diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-07-20 14:46:39 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-07-20 14:46:39 -0700 |
commit | 57f1f9dd3abea322173ea75a15887ccf14bbbe51 (patch) | |
tree | c646994b97061befcecf089bf3b2bf64e9ba9d4e /net | |
parent | e599e16c16a16be9907fb00608212df56d08d57b (diff) | |
parent | 75d42b351f564b2568392a4e53cd74a3d9df4af2 (diff) |
Merge tag 'net-6.5-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from BPF, netfilter, bluetooth and CAN.
Current release - regressions:
- eth: r8169: multiple fixes for PCIe ASPM-related problems
- vrf: fix RCU lockdep splat in output path
Previous releases - regressions:
- gso: fall back to SW segmenting with GSO_UDP_L4 dodgy bit set
- dsa: mv88e6xxx: do a final check before timing out when polling
- nf_tables: fix sleep in atomic in nft_chain_validate
Previous releases - always broken:
- sched: fix undoing tcf_bind_filter() in multiple classifiers
- bpf, arm64: fix BTI type used for freplace attached functions
- can: gs_usb: fix time stamp counter initialization
- nft_set_pipapo: fix improper element removal (leading to UAF)
Misc:
- net: support STP on bridge in non-root netns, STP prevents packet
loops so not supporting it results in freezing systems of
unsuspecting users, and in turn very upset noises being made
- fix kdoc warnings
- annotate various bits of TCP state to prevent data races"
* tag 'net-6.5-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (95 commits)
net: phy: prevent stale pointer dereference in phy_init()
tcp: annotate data-races around fastopenq.max_qlen
tcp: annotate data-races around icsk->icsk_user_timeout
tcp: annotate data-races around tp->notsent_lowat
tcp: annotate data-races around rskq_defer_accept
tcp: annotate data-races around tp->linger2
tcp: annotate data-races around icsk->icsk_syn_retries
tcp: annotate data-races around tp->keepalive_probes
tcp: annotate data-races around tp->keepalive_intvl
tcp: annotate data-races around tp->keepalive_time
tcp: annotate data-races around tp->tsoffset
tcp: annotate data-races around tp->tcp_tx_delay
Bluetooth: MGMT: Use correct address for memcpy()
Bluetooth: btusb: Fix bluetooth on Intel Macbook 2014
Bluetooth: SCO: fix sco_conn related locking and validity issues
Bluetooth: hci_conn: return ERR_PTR instead of NULL when there is no link
Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_remove_adv_monitor()
Bluetooth: coredump: fix building with coredump disabled
Bluetooth: ISO: fix iso_conn related locking and validity issues
Bluetooth: hci_event: call disconnect callback before deleting conn
...
Diffstat (limited to 'net')
34 files changed, 520 insertions, 365 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 056f9516e46d..76222565e2df 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -118,7 +118,7 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) */ params->explicit_connect = false; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (params->auto_connect) { case HCI_AUTO_CONN_EXPLICIT: @@ -127,10 +127,10 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) return; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; default: break; @@ -1426,8 +1426,8 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, if (params->auto_connect == HCI_AUTO_CONN_DISABLED || params->auto_connect == HCI_AUTO_CONN_REPORT || params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); } params->explicit_connect = true; @@ -1684,7 +1684,7 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, if (!link) { hci_conn_drop(acl); hci_conn_drop(sco); - return NULL; + return ERR_PTR(-ENOLINK); } sco->setting = setting; @@ -2254,7 +2254,7 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, if (!link) { hci_conn_drop(le); hci_conn_drop(cis); - return NULL; + return ERR_PTR(-ENOLINK); } /* If LE is already connected and CIS handle is already set proceed to diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 48917c68358d..1ec83985f1ab 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1972,6 +1972,7 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int status = 0; + int handle; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ @@ -1980,9 +1981,10 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: + handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); bt_dev_dbg(hdev, "%s remove monitor %d msft status %d", - hdev->name, monitor->handle, status); + hdev->name, handle, status); break; } @@ -2249,22 +2251,46 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, return NULL; } -/* This function requires the caller holds hdev->lock */ +/* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param; - list_for_each_entry(param, list, action) { + rcu_read_lock(); + + list_for_each_entry_rcu(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && - param->addr_type == addr_type) + param->addr_type == addr_type) { + rcu_read_unlock(); return param; + } } + rcu_read_unlock(); + return NULL; } /* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_del_init(struct hci_conn_params *param) +{ + if (list_empty(¶m->action)) + return; + + list_del_rcu(¶m->action); + synchronize_rcu(); + INIT_LIST_HEAD(¶m->action); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list) +{ + list_add_rcu(¶m->action, list); +} + +/* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { @@ -2297,14 +2323,15 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, return params; } -static void hci_conn_params_free(struct hci_conn_params *params) +void hci_conn_params_free(struct hci_conn_params *params) { + hci_pend_le_list_del_init(params); + if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); } - list_del(¶ms->action); list_del(¶ms->list); kfree(params); } @@ -2342,8 +2369,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) continue; } - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); } BT_DBG("All LE disabled connection parameters were removed"); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 95816a938cea..31ca320ce38d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1564,7 +1564,7 @@ static u8 hci_cc_le_set_privacy_mode(struct hci_dev *hdev, void *data, params = hci_conn_params_lookup(hdev, &cp->bdaddr, cp->bdaddr_type); if (params) - params->privacy_mode = cp->mode; + WRITE_ONCE(params->privacy_mode, cp->mode); hci_dev_unlock(hdev); @@ -2784,6 +2784,9 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) hci_enable_advertising(hdev); } + /* Inform sockets conn is gone before we delete it */ + hci_disconn_cfm(conn, HCI_ERROR_UNSPECIFIED); + goto done; } @@ -2804,8 +2807,8 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; default: @@ -3423,8 +3426,8 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data, case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); hci_update_passive_scan(hdev); break; @@ -5962,7 +5965,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, conn->dst_type); if (params) { - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8561616abbe5..4d1e32bb6a9c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2160,15 +2160,23 @@ static int hci_le_del_accept_list_sync(struct hci_dev *hdev, return 0; } +struct conn_params { + bdaddr_t addr; + u8 addr_type; + hci_conn_flags_t flags; + u8 privacy_mode; +}; + /* Adds connection to resolve list if needed. * Setting params to NULL programs local hdev->irk */ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_add_to_resolv_list cp; struct smp_irk *irk; struct bdaddr_list_with_irk *entry; + struct hci_conn_params *p; if (!use_ll_privacy(hdev)) return 0; @@ -2203,6 +2211,16 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, /* Default privacy mode is always Network */ params->privacy_mode = HCI_NETWORK_PRIVACY; + rcu_read_lock(); + p = hci_pend_le_action_lookup(&hdev->pend_le_conns, + ¶ms->addr, params->addr_type); + if (!p) + p = hci_pend_le_action_lookup(&hdev->pend_le_reports, + ¶ms->addr, params->addr_type); + if (p) + WRITE_ONCE(p->privacy_mode, HCI_NETWORK_PRIVACY); + rcu_read_unlock(); + done: if (hci_dev_test_flag(hdev, HCI_PRIVACY)) memcpy(cp.local_irk, hdev->irk, 16); @@ -2215,7 +2233,7 @@ done: /* Set Device Privacy Mode. */ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_set_privacy_mode cp; struct smp_irk *irk; @@ -2240,6 +2258,8 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, bacpy(&cp.bdaddr, &irk->bdaddr); cp.mode = HCI_DEVICE_PRIVACY; + /* Note: params->privacy_mode is not updated since it is a copy */ + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_PRIVACY_MODE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } @@ -2249,7 +2269,7 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, * properly set the privacy mode. */ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params, + struct conn_params *params, u8 *num_entries) { struct hci_cp_le_add_to_accept_list cp; @@ -2447,6 +2467,52 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, return __hci_cmd_sync_sk(hdev, opcode, 0, NULL, 0, HCI_CMD_TIMEOUT, sk); } +static struct conn_params *conn_params_copy(struct list_head *list, size_t *n) +{ + struct hci_conn_params *params; + struct conn_params *p; + size_t i; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) + ++i; + *n = i; + + rcu_read_unlock(); + + p = kvcalloc(*n, sizeof(struct conn_params), GFP_KERNEL); + if (!p) + return NULL; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) { + /* Racing adds are handled in next scan update */ + if (i >= *n) + break; + + /* No hdev->lock, but: addr, addr_type are immutable. + * privacy_mode is only written by us or in + * hci_cc_le_set_privacy_mode that we wait for. + * We should be idempotent so MGMT updating flags + * while we are processing is OK. + */ + bacpy(&p[i].addr, ¶ms->addr); + p[i].addr_type = params->addr_type; + p[i].flags = READ_ONCE(params->flags); + p[i].privacy_mode = READ_ONCE(params->privacy_mode); + ++i; + } + + rcu_read_unlock(); + + *n = i; + return p; +} + /* Device must not be scanning when updating the accept list. * * Update is done using the following sequence: @@ -2466,11 +2532,12 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, */ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) { - struct hci_conn_params *params; + struct conn_params *params; struct bdaddr_list *b, *t; u8 num_entries = 0; bool pend_conn, pend_report; u8 filter_policy; + size_t i, n; int err; /* Pause advertising if resolving list can be used as controllers @@ -2504,6 +2571,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) if (hci_conn_hash_lookup_le(hdev, &b->bdaddr, b->bdaddr_type)) continue; + /* Pointers not dereferenced, no locks needed */ pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -2532,23 +2600,50 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) * available accept list entries in the controller, then * just abort and return filer policy value to not use the * accept list. + * + * The list and params may be mutated while we wait for events, + * so make a copy and iterate it. */ - list_for_each_entry(params, &hdev->pend_le_conns, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_conns, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* After adding all new pending connections, walk through * the list of pending reports and also add these to the * accept list if there is still space. Abort if space runs out. */ - list_for_each_entry(params, &hdev->pend_le_reports, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_reports, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* Use the allowlist unless the following conditions are all true: * - We are not currently suspending * - There are 1 or more ADV monitors registered and it's not offloaded @@ -4837,12 +4932,12 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) struct hci_conn_params *p; list_for_each_entry(p, &hdev->le_conn_params, list) { + hci_pend_le_list_del_init(p); if (p->conn) { hci_conn_drop(p->conn); hci_conn_put(p->conn); p->conn = NULL; } - list_del_init(&p->action); } BT_DBG("All LE pending actions cleared"); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 0e6cc57b3911..505d62247268 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -123,8 +123,11 @@ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) { struct iso_conn *conn = hcon->iso_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) @@ -300,14 +303,13 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -321,7 +323,6 @@ static int iso_connect_bis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -389,14 +390,13 @@ static int iso_connect_cis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -413,7 +413,6 @@ static int iso_connect_cis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -1072,8 +1071,8 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct iso_conn *conn = iso_pi(sk)->conn; struct sk_buff *skb, **frag; + size_t mtu; int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -1085,11 +1084,18 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - if (sk->sk_state != BT_CONNECTED) + lock_sock(sk); + + if (sk->sk_state != BT_CONNECTED) { + release_sock(sk); return -ENOTCONN; + } + + mtu = iso_pi(sk)->conn->hcon->hdev->iso_mtu; + + release_sock(sk); - skb = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - HCI_ISO_DATA_HDR_SIZE, 0); + skb = bt_skb_sendmsg(sk, msg, len, mtu, HCI_ISO_DATA_HDR_SIZE, 0); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -1102,8 +1108,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, while (len) { struct sk_buff *tmp; - tmp = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - 0, 0); + tmp = bt_skb_sendmsg(sk, msg, len, mtu, 0, 0); if (IS_ERR(tmp)) { kfree_skb(skb); return PTR_ERR(tmp); @@ -1158,15 +1163,19 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, BT_DBG("sk %p", sk); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - lock_sock(sk); iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; case BT_CONNECT: + release_sock(sk); return iso_connect_cis(sk); + default: + release_sock(sk); + break; } } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f7b2d0971f24..d4498037fadc 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1297,15 +1297,15 @@ static void restart_le_actions(struct hci_dev *hdev) /* Needed for AUTO_OFF case where might not "really" * have been powered off. */ - list_del_init(&p->action); + hci_pend_le_list_del_init(p); switch (p->auto_connect) { case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(&p->action, &hdev->pend_le_conns); + hci_pend_le_list_add(p, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(&p->action, &hdev->pend_le_reports); + hci_pend_le_list_add(p, &hdev->pend_le_reports); break; default: break; @@ -5169,7 +5169,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - params->flags = current_flags; + WRITE_ONCE(params->flags, current_flags); status = MGMT_STATUS_SUCCESS; /* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY @@ -7285,7 +7285,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - memcpy(&rp.addr, &cp->addr.bdaddr, sizeof(rp.addr)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); status = mgmt_status(err); if (status == MGMT_STATUS_SUCCESS) { @@ -7580,7 +7580,7 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, if (params->auto_connect == auto_connect) return 0; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (auto_connect) { case HCI_AUTO_CONN_DISABLED: @@ -7589,18 +7589,18 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, * connect to device, keep connecting. */ if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); else - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; } @@ -7823,9 +7823,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - list_del(¶ms->action); - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type); } else { @@ -7856,9 +7854,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, p->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } - list_del(&p->action); - list_del(&p->list); - kfree(p); + hci_conn_params_free(p); } bt_dev_dbg(hdev, "All LE connection parameters were removed"); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index cd1a27ac555d..7762604ddfc0 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -126,8 +126,11 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) struct hci_dev *hdev = hcon->hdev; struct sco_conn *conn = hcon->sco_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) @@ -268,21 +271,21 @@ static int sco_connect(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); - conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); - return -ENOMEM; + err = -ENOMEM; + goto unlock; } - err = sco_chan_add(conn, sk, NULL); - if (err) - return err; - lock_sock(sk); + err = sco_chan_add(conn, sk, NULL); + if (err) { + release_sock(sk); + goto unlock; + } + /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); @@ -296,8 +299,6 @@ static int sco_connect(struct sock *sk) release_sock(sk); - return err; - unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); diff --git a/net/can/bcm.c b/net/can/bcm.c index 9ba35685b043..9168114fc87f 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1526,6 +1526,12 @@ static int bcm_release(struct socket *sock) lock_sock(sk); +#if IS_ENABLED(CONFIG_PROC_FS) + /* remove procfs entry */ + if (net->can.bcmproc_dir && bo->bcm_proc_read) + remove_proc_entry(bo->procname, net->can.bcmproc_dir); +#endif /* CONFIG_PROC_FS */ + list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); @@ -1561,12 +1567,6 @@ static int bcm_release(struct socket *sock) list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); -#if IS_ENABLED(CONFIG_PROC_FS) - /* remove procfs entry */ - if (net->can.bcmproc_dir && bo->bcm_proc_read) - remove_proc_entry(bo->procname, net->can.bcmproc_dir); -#endif /* CONFIG_PROC_FS */ - /* remove device reference */ if (bo->bound) { bo->bound = 0; diff --git a/net/can/raw.c b/net/can/raw.c index 15c79b079184..2302e4882967 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,7 +278,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return; switch (msg) { @@ -292,6 +293,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk); @@ -337,6 +339,7 @@ static int raw_init(struct sock *sk) ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -385,19 +388,13 @@ static int raw_release(struct socket *sock) lock_sock(sk); + rtnl_lock(); /* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } if (ro->count > 1) @@ -405,8 +402,10 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); + rtnl_unlock(); sock_orphan(sk); sock->sk = NULL; @@ -422,6 +421,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,14 +431,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL; + rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -467,26 +466,20 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } ro->ifindex = ifindex; ro->bound = 1; + ro->dev = dev; } out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -553,9 +546,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -596,7 +589,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -614,9 +606,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -640,7 +632,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - dev_put(dev); release_sock(sk); rtnl_unlock(); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index ba06ed42e428..2be2d4922557 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1132,7 +1132,7 @@ static int esp_init_authenc(struct xfrm_state *x, err = crypto_aead_setkey(aead, key, keylen); free_key: - kfree(key); + kfree_sensitive(key); error: return err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0cc19cfbb673..aeebe8816689 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1019,7 +1019,7 @@ static void reqsk_timer_handler(struct timer_list *t) icsk = inet_csk(sk_listener); net = sock_net(sk_listener); - max_syn_ack_retries = icsk->icsk_syn_retries ? : + max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e7391bf310a7..0819d6001b9a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -650,20 +650,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_hashed(osk); - if (ret) { - /* Before deleting the node, we insert a new one to make - * sure that the look-up-sk process would not miss either - * of them and that at least one node would exist in ehash - * table all the time. Otherwise there's a tiny chance - * that lookup process could find nothing in ehash table. - */ - __sk_nulls_add_node_tail_rcu(sk, list); - sk_nulls_del_node_init_rcu(osk); - } - goto unlock; - } - if (found_dup_sk) { + ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -672,7 +660,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); -unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 40052414c7c7..2c1b245dba8e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -88,10 +88,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_tail_rcu(&tw->tw_node, list); + hlist_nulls_add_head_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -144,7 +144,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_tail_rcu(tw, &ehead->chain); + inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 81a1cce1a7d1..22a26d1d29a0 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -548,7 +548,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto err_free_skb; truncate = true; } @@ -689,7 +690,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto free_skb; truncate = true; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e03e08745308..8ed52e1e3c99 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3291,7 +3291,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - inet_csk(sk)->icsk_syn_retries = val; + WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } @@ -3300,7 +3300,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); - inet_csk(sk)->icsk_user_timeout = val; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3312,7 +3312,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; - tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); @@ -3344,7 +3345,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_intvl = val * HZ; + WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } @@ -3356,7 +3357,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3558,19 +3560,19 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else - tp->keepalive_intvl = val * HZ; + WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - icsk->icsk_syn_retries = val; + WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: @@ -3583,18 +3585,18 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -3618,7 +3620,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 0) err = -EINVAL; else - icsk->icsk_user_timeout = val; + WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: @@ -3656,13 +3658,13 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp_raw(); + WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -3674,7 +3676,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -3991,17 +3993,18 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : + val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -4138,11 +4141,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_USER_TIMEOUT: - val = icsk->icsk_user_timeout; + val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: @@ -4154,14 +4157,14 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + tp->tsoffset; + val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 45cc7f1ca296..85e4953f1182 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -296,6 +296,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; + int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying @@ -308,10 +309,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq->max_qlen == 0) + max_qlen = READ_ONCE(fastopenq->max_qlen); + if (max_qlen == 0) return false; - if (fastopenq->qlen >= fastopenq->max_qlen) { + if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd365de4d5ff..069642014636 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -307,8 +307,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port)); - tp->tsoffset = secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr); + WRITE_ONCE(tp->tsoffset, + secure_tcp_ts_off(net, inet->inet_saddr, + inet->inet_daddr)); } inet->inet_id = get_random_u16(); @@ -988,11 +989,12 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, + READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos, tcp_rsk(req)->txhash); + ip_hdr(skb)->tos, + READ_ONCE(tcp_rsk(req)->txhash)); } /* diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 04fc328727e6..c8f2aa003387 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -528,7 +528,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->lsndtime = tcp_jiffies32; - newsk->sk_txhash = treq->txhash; + newsk->sk_txhash = READ_ONCE(treq->txhash); newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); @@ -555,7 +555,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -619,7 +619,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = req->ts_recent; + tmp_opt.ts_recent = READ_ONCE(req->ts_recent); if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; /* We do not store true stamp, but it is not required, @@ -758,8 +758,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ + /* TODO: We probably should defer ts_recent change once + * we take ownership of @req. + */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - req->ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2cb39b6dad02..51d8638d4b4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -878,7 +878,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; - opts->tsecr = req->ts_recent; + opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { @@ -3660,7 +3660,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif - skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, @@ -4210,7 +4210,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) - tcp_rsk(req)->txhash = net_tx_rndhash(); + WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 75aa4de5b731..f402946da344 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -274,13 +274,20 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __sum16 check; __be16 newlen; - if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) - return __udp_gso_segment_list(gso_skb, features, is_ipv6); - mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), + mss); + return NULL; + } + + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) + return __udp_gso_segment_list(gso_skb, features, is_ipv6); + skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ @@ -388,8 +395,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index da80974ad23a..070d87abf7c0 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -955,7 +955,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto tx_err; truncate = true; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 40dd92a2f480..4714eb695913 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1126,10 +1126,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, sk->sk_bound_dev_if, + READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, - tcp_rsk(req)->txhash); + READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ad3b8726873e..09fa7a42cb93 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -43,8 +43,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 57c35c960b2c..9b06c380866b 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -402,7 +402,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) memcpy(laddr.mac, addr->sllc_mac, IFHWADDRLEN); laddr.lsap = addr->sllc_sap; rc = -EADDRINUSE; /* mac + sap clash. */ - ask = llc_lookup_established(sap, &daddr, &laddr); + ask = llc_lookup_established(sap, &daddr, &laddr, &init_net); if (ask) { sock_put(ask); goto out_put; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 912aa9bd5e29..d037009ee10f 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -453,11 +453,13 @@ static int llc_exec_conn_trans_actions(struct sock *sk, static inline bool llc_estab_match(const struct llc_sap *sap, const struct llc_addr *daddr, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return llc->laddr.lsap == laddr->lsap && + return net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && llc->daddr.lsap == daddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac) && ether_addr_equal(llc->daddr.mac, daddr->mac); @@ -468,6 +470,7 @@ static inline bool llc_estab_match(const struct llc_sap *sap, * @sap: SAP * @daddr: address of remote LLC (MAC + SAP) * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection using the remote * mac, remote sap, local mac, and local sap. Returns pointer for @@ -476,7 +479,8 @@ static inline bool llc_estab_match(const struct llc_sap *sap, */ static struct sock *__llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -486,12 +490,12 @@ static struct sock *__llc_lookup_established(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_estab_match(sap, daddr, laddr, rc)) { + if (llc_estab_match(sap, daddr, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_estab_match(sap, daddr, laddr, rc))) { + !llc_estab_match(sap, daddr, laddr, rc, net))) { sock_put(rc); continue; } @@ -513,29 +517,33 @@ found: struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *sk; local_bh_disable(); - sk = __llc_lookup_established(sap, daddr, laddr); + sk = __llc_lookup_established(sap, daddr, laddr, net); local_bh_enable(); return sk; } static inline bool llc_listener_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && + return net_eq(sock_net(sk), net) && + sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } static struct sock *__llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -545,12 +553,12 @@ static struct sock *__llc_lookup_listener(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_listener_match(sap, laddr, rc)) { + if (llc_listener_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_listener_match(sap, laddr, rc))) { + !llc_listener_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -574,6 +582,7 @@ found: * llc_lookup_listener - Finds listener for local MAC + SAP * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection listening on * local mac, and local sap. Returns pointer for parent socket found, @@ -581,24 +590,26 @@ found: * Caller has to make sure local_bh is disabled. */ static struct sock *llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { + struct sock *rc = __llc_lookup_listener(sap, laddr, net); static struct llc_addr null_addr; - struct sock *rc = __llc_lookup_listener(sap, laddr); if (!rc) - rc = __llc_lookup_listener(sap, &null_addr); + rc = __llc_lookup_listener(sap, &null_addr, net); return rc; } static struct sock *__llc_lookup(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { - struct sock *sk = __llc_lookup_established(sap, daddr, laddr); + struct sock *sk = __llc_lookup_established(sap, daddr, laddr, net); - return sk ? : llc_lookup_listener(sap, laddr); + return sk ? : llc_lookup_listener(sap, laddr, net); } /** @@ -776,7 +787,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) llc_pdu_decode_da(skb, daddr.mac); llc_pdu_decode_dsap(skb, &daddr.lsap); - sk = __llc_lookup(sap, &saddr, &daddr); + sk = __llc_lookup(sap, &saddr, &daddr, dev_net(skb->dev)); if (!sk) goto drop; diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index dde9bf08a593..58a5f419adc6 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -92,7 +92,7 @@ int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, u8 dsap) daddr.lsap = dsap; memcpy(daddr.mac, dmac, sizeof(daddr.mac)); memcpy(laddr.mac, lmac, sizeof(laddr.mac)); - existing = llc_lookup_established(llc->sap, &daddr, &laddr); + existing = llc_lookup_established(llc->sap, &daddr, &laddr, sock_net(sk)); if (existing) { if (existing->sk_state == TCP_ESTABLISHED) { sk = existing; diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index c309b72a5877..7cac441862e2 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -163,9 +163,6 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 6805ce43a055..116c0e479183 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -294,25 +294,29 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, static inline bool llc_dgram_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && - llc->laddr.lsap == laddr->lsap && - ether_addr_equal(llc->laddr.mac, laddr->mac); + net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && + ether_addr_equal(llc->laddr.mac, laddr->mac); } /** * llc_lookup_dgram - Finds dgram socket for the local sap/mac * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search socket list of the SAP and finds connection using the local * mac, and local sap. Returns pointer for socket found, %NULL otherwise. */ static struct sock *llc_lookup_dgram(struct llc_sap *sap, - const struct llc_addr *laddr) + const struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -322,12 +326,12 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap, rcu_read_lock_bh(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_dgram_match(sap, laddr, rc)) { + if (llc_dgram_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_dgram_match(sap, laddr, rc))) { + !llc_dgram_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -429,7 +433,7 @@ void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) llc_sap_mcast(sap, &laddr, skb); kfree_skb(skb); } else { - struct sock *sk = llc_lookup_dgram(sap, &laddr); + struct sock *sk = llc_lookup_dgram(sap, &laddr, dev_net(skb->dev)); if (sk) { llc_sap_rcv(sap, skb, sk); sock_put(sk); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 237f739da3ca..b9a4d3fd1d34 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3685,8 +3685,6 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } - - cond_resched(); } return 0; @@ -3710,6 +3708,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) err = nft_chain_validate(&ctx, chain); if (err < 0) return err; + + cond_resched(); } return 0; @@ -4087,6 +4087,8 @@ 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)) + continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); @@ -10517,6 +10519,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; + + /* zero padding hole for memcmp */ + memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { @@ -10799,6 +10804,9 @@ 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)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index db526cb7a485..49915a2a58eb 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1929,7 +1929,11 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, int i, start, rules_fx; match_start = data; - match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + + if (nft_set_ext_exists(&e->ext, NFT_SET_EXT_KEY_END)) + match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + else + match_end = data; start = first_rule; rules_fx = rules_f0; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 466c26df853a..382c7a71f81f 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -406,56 +406,6 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, return 0; } -static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, unsigned long base, - struct nlattr **tb, struct nlattr *est, u32 flags, - struct netlink_ext_ack *extack) -{ - bool is_bpf, is_ebpf, have_exts = false; - u32 gen_flags = 0; - int ret; - - is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; - is_ebpf = tb[TCA_BPF_FD]; - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) - return -EINVAL; - - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, flags, - extack); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_FLAGS]) { - u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); - - if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) - return -EINVAL; - - have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; - } - if (tb[TCA_BPF_FLAGS_GEN]) { - gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); - if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || - !tc_flags_valid(gen_flags)) - return -EINVAL; - } - - prog->exts_integrated = have_exts; - prog->gen_flags = gen_flags; - - ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_CLASSID]) { - prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); - tcf_bind_filter(tp, &prog->res, base); - } - - return 0; -} - static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -463,9 +413,12 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); + bool is_bpf, is_ebpf, have_exts = false; struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; + bool bound_to_filter = false; struct cls_bpf_prog *prog; + u32 gen_flags = 0; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -504,11 +457,51 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, goto errout; prog->handle = handle; - ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], flags, - extack); + is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; + is_ebpf = tb[TCA_BPF_FD]; + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + ret = -EINVAL; + goto errout_idr; + } + + ret = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &prog->exts, + flags, extack); + if (ret < 0) + goto errout_idr; + + if (tb[TCA_BPF_FLAGS]) { + u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); + + if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { + ret = -EINVAL; + goto errout_idr; + } + + have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; + } + if (tb[TCA_BPF_FLAGS_GEN]) { + gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); + if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || + !tc_flags_valid(gen_flags)) { + ret = -EINVAL; + goto errout_idr; + } + } + + prog->exts_integrated = have_exts; + prog->gen_flags = gen_flags; + + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) goto errout_idr; + if (tb[TCA_BPF_CLASSID]) { + prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + tcf_bind_filter(tp, &prog->res, base); + bound_to_filter = true; + } + ret = cls_bpf_offload(tp, prog, oldprog, extack); if (ret) goto errout_parms; @@ -530,6 +523,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, return 0; errout_parms: + if (bound_to_filter) + tcf_unbind_filter(tp, &prog->res); cls_bpf_free_parms(prog); errout_idr: if (!oldprog) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f2b0bc4142fe..8da9d039d964 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2173,53 +2173,6 @@ static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask) return mask->meta.l2_miss; } -static int fl_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_fl_filter *f, struct fl_flow_mask *mask, - unsigned long base, struct nlattr **tb, - struct nlattr *est, - struct fl_flow_tmplt *tmplt, - u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &f->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_FLOWER_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_lock(); - tcf_bind_filter(tp, &f->res, base); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_unlock(); - } - - err = fl_set_key(net, tb, &f->key, &mask->key, extack); - if (err) - return err; - - fl_mask_update_range(mask); - fl_set_masked_key(&f->mkey, &f->key, mask); - - if (!fl_mask_fits_tmplt(tmplt, mask)) { - NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); - return -EINVAL; - } - - /* Enable tc skb extension if filter matches on data extracted from - * this extension. - */ - if (fl_needs_tc_skb_ext(&mask->key)) { - f->needs_tc_skb_ext = 1; - tc_skb_ext_tc_enable(); - } - - return 0; -} - static int fl_ht_insert_unique(struct cls_fl_filter *fnew, struct cls_fl_filter *fold, bool *in_ht) @@ -2251,6 +2204,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_head *head = fl_head_dereference(tp); bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); struct cls_fl_filter *fold = *arg; + bool bound_to_filter = false; struct cls_fl_filter *fnew; struct fl_flow_mask *mask; struct nlattr **tb; @@ -2335,15 +2289,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout_idr; - err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], - tp->chain->tmplt_priv, flags, fnew->flags, - extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &fnew->exts, flags, fnew->flags, + extack); + if (err < 0) goto errout_idr; + if (tb[TCA_FLOWER_CLASSID]) { + fnew->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_bind_filter(tp, &fnew->res, base); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + bound_to_filter = true; + } + + err = fl_set_key(net, tb, &fnew->key, &mask->key, extack); + if (err) + goto unbind_filter; + + fl_mask_update_range(mask); + fl_set_masked_key(&fnew->mkey, &fnew->key, mask); + + if (!fl_mask_fits_tmplt(tp->chain->tmplt_priv, mask)) { + NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); + err = -EINVAL; + goto unbind_filter; + } + + /* Enable tc skb extension if filter matches on data extracted from + * this extension. + */ + if (fl_needs_tc_skb_ext(&mask->key)) { + fnew->needs_tc_skb_ext = 1; + tc_skb_ext_tc_enable(); + } + err = fl_check_assign_mask(head, fnew, fold, mask); if (err) - goto errout_idr; + goto unbind_filter; err = fl_ht_insert_unique(fnew, fold, &in_ht); if (err) @@ -2434,6 +2419,16 @@ errout_hw: fnew->mask->filter_ht_params); errout_mask: fl_mask_put(head, fnew->mask); + +unbind_filter: + if (bound_to_filter) { + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_unbind_filter(tp, &fnew->res); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + } + errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index fa3bbd187eb9..c4ed11df6254 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -159,26 +159,6 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; -static int mall_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long base, struct nlattr **tb, - struct nlattr *est, u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &head->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_MATCHALL_CLASSID]) { - head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); - tcf_bind_filter(tp, &head->res, base); - } - return 0; -} - static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -187,6 +167,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; + bool bound_to_filter = false; struct cls_mall_head *new; u32 userflags = 0; int err; @@ -226,11 +207,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, goto err_alloc_percpu; } - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], - flags, new->flags, extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &new->exts, flags, new->flags, extack); + if (err < 0) goto err_set_parms; + if (tb[TCA_MATCHALL_CLASSID]) { + new->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); + tcf_bind_filter(tp, &new->res, base); + bound_to_filter = true; + } + if (!tc_skip_hw(new->flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long)new, extack); @@ -246,6 +233,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, return 0; err_replace_hw_filter: + if (bound_to_filter) + tcf_unbind_filter(tp, &new->res); err_set_parms: free_percpu(new->pf); err_alloc_percpu: diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d15d50de7980..5abf31e432ca 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -712,8 +712,23 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; +static void u32_unbind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) + tcf_unbind_filter(tp, &n->res); +} + +static void u32_bind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + unsigned long base, struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) { + n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); + tcf_bind_filter(tp, &n->res, base); + } +} + static int u32_set_parms(struct net *net, struct tcf_proto *tp, - unsigned long base, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) @@ -760,10 +775,6 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, if (ht_old) ht_old->refcnt--; } - if (tb[TCA_U32_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } if (ifindex >= 0) n->ifindex = ifindex; @@ -903,17 +914,27 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOMEM; - err = u32_set_parms(net, tp, base, new, tb, - tca[TCA_RATE], flags, new->flags, - extack); + err = u32_set_parms(net, tp, new, tb, tca[TCA_RATE], + flags, new->flags, extack); if (err) { __u32_destroy_key(new); return err; } + u32_bind_filter(tp, new, base, tb); + err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { + u32_unbind_filter(tp, new, tb); + + if (tb[TCA_U32_LINK]) { + struct tc_u_hnode *ht_old; + + ht_old = rtnl_dereference(n->ht_down); + if (ht_old) + ht_old->refcnt++; + } __u32_destroy_key(new); return err; } @@ -1074,15 +1095,18 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], + err = u32_set_parms(net, tp, n, tb, tca[TCA_RATE], flags, n->flags, extack); + + u32_bind_filter(tp, n, base, tb); + if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; err = u32_replace_hw_knode(tp, n, flags, extack); if (err) - goto errhw; + goto errunbind; if (!tc_in_hw(n->flags)) n->flags |= TCA_CLS_FLAGS_NOT_IN_HW; @@ -1100,7 +1124,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return 0; } -errhw: +errunbind: + u32_unbind_filter(tp, n, tb); + #ifdef CONFIG_CLS_U32_MARK free_percpu(n->pcpu_success); #endif |