diff options
Diffstat (limited to 'net')
49 files changed, 666 insertions, 326 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 640b951bf40a..f75ef12f18f7 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1083,8 +1083,28 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->parent) { struct hci_link *link, *t; - list_for_each_entry_safe(link, t, &conn->link_list, list) - hci_conn_unlink(link->conn); + list_for_each_entry_safe(link, t, &conn->link_list, list) { + struct hci_conn *child = link->conn; + + hci_conn_unlink(child); + + /* If hdev is down it means + * hci_dev_close_sync/hci_conn_hash_flush is in progress + * and links don't need to be cleanup as all connections + * would be cleanup. + */ + if (!test_bit(HCI_UP, &hdev->flags)) + continue; + + /* Due to race, SCO connection might be not established + * yet at this point. Delete it now, otherwise it is + * possible for it to be stuck and can't be deleted. + */ + if ((child->type == SCO_LINK || + child->type == ESCO_LINK) && + child->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(child); + } return; } @@ -1092,35 +1112,30 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->link) return; - hci_conn_put(conn->parent); - conn->parent = NULL; - list_del_rcu(&conn->link->list); synchronize_rcu(); + hci_conn_drop(conn->parent); + hci_conn_put(conn->parent); + conn->parent = NULL; + kfree(conn->link); conn->link = NULL; - - /* Due to race, SCO connection might be not established - * yet at this point. Delete it now, otherwise it is - * possible for it to be stuck and can't be deleted. - */ - if (conn->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(conn); } -int hci_conn_del(struct hci_conn *conn) +void hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle); + hci_conn_unlink(conn); + cancel_delayed_work_sync(&conn->disc_work); cancel_delayed_work_sync(&conn->auto_accept_work); cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - hci_conn_unlink(conn); /* Unacked frames */ hdev->acl_cnt += conn->sent; } else if (conn->type == LE_LINK) { @@ -1131,13 +1146,6 @@ int hci_conn_del(struct hci_conn *conn) else hdev->acl_cnt += conn->sent; } else { - struct hci_conn *acl = conn->parent; - - if (acl) { - hci_conn_unlink(conn); - hci_conn_drop(acl); - } - /* Unacked ISO frames */ if (conn->type == ISO_LINK) { if (hdev->iso_pkts) @@ -1160,8 +1168,6 @@ int hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); - - return 0; } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -2462,22 +2468,21 @@ timer: /* Drop all connection on the device */ void hci_conn_hash_flush(struct hci_dev *hdev) { - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c, *n; + struct list_head *head = &hdev->conn_hash.list; + struct hci_conn *conn; BT_DBG("hdev %s", hdev->name); - list_for_each_entry_safe(c, n, &h->list, list) { - c->state = BT_CLOSED; - - hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); - - /* Unlink before deleting otherwise it is possible that - * hci_conn_del removes the link which may cause the list to - * contain items already freed. - */ - hci_conn_unlink(c); - hci_conn_del(c); + /* We should not traverse the list here, because hci_conn_del + * can remove extra links, which may cause the list traversal + * to hit items that have already been released. + */ + while ((conn = list_first_entry_or_null(head, + struct hci_conn, + list)) != NULL) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); + hci_conn_del(conn); } } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index e212e9d7edcb..a3e12a61d456 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -134,6 +134,29 @@ EXPORT_SYMBOL(page_pool_ethtool_stats_get); #define recycle_stat_add(pool, __stat, val) #endif +static bool page_pool_producer_lock(struct page_pool *pool) + __acquires(&pool->ring.producer_lock) +{ + bool in_softirq = in_softirq(); + + if (in_softirq) + spin_lock(&pool->ring.producer_lock); + else + spin_lock_bh(&pool->ring.producer_lock); + + return in_softirq; +} + +static void page_pool_producer_unlock(struct page_pool *pool, + bool in_softirq) + __releases(&pool->ring.producer_lock) +{ + if (in_softirq) + spin_unlock(&pool->ring.producer_lock); + else + spin_unlock_bh(&pool->ring.producer_lock); +} + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -617,6 +640,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) { int i, bulk_len = 0; + bool in_softirq; for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); @@ -635,7 +659,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, return; /* Bulk producer into ptr_ring page_pool cache */ - page_pool_ring_lock(pool); + in_softirq = page_pool_producer_lock(pool); for (i = 0; i < bulk_len; i++) { if (__ptr_ring_produce(&pool->ring, data[i])) { /* ring full */ @@ -644,7 +668,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, } } recycle_stat_add(pool, ring, i); - page_pool_ring_unlock(pool); + page_pool_producer_unlock(pool, in_softirq); /* Hopefully all pages was return into ptr_ring */ if (likely(i == bulk_len)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 653901a1bf75..41de3a2f29e1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2385,6 +2385,37 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_BROADCAST] && nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) return -EINVAL; + + if (tb[IFLA_GSO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_MAX_SEGS] && + (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS || + nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) { + NL_SET_ERR_MSG(extack, "too big gso_max_segs"); + return -EINVAL; + } + + if (tb[IFLA_GRO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GRO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size"); + return -EINVAL; + } } if (tb[IFLA_AF_SPEC]) { @@ -2858,11 +2889,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_size ^ max_size) { netif_set_gso_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -2872,11 +2898,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SEGS]) { u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]); - if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_segs ^ max_segs) { netif_set_gso_max_segs(dev, max_segs); status |= DO_SETLINK_MODIFIED; @@ -2895,11 +2916,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_IPV4_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_ipv4_max_size ^ max_size) { netif_set_gso_ipv4_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -3285,6 +3301,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, struct net_device *dev; unsigned int num_tx_queues = 1; unsigned int num_rx_queues = 1; + int err; if (tb[IFLA_NUM_TX_QUEUES]) num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); @@ -3320,13 +3337,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, if (!dev) return ERR_PTR(-ENOMEM); + err = validate_linkmsg(dev, tb, extack); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + dev_net_set(dev, net); dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); - int err; err = dev_validate_mtu(dev, mtu, extack); if (err) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 515ec5cdc79c..cea28d30abb5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5224,8 +5224,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, } else { skb = skb_clone(orig_skb, GFP_ATOMIC); - if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) + if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { + kfree_skb(skb); return; + } } if (!skb) return; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index f81883759d38..a9060e1f0e43 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -481,8 +481,6 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, msg_rx = sk_psock_peek_msg(psock); } out: - if (psock->work_state.skb && copied > 0) - schedule_work(&psock->work); return copied; } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); @@ -624,42 +622,33 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, - struct sk_buff *skb, int len, int off) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - state->skb = skb; state->len = len; state->off = off; - } else { - sock_drop(psock->sk, skb); } spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_backlog(struct work_struct *work) { - struct sk_psock *psock = container_of(work, struct sk_psock, work); + struct delayed_work *dwork = to_delayed_work(work); + struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; + u32 len = 0, off = 0; bool ingress; - u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (unlikely(state->skb)) { - spin_lock_bh(&psock->ingress_lock); - skb = state->skb; + if (unlikely(state->len)) { len = state->len; off = state->off; - state->skb = NULL; - spin_unlock_bh(&psock->ingress_lock); } - if (skb) - goto start; - while ((skb = skb_dequeue(&psock->ingress_skb))) { + while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; if (skb_bpf_strparser(skb)) { @@ -668,7 +657,6 @@ static void sk_psock_backlog(struct work_struct *work) off = stm->offset; len = stm->full_len; } -start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { @@ -678,22 +666,28 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - sk_psock_skb_state(psock, state, skb, - len, off); + sk_psock_skb_state(psock, state, len, off); + + /* Delay slightly to prioritize any + * other work that might be here. + */ + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_delayed_work(&psock->work, 1); goto end; } /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - sock_drop(psock->sk, skb); goto end; } off += ret; len -= ret; } while (len); - if (!ingress) + skb = skb_dequeue(&psock->ingress_skb); + if (!ingress) { kfree_skb(skb); + } } end: mutex_unlock(&psock->work_mutex); @@ -734,7 +728,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); - INIT_WORK(&psock->work, sk_psock_backlog); + INIT_DELAYED_WORK(&psock->work, sk_psock_backlog); mutex_init(&psock->work_mutex); INIT_LIST_HEAD(&psock->ingress_msg); spin_lock_init(&psock->ingress_lock); @@ -786,11 +780,6 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } - kfree_skb(psock->work_state.skb); - /* We null the skb here to ensure that calls to sk_psock_backlog - * do not pick up the free'd skb. - */ - psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } @@ -809,7 +798,6 @@ void sk_psock_stop(struct sk_psock *psock) spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); - __sk_psock_zap_ingress(psock); spin_unlock_bh(&psock->ingress_lock); } @@ -823,7 +811,8 @@ static void sk_psock_destroy(struct work_struct *work) sk_psock_done_strp(psock); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); + __sk_psock_zap_ingress(psock); mutex_destroy(&psock->work_mutex); psock_progs_drop(&psock->progs); @@ -938,7 +927,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) } skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); + schedule_delayed_work(&psock_other->work, 0); spin_unlock_bh(&psock_other->ingress_lock); return 0; } @@ -990,10 +979,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || - !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - skb_bpf_redirect_clear(skb); + !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) goto out_free; - } skb_bpf_set_ingress(skb); @@ -1018,22 +1005,23 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); err = 0; } spin_unlock_bh(&psock->ingress_lock); - if (err < 0) { - skb_bpf_redirect_clear(skb); + if (err < 0) goto out_free; - } } break; case __SK_REDIRECT: + tcp_eat_skb(psock->sk, skb); err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: + skb_bpf_redirect_clear(skb); + tcp_eat_skb(psock->sk, skb); sock_drop(psock->sk, skb); } @@ -1049,7 +1037,7 @@ static void sk_psock_write_space(struct sock *sk) psock = sk_psock(sk); if (likely(psock)) { if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); write_space = psock->saved_write_space; } rcu_read_unlock(); @@ -1078,8 +1066,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); - if (ret == SK_PASS) - skb_bpf_set_strparser(skb); + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } @@ -1183,12 +1170,11 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) int ret = __SK_DROP; int len = skb->len; - skb_get(skb); - rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; + tcp_eat_skb(sk, skb); sock_drop(sk, skb); goto out; } @@ -1212,12 +1198,21 @@ out: static void sk_psock_verdict_data_ready(struct sock *sk) { struct socket *sock = sk->sk_socket; + int copied; trace_sk_data_ready(sk); if (unlikely(!sock || !sock->ops || !sock->ops->read_skb)) return; - sock->ops->read_skb(sk, sk_psock_verdict_recv); + copied = sock->ops->read_skb(sk, sk_psock_verdict_recv); + if (copied >= 0) { + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + psock->saved_data_ready(sk); + rcu_read_unlock(); + } } void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) diff --git a/net/core/sock.c b/net/core/sock.c index 5440e67bcfe3..24f2761bdb1d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2381,7 +2381,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk_is_tcp(sk)) sk->sk_route_caps |= NETIF_F_GSO; @@ -2400,6 +2399,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } } sk->sk_gso_max_segs = max_segs; + sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 7c189c2e2fbf..00afb66cd095 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1644,9 +1644,10 @@ void sock_map_close(struct sock *sk, long timeout) rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); } + /* Make sure we do not recurse. This is a bug. * Leak the socket instead of crashing on a stack overflow. */ diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index e6adc5dec11a..6d37bab35c8f 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -102,7 +102,7 @@ struct handshake_req_alloc_test_param handshake_req_alloc_params[] = { { .desc = "handshake_req_alloc excessive privsize", .proto = &handshake_req_alloc_proto_6, - .gfp = GFP_KERNEL, + .gfp = GFP_KERNEL | __GFP_NOWARN, .expect_success = false, }, { @@ -209,6 +209,7 @@ static void handshake_req_submit_test4(struct kunit *test) { struct handshake_req *req, *result; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -218,9 +219,10 @@ static void handshake_req_submit_test4(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -241,6 +243,7 @@ static void handshake_req_submit_test5(struct kunit *test) struct handshake_req *req; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; int saved, err; @@ -251,9 +254,10 @@ static void handshake_req_submit_test5(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; net = sock_net(sock->sk); hn = handshake_pernet(net); @@ -276,6 +280,7 @@ static void handshake_req_submit_test6(struct kunit *test) { struct handshake_req *req1, *req2; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -287,9 +292,10 @@ static void handshake_req_submit_test6(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; /* Act */ err = handshake_req_submit(sock, req1, GFP_KERNEL); @@ -307,6 +313,7 @@ static void handshake_req_cancel_test1(struct kunit *test) { struct handshake_req *req; struct socket *sock; + struct file *filp; bool result; int err; @@ -318,8 +325,9 @@ static void handshake_req_cancel_test1(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -340,6 +348,7 @@ static void handshake_req_cancel_test2(struct kunit *test) struct handshake_req *req, *next; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; bool result; int err; @@ -352,8 +361,9 @@ static void handshake_req_cancel_test2(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -380,6 +390,7 @@ static void handshake_req_cancel_test3(struct kunit *test) struct handshake_req *req, *next; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; bool result; int err; @@ -392,8 +403,9 @@ static void handshake_req_cancel_test3(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -436,6 +448,7 @@ static void handshake_req_destroy_test1(struct kunit *test) { struct handshake_req *req; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -448,8 +461,9 @@ static void handshake_req_destroy_test1(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); diff --git a/net/handshake/handshake.h b/net/handshake/handshake.h index 4dac965c99df..8aeaadca844f 100644 --- a/net/handshake/handshake.h +++ b/net/handshake/handshake.h @@ -31,6 +31,7 @@ struct handshake_req { struct list_head hr_list; struct rhash_head hr_rhash; unsigned long hr_flags; + struct file *hr_file; const struct handshake_proto *hr_proto; struct sock *hr_sk; void (*hr_odestruct)(struct sock *sk); diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index 35c9c445e0b8..1086653e1fad 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -48,7 +48,7 @@ int handshake_genl_notify(struct net *net, const struct handshake_proto *proto, proto->hp_handler_class)) return -ESRCH; - msg = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + msg = genlmsg_new(GENLMSG_DEFAULT_SIZE, flags); if (!msg) return -ENOMEM; @@ -99,9 +99,6 @@ static int handshake_dup(struct socket *sock) struct file *file; int newfd; - if (!sock->file) - return -EBADF; - file = get_file(sock->file); newfd = get_unused_fd_flags(O_CLOEXEC); if (newfd < 0) { @@ -142,15 +139,16 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) goto out_complete; } err = req->hr_proto->hp_accept(req, info, fd); - if (err) + if (err) { + fput(sock->file); goto out_complete; + } trace_handshake_cmd_accept(net, req, req->hr_sk, fd); return 0; out_complete: handshake_complete(req, -EIO, NULL); - fput(sock->file); out_status: trace_handshake_cmd_accept_err(net, req, NULL, err); return err; @@ -159,8 +157,8 @@ out_status: int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); + struct handshake_req *req = NULL; struct socket *sock = NULL; - struct handshake_req *req; int fd, status, err; if (GENL_REQ_ATTR_CHECK(info, HANDSHAKE_A_DONE_SOCKFD)) diff --git a/net/handshake/request.c b/net/handshake/request.c index 94d5cef3e048..d78d41abb3d9 100644 --- a/net/handshake/request.c +++ b/net/handshake/request.c @@ -239,6 +239,7 @@ int handshake_req_submit(struct socket *sock, struct handshake_req *req, } req->hr_odestruct = req->hr_sk->sk_destruct; req->hr_sk->sk_destruct = handshake_sk_destruct; + req->hr_file = sock->file; ret = -EOPNOTSUPP; net = sock_net(req->hr_sk); @@ -334,6 +335,9 @@ bool handshake_req_cancel(struct sock *sk) return false; } + /* Request accepted and waiting for DONE */ + fput(req->hr_file); + out_true: trace_handshake_cancel(net, req, sk); diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index fcbeb63b4eb1..b735f5cced2f 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -31,6 +31,7 @@ struct tls_handshake_req { int th_type; unsigned int th_timeout_ms; int th_auth_mode; + const char *th_peername; key_serial_t th_keyring; key_serial_t th_certificate; key_serial_t th_privkey; @@ -48,6 +49,7 @@ tls_handshake_req_init(struct handshake_req *req, treq->th_timeout_ms = args->ta_timeout_ms; treq->th_consumer_done = args->ta_done; treq->th_consumer_data = args->ta_data; + treq->th_peername = args->ta_peername; treq->th_keyring = args->ta_keyring; treq->th_num_peerids = 0; treq->th_certificate = TLS_NO_CERT; @@ -214,6 +216,12 @@ static int tls_handshake_accept(struct handshake_req *req, ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_MESSAGE_TYPE, treq->th_type); if (ret < 0) goto out_cancel; + if (treq->th_peername) { + ret = nla_put_string(msg, HANDSHAKE_A_ACCEPT_PEERNAME, + treq->th_peername); + if (ret < 0) + goto out_cancel; + } if (treq->th_timeout_ms) { ret = nla_put_u32(msg, HANDSHAKE_A_ACCEPT_TIMEOUT, treq->th_timeout_ms); if (ret < 0) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c4aab3aacbd8..4a76ebf793b8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -586,6 +586,7 @@ 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_*. @@ -601,6 +602,7 @@ 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; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 65ad4251f6fd..1386787eaf1a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1142,6 +1142,7 @@ 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/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b511ff0adc0a..8e97d8d4cc9d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff712bf2a98d..eadf1c9ef7e4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4d6392c16b7a..8d20d9221238 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1571,7 +1571,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) * calculation of whether or not we must ACK for the sake of * a window update. */ -static void __tcp_cleanup_rbuf(struct sock *sk, int copied) +void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; @@ -1773,7 +1773,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); - consume_skb(skb); if (used < 0) { if (!copied) copied = used; @@ -1787,14 +1786,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) break; } } - WRITE_ONCE(tp->copied_seq, seq); - - tcp_rcv_space_adjust(sk); - - /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) - __tcp_cleanup_rbuf(sk, copied); - return copied; } EXPORT_SYMBOL(tcp_read_skb); @@ -3090,6 +3081,12 @@ 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); @@ -4081,7 +4078,8 @@ int do_tcp_getsockopt(struct sock *sk, int level, switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; - if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + if (tp->rx_opt.user_mss && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 2e9547467edb..5f93918c063c 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -11,6 +11,24 @@ #include <net/inet_common.h> #include <net/tls.h> +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tcp; + int copied; + + if (!skb || !skb->len || !sk_is_tcp(sk)) + return; + + if (skb_bpf_strparser(skb)) + return; + + tcp = tcp_sk(sk); + copied = tcp->copied_seq + skb->len; + WRITE_ONCE(tcp->copied_seq, copied); + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, skb->len); +} + static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -174,14 +192,34 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, return ret; } +static bool is_next_msg_fin(struct sk_psock *psock) +{ + struct scatterlist *sge; + struct sk_msg *msg_rx; + int i; + + msg_rx = sk_psock_peek_msg(psock); + i = msg_rx->sg.start; + sge = sk_msg_elem(msg_rx, i); + if (!sge->length) { + struct sk_buff *skb = msg_rx->skb; + + if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + return true; + } + return false; +} + static int tcp_bpf_recvmsg_parser(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { + struct tcp_sock *tcp = tcp_sk(sk); + u32 seq = tcp->copied_seq; struct sk_psock *psock; - int copied; + int copied = 0; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -194,8 +232,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return tcp_recvmsg(sk, msg, len, flags, addr_len); lock_sock(sk); + + /* We may have received data on the sk_receive_queue pre-accept and + * then we can not use read_skb in this context because we haven't + * assigned a sk_socket yet so have no link to the ops. The work-around + * is to check the sk_receive_queue and in these cases read skbs off + * queue again. The read_skb hook is not running at this point because + * of lock_sock so we avoid having multiple runners in read_skb. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + tcp_data_ready(sk); + /* This handles the ENOMEM errors if we both receive data + * pre accept and are already under memory pressure. At least + * let user know to retry. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + copied = -EAGAIN; + goto out; + } + } + msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); + /* The typical case for EFAULT is the socket was gracefully + * shutdown with a FIN pkt. So check here the other case is + * some error on copy_page_to_iter which would be unexpected. + * On fin return correct return code to zero. + */ + if (copied == -EFAULT) { + bool is_fin = is_next_msg_fin(psock); + + if (is_fin) { + copied = 0; + seq++; + goto out; + } + } + seq += copied; if (!copied) { long timeo; int data; @@ -233,6 +306,10 @@ msg_bytes_ready: copied = -EAGAIN; } out: + WRITE_ONCE(tcp->copied_seq, seq); + tcp_rcv_space_adjust(sk); + if (copied > 0) + __tcp_cleanup_rbuf(sk, copied); release_sock(sk); sk_psock_put(sk, psock); return copied; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 61b6710f337a..bf8b22218dd4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) } } -static void tcp_sack_compress_send_ack(struct sock *sk) +void tcp_sack_compress_send_ack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b839c2f91292..39eb947fe392 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -290,9 +290,19 @@ static int tcp_write_timeout(struct sock *sk) void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; + + /* Handling the sack compression case */ + if (tp->compressed_ack) { + tcp_mstamp_refresh(tp); + tcp_sack_compress_send_ack(sk); + return; + } + + if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -312,7 +322,7 @@ void tcp_delack_timer_handler(struct sock *sk) inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } - tcp_mstamp_refresh(tcp_sk(sk)); + tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index aa32afd871ee..9482def1f310 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1818,7 +1818,7 @@ EXPORT_SYMBOL(__skb_recv_udp); int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; - int err, copied; + int err; try_again: skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); @@ -1837,10 +1837,7 @@ try_again: } WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL(udp_read_skb); diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index e0c9cc39b81e..56d94d23b9e0 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -64,6 +64,8 @@ struct proto udplite_prot = { .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udplite_table, }; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index da46c4284676..49e31e4ae7b7 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -143,6 +143,8 @@ int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type) optlen = 1; break; default: + if (len < 2) + goto bad; optlen = nh[offset + 1] + 2; if (optlen > len) goto bad; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d0adb612bdd..44ee7a2e72ac 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 67eaf3ca14ce..3bab0cc13697 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -60,6 +60,8 @@ struct proto udplitev6_prot = { .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, }; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08dc53f56bc2..67311e7d5b21 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -90,8 +90,8 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) if (err) return err; - msk->first = ssock->sk; - msk->subflow = ssock; + WRITE_ONCE(msk->first, ssock->sk); + WRITE_ONCE(msk->subflow, ssock); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); @@ -603,7 +603,7 @@ static bool mptcp_check_data_fin(struct sock *sk) WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ switch (sk->sk_state) { @@ -825,6 +825,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) mptcp_data_unlock(sk); } +static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) +{ + mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); + WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); +} + static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; @@ -839,6 +846,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sock_graft(ssk, sk->sk_socket); mptcp_sockopt_sync_locked(msk, ssk); + mptcp_subflow_joined(msk, ssk); return true; } @@ -910,7 +918,7 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) /* hopefully temporary hack: propagate shutdown status * to msk, when all subflows agree on it */ - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ sk->sk_data_ready(sk); @@ -1702,7 +1710,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, lock_sock(ssk); msg->msg_flags |= MSG_DONTWAIT; - msk->connect_flags = O_NONBLOCK; msk->fastopening = 1; ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); msk->fastopening = 0; @@ -2283,7 +2290,7 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) { if (msk->subflow) { iput(SOCK_INODE(msk->subflow)); - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); } } @@ -2420,7 +2427,7 @@ out_release: sock_put(ssk); if (ssk == msk->first) - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); out: if (ssk == msk->last_snd) @@ -2527,7 +2534,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) } inet_sk_state_store(sk, TCP_CLOSE); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); @@ -2721,7 +2728,7 @@ static int __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); @@ -2959,7 +2966,7 @@ bool __mptcp_close(struct sock *sk, long timeout) bool do_cancel_work = false; int subflows_alive = 0; - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_listen_inuse_dec(sk); @@ -3039,7 +3046,7 @@ static void mptcp_close(struct sock *sk, long timeout) sock_put(sk); } -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); @@ -3102,7 +3109,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; } @@ -3116,9 +3123,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req) +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -3137,7 +3145,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) @@ -3150,10 +3158,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; sock_reset_flag(nsk, SOCK_RCU_FREE); - /* will be fully established after successful MPC subflow creation */ - inet_sk_state_store(nsk, TCP_SYN_RECV); - security_inet_csk_clone(nsk, req); + + /* this can't race with mptcp_close(), as the msk is + * not yet exposted to user-space + */ + inet_sk_state_store(nsk, TCP_ESTABLISHED); + + /* The msk maintain a ref to each subflow in the connections list */ + WRITE_ONCE(msk->first, ssk); + list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + sock_hold(ssk); + + /* new mpc subflow takes ownership of the newly + * created mptcp socket + */ + mptcp_token_accept(subflow_req, msk); + + /* set msk addresses early to ensure mptcp_pm_get_local_id() + * uses the correct data + */ + mptcp_copy_inaddrs(nsk, ssk); + mptcp_propagate_sndbuf(nsk, ssk); + + mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3185,7 +3213,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, struct socket *listener; struct sock *newsk; - listener = msk->subflow; + listener = READ_ONCE(msk->subflow); if (WARN_ON_ONCE(!listener)) { *err = -EINVAL; return NULL; @@ -3465,14 +3493,16 @@ bool mptcp_finish_join(struct sock *ssk) return false; } - if (!list_empty(&subflow->node)) - goto out; + /* active subflow, already present inside the conn_list */ + if (!list_empty(&subflow->node)) { + mptcp_subflow_joined(msk, ssk); + return true; + } if (!mptcp_pm_allow_new_subflow(msk)) goto err_prohibited; - /* active connections are already on conn_list. - * If we can't acquire msk socket lock here, let the release callback + /* If we can't acquire msk socket lock here, let the release callback * handle it */ mptcp_data_lock(parent); @@ -3495,11 +3525,6 @@ err_prohibited: return false; } - subflow->map_seq = READ_ONCE(msk->ack_seq); - WRITE_ONCE(msk->allow_infinite_fallback, false); - -out: - mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); return true; } @@ -3617,9 +3642,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) * acquired the subflow socket lock, too. */ if (msk->fastopening) - err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1); + err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1); else - err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags); + err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK); inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; /* on successful connect, the msk state will be moved to established by @@ -3632,12 +3657,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) mptcp_copy_inaddrs(sk, ssock->sk); - /* unblocking connect, mptcp-level inet_stream_connect will error out - * without changing the socket state, update it here. + /* silence EINPROGRESS and let the caller inet_stream_connect + * handle the connection in progress */ - if (err == -EINPROGRESS) - sk->sk_socket->state = ssock->state; - return err; + return 0; } static struct proto mptcp_prot = { @@ -3696,18 +3719,6 @@ unlock: return err; } -static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) -{ - int ret; - - lock_sock(sock->sk); - mptcp_sk(sock->sk)->connect_flags = flags; - ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); - release_sock(sock->sk); - return ret; -} - static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); @@ -3751,10 +3762,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, pr_debug("msk=%p", msk); - /* buggy applications can call accept on socket states other then LISTEN + /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ - ssock = msk->subflow; + ssock = READ_ONCE(msk->subflow); if (!ssock) return -EINVAL; @@ -3800,9 +3811,6 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN)) - return EPOLLOUT | EPOLLWRNORM; - if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; @@ -3820,6 +3828,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; struct mptcp_sock *msk; __poll_t mask = 0; + u8 shutdown; int state; msk = mptcp_sk(sk); @@ -3828,23 +3837,30 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) { - if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk)) + struct socket *ssock = READ_ONCE(msk->subflow); + + if (WARN_ON_ONCE(!ssock || !ssock->sk)) return 0; - return inet_csk_listen_poll(msk->subflow->sk); + return inet_csk_listen_poll(ssock->sk); } + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + mask |= EPOLLHUP; + if (shutdown & RCV_SHUTDOWN) + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; + if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(msk); - mask |= mptcp_check_writeable(msk); + if (shutdown & SEND_SHUTDOWN) + mask |= EPOLLOUT | EPOLLWRNORM; + else + mask |= mptcp_check_writeable(msk); } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) - mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); @@ -3859,7 +3875,7 @@ static const struct proto_ops mptcp_stream_ops = { .owner = THIS_MODULE, .release = inet_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet_getname, @@ -3954,7 +3970,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { .owner = THIS_MODULE, .release = inet6_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet6_getname, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 2d7b2c80a164..c5255258bfb3 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -297,7 +297,6 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1; - int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -306,7 +305,11 @@ struct mptcp_sock { struct list_head rtx_queue; struct mptcp_data_frag *first_pending; struct list_head join_list; - struct socket *subflow; /* outgoing connect/listener/!mp_capable */ + struct socket *subflow; /* outgoing connect/listener/!mp_capable + * The mptcp ops can safely dereference, using suitable + * ONCE annotation, the subflow outside the socket + * lock as such sock is freed after close(). + */ struct sock *first; struct mptcp_pm_data pm; struct { @@ -613,7 +616,6 @@ int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); int mptcp_get_pm_type(const struct net *net); -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); @@ -683,9 +685,10 @@ void __init mptcp_proto_init(void); int __init mptcp_proto_v6_init(void); #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req); +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ba065b66551a..4688daa6b38b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -815,38 +815,12 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { - ctx->conn = mptcp_sk_clone(listener->conn, &mp_opt, req); + ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req); if (!ctx->conn) goto fallback; owner = mptcp_sk(ctx->conn); - - /* this can't race with mptcp_close(), as the msk is - * not yet exposted to user-space - */ - inet_sk_state_store(ctx->conn, TCP_ESTABLISHED); - - /* record the newly created socket as the first msk - * subflow, but don't link it yet into conn_list - */ - WRITE_ONCE(owner->first, child); - - /* new mpc subflow takes ownership of the newly - * created mptcp socket - */ - owner->setsockopt_seq = ctx->setsockopt_seq; mptcp_pm_new_connection(owner, child, 1); - mptcp_token_accept(subflow_req, owner); - - /* set msk addresses early to ensure mptcp_pm_get_local_id() - * uses the correct data - */ - mptcp_copy_inaddrs(ctx->conn, child); - mptcp_propagate_sndbuf(ctx->conn, child); - - mptcp_rcv_space_init(owner, child); - list_add(&ctx->node, &owner->conn_list); - sock_hold(child); /* with OoO packets we can reach here without ingress * mpc option diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c87804112d0c..3a1e0fd5bf14 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1779,7 +1779,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, break; } } - if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) + if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index 3f99b432ea70..e2d2af924cff 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -123,7 +123,7 @@ void nr_write_internal(struct sock *sk, int frametype) unsigned char *dptr; int len, timeout; - len = NR_NETWORK_LEN + NR_TRANSPORT_LEN; + len = NR_TRANSPORT_LEN; switch (frametype & 0x0F) { case NR_CONNREQ: @@ -141,7 +141,8 @@ void nr_write_internal(struct sock *sk, int frametype) return; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(NR_NETWORK_LEN + len, GFP_ATOMIC); + if (!skb) return; /* @@ -149,7 +150,7 @@ void nr_write_internal(struct sock *sk, int frametype) */ skb_reserve(skb, NR_NETWORK_LEN); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); switch (frametype & 0x0F) { case NR_CONNREQ: diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 94c6a1ffa459..a2dbeb264f26 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3201,6 +3201,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, lock_sock(sk); spin_lock(&po->bind_lock); + if (!proto) + proto = po->num; + rcu_read_lock(); if (po->fanout) { @@ -3299,7 +3302,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; - return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); + return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) @@ -3316,8 +3319,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len if (sll->sll_family != AF_PACKET) return -EINVAL; - return packet_do_bind(sk, NULL, sll->sll_ifindex, - sll->sll_protocol ? : pkt_sk(sk)->num); + return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { diff --git a/net/packet/diag.c b/net/packet/diag.c index d0c4eda4cdc6..f6b200cb3c06 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -143,7 +143,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, rp = nlmsg_data(nlh); rp->pdiag_family = AF_PACKET; rp->pdiag_type = sk->sk_type; - rp->pdiag_num = ntohs(po->num); + rp->pdiag_num = ntohs(READ_ONCE(po->num)); rp->pdiag_ino = sk_ino; sock_diag_save_cookie(sk, rp->pdiag_cookie); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 31f738d65f1c..da0b3b5157d5 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -980,6 +980,7 @@ static int __init af_rxrpc_init(void) BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); ret = -ENOMEM; + rxrpc_gen_version_string(); rxrpc_call_jar = kmem_cache_create( "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, SLAB_HWCACHE_ALIGN, NULL); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5d44dc08f66d..e8e14c6f904d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1068,6 +1068,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, /* * local_event.c */ +void rxrpc_gen_version_string(void); void rxrpc_send_version_request(struct rxrpc_local *local, struct rxrpc_host_header *hdr, struct sk_buff *skb); diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 5e69ea6b233d..993c69f97488 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -16,7 +16,16 @@ #include <generated/utsrelease.h> #include "ar-internal.h" -static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; +static char rxrpc_version_string[65]; // "linux-" UTS_RELEASE " AF_RXRPC"; + +/* + * Generate the VERSION packet string. + */ +void rxrpc_gen_version_string(void) +{ + snprintf(rxrpc_version_string, sizeof(rxrpc_version_string), + "linux-%.49s AF_RXRPC", UTS_RELEASE); +} /* * Reply to a version request diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9dbc43388e57..815c3e416bc5 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1153,6 +1153,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index fdb8f429333d..014209b1dd58 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1252,7 +1252,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev, sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { @@ -1591,11 +1596,20 @@ replay: NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; + } qdisc_refcount_inc(q); goto graft; } else { diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 84838128b9c5..e43a45499372 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -80,6 +80,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_INGRESS) + return -EOPNOTSUPP; + net_inc_ingress_queue(); mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); @@ -101,6 +104,9 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_INGRESS) + return; + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } @@ -134,7 +140,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -219,6 +225,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_CLSACT) + return -EOPNOTSUPP; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -248,6 +257,9 @@ static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_CLSACT) + return; + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); @@ -269,7 +281,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 2f66a2006517..2abe45af98e7 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -324,9 +324,12 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) t->pl.probe_size += SCTP_PL_BIG_STEP; } else if (t->pl.state == SCTP_PL_SEARCH) { if (!t->pl.probe_high) { - t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, - SCTP_MAX_PLPMTU); - return false; + if (t->pl.probe_size < SCTP_MAX_PLPMTU) { + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, + SCTP_MAX_PLPMTU); + return false; + } + t->pl.probe_high = SCTP_MAX_PLPMTU; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -341,7 +344,7 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) } else if (t->pl.state == SCTP_PL_COMPLETE) { /* Raise probe_size again after 30 * interval in Search Complete */ t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_MIN_STEP, SCTP_MAX_PLPMTU); } return t->pl.state == SCTP_PL_COMPLETE; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 50c38b624f77..538e9c6ec8c9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2000,8 +2000,10 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, return rc; /* create send buffer and rmb */ - if (smc_buf_create(new_smc, false)) + if (smc_buf_create(new_smc, false)) { + smc_conn_abort(new_smc, ini->first_contact_local); return SMC_CLC_DECL_MEM; + } return 0; } @@ -2217,8 +2219,11 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, smcr_version = ini->smcr_version; ini->smcr_version = SMC_V2; rc = smc_listen_rdma_init(new_smc, ini); - if (!rc) + if (!rc) { rc = smc_listen_rdma_reg(new_smc, ini->first_contact_local); + if (rc) + smc_conn_abort(new_smc, ini->first_contact_local); + } if (!rc) return; ini->smcr_version = smcr_version; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 454356771cda..3f465faf2b68 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -127,6 +127,7 @@ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first) int i, j; /* do link balancing */ + conn->lnk = NULL; /* reset conn->lnk first */ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &conn->lgr->lnk[i]; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a0840b8c935b..7a8d9163d186 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -578,7 +578,10 @@ static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, { struct smc_buf_desc *buf_next; - if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { + if (!buf_pos) + return _smc_llc_get_next_rmb(lgr, buf_lst); + + if (list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { (*buf_lst)++; return _smc_llc_get_next_rmb(lgr, buf_lst); } @@ -614,6 +617,8 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, goto out; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); for (i = 0; i < ext->num_rkeys; i++) { + while (buf_pos && !(buf_pos)->used) + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); if (!buf_pos) break; rmb = buf_pos; @@ -623,8 +628,6 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, cpu_to_be64((uintptr_t)rmb->cpu_addr) : cpu_to_be64((u64)sg_dma_address(rmb->sgt[lnk_idx].sgl)); buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); - while (buf_pos && !(buf_pos)->used) - buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); } len += i * sizeof(ext->rt[0]); out: diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c8321de341ee..6debf4fd42d4 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -927,11 +927,10 @@ static void __rpc_execute(struct rpc_task *task) */ do_action = task->tk_action; /* Tasks with an RPC error status should exit */ - if (do_action != rpc_exit_task && + if (do_action && do_action != rpc_exit_task && (status = READ_ONCE(task->tk_rpc_status)) != 0) { task->tk_status = status; - if (do_action != NULL) - do_action = rpc_exit_task; + do_action = rpc_exit_task; } /* Callbacks override all actions */ if (task->tk_callback) { diff --git a/net/tls/tls.h b/net/tls/tls.h index 804c3880d028..0672acab2773 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -167,6 +167,11 @@ static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) return ctx->strp.msg_ready; } +static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) +{ + return ctx->strp.mixed_decrypted; +} + #ifdef CONFIG_TLS_DEVICE int tls_device_init(void); void tls_device_cleanup(void); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index a7cc4f9faac2..bf69c9d6d06c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1007,20 +1007,14 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb = tls_strp_msg(sw_ctx); struct strp_msg *rxm = strp_msg(skb); - int is_decrypted = skb->decrypted; - int is_encrypted = !is_decrypted; - struct sk_buff *skb_iter; - int left; - - left = rxm->full_len - skb->len; - /* Check if all the data is decrypted already */ - skb_iter = skb_shinfo(skb)->frag_list; - while (skb_iter && left > 0) { - is_decrypted &= skb_iter->decrypted; - is_encrypted &= !skb_iter->decrypted; - - left -= skb_iter->len; - skb_iter = skb_iter->next; + int is_decrypted, is_encrypted; + + if (!tls_strp_msg_mixed_decrypted(sw_ctx)) { + is_decrypted = skb->decrypted; + is_encrypted = !is_decrypted; + } else { + is_decrypted = 0; + is_encrypted = 0; } trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 955ac3e0bf4d..f37f4a0fcd3c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -20,7 +20,9 @@ static void tls_strp_abort_strp(struct tls_strparser *strp, int err) strp->stopped = 1; /* Report an error on the lower socket */ - strp->sk->sk_err = -err; + WRITE_ONCE(strp->sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(strp->sk); } @@ -29,34 +31,50 @@ static void tls_strp_anchor_free(struct tls_strparser *strp) struct skb_shared_info *shinfo = skb_shinfo(strp->anchor); DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1); - shinfo->frag_list = NULL; + if (!strp->copy_mode) + shinfo->frag_list = NULL; consume_skb(strp->anchor); strp->anchor = NULL; } -/* Create a new skb with the contents of input copied to its page frags */ -static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) +static struct sk_buff * +tls_strp_skb_copy(struct tls_strparser *strp, struct sk_buff *in_skb, + int offset, int len) { - struct strp_msg *rxm; struct sk_buff *skb; - int i, err, offset; + int i, err; - skb = alloc_skb_with_frags(0, strp->stm.full_len, TLS_PAGE_ORDER, + skb = alloc_skb_with_frags(0, len, TLS_PAGE_ORDER, &err, strp->sk->sk_allocation); if (!skb) return NULL; - offset = strp->stm.offset; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - WARN_ON_ONCE(skb_copy_bits(strp->anchor, offset, + WARN_ON_ONCE(skb_copy_bits(in_skb, offset, skb_frag_address(frag), skb_frag_size(frag))); offset += skb_frag_size(frag); } - skb_copy_header(skb, strp->anchor); + skb->len = len; + skb->data_len = len; + skb_copy_header(skb, in_skb); + return skb; +} + +/* Create a new skb with the contents of input copied to its page frags */ +static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) +{ + struct strp_msg *rxm; + struct sk_buff *skb; + + skb = tls_strp_skb_copy(strp, strp->anchor, strp->stm.offset, + strp->stm.full_len); + if (!skb) + return NULL; + rxm = strp_msg(skb); rxm->offset = 0; return skb; @@ -180,22 +198,22 @@ static void tls_strp_flush_anchor_copy(struct tls_strparser *strp) for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], false); shinfo->nr_frags = 0; + if (strp->copy_mode) { + kfree_skb_list(shinfo->frag_list); + shinfo->frag_list = NULL; + } strp->copy_mode = 0; + strp->mixed_decrypted = 0; } -static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, - unsigned int offset, size_t in_len) +static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) { - struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; - struct sk_buff *skb; - skb_frag_t *frag; size_t len, chunk; + skb_frag_t *frag; int sz; - if (strp->msg_ready) - return 0; - - skb = strp->anchor; frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; len = in_len; @@ -208,19 +226,26 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size(frag), chunk)); - sz = tls_rx_msg_size(strp, strp->anchor); - if (sz < 0) { - desc->error = sz; - return 0; - } - - /* We may have over-read, sz == 0 is guaranteed under-read */ - if (sz > 0) - chunk = min_t(size_t, chunk, sz - skb->len); - skb->len += chunk; skb->data_len += chunk; skb_frag_size_add(frag, chunk); + + sz = tls_rx_msg_size(strp, skb); + if (sz < 0) + return sz; + + /* We may have over-read, sz == 0 is guaranteed under-read */ + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + skb_frag_size_add(frag, -over); + + chunk -= over; + } + frag++; len -= chunk; offset += chunk; @@ -247,15 +272,99 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, offset += chunk; } - if (strp->stm.full_len == skb->len) { +read_done: + return in_len - len; +} + +static int tls_strp_copyin_skb(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) +{ + struct sk_buff *nskb, *first, *last; + struct skb_shared_info *shinfo; + size_t chunk; + int sz; + + if (strp->stm.full_len) + chunk = strp->stm.full_len - skb->len; + else + chunk = TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; + chunk = min(chunk, in_len); + + nskb = tls_strp_skb_copy(strp, in_skb, offset, chunk); + if (!nskb) + return -ENOMEM; + + shinfo = skb_shinfo(skb); + if (!shinfo->frag_list) { + shinfo->frag_list = nskb; + nskb->prev = nskb; + } else { + first = shinfo->frag_list; + last = first->prev; + last->next = nskb; + first->prev = nskb; + } + + skb->len += chunk; + skb->data_len += chunk; + + if (!strp->stm.full_len) { + sz = tls_rx_msg_size(strp, skb); + if (sz < 0) + return sz; + + /* We may have over-read, sz == 0 is guaranteed under-read */ + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + __pskb_trim(nskb, nskb->len - over); + + chunk -= over; + } + + strp->stm.full_len = sz; + } + + return chunk; +} + +static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, + unsigned int offset, size_t in_len) +{ + struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; + struct sk_buff *skb; + int ret; + + if (strp->msg_ready) + return 0; + + skb = strp->anchor; + if (!skb->len) + skb_copy_decrypted(skb, in_skb); + else + strp->mixed_decrypted |= !!skb_cmp_decrypted(skb, in_skb); + + if (IS_ENABLED(CONFIG_TLS_DEVICE) && strp->mixed_decrypted) + ret = tls_strp_copyin_skb(strp, skb, in_skb, offset, in_len); + else + ret = tls_strp_copyin_frag(strp, skb, in_skb, offset, in_len); + if (ret < 0) { + desc->error = ret; + ret = 0; + } + + if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; strp->msg_ready = 1; tls_rx_msg_ready(strp); } -read_done: - return in_len - len; + return ret; } static int tls_strp_read_copyin(struct tls_strparser *strp) @@ -315,15 +424,19 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; } -static bool tls_strp_check_no_dup(struct tls_strparser *strp) +static bool tls_strp_check_queue_ok(struct tls_strparser *strp) { unsigned int len = strp->stm.offset + strp->stm.full_len; - struct sk_buff *skb; + struct sk_buff *first, *skb; u32 seq; - skb = skb_shinfo(strp->anchor)->frag_list; - seq = TCP_SKB_CB(skb)->seq; + first = skb_shinfo(strp->anchor)->frag_list; + skb = first; + seq = TCP_SKB_CB(first)->seq; + /* Make sure there's no duplicate data in the queue, + * and the decrypted status matches. + */ while (skb->len < len) { seq += skb->len; len -= skb->len; @@ -331,6 +444,8 @@ static bool tls_strp_check_no_dup(struct tls_strparser *strp) if (TCP_SKB_CB(skb)->seq != seq) return false; + if (skb_cmp_decrypted(first, skb)) + return false; } return true; @@ -411,7 +526,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copy(strp, true); } - if (!tls_strp_check_no_dup(strp)) + if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); strp->msg_ready = 1; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 635b8bf6b937..1a53c8f481e9 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -70,7 +70,9 @@ noinline void tls_err_abort(struct sock *sk, int err) { WARN_ON_ONCE(err >= 0); /* sk->sk_err should contain a positive error code. */ - sk->sk_err = -err; + WRITE_ONCE(sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(sk); } @@ -2304,10 +2306,14 @@ static void tls_data_ready(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_psock *psock; + gfp_t alloc_save; trace_sk_data_ready(sk); + alloc_save = sk->sk_allocation; + sk->sk_allocation = GFP_ATOMIC; tls_strp_data_ready(&ctx->strp); + sk->sk_allocation = alloc_save; psock = sk_psock_get(sk); if (psock) { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index cc695c9f09ec..e7728b57a8c7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2553,7 +2553,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; - int err, copied; + int err; mutex_lock(&u->iolock); skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); @@ -2561,10 +2561,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } /* diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e4878551f140..b769fc258931 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1441,7 +1441,6 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto struct sock *sk = sk_vsock(vsk); struct sk_buff *skb; int off = 0; - int copied; int err; spin_lock_bh(&vvs->rx_lock); @@ -1454,9 +1453,7 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL_GPL(virtio_transport_read_skb); |