --git a/net/core/dev.h b/net/core/dev.h index e075e198092c..fa2e9c5c4122 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -62,6 +62,9 @@ struct netdev_name_node { int netdev_get_name(struct net *net, char *name, int ifindex); int dev_change_name(struct net_device *dev, const char *newname); +#define netdev_for_each_altname(dev, namenode) \ + list_for_each_entry((namenode), &(dev)->name_node->list, list) + int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b3b3af0e7844..272f09251343 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1446,7 +1446,7 @@ proto_again: break; } - nhoff += ntohs(hdr->message_length); + nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6b76cd103195..df81c1f0a570 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -251,7 +251,8 @@ bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) static int neigh_forced_gc(struct neigh_table *tbl) { - int max_clean = atomic_read(&tbl->gc_entries) - tbl->gc_thresh2; + int max_clean = atomic_read(&tbl->gc_entries) - + READ_ONCE(tbl->gc_thresh2); unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; @@ -280,7 +281,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) } } - tbl->last_flush = jiffies; + WRITE_ONCE(tbl->last_flush, jiffies); write_unlock_bh(&tbl->lock); @@ -410,7 +411,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, */ __skb_queue_purge(&n->arp_queue); n->arp_queue_len_bytes = 0; - n->output = neigh_blackhole; + WRITE_ONCE(n->output, neigh_blackhole); if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; else @@ -464,17 +465,17 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, { struct neighbour *n = NULL; unsigned long now = jiffies; - int entries; + int entries, gc_thresh3; if (exempt_from_gc) goto do_alloc; entries = atomic_inc_return(&tbl->gc_entries) - 1; - if (entries >= tbl->gc_thresh3 || - (entries >= tbl->gc_thresh2 && - time_after(now, tbl->last_flush + 5 * HZ))) { - if (!neigh_forced_gc(tbl) && - entries >= tbl->gc_thresh3) { + gc_thresh3 = READ_ONCE(tbl->gc_thresh3); + if (entries >= gc_thresh3 || + (entries >= READ_ONCE(tbl->gc_thresh2) && + time_after(now, READ_ONCE(tbl->last_flush) + 5 * HZ))) { + if (!neigh_forced_gc(tbl) && entries >= gc_thresh3) { net_info_ratelimited("%s: neighbor table overflow!\n", tbl->id); NEIGH_CACHE_STAT_INC(tbl, table_fulls); @@ -920,7 +921,7 @@ static void neigh_suspect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is suspected\n", neigh); - neigh->output = neigh->ops->output; + WRITE_ONCE(neigh->output, neigh->ops->output); } /* Neighbour state is OK; @@ -932,7 +933,7 @@ static void neigh_connect(struct neighbour *neigh) { neigh_dbg(2, "neigh %p is connected\n", neigh); - neigh->output = neigh->ops->connected_output; + WRITE_ONCE(neigh->output, neigh->ops->connected_output); } static void neigh_periodic_work(struct work_struct *work) @@ -955,13 +956,14 @@ static void neigh_periodic_work(struct work_struct *work) if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; - tbl->last_rand = jiffies; + + WRITE_ONCE(tbl->last_rand, jiffies); list_for_each_entry(p, &tbl->parms_list, list) p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + if (atomic_read(&tbl->entries) < READ_ONCE(tbl->gc_thresh1)) goto out; for (i = 0 ; i < (1 << nht->hash_shift); i++) { @@ -988,7 +990,9 @@ static void neigh_periodic_work(struct work_struct *work) (state == NUD_FAILED || !time_in_range_open(jiffies, n->used, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); neigh_mark_dead(n); write_unlock(&n->lock); neigh_cleanup_and_release(n); @@ -1447,7 +1451,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, if (n2) n1 = n2; } - n1->output(n1, skb); + READ_ONCE(n1->output)(n1, skb); if (n2) neigh_release(n2); rcu_read_unlock(); @@ -2165,15 +2169,16 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndtmsg->ndtm_pad2 = 0; if (nla_put_string(skb, NDTA_NAME, tbl->id) || - nla_put_msecs(skb, NDTA_GC_INTERVAL, tbl->gc_interval, NDTA_PAD) || - nla_put_u32(skb, NDTA_THRESH1, tbl->gc_thresh1) || - nla_put_u32(skb, NDTA_THRESH2, tbl->gc_thresh2) || - nla_put_u32(skb, NDTA_THRESH3, tbl->gc_thresh3)) + nla_put_msecs(skb, NDTA_GC_INTERVAL, READ_ONCE(tbl->gc_interval), + NDTA_PAD) || + nla_put_u32(skb, NDTA_THRESH1, READ_ONCE(tbl->gc_thresh1)) || + nla_put_u32(skb, NDTA_THRESH2, READ_ONCE(tbl->gc_thresh2)) || + nla_put_u32(skb, NDTA_THRESH3, READ_ONCE(tbl->gc_thresh3))) goto nla_put_failure; { unsigned long now = jiffies; - long flush_delta = now - tbl->last_flush; - long rand_delta = now - tbl->last_rand; + long flush_delta = now - READ_ONCE(tbl->last_flush); + long rand_delta = now - READ_ONCE(tbl->last_rand); struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, @@ -2181,7 +2186,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), - .ndtc_proxy_qlen = tbl->proxy_queue.qlen, + .ndtc_proxy_qlen = READ_ONCE(tbl->proxy_queue.qlen), }; rcu_read_lock(); @@ -2204,17 +2209,17 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, struct neigh_statistics *st; st = per_cpu_ptr(tbl->stats, cpu); - ndst.ndts_allocs += st->allocs; - ndst.ndts_destroys += st->destroys; - ndst.ndts_hash_grows += st->hash_grows; - ndst.ndts_res_failed += st->res_failed; - ndst.ndts_lookups += st->lookups; - ndst.ndts_hits += st->hits; - ndst.ndts_rcv_probes_mcast += st->rcv_probes_mcast; - ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; - ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; - ndst.ndts_forced_gc_runs += st->forced_gc_runs; - ndst.ndts_table_fulls += st->table_fulls; + ndst.ndts_allocs += READ_ONCE(st->allocs); + ndst.ndts_destroys += READ_ONCE(st->destroys); + ndst.ndts_hash_grows += READ_ONCE(st->hash_grows); + ndst.ndts_res_failed += READ_ONCE(st->res_failed); + ndst.ndts_lookups += READ_ONCE(st->lookups); + ndst.ndts_hits += READ_ONCE(st->hits); + ndst.ndts_rcv_probes_mcast += READ_ONCE(st->rcv_probes_mcast); + ndst.ndts_rcv_probes_ucast += READ_ONCE(st->rcv_probes_ucast); + ndst.ndts_periodic_gc_runs += READ_ONCE(st->periodic_gc_runs); + ndst.ndts_forced_gc_runs += READ_ONCE(st->forced_gc_runs); + ndst.ndts_table_fulls += READ_ONCE(st->table_fulls); } if (nla_put_64bit(skb, NDTA_STATS, sizeof(ndst), &ndst, @@ -2443,16 +2448,16 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout_tbl_lock; if (tb[NDTA_THRESH1]) - tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); + WRITE_ONCE(tbl->gc_thresh1, nla_get_u32(tb[NDTA_THRESH1])); if (tb[NDTA_THRESH2]) - tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]); + WRITE_ONCE(tbl->gc_thresh2, nla_get_u32(tb[NDTA_THRESH2])); if (tb[NDTA_THRESH3]) - tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]); + WRITE_ONCE(tbl->gc_thresh3, nla_get_u32(tb[NDTA_THRESH3])); if (tb[NDTA_GC_INTERVAL]) - tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]); + WRITE_ONCE(tbl->gc_interval, nla_get_msecs(tb[NDTA_GC_INTERVAL])); err = 0; @@ -3153,7 +3158,7 @@ int neigh_xmit(int index, struct net_device *dev, rcu_read_unlock(); goto out_kfree_skb; } - err = neigh->output(neigh, skb); + err = READ_ONCE(neigh->output)(neigh, skb); rcu_read_unlock(); } else if (index == NEIGH_LINK_TABLE) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index f56b8d697014..4d1696677c48 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -669,19 +669,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_puts(seq, " Flags: "); for (i = 0; i < NR_PKT_FLAGS; i++) { - if (i == F_FLOW_SEQ) + if (i == FLOW_SEQ_SHIFT) if (!pkt_dev->cflows) continue; - if (pkt_dev->flags & (1 << i)) + if (pkt_dev->flags & (1 << i)) { seq_printf(seq, "%s ", pkt_flag_names[i]); - else if (i == F_FLOW_SEQ) - seq_puts(seq, "FLOW_RND "); - #ifdef CONFIG_XFRM - if (i == F_IPSEC && pkt_dev->spi) - seq_printf(seq, "spi:%u", pkt_dev->spi); + if (i == IPSEC_SHIFT && pkt_dev->spi) + seq_printf(seq, "spi:%u ", pkt_dev->spi); #endif + } else if (i == FLOW_SEQ_SHIFT) { + seq_puts(seq, "FLOW_RND "); + } } seq_puts(seq, "\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4a2ec33bfb51..53c377d054f0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5503,13 +5503,11 @@ static unsigned int rtnl_offload_xstats_get_size_hw_s_info_one(const struct net_device *dev, enum netdev_offload_xstats_type type) { - bool enabled = netdev_offload_xstats_enabled(dev, type); - return nla_total_size(0) + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST */ nla_total_size(sizeof(u8)) + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED */ - (enabled ? nla_total_size(sizeof(u8)) : 0) + + nla_total_size(sizeof(u8)) + 0; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4eaf7ed0d1f4..2bfa6a7ba244 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -62,6 +62,7 @@ #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/kcov.h> +#include <linux/iov_iter.h> #include <net/protocol.h> #include <net/dst.h> @@ -6931,3 +6932,42 @@ out: return spliced ?: ret; } EXPORT_SYMBOL(skb_splice_from_iter); + +static __always_inline +size_t memcpy_from_iter_csum(void *iter_from, size_t progress, + size_t len, void *to, void *priv2) +{ + __wsum *csum = priv2; + __wsum next = csum_partial_copy_nocheck(iter_from, to + progress, len); + + *csum = csum_block_add(*csum, next, progress); + return 0; +} + +static __always_inline +size_t copy_from_user_iter_csum(void __user *iter_from, size_t progress, + size_t len, void *to, void *priv2) +{ + __wsum next, *csum = priv2; + + next = csum_and_copy_from_user(iter_from, to + progress, len); + *csum = csum_block_add(*csum, next, progress); + return next ? 0 : len; +} + +bool csum_and_copy_from_iter_full(void *addr, size_t bytes, + __wsum *csum, struct iov_iter *i) +{ + size_t copied; + + if (WARN_ON_ONCE(!i->data_source)) + return false; + copied = iterate_and_advance2(i, bytes, addr, csum, + copy_from_user_iter_csum, + memcpy_from_iter_csum); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; +} +EXPORT_SYMBOL(csum_and_copy_from_iter_full); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index cb11750b1df5..4292c2ed1828 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -668,6 +668,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; @@ -1267,6 +1269,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; diff --git a/net/core/stream.c b/net/core/stream.c index f5c4e47df165..96fbcb9bbb30 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -117,7 +117,7 @@ EXPORT_SYMBOL(sk_stream_wait_close); */ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) { - int err = 0; + int ret, err = 0; long vm_wait = 0; long current_timeo = *timeo_p; DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -142,11 +142,13 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || - (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || - (sk_stream_memory_free(sk) && - !vm_wait), &wait); + ret = sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || + (sk_stream_memory_free(sk) && !vm_wait), + &wait); sk->sk_write_pending--; + if (ret < 0) + goto do_error; if (vm_wait) { vm_wait -= current_timeo; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8f56e8723c73..69453b936bd5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -254,13 +254,8 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 33f6ccf6ba77..c693a570682f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -83,13 +83,8 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, - * which is in byte 7 of the dccp header. - * Our caller (icmpv6_notify()) already pulled 8 bytes for us. - * - * Later on, we want to access the sequence number fields, which are - * beyond 8 bytes, so we have to pskb_may_pull() ourselves. - */ + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; diff --git a/net/devlink/health.c b/net/devlink/health.c index 638cad8d5c65..51e6e81e31bb 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -58,7 +58,6 @@ struct devlink_health_reporter { struct devlink *devlink; struct devlink_port *devlink_port; struct devlink_fmsg *dump_fmsg; - struct mutex dump_lock; /* lock parallel read/write from dump buffers */ u64 graceful_period; bool auto_recover; bool auto_dump; @@ -125,7 +124,6 @@ __devlink_health_reporter_create(struct devlink *devlink, reporter->graceful_period = graceful_period; reporter->auto_recover = !!ops->recover; reporter->auto_dump = !!ops->dump; - mutex_init(&reporter->dump_lock); return reporter; } @@ -226,7 +224,6 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_create); static void devlink_health_reporter_free(struct devlink_health_reporter *reporter) { - mutex_destroy(&reporter->dump_lock); if (reporter->dump_fmsg) devlink_fmsg_free(reporter->dump_fmsg); kfree(reporter); @@ -625,10 +622,10 @@ int devlink_health_report(struct devlink_health_reporter *reporter, } if (reporter->auto_dump) { - mutex_lock(&reporter->dump_lock); + devl_lock(devlink); /* store current dump of current error, for later analysis */ devlink_health_do_dump(reporter, priv_ctx, NULL); - mutex_unlock(&reporter->dump_lock); + devl_unlock(devlink); } if (!reporter->auto_recover) @@ -1262,7 +1259,7 @@ out: } static struct devlink_health_reporter * -devlink_health_reporter_get_from_cb(struct netlink_callback *cb) +devlink_health_reporter_get_from_cb_lock(struct netlink_callback *cb) { const struct genl_info *info = genl_info_dump(cb); struct devlink_health_reporter *reporter; @@ -1272,10 +1269,12 @@ devlink_health_reporter_get_from_cb(struct netlink_callback *cb) devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs); if (IS_ERR(devlink)) return NULL; - devl_unlock(devlink); reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); - devlink_put(devlink); + if (!reporter) { + devl_unlock(devlink); + devlink_put(devlink); + } return reporter; } @@ -1284,16 +1283,20 @@ int devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_health_reporter *reporter; + struct devlink *devlink; int err; - reporter = devlink_health_reporter_get_from_cb(cb); + reporter = devlink_health_reporter_get_from_cb_lock(cb); if (!reporter) return -EINVAL; - if (!reporter->ops->dump) + devlink = reporter->devlink; + if (!reporter->ops->dump) { + devl_unlock(devlink); + devlink_put(devlink); return -EOPNOTSUPP; + } - mutex_lock(&reporter->dump_lock); if (!state->idx) { err = devlink_health_do_dump(reporter, NULL, cb->extack); if (err) @@ -1309,7 +1312,8 @@ int devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, err = devlink_fmsg_dumpit(reporter->dump_fmsg, skb, cb, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET); unlock: - mutex_unlock(&reporter->dump_lock); + devl_unlock(devlink); + devlink_put(devlink); return err; } @@ -1326,9 +1330,7 @@ int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, if (!reporter->ops->dump) return -EOPNOTSUPP; - mutex_lock(&reporter->dump_lock); devlink_health_dump_clear(reporter); - mutex_unlock(&reporter->dump_lock); return 0; } diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c index b238a1afe9ae..b1e2e3b5027f 100644 --- a/net/ethtool/plca.c +++ b/net/ethtool/plca.c @@ -21,16 +21,6 @@ struct plca_reply_data { #define PLCA_REPDATA(__reply_base) \ container_of(__reply_base, struct plca_reply_data, base) -static void plca_update_sint(int *dst, const struct nlattr *attr, - bool *mod) -{ - if (!attr) - return; - - *dst = nla_get_u32(attr); - *mod = true; -} - // PLCA get configuration message ------------------------------------------- // const struct nla_policy ethnl_plca_get_cfg_policy[] = { @@ -38,6 +28,29 @@ const struct nla_policy ethnl_plca_get_cfg_policy[] = { NLA_POLICY_NESTED(ethnl_header_policy), }; +static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid, + bool *mod) +{ + const struct nlattr *attr = tb[attrid]; + + if (!attr || + WARN_ON_ONCE(attrid >= ARRAY_SIZE(ethnl_plca_set_cfg_policy))) + return; + + switch (ethnl_plca_set_cfg_policy[attrid].type) { + case NLA_U8: + *dst = nla_get_u8(attr); + break; + case NLA_U32: + *dst = nla_get_u32(attr); + break; + default: + WARN_ON_ONCE(1); + } + + *mod = true; +} + static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) @@ -144,13 +157,13 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) return -EOPNOTSUPP; memset(&plca_cfg, 0xff, sizeof(plca_cfg)); - plca_update_sint(&plca_cfg.enabled, tb[ETHTOOL_A_PLCA_ENABLED], &mod); - plca_update_sint(&plca_cfg.node_id, tb[ETHTOOL_A_PLCA_NODE_ID], &mod); - plca_update_sint(&plca_cfg.node_cnt, tb[ETHTOOL_A_PLCA_NODE_CNT], &mod); - plca_update_sint(&plca_cfg.to_tmr, tb[ETHTOOL_A_PLCA_TO_TMR], &mod); - plca_update_sint(&plca_cfg.burst_cnt, tb[ETHTOOL_A_PLCA_BURST_CNT], + plca_update_sint(&plca_cfg.enabled, tb, ETHTOOL_A_PLCA_ENABLED, &mod); + plca_update_sint(&plca_cfg.node_id, tb, ETHTOOL_A_PLCA_NODE_ID, &mod); + plca_update_sint(&plca_cfg.node_cnt, tb, ETHTOOL_A_PLCA_NODE_CNT, &mod); + plca_update_sint(&plca_cfg.to_tmr, tb, ETHTOOL_A_PLCA_TO_TMR, &mod); + plca_update_sint(&plca_cfg.burst_cnt, tb, ETHTOOL_A_PLCA_BURST_CNT, &mod); - plca_update_sint(&plca_cfg.burst_tmr, tb[ETHTOOL_A_PLCA_BURST_TMR], + plca_update_sint(&plca_cfg.burst_tmr, tb, ETHTOOL_A_PLCA_BURST_TMR, &mod); if (!mod) return 0; diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index 6d37bab35c8f..16ed7bfd29e4 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -235,7 +235,7 @@ static void handshake_req_submit_test4(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, req, result); handshake_req_cancel(sock->sk); - sock_release(sock); + fput(filp); } static void handshake_req_submit_test5(struct kunit *test) @@ -272,7 +272,7 @@ static void handshake_req_submit_test5(struct kunit *test) /* Assert */ KUNIT_EXPECT_EQ(test, err, -EAGAIN); - sock_release(sock); + fput(filp); hn->hn_pending = saved; } @@ -306,7 +306,7 @@ static void handshake_req_submit_test6(struct kunit *test) KUNIT_EXPECT_EQ(test, err, -EBUSY); handshake_req_cancel(sock->sk); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test1(struct kunit *test) @@ -340,7 +340,7 @@ static void handshake_req_cancel_test1(struct kunit *test) /* Assert */ KUNIT_EXPECT_TRUE(test, result); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test2(struct kunit *test) @@ -382,7 +382,7 @@ static void handshake_req_cancel_test2(struct kunit *test) /* Assert */ KUNIT_EXPECT_TRUE(test, result); - sock_release(sock); + fput(filp); } static void handshake_req_cancel_test3(struct kunit *test) @@ -427,7 +427,7 @@ static void handshake_req_cancel_test3(struct kunit *test) /* Assert */ KUNIT_EXPECT_FALSE(test, result); - sock_release(sock); + fput(filp); } static struct handshake_req *handshake_req_destroy_test; @@ -471,7 +471,7 @@ static void handshake_req_destroy_test1(struct kunit *test) handshake_req_cancel(sock->sk); /* Act */ - sock_release(sock); + fput(filp); /* Assert */ KUNIT_EXPECT_PTR_EQ(test, handshake_req_destroy_test, req); diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index d0bc1dd8e65a..80c7302692c7 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -87,29 +87,6 @@ struct nlmsghdr *handshake_genl_put(struct sk_buff *msg, } EXPORT_SYMBOL(handshake_genl_put); -/* - * dup() a kernel socket for use as a user space file descriptor - * in the current process. The kernel socket must have an - * instatiated struct file. - * - * Implicit argument: "current()" - */ -static int handshake_dup(struct socket *sock) -{ - struct file *file; - int newfd; - - file = get_file(sock->file); - newfd = get_unused_fd_flags(O_CLOEXEC); - if (newfd < 0) { - fput(file); - return newfd; - } - - fd_install(newfd, file); - return newfd; -} - int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); @@ -133,17 +110,20 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) goto out_status; sock = req->hr_sk->sk_socket; - fd = handshake_dup(sock); + fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; goto out_complete; } + err = req->hr_proto->hp_accept(req, info, fd); if (err) { - fput(sock->file); + put_unused_fd(fd); goto out_complete; } + fd_install(fd, get_file(sock->file)); + trace_handshake_cmd_accept(net, req, req->hr_sk, fd); return 0; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index b77f1189d19d..6d14d935ee82 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -288,13 +288,13 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) /* And leave the HSR tag. */ if (ethhdr->h_proto == htons(ETH_P_HSR)) { - pull_size = sizeof(struct ethhdr); + pull_size = sizeof(struct hsr_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; } /* And leave the HSR sup tag. */ - pull_size = sizeof(struct hsr_tag); + pull_size = sizeof(struct hsr_sup_tag); skb_pull(skb, pull_size); total_pull_size += pull_size; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 6851e33df7d1..18e01791ad79 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -83,7 +83,7 @@ struct hsr_vlan_ethhdr { struct hsr_sup_tlv { u8 HSR_TLV_type; u8 HSR_TLV_length; -}; +} __packed; /* HSR/PRP Supervision Frame data types. * Field names as defined in the IEC:2010 standard for HSR. diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3d2e30e20473..2713c9b06c4c 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -597,7 +597,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; - sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -613,7 +612,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; - sk->sk_wait_pending--; return timeo; } @@ -642,6 +640,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { + sk->sk_disconnects++; err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; @@ -696,6 +695,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; + int dis = sk->sk_disconnects; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) @@ -704,6 +704,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; + + if (dis != sk->sk_disconnects) { + err = -EPIPE; + goto out; + } } /* Connection was closed by RST, timeout, ICMP error @@ -725,6 +730,7 @@ out: sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; + sk->sk_disconnects++; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 2be2d4922557..4ccfc104f13a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -732,7 +732,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; @@ -784,7 +786,7 @@ int esp_input_done2(struct sk_buff *skb, int err) /* * 1) if the NAT-T peer's IP or port changed then - * advertize the change to the keying daemon. + * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index eafa4a033515..5eb1b8d302bb 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1325,15 +1325,18 @@ __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope) { struct fib_nh *nh; + __be32 saddr; if (nhc->nhc_family != AF_INET) return inet_select_addr(nhc->nhc_dev, 0, scope); nh = container_of(nhc, struct fib_nh, nh_common); - nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid); + saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - return nh->nh_saddr; + WRITE_ONCE(nh->nh_saddr, saddr); + WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid)); + + return saddr; } __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) @@ -1347,8 +1350,9 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); - if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid)) - return nh->nh_saddr; + if (READ_ONCE(nh->nh_saddr_genid) == + atomic_read(&net->ipv4.dev_addr_genid)) + return READ_ONCE(nh->nh_saddr); } return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope); @@ -1887,6 +1891,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; + fi->pfsrc_removed = true; ret++; } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d13fb9e76b97..9bdfdab906fe 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2027,6 +2027,7 @@ void fib_table_flush_external(struct fib_table *tb) int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; + struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; @@ -2089,6 +2090,9 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); + if (fi->pfsrc_removed) + rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, + KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index aeebe8816689..394a498c2823 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1145,7 +1145,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); - newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c32f5e28758b..598c1b114d2c 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -149,8 +149,14 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb2->family) - return false; + if (sk->sk_family != tb2->family) { + if (sk->sk_family == AF_INET) + return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) && + tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; + + return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) && + sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr; + } if (sk->sk_family == AF_INET6) return ipv6_addr_equal(&tb2->v6_rcv_saddr, @@ -819,19 +825,7 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, tb->l3mdev != l3mdev) return false; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb->family) { - if (sk->sk_family == AF_INET) - return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) && - tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; - - return false; - } - - if (sk->sk_family == AF_INET6) - return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); -#endif - return tb->rcv_saddr == sk->sk_rcv_saddr; + return inet_bind2_bucket_addr_match(tb, sk); } bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 66f419e7f9a7..b214b5a2e045 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1213,6 +1213,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1230,7 +1231,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) @@ -3415,6 +3417,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); + fri.offload_failed = + READ_ONCE(fa->offload_failed); break; } } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0c3040a63ebd..3d3a24f79573 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; - sk_wait_data(sk, &timeo, NULL); + ret = sk_wait_data(sk, &timeo, NULL); + if (ret < 0) + break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -925,10 +927,11 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -/* In some cases, both sendmsg() could have added an skb to the write queue, - * but failed adding payload on it. We need to remove it to consume less +/* In some cases, sendmsg() could have added an skb to the write queue, + * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger - * epoll() users. + * epoll() users. Another reason is that tcp_write_xmit() does not like + * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { @@ -1287,6 +1290,7 @@ new_segment: wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); @@ -1621,16 +1625,13 @@ EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { - struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; struct sk_buff *skb; int copied = 0; - u32 offset; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; @@ -1643,13 +1644,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) copied = used; break; } - seq += used; copied += used; - if (tcp_flags & TCPHDR_FIN) { - ++seq; + if (tcp_flags & TCPHDR_FIN) break; - } } return copied; } @@ -2448,7 +2446,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); - sk_wait_data(sk, &timeo, last); + err = sk_wait_data(sk, &timeo, last); + if (err < 0) { + err = copied ? : err; + goto out; + } } if ((flags & MSG_PEEK) && @@ -2972,12 +2974,6 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 81f0dff69e0b..53b0d62fd2c2 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -222,6 +222,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int *addr_len) { struct tcp_sock *tcp = tcp_sk(sk); + int peek = flags & MSG_PEEK; u32 seq = tcp->copied_seq; struct sk_psock *psock; int copied = 0; @@ -306,15 +307,22 @@ msg_bytes_ready: } data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + copied = data; + goto unlock; + } if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; } out: - WRITE_ONCE(tcp->copied_seq, seq); + if (!peek) + WRITE_ONCE(tcp->copied_seq, seq); tcp_rcv_space_adjust(sk); if (copied > 0) __tcp_cleanup_rbuf(sk, copied); + +unlock: release_sock(sk); sk_psock_put(sk, psock); return copied; @@ -349,6 +357,10 @@ msg_bytes_ready: timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + ret = data; + goto unlock; + } if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; @@ -359,6 +371,8 @@ msg_bytes_ready: copied = -EAGAIN; } ret = copied; + +unlock: release_sock(sk); sk_psock_put(sk, psock); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 06fe1cf645d5..804821d6bd4d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -253,6 +253,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (unlikely(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE)) tcp_gro_dev_warn(sk, skb, len); + /* If the skb has a len of exactly 1*MSS and has the PSH bit + * set then it is likely the end of an application write. So + * more data may not be arriving soon, and yet the data sender + * may be waiting for an ACK if cwnd-bound or using TX zero + * copy. So we set ICSK_ACK_PUSHED here so that + * tcp_cleanup_rbuf() will send an ACK immediately if the app + * reads all of the data and is not ping-pong. If len > MSS + * then this logic does not matter (and does not hurt) because + * tcp_cleanup_rbuf() will always ACK immediately if the app + * reads data and there is more than an MSS of unACKed data. + */ + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. @@ -2194,16 +2207,17 @@ void tcp_enter_loss(struct sock *sk) * restore sanity to the SACK scoreboard. If the apparent reneging * persists until this RTO then we'll clear the SACK scoreboard. */ -static bool tcp_check_sack_reneging(struct sock *sk, int flag) +static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag) { - if (flag & FLAG_SACK_RENEGING && - flag & FLAG_SND_UNA_ADVANCED) { + if (*ack_flag & FLAG_SACK_RENEGING && + *ack_flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); + *ack_flag &= ~FLAG_SET_XMIT_TIMER; return true; } return false; @@ -2973,7 +2987,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, tp->prior_ssthresh = 0; /* B. In all the states check for reneging SACKs. */ - if (tcp_check_sack_reneging(sk, flag)) + if (tcp_check_sack_reneging(sk, ack_flag)) return; /* C. Check consistency of the current state. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 27140e5cdc06..4167e8a48b60 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1869,6 +1869,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TLS_DEVICE tail->decrypted != skb->decrypted || #endif + !mptcp_skb_can_collapse(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index ccfc8bbf7455..f0723460753c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -177,8 +177,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, - u32 rcv_nxt) +static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -192,7 +191,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ - tcp_dec_quickack_mode(sk, pkts); + tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1387,7 +1386,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -2457,6 +2456,7 @@ static int tcp_mtu_probe(struct sock *sk) /* build the payload, and be prepared to abort if this fails. */ if (tcp_clone_payload(sk, nskb, probe_size)) { + tcp_skb_tsorted_anchor_cleanup(nskb); consume_skb(nskb); return -1; } @@ -2542,6 +2542,18 @@ static bool tcp_pacing_check(struct sock *sk) return true; } +static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) +{ + const struct rb_node *node = sk->tcp_rtx_queue.rb_node; + + /* No skb in the rtx queue. */ + if (!node) + return true; + + /* Only one skb in rtx queue. */ + return !node->rb_left && !node->rb_right; +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2579,12 +2591,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send skb if rtx queue is empty. + /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (tcp_rtx_queue_empty(sk)) + if (tcp_rtx_queue_empty_or_single_skb(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2788,7 +2800,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, rto_delta_us; + u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS @@ -2812,11 +2824,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { - timeout = usecs_to_jiffies(tp->srtt_us >> 2); + timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) - timeout += TCP_RTO_MIN; + timeout_us += tcp_rto_min_us(sk); else - timeout += TCP_TIMEOUT_MIN; + timeout_us += TCP_TIMEOUT_MIN_US; + timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index acf4869c5d3b..bba10110fbbc 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -104,7 +104,7 @@ bool tcp_rack_mark_lost(struct sock *sk) tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { - timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN; + timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US); inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index fddd0cbdede1..2cc1a45742d8 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -770,7 +770,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; @@ -831,7 +833,7 @@ int esp6_input_done2(struct sk_buff *skb, int err) /* * 1) if the NAT-T peer's IP or port changed then - * advertize the change to the keying daemon. + * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3a88545a265d..44b6949d72b2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1640,9 +1640,12 @@ process: struct sock *nsk; sk = req->rsk_listener; - drop_reason = tcp_inbound_md5_hash(sk, skb, - &hdr->saddr, &hdr->daddr, - AF_INET6, dif, sdif); + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + drop_reason = SKB_DROP_REASON_XFRM_POLICY; + else + drop_reason = tcp_inbound_md5_hash(sk, skb, + &hdr->saddr, &hdr->daddr, + AF_INET6, dif, sdif); if (drop_reason) { sk_drops_add(sk, skb); reqsk_put(req); @@ -1689,6 +1692,7 @@ process: } goto discard_and_relse; } + nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 41a680c76d2e..42fb6996b077 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -117,10 +117,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt6.rt6i_idev)) - in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); rt6_uncached_list_del(&xdst->u.rt6); + if (likely(xdst->u.rt6.rt6i_idev)) + in6_dev_put(xdst->u.rt6.rt6i_idev); xfrm_dst_destroy(xdst); } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index ed8ebb6f5909..11f3d375cec0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -507,7 +507,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) */ if (len > INT_MAX - transhdrlen) return -EMSGSIZE; - ulen = len + transhdrlen; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) @@ -628,6 +627,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); + ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 45e7a5d9c7d9..0e3a1753a51c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -566,6 +566,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, } err = ieee80211_key_link(key, link, sta); + /* KRACK protection, shouldn't happen but just silently accept key */ + if (err == -EALREADY) + err = 0; out_unlock: mutex_unlock(&local->sta_mtx); @@ -1857,7 +1860,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, - params->vht_capa, link_sta); + params->vht_capa, NULL, + link_sta); if (params->he_capa) ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index e1900077bc4b..5542c93edfba 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1072,7 +1072,7 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, &chandef); memcpy(&cap_ie, elems->vht_cap_elem, sizeof(cap_ie)); ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, - &cap_ie, + &cap_ie, NULL, &sta->deflink); if (memcmp(&cap, &sta->sta.deflink.vht_cap, sizeof(cap))) rates_updated |= true; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 06bd406846d2..98ef1fe1226e 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -676,7 +676,7 @@ struct ieee80211_if_mesh { struct timer_list mesh_path_root_timer; unsigned long wrkq_flags; - unsigned long mbss_changed; + unsigned long mbss_changed[64 / BITS_PER_LONG]; bool userspace_handles_dfs; @@ -2141,6 +2141,7 @@ void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_vht_cap *vht_cap_ie, + const struct ieee80211_vht_cap *vht_cap_ie2, struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 13050dc9321f..a2db0585dce0 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -802,6 +802,9 @@ static void ieee80211_key_destroy(struct ieee80211_key *key, void ieee80211_key_free_unused(struct ieee80211_key *key) { + if (!key) + return; + WARN_ON(key->sdata || key->local); ieee80211_key_free_common(key); } @@ -854,7 +857,7 @@ int ieee80211_key_link(struct ieee80211_key *key, * can cause warnings to appear. */ bool delay_tailroom = sdata->vif.type == NL80211_IFTYPE_STATION; - int ret = -EOPNOTSUPP; + int ret; mutex_lock(&sdata->local->key_mtx); @@ -868,8 +871,10 @@ int ieee80211_key_link(struct ieee80211_key *key, * the same cipher. Enforce the assumption for pairwise keys. */ if ((alt_key && alt_key->conf.cipher != key->conf.cipher) || - (old_key && old_key->conf.cipher != key->conf.cipher)) + (old_key && old_key->conf.cipher != key->conf.cipher)) { + ret = -EOPNOTSUPP; goto out; + } } else if (sta) { struct link_sta_info *link_sta = &sta->deflink; int link_id = key->conf.link_id; @@ -895,8 +900,10 @@ int ieee80211_key_link(struct ieee80211_key *key, /* Non-pairwise keys must also not switch the cipher on rekey */ if (!pairwise) { - if (old_key && old_key->conf.cipher != key->conf.cipher) + if (old_key && old_key->conf.cipher != key->conf.cipher) { + ret = -EOPNOTSUPP; goto out; + } } /* @@ -904,8 +911,7 @@ int ieee80211_key_link(struct ieee80211_key *key, * new version of the key to avoid nonce reuse or replay issues. */ if (ieee80211_key_identical(sdata, old_key, key)) { - ieee80211_key_free_unused(key); - ret = 0; + ret = -EALREADY; goto out; } @@ -930,7 +936,10 @@ int ieee80211_key_link(struct ieee80211_key *key, ieee80211_key_free(key, delay_tailroom); } + key = NULL; + out: + ieee80211_key_free_unused(key); mutex_unlock(&sdata->local->key_mtx); return ret; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index af8c5fc2db14..e31c312c124a 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1175,7 +1175,7 @@ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, /* if we race with running work, worst case this work becomes a noop */ for_each_set_bit(bit, &bits, sizeof(changed) * BITS_PER_BYTE) - set_bit(bit, &ifmsh->mbss_changed); + set_bit(bit, ifmsh->mbss_changed); set_bit(MESH_WORK_MBSS_CHANGED, &ifmsh->wrkq_flags); wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work); } @@ -1257,7 +1257,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) /* clear any mesh work (for next join) we may have accrued */ ifmsh->wrkq_flags = 0; - ifmsh->mbss_changed = 0; + memset(ifmsh->mbss_changed, 0, sizeof(ifmsh->mbss_changed)); local->fif_other_bss--; atomic_dec(&local->iff_allmultis); @@ -1724,9 +1724,9 @@ static void mesh_bss_info_changed(struct ieee80211_sub_if_data *sdata) u32 bit; u64 changed = 0; - for_each_set_bit(bit, &ifmsh->mbss_changed, + for_each_set_bit(bit, ifmsh->mbss_changed, sizeof(changed) * BITS_PER_BYTE) { - clear_bit(bit, &ifmsh->mbss_changed); + clear_bit(bit, ifmsh->mbss_changed); changed |= BIT(bit); } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index f3d5bb0a59f1..a1e526419e9d 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -451,7 +451,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, changed |= IEEE80211_RC_BW_CHANGED; ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, - elems->vht_cap_elem, + elems->vht_cap_elem, NULL, &sta->deflink); ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, elems->he_cap, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index f93eb38ae0b8..0c9198997482 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4202,10 +4202,33 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, elems->ht_cap_elem, link_sta); - if (elems->vht_cap_elem && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT)) + if (elems->vht_cap_elem && + !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT)) { + const struct ieee80211_vht_cap *bss_vht_cap = NULL; + const struct cfg80211_bss_ies *ies; + + /* + * Cisco AP module 9115 with FW 17.3 has a bug and sends a + * too large maximum MPDU length in the association response + * (indicating 12k) that it cannot actually process ... + * Work around that. + */ + rcu_read_lock(); + ies = rcu_dereference(cbss->ies); + if (ies) { + const struct element *elem; + + elem = cfg80211_find_elem(WLAN_EID_VHT_CAPABILITY, + ies->data, ies->len); + if (elem && elem->datalen >= sizeof(*bss_vht_cap)) + bss_vht_cap = (const void *)elem->data; + } + ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, elems->vht_cap_elem, - link_sta); + bss_vht_cap, link_sta); + rcu_read_unlock(); + } if (elems->he_operation && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) && elems->he_cap) { @@ -5107,9 +5130,10 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, continue; valid_links |= BIT(link_id); - if (assoc_data->link[link_id].disabled) { + if (assoc_data->link[link_id].disabled) dormant_links |= BIT(link_id); - } else if (link_id != assoc_data->assoc_link_id) { + + if (link_id != assoc_data->assoc_link_id) { err = ieee80211_sta_allocate_link(sta, link_id); if (err) goto out_err; @@ -5124,7 +5148,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link; struct link_sta_info *link_sta; - if (!cbss || assoc_data->link[link_id].disabled) + if (!cbss) continue; link = sdata_dereference(sdata->link[link_id], sdata); @@ -5429,17 +5453,18 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { struct ieee80211_link_data *link; - link = sdata_dereference(sdata->link[link_id], sdata); - if (!link) - continue; - if (!assoc_data->link[link_id].bss) continue; resp.links[link_id].bss = assoc_data->link[link_id].bss; - resp.links[link_id].addr = link->conf->addr; + ether_addr_copy(resp.links[link_id].addr, + assoc_data->link[link_id].addr); resp.links[link_id].status = assoc_data->link[link_id].status; + link = sdata_dereference(sdata->link[link_id], sdata); + if (!link) + continue; + /* get uapsd queues configuration - same for all links */ resp.uapsd_queues = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index e751cda5eef6..8f6b6f56b65b 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2468,8 +2468,7 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) /* drop unicast public action frames when using MPF */ if (is_unicast_ether_addr(mgmt->da) && - ieee80211_is_public_action((void *)rx->skb->data, - rx->skb->len)) + ieee80211_is_protected_dual_of_public_action(rx->skb)) return -EACCES; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 7fe7280e8437..d45d4be63dd8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -665,7 +665,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) } if (unlikely(tx->key && tx->key->flags & KEY_FLAG_TAINTED && - !ieee80211_is_deauth(hdr->frame_control))) + !ieee80211_is_deauth(hdr->frame_control)) && + tx->skb->protocol != tx->sdata->control_port_protocol) return TX_DROP; if (!skip_hw && tx->key && diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index c1250aa47808..b3a5c3e96a72 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -4,7 +4,7 @@ * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2022 Intel Corporation + * Copyright (C) 2018 - 2023 Intel Corporation */ #include <linux/ieee80211.h> @@ -116,12 +116,14 @@ void ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, const struct ieee80211_vht_cap *vht_cap_ie, + const struct ieee80211_vht_cap *vht_cap_ie2, struct link_sta_info *link_sta) { struct ieee80211_sta_vht_cap *vht_cap = &link_sta->pub->vht_cap; struct ieee80211_sta_vht_cap own_cap; u32 cap_info, i; bool have_80mhz; + u32 mpdu_len; memset(vht_cap, 0, sizeof(*vht_cap)); @@ -318,10 +320,20 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, link_sta->pub->bandwidth = ieee80211_sta_cur_vht_bw(link_sta); /* + * Work around the Cisco 9115 FW 17.3 bug by taking the min of + * both reported MPDU lengths. + */ + mpdu_len = vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK; + if (vht_cap_ie2) + mpdu_len = min_t(u32, mpdu_len, + le32_get_bits(vht_cap_ie2->vht_cap_info, + IEEE80211_VHT_CAP_MAX_MPDU_MASK)); + + /* * FIXME - should the amsdu len be per link? store per link * and maintain a minimum? */ - switch (vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK) { + switch (mpdu_len) { case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: link_sta->pub->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454; break; diff --git a/net/mctp/route.c b/net/mctp/route.c index ab62fe447038..7a47a58aa54b 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -737,6 +737,8 @@ struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, { struct mctp_route *tmp, *rt = NULL; + rcu_read_lock(); + list_for_each_entry_rcu(tmp, &net->mctp.routes, list) { /* TODO: add metrics */ if (mctp_rt_match_eid(tmp, dnet, daddr)) { @@ -747,21 +749,29 @@ struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, } } + rcu_read_unlock(); + return rt; } static struct mctp_route *mctp_route_lookup_null(struct net *net, struct net_device *dev) { - struct mctp_route *rt; + struct mctp_route *tmp, *rt = NULL; - list_for_each_entry_rcu(rt, &net->mctp.routes, list) { - if (rt->dev->dev == dev && rt->type == RTN_LOCAL && - refcount_inc_not_zero(&rt->refs)) - return rt; + rcu_read_lock(); + + list_for_each_entry_rcu(tmp, &net->mctp.routes, list) { + if (tmp->dev->dev == dev && tmp->type == RTN_LOCAL && + refcount_inc_not_zero(&tmp->refs)) { + rt = tmp; + break; + } } - return NULL; + rcu_read_unlock(); + + return rt; } static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c254accb14de..cd15ec73073e 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1269,12 +1269,13 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) if (rcv_wnd == rcv_wnd_old) break; - if (before64(rcv_wnd_new, rcv_wnd)) { + + rcv_wnd_old = rcv_wnd; + if (before64(rcv_wnd_new, rcv_wnd_old)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE); goto raise_win; } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); - rcv_wnd_old = rcv_wnd; } return; } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index b5a8aa4c1ebd..d042d32beb4d 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -307,12 +307,6 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) goto create_err; } - if (addr_l.id == 0) { - NL_SET_ERR_MSG_ATTR(info->extack, laddr, "missing local addr id"); - err = -EINVAL; - goto create_err; - } - err = mptcp_pm_parse_addr(raddr, info, &addr_r); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr"); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a7fc16f5175d..886ab689a8ae 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -405,7 +405,7 @@ drop: return false; } -static void mptcp_stop_timer(struct sock *sk) +static void mptcp_stop_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -770,6 +770,46 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) return moved; } +static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) +{ + int err = sock_error(ssk); + int ssk_state; + + if (!err) + return false; + + /* only propagate errors on fallen-back sockets or + * on MPC connect + */ + if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) + return false; + + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); + WRITE_ONCE(sk->sk_err, -err); + + /* This barrier is coupled with smp_rmb() in mptcp_poll() */ + smp_wmb(); + sk_error_report(sk); + return true; +} + +void __mptcp_error_report(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) + if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow))) + break; +} + /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ @@ -852,6 +892,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); + mptcp_stop_tout_timer(sk); return true; } @@ -871,12 +912,12 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list } } -static bool mptcp_timer_pending(struct sock *sk) +static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); } -static void mptcp_reset_timer(struct sock *sk) +static void mptcp_reset_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; @@ -1010,10 +1051,10 @@ static void __mptcp_clean_una(struct sock *sk) out: if (snd_una == READ_ONCE(msk->snd_nxt) && snd_una == READ_ONCE(msk->write_seq)) { - if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) - mptcp_stop_timer(sk); + if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) + mptcp_stop_rtx_timer(sk); } else { - mptcp_reset_timer(sk); + mptcp_reset_rtx_timer(sk); } } @@ -1257,7 +1298,7 @@ alloc_skb: if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (snd_una != msk->snd_nxt) { + if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { tcp_remove_empty_skb(ssk); return 0; } @@ -1265,11 +1306,6 @@ alloc_skb: zero_window_probe = true; data_seq = snd_una - 1; copy = 1; - - /* all mptcp-level data is acked, no skbs should be present into the - * ssk write queue - */ - WARN_ON_ONCE(reuse_skb); } copy = min_t(size_t, copy, info->limit - info->sent); @@ -1298,7 +1334,6 @@ alloc_skb: if (reuse_skb) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += copy; - WARN_ON_ONCE(zero_window_probe); goto out; } @@ -1586,8 +1621,8 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) mptcp_push_release(ssk, &info); /* ensure the rtx timer is running */ - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (do_check_data_fin) mptcp_check_send_data_fin(sk); } @@ -1650,8 +1685,8 @@ out: if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) @@ -2220,7 +2255,7 @@ static void mptcp_retransmit_timer(struct timer_list *t) sock_put(sk); } -static void mptcp_timeout_timer(struct timer_list *t) +static void mptcp_tout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); @@ -2313,6 +2348,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) #define MPTCP_CF_PUSH BIT(1) #define MPTCP_CF_FASTCLOSE BIT(2) +/* be sure to send a reset only if the caller asked for it, also + * clean completely the subflow status when the subflow reaches + * TCP_CLOSE state + */ +static void __mptcp_subflow_disconnect(struct sock *ssk, + struct mptcp_subflow_context *subflow, + unsigned int flags) +{ + if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + (flags & MPTCP_CF_FASTCLOSE)) { + /* The MPTCP code never wait on the subflow sockets, TCP-level + * disconnect should never fail + */ + WARN_ON_ONCE(tcp_disconnect(ssk, 0)); + mptcp_subflow_ctx_reset(subflow); + } else { + tcp_shutdown(ssk, SEND_SHUTDOWN); + } +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2329,18 +2384,14 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, 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. + * to an incoming reset or listener shutdown, the subflow socket is + * already deleted by inet_child_forget() and the mptcp socket can't + * survive too. */ - if (msk->in_accept_queue && msk->first == ssk) { - if (!sock_flag(sk, SOCK_DEAD) && !sock_flag(ssk, SOCK_DEAD)) - return; - + if (msk->in_accept_queue && msk->first == ssk && + (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ + mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1)); sock_set_flag(sk, SOCK_DEAD); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); @@ -2354,7 +2405,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { - /* be sure to force the tcp_disconnect() path, + /* be sure to force the tcp_close path * to generate the egress reset */ ssk->sk_lingertime = 0; @@ -2364,11 +2415,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { - /* The MPTCP code never wait on the subflow sockets, TCP-level - * disconnect should never fail - */ - WARN_ON_ONCE(tcp_disconnect(ssk, 0)); - mptcp_subflow_ctx_reset(subflow); + __mptcp_subflow_disconnect(ssk, subflow, flags); release_sock(ssk); goto out; @@ -2392,6 +2439,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, } out_release: + __mptcp_subflow_error_report(sk, ssk); release_sock(ssk); sock_put(ssk); @@ -2402,6 +2450,22 @@ out_release: out: if (need_push) __mptcp_push_pending(sk, 0); + + /* Catch every 'all subflows closed' scenario, including peers silently + * closing them, e.g. due to timeout. + * For established sockets, allow an additional timeout before closing, + * as the protocol can still create more subflows. + */ + if (list_is_singular(&msk->conn_list) && msk->first && + inet_sk_state_load(msk->first) == TCP_CLOSE) { + if (sk->sk_state != TCP_ESTABLISHED || + msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_close_wake_up(sk); + } else { + mptcp_start_tout_timer(sk); + } + } } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, @@ -2445,23 +2509,14 @@ static void __mptcp_close_subflow(struct sock *sk) } -static bool mptcp_should_close(const struct sock *sk) +static bool mptcp_close_tout_expired(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 || mptcp_sk(sk)->in_accept_queue) - return true; + if (!inet_csk(sk)->icsk_mtup.probe_timestamp || + sk->sk_state == TCP_CLOSE) + return false; - /* if all subflows are in closed status don't bother with additional - * timeout - */ - mptcp_for_each_subflow(mptcp_sk(sk), subflow) { - if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) != - TCP_CLOSE) - return false; - } - return true; + return time_after32(tcp_jiffies32, + inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN); } static void mptcp_check_fastclose(struct mptcp_sock *msk) @@ -2588,27 +2643,28 @@ static void __mptcp_retrans(struct sock *sk) reset_timer: mptcp_check_and_set_pending(sk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout) +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; - if (!fail_tout && !sock_flag(sk, SOCK_DEAD)) + if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; - close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN; + close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + + TCP_TIMEWAIT_LEN; /* the close timeout takes precedence on the fail one, and here at least one of * them is active */ - timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout; + timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; sk_reset_timer(sk, &sk->sk_timer, timeout); } @@ -2627,8 +2683,6 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) mptcp_subflow_reset(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); - - mptcp_reset_timeout(msk, 0); } static void mptcp_do_fastclose(struct sock *sk) @@ -2665,18 +2719,14 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(sk); - /* There is no point in keeping around an orphaned sk timedout or - * closed, but we need the msk around to reply to incoming DATA_FIN, - * even if it is orphaned and in FIN_WAIT2 state - */ - if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_should_close(sk)) - mptcp_do_fastclose(sk); + if (mptcp_close_tout_expired(sk)) { + mptcp_do_fastclose(sk); + mptcp_close_wake_up(sk); + } - if (sk->sk_state == TCP_CLOSE) { - __mptcp_destroy_sock(sk); - goto unlock; - } + if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) { + __mptcp_destroy_sock(sk); + goto unlock; } if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) @@ -2717,7 +2767,7 @@ static void __mptcp_init_sock(struct sock *sk) /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); - timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); + timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) @@ -2808,8 +2858,8 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } break; } @@ -2892,7 +2942,7 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); msk->pm.status = 0; mptcp_release_sched(msk); @@ -2975,7 +3025,6 @@ bool __mptcp_close(struct sock *sk, long timeout) cleanup: /* orphan all the subflows */ - inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); @@ -3012,7 +3061,7 @@ cleanup: __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - mptcp_reset_timeout(msk, 0); + mptcp_start_tout_timer(sk); } return do_cancel_work; @@ -3059,12 +3108,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under * msk->firstsocket lock). @@ -3075,8 +3118,8 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); - mptcp_stop_timer(sk); - sk_stop_timer(sk, &sk->sk_timer); + mptcp_stop_rtx_timer(sk); + mptcp_stop_tout_timer(sk); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); @@ -3134,7 +3177,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif - nsk->sk_wait_pending = 0; __mptcp_init_sock(nsk); msk = mptcp_sk(nsk); @@ -3386,24 +3428,21 @@ static void schedule_3rdack_retransmission(struct sock *ssk) sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); } -void mptcp_subflow_process_delegated(struct sock *ssk) +void mptcp_subflow_process_delegated(struct sock *ssk, long status) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + if (status & BIT(MPTCP_DELEGATE_SEND)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, true); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); - mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND); } - if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) { + if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); - mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK); - } } static int mptcp_hash(struct sock *sk) @@ -3929,14 +3968,17 @@ static int mptcp_napi_poll(struct napi_struct *napi, int budget) struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bh_lock_sock_nested(ssk); - if (!sock_owned_by_user(ssk) && - mptcp_subflow_has_delegated_action(subflow)) - mptcp_subflow_process_delegated(ssk); - /* ... elsewhere tcp_release_cb_override already processed - * the action or will do at next release_sock(). - * In both case must dequeue the subflow here - on the same - * CPU that scheduled it. - */ + if (!sock_owned_by_user(ssk)) { + mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0)); + } else { + /* tcp_release_cb_override already processed + * the action or will do at next release_sock(). + * In both case must dequeue the subflow here - on the same + * CPU that scheduled it. + */ + smp_wmb(); + clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status); + } bh_unlock_sock(ssk); sock_put(ssk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7254b3562575..3612545fa62e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -444,9 +444,11 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); -#define MPTCP_DELEGATE_SEND 0 -#define MPTCP_DELEGATE_ACK 1 +#define MPTCP_DELEGATE_SCHEDULED 0 +#define MPTCP_DELEGATE_SEND 1 +#define MPTCP_DELEGATE_ACK 2 +#define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED)) /* MPTCP subflow context */ struct mptcp_subflow_context { struct list_head node;/* conn_list of subflows */ @@ -564,23 +566,24 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow) return subflow->map_seq + mptcp_subflow_get_map_offset(subflow); } -void mptcp_subflow_process_delegated(struct sock *ssk); +void mptcp_subflow_process_delegated(struct sock *ssk, long actions); static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action) { + long old, set_bits = BIT(MPTCP_DELEGATE_SCHEDULED) | BIT(action); struct mptcp_delegated_action *delegated; bool schedule; /* the caller held the subflow bh socket lock */ lockdep_assert_in_softirq(); - /* The implied barrier pairs with mptcp_subflow_delegated_done(), and - * ensures the below list check sees list updates done prior to status - * bit changes + /* The implied barrier pairs with tcp_release_cb_override() + * mptcp_napi_poll(), and ensures the below list check sees list + * updates done prior to delegated status bits changes */ - if (!test_and_set_bit(action, &subflow->delegated_status)) { - /* still on delegated list from previous scheduling */ - if (!list_empty(&subflow->delegated_node)) + old = set_mask_bits(&subflow->delegated_status, 0, set_bits); + if (!(old & BIT(MPTCP_DELEGATE_SCHEDULED))) { + if (WARN_ON_ONCE(!list_empty(&subflow->delegated_node))) return; delegated = this_cpu_ptr(&mptcp_delegated_actions); @@ -605,20 +608,6 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) return ret; } -static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) -{ - return !!READ_ONCE(subflow->delegated_status); -} - -static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action) -{ - /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before - * touching the status bit - */ - smp_wmb(); - clear_bit(action, &subflow->delegated_status); -} - int mptcp_is_enabled(const struct net *net); unsigned int mptcp_get_add_addr_timeout(const struct net *net); int mptcp_is_checksum_enabled(const struct net *net); @@ -718,7 +707,29 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout); +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); + +static inline void mptcp_stop_tout_timer(struct sock *sk) +{ + if (!inet_csk(sk)->icsk_mtup.probe_timestamp) + return; + + sk_stop_timer(sk, &sk->sk_timer); + inet_csk(sk)->icsk_mtup.probe_timestamp = 0; +} + +static inline void mptcp_set_close_tout(struct sock *sk, unsigned long tout) +{ + /* avoid 0 timestamp, as that means no close timeout */ + inet_csk(sk)->icsk_mtup.probe_timestamp = tout ? : 1; +} + +static inline void mptcp_start_tout_timer(struct sock *sk) +{ + mptcp_set_close_tout(sk, tcp_jiffies32); + mptcp_reset_tout_timer(mptcp_sk(sk), 0); +} + static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9bf3c7bc1762..9c1f8d1d63d2 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1226,7 +1226,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) WRITE_ONCE(subflow->fail_tout, fail_tout); tcp_send_ack(ssk); - mptcp_reset_timeout(msk, subflow->fail_tout); + mptcp_reset_tout_timer(msk, subflow->fail_tout); } static bool subflow_check_data_avail(struct sock *ssk) @@ -1362,42 +1362,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } -void __mptcp_error_report(struct sock *sk) -{ - struct mptcp_subflow_context *subflow; - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int err = sock_error(ssk); - int ssk_state; - - if (!err) - continue; - - /* only propagate errors on fallen-back sockets or - * on MPC connect - */ - if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) - continue; - - /* We need to propagate only transition to CLOSE state. - * Orphaned socket will see such state change via - * subflow_sched_work_if_closed() and that path will properly - * destroy the msk as needed. - */ - ssk_state = inet_sk_state_load(ssk); - if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); - WRITE_ONCE(sk->sk_err, -err); - - /* This barrier is coupled with smp_rmb() in mptcp_poll() */ - smp_wmb(); - sk_error_report(sk); - break; - } -} - static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; @@ -1588,6 +1552,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, mptcp_sock_graft(ssk, sk->sk_socket); iput(SOCK_INODE(sf)); WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_stop_tout_timer(sk); return 0; failed_unlink: @@ -1991,9 +1956,15 @@ static void subflow_ulp_clone(const struct request_sock *req, static void tcp_release_cb_override(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + long status; - if (mptcp_subflow_has_delegated_action(subflow)) - mptcp_subflow_process_delegated(ssk); + /* process and clear all the pending actions, but leave the subflow into + * the napi queue. To respect locking, only the same CPU that originated + * the action can touch the list. mptcp_napi_poll will take care of it. + */ + status = set_mask_bits(&subflow->delegated_status, MPTCP_DELEGATE_ACTIONS_MASK, 0); + if (status) + mptcp_subflow_process_delegated(ssk, status); tcp_release_cb(ssk); } diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 62fb1031763d..f8854bff286c 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -89,6 +89,11 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, if ((had_link == has_link) || chained) return 0; + if (had_link) + netif_carrier_off(ndp->ndev.dev); + else + netif_carrier_on(ndp->ndev.dev); + if (!ndp->multi_package && !nc->package->multi_channel) { if (had_link) { ndp->flags |= NCSI_DEV_RESHUFFLE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e564b5174261..35d2f9c9ada0 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -683,6 +683,14 @@ __ip_set_put(struct ip_set *set) * a separate reference counter */ static void +__ip_set_get_netlink(struct ip_set *set) +{ + write_lock_bh(&ip_set_ref_lock); + set->ref_netlink++; + write_unlock_bh(&ip_set_ref_lock); +} + +static void __ip_set_put_netlink(struct ip_set *set) { write_lock_bh(&ip_set_ref_lock); @@ -1693,11 +1701,11 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, do { if (retried) { - __ip_set_get(set); + __ip_set_get_netlink(set); nfnl_unlock(NFNL_SUBSYS_IPSET); cond_resched(); nfnl_lock(NFNL_SUBSYS_IPSET); - __ip_set_put(set); + __ip_set_put_netlink(set); } ip_set_lock(set); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index da5af28ff57b..4174076c66fa 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1439,7 +1439,7 @@ static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) sin.sin_addr.s_addr = addr; sin.sin_port = 0; - return sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin)); + return kernel_bind(sock, (struct sockaddr *)&sin, sizeof(sin)); } static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, @@ -1505,8 +1505,8 @@ static int make_send_sock(struct netns_ipvs *ipvs, int id, } get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); - result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr, - salen, 0); + result = kernel_connect(sock, (struct sockaddr *)&mcast_addr, + salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); goto error; @@ -1546,7 +1546,7 @@ static int make_receive_sock(struct netns_ipvs *ipvs, int id, get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); sock->sk->sk_bound_dev_if = dev->ifindex; - result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); + result = kernel_bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); goto error; diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index c7a6114091ae..b21799d468d2 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -381,6 +381,8 @@ __bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) struct nf_conn *nfct = (struct nf_conn *)nfct_i; int err; + if (!nf_ct_is_confirmed(nfct)) + nfct->timeout += nfct_time_stamp; nfct->status |= IPS_CONFIRMED; err = nf_conntrack_hash_check_insert(nfct); if (err < 0) { diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 0b513f7bf9f3..dd62cc12e775 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -40,10 +40,10 @@ static const u8 nf_ct_ext_type_len[NF_CT_EXT_NUM] = { [NF_CT_EXT_ECACHE] = sizeof(struct nf_conntrack_ecache), #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP - [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_acct), + [NF_CT_EXT_TSTAMP] = sizeof(struct nf_conn_tstamp), #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT - [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_tstamp), + [NF_CT_EXT_TIMEOUT] = sizeof(struct nf_conn_timeout), #endif #ifdef CONFIG_NF_CONNTRACK_LABELS [NF_CT_EXT_LABELS] = sizeof(struct nf_conn_labels), diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index b6bcc8f2f46b..c6bd533983c1 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -112,7 +112,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, /* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* cookie_ack */ {sCL, sCL, sCW, sES, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, /* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -126,7 +126,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_echo */ {sIV, sCL, sCE, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, /* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, @@ -412,6 +412,9 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; + } else if (sch->type == SCTP_CID_COOKIE_ACK) { + ct->proto.sctp.init[dir] = 0; + ct->proto.sctp.init[!dir] = 0; } else if (sch->type == SCTP_CID_HEARTBEAT) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); @@ -461,16 +464,18 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } /* If it is an INIT or an INIT ACK note down the vtag */ - if (sch->type == SCTP_CID_INIT || - sch->type == SCTP_CID_INIT_ACK) { - struct sctp_inithdr _inithdr, *ih; + if (sch->type == SCTP_CID_INIT) { + struct sctp_inithdr _ih, *ih; - ih = skb_header_pointer(skb, offset + sizeof(_sch), - sizeof(_inithdr), &_inithdr); - if (ih == NULL) + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) goto out_unlock; - pr_debug("Setting vtag %x for dir %d\n", - ih->init_tag, !dir); + + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir]) + ct->proto.sctp.init[!dir] = 0; + ct->proto.sctp.init[dir] = 1; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; /* don't renew timeout on init retransmit so @@ -481,6 +486,24 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, old_state == SCTP_CONNTRACK_CLOSED && nf_ct_is_confirmed(ct)) ignore = true; + } else if (sch->type == SCTP_CID_INIT_ACK) { + struct sctp_inithdr _ih, *ih; + __be32 vtag; + + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(*ih), &_ih); + if (!ih) + goto out_unlock; + + vtag = ct->proto.sctp.vtag[!dir]; + if (!ct->proto.sctp.init[!dir] && vtag && vtag != ih->init_tag) + goto out_unlock; + /* collision */ + if (ct->proto.sctp.init[dir] && ct->proto.sctp.init[!dir] && + vtag != ih->init_tag) + goto out_unlock; + + pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); + ct->proto.sctp.vtag[!dir] = ih->init_tag; } ct->proto.sctp.state = new_state; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1d34d700bd09..920a5a29ae1d 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -316,12 +316,6 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, } EXPORT_SYMBOL_GPL(flow_offload_refresh); -static bool nf_flow_is_outdated(const struct flow_offload *flow) -{ - return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && - !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); -} - static inline bool nf_flow_has_expired(const struct flow_offload *flow) { return nf_flow_timeout_delta(flow->timeout) <= 0; @@ -407,12 +401,18 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } +static bool nf_flow_custom_gc(struct nf_flowtable *flow_table, + const struct flow_offload *flow) +{ + return flow_table->type->gc && flow_table->type->gc(flow); +} + static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - nf_flow_is_outdated(flow)) + nf_flow_custom_gc(flow_table, flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e429ebba74b3..29c651804cb2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1219,6 +1219,10 @@ static int nf_tables_updtable(struct nft_ctx *ctx) flags & NFT_TABLE_F_OWNER)) return -EOPNOTSUPP; + /* No dormant off/on/off/on games in single transaction */ + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, sizeof(struct nft_trans_table)); if (trans == NULL) @@ -1432,7 +1436,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -1446,8 +1450,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, set)) continue; - if (nft_set_is_anonymous(set) && - !list_empty(&set->bindings)) + if (nft_set_is_anonymous(set)) continue; err = nft_delset(ctx, set); @@ -1477,7 +1480,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx->chain = chain; @@ -2910,6 +2913,9 @@ static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, return PTR_ERR(chain); } + if (nft_chain_binding(chain)) + return -EOPNOTSUPP; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, chain, nla); if (nla[NFTA_CHAIN_HOOK]) { @@ -3160,7 +3166,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, if (err < 0) return err; - if (!tb[NFTA_EXPR_DATA]) + if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME]) return -EINVAL; type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); @@ -3449,6 +3455,8 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int s_idx = cb->args[0]; + unsigned int entries = 0; + int ret = 0; u64 handle; prule = NULL; @@ -3471,9 +3479,11 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, handle, reset) < 0) - return 1; - + table, chain, rule, handle, reset) < 0) { + ret = 1; + break; + } + entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: prule = rule; @@ -3481,10 +3491,10 @@ cont_skip: (*idx)++; } - if (reset && *idx) - audit_log_rule_reset(table, cb->seq, *idx); + if (reset && entries) + audit_log_rule_reset(table, cb->seq, entries); - return 0; + return ret; } static int nf_tables_dump_rules(struct sk_buff *skb, @@ -3971,6 +3981,11 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { + if (nft_chain_binding(chain)) { + err = -EOPNOTSUPP; + goto err_destroy_flow_rule; + } + err = nft_delrule(&ctx, old_rule); if (err < 0) goto err_destroy_flow_rule; @@ -4078,7 +4093,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); } - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) return -EOPNOTSUPP; } @@ -4112,7 +4127,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; @@ -5541,7 +5556,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - u64 timeout = 0; nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (nest == NULL) @@ -5577,15 +5591,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, htonl(*nft_set_ext_flags(ext)))) goto nla_put_failure; - if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { - timeout = *nft_set_ext_timeout(ext); - if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - nf_jiffies64_to_msecs(timeout), - NFTA_SET_ELEM_PAD)) - goto nla_put_failure; - } else if (set->flags & NFT_SET_TIMEOUT) { - timeout = READ_ONCE(set->timeout); - } + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && + nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, + nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), + NFTA_SET_ELEM_PAD)) + goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { u64 expires, now = get_jiffies_64(); @@ -5600,9 +5610,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; - - if (reset) - *nft_set_ext_expiration(ext) = now + timeout; } if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { @@ -7183,8 +7190,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && - (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) + if (nft_set_is_anonymous(set)) + return -EOPNOTSUPP; + + if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) return -EBUSY; nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); @@ -7598,6 +7607,16 @@ nla_put_failure: return -1; } +static void audit_log_obj_reset(const struct nft_table *table, + unsigned int base_seq, unsigned int nentries) +{ + char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); + + audit_log_nfcfg(buf, table->family, nentries, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); +} + struct nft_obj_filter { char *table; u32 type; @@ -7612,8 +7631,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; + unsigned int entries = 0; struct nft_object *obj; bool reset = false; + int rc = 0; if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) reset = true; @@ -7626,6 +7647,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) if (family != NFPROTO_UNSPEC && family != table->family) continue; + entries = 0; list_for_each_entry_rcu(obj, &table->objects, list) { if (!nft_is_active(net, obj)) goto cont; @@ -7641,34 +7663,27 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) filter->type != NFT_OBJECT_UNSPEC && obj->ops->type->type != filter->type) goto cont; - if (reset) { - char *buf = kasprintf(GFP_ATOMIC, - "%s:%u", - table->name, - nft_net->base_seq); - - audit_log_nfcfg(buf, - family, - obj->handle, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); - } - if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NFT_MSG_NEWOBJ, - NLM_F_MULTI | NLM_F_APPEND, - table->family, table, - obj, reset) < 0) - goto done; + rc = nf_tables_fill_obj_info(skb, net, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NFT_MSG_NEWOBJ, + NLM_F_MULTI | NLM_F_APPEND, + table->family, table, + obj, reset); + if (rc < 0) + break; + entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } + if (reset && entries) + audit_log_obj_reset(table, nft_net->base_seq, entries); + if (rc < 0) + break; } -done: rcu_read_unlock(); cb->args[0] = idx; @@ -7773,7 +7788,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, audit_log_nfcfg(buf, family, - obj->handle, + 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); @@ -7854,24 +7869,14 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, return nft_delobj(&ctx, obj); } -void nft_obj_notify(struct net *net, const struct nft_table *table, - struct nft_object *obj, u32 portid, u32 seq, int event, - u16 flags, int family, int report, gfp_t gfp) +static void +__nft_obj_notify(struct net *net, const struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, int event, + u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; int err; - char *buf = kasprintf(gfp, "%s:%u", - table->name, nft_net->base_seq); - - audit_log_nfcfg(buf, - family, - obj->handle, - event == NFT_MSG_NEWOBJ ? - AUDIT_NFT_OP_OBJ_REGISTER : - AUDIT_NFT_OP_OBJ_UNREGISTER, - gfp); - kfree(buf); if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -7894,13 +7899,35 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } + +void nft_obj_notify(struct net *net, const struct nft_table *table, + struct nft_object *obj, u32 portid, u32 seq, int event, + u16 flags, int family, int report, gfp_t gfp) +{ + struct nftables_pernet *nft_net = nft_pernet(net); + char *buf = kasprintf(gfp, "%s:%u", + table->name, nft_net->base_seq); + + audit_log_nfcfg(buf, + family, + obj->handle, + event == NFT_MSG_NEWOBJ ? + AUDIT_NFT_OP_OBJ_REGISTER : + AUDIT_NFT_OP_OBJ_UNREGISTER, + gfp); + kfree(buf); + + __nft_obj_notify(net, table, obj, portid, seq, event, + flags, family, report, gfp); +} EXPORT_SYMBOL_GPL(nft_obj_notify); static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { - nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, - ctx->flags, ctx->family, ctx->report, GFP_KERNEL); + __nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, + ctx->seq, event, ctx->flags, ctx->family, + ctx->report, GFP_KERNEL); } /* @@ -9562,12 +9589,15 @@ static int nft_trans_gc_space(struct nft_trans_gc *trans) struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { + struct nft_set *set; + if (nft_trans_gc_space(gc)) return gc; + set = gc->set; nft_trans_gc_queue_work(gc); - return nft_trans_gc_alloc(gc->set, gc_seq, gfp); + return nft_trans_gc_alloc(set, gc_seq, gfp); } void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) @@ -9582,15 +9612,18 @@ void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) { + struct nft_set *set; + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) return NULL; if (nft_trans_gc_space(gc)) return gc; + set = gc->set; call_rcu(&gc->rcu, nft_trans_gc_trans_free); - return nft_trans_gc_alloc(gc->set, 0, gfp); + return nft_trans_gc_alloc(set, 0, gfp); } void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) @@ -9605,8 +9638,9 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) call_rcu(&trans->rcu, nft_trans_gc_trans_free); } -struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq) +static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq, + bool sync) { struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; @@ -9622,7 +9656,11 @@ struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, nft_set_elem_dead(ext); dead_elem: - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (sync) + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + else + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) return NULL; @@ -9632,6 +9670,17 @@ dead_elem: return gc; } +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + return nft_trans_gc_catchall(gc, gc_seq, false); +} + +struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) +{ + return nft_trans_gc_catchall(gc, 0, true); +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -11054,7 +11103,7 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { - if (nft_chain_is_bound(chain)) + if (nft_chain_binding(chain)) continue; ctx.chain = chain; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 53c9e76473ba..f03f4d4d7d88 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -698,8 +698,8 @@ nfulnl_log_packet(struct net *net, unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; + enum ip_conntrack_info ctinfo = 0; struct nf_conn *ct = NULL; - enum ip_conntrack_info ctinfo; if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 28e2873ba24e..928312d01eb1 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -298,6 +298,7 @@ static int nft_inner_init(const struct nft_ctx *ctx, int err; if (!tb[NFTA_INNER_FLAGS] || + !tb[NFTA_INNER_NUM] || !tb[NFTA_INNER_HDRSIZE] || !tb[NFTA_INNER_TYPE] || !tb[NFTA_INNER_EXPR]) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 8cb800989947..0a689c8e0295 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -154,6 +154,17 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt) return pkt->inneroff; } +static bool nft_payload_need_vlan_copy(const struct nft_payload *priv) +{ + unsigned int len = priv->offset + priv->len; + + /* data past ether src/dst requested, copy needed */ + if (len > offsetof(struct ethhdr, h_proto)) + return true; + + return false; +} + void nft_payload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -168,11 +179,11 @@ void nft_payload_eval(const struct nft_expr *expr, switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: - if (!skb_mac_header_was_set(skb)) + if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0) goto err; if (skb_vlan_tag_present(skb) && - priv->offset >= offsetof(struct ethhdr, h_proto)) { + nft_payload_need_vlan_copy(priv)) { if (!nft_payload_copy_vlan(dest, skb, priv->offset, priv->len)) goto err; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 524763659f25..2013de934cef 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -338,12 +338,9 @@ static void nft_rhash_gc(struct work_struct *work) while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) { - nft_trans_gc_destroy(gc); - gc = NULL; - goto try_later; - } - continue; + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; } /* Ruleset has been updated, try later. */ @@ -372,7 +369,7 @@ dead_elem: nft_trans_gc_elem_add(gc, he); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: /* catchall list iteration requires rcu read side lock. */ diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 6af9c9ed4b5c..c0dcc40de358 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1596,7 +1596,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (!gc) - break; + return; nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); @@ -1610,7 +1610,7 @@ static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall(gc, 0); + gc = nft_trans_gc_catchall_sync(gc); if (gc) { nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583e..2e164a319945 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -147,7 +147,7 @@ struct nft_pipapo_match { unsigned long * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; - struct nft_pipapo_field f[]; + struct nft_pipapo_field f[] __counted_by(field_count); }; /** diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index f250b5399344..e34662f4a71e 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -233,10 +233,9 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, rb_erase(&rbe->node, &priv->root); } -static int nft_rbtree_gc_elem(const struct nft_set *__set, - struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, - u8 genmask) +static const struct nft_rbtree_elem * +nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe, u8 genmask) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -246,7 +245,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); if (!gc) - return -ENOMEM; + return ERR_PTR(-ENOMEM); /* search for end interval coming before this element. * end intervals don't carry a timeout extension, they @@ -261,6 +260,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, prev = rb_prev(prev); } + rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); nft_rbtree_gc_remove(net, set, priv, rbe_prev); @@ -272,7 +272,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, */ gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe_prev); } @@ -280,13 +280,13 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, nft_rbtree_gc_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) - return -ENOMEM; + return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe); nft_trans_gc_queue_sync_done(gc); - return 0; + return rbe_prev; } static bool nft_rbtree_update_first(const struct nft_set *set, @@ -314,7 +314,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); - int d, err; + int d; /* Descend the tree to search for an existing element greater than the * key value to insert that is greater than the new element. This is the @@ -363,9 +363,14 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (nft_set_elem_expired(&rbe->ext) && nft_set_elem_active(&rbe->ext, cur_genmask)) { - err = nft_rbtree_gc_elem(set, priv, rbe, genmask); - if (err < 0) - return err; + const struct nft_rbtree_elem *removed_end; + + removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + if (IS_ERR(removed_end)) + return PTR_ERR(removed_end); + + if (removed_end == rbe_le || removed_end == rbe_ge) + return -EAGAIN; continue; } @@ -486,11 +491,18 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *rbe = elem->priv; int err; - write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); - err = __nft_rbtree_insert(net, set, rbe, ext); - write_seqcount_end(&priv->count); - write_unlock_bh(&priv->lock); + do { + if (fatal_signal_pending(current)) + return -EINTR; + + cond_resched(); + + write_lock_bh(&priv->lock); + write_seqcount_begin(&priv->count); + err = __nft_rbtree_insert(net, set, rbe, ext); + write_seqcount_end(&priv->count); + write_unlock_bh(&priv->lock); + } while (err == -EAGAIN); return err; } @@ -556,6 +568,8 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; + } else if (nft_set_elem_expired(&rbe->ext)) { + break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; @@ -622,8 +636,7 @@ static void nft_rbtree_gc(struct work_struct *work) if (!gc) goto done; - write_lock_bh(&priv->lock); - write_seqcount_begin(&priv->count); + read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { /* Ruleset has been updated, try later. */ @@ -670,11 +683,10 @@ dead_elem: nft_trans_gc_elem_add(gc, rbe); } - gc = nft_trans_gc_catchall(gc, gc_seq); + gc = nft_trans_gc_catchall_async(gc, gc_seq); try_later: - write_seqcount_end(&priv->count); - write_unlock_bh(&priv->lock); + read_unlock_bh(&priv->lock); if (gc) nft_trans_gc_queue_async_done(gc); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 642b9d382fb4..eb086b06d60d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -352,7 +352,7 @@ static void netlink_overrun(struct sock *sk) if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { - sk->sk_err = ENOBUFS; + WRITE_ONCE(sk->sk_err, ENOBUFS); sk_error_report(sk); } } @@ -1605,7 +1605,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) goto out; } - sk->sk_err = p->code; + WRITE_ONCE(sk->sk_err, p->code); sk_error_report(sk); out: return ret; @@ -1991,7 +1991,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { - sk->sk_err = -ret; + WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); } } @@ -2511,7 +2511,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, err_bad_put: nlmsg_free(skb); err_skb: - NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index f60e424e0607..1dac28136e6a 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -203,17 +203,13 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) { llcp_sock = tmp_sock; + sock_hold(&llcp_sock->sk); break; } } read_unlock(&local->sockets.lock); - if (llcp_sock == NULL) - return NULL; - - sock_hold(&llcp_sock->sk); - return llcp_sock; } @@ -346,7 +342,8 @@ static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len) static struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, - const u8 *sn, size_t sn_len) + const u8 *sn, size_t sn_len, + bool needref) { struct sock *sk; struct nfc_llcp_sock *llcp_sock, *tmp_sock; @@ -382,6 +379,8 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, if (memcmp(sn, tmp_sock->service_name, sn_len) == 0) { llcp_sock = tmp_sock; + if (needref) + sock_hold(&llcp_sock->sk); break; } } @@ -423,7 +422,8 @@ u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, * to this service name. */ if (nfc_llcp_sock_from_sn(local, sock->service_name, - sock->service_name_len) != NULL) { + sock->service_name_len, + false) != NULL) { mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; @@ -824,16 +824,7 @@ out: static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, const u8 *sn, size_t sn_len) { - struct nfc_llcp_sock *llcp_sock; - - llcp_sock = nfc_llcp_sock_from_sn(local, sn, sn_len); - - if (llcp_sock == NULL) - return NULL; - - sock_hold(&llcp_sock->sk); - - return llcp_sock; + return nfc_llcp_sock_from_sn(local, sn, sn_len, true); } static const u8 *nfc_llcp_connect_sn(const struct sk_buff *skb, size_t *sn_len) @@ -1298,7 +1289,8 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, } llcp_sock = nfc_llcp_sock_from_sn(local, service_name, - service_name_len); + service_name_len, + true); if (!llcp_sock) { sap = 0; goto add_snl; @@ -1318,6 +1310,7 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, if (sap == LLCP_SAP_MAX) { sap = 0; + nfc_llcp_sock_put(llcp_sock); goto add_snl; } @@ -1335,6 +1328,7 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, pr_debug("%p %d\n", llcp_sock, sap); + nfc_llcp_sock_put(llcp_sock); add_snl: sdp = nfc_llcp_build_sdres_tlv(tid, sap); if (sdp == NULL) @@ -1636,7 +1630,9 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) timer_setup(&local->sdreq_timer, nfc_llcp_sdreq_timer, 0); INIT_WORK(&local->sdreq_timeout_work, nfc_llcp_sdreq_timeout_work); + spin_lock(&llcp_devices_lock); list_add(&local->list, &llcp_devices); + spin_unlock(&llcp_devices_lock); return 0; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index fff755dde30d..6c9592d05120 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -909,6 +909,11 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, return -EINVAL; } + if (protocol >= NFC_PROTO_MAX) { + pr_err("the requested nfc protocol is invalid\n"); + return -EINVAL; + } + if (!(nci_target->supported_protocols & (1 << protocol))) { pr_err("target does not support the requested protocol 0x%x\n", protocol); diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index 0935527d1d12..b68150c971d0 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -151,6 +151,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge) int ret; skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL); + if (!skb) + return -ENOMEM; /* add the NCI SPI header to the start of the buffer */ hdr = skb_push(skb, NCI_SPI_HDR_LEN); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8f97648d652f..a84e00b5904b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3607,7 +3607,12 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; - memcpy(sll->sll_addr_flex, dev->dev_addr, dev->addr_len); + + /* Let __fortify_memcpy_chk() know the actual buffer size. */ + memcpy(((struct sockaddr_storage *)sll)->__data + + offsetof(struct sockaddr_ll, sll_addr) - + offsetofend(struct sockaddr_ll, sll_family), + dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index d36f3f6b4351..b15cf316b23a 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -86,11 +86,13 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_RESOLVED: - rdma_set_service_type(cm_id, conn->c_tos); - rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); - /* XXX do we need to clean up if this fails? */ - ret = rdma_resolve_route(cm_id, - RDS_RDMA_RESOLVE_TIMEOUT_MS); + if (conn) { + rdma_set_service_type(cm_id, conn->c_tos); + rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); + /* XXX do we need to clean up if this fails? */ + ret = rdma_resolve_route(cm_id, + RDS_RDMA_RESOLVE_TIMEOUT_MS); + } break; case RDMA_CM_EVENT_ROUTE_RESOLVED: diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index f0c477c5d1db..a0046e99d6df 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -145,7 +145,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) addrlen = sizeof(sin); } - ret = sock->ops->bind(sock, addr, addrlen); + ret = kernel_bind(sock, addr, addrlen); if (ret) { rdsdebug("bind failed with %d at address %pI6c\n", ret, &conn->c_laddr); @@ -173,7 +173,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) * own the socket */ rds_tcp_set_callbacks(sock, cp); - ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK); + ret = kernel_connect(sock, addr, addrlen, O_NONBLOCK); rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 014fa24418c1..53b3535a1e4a 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -306,7 +306,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6) addr_len = sizeof(*sin); } - ret = sock->ops->bind(sock, (struct sockaddr *)&ss, addr_len); + ret = kernel_bind(sock, (struct sockaddr *)&ss, addr_len); if (ret < 0) { rdsdebug("could not bind %s listener socket: %d\n", isv6 ? "IPv6" : "IPv4", ret); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 01fca7a10b4b..14cc8fe8584b 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -48,6 +48,7 @@ struct rfkill { bool persistent; bool polling_paused; bool suspended; + bool need_sync; const struct rfkill_ops *ops; void *data; @@ -368,6 +369,17 @@ static void rfkill_set_block(struct rfkill *rfkill, bool blocked) rfkill_event(rfkill); } +static void rfkill_sync(struct rfkill *rfkill) +{ + lockdep_assert_held(&rfkill_global_mutex); + + if (!rfkill->need_sync) + return; + + rfkill_set_block(rfkill, rfkill_global_states[rfkill->type].cur); + rfkill->need_sync = false; +} + static void rfkill_update_global_state(enum rfkill_type type, bool blocked) { int i; @@ -730,6 +742,10 @@ static ssize_t soft_show(struct device *dev, struct device_attribute *attr, { struct rfkill *rfkill = to_rfkill(dev); + mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); + mutex_unlock(&rfkill_global_mutex); + return sysfs_emit(buf, "%d\n", (rfkill->state & RFKILL_BLOCK_SW) ? 1 : 0); } @@ -751,6 +767,7 @@ static ssize_t soft_store(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); rfkill_set_block(rfkill, state); mutex_unlock(&rfkill_global_mutex); @@ -783,6 +800,10 @@ static ssize_t state_show(struct device *dev, struct device_attribute *attr, { struct rfkill *rfkill = to_rfkill(dev); + mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); + mutex_unlock(&rfkill_global_mutex); + return sysfs_emit(buf, "%d\n", user_state_from_blocked(rfkill->state)); } @@ -805,6 +826,7 @@ static ssize_t state_store(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&rfkill_global_mutex); + rfkill_sync(rfkill); rfkill_set_block(rfkill, state == RFKILL_USER_STATE_SOFT_BLOCKED); mutex_unlock(&rfkill_global_mutex); @@ -1032,14 +1054,10 @@ static void rfkill_uevent_work(struct work_struct *work) static void rfkill_sync_work(struct work_struct *work) { - struct rfkill *rfkill; - bool cur; - - rfkill = container_of(work, struct rfkill, sync_work); + struct rfkill *rfkill = container_of(work, struct rfkill, sync_work); mutex_lock(&rfkill_global_mutex); - cur = rfkill_global_states[rfkill->type].cur; - rfkill_set_block(rfkill, cur); + rfkill_sync(rfkill); mutex_unlock(&rfkill_global_mutex); } @@ -1087,6 +1105,7 @@ int __must_check rfkill_register(struct rfkill *rfkill) round_jiffies_relative(POLL_INTERVAL)); if (!rfkill->persistent || rfkill_epo_lock_active) { + rfkill->need_sync = true; schedule_work(&rfkill->sync_work); } else { #ifdef CONFIG_RFKILL_INPUT @@ -1161,7 +1180,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) init_waitqueue_head(&data->read_wait); mutex_lock(&rfkill_global_mutex); - mutex_lock(&data->mtx); /* * start getting events from elsewhere but hold mtx to get * startup events added first @@ -1171,11 +1189,13 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) goto free; + rfkill_sync(rfkill); rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD); + mutex_lock(&data->mtx); list_add_tail(&ev->list, &data->events); + mutex_unlock(&data->mtx); } list_add(&data->list, &rfkill_fds); - mutex_unlock(&data->mtx); mutex_unlock(&rfkill_global_mutex); file->private_data = data; @@ -1183,7 +1203,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) return stream_open(inode, file); free: - mutex_unlock(&data->mtx); mutex_unlock(&rfkill_global_mutex); mutex_destroy(&data->mtx); list_for_each_entry_safe(ev, tmp, &data->events, list) diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index e9d1b2f2ff0a..5a81505fba9a 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -108,13 +108,13 @@ static int rfkill_gpio_probe(struct platform_device *pdev) rfkill->clk = devm_clk_get(&pdev->dev, NULL); - gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); rfkill->reset_gpio = gpio; - gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 7c652d14528b..fb52d6f9aff9 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -278,7 +278,16 @@ err_nat: return err; } +static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + static struct nf_flowtable_type flowtable_ct = { + .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, .owner = THIS_MODULE, }; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index da4c179a4d41..6663e971a13e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -366,7 +366,7 @@ static int u32_init(struct tcf_proto *tp) idr_init(&root_ht->handle_idr); if (tp_c == NULL) { - tp_c = kzalloc(struct_size(tp_c, hlist->ht, 1), GFP_KERNEL); + tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL); if (tp_c == NULL) { kfree(root_ht); return -ENOBUFS; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3554085bc2be..880c5f16b29c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -902,6 +902,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc, cl->cl_flags |= HFSC_USC; } +static void +hfsc_upgrade_rt(struct hfsc_class *cl) +{ + cl->cl_fsc = cl->cl_rsc; + rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); + cl->cl_flags |= HFSC_FSC; +} + static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { [TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) }, @@ -1011,10 +1019,6 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (parent == NULL) return -ENOENT; } - if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { - NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC"); - return -EINVAL; - } if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0) return -EINVAL; @@ -1065,6 +1069,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->cf_tree = RB_ROOT; sch_tree_lock(sch); + /* Check if the inner class is a misconfigured 'rt' */ + if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { + NL_SET_ERR_MSG(extack, + "Forced curve change on parent 'rt' to 'sc'"); + hfsc_upgrade_rt(parent); + } qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 796529167e8d..c45c192b7878 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1159,8 +1159,7 @@ int sctp_assoc_update(struct sctp_association *asoc, /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) - if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) && - !sctp_assoc_add_peer(asoc, &trans->ipaddr, + if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ab943e8fb1db..7f89e43154c0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2450,6 +2450,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, if (trans) { trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval); + sctp_transport_reset_hb_timer(trans); } else if (asoc) { asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval); diff --git a/net/smc/Kconfig b/net/smc/Kconfig index 1ab3c5a2c5ad..746be3996768 100644 --- a/net/smc/Kconfig +++ b/net/smc/Kconfig @@ -2,6 +2,7 @@ config SMC tristate "SMC socket protocol family" depends on INET && INFINIBAND + depends on m || ISM != m help SMC-R provides a "sockets over RDMA" solution making use of RDMA over Converged Ethernet (RoCE) technology to upgrade diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index bacdd971615e..35ddebae8894 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1201,6 +1201,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, (struct smc_clc_msg_accept_confirm_v2 *)aclc; struct smc_clc_first_contact_ext *fce = smc_get_clc_first_contact_ext(clc_v2, false); + struct net *net = sock_net(&smc->sk); int rc; if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1) @@ -1210,7 +1211,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN); ini->smcrv2.uses_gateway = false; } else { - if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr, + if (smc_ib_find_route(net, smc->clcsock->sk->sk_rcv_saddr, smc_ib_gid_to_ipv4(aclc->r0.lcl.gid), ini->smcrv2.nexthop_mac, &ini->smcrv2.uses_gateway)) @@ -2361,7 +2362,7 @@ static int smc_listen_find_device(struct smc_sock *new_smc, smc_find_ism_store_rc(rc, ini); return (!rc) ? 0 : ini->rc; } - return SMC_CLC_DECL_NOSMCDEV; + return prfx_rc; } /* listen worker: finish RDMA setup */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 9b66d6aeeb1a..89981dbe46c9 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -193,7 +193,7 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; } -int smc_ib_find_route(__be32 saddr, __be32 daddr, +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway) { struct neighbour *neigh = NULL; @@ -205,7 +205,7 @@ int smc_ib_find_route(__be32 saddr, __be32 daddr, if (daddr == cpu_to_be32(INADDR_NONE)) goto out; - rt = ip_route_output_flow(&init_net, &fl4, NULL); + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out; if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) @@ -235,6 +235,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev, if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) { struct in_device *in_dev = __in_dev_get_rcu(ndev); + struct net *net = dev_net(ndev); const struct in_ifaddr *ifa; bool subnet_match = false; @@ -248,7 +249,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev, } if (!subnet_match) goto out; - if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr, + if (smcrv2->daddr && smc_ib_find_route(net, smcrv2->saddr, smcrv2->daddr, smcrv2->nexthop_mac, &smcrv2->uses_gateway)) diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 4df5f8c8a0a1..ef8ac2b7546d 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -112,7 +112,7 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk, int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index, struct smc_init_info_smcrv2 *smcrv2); -int smc_ib_find_route(__be32 saddr, __be32 daddr, +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway); bool smc_ib_is_valid_local_systemid(void); int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index aa8928975cc6..9d32058db2b5 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -92,13 +92,14 @@ do { \ typeof(_smc_stats) stats = (_smc_stats); \ typeof(_tech) t = (_tech); \ typeof(_len) l = (_len); \ - int _pos = fls64((l) >> 13); \ + int _pos; \ typeof(_rc) r = (_rc); \ int m = SMC_BUF_MAX - 1; \ this_cpu_inc((*stats).smc[t].key ## _cnt); \ - if (r <= 0) \ + if (r <= 0 || l <= 0) \ break; \ - _pos = (_pos < m) ? ((l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + _pos = fls64((l - 1) >> 13); \ + _pos = (_pos <= m) ? _pos : m; \ this_cpu_inc((*stats).smc[t].key ## _pd.buf[_pos]); \ this_cpu_add((*stats).smc[t].key ## _bytes, r); \ } \ @@ -138,9 +139,12 @@ while (0) do { \ typeof(_len) _l = (_len); \ typeof(_tech) t = (_tech); \ - int _pos = fls((_l) >> 13); \ + int _pos; \ int m = SMC_BUF_MAX - 1; \ - _pos = (_pos < m) ? ((_l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + if (_l <= 0) \ + break; \ + _pos = fls((_l - 1) >> 13); \ + _pos = (_pos <= m) ? _pos : m; \ this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \ } \ while (0) diff --git a/net/socket.c b/net/socket.c index be301d523679..5740475e084c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -737,6 +737,14 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) return ret; } +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + int err = security_socket_sendmsg(sock, msg, + msg_data_left(msg)); + + return err ?: sock_sendmsg_nosec(sock, msg); +} + /** * sock_sendmsg - send a message through @sock * @sock: socket @@ -747,10 +755,19 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) */ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { - int err = security_socket_sendmsg(sock, msg, - msg_data_left(msg)); + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int ret; - return err ?: sock_sendmsg_nosec(sock, msg); + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + + return ret; } EXPORT_SYMBOL(sock_sendmsg); @@ -1138,7 +1155,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -2174,7 +2191,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -2538,7 +2555,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. @@ -3499,7 +3516,12 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { - return READ_ONCE(sock->ops)->bind(sock, addr, addrlen); + struct sockaddr_storage address; + + memcpy(&address, addr, addrlen); + + return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *)&address, + addrlen); } EXPORT_SYMBOL(kernel_bind); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 2f16f9d17966..814b0169f972 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -769,9 +769,14 @@ int rpcauth_wrap_req(struct rpc_task *task, struct xdr_stream *xdr) * @task: controlling RPC task * @xdr: xdr_stream containing RPC Reply header * - * On success, @xdr is updated to point past the verifier and - * zero is returned. Otherwise, @xdr is in an undefined state - * and a negative errno is returned. + * Return values: + * %0: Verifier is valid. @xdr now points past the verifier. + * %-EIO: Verifier is corrupted or message ended early. + * %-EACCES: Verifier is intact but not valid. + * %-EPROTONOSUPPORT: Server does not support the requested auth type. + * + * When a negative errno is returned, @xdr is left in an undefined + * state. */ int rpcauth_checkverf(struct rpc_task *task, struct xdr_stream *xdr) diff --git a/net/sunrpc/auth_tls.c b/net/sunrpc/auth_tls.c index de7678f8a23d..87f570fd3b00 100644 --- a/net/sunrpc/auth_tls.c +++ b/net/sunrpc/auth_tls.c @@ -129,9 +129,9 @@ static int tls_validate(struct rpc_task *task, struct xdr_stream *xdr) if (*p != rpc_auth_null) return -EIO; if (xdr_stream_decode_opaque_inline(xdr, &str, starttls_len) != starttls_len) - return -EIO; + return -EPROTONOSUPPORT; if (memcmp(str, starttls_token, starttls_len)) - return -EIO; + return -EPROTONOSUPPORT; return 0; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8d75290f1a31..9c210273d06b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2476,8 +2476,7 @@ call_status(struct rpc_task *task) goto out_exit; } task->tk_action = call_encode; - if (status != -ECONNRESET && status != -ECONNABORTED) - rpc_check_timeout(task); + rpc_check_timeout(task); return; out_exit: rpc_call_rpcerror(task, status); @@ -2725,7 +2724,15 @@ out_unparsable: out_verifier: trace_rpc_bad_verifier(task); - goto out_err; + switch (error) { + case -EPROTONOSUPPORT: + goto out_err; + case -EACCES: + /* Re-encode with a fresh cred */ + fallthrough; + default: + goto out_garbage; + } out_msg_denied: error = -EACCES; @@ -2751,6 +2758,7 @@ out_msg_denied: case rpc_autherr_rejectedverf: case rpcsec_gsserr_credproblem: case rpcsec_gsserr_ctxproblem: + rpcauth_invalcred(task); if (!task->tk_cred_retry) break; task->tk_cred_retry--; @@ -2907,19 +2915,22 @@ static const struct rpc_call_ops rpc_cb_add_xprt_call_ops = { * @clnt: pointer to struct rpc_clnt * @xps: pointer to struct rpc_xprt_switch, * @xprt: pointer struct rpc_xprt - * @dummy: unused + * @in_max_connect: pointer to the max_connect value for the passed in xprt transport */ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, - void *dummy) + void *in_max_connect) { struct rpc_cb_add_xprt_calldata *data; struct rpc_task *task; + int max_connect = clnt->cl_max_connect; - if (xps->xps_nunique_destaddr_xprts + 1 > clnt->cl_max_connect) { + if (in_max_connect) + max_connect = *(int *)in_max_connect; + if (xps->xps_nunique_destaddr_xprts + 1 > max_connect) { rcu_read_lock(); pr_warn("SUNRPC: reached max allowed number (%d) did not add " - "transport to server: %s\n", clnt->cl_max_connect, + "transport to server: %s\n", max_connect, rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); rcu_read_unlock(); return -EINVAL; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 71cd916e384f..a15bf2ede89b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2672,6 +2672,10 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) rcu_read_lock(); lower_xprt = rcu_dereference(lower_clnt->cl_xprt); rcu_read_unlock(); + + if (wait_on_bit_lock(&lower_xprt->state, XPRT_LOCKED, TASK_KILLABLE)) + goto out_unlock; + status = xs_tls_handshake_sync(lower_xprt, &upper_xprt->xprtsec); if (status) { trace_rpc_tls_not_started(upper_clnt, upper_xprt); @@ -2681,6 +2685,7 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) status = xs_tcp_tls_finish_connecting(lower_xprt, upper_transport); if (status) goto out_close; + xprt_release_write(lower_xprt, NULL); trace_rpc_socket_connect(upper_xprt, upper_transport->sock, 0); if (!xprt_test_and_set_connected(upper_xprt)) { @@ -2702,6 +2707,7 @@ out_unlock: return; out_close: + xprt_release_write(lower_xprt, NULL); rpc_shutdown_client(lower_clnt); /* xprt_force_disconnect() wakes tasks with a fixed tk_status code. diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 302fd749c424..43c3f1c971b8 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1441,14 +1441,14 @@ static int tipc_crypto_key_revoke(struct net *net, u8 tx_key) struct tipc_crypto *tx = tipc_net(net)->crypto_tx; struct tipc_key key; - spin_lock(&tx->lock); + spin_lock_bh(&tx->lock); key = tx->key; WARN_ON(!key.active || tx_key != key.active); /* Free the active key */ tipc_crypto_key_set_state(tx, key.passive, 0, key.pending); tipc_crypto_key_detach(tx->aead[key.active], &tx->lock); - spin_unlock(&tx->lock); + spin_unlock_bh(&tx->lock); pr_warn("%s: key is revoked\n", tx->name); return -EKEYREVOKED; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 02f583ff9239..002483e60c19 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -139,8 +139,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) int wait_on_pending_writer(struct sock *sk, long *timeo) { - int rc = 0; DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret, rc = 0; add_wait_queue(sk_sleep(sk), &wait); while (1) { @@ -154,9 +154,13 @@ int wait_on_pending_writer(struct sock *sk, long *timeo) break; } - if (sk_wait_event(sk, timeo, - !READ_ONCE(sk->sk_write_pending), &wait)) + ret = sk_wait_event(sk, timeo, + !READ_ONCE(sk->sk_write_pending), &wait); + if (ret) { + if (ret < 0) + rc = ret; break; + } } remove_wait_queue(sk_sleep(sk), &wait); return rc; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d1fc295b83b5..e9d1e83a859d 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1291,6 +1291,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; long timeo; timeo = sock_rcvtimeo(sk, nonblock); @@ -1302,6 +1303,9 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, if (sk->sk_err) return sock_error(sk); + if (ret < 0) + return ret; + if (!skb_queue_empty(&sk->sk_receive_queue)) { tls_strp_check_rcv(&ctx->strp); if (tls_strp_msg_ready(ctx)) @@ -1320,10 +1324,10 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, released = true; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, - tls_strp_msg_ready(ctx) || - !sk_psock_queue_empty(psock), - &wait); + ret = sk_wait_event(sk, &timeo, + tls_strp_msg_ready(ctx) || + !sk_psock_queue_empty(psock), + &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); @@ -1852,6 +1856,7 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx, bool nonblock) { long timeo; + int ret; timeo = sock_rcvtimeo(sk, nonblock); @@ -1861,14 +1866,16 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx, ctx->reader_contended = 1; add_wait_queue(&ctx->wq, &wait); - sk_wait_event(sk, &timeo, - !READ_ONCE(ctx->reader_present), &wait); + ret = sk_wait_event(sk, &timeo, + !READ_ONCE(ctx->reader_present), &wait); remove_wait_queue(&ctx->wq, &wait); if (timeo <= 0) return -EAGAIN; if (signal_pending(current)) return sock_intr_errno(timeo); + if (ret < 0) + return ret; } WRITE_ONCE(ctx->reader_present, 1); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index e95df847176b..b80bf681327b 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -555,6 +555,11 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) virtio_device_ready(vdev); + return 0; +} + +static void virtio_vsock_vqs_start(struct virtio_vsock *vsock) +{ mutex_lock(&vsock->tx_lock); vsock->tx_run = true; mutex_unlock(&vsock->tx_lock); @@ -569,7 +574,16 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) vsock->event_run = true; mutex_unlock(&vsock->event_lock); - return 0; + /* virtio_transport_send_pkt() can queue packets once + * the_virtio_vsock is set, but they won't be processed until + * vsock->tx_run is set to true. We queue vsock->send_pkt_work + * when initialization finishes to send those packets queued + * earlier. + * We don't need to queue the other workers (rx, event) because + * as long as we don't fill the queues with empty buffers, the + * host can't send us any notification. + */ + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); } static void virtio_vsock_vqs_del(struct virtio_vsock *vsock) @@ -664,6 +678,7 @@ static int virtio_vsock_probe(struct virtio_device *vdev) goto out; rcu_assign_pointer(the_virtio_vsock, vsock); + virtio_vsock_vqs_start(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -736,6 +751,7 @@ static int virtio_vsock_restore(struct virtio_device *vdev) goto out; rcu_assign_pointer(the_virtio_vsock, vsock); + virtio_vsock_vqs_start(vsock); out: mutex_unlock(&the_virtio_vsock_mutex); diff --git a/net/wireless/core.c b/net/wireless/core.c index 25bc2e50a061..acec41c1809a 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1181,16 +1181,11 @@ void wiphy_rfkill_set_hw_state_reason(struct wiphy *wiphy, bool blocked, } EXPORT_SYMBOL(wiphy_rfkill_set_hw_state_reason); -void cfg80211_cqm_config_free(struct wireless_dev *wdev) -{ - kfree(wdev->cqm_config); - wdev->cqm_config = NULL; -} - static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, bool unregister_netdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_cqm_config *cqm_config; unsigned int link_id; ASSERT_RTNL(); @@ -1227,7 +1222,10 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, kfree_sensitive(wdev->wext.keys); wdev->wext.keys = NULL; #endif - cfg80211_cqm_config_free(wdev); + wiphy_work_cancel(wdev->wiphy, &wdev->cqm_rssi_work); + /* deleted from the list, so can't be found from nl80211 any more */ + cqm_config = rcu_access_pointer(wdev->cqm_config); + kfree_rcu(cqm_config, rcu_head); /* * Ensure that all events have been processed and @@ -1379,6 +1377,8 @@ void cfg80211_init_wdev(struct wireless_dev *wdev) wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; #endif + wiphy_work_init(&wdev->cqm_rssi_work, cfg80211_cqm_rssi_notify_work); + if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT) wdev->ps = true; else @@ -1622,7 +1622,7 @@ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work) list_add_tail(&work->entry, &rdev->wiphy_work_list); spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); - schedule_work(&rdev->wiphy_work); + queue_work(system_unbound_wq, &rdev->wiphy_work); } EXPORT_SYMBOL_GPL(wiphy_work_queue); diff --git a/net/wireless/core.h b/net/wireless/core.h index 507d184b8b40..ba9c7170afa4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -295,12 +295,17 @@ struct cfg80211_beacon_registration { }; struct cfg80211_cqm_config { + struct rcu_head rcu_head; u32 rssi_hyst; s32 last_rssi_event_value; + enum nl80211_cqm_rssi_threshold_event last_rssi_event_type; int n_rssi_thresholds; s32 rssi_thresholds[] __counted_by(n_rssi_thresholds); }; +void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, + struct wiphy_work *work); + void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev); /* free object */ @@ -566,8 +571,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, #define CFG80211_DEV_WARN_ON(cond) ({bool __r = (cond); __r; }) #endif -void cfg80211_cqm_config_free(struct wireless_dev *wdev); - void cfg80211_release_pmsr(struct wireless_dev *wdev, u32 portid); void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev); void cfg80211_pmsr_free_wk(struct work_struct *work); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 775cac4d6100..55a1d3633853 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -43,16 +43,18 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { cr.links[link_id].status = data->links[link_id].status; + cr.links[link_id].bss = data->links[link_id].bss; + WARN_ON_ONCE(cr.links[link_id].status != WLAN_STATUS_SUCCESS && (!cr.ap_mld_addr || !cr.links[link_id].bss)); - cr.links[link_id].bss = data->links[link_id].bss; if (!cr.links[link_id].bss) continue; cr.links[link_id].bssid = data->links[link_id].bss->bssid; cr.links[link_id].addr = data->links[link_id].addr; /* need to have local link addresses for MLO connections */ - WARN_ON(cr.ap_mld_addr && !cr.links[link_id].addr); + WARN_ON(cr.ap_mld_addr && + !is_valid_ether_addr(cr.links[link_id].addr)); BUG_ON(!cr.links[link_id].bss->channel); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index de47838aca4f..931a03f4549c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5909,6 +5909,21 @@ out: nlmsg_free(msg); } +static int nl80211_validate_ap_phy_operation(struct cfg80211_ap_settings *params) +{ + struct ieee80211_channel *channel = params->chandef.chan; + + if ((params->he_cap || params->he_oper) && + (channel->flags & IEEE80211_CHAN_NO_HE)) + return -EOPNOTSUPP; + + if ((params->eht_cap || params->eht_oper) && + (channel->flags & IEEE80211_CHAN_NO_EHT)) + return -EOPNOTSUPP; + + return 0; +} + static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -6178,6 +6193,10 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (err) goto out_unlock; + err = nl80211_validate_ap_phy_operation(params); + if (err) + goto out_unlock; + if (info->attrs[NL80211_ATTR_AP_SETTINGS_FLAGS]) params->flags = nla_get_u32( info->attrs[NL80211_ATTR_AP_SETTINGS_FLAGS]); @@ -8482,7 +8501,7 @@ static int nl80211_update_mesh_config(struct sk_buff *skb, struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct mesh_config cfg; + struct mesh_config cfg = {}; u32 mask; int err; @@ -12796,7 +12815,8 @@ static int nl80211_set_cqm_txe(struct genl_info *info, } static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct net_device *dev, + struct cfg80211_cqm_config *cqm_config) { struct wireless_dev *wdev = dev->ieee80211_ptr; s32 last, low, high; @@ -12805,7 +12825,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, int err; /* RSSI reporting disabled? */ - if (!wdev->cqm_config) + if (!cqm_config) return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); /* @@ -12814,7 +12834,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, * connection is established and enough beacons received to calculate * the average. */ - if (!wdev->cqm_config->last_rssi_event_value && + if (!cqm_config->last_rssi_event_value && wdev->links[0].client.current_bss && rdev->ops->get_station) { struct station_info sinfo = {}; @@ -12828,30 +12848,30 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, cfg80211_sinfo_release_content(&sinfo); if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG)) - wdev->cqm_config->last_rssi_event_value = + cqm_config->last_rssi_event_value = (s8) sinfo.rx_beacon_signal_avg; } - last = wdev->cqm_config->last_rssi_event_value; - hyst = wdev->cqm_config->rssi_hyst; - n = wdev->cqm_config->n_rssi_thresholds; + last = cqm_config->last_rssi_event_value; + hyst = cqm_config->rssi_hyst; + n = cqm_config->n_rssi_thresholds; for (i = 0; i < n; i++) { i = array_index_nospec(i, n); - if (last < wdev->cqm_config->rssi_thresholds[i]) + if (last < cqm_config->rssi_thresholds[i]) break; } low_index = i - 1; if (low_index >= 0) { low_index = array_index_nospec(low_index, n); - low = wdev->cqm_config->rssi_thresholds[low_index] - hyst; + low = cqm_config->rssi_thresholds[low_index] - hyst; } else { low = S32_MIN; } if (i < n) { i = array_index_nospec(i, n); - high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1; + high = cqm_config->rssi_thresholds[i] + hyst - 1; } else { high = S32_MAX; } @@ -12864,6 +12884,7 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, u32 hysteresis) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_cqm_config *cqm_config = NULL, *old; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; int i, err; @@ -12881,10 +12902,6 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; - wdev_lock(wdev); - cfg80211_cqm_config_free(wdev); - wdev_unlock(wdev); - if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) { if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */ return rdev_set_cqm_rssi_config(rdev, dev, 0, 0); @@ -12901,9 +12918,10 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, n_thresholds = 0; wdev_lock(wdev); - if (n_thresholds) { - struct cfg80211_cqm_config *cqm_config; + old = rcu_dereference_protected(wdev->cqm_config, + lockdep_is_held(&wdev->mtx)); + if (n_thresholds) { cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds, n_thresholds), GFP_KERNEL); @@ -12918,11 +12936,18 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, flex_array_size(cqm_config, rssi_thresholds, n_thresholds)); - wdev->cqm_config = cqm_config; + rcu_assign_pointer(wdev->cqm_config, cqm_config); + } else { + RCU_INIT_POINTER(wdev->cqm_config, NULL); } - err = cfg80211_cqm_rssi_update(rdev, dev); - + err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); + if (err) { + rcu_assign_pointer(wdev->cqm_config, old); + kfree_rcu(cqm_config, rcu_head); + } else { + kfree_rcu(old, rcu_head); + } unlock: wdev_unlock(wdev); @@ -19073,9 +19098,8 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, s32 rssi_level, gfp_t gfp) { - struct sk_buff *msg; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_cqm_config *cqm_config; trace_cfg80211_cqm_rssi_notify(dev, rssi_event, rssi_level); @@ -19083,18 +19107,41 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_event != NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH)) return; - if (wdev->cqm_config) { - wdev->cqm_config->last_rssi_event_value = rssi_level; + rcu_read_lock(); + cqm_config = rcu_dereference(wdev->cqm_config); + if (cqm_config) { + cqm_config->last_rssi_event_value = rssi_level; + cqm_config->last_rssi_event_type = rssi_event; + wiphy_work_queue(wdev->wiphy, &wdev->cqm_rssi_work); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); - cfg80211_cqm_rssi_update(rdev, dev); +void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work) +{ + struct wireless_dev *wdev = container_of(work, struct wireless_dev, + cqm_rssi_work); + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); + enum nl80211_cqm_rssi_threshold_event rssi_event; + struct cfg80211_cqm_config *cqm_config; + struct sk_buff *msg; + s32 rssi_level; - if (rssi_level == 0) - rssi_level = wdev->cqm_config->last_rssi_event_value; - } + wdev_lock(wdev); + cqm_config = rcu_dereference_protected(wdev->cqm_config, + lockdep_is_held(&wdev->mtx)); + if (!wdev->cqm_config) + goto unlock; - msg = cfg80211_prepare_cqm(dev, NULL, gfp); + cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); + + rssi_level = cqm_config->last_rssi_event_value; + rssi_event = cqm_config->last_rssi_event_type; + + msg = cfg80211_prepare_cqm(wdev->netdev, NULL, GFP_KERNEL); if (!msg) - return; + goto unlock; if (nla_put_u32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, rssi_event)) @@ -19104,14 +19151,15 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, rssi_level)) goto nla_put_failure; - cfg80211_send_cqm(msg, gfp); + cfg80211_send_cqm(msg, GFP_KERNEL); - return; + goto unlock; nla_put_failure: nlmsg_free(msg); + unlock: + wdev_unlock(wdev); } -EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer, u32 num_packets, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 0cf1ce7b6934..8210a6090ac1 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -908,6 +908,10 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) !cfg80211_find_ssid_match(ap, request)) continue; + if (!is_broadcast_ether_addr(request->bssid) && + !ether_addr_equal(request->bssid, ap->bssid)) + continue; + if (!request->n_ssids && ap->multi_bss && !ap->transmitted_bssid) continue; @@ -2121,7 +2125,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, if (!res) goto drop; - rdev_inform_bss(rdev, &res->pub, ies, data->drv_data); + rdev_inform_bss(rdev, &res->pub, ies, drv_data->drv_data); if (data->bss_source == BSS_SOURCE_MBSSID) { /* this is a nontransmitting bss, we need to add it to diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c index f8905400ee07..d2c264030017 100644 --- a/net/xdp/xsk_queue.c +++ b/net/xdp/xsk_queue.c @@ -34,6 +34,16 @@ struct xsk_queue *xskq_create(u32 nentries, bool umem_queue) q->ring_mask = nentries - 1; size = xskq_get_ring_size(q, umem_queue); + + /* size which is overflowing or close to SIZE_MAX will become 0 in + * PAGE_ALIGN(), checking SIZE_MAX is enough due to the previous + * is_power_of_2(), the rest will be handled by vmalloc_user() + */ + if (unlikely(size == SIZE_MAX)) { + kfree(q); + return NULL; + } + size = PAGE_ALIGN(size); q->ring = vmalloc_user(size); diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index b86474084690..e21cc71095bb 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -380,8 +380,8 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err) skb->dev = dev; if (err) { - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_dropped); return 0; } @@ -426,7 +426,6 @@ static int xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); unsigned int length = skb->len; struct net_device *tdev; @@ -473,7 +472,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) tdev = dst->dev; if (tdev == dev) { - stats->collisions++; + DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", dev->name); goto tx_err_dst_release; @@ -512,13 +511,13 @@ xmit: if (net_xmit_eval(err) == 0) { dev_sw_netstats_tx_add(dev, 1, length); } else { - stats->tx_errors++; - stats->tx_aborted_errors++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_aborted_errors); } return 0; tx_err_link_failure: - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); @@ -528,7 +527,6 @@ tx_err_dst_release: static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; @@ -545,7 +543,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); if (dst->error) { dst_release(dst); - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, dst); @@ -561,7 +559,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); if (IS_ERR(rt)) { - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, &rt->dst); @@ -580,8 +578,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_err: - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d6b405782b63..d24b4d4f620e 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -851,7 +851,7 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, struct hlist_node *newpos = NULL; bool matches_s, matches_d; - if (!policy->bydst_reinsert) + if (policy->walk.dead || !policy->bydst_reinsert) continue; WARN_ON_ONCE(policy->family != family); @@ -1256,8 +1256,11 @@ static void xfrm_hash_rebuild(struct work_struct *work) struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; + if (policy->walk.dead) + continue; + dir = xfrm_policy_id2dir(policy->index); - if (policy->walk.dead || dir >= XFRM_POLICY_MAX) + if (dir >= XFRM_POLICY_MAX) continue; if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { @@ -1372,8 +1375,6 @@ EXPORT_SYMBOL(xfrm_policy_hash_rebuild); * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { - static u32 idx_generator; - for (;;) { struct hlist_head *list; struct xfrm_policy *p; @@ -1381,8 +1382,8 @@ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) int found; if (!index) { - idx = (idx_generator | dir); - idx_generator += 8; + idx = (net->xfrm.idx_generator | dir); + net->xfrm.idx_generator += 8; } else { idx = index; index = 0; @@ -1823,9 +1824,11 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + if (pol->walk.dead) + continue; + dir = xfrm_policy_id2dir(pol->index); - if (pol->walk.dead || - dir >= XFRM_POLICY_MAX || + if (dir >= XFRM_POLICY_MAX || pol->type != type) continue; @@ -1862,9 +1865,11 @@ int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + if (pol->walk.dead) + continue; + dir = xfrm_policy_id2dir(pol->index); - if (pol->walk.dead || - dir >= XFRM_POLICY_MAX || + if (dir >= XFRM_POLICY_MAX || pol->xdo.dev != dev) continue; @@ -3215,7 +3220,7 @@ no_transform: } for (i = 0; i < num_pols; i++) - pols[i]->curlft.use_time = ktime_get_real_seconds(); + WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds()); if (num_xfrms < 0) { /* Prohibit the flow */ |