diff options
Diffstat (limited to 'net')
412 files changed, 10910 insertions, 7286 deletions
diff --git a/net/802/garp.c b/net/802/garp.c index f6012f8e59f0..fc9eb02a912f 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -407,7 +407,7 @@ static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(garp_join_time) * prandom_u32() >> 32; + delay = prandom_u32_max(msecs_to_jiffies(garp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/802/mrp.c b/net/802/mrp.c index 35e04cc5390c..6c927d4b35f0 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -592,7 +592,7 @@ static void mrp_join_timer_arm(struct mrp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32; + delay = prandom_u32_max(msecs_to_jiffies(mrp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } @@ -606,7 +606,10 @@ static void mrp_join_timer(struct timer_list *t) spin_unlock(&app->lock); mrp_queue_xmit(app); - mrp_join_timer_arm(app); + spin_lock(&app->lock); + if (likely(app->active)) + mrp_join_timer_arm(app); + spin_unlock(&app->lock); } static void mrp_periodic_timer_arm(struct mrp_applicant *app) @@ -620,11 +623,12 @@ static void mrp_periodic_timer(struct timer_list *t) struct mrp_applicant *app = from_timer(app, t, periodic_timer); spin_lock(&app->lock); - mrp_mad_event(app, MRP_EVENT_PERIODIC); - mrp_pdu_queue(app); + if (likely(app->active)) { + mrp_mad_event(app, MRP_EVENT_PERIODIC); + mrp_pdu_queue(app); + mrp_periodic_timer_arm(app); + } spin_unlock(&app->lock); - - mrp_periodic_timer_arm(app); } static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) @@ -872,6 +876,7 @@ int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) app->dev = dev; app->app = appl; app->mad = RB_ROOT; + app->active = true; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); @@ -900,6 +905,9 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) RCU_INIT_POINTER(port->applicants[appl->type], NULL); + spin_lock_bh(&app->lock); + app->active = false; + spin_unlock_bh(&app->lock); /* Delete timer and generate a final TX event to flush out * all pending messages before the applicant is gone. */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e1bb41a443c4..296d0145932f 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -712,13 +712,13 @@ static void vlan_dev_get_stats64(struct net_device *dev, p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); do { - start = u64_stats_fetch_begin_irq(&p->syncp); + start = u64_stats_fetch_begin(&p->syncp); rxpackets = u64_stats_read(&p->rx_packets); rxbytes = u64_stats_read(&p->rx_bytes); rxmulticast = u64_stats_read(&p->rx_multicast); txpackets = u64_stats_read(&p->tx_packets); txbytes = u64_stats_read(&p->tx_bytes); - } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rxpackets; stats->rx_bytes += rxbytes; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 56a186768750..07db2f436d44 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -120,7 +120,7 @@ struct p9_conn { struct list_head unsent_req_list; struct p9_req_t *rreq; struct p9_req_t *wreq; - char tmp_buf[7]; + char tmp_buf[P9_HDRSZ]; struct p9_fcall rc; int wpos; int wsize; @@ -202,9 +202,11 @@ static void p9_conn_cancel(struct p9_conn *m, int err) list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } spin_unlock(&m->req_lock); @@ -291,7 +293,7 @@ static void p9_read_work(struct work_struct *work) if (!m->rc.sdata) { m->rc.sdata = m->tmp_buf; m->rc.offset = 0; - m->rc.capacity = 7; /* start by reading header */ + m->rc.capacity = P9_HDRSZ; /* start by reading header */ } clear_bit(Rpending, &m->wsched); @@ -314,7 +316,7 @@ static void p9_read_work(struct work_struct *work) p9_debug(P9_DEBUG_TRANS, "got new header\n"); /* Header size */ - m->rc.size = 7; + m->rc.size = P9_HDRSZ; err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0); if (err) { p9_debug(P9_DEBUG_ERROR, @@ -322,14 +324,6 @@ static void p9_read_work(struct work_struct *work) goto error; } - if (m->rc.size >= m->client->msize) { - p9_debug(P9_DEBUG_ERROR, - "requested packet size too big: %d\n", - m->rc.size); - err = -EIO; - goto error; - } - p9_debug(P9_DEBUG_TRANS, "mux %p pkt: size: %d bytes tag: %d\n", m, m->rc.size, m->rc.tag); @@ -342,6 +336,14 @@ static void p9_read_work(struct work_struct *work) goto error; } + if (m->rc.size > m->rreq->rc.capacity) { + p9_debug(P9_DEBUG_ERROR, + "requested packet size too big: %d for tag %d with capacity %zd\n", + m->rc.size, m->rc.tag, m->rreq->rc.capacity); + err = -EIO; + goto error; + } + if (!m->rreq->rc.sdata) { p9_debug(P9_DEBUG_ERROR, "No recv fcall for tag %d (req %p), disconnecting!\n", @@ -860,8 +862,10 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) struct file *file; p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); - if (!p) + if (!p) { + sock_release(csocket); return -ENOMEM; + } csocket->sk->sk_allocation = GFP_NOIO; file = sock_alloc_file(csocket, 0, NULL); diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index b15c64128c3e..aaa5fd364691 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -208,6 +208,14 @@ static void p9_xen_response(struct work_struct *work) continue; } + if (h.size > req->rc.capacity) { + dev_warn(&priv->dev->dev, + "requested packet size too big: %d for tag %d with capacity %zd\n", + h.size, h.tag, req->rc.capacity); + req->status = REQ_STATUS_ERROR; + goto recv_error; + } + memcpy(&req->rc, &h, sizeof(h)); req->rc.offset = 0; @@ -217,6 +225,7 @@ static void p9_xen_response(struct work_struct *work) masked_prod, &masked_cons, XEN_9PFS_RING_SIZE(ring)); +recv_error: virt_mb(); cons += h.size; ring->intf->in_cons = cons; diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 829db9eba0cb..aaf64b953915 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -219,11 +219,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, if (!page) return -ENOMEM; - for (p = page, len = 0; len < nbytes; p++, len++) { + for (p = page, len = 0; len < nbytes; p++) { if (get_user(*p, buff++)) { free_page((unsigned long)page); return -EFAULT; } + len += 1; if (*p == '\0' || *p == '\n') break; } diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 6b4c25a92377..d8da400cb4de 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -723,7 +723,7 @@ static int ax25_getsockopt(struct socket *sock, int level, int optname, if (maxlen < 1) return -EFAULT; - valptr = (void *) &val; + valptr = &val; length = min_t(unsigned int, maxlen, sizeof(int)); lock_sock(sk); @@ -785,7 +785,7 @@ static int ax25_getsockopt(struct socket *sock, int level, int optname, length = 1; } - valptr = (void *) devname; + valptr = devname; break; default: diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a5e4a4e976cf..ad5714f737be 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1267,7 +1267,8 @@ batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, * * Return: 0 on success or negative error number in case of failure */ -static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int batadv_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); @@ -1332,7 +1333,8 @@ err_put_softif: * @skb: Netlink message with request data * @info: receiver information */ -static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void batadv_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7a59c4487050..a6c12863a253 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1067,10 +1067,21 @@ int hci_conn_del(struct hci_conn *conn) hdev->acl_cnt += conn->sent; } else { struct hci_conn *acl = conn->link; + if (acl) { acl->link = NULL; hci_conn_drop(acl); } + + /* Unacked ISO frames */ + if (conn->type == ISO_LINK) { + if (hdev->iso_pkts) + hdev->iso_cnt += conn->sent; + else if (hdev->le_pkts) + hdev->le_cnt += conn->sent; + else + hdev->acl_cnt += conn->sent; + } } if (conn->amp_mgr) @@ -1761,6 +1772,7 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, if (!cis) return ERR_PTR(-ENOMEM); cis->cleanup = cis_cleanup; + cis->dst_type = dst_type; } if (cis->state == BT_CONNECTED) @@ -2140,12 +2152,6 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, struct hci_conn *le; struct hci_conn *cis; - /* Convert from ISO socket address type to HCI address type */ - if (dst_type == BDADDR_LE_PUBLIC) - dst_type = ADDR_LE_DEV_PUBLIC; - else - dst_type = ADDR_LE_DEV_RANDOM; - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) le = hci_connect_le(hdev, dst, dst_type, false, BT_SECURITY_LOW, diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 613039ba5dbf..f825857db6d0 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -235,6 +235,14 @@ static int iso_chan_add(struct iso_conn *conn, struct sock *sk, return err; } +static inline u8 le_addr_type(u8 bdaddr_type) +{ + if (bdaddr_type == BDADDR_LE_PUBLIC) + return ADDR_LE_DEV_PUBLIC; + else + return ADDR_LE_DEV_RANDOM; +} + static int iso_connect_bis(struct sock *sk) { struct iso_conn *conn; @@ -328,14 +336,16 @@ static int iso_connect_cis(struct sock *sk) /* Just bind if DEFER_SETUP has been set */ if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { hcon = hci_bind_cis(hdev, &iso_pi(sk)->dst, - iso_pi(sk)->dst_type, &iso_pi(sk)->qos); + le_addr_type(iso_pi(sk)->dst_type), + &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto done; } } else { hcon = hci_connect_cis(hdev, &iso_pi(sk)->dst, - iso_pi(sk)->dst_type, &iso_pi(sk)->qos); + le_addr_type(iso_pi(sk)->dst_type), + &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto done; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 1f34b82ca0ec..9c24947aa41e 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1990,7 +1990,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, if (link_type == LE_LINK && c->src_type == BDADDR_BREDR) continue; - if (c->psm == psm) { + if (c->chan_type != L2CAP_CHAN_FIXED && c->psm == psm) { int src_match, dst_match; int src_any, dst_any; @@ -3764,7 +3764,8 @@ done: l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc, endptr - ptr); - if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { + if (remote_efs && + test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->remote_id = efs.id; chan->remote_stype = efs.stype; chan->remote_msdu = le16_to_cpu(efs.msdu); @@ -5813,6 +5814,19 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm), scid, mtu, mps); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + chan = NULL; + goto response; + } + /* Check if we have socket listening on psm */ pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, &conn->hcon->dst, LE_LINK); @@ -6001,6 +6015,18 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, psm = req->psm; + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + goto response; + } + BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps); memset(&pdu, 0, sizeof(pdu)); @@ -6885,6 +6911,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb, u8 event) { + struct l2cap_ctrl local_control; int err = 0; bool skb_in_use = false; @@ -6909,15 +6936,32 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, chan->buffer_seq = chan->expected_tx_seq; skb_in_use = true; + /* l2cap_reassemble_sdu may free skb, hence invalidate + * control, so make a copy in advance to use it after + * l2cap_reassemble_sdu returns and to avoid the race + * condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but + * it was freed by skb_free_datagram. + */ + local_control = *control; err = l2cap_reassemble_sdu(chan, skb, control); if (err) break; - if (control->final) { + if (local_control.final) { if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) { - control->final = 0; - l2cap_retransmit_all(chan, control); + local_control.final = 0; + l2cap_retransmit_all(chan, &local_control); l2cap_ertm_send(chan); } } @@ -7297,11 +7341,27 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb) { + /* l2cap_reassemble_sdu may free skb, hence invalidate control, so store + * the txseq field in advance to use it after l2cap_reassemble_sdu + * returns and to avoid the race condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but it was freed by + * skb_free_datagram. + */ + u16 txseq = control->txseq; + BT_DBG("chan %p, control %p, skb %p, state %d", chan, control, skb, chan->rx_state); - if (l2cap_classify_txseq(chan, control->txseq) == - L2CAP_TXSEQ_EXPECTED) { + if (l2cap_classify_txseq(chan, txseq) == L2CAP_TXSEQ_EXPECTED) { l2cap_pass_to_tx(chan, control); BT_DBG("buffer_seq %u->%u", chan->buffer_seq, @@ -7324,8 +7384,8 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, } } - chan->last_acked_seq = control->txseq; - chan->expected_tx_seq = __next_seq(chan, control->txseq); + chan->last_acked_seq = txseq; + chan->expected_tx_seq = __next_seq(chan, txseq); return 0; } @@ -7581,6 +7641,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, return; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); } else { BT_DBG("unknown cid 0x%4.4x", cid); @@ -8426,9 +8487,8 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) * expected length. */ if (skb->len < L2CAP_LEN_SIZE) { - if (l2cap_recv_frag(conn, skb, conn->mtu) < 0) - goto drop; - return; + l2cap_recv_frag(conn, skb, conn->mtu); + break; } len = get_unaligned_le16(skb->data) + L2CAP_HDR_SIZE; @@ -8472,7 +8532,7 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) /* Header still could not be read just continue */ if (conn->rx_skb->len < L2CAP_LEN_SIZE) - return; + break; } if (skb->len > conn->rx_len) { diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index e78dadfc5829..2d434c1f4617 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -156,29 +156,29 @@ static bool bpf_dummy_ops_is_valid_access(int off, int size, } static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag) { const struct btf_type *state; + const struct btf_type *t; s32 type_id; int err; - type_id = btf_find_by_name_kind(btf, "bpf_dummy_ops_state", + type_id = btf_find_by_name_kind(reg->btf, "bpf_dummy_ops_state", BTF_KIND_STRUCT); if (type_id < 0) return -EINVAL; - state = btf_type_by_id(btf, type_id); + t = btf_type_by_id(reg->btf, reg->btf_id); + state = btf_type_by_id(reg->btf, type_id); if (t != state) { bpf_log(log, "only access to bpf_dummy_ops_state is supported\n"); return -EACCES; } - err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + err = btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); if (err < 0) return err; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 13d578ce2a09..6094ef7cffcd 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -774,6 +774,7 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, if (user_size > size) return ERR_PTR(-EMSGSIZE); + size = SKB_DATA_ALIGN(size); data = kzalloc(size + headroom + tailroom, GFP_USER); if (!data) return ERR_PTR(-ENOMEM); @@ -979,9 +980,6 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) { struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb; - if (!skb->len) - return -EINVAL; - if (!__skb) return 0; diff --git a/net/bridge/br.c b/net/bridge/br.c index 96e91d69a9a8..4f5098d33a46 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -166,13 +166,14 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid, false); + fdb_info->vid, + fdb_info->locked, false); if (err) { err = notifier_from_errno(err); break; } br_fdb_offloaded_set(br, p, fdb_info->addr, - fdb_info->vid, true); + fdb_info->vid, fdb_info->offloaded); break; case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e7f4fccb6adb..e69a872bfc1d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -105,6 +105,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; + u32 ext_flags = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) @@ -125,11 +126,16 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_flags |= NTF_EXT_LEARNED; if (test_bit(BR_FDB_STICKY, &fdb->flags)) ndm->ndm_flags |= NTF_STICKY; + if (test_bit(BR_FDB_LOCKED, &fdb->flags)) + ext_flags |= NTF_EXT_LOCKED; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) goto nla_put_failure; + if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) + goto nla_put_failure; + ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); @@ -171,6 +177,7 @@ static inline size_t fdb_nlmsg_size(void) return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + + nla_total_size(sizeof(u32)) /* NDA_FLAGS_EXT */ + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(0) /* NDA_FDB_EXT_ATTRS */ @@ -879,6 +886,11 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, &fdb->flags))) clear_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags); + /* Clear locked flag when roaming to an + * unlocked port. + */ + if (unlikely(test_bit(BR_FDB_LOCKED, &fdb->flags))) + clear_bit(BR_FDB_LOCKED, &fdb->flags); } if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags))) @@ -1082,6 +1094,9 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, modified = true; } + if (test_and_clear_bit(BR_FDB_LOCKED, &fdb->flags)) + modified = true; + if (fdb_handle_notify(fdb, notify)) modified = true; @@ -1124,7 +1139,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, "FDB entry towards bridge must be permanent"); return -EINVAL; } - err = br_fdb_external_learn_add(br, p, addr, vid, true); + err = br_fdb_external_learn_add(br, p, addr, vid, false, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb); @@ -1150,6 +1165,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_bridge_port *p = NULL; struct net_bridge_vlan *v; struct net_bridge *br = NULL; + u32 ext_flags = 0; int err = 0; trace_br_fdb_add(ndm, dev, addr, vid, nlh_flags); @@ -1178,6 +1194,14 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], vg = nbp_vlan_group(p); } + if (tb[NDA_FLAGS_EXT]) + ext_flags = nla_get_u32(tb[NDA_FLAGS_EXT]); + + if (ext_flags & NTF_EXT_LOCKED) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add FDB entry with \"locked\" flag set"); + return -EINVAL; + } + if (tb[NDA_FDB_EXT_ATTRS]) { attr = tb[NDA_FDB_EXT_ATTRS]; err = nla_parse_nested(nfea_tb, NFEA_MAX, attr, @@ -1353,7 +1377,7 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, + const unsigned char *addr, u16 vid, bool locked, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; @@ -1362,6 +1386,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, trace_br_fdb_external_learn_add(br, p, addr, vid); + if (locked && (!p || !(p->flags & BR_PORT_MAB))) + return -EINVAL; + spin_lock_bh(&br->hash_lock); fdb = br_fdb_find(br, addr, vid); @@ -1374,6 +1401,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (!p) flags |= BIT(BR_FDB_LOCAL); + if (locked) + flags |= BIT(BR_FDB_LOCKED); + fdb = fdb_create(br, p, addr, vid, flags); if (!fdb) { err = -ENOMEM; @@ -1381,6 +1411,13 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { + if (locked && + (!test_bit(BR_FDB_LOCKED, &fdb->flags) || + READ_ONCE(fdb->dst) != p)) { + err = -EINVAL; + goto err_unlock; + } + fdb->updated = jiffies; if (READ_ONCE(fdb->dst) != p) { @@ -1397,6 +1434,11 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } + if (locked != test_bit(BR_FDB_LOCKED, &fdb->flags)) { + change_bit(BR_FDB_LOCKED, &fdb->flags); + modified = true; + } + if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 68b3e850bcb9..3027e8f6be15 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -109,9 +109,26 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_fdb_entry *fdb_src = br_fdb_find_rcu(br, eth_hdr(skb)->h_source, vid); - if (!fdb_src || READ_ONCE(fdb_src->dst) != p || - test_bit(BR_FDB_LOCAL, &fdb_src->flags)) + if (!fdb_src) { + /* FDB miss. Create locked FDB entry if MAB is enabled + * and drop the packet. + */ + if (p->flags & BR_PORT_MAB) + br_fdb_update(br, p, eth_hdr(skb)->h_source, + vid, BIT(BR_FDB_LOCKED)); goto drop; + } else if (READ_ONCE(fdb_src->dst) != p || + test_bit(BR_FDB_LOCAL, &fdb_src->flags)) { + /* FDB mismatch. Drop the packet without roaming. */ + goto drop; + } else if (test_bit(BR_FDB_LOCKED, &fdb_src->flags)) { + /* FDB match, but entry is locked. Refresh it and drop + * the packet. + */ + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, + BIT(BR_FDB_LOCKED)); + goto drop; + } } nbp_switchdev_frame_mark(p, skb); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 589ff497d50c..321be94c445a 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -866,7 +866,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, unsigned long now = jiffies; unsigned char flags = 0; u8 filter_mode; - int err; __mdb_entry_to_br_ip(entry, &group, mdb_attrs); @@ -892,13 +891,9 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, return -EINVAL; } - mp = br_mdb_ip_get(br, &group); - if (!mp) { - mp = br_multicast_new_group(br, &group); - err = PTR_ERR_OR_ZERO(mp); - if (err) - return err; - } + mp = br_multicast_new_group(br, &group); + if (IS_ERR(mp)) + return PTR_ERR(mp); /* host join */ if (!port) { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index db4f2641d1cd..5e988f0ed2c0 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2669,7 +2669,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge_mcast *brmctx, if (!pmctx || igmpv2) continue; - spin_lock_bh(&brmctx->br->multicast_lock); + spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto unlock_continue; @@ -2717,7 +2717,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge_mcast *brmctx, if (changed) br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: - spin_unlock_bh(&brmctx->br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); } return err; @@ -2807,7 +2807,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge_mcast *brmctx, if (!pmctx || mldv1) continue; - spin_lock_bh(&brmctx->br->multicast_lock); + spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto unlock_continue; @@ -2859,7 +2859,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge_mcast *brmctx, if (changed) br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: - spin_unlock_bh(&brmctx->br->multicast_lock); + spin_unlock(&brmctx->br->multicast_lock); } return err; @@ -4899,9 +4899,9 @@ void br_multicast_get_stats(const struct net_bridge *br, unsigned int start; do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); memcpy(&temp, &cpu_stats->mstats, sizeof(temp)); - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); mcast_stats_add_dir(tdst.igmp_v1queries, temp.igmp_v1queries); mcast_stats_add_dir(tdst.igmp_v2queries, temp.igmp_v2queries); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5aeb3646e74c..4316cc82ae17 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -188,6 +188,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -274,7 +275,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || - nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED))) + nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) || + nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -876,6 +878,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, + [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; @@ -943,6 +946,22 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); + br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); + + if ((p->flags & BR_PORT_MAB) && + (!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) { + NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); + p->flags = old_flags; + return -EINVAL; + } else if (!(p->flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { + struct net_bridge_fdb_flush_desc desc = { + .flags = BIT(BR_FDB_LOCKED), + .flags_mask = BIT(BR_FDB_LOCKED), + .port_ifindex = p->dev->ifindex, + }; + + br_fdb_flush(p->br, &desc); + } changed_mask = old_flags ^ p->flags; @@ -1332,7 +1351,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_FDB_FLUSH]) { struct net_bridge_fdb_flush_desc desc = { - .flags_mask = BR_FDB_STATIC + .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 06e5f6faa431..4c4fda930068 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -251,7 +251,8 @@ enum { BR_FDB_ADDED_BY_EXT_LEARN, BR_FDB_OFFLOADED, BR_FDB_NOTIFY, - BR_FDB_NOTIFY_INACTIVE + BR_FDB_NOTIFY_INACTIVE, + BR_FDB_LOCKED, }; struct net_bridge_fdb_key { @@ -810,7 +811,7 @@ int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, - bool swdev_notify); + bool locked, bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool swdev_notify); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8f3d76c751dd..7eb6fd5bb917 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -71,7 +71,7 @@ bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, } /* Flags that can be offloaded to hardware */ -#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | \ +#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | BR_PORT_MAB | \ BR_MCAST_FLOOD | BR_BCAST_FLOOD | BR_PORT_LOCKED | \ BR_HAIRPIN_MODE | BR_ISOLATED | BR_MULTICAST_TO_UNICAST) @@ -136,6 +136,7 @@ static void br_switchdev_fdb_populate(struct net_bridge *br, item->added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); item->offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); item->is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); + item->locked = false; item->info.dev = (!p || item->is_local) ? br->dev : p->dev; item->info.ctx = ctx; } @@ -146,6 +147,9 @@ br_switchdev_fdb_notify(struct net_bridge *br, { struct switchdev_notifier_fdb_info item; + if (test_bit(BR_FDB_LOCKED, &fdb->flags)) + return; + br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 612e367fff20..ea733542244c 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -345,7 +345,7 @@ static int set_flush(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct net_bridge_fdb_flush_desc desc = { - .flags_mask = BR_FDB_STATIC + .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 6e53dc991409..bc75fa1e4666 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -959,6 +959,8 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; @@ -973,8 +975,11 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, /* Delete VLANs for the old proto from the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); - list_for_each_entry(vlan, &vg->vlan_list, vlist) + list_for_each_entry(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; vlan_vid_del(p->dev, oldproto, vlan->vid); + } } return 0; @@ -983,13 +988,19 @@ err_filt: attr.u.vlan_protocol = ntohs(oldproto); switchdev_port_attr_set(br->dev, &attr, NULL); - list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) + list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; vlan_vid_del(p->dev, proto, vlan->vid); + } list_for_each_entry_continue_reverse(p, &br->port_list, list) { vg = nbp_vlan_group(p); - list_for_each_entry(vlan, &vg->vlan_list, vlist) + list_for_each_entry(vlan, &vg->vlan_list, vlist) { + if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) + continue; vlan_vid_del(p->dev, proto, vlan->vid); + } } return err; @@ -1378,12 +1389,12 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, cpu_stats = per_cpu_ptr(v->stats, i); do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); rxpackets = u64_stats_read(&cpu_stats->rx_packets); rxbytes = u64_stats_read(&cpu_stats->rx_bytes); txbytes = u64_stats_read(&cpu_stats->tx_bytes); txpackets = u64_stats_read(&cpu_stats->tx_packets); - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rxpackets); u64_stats_add(&stats->rx_bytes, rxbytes); diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 4d63ef13a1fd..f35fc87c453a 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -310,9 +310,6 @@ static int chnl_net_open(struct net_device *dev) if (result == 0) { pr_debug("connect timeout\n"); - caif_disconnect_client(dev_net(dev), &priv->chnl); - priv->state = CAIF_DISCONNECTED; - pr_debug("state disconnected\n"); result = -ETIMEDOUT; goto error; } diff --git a/net/can/af_can.c b/net/can/af_can.c index 9503ab10f9b8..27dcdcc0b808 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -450,7 +450,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, /* insert new receiver (dev,canid,mask) -> (func,data) */ - if (dev && dev->type != ARPHRD_CAN) + if (dev && (dev->type != ARPHRD_CAN || !can_get_ml_priv(dev))) return -ENODEV; if (dev && !net_eq(net, dev_net(dev))) @@ -902,6 +902,7 @@ out_pernet: static __exit void can_exit(void) { /* protocol unregister */ + dev_remove_pack(&canxl_packet); dev_remove_pack(&canfd_packet); dev_remove_pack(&can_packet); sock_unregister(PF_CAN); diff --git a/net/can/isotp.c b/net/can/isotp.c index a9d1357f8489..608f8c24ae46 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -111,6 +111,9 @@ MODULE_ALIAS("can-proto-6"); #define ISOTP_FC_WT 1 /* wait */ #define ISOTP_FC_OVFLW 2 /* overflow */ +#define ISOTP_FC_TIMEOUT 1 /* 1 sec */ +#define ISOTP_ECHO_TIMEOUT 2 /* 2 secs */ + enum { ISOTP_IDLE = 0, ISOTP_WAIT_FIRST_FC, @@ -258,7 +261,8 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) so->lastrxcf_tstamp = ktime_set(0, 0); /* start rx timeout watchdog */ - hrtimer_start(&so->rxtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), + HRTIMER_MODE_REL_SOFT); return 0; } @@ -344,6 +348,8 @@ static int check_pad(struct isotp_sock *so, struct canfd_frame *cf, return 0; } +static void isotp_send_cframe(struct isotp_sock *so); + static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) { struct sock *sk = &so->sk; @@ -398,14 +404,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) case ISOTP_FC_CTS: so->tx.bs = 0; so->tx.state = ISOTP_SENDING; - /* start cyclic timer for sending CF frame */ - hrtimer_start(&so->txtimer, so->tx_gap, + /* send CF frame and enable echo timeout handling */ + hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); + isotp_send_cframe(so); break; case ISOTP_FC_WT: /* start timer to wait for next FC frame */ - hrtimer_start(&so->txtimer, ktime_set(1, 0), + hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); break; @@ -600,7 +607,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* perform blocksize handling, if enabled */ if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) { /* start rx timeout watchdog */ - hrtimer_start(&so->rxtimer, ktime_set(1, 0), + hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } @@ -829,7 +836,7 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf = (struct canfd_frame *)skb->data; - /* only handle my own local echo skb's */ + /* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk || so->cfecho != *(u32 *)cf->data) return; @@ -849,13 +856,16 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { /* stop and wait for FC with timeout */ so->tx.state = ISOTP_WAIT_FC; - hrtimer_start(&so->txtimer, ktime_set(1, 0), + hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return; } /* no gap between data frames needed => use burst mode */ if (!so->tx_gap) { + /* enable echo timeout handling */ + hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); return; } @@ -879,7 +889,7 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) /* start timeout for unlikely lost echo skb */ hrtimer_set_expires(&so->txtimer, ktime_add(ktime_get(), - ktime_set(2, 0))); + ktime_set(ISOTP_ECHO_TIMEOUT, 0))); restart = HRTIMER_RESTART; /* push out the next consecutive frame */ @@ -907,7 +917,8 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) break; default: - WARN_ON_ONCE(1); + WARN_ONCE(1, "can-isotp: tx timer state %08X cfecho %08X\n", + so->tx.state, so->cfecho); } return restart; @@ -923,7 +934,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; - s64 hrtimer_sec = 0; + s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT; int off; int err; @@ -942,6 +953,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_out; + + so->tx.state = ISOTP_SENDING; } if (!size || size > MAX_MSG_LENGTH) { @@ -986,6 +999,10 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); + /* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ + if (so->cfecho) + pr_notice_once("can-isotp: uninit cfecho %08X\n", so->cfecho); + /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { /* The message size generally fits into a SingleFrame - good. @@ -1011,11 +1028,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) else cf->data[ae] |= size; - so->tx.state = ISOTP_IDLE; - wake_up_interruptible(&so->wait); - - /* don't enable wait queue for a single frame transmission */ - wait_tx_done = 0; + /* set CF echo tag for isotp_rcv_echo() (SF-mode) */ + so->cfecho = *(u32 *)cf->data; } else { /* send first frame */ @@ -1031,31 +1045,23 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* disable wait for FCs due to activated block size */ so->txfc.bs = 0; - /* cfecho should have been zero'ed by init */ - if (so->cfecho) - pr_notice_once("can-isotp: no fc cfecho %08X\n", - so->cfecho); - - /* set consecutive frame echo tag */ + /* set CF echo tag for isotp_rcv_echo() (CF-mode) */ so->cfecho = *(u32 *)cf->data; - - /* switch directly to ISOTP_SENDING state */ - so->tx.state = ISOTP_SENDING; - - /* start timeout for unlikely lost echo skb */ - hrtimer_sec = 2; } else { /* standard flow control check */ so->tx.state = ISOTP_WAIT_FIRST_FC; /* start timeout for FC */ - hrtimer_sec = 1; - } + hrtimer_sec = ISOTP_FC_TIMEOUT; - hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), - HRTIMER_MODE_REL_SOFT); + /* no CF echo tag for isotp_rcv_echo() (FF-mode) */ + so->cfecho = 0; + } } + hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + HRTIMER_MODE_REL_SOFT); + /* send the first or only CAN frame */ cf->flags = so->ll.tx_flags; @@ -1068,8 +1074,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) __func__, ERR_PTR(err)); /* no transmission -> no timeout monitoring */ - if (hrtimer_sec) - hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->txtimer); /* reset consecutive frame echo tag */ so->cfecho = 0; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 144c86b0e3ff..821d4ff303b3 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -336,6 +336,9 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) /* re-claim the CAN_HDR from the SKB */ cf = skb_push(skb, J1939_CAN_HDR); + /* initialize header structure */ + memset(cf, 0, J1939_CAN_HDR); + /* make it a full can frame again */ skb_put(skb, J1939_CAN_FTR + (8 - dlc)); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index d7d86c944d76..f26f4cfa9e63 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -342,10 +342,12 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) __skb_unlink(do_skb, &session->skb_queue); /* drop ref taken in j1939_session_skb_queue() */ skb_unref(do_skb); + spin_unlock_irqrestore(&session->skb_queue.lock, flags); kfree_skb(do_skb); + } else { + spin_unlock_irqrestore(&session->skb_queue.lock, flags); } - spin_unlock_irqrestore(&session->skb_queue.lock, flags); } void j1939_session_skb_queue(struct j1939_session *session, @@ -985,7 +987,7 @@ static int j1939_session_tx_eoma(struct j1939_session *session) /* wait for the EOMA packet to come in */ j1939_tp_set_rxtimeout(session, 1250); - netdev_dbg(session->priv->ndev, "%p: 0x%p\n", __func__, session); + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); return 0; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 6a6898ee4049..db60217f911b 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -222,7 +222,7 @@ static void pick_new_mon(struct ceph_mon_client *monc) max--; } - n = prandom_u32() % max; + n = prandom_u32_max(max); if (o >= 0 && n >= o) n++; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 87b883c7bfd6..4e4f1e4bc265 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1479,7 +1479,7 @@ static bool target_should_be_paused(struct ceph_osd_client *osdc, static int pick_random_replica(const struct ceph_osds *acting) { - int i = prandom_u32() % acting->size; + int i = prandom_u32_max(acting->size); dout("%s picked osd%d, primary osd%d\n", __func__, acting->osds[i], acting->primary); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 94374d529ea4..9d2288c0736e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -48,10 +48,8 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { - struct bpf_local_storage_elem *selem; struct bpf_local_storage *sk_storage; bool free_sk_storage = false; - struct hlist_node *n; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); @@ -60,24 +58,8 @@ void bpf_sk_storage_free(struct sock *sk) return; } - /* Netiher the bpf_prog nor the bpf-map's syscall - * could be modifying the sk_storage->list now. - * Thus, no elem can be added-to or deleted-from the - * sk_storage->list by the bpf_prog or by the bpf-map's syscall. - * - * It is racing with bpf_local_storage_map_free() alone - * when unlinking elem from the sk_storage->list and - * the map's bucket->list. - */ raw_spin_lock_bh(&sk_storage->lock); - hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) { - /* Always unlink from map before unlinking from - * sk_storage. - */ - bpf_selem_unlink_map(selem); - free_sk_storage = bpf_selem_unlink_storage_nolock( - sk_storage, selem, true, false); - } + free_sk_storage = bpf_local_storage_unlink_nolock(sk_storage); raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); @@ -87,23 +69,12 @@ void bpf_sk_storage_free(struct sock *sk) static void bpf_sk_storage_map_free(struct bpf_map *map) { - struct bpf_local_storage_map *smap; - - smap = (struct bpf_local_storage_map *)map; - bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); - bpf_local_storage_map_free(smap, NULL); + bpf_local_storage_map_free(map, &sk_cache, NULL); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { - struct bpf_local_storage_map *smap; - - smap = bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); - - smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); - return &smap->map; + return bpf_local_storage_map_alloc(attr, &sk_cache); } static int notsupp_get_next_key(struct bpf_map *map, void *key, @@ -176,7 +147,7 @@ bpf_sk_storage_clone_elem(struct sock *newsk, if (!copy_selem) return NULL; - if (map_value_has_spin_lock(&smap->map)) + if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data, true); else @@ -595,7 +566,7 @@ static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) if (!nla_value) goto errout; - if (map_value_has_spin_lock(&smap->map)) + if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, nla_data(nla_value), sdata->data, true); else diff --git a/net/core/dev.c b/net/core/dev.c index fa53830d0683..7627c475d991 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1163,22 +1163,6 @@ int dev_change_name(struct net_device *dev, const char *newname) net = dev_net(dev); - /* Some auto-enslaved devices e.g. failover slaves are - * special, as userspace might rename the device after - * the interface had been brought up and running since - * the point kernel initiated auto-enslavement. Allow - * live name change even when these slave devices are - * up and running. - * - * Typically, users of these auto-enslaving devices - * don't actually care about slave name change, as - * they are supposed to operate on master interface - * directly. - */ - if (dev->flags & IFF_UP && - likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) - return -EBUSY; - down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { @@ -1195,7 +1179,8 @@ int dev_change_name(struct net_device *dev, const char *newname) } if (oldname[0] && !strchr(oldname, '%')) - netdev_info(dev, "renamed from %s\n", oldname); + netdev_info(dev, "renamed from %s%s\n", oldname, + dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; dev->name_assign_type = NET_NAME_RENAMED; @@ -1333,7 +1318,7 @@ void netdev_state_change(struct net_device *dev) call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); - rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL); } } EXPORT_SYMBOL(netdev_state_change); @@ -1469,7 +1454,7 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) if (ret < 0) return ret; - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; @@ -1541,7 +1526,7 @@ void dev_close_many(struct list_head *head, bool unlink) __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); @@ -1621,10 +1606,10 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) - N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) - N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) - N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) - N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) + N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) + N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) + N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) + N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) @@ -1876,6 +1861,22 @@ int unregister_netdevice_notifier_net(struct net *net, } EXPORT_SYMBOL(unregister_netdevice_notifier_net); +static void __move_netdevice_notifier_net(struct net *src_net, + struct net *dst_net, + struct notifier_block *nb) +{ + __unregister_netdevice_notifier_net(src_net, nb); + __register_netdevice_notifier_net(dst_net, nb, true); +} + +void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, + struct notifier_block *nb) +{ + rtnl_lock(); + __move_netdevice_notifier_net(src_net, dst_net, nb); + rtnl_unlock(); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -1912,10 +1913,8 @@ static void move_netdevice_notifiers_dev_net(struct net_device *dev, { struct netdev_net_notifier *nn; - list_for_each_entry(nn, &dev->net_notifier_list, list) { - __unregister_netdevice_notifier_net(dev_net(dev), nn->nb); - __register_netdevice_notifier_net(net, nn->nb, true); - } + list_for_each_entry(nn, &dev->net_notifier_list, list) + __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** @@ -2074,13 +2073,10 @@ static DECLARE_WORK(netstamp_work, netstamp_clear); void net_enable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL - int wanted; + int wanted = atomic_read(&netstamp_wanted); - while (1) { - wanted = atomic_read(&netstamp_wanted); - if (wanted <= 0) - break; - if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted) + while (wanted > 0) { + if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1)) return; } atomic_inc(&netstamp_needed_deferred); @@ -2094,13 +2090,10 @@ EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL - int wanted; + int wanted = atomic_read(&netstamp_wanted); - while (1) { - wanted = atomic_read(&netstamp_wanted); - if (wanted <= 1) - break; - if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted) + while (wanted > 1) { + if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1)) return; } atomic_dec(&netstamp_needed_deferred); @@ -5136,11 +5129,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); + *ret = NET_RX_DROP; return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_REDIRECT: /* skb_mac_header check was done by cls/act_bpf, so @@ -5153,8 +5148,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, *another = true; break; } + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_CONSUMED: + *ret = NET_RX_SUCCESS; return NULL; default: break; @@ -5982,10 +5979,9 @@ EXPORT_SYMBOL(__napi_schedule); */ bool napi_schedule_prep(struct napi_struct *n) { - unsigned long val, new; + unsigned long new, val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); if (unlikely(val & NAPIF_STATE_DISABLE)) return false; new = val | NAPIF_STATE_SCHED; @@ -5998,7 +5994,7 @@ bool napi_schedule_prep(struct napi_struct *n) */ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * NAPIF_STATE_MISSED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); return !(val & NAPIF_STATE_SCHED); } @@ -6066,9 +6062,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) local_irq_restore(flags); } + val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); - WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | @@ -6081,7 +6076,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) */ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * NAPIF_STATE_SCHED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); if (unlikely(val & NAPIF_STATE_MISSED)) { __napi_schedule(n); @@ -6402,19 +6397,16 @@ void napi_disable(struct napi_struct *n) might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); - for ( ; ; ) { - val = READ_ONCE(n->state); - if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { + val = READ_ONCE(n->state); + do { + while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); - continue; + val = READ_ONCE(n->state); } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); - - if (cmpxchg(&n->state, val, new) == val) - break; - } + } while (!try_cmpxchg(&n->state, &val, new)); hrtimer_cancel(&n->timer); @@ -6431,16 +6423,15 @@ EXPORT_SYMBOL(napi_disable); */ void napi_enable(struct napi_struct *n) { - unsigned long val, new; + unsigned long new, val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); if (n->dev->threaded && n->thread) new |= NAPIF_STATE_THREADED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); } EXPORT_SYMBOL(napi_enable); @@ -8347,7 +8338,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) - __dev_notify_flags(dev, old_flags, IFF_PROMISC); + __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); return 0; } @@ -8402,7 +8393,7 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, - dev->gflags ^ old_gflags); + dev->gflags ^ old_gflags, 0, NULL); } return 0; } @@ -8565,12 +8556,13 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags, } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, - unsigned int gchanges) + unsigned int gchanges, u32 portid, + const struct nlmsghdr *nlh) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) - rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); + rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh); if (changes & IFF_UP) { if (dev->flags & IFF_UP) @@ -8612,7 +8604,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); - __dev_notify_flags(dev, old_flags, changes); + __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } EXPORT_SYMBOL(dev_change_flags); @@ -8818,7 +8810,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; @@ -10055,7 +10047,7 @@ int register_netdevice(struct net_device *dev) dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; write_unlock(&dev_base_lock); if (ret) - goto err_uninit; + goto err_uninit_notify; __netdev_update_features(dev); @@ -10097,11 +10089,13 @@ int register_netdevice(struct net_device *dev) */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); out: return ret; +err_uninit_notify: + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10375,24 +10369,16 @@ void netdev_run_todo(void) void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { -#if BITS_PER_LONG == 64 - BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); - memcpy(stats64, netdev_stats, sizeof(*netdev_stats)); - /* zero out counters that only exist in rtnl_link_stats64 */ - memset((char *)stats64 + sizeof(*netdev_stats), 0, - sizeof(*stats64) - sizeof(*netdev_stats)); -#else - size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long); - const unsigned long *src = (const unsigned long *)netdev_stats; + size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); + const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = src[i]; + dst[i] = atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); -#endif } EXPORT_SYMBOL(netdev_stats_to_stats64); @@ -10473,12 +10459,12 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, stats = per_cpu_ptr(netstats, cpu); do { - start = u64_stats_fetch_begin_irq(&stats->syncp); + start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; @@ -10776,14 +10762,8 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) } EXPORT_SYMBOL(unregister_netdevice_queue); -/** - * unregister_netdevice_many - unregister many devices - * @head: list of devices - * - * Note: As most callers use a stack allocated list_head, - * we force a list_del() to make sure stack wont be corrupted later. - */ -void unregister_netdevice_many(struct list_head *head) +void unregister_netdevice_many_notify(struct list_head *head, + u32 portid, const struct nlmsghdr *nlh) { struct net_device *dev, *tmp; LIST_HEAD(close_head); @@ -10845,7 +10825,8 @@ void unregister_netdevice_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL, NULL, 0); + GFP_KERNEL, NULL, 0, + portid, nlmsg_seq(nlh)); /* * Flush the unicast and multicast chains @@ -10856,11 +10837,13 @@ void unregister_netdevice_many(struct list_head *head) netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); + if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (skb) - rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); @@ -10883,6 +10866,18 @@ void unregister_netdevice_many(struct list_head *head) list_del(head); } + +/** + * unregister_netdevice_many - unregister many devices + * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. + */ +void unregister_netdevice_many(struct list_head *head) +{ + unregister_netdevice_many_notify(head, 0, NULL); +} EXPORT_SYMBOL(unregister_netdevice_many); /** @@ -11038,7 +11033,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); synchronize_net(); err = 0; diff --git a/net/core/dev.h b/net/core/dev.h index cbb8a925175a..814ed5b7b960 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -88,6 +88,13 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier); void __dev_set_rx_mode(struct net_device *dev); +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, + unsigned int gchanges, u32 portid, + const struct nlmsghdr *nlh); + +void unregister_netdevice_many_notify(struct list_head *head, + u32 portid, const struct nlmsghdr *nlh); + static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 7674bb9f3076..5cdbfbf9a7dc 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -342,7 +342,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data), + min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return 0; diff --git a/net/core/devlink.c b/net/core/devlink.c index 89baa7c0938b..0e10a8a68c5e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -71,6 +71,7 @@ struct devlink { refcount_t refcount; struct completion comp; struct rcu_head rcu; + struct notifier_block netdevice_nb; char priv[] __aligned(NETDEV_ALIGN); }; @@ -769,7 +770,7 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) #define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) #define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) -static int devlink_nl_pre_doit(const struct genl_ops *ops, +static int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct devlink_linecard *linecard; @@ -827,7 +828,7 @@ unlock: return err; } -static void devlink_nl_post_doit(const struct genl_ops *ops, +static void devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct devlink_linecard *linecard; @@ -879,6 +880,24 @@ nla_put_failure: return -EMSGSIZE; } +int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) +{ + if (devlink_nl_put_handle(msg, devlink_port->devlink)) + return -EMSGSIZE; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + return -EMSGSIZE; + return 0; +} + +size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) +{ + struct devlink *devlink = devlink_port->devlink; + + return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */ + + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */ + + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ +} + struct devlink_reload_combination { enum devlink_reload_action action; enum devlink_reload_limit limit; @@ -1184,6 +1203,14 @@ static int devlink_nl_rate_fill(struct sk_buff *msg, devlink_rate->tx_max, DEVLINK_ATTR_PAD)) goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY, + devlink_rate->tx_priority)) + goto nla_put_failure; + + if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_WEIGHT, + devlink_rate->tx_weight)) + goto nla_put_failure; + if (devlink_rate->parent) if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, devlink_rate->parent->name)) @@ -1292,8 +1319,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; - /* Hold rtnl lock while accessing port's netdev attributes. */ - rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -1302,18 +1327,15 @@ static int devlink_nl_port_fill(struct sk_buff *msg, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { - struct net *net = devlink_net(devlink_port->devlink); - struct net_device *netdev = devlink_port->type_dev; - - if (netdev && net_eq(net, dev_net(netdev)) && + if (devlink_port->type_eth.netdev && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, - netdev->ifindex) || + devlink_port->type_eth.ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, - netdev->name))) + devlink_port->type_eth.ifname))) goto nla_put_failure_type_locked; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { - struct ib_device *ibdev = devlink_port->type_dev; + struct ib_device *ibdev = devlink_port->type_ib.ibdev; if (ibdev && nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, @@ -1321,7 +1343,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); - rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) @@ -1336,7 +1357,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); - rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -1867,10 +1887,8 @@ devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, int err = -EOPNOTSUPP; parent = devlink_rate->parent; - if (parent && len) { - NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent."); - return -EBUSY; - } else if (parent && !len) { + + if (parent && !len) { if (devlink_rate_is_leaf(devlink_rate)) err = ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, @@ -1884,7 +1902,7 @@ devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, refcount_dec(&parent->refcnt); devlink_rate->parent = NULL; - } else if (!parent && len) { + } else if (len) { parent = devlink_rate_node_get_by_name(devlink, parent_name); if (IS_ERR(parent)) return -ENODEV; @@ -1911,6 +1929,10 @@ devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, if (err) return err; + if (devlink_rate->parent) + /* we're reassigning to other parent in this case */ + refcount_dec(&devlink_rate->parent->refcnt); + refcount_inc(&parent->refcnt); devlink_rate->parent = parent; } @@ -1924,6 +1946,8 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, { struct nlattr *nla_parent, **attrs = info->attrs; int err = -EOPNOTSUPP; + u32 priority; + u32 weight; u64 rate; if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { @@ -1952,6 +1976,34 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, devlink_rate->tx_max = rate; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]) { + priority = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_priority_set(devlink_rate, devlink_rate->priv, + priority, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_priority_set(devlink_rate, devlink_rate->priv, + priority, info->extack); + + if (err) + return err; + devlink_rate->tx_priority = priority; + } + + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]) { + weight = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_weight_set(devlink_rate, devlink_rate->priv, + weight, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_weight_set(devlink_rate, devlink_rate->priv, + weight, info->extack); + + if (err) + return err; + devlink_rate->tx_weight = weight; + } + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; if (nla_parent) { err = devlink_nl_rate_parent_node_set(devlink_rate, info, @@ -1983,6 +2035,18 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_leaf_tx_priority_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_PRIORITY], + "TX priority set isn't supported for the leafs"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_leaf_tx_weight_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_WEIGHT], + "TX weight set isn't supported for the leafs"); + return false; + } } else if (type == DEVLINK_RATE_TYPE_NODE) { if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); @@ -1997,6 +2061,18 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_node_tx_priority_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_PRIORITY], + "TX priority set isn't supported for the nodes"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_node_tx_weight_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_WEIGHT], + "TX weight set isn't supported for the nodes"); + return false; + } } else { WARN(1, "Unknown type of rate object"); return false; @@ -4490,8 +4566,11 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, if (err) return err; - if (dest_net && !net_eq(dest_net, curr_net)) + if (dest_net && !net_eq(dest_net, curr_net)) { + move_netdevice_notifier_net(curr_net, dest_net, + &devlink->netdevice_nb); write_pnet(&devlink->_net, dest_net); + } err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); @@ -7767,8 +7846,6 @@ int devlink_health_report(struct devlink_health_reporter *reporter, return -ECANCELED; } - reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; - if (reporter->auto_dump) { mutex_lock(&reporter->dump_lock); /* store current dump of current error, for later analysis */ @@ -8304,10 +8381,10 @@ static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, cpu_stats = per_cpu_ptr(trap_stats, i); do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); rx_packets = u64_stats_read(&cpu_stats->rx_packets); rx_bytes = u64_stats_read(&cpu_stats->rx_bytes); - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rx_packets); u64_stats_add(&stats->rx_bytes, rx_bytes); @@ -9172,6 +9249,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -9602,6 +9681,9 @@ void devlink_set_features(struct devlink *devlink, u64 features) } EXPORT_SYMBOL_GPL(devlink_set_features); +static int devlink_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr); + /** * devlink_alloc_ns - Allocate new devlink instance resources * in specific namespace @@ -9632,10 +9714,13 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, &last_id, GFP_KERNEL); - if (ret < 0) { - kfree(devlink); - return NULL; - } + if (ret < 0) + goto err_xa_alloc; + + devlink->netdevice_nb.notifier_call = devlink_netdevice_event; + ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + if (ret) + goto err_register_netdevice_notifier; devlink->dev = dev; devlink->ops = ops; @@ -9662,6 +9747,12 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, init_completion(&devlink->comp); return devlink; + +err_register_netdevice_notifier: + xa_erase(&devlinks, devlink->index); +err_xa_alloc: + kfree(devlink); + return NULL; } EXPORT_SYMBOL_GPL(devlink_alloc_ns); @@ -9815,6 +9906,10 @@ void devlink_free(struct devlink *devlink) WARN_ON(!list_empty(&devlink->port_list)); xa_destroy(&devlink->snapshot_ids); + + WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), + &devlink->netdevice_nb)); + xa_erase(&devlinks, devlink->index); kfree(devlink); @@ -9967,6 +10062,7 @@ EXPORT_SYMBOL_GPL(devlink_port_register); void devl_port_unregister(struct devlink_port *devlink_port) { lockdep_assert_held(&devlink_port->devlink->lock); + WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); @@ -9994,20 +10090,6 @@ void devlink_port_unregister(struct devlink_port *devlink_port) } EXPORT_SYMBOL_GPL(devlink_port_unregister); -static void __devlink_port_type_set(struct devlink_port *devlink_port, - enum devlink_port_type type, - void *type_dev) -{ - ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); - - devlink_port_type_warn_cancel(devlink_port); - spin_lock_bh(&devlink_port->type_lock); - devlink_port->type = type; - devlink_port->type_dev = type_dev; - spin_unlock_bh(&devlink_port->type_lock); - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); -} - static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, struct net_device *netdev) { @@ -10045,23 +10127,58 @@ static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, } } +static void __devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type type, + void *type_dev) +{ + struct net_device *netdev = type_dev; + + ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); + + if (type == DEVLINK_PORT_TYPE_NOTSET) { + devlink_port_type_warn_schedule(devlink_port); + } else { + devlink_port_type_warn_cancel(devlink_port); + if (type == DEVLINK_PORT_TYPE_ETH && netdev) + devlink_port_type_netdev_checks(devlink_port, netdev); + } + + spin_lock_bh(&devlink_port->type_lock); + devlink_port->type = type; + switch (type) { + case DEVLINK_PORT_TYPE_ETH: + devlink_port->type_eth.netdev = netdev; + if (netdev) { + ASSERT_RTNL(); + devlink_port->type_eth.ifindex = netdev->ifindex; + BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) != + sizeof(netdev->name)); + strcpy(devlink_port->type_eth.ifname, netdev->name); + } + break; + case DEVLINK_PORT_TYPE_IB: + devlink_port->type_ib.ibdev = type_dev; + break; + default: + break; + } + spin_unlock_bh(&devlink_port->type_lock); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} + /** * devlink_port_type_eth_set - Set port type to Ethernet * * @devlink_port: devlink port - * @netdev: related netdevice + * + * If driver is calling this, most likely it is doing something wrong. */ -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) +void devlink_port_type_eth_set(struct devlink_port *devlink_port) { - if (netdev) - devlink_port_type_netdev_checks(devlink_port, netdev); - else - dev_warn(devlink_port->devlink->dev, - "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", - devlink_port->index); - - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); @@ -10082,14 +10199,71 @@ EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); * devlink_port_type_clear - Clear port type * * @devlink_port: devlink port + * + * If driver is calling this for clearing Ethernet type, most likely + * it is doing something wrong. */ void devlink_port_type_clear(struct devlink_port *devlink_port) { + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); - devlink_port_type_warn_schedule(devlink_port); } EXPORT_SYMBOL_GPL(devlink_port_type_clear); +static int devlink_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct devlink_port *devlink_port = netdev->devlink_port; + struct devlink *devlink; + + devlink = container_of(nb, struct devlink, netdevice_nb); + + if (!devlink_port || devlink_port->devlink != devlink) + return NOTIFY_OK; + + switch (event) { + case NETDEV_POST_INIT: + /* Set the type but not netdev pointer. It is going to be set + * later on by NETDEV_REGISTER event. Happens once during + * netdevice register + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, + NULL); + break; + case NETDEV_REGISTER: + case NETDEV_CHANGENAME: + /* Set the netdev on top of previously set type. Note this + * event happens also during net namespace change so here + * we take into account netdev pointer appearing in this + * namespace. + */ + __devlink_port_type_set(devlink_port, devlink_port->type, + netdev); + break; + case NETDEV_UNREGISTER: + /* Clear netdev pointer, but not the type. This event happens + * also during net namespace change so we need to clear + * pointer to netdev that is going to another net namespace. + */ + __devlink_port_type_set(devlink_port, devlink_port->type, + NULL); + break; + case NETDEV_PRE_UNINIT: + /* Clear the type and the netdev pointer. Happens one during + * netdevice unregister. + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, + NULL); + break; + } + + return NOTIFY_OK; +} + static int __devlink_port_attrs_set(struct devlink_port *devlink_port, enum devlink_port_flavour flavour) { @@ -10211,13 +10385,60 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); /** + * devl_rate_node_create - create devlink rate node + * @devlink: devlink instance + * @priv: driver private data + * @node_name: name of the resulting node + * @parent: parent devlink_rate struct + * + * Create devlink rate object of type node + */ +struct devlink_rate * +devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name, + struct devlink_rate *parent) +{ + struct devlink_rate *rate_node; + + rate_node = devlink_rate_node_get_by_name(devlink, node_name); + if (!IS_ERR(rate_node)) + return ERR_PTR(-EEXIST); + + rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL); + if (!rate_node) + return ERR_PTR(-ENOMEM); + + if (parent) { + rate_node->parent = parent; + refcount_inc(&rate_node->parent->refcnt); + } + + rate_node->type = DEVLINK_RATE_TYPE_NODE; + rate_node->devlink = devlink; + rate_node->priv = priv; + + rate_node->name = kstrdup(node_name, GFP_KERNEL); + if (!rate_node->name) { + kfree(rate_node); + return ERR_PTR(-ENOMEM); + } + + refcount_set(&rate_node->refcnt, 1); + list_add(&rate_node->list, &devlink->rate_list); + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + return rate_node; +} +EXPORT_SYMBOL_GPL(devl_rate_node_create); + +/** * devl_rate_leaf_create - create devlink rate leaf * @devlink_port: devlink port object to create rate object on * @priv: driver private data + * @parent: parent devlink_rate struct * * Create devlink rate object of type leaf on provided @devlink_port. */ -int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv) +int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv, + struct devlink_rate *parent) { struct devlink *devlink = devlink_port->devlink; struct devlink_rate *devlink_rate; @@ -10231,6 +10452,11 @@ int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv) if (!devlink_rate) return -ENOMEM; + if (parent) { + devlink_rate->parent = parent; + refcount_inc(&devlink_rate->parent->refcnt); + } + devlink_rate->type = DEVLINK_RATE_TYPE_LEAF; devlink_rate->devlink = devlink; devlink_rate->devlink_port = devlink_port; @@ -11624,6 +11850,8 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(ESP_PARSING, DROP), DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), DEVLINK_TRAP(DMAC_FILTER, DROP), + DEVLINK_TRAP(EAPOL, CONTROL), + DEVLINK_TRAP(LOCKED_PORT, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -11659,6 +11887,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(ACL_SAMPLE), DEVLINK_TRAP_GROUP(ACL_TRAP), DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), + DEVLINK_TRAP_GROUP(EAPOL), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) @@ -12016,7 +12245,7 @@ devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) - metadata->input_dev = in_devlink_port->type_dev; + metadata->input_dev = in_devlink_port->type_eth.netdev; spin_unlock(&in_devlink_port->type_lock); } @@ -12416,14 +12645,6 @@ free_msg: nlmsg_free(msg); } -static struct devlink_port *netdev_to_devlink_port(struct net_device *dev) -{ - if (!dev->netdev_ops->ndo_get_devlink_port) - return NULL; - - return dev->netdev_ops->ndo_get_devlink_port(dev); -} - void devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len) { @@ -12469,7 +12690,7 @@ int devlink_compat_phys_port_name_get(struct net_device *dev, */ ASSERT_RTNL(); - devlink_port = netdev_to_devlink_port(dev); + devlink_port = dev->devlink_port; if (!devlink_port) return -EOPNOTSUPP; @@ -12485,7 +12706,7 @@ int devlink_compat_switch_id_get(struct net_device *dev, * devlink_port instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ - devlink_port = netdev_to_devlink_port(dev); + devlink_port = dev->devlink_port; if (!devlink_port || !devlink_port->switch_port) return -EOPNOTSUPP; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index f084a4a6b7ab..5a782d1d8fd3 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1432,9 +1432,9 @@ static void net_dm_stats_read(struct net_dm_stats *stats) u64 dropped; do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } @@ -1476,9 +1476,9 @@ static void net_dm_hw_stats_read(struct net_dm_stats *stats) u64 dropped; do { - start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } @@ -1620,7 +1620,7 @@ static const struct genl_small_ops dropmon_ops[] = { }, }; -static int net_dm_nl_pre_doit(const struct genl_ops *ops, +static int net_dm_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_lock(&net_dm_mutex); @@ -1628,7 +1628,7 @@ static int net_dm_nl_pre_doit(const struct genl_ops *ops, return 0; } -static void net_dm_nl_post_doit(const struct genl_ops *ops, +static void net_dm_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_unlock(&net_dm_mutex); diff --git a/net/core/failover.c b/net/core/failover.c index 864d2d83eff4..655411c4ca51 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev) goto err_upper_link; } - slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; err_upper_link: netdev_rx_handler_unregister(slave_dev); done: @@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev) netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) diff --git a/net/core/filter.c b/net/core/filter.c index bb0136e7a8e4..37baaa6b8fc3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -325,11 +325,11 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: - *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET); - if (PKT_VLAN_PRESENT_BIT) - *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_all) != 4); + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, vlan_all)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); + *insn++ = BPF_ALU32_IMM(BPF_MOV, dst_reg, 1); break; } @@ -2124,6 +2124,11 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, { unsigned int mlen = skb_network_offset(skb); + if (unlikely(skb->len <= mlen)) { + kfree_skb(skb); + return -ERANGE; + } + if (mlen) { __skb_pull(skb, mlen); @@ -2145,7 +2150,7 @@ static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { /* Verify that a link layer header is carried */ - if (unlikely(skb->mac_header >= skb->network_header)) { + if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) { kfree_skb(skb); return -ERANGE; } @@ -4104,7 +4109,10 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .arg2_type = ARG_ANYTHING, }; -/* XDP_REDIRECT works by a three-step process, implemented in the functions +/** + * DOC: xdp redirect + * + * XDP_REDIRECT works by a three-step process, implemented in the functions * below: * * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target @@ -4119,7 +4127,8 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(), * which will flush all the different bulk queues, thus completing the * redirect. - * + */ +/* * Pointers to the map entries will be kept around for this whole sequence of * steps, protected by RCU. However, there is no top-level rcu_read_lock() in * the core code; instead, the RCU protection relies on everything happening @@ -4410,10 +4419,10 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, +BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key, u64, flags) { - return map->ops->map_redirect(map, ifindex, flags); + return map->ops->map_redirect(map, key, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { @@ -6428,7 +6437,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, else sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, - dif, sdif, &udp_table, NULL); + dif, sdif, net->ipv4.udp_table, NULL); #if IS_ENABLED(CONFIG_IPV6) } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; @@ -6444,7 +6453,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, src6, tuple->ipv6.sport, dst6, tuple->ipv6.dport, dif, sdif, - &udp_table, NULL); + net->ipv4.udp_table, NULL); #endif } @@ -8647,28 +8656,25 @@ static bool tc_cls_act_is_valid_access(int off, int size, DEFINE_MUTEX(nf_conn_btf_access_lock); EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); -int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, u32 *next_btf_id, - enum bpf_type_flag *flag); +int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag); EXPORT_SYMBOL_GPL(nfct_btf_struct_access); static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { int ret = -EACCES; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) - ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag); + ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_unlock(&nf_conn_btf_access_lock); return ret; @@ -8734,21 +8740,18 @@ void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static int xdp_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { int ret = -EACCES; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) - ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag); + ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_unlock(&nf_conn_btf_access_lock); return ret; @@ -8921,6 +8924,10 @@ static bool sock_ops_is_valid_access(int off, int size, bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case offsetof(struct bpf_sock_ops, skb_hwtstamp): + if (size != sizeof(__u64)) + return false; + break; default: if (size != size_default) return false; @@ -9104,21 +9111,21 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, return insn; } -static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, +static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - BPF_REG_AX, si->src_reg, + BPF_REG_AX, skb_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, + dst_reg, skb_reg, offsetof(struct sk_buff, head)); - *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - si->dst_reg, si->src_reg, + dst_reg, skb_reg, offsetof(struct sk_buff, end)); #endif @@ -9290,13 +9297,11 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, vlan_present): - *target_size = 1; - *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, - PKT_VLAN_PRESENT_OFFSET); - if (PKT_VLAN_PRESENT_BIT) - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + bpf_target_off(struct sk_buff, + vlan_all, 4, target_size)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_ALU32_IMM(BPF_MOV, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): @@ -9511,7 +9516,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, gso_segs): - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -9519,7 +9524,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct __sk_buff, gso_size): - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -9546,7 +9551,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -10396,6 +10401,25 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, tcp_flags), si->dst_reg, si->dst_reg, off); break; + case offsetof(struct bpf_sock_ops, skb_hwtstamp): { + struct bpf_insn *jmp_on_null_skb; + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + /* Reserve one insn to test skb == NULL */ + jmp_on_null_skb = insn++; + insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn); + *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + hwtstamps, 8, + target_size)); + *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, + insn - jmp_on_null_skb - 1); + break; + } } return insn - insn_buf; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 25cd35f5922e..25fb0bbc310f 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -296,7 +296,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - key->ct_mark = ct->mark; + key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); @@ -971,12 +971,14 @@ bool __skb_flow_dissect(const struct net *net, #if IS_ENABLED(CONFIG_NET_DSA) if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && proto == htons(ETH_P_XDSA))) { + struct metadata_dst *md_dst = skb_metadata_dst(skb); const struct dsa_device_ops *ops; int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; /* Only DSA header taggers break flow dissection */ - if (ops->needed_headroom) { + if (ops->needed_headroom && + (!md_dst || md_dst->type != METADATA_HW_PORT_MUX)) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index abe423fd5736..acfc1f88ea79 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -97,6 +97,13 @@ void flow_rule_match_cvlan(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_cvlan); +void flow_rule_match_arp(const struct flow_rule *rule, + struct flow_match_arp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ARP, out); +} +EXPORT_SYMBOL(flow_rule_match_arp); + void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out) { diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index c8d137ef5980..b71ccaec0991 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -135,10 +135,10 @@ static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_sync *bstats, u64 bytes, packets; do { - start = u64_stats_fetch_begin_irq(&bcpu->syncp); + start = u64_stats_fetch_begin(&bcpu->syncp); bytes = u64_stats_read(&bcpu->bytes); packets = u64_stats_read(&bcpu->packets); - } while (u64_stats_fetch_retry_irq(&bcpu->syncp, start)); + } while (u64_stats_fetch_retry(&bcpu->syncp, start)); t_bytes += bytes; t_packets += packets; @@ -162,10 +162,10 @@ void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, } do { if (running) - start = u64_stats_fetch_begin_irq(&b->syncp); + start = u64_stats_fetch_begin(&b->syncp); bytes = u64_stats_read(&b->bytes); packets = u64_stats_read(&b->packets); - } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); + } while (running && u64_stats_fetch_retry(&b->syncp, start)); _bstats_update(bstats, bytes, packets); } @@ -187,10 +187,10 @@ static void gnet_stats_read_basic(u64 *ret_bytes, u64 *ret_packets, u64 bytes, packets; do { - start = u64_stats_fetch_begin_irq(&bcpu->syncp); + start = u64_stats_fetch_begin(&bcpu->syncp); bytes = u64_stats_read(&bcpu->bytes); packets = u64_stats_read(&bcpu->packets); - } while (u64_stats_fetch_retry_irq(&bcpu->syncp, start)); + } while (u64_stats_fetch_retry(&bcpu->syncp, start)); t_bytes += bytes; t_packets += packets; @@ -201,10 +201,10 @@ static void gnet_stats_read_basic(u64 *ret_bytes, u64 *ret_packets, } do { if (running) - start = u64_stats_fetch_begin_irq(&b->syncp); + start = u64_stats_fetch_begin(&b->syncp); *ret_bytes = u64_stats_read(&b->bytes); *ret_packets = u64_stats_read(&b->packets); - } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); + } while (running && u64_stats_fetch_retry(&b->syncp, start)); } static int diff --git a/net/core/gro.c b/net/core/gro.c index bc9451743307..fd8c6a7e8d3e 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -370,9 +370,7 @@ static void gro_list_prepare(const struct list_head *head, } diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); - if (skb_vlan_tag_present(p)) - diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); + diffs |= p->vlan_all ^ skb->vlan_all; diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), @@ -489,45 +487,45 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - - skb_set_network_header(skb, skb_gro_offset(skb)); - skb_reset_mac_len(skb); - BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32)); - BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed), - sizeof(u32))); /* Avoid slow unaligned acc */ - *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; - NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->count = 1; - if (unlikely(skb_is_gso(skb))) { - NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; - /* Only support TCP at the moment. */ - if (!skb_is_gso_tcp(skb)) - NAPI_GRO_CB(skb)->flush = 1; - } - - /* Setup for GRO checksum validation */ - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - NAPI_GRO_CB(skb)->csum = skb->csum; - NAPI_GRO_CB(skb)->csum_valid = 1; - break; - case CHECKSUM_UNNECESSARY: - NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - break; - } + if (ptype->type == type && ptype->callbacks.gro_receive) + goto found_ptype; + } + rcu_read_unlock(); + goto normal; + +found_ptype: + skb_set_network_header(skb, skb_gro_offset(skb)); + skb_reset_mac_len(skb); + BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed), + sizeof(u32))); /* Avoid slow unaligned acc */ + *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; + NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb); + NAPI_GRO_CB(skb)->is_atomic = 1; + NAPI_GRO_CB(skb)->count = 1; + if (unlikely(skb_is_gso(skb))) { + NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; + /* Only support TCP at the moment. */ + if (!skb_is_gso_tcp(skb)) + NAPI_GRO_CB(skb)->flush = 1; + } - pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, - ipv6_gro_receive, inet_gro_receive, - &gro_list->list, skb); + /* Setup for GRO checksum validation */ + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + NAPI_GRO_CB(skb)->csum = skb->csum; + NAPI_GRO_CB(skb)->csum_valid = 1; + break; + case CHECKSUM_UNNECESSARY: + NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; break; } - rcu_read_unlock(); - if (&ptype->list == head) - goto normal; + pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, + ipv6_gro_receive, inet_gro_receive, + &gro_list->list, skb); + + rcu_read_unlock(); if (PTR_ERR(pp) == -EINPROGRESS) { ret = GRO_CONSUMED; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index aa6cb1f90966..c469d1c4db5d 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -38,9 +38,23 @@ static unsigned char default_operstate(const struct net_device *dev) if (netif_testing(dev)) return IF_OPER_TESTING; - if (!netif_carrier_ok(dev)) - return (dev->ifindex != dev_get_iflink(dev) ? - IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN); + /* Some uppers (DSA) have additional sources for being down, so + * first check whether lower is indeed the source of its down state. + */ + if (!netif_carrier_ok(dev)) { + int iflink = dev_get_iflink(dev); + struct net_device *peer; + + if (iflink == dev->ifindex) + return IF_OPER_DOWN; + + peer = __dev_get_by_index(dev_net(dev), iflink); + if (!peer) + return IF_OPER_DOWN; + + return netif_carrier_ok(peer) ? IF_OPER_DOWN : + IF_OPER_LOWERLAYERDOWN; + } if (netif_dormant(dev)) return IF_OPER_DORMANT; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 6fac2f0ef074..711cd3b4347a 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -48,9 +48,11 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "RPL"; case LWTUNNEL_ENCAP_IOAM6: return "IOAM6"; + case LWTUNNEL_ENCAP_XFRM: + /* module autoload not supported for encap type */ + return NULL; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: - case LWTUNNEL_ENCAP_XFRM: case LWTUNNEL_ENCAP_NONE: case __LWTUNNEL_ENCAP_MAX: /* should not have got here */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e93edb810103..952a54763358 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -111,7 +111,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (prandom_u32() % base) + (base >> 1) : 0; + return base ? prandom_u32_max(base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -307,7 +307,31 @@ static int neigh_del_timer(struct neighbour *n) return 0; } -static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_parms_qlen_dec(struct net_device *dev, int family) +{ + struct neigh_parms *p; + + rcu_read_lock(); + p = neigh_get_dev_parms_rcu(dev, family); + if (p) + p->qlen--; + rcu_read_unlock(); +} + +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net, + int family) { struct sk_buff_head tmp; unsigned long flags; @@ -321,13 +345,7 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) struct net_device *dev = skb->dev; if (net == NULL || net_eq(dev_net(dev), net)) { - struct in_device *in_dev; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, family); __skb_unlink(skb, list); __skb_queue_tail(&tmp, skb); } @@ -409,7 +427,8 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL, + tbl->family); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; @@ -1621,13 +1640,8 @@ static void neigh_proxy_process(struct timer_list *t) if (tdif <= 0) { struct net_device *dev = skb->dev; - struct in_device *in_dev; - rcu_read_lock(); - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - in_dev->arp_parms->qlen--; - rcu_read_unlock(); + neigh_parms_qlen_dec(dev, tbl->family); __skb_unlink(skb, &tbl->proxy_queue); if (tbl->proxy_redo && netif_running(dev)) { @@ -1821,7 +1835,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue, NULL); + pneigh_queue_purge(&tbl->proxy_queue, NULL, tbl->family); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); @@ -3539,18 +3553,6 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write, return ret; } -static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, - int family) -{ - switch (family) { - case AF_INET: - return __in_dev_arp_parms_get_rcu(dev); - case AF_INET6: - return __in6_dev_nd_parms_get_rcu(dev); - } - return NULL; -} - static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, int index) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 8409d41405df..679b84cc8794 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -532,7 +532,7 @@ static ssize_t phys_port_name_show(struct device *dev, * returning early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && - !netdev->netdev_ops->ndo_get_devlink_port) + !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) @@ -562,7 +562,7 @@ static ssize_t phys_switch_id_show(struct device *dev, * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && - !netdev->netdev_ops->ndo_get_devlink_port) + !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 0ec2f5906a27..5581d22cc191 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -117,6 +117,7 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data) static int ops_init(const struct pernet_operations *ops, struct net *net) { + struct net_generic *ng; int err = -ENOMEM; void *data = NULL; @@ -135,7 +136,13 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) if (!err) return 0; + if (ops->id && ops->size) { cleanup: + ng = rcu_dereference_protected(net->gen, + lockdep_is_held(&pernet_ops_rwsem)); + ng->ptr[*ops->id] = NULL; + } + kfree(data); out: @@ -309,6 +316,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128); + ref_tracker_dir_init(&net->notrefcnt_tracker, 128); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); @@ -429,6 +437,10 @@ static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); + + /* There should not be any trackers left there. */ + ref_tracker_dir_exit(&net->notrefcnt_tracker); + kmem_cache_free(net_cachep, net); } } diff --git a/net/core/of_net.c b/net/core/of_net.c index f1a9bf7578e7..55d3fe229269 100644 --- a/net/core/of_net.c +++ b/net/core/of_net.c @@ -57,7 +57,7 @@ static int of_get_mac_addr(struct device_node *np, const char *name, u8 *addr) return -ENODEV; } -static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr) +int of_get_mac_address_nvmem(struct device_node *np, u8 *addr) { struct platform_device *pdev = of_find_device_by_node(np); struct nvmem_cell *cell; @@ -94,6 +94,7 @@ static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr) return 0; } +EXPORT_SYMBOL(of_get_mac_address_nvmem); /** * of_get_mac_address() @@ -140,7 +141,7 @@ int of_get_mac_address(struct device_node *np, u8 *addr) if (!ret) return 0; - return of_get_mac_addr_nvmem(np, addr); + return of_get_mac_address_nvmem(np, addr); } EXPORT_SYMBOL(of_get_mac_address); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 88906ba6d9a7..c3763056c554 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2324,7 +2324,7 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) pkt_dev->curfl = 0; /*reset */ } } else { - flow = prandom_u32() % pkt_dev->cflows; + flow = prandom_u32_max(pkt_dev->cflows); pkt_dev->curfl = flow; if (pkt_dev->flows[flow].count > pkt_dev->lflow) { @@ -2380,10 +2380,9 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev) else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) { __u16 t; if (pkt_dev->flags & F_QUEUE_MAP_RND) { - t = prandom_u32() % - (pkt_dev->queue_map_max - - pkt_dev->queue_map_min + 1) - + pkt_dev->queue_map_min; + t = prandom_u32_max(pkt_dev->queue_map_max - + pkt_dev->queue_map_min + 1) + + pkt_dev->queue_map_min; } else { t = pkt_dev->cur_queue_map + 1; if (t > pkt_dev->queue_map_max) @@ -2412,7 +2411,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACSRC_RND) - mc = prandom_u32() % pkt_dev->src_mac_count; + mc = prandom_u32_max(pkt_dev->src_mac_count); else { mc = pkt_dev->cur_src_mac_offset++; if (pkt_dev->cur_src_mac_offset >= @@ -2438,7 +2437,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACDST_RND) - mc = prandom_u32() % pkt_dev->dst_mac_count; + mc = prandom_u32_max(pkt_dev->dst_mac_count); else { mc = pkt_dev->cur_dst_mac_offset++; @@ -2465,23 +2464,23 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) for (i = 0; i < pkt_dev->nr_labels; i++) if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM) pkt_dev->labels[i] = MPLS_STACK_BOTTOM | - ((__force __be32)prandom_u32() & + ((__force __be32)get_random_u32() & htonl(0x000fffff)); } if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { - pkt_dev->vlan_id = prandom_u32() & (4096 - 1); + pkt_dev->vlan_id = prandom_u32_max(4096); } if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { - pkt_dev->svlan_id = prandom_u32() & (4096 - 1); + pkt_dev->svlan_id = prandom_u32_max(4096); } if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { if (pkt_dev->flags & F_UDPSRC_RND) - pkt_dev->cur_udp_src = prandom_u32() % - (pkt_dev->udp_src_max - pkt_dev->udp_src_min) - + pkt_dev->udp_src_min; + pkt_dev->cur_udp_src = prandom_u32_max( + pkt_dev->udp_src_max - pkt_dev->udp_src_min) + + pkt_dev->udp_src_min; else { pkt_dev->cur_udp_src++; @@ -2492,9 +2491,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { if (pkt_dev->flags & F_UDPDST_RND) { - pkt_dev->cur_udp_dst = prandom_u32() % - (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) - + pkt_dev->udp_dst_min; + pkt_dev->cur_udp_dst = prandom_u32_max( + pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) + + pkt_dev->udp_dst_min; } else { pkt_dev->cur_udp_dst++; if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) @@ -2509,7 +2508,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (imn < imx) { __u32 t; if (pkt_dev->flags & F_IPSRC_RND) - t = prandom_u32() % (imx - imn) + imn; + t = prandom_u32_max(imx - imn) + imn; else { t = ntohl(pkt_dev->cur_saddr); t++; @@ -2531,8 +2530,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->flags & F_IPDST_RND) { do { - t = prandom_u32() % - (imx - imn) + imn; + t = prandom_u32_max(imx - imn) + + imn; s = htonl(t); } while (ipv4_is_loopback(s) || ipv4_is_multicast(s) || @@ -2569,7 +2568,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) for (i = 0; i < 4; i++) { pkt_dev->cur_in6_daddr.s6_addr32[i] = - (((__force __be32)prandom_u32() | + (((__force __be32)get_random_u32() | pkt_dev->min_in6_daddr.s6_addr32[i]) & pkt_dev->max_in6_daddr.s6_addr32[i]); } @@ -2579,9 +2578,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { __u32 t; if (pkt_dev->flags & F_TXSIZE_RND) { - t = prandom_u32() % - (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size) - + pkt_dev->min_pkt_size; + t = prandom_u32_max(pkt_dev->max_pkt_size - + pkt_dev->min_pkt_size) + + pkt_dev->min_pkt_size; } else { t = pkt_dev->cur_pkt_size + 1; if (t > pkt_dev->max_pkt_size) @@ -2590,7 +2589,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) pkt_dev->cur_pkt_size = t; } else if (pkt_dev->n_imix_entries > 0) { struct imix_pkt *entry; - __u32 t = prandom_u32() % IMIX_PRECISION; + __u32 t = prandom_u32_max(IMIX_PRECISION); __u8 entry_index = pkt_dev->imix_distribution[t]; entry = &pkt_dev->imix_entries[entry_index]; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 74864dc46a7e..64289bc98887 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -53,6 +53,7 @@ #include <net/fib_rules.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> +#include <net/devlink.h> #include "dev.h" @@ -760,7 +761,7 @@ int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) EXPORT_SYMBOL(rtnl_unicast); void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, - struct nlmsghdr *nlh, gfp_t flags) + const struct nlmsghdr *nlh, gfp_t flags) { struct sock *rtnl = net->rtnl; @@ -1038,6 +1039,16 @@ static size_t rtnl_proto_down_size(const struct net_device *dev) return size; } +static size_t rtnl_devlink_port_size(const struct net_device *dev) +{ + size_t size = nla_total_size(0); /* nest IFLA_DEVLINK_PORT */ + + if (dev->devlink_port) + size += devlink_nl_port_handle_size(dev->devlink_port); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1091,6 +1102,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MAX_MTU */ + rtnl_prop_list_size(dev) + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + + rtnl_devlink_port_size(dev) + 0; } @@ -1728,6 +1740,30 @@ nla_put_failure: return -EMSGSIZE; } +static int rtnl_fill_devlink_port(struct sk_buff *skb, + const struct net_device *dev) +{ + struct nlattr *devlink_port_nest; + int ret; + + devlink_port_nest = nla_nest_start(skb, IFLA_DEVLINK_PORT); + if (!devlink_port_nest) + return -EMSGSIZE; + + if (dev->devlink_port) { + ret = devlink_nl_port_handle_fill(skb, dev->devlink_port); + if (ret < 0) + goto nest_cancel; + } + + nla_nest_end(skb, devlink_port_nest); + return 0; + +nest_cancel: + nla_nest_cancel(skb, devlink_port_nest); + return ret; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, @@ -1865,6 +1901,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, dev->dev.parent->bus->name)) goto nla_put_failure; + if (rtnl_fill_devlink_port(skb, dev)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -3110,7 +3149,7 @@ static int rtnl_group_dellink(const struct net *net, int group) return 0; } -int rtnl_delete_link(struct net_device *dev) +int rtnl_delete_link(struct net_device *dev, u32 portid, const struct nlmsghdr *nlh) { const struct rtnl_link_ops *ops; LIST_HEAD(list_kill); @@ -3120,7 +3159,7 @@ int rtnl_delete_link(struct net_device *dev) return -EOPNOTSUPP; ops->dellink(dev, &list_kill); - unregister_netdevice_many(&list_kill); + unregister_netdevice_many_notify(&list_kill, portid, nlh); return 0; } @@ -3130,6 +3169,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + u32 portid = NETLINK_CB(skb).portid; struct net *tgt_net = net; struct net_device *dev = NULL; struct ifinfomsg *ifm; @@ -3171,7 +3211,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } - err = rtnl_delete_link(dev); + err = rtnl_delete_link(dev, portid, nlh); out: if (netnsid >= 0) @@ -3180,7 +3220,8 @@ out: return err; } -int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) +int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, + u32 portid, const struct nlmsghdr *nlh) { unsigned int old_flags; int err; @@ -3194,10 +3235,10 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { - __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags)); + __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags), portid, nlh); } else { dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - __dev_notify_flags(dev, old_flags, ~0U); + __dev_notify_flags(dev, old_flags, ~0U, portid, nlh); } return 0; } @@ -3311,11 +3352,13 @@ static int rtnl_group_changelink(const struct sk_buff *skb, static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, const struct rtnl_link_ops *ops, + const struct nlmsghdr *nlh, struct nlattr **tb, struct nlattr **data, struct netlink_ext_ack *extack) { unsigned char name_assign_type = NET_NAME_USER; struct net *net = sock_net(skb->sk); + u32 portid = NETLINK_CB(skb).portid; struct net *dest_net, *link_net; struct net_device *dev; char ifname[IFNAMSIZ]; @@ -3369,7 +3412,7 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, goto out; } - err = rtnl_configure_link(dev, ifm); + err = rtnl_configure_link(dev, ifm, portid, nlh); if (err < 0) goto out_unregister; if (link_net) { @@ -3578,7 +3621,7 @@ replay: return -EOPNOTSUPP; } - return rtnl_newlink_create(skb, ifm, ops, tb, data, extack); + return rtnl_newlink_create(skb, ifm, ops, nlh, tb, data, extack); } static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -3896,7 +3939,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex) + int new_ifindex, u32 portid, u32 seq) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -3907,7 +3950,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, goto errout; err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), - type, 0, 0, change, 0, 0, event, + type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ @@ -3922,16 +3965,18 @@ errout: return NULL; } -void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) +void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, + u32 portid, const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); + rtnl_notify(skb, net, portid, RTNLGRP_LINK, nlh, flags); } static void rtmsg_ifinfo_event(int type, struct net_device *dev, unsigned int change, u32 event, - gfp_t flags, int *new_nsid, int new_ifindex) + gfp_t flags, int *new_nsid, int new_ifindex, + u32 portid, const struct nlmsghdr *nlh) { struct sk_buff *skb; @@ -3939,23 +3984,23 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex); + new_ifindex, portid, nlmsg_seq(nlh)); if (skb) - rtmsg_ifinfo_send(skb, dev, flags); + rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, - gfp_t flags) + gfp_t flags, u32 portid, const struct nlmsghdr *nlh) { rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, - NULL, 0); + NULL, 0, portid, nlh); } void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, gfp_t flags, int *new_nsid, int new_ifindex) { rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, - new_nsid, new_ifindex); + new_nsid, new_ifindex, 0, NULL); } static int nlmsg_populate_fdb_fill(struct sk_buff *skb, @@ -4045,6 +4090,11 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, return err; } + if (tb[NDA_FLAGS_EXT]) { + netdev_info(dev, "invalid flags given to default FDB implementation\n"); + return err; + } + if (vid) { netdev_info(dev, "vlans aren't supported yet for dev_uc|mc_add()\n"); return err; @@ -6140,7 +6190,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_CHANGELOWERSTATE: case NETDEV_CHANGE_TX_QUEUE_LEN: rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), - GFP_KERNEL, NULL, 0); + GFP_KERNEL, NULL, 0, 0, NULL); break; default: break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d9719e72f9d..4bf95e36ed16 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -94,6 +94,7 @@ EXPORT_SYMBOL(sysctl_max_skb_frags); #undef FN #define FN(reason) [SKB_DROP_REASON_##reason] = #reason, const char * const drop_reasons[] = { + [SKB_CONSUMED] = "CONSUMED", DEFINE_DROP_REASON(FN, FN) }; EXPORT_SYMBOL(drop_reasons); @@ -506,14 +507,14 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, */ size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); + osize = kmalloc_size_roundup(size); + data = kmalloc_reserve(osize, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; - /* kmalloc(size) might give us more room than requested. + /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ - osize = ksize(data); size = SKB_WITH_OVERHEAD(osize); prefetchw(data + size); @@ -748,6 +749,13 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +static bool skb_pp_recycle(struct sk_buff *skb, void *data) +{ + if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) + return false; + return page_pool_return_skb_page(virt_to_page(data)); +} + static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; @@ -761,7 +769,7 @@ static void skb_free_head(struct sk_buff *skb) } } -static void skb_release_data(struct sk_buff *skb) +static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason) { struct skb_shared_info *shinfo = skb_shinfo(skb); int i; @@ -784,7 +792,7 @@ static void skb_release_data(struct sk_buff *skb) free_head: if (shinfo->frag_list) - kfree_skb_list(shinfo->frag_list); + kfree_skb_list_reason(shinfo->frag_list, reason); skb_free_head(skb); exit: @@ -847,11 +855,11 @@ void skb_release_head_state(struct sk_buff *skb) } /* Free everything but the sk_buff shell. */ -static void skb_release_all(struct sk_buff *skb) +static void skb_release_all(struct sk_buff *skb, enum skb_drop_reason reason) { skb_release_head_state(skb); if (likely(skb->head)) - skb_release_data(skb); + skb_release_data(skb, reason); } /** @@ -865,7 +873,7 @@ static void skb_release_all(struct sk_buff *skb) void __kfree_skb(struct sk_buff *skb) { - skb_release_all(skb); + skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED); kfree_skbmem(skb); } EXPORT_SYMBOL(__kfree_skb); @@ -887,7 +895,10 @@ kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) DEBUG_NET_WARN_ON_ONCE(reason <= 0 || reason >= SKB_DROP_REASON_MAX); - trace_kfree_skb(skb, __builtin_return_address(0), reason); + if (reason == SKB_CONSUMED) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, __builtin_return_address(0), reason); __kfree_skb(skb); } EXPORT_SYMBOL(kfree_skb_reason); @@ -1045,7 +1056,7 @@ EXPORT_SYMBOL(consume_skb); void __consume_stateless_skb(struct sk_buff *skb) { trace_consume_skb(skb); - skb_release_data(skb); + skb_release_data(skb, SKB_CONSUMED); kfree_skbmem(skb); } @@ -1070,7 +1081,7 @@ static void napi_skb_cache_put(struct sk_buff *skb) void __kfree_skb_defer(struct sk_buff *skb) { - skb_release_all(skb); + skb_release_all(skb, SKB_DROP_REASON_NOT_SPECIFIED); napi_skb_cache_put(skb); } @@ -1108,7 +1119,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget) return; } - skb_release_all(skb); + skb_release_all(skb, SKB_CONSUMED); napi_skb_cache_put(skb); } EXPORT_SYMBOL(napi_consume_skb); @@ -1239,7 +1250,7 @@ EXPORT_SYMBOL_GPL(alloc_skb_for_msg); */ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) { - skb_release_all(dst); + skb_release_all(dst, SKB_CONSUMED); return __skb_clone(dst, src); } EXPORT_SYMBOL_GPL(skb_morph); @@ -1256,13 +1267,12 @@ int mm_account_pinned_pages(struct mmpin *mmp, size_t size) max_pg = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; user = mmp->user ? : current_user(); + old_pg = atomic_long_read(&user->locked_vm); do { - old_pg = atomic_long_read(&user->locked_vm); new_pg = old_pg + num_pg; if (new_pg > max_pg) return -ENOBUFS; - } while (atomic_long_cmpxchg(&user->locked_vm, old_pg, new_pg) != - old_pg); + } while (!atomic_long_try_cmpxchg(&user->locked_vm, &old_pg, new_pg)); if (!mmp->user) { mmp->user = get_uid(user); @@ -1814,10 +1824,11 @@ EXPORT_SYMBOL(__pskb_copy_fclone); int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask) { - int i, osize = skb_end_offset(skb); - int size = osize + nhead + ntail; + unsigned int osize = skb_end_offset(skb); + unsigned int size = osize + nhead + ntail; long off; u8 *data; + int i; BUG_ON(nhead < 0); @@ -1825,15 +1836,16 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb_zcopy_downgrade_managed(skb); - size = SKB_DATA_ALIGN(size); - if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), - gfp_mask, NUMA_NO_NODE, NULL); + + size = SKB_DATA_ALIGN(size); + size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = kmalloc_size_roundup(size); + data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; - size = SKB_WITH_OVERHEAD(ksize(data)); + size = SKB_WITH_OVERHEAD(size); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. @@ -1860,7 +1872,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - skb_release_data(skb); + skb_release_data(skb, SKB_CONSUMED); } else { skb_free_head(skb); } @@ -3971,7 +3983,7 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } else if (i < MAX_SKB_FRAGS) { skb_zcopy_downgrade_managed(skb); get_page(page); - skb_fill_page_desc(skb, i, page, offset, size); + skb_fill_page_desc_noacc(skb, i, page, offset, size); } else { return -EMSGSIZE; } @@ -4134,23 +4146,25 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, int i = 0; int pos; - if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) && - (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) { - /* gso_size is untrusted, and we have a frag_list with a linear - * non head_frag head. - * - * (we assume checking the first list_skb member suffices; - * i.e if either of the list_skb members have non head_frag - * head, then the first one has too). - * - * If head_skb's headlen does not fit requested gso_size, it - * means that the frag_list members do NOT terminate on exact - * gso_size boundaries. Hence we cannot perform skb_frag_t page - * sharing. Therefore we must fallback to copying the frag_list - * skbs; we do so by disabling SG. - */ - if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) - features &= ~NETIF_F_SG; + if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && + mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { + struct sk_buff *check_skb; + + for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { + if (skb_headlen(check_skb) && !check_skb->head_frag) { + /* gso_size is untrusted, and we have a frag_list with + * a linear non head_frag item. + * + * If head_skb's headlen does not fit requested gso_size, + * it means that the frag_list members do NOT terminate + * on exact gso_size boundaries. Hence we cannot perform + * skb_frag_t page sharing. Therefore we must fallback to + * copying the frag_list skbs; we do so by disabling SG. + */ + features &= ~NETIF_F_SG; + break; + } + } } __skb_push(head_skb, doffset); @@ -6167,21 +6181,20 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, const int headlen, gfp_t gfp_mask) { int i; - int size = skb_end_offset(skb); + unsigned int size = skb_end_offset(skb); int new_hlen = headlen - off; u8 *data; - size = SKB_DATA_ALIGN(size); - if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - data = kmalloc_reserve(size + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), - gfp_mask, NUMA_NO_NODE, NULL); + + size = SKB_DATA_ALIGN(size); + size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = kmalloc_size_roundup(size); + data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; - - size = SKB_WITH_OVERHEAD(ksize(data)); + size = SKB_WITH_OVERHEAD(size); /* Copy real data, and all frags */ skb_copy_from_linear_data_offset(skb, off, data, new_hlen); @@ -6201,7 +6214,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - skb_release_data(skb); + skb_release_data(skb, SKB_CONSUMED); } else { /* we can reuse existing recount- all we did was * relocate values @@ -6286,22 +6299,21 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, int pos, gfp_t gfp_mask) { int i, k = 0; - int size = skb_end_offset(skb); + unsigned int size = skb_end_offset(skb); u8 *data; const int nfrags = skb_shinfo(skb)->nr_frags; struct skb_shared_info *shinfo; - size = SKB_DATA_ALIGN(size); - if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - data = kmalloc_reserve(size + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), - gfp_mask, NUMA_NO_NODE, NULL); + + size = SKB_DATA_ALIGN(size); + size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = kmalloc_size_roundup(size); + data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; - - size = SKB_WITH_OVERHEAD(ksize(data)); + size = SKB_WITH_OVERHEAD(size); memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); @@ -6345,7 +6357,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, kfree(data); return -ENOMEM; } - skb_release_data(skb); + skb_release_data(skb, SKB_CONSUMED); skb->head = data; skb->head_frag = 0; @@ -6424,6 +6436,7 @@ void skb_condense(struct sk_buff *skb) */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } +EXPORT_SYMBOL(skb_condense); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ca70525621c7..e6b9ced3eda8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -500,11 +500,11 @@ bool sk_msg_is_readable(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_msg_is_readable); -static struct sk_msg *alloc_sk_msg(void) +static struct sk_msg *alloc_sk_msg(gfp_t gfp) { struct sk_msg *msg; - msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_KERNEL); + msg = kzalloc(sizeof(*msg), gfp | __GFP_NOWARN); if (unlikely(!msg)) return NULL; sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); @@ -520,7 +520,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, if (!sk_rmem_schedule(sk, skb, skb->truesize)) return NULL; - return alloc_sk_msg(); + return alloc_sk_msg(GFP_KERNEL); } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, @@ -597,7 +597,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) { - struct sk_msg *msg = alloc_sk_msg(); + struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC); struct sock *sk = psock->sk; int err; @@ -803,16 +803,13 @@ static void sk_psock_link_destroy(struct sk_psock *psock) } } -void sk_psock_stop(struct sk_psock *psock, bool wait) +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); - - if (wait) - cancel_work_sync(&psock->work); } static void sk_psock_done_strp(struct sk_psock *psock); @@ -850,7 +847,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); - sk_psock_stop(psock, false); + sk_psock_stop(psock); INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); diff --git a/net/core/sock.c b/net/core/sock.c index a3ba0358c77c..4571914a4aa8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1436,7 +1436,7 @@ set_sndbuf: break; } case SO_INCOMING_CPU: - WRITE_ONCE(sk->sk_incoming_cpu, val); + reuseport_update_incoming_cpu(sk, val); break; case SO_CNX_ADVICE: @@ -2094,6 +2094,9 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, if (likely(sk->sk_net_refcnt)) { get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); + } else { + __netns_tracker_alloc(net, &sk->ns_tracker, + false, priority); } sock_net_set(sk, net); @@ -2149,6 +2152,9 @@ static void __sk_destruct(struct rcu_head *head) if (likely(sk->sk_net_refcnt)) put_net_track(sock_net(sk), &sk->ns_tracker); + else + __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); + sk_prot_free(sk->sk_prot_creator, sk); } @@ -2237,6 +2243,14 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) if (likely(newsk->sk_net_refcnt)) { get_net_track(sock_net(newsk), &newsk->ns_tracker, priority); sock_inuse_add(sock_net(newsk), 1); + } else { + /* Kernel sockets are not elevating the struct net refcount. + * Instead, use a tracker to more easily detect if a layer + * is not properly dismantling its kernel sockets at netns + * destroy time. + */ + __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, + false, priority); } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); @@ -2730,7 +2744,7 @@ failure: } EXPORT_SYMBOL(sock_alloc_send_pskb); -int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, +int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; @@ -2784,7 +2798,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; - ret = __sock_cmsg_send(sk, msg, cmsg, sockc); + ret = __sock_cmsg_send(sk, cmsg, sockc); if (ret) return ret; } diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index f7cf74cdd3db..b1e29e18d1d6 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -25,14 +25,17 @@ DEFINE_COOKIE(sock_cookie); u64 __sock_gen_cookie(struct sock *sk) { - while (1) { - u64 res = atomic64_read(&sk->sk_cookie); + u64 res = atomic64_read(&sk->sk_cookie); - if (res) - return res; - res = gen_cookie_next(&sock_cookie); - atomic64_cmpxchg(&sk->sk_cookie, 0, res); + if (!res) { + u64 new = gen_cookie_next(&sock_cookie); + + atomic64_cmpxchg(&sk->sk_cookie, res, new); + + /* Another thread might have changed sk_cookie before us. */ + res = atomic64_read(&sk->sk_cookie); } + return res; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index a660baedd9e7..81beb16ab1eb 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1596,7 +1596,7 @@ void sock_map_destroy(struct sock *sk) saved_destroy = psock->saved_destroy; sock_map_remove_links(sk, psock); rcu_read_unlock(); - sk_psock_stop(psock, false); + sk_psock_stop(psock); sk_psock_put(sk, psock); saved_destroy(sk); } @@ -1619,9 +1619,10 @@ void sock_map_close(struct sock *sk, long timeout) saved_close = psock->saved_close; sock_map_remove_links(sk, psock); rcu_read_unlock(); - sk_psock_stop(psock, true); - sk_psock_put(sk, psock); + sk_psock_stop(psock); release_sock(sk); + cancel_work_sync(&psock->work); + sk_psock_put(sk, psock); saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5daa1fa54249..5a165286e4d8 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -21,6 +21,86 @@ static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); +void reuseport_has_conns_set(struct sock *sk) +{ + struct sock_reuseport *reuse; + + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (likely(reuse)) + reuse->has_conns = 1; + spin_unlock_bh(&reuseport_lock); +} +EXPORT_SYMBOL(reuseport_has_conns_set); + +static void __reuseport_get_incoming_cpu(struct sock_reuseport *reuse) +{ + /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ + WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu + 1); +} + +static void __reuseport_put_incoming_cpu(struct sock_reuseport *reuse) +{ + /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ + WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu - 1); +} + +static void reuseport_get_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) +{ + if (sk->sk_incoming_cpu >= 0) + __reuseport_get_incoming_cpu(reuse); +} + +static void reuseport_put_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) +{ + if (sk->sk_incoming_cpu >= 0) + __reuseport_put_incoming_cpu(reuse); +} + +void reuseport_update_incoming_cpu(struct sock *sk, int val) +{ + struct sock_reuseport *reuse; + int old_sk_incoming_cpu; + + if (unlikely(!rcu_access_pointer(sk->sk_reuseport_cb))) { + /* Paired with REAE_ONCE() in sk_incoming_cpu_update() + * and compute_score(). + */ + WRITE_ONCE(sk->sk_incoming_cpu, val); + return; + } + + spin_lock_bh(&reuseport_lock); + + /* This must be done under reuseport_lock to avoid a race with + * reuseport_grow(), which accesses sk->sk_incoming_cpu without + * lock_sock() when detaching a shutdown()ed sk. + * + * Paired with READ_ONCE() in reuseport_select_sock_by_hash(). + */ + old_sk_incoming_cpu = sk->sk_incoming_cpu; + WRITE_ONCE(sk->sk_incoming_cpu, val); + + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + + /* reuseport_grow() has detached a closed sk. */ + if (!reuse) + goto out; + + if (old_sk_incoming_cpu < 0 && val >= 0) + __reuseport_get_incoming_cpu(reuse); + else if (old_sk_incoming_cpu >= 0 && val < 0) + __reuseport_put_incoming_cpu(reuse); + +out: + spin_unlock_bh(&reuseport_lock); +} + static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) @@ -48,6 +128,7 @@ static void __reuseport_add_sock(struct sock *sk, /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ smp_wmb(); reuse->num_socks++; + reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_sock(struct sock *sk, @@ -60,6 +141,7 @@ static bool __reuseport_detach_sock(struct sock *sk, reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; reuse->num_socks--; + reuseport_put_incoming_cpu(sk, reuse); return true; } @@ -70,6 +152,7 @@ static void __reuseport_add_closed_sock(struct sock *sk, reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); + reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_closed_sock(struct sock *sk, @@ -83,6 +166,7 @@ static bool __reuseport_detach_closed_sock(struct sock *sk, reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); + reuseport_put_incoming_cpu(sk, reuse); return true; } @@ -150,6 +234,7 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; + reuseport_get_incoming_cpu(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: @@ -193,6 +278,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; more_reuse->has_conns = reuse->has_conns; + more_reuse->incoming_cpu = reuse->incoming_cpu; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); @@ -442,18 +528,32 @@ static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, u32 hash, u16 num_socks) { + struct sock *first_valid_sk = NULL; int i, j; i = j = reciprocal_scale(hash, num_socks); - while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { + do { + struct sock *sk = reuse->socks[i]; + + if (sk->sk_state != TCP_ESTABLISHED) { + /* Paired with WRITE_ONCE() in __reuseport_(get|put)_incoming_cpu(). */ + if (!READ_ONCE(reuse->incoming_cpu)) + return sk; + + /* Paired with WRITE_ONCE() in reuseport_update_incoming_cpu(). */ + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) + return sk; + + if (!first_valid_sk) + first_valid_sk = sk; + } + i++; if (i >= num_socks) i = 0; - if (i == j) - return NULL; - } + } while (i != j); - return reuse->socks[i]; + return first_valid_sk; } /** diff --git a/net/core/stream.c b/net/core/stream.c index 1105057ce00a..75fded8495f5 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -123,7 +123,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT_FUNC(wait, woken_wake_function); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; + current_timeo = vm_wait = prandom_u32_max(HZ / 5) + 2; add_wait_queue(sk_sleep(sk), &wait); diff --git a/net/core/utils.c b/net/core/utils.c index 938495bc1d34..c994e95172ac 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -302,7 +302,7 @@ static int inet4_pton(const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in *addr4 = (struct sockaddr_in *)addr; - int srclen = strlen(src); + size_t srclen = strlen(src); if (srclen > INET_ADDRSTRLEN) return -EINVAL; @@ -322,7 +322,7 @@ static int inet6_pton(struct net *net, const char *src, u16 port_num, { struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr; const char *scope_delim; - int srclen = strlen(src); + size_t srclen = strlen(src); if (srclen > INET6_ADDRSTRLEN) return -EINVAL; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index dc4fb699b56c..f9949e051f49 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -166,6 +166,7 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, [DCB_ATTR_DCB_BUFFER] = {.len = sizeof(struct dcbnl_buffer)}, + [DCB_ATTR_DCB_APP_TRUST_TABLE] = {.type = NLA_NESTED}, }; /* DCB number of traffic classes nested attributes. */ @@ -179,6 +180,38 @@ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { static LIST_HEAD(dcb_app_list); static DEFINE_SPINLOCK(dcb_lock); +static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) +{ + switch (selector) { + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + case IEEE_8021QAZ_APP_SEL_STREAM: + case IEEE_8021QAZ_APP_SEL_DGRAM: + case IEEE_8021QAZ_APP_SEL_ANY: + case IEEE_8021QAZ_APP_SEL_DSCP: + return DCB_ATTR_IEEE_APP; + case DCB_APP_SEL_PCP: + return DCB_ATTR_DCB_APP; + default: + return DCB_ATTR_IEEE_APP_UNSPEC; + } +} + +static bool dcbnl_app_attr_type_validate(enum ieee_attrs_app type) +{ + switch (type) { + case DCB_ATTR_IEEE_APP: + case DCB_ATTR_DCB_APP: + return true; + default: + return false; + } +} + +static bool dcbnl_app_selector_validate(enum ieee_attrs_app type, u8 selector) +{ + return dcbnl_app_attr_type_get(selector) == type; +} + static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq, u32 flags, struct nlmsghdr **nlhp) { @@ -1027,12 +1060,51 @@ nla_put_failure: return err; } +static int dcbnl_getapptrust(struct net_device *netdev, struct sk_buff *skb) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + enum ieee_attrs_app type; + struct nlattr *apptrust; + int nselectors, err, i; + u8 *selectors; + + selectors = kzalloc(IEEE_8021QAZ_APP_SEL_MAX + 1, GFP_KERNEL); + if (!selectors) + return -ENOMEM; + + err = ops->dcbnl_getapptrust(netdev, selectors, &nselectors); + if (err) { + err = 0; + goto out; + } + + apptrust = nla_nest_start(skb, DCB_ATTR_DCB_APP_TRUST_TABLE); + if (!apptrust) { + err = -EMSGSIZE; + goto out; + } + + for (i = 0; i < nselectors; i++) { + type = dcbnl_app_attr_type_get(selectors[i]); + err = nla_put_u8(skb, type, selectors[i]); + if (err) { + nla_nest_cancel(skb, apptrust); + goto out; + } + } + nla_nest_end(skb, apptrust); + +out: + kfree(selectors); + return err; +} + /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee, *app; struct dcb_app_type *itr; - const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; int dcbx; int err; @@ -1116,8 +1188,9 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { - err = nla_put(skb, DCB_ATTR_IEEE_APP, sizeof(itr->app), - &itr->app); + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(itr->app.selector); + err = nla_put(skb, type, sizeof(itr->app), &itr->app); if (err) { spin_unlock_bh(&dcb_lock); return -EMSGSIZE; @@ -1133,6 +1206,12 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); + if (ops->dcbnl_getapptrust) { + err = dcbnl_getapptrust(netdev, skb); + if (err) + return err; + } + /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; @@ -1493,9 +1572,10 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, int rem; nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + enum ieee_attrs_app type = nla_type(attr); struct dcb_app *app_data; - if (nla_type(attr) != DCB_ATTR_IEEE_APP) + if (!dcbnl_app_attr_type_validate(type)) continue; if (nla_len(attr) < sizeof(struct dcb_app)) { @@ -1504,6 +1584,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, } app_data = nla_data(attr); + + if (!dcbnl_app_selector_validate(type, + app_data->selector)) { + err = -EINVAL; + goto err; + } + if (ops->ieee_setapp) err = ops->ieee_setapp(netdev, app_data); else @@ -1513,6 +1600,53 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, } } + if (ieee[DCB_ATTR_DCB_APP_TRUST_TABLE]) { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; + struct nlattr *attr; + int nselectors = 0; + int rem; + + if (!ops->dcbnl_setapptrust) { + err = -EOPNOTSUPP; + goto err; + } + + nla_for_each_nested(attr, ieee[DCB_ATTR_DCB_APP_TRUST_TABLE], + rem) { + enum ieee_attrs_app type = nla_type(attr); + u8 selector; + int i; + + if (!dcbnl_app_attr_type_validate(type) || + nla_len(attr) != 1 || + nselectors >= sizeof(selectors)) { + err = -EINVAL; + goto err; + } + + selector = nla_get_u8(attr); + + if (!dcbnl_app_selector_validate(type, selector)) { + err = -EINVAL; + goto err; + } + + /* Duplicate selector ? */ + for (i = 0; i < nselectors; i++) { + if (selectors[i] == selector) { + err = -EINVAL; + goto err; + } + } + + selectors[nselectors++] = selector; + } + + err = ops->dcbnl_setapptrust(netdev, selectors, nselectors); + if (err) + goto err; + } + err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); @@ -1554,11 +1688,20 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, int rem; nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + enum ieee_attrs_app type = nla_type(attr); struct dcb_app *app_data; - if (nla_type(attr) != DCB_ATTR_IEEE_APP) + if (!dcbnl_app_attr_type_validate(type)) continue; + app_data = nla_data(attr); + + if (!dcbnl_app_selector_validate(type, + app_data->selector)) { + err = -EINVAL; + goto err; + } + if (ops->ieee_delapp) err = ops->ieee_delapp(netdev, app_data); else diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 7dfc00c9fb32..9ddc3a9e89e4 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -278,6 +278,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned int len); +void dccp_destruct_common(struct sock *sk); int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); void dccp_destroy_sock(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 6a6e121dc00c..b780827f5e0a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -45,11 +45,10 @@ static unsigned int dccp_v4_pernet_id __read_mostly; int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -91,26 +90,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) daddr = fl4->daddr; if (inet->inet_saddr == 0) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = - inet_bhashfn_portaddr(&dccp_hashinfo, sk, - sock_net(sk), - inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } inet->inet_dport = usin->sin_port; @@ -144,7 +130,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = prandom_u32(); + inet->inet_id = get_random_u16(); err = dccp_connect(sk); rt = NULL; @@ -157,6 +143,7 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; @@ -443,7 +430,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = prandom_u32(); + newinet->inet_id = get_random_u16(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e57b43006074..4260fe466993 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -934,26 +934,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (saddr == NULL) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(&dccp_hashinfo, - sk, sock_net(sk), - inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } - saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -985,6 +970,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; @@ -1021,6 +1007,12 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .sockaddr_len = sizeof(struct sockaddr_in6), }; +static void dccp_v6_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); + inet6_sock_destruct(sk); +} + /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ @@ -1033,17 +1025,12 @@ static int dccp_v6_init_sock(struct sock *sk) if (unlikely(!dccp_v6_ctl_sock_initialized)) dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + sk->sk_destruct = dccp_v6_sk_destruct; } return err; } -static void dccp_v6_destroy_sock(struct sock *sk) -{ - dccp_destroy_sock(sk); - inet6_destroy_sock(sk); -} - static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; @@ -1066,7 +1053,7 @@ static struct proto dccp_v6_prot = { .accept = inet_csk_accept, .get_port = inet_csk_get_port, .shutdown = dccp_shutdown, - .destroy = dccp_v6_destroy_sock, + .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), diff --git a/net/dccp/proto.c b/net/dccp/proto.c index c548ca3e9b0e..a06b5641287a 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -171,12 +171,18 @@ const char *dccp_packet_name(const int type) EXPORT_SYMBOL_GPL(dccp_packet_name); -static void dccp_sk_destruct(struct sock *sk) +void dccp_destruct_common(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = NULL; +} +EXPORT_SYMBOL_GPL(dccp_destruct_common); + +static void dccp_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); inet_sock_destruct(sk); } @@ -279,8 +285,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 3eef72ce99a4..8e698bea99a3 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -18,6 +18,12 @@ if NET_DSA # Drivers must select the appropriate tagging format(s) +config NET_DSA_TAG_NONE + tristate "No-op tag driver" + help + Say Y or M if you want to enable support for switches which don't tag + frames over the CPU port. + config NET_DSA_TAG_AR9331 tristate "Tag driver for Atheros AR9331 SoC with built-in switch" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index bf57ef3bce2a..cc7e93a562fe 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -2,13 +2,14 @@ # the core obj-$(CONFIG_NET_DSA) += dsa_core.o dsa_core-y += \ + devlink.o \ dsa.o \ - dsa2.o \ master.o \ netlink.o \ port.o \ slave.o \ switch.o \ + tag.o \ tag_8021q.o # tagging formats @@ -20,6 +21,7 @@ obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o +obj-$(CONFIG_NET_DSA_TAG_NONE) += tag_none.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o diff --git a/net/dsa/devlink.c b/net/dsa/devlink.c new file mode 100644 index 000000000000..431bf52290a1 --- /dev/null +++ b/net/dsa/devlink.c @@ -0,0 +1,391 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * DSA devlink handling + */ + +#include <net/dsa.h> +#include <net/devlink.h> + +#include "devlink.h" + +static int dsa_devlink_info_get(struct devlink *dl, + struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (ds->ops->devlink_info_get) + return ds->ops->devlink_info_get(ds, req, extack); + + return -EOPNOTSUPP; +} + +static int dsa_devlink_sb_pool_get(struct devlink *dl, + unsigned int sb_index, u16 pool_index, + struct devlink_sb_pool_info *pool_info) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_pool_get(ds, sb_index, pool_index, + pool_info); +} + +static int dsa_devlink_sb_pool_set(struct devlink *dl, unsigned int sb_index, + u16 pool_index, u32 size, + enum devlink_sb_threshold_type threshold_type, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_pool_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_pool_set(ds, sb_index, pool_index, size, + threshold_type, extack); +} + +static int dsa_devlink_sb_port_pool_get(struct devlink_port *dlp, + unsigned int sb_index, u16 pool_index, + u32 *p_threshold) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_port_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_port_pool_get(ds, port, sb_index, + pool_index, p_threshold); +} + +static int dsa_devlink_sb_port_pool_set(struct devlink_port *dlp, + unsigned int sb_index, u16 pool_index, + u32 threshold, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_port_pool_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_port_pool_set(ds, port, sb_index, + pool_index, threshold, extack); +} + +static int +dsa_devlink_sb_tc_pool_bind_get(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 *p_pool_index, u32 *p_threshold) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_tc_pool_bind_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_tc_pool_bind_get(ds, port, sb_index, + tc_index, pool_type, + p_pool_index, p_threshold); +} + +static int +dsa_devlink_sb_tc_pool_bind_set(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 pool_index, u32 threshold, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_tc_pool_bind_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_tc_pool_bind_set(ds, port, sb_index, + tc_index, pool_type, + pool_index, threshold, + extack); +} + +static int dsa_devlink_sb_occ_snapshot(struct devlink *dl, + unsigned int sb_index) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_occ_snapshot) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_snapshot(ds, sb_index); +} + +static int dsa_devlink_sb_occ_max_clear(struct devlink *dl, + unsigned int sb_index) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_occ_max_clear) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_max_clear(ds, sb_index); +} + +static int dsa_devlink_sb_occ_port_pool_get(struct devlink_port *dlp, + unsigned int sb_index, + u16 pool_index, u32 *p_cur, + u32 *p_max) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_occ_port_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_port_pool_get(ds, port, sb_index, + pool_index, p_cur, p_max); +} + +static int +dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u32 *p_cur, u32 *p_max) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_occ_tc_port_bind_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_tc_port_bind_get(ds, port, + sb_index, tc_index, + pool_type, p_cur, + p_max); +} + +static const struct devlink_ops dsa_devlink_ops = { + .info_get = dsa_devlink_info_get, + .sb_pool_get = dsa_devlink_sb_pool_get, + .sb_pool_set = dsa_devlink_sb_pool_set, + .sb_port_pool_get = dsa_devlink_sb_port_pool_get, + .sb_port_pool_set = dsa_devlink_sb_port_pool_set, + .sb_tc_pool_bind_get = dsa_devlink_sb_tc_pool_bind_get, + .sb_tc_pool_bind_set = dsa_devlink_sb_tc_pool_bind_set, + .sb_occ_snapshot = dsa_devlink_sb_occ_snapshot, + .sb_occ_max_clear = dsa_devlink_sb_occ_max_clear, + .sb_occ_port_pool_get = dsa_devlink_sb_occ_port_pool_get, + .sb_occ_tc_port_bind_get = dsa_devlink_sb_occ_tc_port_bind_get, +}; + +int dsa_devlink_param_get(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_param_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_param_get(ds, id, ctx); +} +EXPORT_SYMBOL_GPL(dsa_devlink_param_get); + +int dsa_devlink_param_set(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_param_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_param_set(ds, id, ctx); +} +EXPORT_SYMBOL_GPL(dsa_devlink_param_set); + +int dsa_devlink_params_register(struct dsa_switch *ds, + const struct devlink_param *params, + size_t params_count) +{ + return devlink_params_register(ds->devlink, params, params_count); +} +EXPORT_SYMBOL_GPL(dsa_devlink_params_register); + +void dsa_devlink_params_unregister(struct dsa_switch *ds, + const struct devlink_param *params, + size_t params_count) +{ + devlink_params_unregister(ds->devlink, params, params_count); +} +EXPORT_SYMBOL_GPL(dsa_devlink_params_unregister); + +int dsa_devlink_resource_register(struct dsa_switch *ds, + const char *resource_name, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + const struct devlink_resource_size_params *size_params) +{ + return devlink_resource_register(ds->devlink, resource_name, + resource_size, resource_id, + parent_resource_id, + size_params); +} +EXPORT_SYMBOL_GPL(dsa_devlink_resource_register); + +void dsa_devlink_resources_unregister(struct dsa_switch *ds) +{ + devlink_resources_unregister(ds->devlink); +} +EXPORT_SYMBOL_GPL(dsa_devlink_resources_unregister); + +void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, + u64 resource_id, + devlink_resource_occ_get_t *occ_get, + void *occ_get_priv) +{ + return devlink_resource_occ_get_register(ds->devlink, resource_id, + occ_get, occ_get_priv); +} +EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_register); + +void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, + u64 resource_id) +{ + devlink_resource_occ_get_unregister(ds->devlink, resource_id); +} +EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister); + +struct devlink_region * +dsa_devlink_region_create(struct dsa_switch *ds, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + return devlink_region_create(ds->devlink, ops, region_max_snapshots, + region_size); +} +EXPORT_SYMBOL_GPL(dsa_devlink_region_create); + +struct devlink_region * +dsa_devlink_port_region_create(struct dsa_switch *ds, + int port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + + return devlink_port_region_create(&dp->devlink_port, ops, + region_max_snapshots, + region_size); +} +EXPORT_SYMBOL_GPL(dsa_devlink_port_region_create); + +void dsa_devlink_region_destroy(struct devlink_region *region) +{ + devlink_region_destroy(region); +} +EXPORT_SYMBOL_GPL(dsa_devlink_region_destroy); + +int dsa_port_devlink_setup(struct dsa_port *dp) +{ + struct devlink_port *dlp = &dp->devlink_port; + struct dsa_switch_tree *dst = dp->ds->dst; + struct devlink_port_attrs attrs = {}; + struct devlink *dl = dp->ds->devlink; + struct dsa_switch *ds = dp->ds; + const unsigned char *id; + unsigned char len; + int err; + + memset(dlp, 0, sizeof(*dlp)); + devlink_port_init(dl, dlp); + + if (ds->ops->port_setup) { + err = ds->ops->port_setup(ds, dp->index); + if (err) + return err; + } + + id = (const unsigned char *)&dst->index; + len = sizeof(dst->index); + + attrs.phys.port_number = dp->index; + memcpy(attrs.switch_id.id, id, len); + attrs.switch_id.id_len = len; + + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + attrs.flavour = DEVLINK_PORT_FLAVOUR_UNUSED; + break; + case DSA_PORT_TYPE_CPU: + attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU; + break; + case DSA_PORT_TYPE_DSA: + attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA; + break; + case DSA_PORT_TYPE_USER: + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + break; + } + + devlink_port_attrs_set(dlp, &attrs); + err = devlink_port_register(dl, dlp, dp->index); + if (err) { + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); + return err; + } + + return 0; +} + +void dsa_port_devlink_teardown(struct dsa_port *dp) +{ + struct devlink_port *dlp = &dp->devlink_port; + struct dsa_switch *ds = dp->ds; + + devlink_port_unregister(dlp); + + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); + + devlink_port_fini(dlp); +} + +void dsa_switch_devlink_register(struct dsa_switch *ds) +{ + devlink_register(ds->devlink); +} + +void dsa_switch_devlink_unregister(struct dsa_switch *ds) +{ + devlink_unregister(ds->devlink); +} + +int dsa_switch_devlink_alloc(struct dsa_switch *ds) +{ + struct dsa_devlink_priv *dl_priv; + struct devlink *dl; + + /* Add the switch to devlink before calling setup, so that setup can + * add dpipe tables + */ + dl = devlink_alloc(&dsa_devlink_ops, sizeof(*dl_priv), ds->dev); + if (!dl) + return -ENOMEM; + + ds->devlink = dl; + + dl_priv = devlink_priv(ds->devlink); + dl_priv->ds = ds; + + return 0; +} + +void dsa_switch_devlink_free(struct dsa_switch *ds) +{ + devlink_free(ds->devlink); + ds->devlink = NULL; +} diff --git a/net/dsa/devlink.h b/net/dsa/devlink.h new file mode 100644 index 000000000000..4d9f4f23705b --- /dev/null +++ b/net/dsa/devlink.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_DEVLINK_H +#define __DSA_DEVLINK_H + +struct dsa_port; +struct dsa_switch; + +int dsa_port_devlink_setup(struct dsa_port *dp); +void dsa_port_devlink_teardown(struct dsa_port *dp); +void dsa_switch_devlink_register(struct dsa_switch *ds); +void dsa_switch_devlink_unregister(struct dsa_switch *ds); +int dsa_switch_devlink_alloc(struct dsa_switch *ds); +void dsa_switch_devlink_free(struct dsa_switch *ds); + +#endif diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 64b14f655b23..e5f156940c67 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1,453 +1,1637 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * net/dsa/dsa.c - Hardware switch handling + * DSA topology and switch handling + * * Copyright (c) 2008-2009 Marvell Semiconductor * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> + * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> */ #include <linux/device.h> +#include <linux/err.h> #include <linux/list.h> #include <linux/module.h> #include <linux/netdevice.h> -#include <linux/sysfs.h> -#include <linux/ptp_classify.h> +#include <linux/slab.h> +#include <linux/rtnetlink.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <net/sch_generic.h> + +#include "devlink.h" +#include "dsa.h" +#include "master.h" +#include "netlink.h" +#include "port.h" +#include "slave.h" +#include "switch.h" +#include "tag.h" + +#define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG + +static DEFINE_MUTEX(dsa2_mutex); +LIST_HEAD(dsa_tree_list); -#include "dsa_priv.h" +static struct workqueue_struct *dsa_owq; -static LIST_HEAD(dsa_tag_drivers_list); -static DEFINE_MUTEX(dsa_tag_drivers_lock); +/* Track the bridges with forwarding offload enabled */ +static unsigned long dsa_fwd_offloading_bridges; -static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, - struct net_device *dev) +bool dsa_schedule_work(struct work_struct *work) { - /* Just return the original SKB */ - return skb; + return queue_work(dsa_owq, work); } -static const struct dsa_device_ops none_ops = { - .name = "none", - .proto = DSA_TAG_PROTO_NONE, - .xmit = dsa_slave_notag_xmit, - .rcv = NULL, -}; +void dsa_flush_workqueue(void) +{ + flush_workqueue(dsa_owq); +} +EXPORT_SYMBOL_GPL(dsa_flush_workqueue); -DSA_TAG_DRIVER(none_ops); +/** + * dsa_lag_map() - Map LAG structure to a linear LAG array + * @dst: Tree in which to record the mapping. + * @lag: LAG structure that is to be mapped to the tree's array. + * + * dsa_lag_id/dsa_lag_by_id can then be used to translate between the + * two spaces. The size of the mapping space is determined by the + * driver by setting ds->num_lag_ids. It is perfectly legal to leave + * it unset if it is not needed, in which case these functions become + * no-ops. + */ +void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag) +{ + unsigned int id; + + for (id = 1; id <= dst->lags_len; id++) { + if (!dsa_lag_by_id(dst, id)) { + dst->lags[id - 1] = lag; + lag->id = id; + return; + } + } -static void dsa_tag_driver_register(struct dsa_tag_driver *dsa_tag_driver, - struct module *owner) + /* No IDs left, which is OK. Some drivers do not need it. The + * ones that do, e.g. mv88e6xxx, will discover that dsa_lag_id + * returns an error for this device when joining the LAG. The + * driver can then return -EOPNOTSUPP back to DSA, which will + * fall back to a software LAG. + */ +} + +/** + * dsa_lag_unmap() - Remove a LAG ID mapping + * @dst: Tree in which the mapping is recorded. + * @lag: LAG structure that was mapped. + * + * As there may be multiple users of the mapping, it is only removed + * if there are no other references to it. + */ +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag) { - dsa_tag_driver->owner = owner; + unsigned int id; - mutex_lock(&dsa_tag_drivers_lock); - list_add_tail(&dsa_tag_driver->list, &dsa_tag_drivers_list); - mutex_unlock(&dsa_tag_drivers_lock); + dsa_lags_foreach_id(id, dst) { + if (dsa_lag_by_id(dst, id) == lag) { + dst->lags[id - 1] = NULL; + lag->id = 0; + break; + } + } } -void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], - unsigned int count, struct module *owner) +struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, + const struct net_device *lag_dev) { - unsigned int i; + struct dsa_port *dp; - for (i = 0; i < count; i++) - dsa_tag_driver_register(dsa_tag_driver_array[i], owner); + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_lag_dev_get(dp) == lag_dev) + return dp->lag; + + return NULL; } -static void dsa_tag_driver_unregister(struct dsa_tag_driver *dsa_tag_driver) +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br) { - mutex_lock(&dsa_tag_drivers_lock); - list_del(&dsa_tag_driver->list); - mutex_unlock(&dsa_tag_drivers_lock); + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_bridge_dev_get(dp) == br) + return dp->bridge; + + return NULL; } -EXPORT_SYMBOL_GPL(dsa_tag_drivers_register); -void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], - unsigned int count) +static int dsa_bridge_num_find(const struct net_device *bridge_dev) { - unsigned int i; + struct dsa_switch_tree *dst; - for (i = 0; i < count; i++) - dsa_tag_driver_unregister(dsa_tag_driver_array[i]); + list_for_each_entry(dst, &dsa_tree_list, list) { + struct dsa_bridge *bridge; + + bridge = dsa_tree_bridge_find(dst, bridge_dev); + if (bridge) + return bridge->num; + } + + return 0; } -EXPORT_SYMBOL_GPL(dsa_tag_drivers_unregister); -const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) { - return ops->name; -}; + unsigned int bridge_num = dsa_bridge_num_find(bridge_dev); + + /* Switches without FDB isolation support don't get unique + * bridge numbering + */ + if (!max) + return 0; + + if (!bridge_num) { + /* First port that requests FDB isolation or TX forwarding + * offload for this bridge + */ + bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, + DSA_MAX_NUM_OFFLOADING_BRIDGES, + 1); + if (bridge_num >= max) + return 0; + + set_bit(bridge_num, &dsa_fwd_offloading_bridges); + } + + return bridge_num; +} + +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num) +{ + /* Since we refcount bridges, we know that when we call this function + * it is no longer in use, so we can just go ahead and remove it from + * the bit mask. + */ + clear_bit(bridge_num, &dsa_fwd_offloading_bridges); +} + +struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) +{ + struct dsa_switch_tree *dst; + struct dsa_port *dp; + + list_for_each_entry(dst, &dsa_tree_list, list) { + if (dst->index != tree_index) + continue; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->ds->index != sw_index) + continue; + + return dp->ds; + } + } + + return NULL; +} +EXPORT_SYMBOL_GPL(dsa_switch_find); + +static struct dsa_switch_tree *dsa_tree_find(int index) +{ + struct dsa_switch_tree *dst; + + list_for_each_entry(dst, &dsa_tree_list, list) + if (dst->index == index) + return dst; + + return NULL; +} + +static struct dsa_switch_tree *dsa_tree_alloc(int index) +{ + struct dsa_switch_tree *dst; + + dst = kzalloc(sizeof(*dst), GFP_KERNEL); + if (!dst) + return NULL; + + dst->index = index; + + INIT_LIST_HEAD(&dst->rtable); + + INIT_LIST_HEAD(&dst->ports); + + INIT_LIST_HEAD(&dst->list); + list_add_tail(&dst->list, &dsa_tree_list); + + kref_init(&dst->refcount); -/* Function takes a reference on the module owning the tagger, - * so dsa_tag_driver_put must be called afterwards. + return dst; +} + +static void dsa_tree_free(struct dsa_switch_tree *dst) +{ + if (dst->tag_ops) + dsa_tag_driver_put(dst->tag_ops); + list_del(&dst->list); + kfree(dst); +} + +static struct dsa_switch_tree *dsa_tree_get(struct dsa_switch_tree *dst) +{ + if (dst) + kref_get(&dst->refcount); + + return dst; +} + +static struct dsa_switch_tree *dsa_tree_touch(int index) +{ + struct dsa_switch_tree *dst; + + dst = dsa_tree_find(index); + if (dst) + return dsa_tree_get(dst); + else + return dsa_tree_alloc(index); +} + +static void dsa_tree_release(struct kref *ref) +{ + struct dsa_switch_tree *dst; + + dst = container_of(ref, struct dsa_switch_tree, refcount); + + dsa_tree_free(dst); +} + +static void dsa_tree_put(struct dsa_switch_tree *dst) +{ + if (dst) + kref_put(&dst->refcount, dsa_tree_release); +} + +static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, + struct device_node *dn) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dp->dn == dn) + return dp; + + return NULL; +} + +static struct dsa_link *dsa_link_touch(struct dsa_port *dp, + struct dsa_port *link_dp) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst; + struct dsa_link *dl; + + dst = ds->dst; + + list_for_each_entry(dl, &dst->rtable, list) + if (dl->dp == dp && dl->link_dp == link_dp) + return dl; + + dl = kzalloc(sizeof(*dl), GFP_KERNEL); + if (!dl) + return NULL; + + dl->dp = dp; + dl->link_dp = link_dp; + + INIT_LIST_HEAD(&dl->list); + list_add_tail(&dl->list, &dst->rtable); + + return dl; +} + +static bool dsa_port_setup_routing_table(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst = ds->dst; + struct device_node *dn = dp->dn; + struct of_phandle_iterator it; + struct dsa_port *link_dp; + struct dsa_link *dl; + int err; + + of_for_each_phandle(&it, err, dn, "link", NULL, 0) { + link_dp = dsa_tree_find_port_by_node(dst, it.node); + if (!link_dp) { + of_node_put(it.node); + return false; + } + + dl = dsa_link_touch(dp, link_dp); + if (!dl) { + of_node_put(it.node); + return false; + } + } + + return true; +} + +static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst) +{ + bool complete = true; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_dsa(dp)) { + complete = dsa_port_setup_routing_table(dp); + if (!complete) + break; + } + } + + return complete; +} + +static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_cpu(dp)) + return dp; + + return NULL; +} + +struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst) +{ + struct device_node *ethernet; + struct net_device *master; + struct dsa_port *cpu_dp; + + cpu_dp = dsa_tree_find_first_cpu(dst); + ethernet = of_parse_phandle(cpu_dp->dn, "ethernet", 0); + master = of_find_net_device_by_node(ethernet); + of_node_put(ethernet); + + return master; +} + +/* Assign the default CPU port (the first one in the tree) to all ports of the + * fabric which don't already have one as part of their own switch. */ -const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf) +static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) { - const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); - struct dsa_tag_driver *dsa_tag_driver; + struct dsa_port *cpu_dp, *dp; - mutex_lock(&dsa_tag_drivers_lock); - list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { - const struct dsa_device_ops *tmp = dsa_tag_driver->ops; + cpu_dp = dsa_tree_find_first_cpu(dst); + if (!cpu_dp) { + pr_err("DSA: tree %d has no CPU port\n", dst->index); + return -EINVAL; + } - if (!sysfs_streq(buf, tmp->name)) + list_for_each_entry(dp, &dst->ports, list) { + if (dp->cpu_dp) continue; - if (!try_module_get(dsa_tag_driver->owner)) - break; + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) + dp->cpu_dp = cpu_dp; + } - ops = tmp; - break; + return 0; +} + +/* Perform initial assignment of CPU ports to user ports and DSA links in the + * fabric, giving preference to CPU ports local to each switch. Default to + * using the first CPU port in the switch tree if the port does not have a CPU + * port local to this switch. + */ +static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp, *dp; + + list_for_each_entry(cpu_dp, &dst->ports, list) { + if (!dsa_port_is_cpu(cpu_dp)) + continue; + + /* Prefer a local CPU port */ + dsa_switch_for_each_port(dp, cpu_dp->ds) { + /* Prefer the first local CPU port found */ + if (dp->cpu_dp) + continue; + + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) + dp->cpu_dp = cpu_dp; + } } - mutex_unlock(&dsa_tag_drivers_lock); - return ops; + return dsa_tree_setup_default_cpu(dst); } -const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol) +static void dsa_tree_teardown_cpu_ports(struct dsa_switch_tree *dst) { - struct dsa_tag_driver *dsa_tag_driver; - const struct dsa_device_ops *ops; - bool found = false; + struct dsa_port *dp; - request_module("%s%d", DSA_TAG_DRIVER_ALIAS, tag_protocol); + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) + dp->cpu_dp = NULL; +} - mutex_lock(&dsa_tag_drivers_lock); - list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { - ops = dsa_tag_driver->ops; - if (ops->proto == tag_protocol) { - found = true; +static int dsa_port_setup(struct dsa_port *dp) +{ + bool dsa_port_link_registered = false; + struct dsa_switch *ds = dp->ds; + bool dsa_port_enabled = false; + int err = 0; + + if (dp->setup) + return 0; + + err = dsa_port_devlink_setup(dp); + if (err) + return err; + + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + dsa_port_disable(dp); + break; + case DSA_PORT_TYPE_CPU: + if (dp->dn) { + err = dsa_shared_port_link_register_of(dp); + if (err) + break; + dsa_port_link_registered = true; + } else { + dev_warn(ds->dev, + "skipping link registration for CPU port %d\n", + dp->index); + } + + err = dsa_port_enable(dp, NULL); + if (err) break; + dsa_port_enabled = true; + + break; + case DSA_PORT_TYPE_DSA: + if (dp->dn) { + err = dsa_shared_port_link_register_of(dp); + if (err) + break; + dsa_port_link_registered = true; + } else { + dev_warn(ds->dev, + "skipping link registration for DSA port %d\n", + dp->index); } + + err = dsa_port_enable(dp, NULL); + if (err) + break; + dsa_port_enabled = true; + + break; + case DSA_PORT_TYPE_USER: + of_get_mac_address(dp->dn, dp->mac); + err = dsa_slave_create(dp); + break; } - if (found) { - if (!try_module_get(dsa_tag_driver->owner)) - ops = ERR_PTR(-ENOPROTOOPT); - } else { - ops = ERR_PTR(-ENOPROTOOPT); + if (err && dsa_port_enabled) + dsa_port_disable(dp); + if (err && dsa_port_link_registered) + dsa_shared_port_link_unregister_of(dp); + if (err) { + dsa_port_devlink_teardown(dp); + return err; } - mutex_unlock(&dsa_tag_drivers_lock); + dp->setup = true; - return ops; + return 0; } -void dsa_tag_driver_put(const struct dsa_device_ops *ops) +static void dsa_port_teardown(struct dsa_port *dp) { - struct dsa_tag_driver *dsa_tag_driver; + if (!dp->setup) + return; - mutex_lock(&dsa_tag_drivers_lock); - list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { - if (dsa_tag_driver->ops == ops) { - module_put(dsa_tag_driver->owner); - break; + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + break; + case DSA_PORT_TYPE_CPU: + dsa_port_disable(dp); + if (dp->dn) + dsa_shared_port_link_unregister_of(dp); + break; + case DSA_PORT_TYPE_DSA: + dsa_port_disable(dp); + if (dp->dn) + dsa_shared_port_link_unregister_of(dp); + break; + case DSA_PORT_TYPE_USER: + if (dp->slave) { + dsa_slave_destroy(dp->slave); + dp->slave = NULL; } + break; } - mutex_unlock(&dsa_tag_drivers_lock); + + dsa_port_devlink_teardown(dp); + + dp->setup = false; } -static int dev_is_class(struct device *dev, void *class) +static int dsa_port_setup_as_unused(struct dsa_port *dp) { - if (dev->class != NULL && !strcmp(dev->class->name, class)) - return 1; + dp->type = DSA_PORT_TYPE_UNUSED; + return dsa_port_setup(dp); +} + +static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds) +{ + const struct dsa_device_ops *tag_ops = ds->dst->tag_ops; + struct dsa_switch_tree *dst = ds->dst; + int err; + + if (tag_ops->proto == dst->default_proto) + goto connect; + + rtnl_lock(); + err = ds->ops->change_tag_protocol(ds, tag_ops->proto); + rtnl_unlock(); + if (err) { + dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n", + tag_ops->name, ERR_PTR(err)); + return err; + } + +connect: + if (tag_ops->connect) { + err = tag_ops->connect(ds); + if (err) + return err; + } + + if (ds->ops->connect_tag_protocol) { + err = ds->ops->connect_tag_protocol(ds, tag_ops->proto); + if (err) { + dev_err(ds->dev, + "Unable to connect to tag protocol \"%s\": %pe\n", + tag_ops->name, ERR_PTR(err)); + goto disconnect; + } + } return 0; + +disconnect: + if (tag_ops->disconnect) + tag_ops->disconnect(ds); + + return err; } -static struct device *dev_find_class(struct device *parent, char *class) +static void dsa_switch_teardown_tag_protocol(struct dsa_switch *ds) { - if (dev_is_class(parent, class)) { - get_device(parent); - return parent; - } + const struct dsa_device_ops *tag_ops = ds->dst->tag_ops; - return device_find_child(parent, class, dev_is_class); + if (tag_ops->disconnect) + tag_ops->disconnect(ds); } -struct net_device *dsa_dev_to_net_device(struct device *dev) +static int dsa_switch_setup(struct dsa_switch *ds) { - struct device *d; + struct device_node *dn; + int err; - d = dev_find_class(dev, "net"); - if (d != NULL) { - struct net_device *nd; + if (ds->setup) + return 0; - nd = to_net_dev(d); - dev_hold(nd); - put_device(d); + /* Initialize ds->phys_mii_mask before registering the slave MDIO bus + * driver and before ops->setup() has run, since the switch drivers and + * the slave MDIO bus driver rely on these values for probing PHY + * devices or not + */ + ds->phys_mii_mask |= dsa_user_ports(ds); - return nd; + err = dsa_switch_devlink_alloc(ds); + if (err) + return err; + + err = dsa_switch_register_notifier(ds); + if (err) + goto devlink_free; + + ds->configure_vlan_while_not_filtering = true; + + err = ds->ops->setup(ds); + if (err < 0) + goto unregister_notifier; + + err = dsa_switch_setup_tag_protocol(ds); + if (err) + goto teardown; + + if (!ds->slave_mii_bus && ds->ops->phy_read) { + ds->slave_mii_bus = mdiobus_alloc(); + if (!ds->slave_mii_bus) { + err = -ENOMEM; + goto teardown; + } + + dsa_slave_mii_bus_init(ds); + + dn = of_get_child_by_name(ds->dev->of_node, "mdio"); + + err = of_mdiobus_register(ds->slave_mii_bus, dn); + of_node_put(dn); + if (err < 0) + goto free_slave_mii_bus; } - return NULL; + dsa_switch_devlink_register(ds); + + ds->setup = true; + return 0; + +free_slave_mii_bus: + if (ds->slave_mii_bus && ds->ops->phy_read) + mdiobus_free(ds->slave_mii_bus); +teardown: + if (ds->ops->teardown) + ds->ops->teardown(ds); +unregister_notifier: + dsa_switch_unregister_notifier(ds); +devlink_free: + dsa_switch_devlink_free(ds); + return err; } -EXPORT_SYMBOL_GPL(dsa_dev_to_net_device); -/* Determine if we should defer delivery of skb until we have a rx timestamp. - * - * Called from dsa_switch_rcv. For now, this will only work if tagging is - * enabled on the switch. Normally the MAC driver would retrieve the hardware - * timestamp when it reads the packet out of the hardware. However in a DSA - * switch, the DSA driver owning the interface to which the packet is - * delivered is never notified unless we do so here. +static void dsa_switch_teardown(struct dsa_switch *ds) +{ + if (!ds->setup) + return; + + dsa_switch_devlink_unregister(ds); + + if (ds->slave_mii_bus && ds->ops->phy_read) { + mdiobus_unregister(ds->slave_mii_bus); + mdiobus_free(ds->slave_mii_bus); + ds->slave_mii_bus = NULL; + } + + dsa_switch_teardown_tag_protocol(ds); + + if (ds->ops->teardown) + ds->ops->teardown(ds); + + dsa_switch_unregister_notifier(ds); + + dsa_switch_devlink_free(ds); + + ds->setup = false; +} + +/* First tear down the non-shared, then the shared ports. This ensures that + * all work items scheduled by our switchdev handlers for user ports have + * completed before we destroy the refcounting kept on the shared ports. */ -static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p, - struct sk_buff *skb) +static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst) { - struct dsa_switch *ds = p->dp->ds; - unsigned int type; + struct dsa_port *dp; - if (skb_headroom(skb) < ETH_HLEN) - return false; + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) + dsa_port_teardown(dp); + + dsa_flush_workqueue(); + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) + dsa_port_teardown(dp); +} - __skb_push(skb, ETH_HLEN); +static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; - type = ptp_classify_raw(skb); + list_for_each_entry(dp, &dst->ports, list) + dsa_switch_teardown(dp->ds); +} - __skb_pull(skb, ETH_HLEN); +/* Bring shared ports up first, then non-shared ports */ +static int dsa_tree_setup_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + int err = 0; - if (type == PTP_CLASS_NONE) - return false; + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) { + err = dsa_port_setup(dp); + if (err) + goto teardown; + } + } - if (likely(ds->ops->port_rxtstamp)) - return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) { + err = dsa_port_setup(dp); + if (err) { + err = dsa_port_setup_as_unused(dp); + if (err) + goto teardown; + } + } + } - return false; + return 0; + +teardown: + dsa_tree_teardown_ports(dst); + + return err; } -static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *unused) +static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) { - struct dsa_port *cpu_dp = dev->dsa_ptr; - struct sk_buff *nskb = NULL; - struct dsa_slave_priv *p; + struct dsa_port *dp; + int err = 0; - if (unlikely(!cpu_dp)) { - kfree_skb(skb); - return 0; + list_for_each_entry(dp, &dst->ports, list) { + err = dsa_switch_setup(dp->ds); + if (err) { + dsa_tree_teardown_switches(dst); + break; + } } - skb = skb_unshare(skb, GFP_ATOMIC); - if (!skb) - return 0; + return err; +} - nskb = cpu_dp->rcv(skb, dev); - if (!nskb) { - kfree_skb(skb); - return 0; +static int dsa_tree_setup_master(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp; + int err = 0; + + rtnl_lock(); + + dsa_tree_for_each_cpu_port(cpu_dp, dst) { + struct net_device *master = cpu_dp->master; + bool admin_up = (master->flags & IFF_UP) && + !qdisc_tx_is_noop(master); + + err = dsa_master_setup(master, cpu_dp); + if (err) + break; + + /* Replay master state event */ + dsa_tree_master_admin_state_change(dst, master, admin_up); + dsa_tree_master_oper_state_change(dst, master, + netif_oper_up(master)); } - skb = nskb; - skb_push(skb, ETH_HLEN); - skb->pkt_type = PACKET_HOST; - skb->protocol = eth_type_trans(skb, skb->dev); + rtnl_unlock(); + + return err; +} + +static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp; - if (unlikely(!dsa_slave_dev_check(skb->dev))) { - /* Packet is to be injected directly on an upper - * device, e.g. a team/bond, so skip all DSA-port - * specific actions. + rtnl_lock(); + + dsa_tree_for_each_cpu_port(cpu_dp, dst) { + struct net_device *master = cpu_dp->master; + + /* Synthesizing an "admin down" state is sufficient for + * the switches to get a notification if the master is + * currently up and running. */ - netif_rx(skb); - return 0; + dsa_tree_master_admin_state_change(dst, master, false); + + dsa_master_teardown(master); } - p = netdev_priv(skb->dev); + rtnl_unlock(); +} - if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { - nskb = dsa_untag_bridge_pvid(skb); - if (!nskb) { - kfree_skb(skb); - return 0; - } - skb = nskb; +static int dsa_tree_setup_lags(struct dsa_switch_tree *dst) +{ + unsigned int len = 0; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->ds->num_lag_ids > len) + len = dp->ds->num_lag_ids; } - dev_sw_netstats_rx_add(skb->dev, skb->len); + if (!len) + return 0; + + dst->lags = kcalloc(len, sizeof(*dst->lags), GFP_KERNEL); + if (!dst->lags) + return -ENOMEM; + + dst->lags_len = len; + return 0; +} + +static void dsa_tree_teardown_lags(struct dsa_switch_tree *dst) +{ + kfree(dst->lags); +} + +static int dsa_tree_setup(struct dsa_switch_tree *dst) +{ + bool complete; + int err; + + if (dst->setup) { + pr_err("DSA: tree %d already setup! Disjoint trees?\n", + dst->index); + return -EEXIST; + } - if (dsa_skb_defer_rx_timestamp(p, skb)) + complete = dsa_tree_setup_routing_table(dst); + if (!complete) return 0; - gro_cells_receive(&p->gcells, skb); + err = dsa_tree_setup_cpu_ports(dst); + if (err) + return err; + + err = dsa_tree_setup_switches(dst); + if (err) + goto teardown_cpu_ports; + + err = dsa_tree_setup_ports(dst); + if (err) + goto teardown_switches; + + err = dsa_tree_setup_master(dst); + if (err) + goto teardown_ports; + + err = dsa_tree_setup_lags(dst); + if (err) + goto teardown_master; + + dst->setup = true; + + pr_info("DSA: tree %d setup\n", dst->index); return 0; + +teardown_master: + dsa_tree_teardown_master(dst); +teardown_ports: + dsa_tree_teardown_ports(dst); +teardown_switches: + dsa_tree_teardown_switches(dst); +teardown_cpu_ports: + dsa_tree_teardown_cpu_ports(dst); + + return err; } -#ifdef CONFIG_PM_SLEEP -static bool dsa_port_is_initialized(const struct dsa_port *dp) +static void dsa_tree_teardown(struct dsa_switch_tree *dst) { - return dp->type == DSA_PORT_TYPE_USER && dp->slave; + struct dsa_link *dl, *next; + + if (!dst->setup) + return; + + dsa_tree_teardown_lags(dst); + + dsa_tree_teardown_master(dst); + + dsa_tree_teardown_ports(dst); + + dsa_tree_teardown_switches(dst); + + dsa_tree_teardown_cpu_ports(dst); + + list_for_each_entry_safe(dl, next, &dst->rtable, list) { + list_del(&dl->list); + kfree(dl); + } + + pr_info("DSA: tree %d torn down\n", dst->index); + + dst->setup = false; } -int dsa_switch_suspend(struct dsa_switch *ds) +static int dsa_tree_bind_tag_proto(struct dsa_switch_tree *dst, + const struct dsa_device_ops *tag_ops) +{ + const struct dsa_device_ops *old_tag_ops = dst->tag_ops; + struct dsa_notifier_tag_proto_info info; + int err; + + dst->tag_ops = tag_ops; + + /* Notify the switches from this tree about the connection + * to the new tagger + */ + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_CONNECT, &info); + if (err && err != -EOPNOTSUPP) + goto out_disconnect; + + /* Notify the old tagger about the disconnection from this tree */ + info.tag_ops = old_tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); + + return 0; + +out_disconnect: + info.tag_ops = tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); + dst->tag_ops = old_tag_ops; + + return err; +} + +/* Since the dsa/tagging sysfs device attribute is per master, the assumption + * is that all DSA switches within a tree share the same tagger, otherwise + * they would have formed disjoint trees (different "dsa,member" values). + */ +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops) { + struct dsa_notifier_tag_proto_info info; struct dsa_port *dp; - int ret = 0; + int err = -EBUSY; + + if (!rtnl_trylock()) + return restart_syscall(); + + /* At the moment we don't allow changing the tag protocol under + * traffic. The rtnl_mutex also happens to serialize concurrent + * attempts to change the tagging protocol. If we ever lift the IFF_UP + * restriction, there needs to be another mutex which serializes this. + */ + dsa_tree_for_each_user_port(dp, dst) { + if (dsa_port_to_master(dp)->flags & IFF_UP) + goto out_unlock; + + if (dp->slave->flags & IFF_UP) + goto out_unlock; + } - /* Suspend slave network devices */ - dsa_switch_for_each_port(dp, ds) { - if (!dsa_port_is_initialized(dp)) - continue; + /* Notify the tag protocol change */ + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); + if (err) + goto out_unwind_tagger; - ret = dsa_slave_suspend(dp->slave); - if (ret) - return ret; + err = dsa_tree_bind_tag_proto(dst, tag_ops); + if (err) + goto out_unwind_tagger; + + rtnl_unlock(); + + return 0; + +out_unwind_tagger: + info.tag_ops = old_tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); +out_unlock: + rtnl_unlock(); + return err; +} + +static void dsa_tree_master_state_change(struct dsa_switch_tree *dst, + struct net_device *master) +{ + struct dsa_notifier_master_state_info info; + struct dsa_port *cpu_dp = master->dsa_ptr; + + info.master = master; + info.operational = dsa_port_master_is_operational(cpu_dp); + + dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info); +} + +void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + /* Don't keep track of admin state on LAG DSA masters, + * but rather just of physical DSA masters + */ + if (netif_is_lag_master(master)) + return; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (up && cpu_dp->master_oper_up)) + notify = true; + + cpu_dp->master_admin_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + +void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + /* Don't keep track of oper state on LAG DSA masters, + * but rather just of physical DSA masters + */ + if (netif_is_lag_master(master)) + return; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (cpu_dp->master_admin_up && up)) + notify = true; + + cpu_dp->master_oper_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + +static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) +{ + struct dsa_switch_tree *dst = ds->dst; + struct dsa_port *dp; + + dsa_switch_for_each_port(dp, ds) + if (dp->index == index) + return dp; + + dp = kzalloc(sizeof(*dp), GFP_KERNEL); + if (!dp) + return NULL; + + dp->ds = ds; + dp->index = index; + + mutex_init(&dp->addr_lists_lock); + mutex_init(&dp->vlans_lock); + INIT_LIST_HEAD(&dp->fdbs); + INIT_LIST_HEAD(&dp->mdbs); + INIT_LIST_HEAD(&dp->vlans); + INIT_LIST_HEAD(&dp->list); + list_add_tail(&dp->list, &dst->ports); + + return dp; +} + +static int dsa_port_parse_user(struct dsa_port *dp, const char *name) +{ + dp->type = DSA_PORT_TYPE_USER; + dp->name = name; + + return 0; +} + +static int dsa_port_parse_dsa(struct dsa_port *dp) +{ + dp->type = DSA_PORT_TYPE_DSA; + + return 0; +} + +static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, + struct net_device *master) +{ + enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; + struct dsa_switch *mds, *ds = dp->ds; + unsigned int mdp_upstream; + struct dsa_port *mdp; + + /* It is possible to stack DSA switches onto one another when that + * happens the switch driver may want to know if its tagging protocol + * is going to work in such a configuration. + */ + if (dsa_slave_dev_check(master)) { + mdp = dsa_slave_to_port(master); + mds = mdp->ds; + mdp_upstream = dsa_upstream_port(mds, mdp->index); + tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, + DSA_TAG_PROTO_NONE); } - if (ds->ops->suspend) - ret = ds->ops->suspend(ds); + /* If the master device is not itself a DSA slave in a disjoint DSA + * tree, then return immediately. + */ + return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); +} - return ret; +static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, + const char *user_protocol) +{ + const struct dsa_device_ops *tag_ops = NULL; + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst = ds->dst; + enum dsa_tag_protocol default_proto; + + /* Find out which protocol the switch would prefer. */ + default_proto = dsa_get_tag_protocol(dp, master); + if (dst->default_proto) { + if (dst->default_proto != default_proto) { + dev_err(ds->dev, + "A DSA switch tree can have only one tagging protocol\n"); + return -EINVAL; + } + } else { + dst->default_proto = default_proto; + } + + /* See if the user wants to override that preference. */ + if (user_protocol) { + if (!ds->ops->change_tag_protocol) { + dev_err(ds->dev, "Tag protocol cannot be modified\n"); + return -EINVAL; + } + + tag_ops = dsa_tag_driver_get_by_name(user_protocol); + if (IS_ERR(tag_ops)) { + dev_warn(ds->dev, + "Failed to find a tagging driver for protocol %s, using default\n", + user_protocol); + tag_ops = NULL; + } + } + + if (!tag_ops) + tag_ops = dsa_tag_driver_get_by_id(default_proto); + + if (IS_ERR(tag_ops)) { + if (PTR_ERR(tag_ops) == -ENOPROTOOPT) + return -EPROBE_DEFER; + + dev_warn(ds->dev, "No tagger for this switch\n"); + return PTR_ERR(tag_ops); + } + + if (dst->tag_ops) { + if (dst->tag_ops != tag_ops) { + dev_err(ds->dev, + "A DSA switch tree can have only one tagging protocol\n"); + + dsa_tag_driver_put(tag_ops); + return -EINVAL; + } + + /* In the case of multiple CPU ports per switch, the tagging + * protocol is still reference-counted only per switch tree. + */ + dsa_tag_driver_put(tag_ops); + } else { + dst->tag_ops = tag_ops; + } + + dp->master = master; + dp->type = DSA_PORT_TYPE_CPU; + dsa_port_set_tag_protocol(dp, dst->tag_ops); + dp->dst = dst; + + /* At this point, the tree may be configured to use a different + * tagger than the one chosen by the switch driver during + * .setup, in the case when a user selects a custom protocol + * through the DT. + * + * This is resolved by syncing the driver with the tree in + * dsa_switch_setup_tag_protocol once .setup has run and the + * driver is ready to accept calls to .change_tag_protocol. If + * the driver does not support the custom protocol at that + * point, the tree is wholly rejected, thereby ensuring that the + * tree and driver are always in agreement on the protocol to + * use. + */ + return 0; } -EXPORT_SYMBOL_GPL(dsa_switch_suspend); -int dsa_switch_resume(struct dsa_switch *ds) +static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) +{ + struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0); + const char *name = of_get_property(dn, "label", NULL); + bool link = of_property_read_bool(dn, "link"); + + dp->dn = dn; + + if (ethernet) { + struct net_device *master; + const char *user_protocol; + + master = of_find_net_device_by_node(ethernet); + of_node_put(ethernet); + if (!master) + return -EPROBE_DEFER; + + user_protocol = of_get_property(dn, "dsa-tag-protocol", NULL); + return dsa_port_parse_cpu(dp, master, user_protocol); + } + + if (link) + return dsa_port_parse_dsa(dp); + + return dsa_port_parse_user(dp, name); +} + +static int dsa_switch_parse_ports_of(struct dsa_switch *ds, + struct device_node *dn) { + struct device_node *ports, *port; struct dsa_port *dp; - int ret = 0; + int err = 0; + u32 reg; + + ports = of_get_child_by_name(dn, "ports"); + if (!ports) { + /* The second possibility is "ethernet-ports" */ + ports = of_get_child_by_name(dn, "ethernet-ports"); + if (!ports) { + dev_err(ds->dev, "no ports child node found\n"); + return -EINVAL; + } + } - if (ds->ops->resume) - ret = ds->ops->resume(ds); + for_each_available_child_of_node(ports, port) { + err = of_property_read_u32(port, "reg", ®); + if (err) { + of_node_put(port); + goto out_put_node; + } - if (ret) - return ret; + if (reg >= ds->num_ports) { + dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%u)\n", + port, reg, ds->num_ports); + of_node_put(port); + err = -EINVAL; + goto out_put_node; + } - /* Resume slave network devices */ - dsa_switch_for_each_port(dp, ds) { - if (!dsa_port_is_initialized(dp)) - continue; + dp = dsa_to_port(ds, reg); - ret = dsa_slave_resume(dp->slave); - if (ret) - return ret; + err = dsa_port_parse_of(dp, port); + if (err) { + of_node_put(port); + goto out_put_node; + } + } + +out_put_node: + of_node_put(ports); + return err; +} + +static int dsa_switch_parse_member_of(struct dsa_switch *ds, + struct device_node *dn) +{ + u32 m[2] = { 0, 0 }; + int sz; + + /* Don't error out if this optional property isn't found */ + sz = of_property_read_variable_u32_array(dn, "dsa,member", m, 2, 2); + if (sz < 0 && sz != -EINVAL) + return sz; + + ds->index = m[1]; + + ds->dst = dsa_tree_touch(m[0]); + if (!ds->dst) + return -ENOMEM; + + if (dsa_switch_find(ds->dst->index, ds->index)) { + dev_err(ds->dev, + "A DSA switch with index %d already exists in tree %d\n", + ds->index, ds->dst->index); + return -EEXIST; } + if (ds->dst->last_switch < ds->index) + ds->dst->last_switch = ds->index; + return 0; } -EXPORT_SYMBOL_GPL(dsa_switch_resume); -#endif -static struct packet_type dsa_pack_type __read_mostly = { - .type = cpu_to_be16(ETH_P_XDSA), - .func = dsa_switch_rcv, -}; +static int dsa_switch_touch_ports(struct dsa_switch *ds) +{ + struct dsa_port *dp; + int port; -static struct workqueue_struct *dsa_owq; + for (port = 0; port < ds->num_ports; port++) { + dp = dsa_port_touch(ds, port); + if (!dp) + return -ENOMEM; + } -bool dsa_schedule_work(struct work_struct *work) + return 0; +} + +static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn) { - return queue_work(dsa_owq, work); + int err; + + err = dsa_switch_parse_member_of(ds, dn); + if (err) + return err; + + err = dsa_switch_touch_ports(ds); + if (err) + return err; + + return dsa_switch_parse_ports_of(ds, dn); } -void dsa_flush_workqueue(void) +static int dev_is_class(struct device *dev, void *class) { - flush_workqueue(dsa_owq); + if (dev->class != NULL && !strcmp(dev->class->name, class)) + return 1; + + return 0; } -EXPORT_SYMBOL_GPL(dsa_flush_workqueue); -int dsa_devlink_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) +static struct device *dev_find_class(struct device *parent, char *class) { - struct dsa_switch *ds = dsa_devlink_to_ds(dl); + if (dev_is_class(parent, class)) { + get_device(parent); + return parent; + } - if (!ds->ops->devlink_param_get) - return -EOPNOTSUPP; + return device_find_child(parent, class, dev_is_class); +} + +static struct net_device *dsa_dev_to_net_device(struct device *dev) +{ + struct device *d; + + d = dev_find_class(dev, "net"); + if (d != NULL) { + struct net_device *nd; + + nd = to_net_dev(d); + dev_hold(nd); + put_device(d); - return ds->ops->devlink_param_get(ds, id, ctx); + return nd; + } + + return NULL; } -EXPORT_SYMBOL_GPL(dsa_devlink_param_get); -int dsa_devlink_param_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) +static int dsa_port_parse(struct dsa_port *dp, const char *name, + struct device *dev) { - struct dsa_switch *ds = dsa_devlink_to_ds(dl); + if (!strcmp(name, "cpu")) { + struct net_device *master; + + master = dsa_dev_to_net_device(dev); + if (!master) + return -EPROBE_DEFER; + + dev_put(master); - if (!ds->ops->devlink_param_set) - return -EOPNOTSUPP; + return dsa_port_parse_cpu(dp, master, NULL); + } + + if (!strcmp(name, "dsa")) + return dsa_port_parse_dsa(dp); - return ds->ops->devlink_param_set(ds, id, ctx); + return dsa_port_parse_user(dp, name); } -EXPORT_SYMBOL_GPL(dsa_devlink_param_set); -int dsa_devlink_params_register(struct dsa_switch *ds, - const struct devlink_param *params, - size_t params_count) +static int dsa_switch_parse_ports(struct dsa_switch *ds, + struct dsa_chip_data *cd) { - return devlink_params_register(ds->devlink, params, params_count); + bool valid_name_found = false; + struct dsa_port *dp; + struct device *dev; + const char *name; + unsigned int i; + int err; + + for (i = 0; i < DSA_MAX_PORTS; i++) { + name = cd->port_names[i]; + dev = cd->netdev[i]; + dp = dsa_to_port(ds, i); + + if (!name) + continue; + + err = dsa_port_parse(dp, name, dev); + if (err) + return err; + + valid_name_found = true; + } + + if (!valid_name_found && i == DSA_MAX_PORTS) + return -EINVAL; + + return 0; } -EXPORT_SYMBOL_GPL(dsa_devlink_params_register); -void dsa_devlink_params_unregister(struct dsa_switch *ds, - const struct devlink_param *params, - size_t params_count) +static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd) { - devlink_params_unregister(ds->devlink, params, params_count); + int err; + + ds->cd = cd; + + /* We don't support interconnected switches nor multiple trees via + * platform data, so this is the unique switch of the tree. + */ + ds->index = 0; + ds->dst = dsa_tree_touch(0); + if (!ds->dst) + return -ENOMEM; + + err = dsa_switch_touch_ports(ds); + if (err) + return err; + + return dsa_switch_parse_ports(ds, cd); } -EXPORT_SYMBOL_GPL(dsa_devlink_params_unregister); -int dsa_devlink_resource_register(struct dsa_switch *ds, - const char *resource_name, - u64 resource_size, - u64 resource_id, - u64 parent_resource_id, - const struct devlink_resource_size_params *size_params) +static void dsa_switch_release_ports(struct dsa_switch *ds) { - return devlink_resource_register(ds->devlink, resource_name, - resource_size, resource_id, - parent_resource_id, - size_params); + struct dsa_port *dp, *next; + + dsa_switch_for_each_port_safe(dp, next, ds) { + WARN_ON(!list_empty(&dp->fdbs)); + WARN_ON(!list_empty(&dp->mdbs)); + WARN_ON(!list_empty(&dp->vlans)); + list_del(&dp->list); + kfree(dp); + } } -EXPORT_SYMBOL_GPL(dsa_devlink_resource_register); -void dsa_devlink_resources_unregister(struct dsa_switch *ds) +static int dsa_switch_probe(struct dsa_switch *ds) { - devlink_resources_unregister(ds->devlink); + struct dsa_switch_tree *dst; + struct dsa_chip_data *pdata; + struct device_node *np; + int err; + + if (!ds->dev) + return -ENODEV; + + pdata = ds->dev->platform_data; + np = ds->dev->of_node; + + if (!ds->num_ports) + return -EINVAL; + + if (np) { + err = dsa_switch_parse_of(ds, np); + if (err) + dsa_switch_release_ports(ds); + } else if (pdata) { + err = dsa_switch_parse(ds, pdata); + if (err) + dsa_switch_release_ports(ds); + } else { + err = -ENODEV; + } + + if (err) + return err; + + dst = ds->dst; + dsa_tree_get(dst); + err = dsa_tree_setup(dst); + if (err) { + dsa_switch_release_ports(ds); + dsa_tree_put(dst); + } + + return err; } -EXPORT_SYMBOL_GPL(dsa_devlink_resources_unregister); -void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, - u64 resource_id, - devlink_resource_occ_get_t *occ_get, - void *occ_get_priv) +int dsa_register_switch(struct dsa_switch *ds) { - return devlink_resource_occ_get_register(ds->devlink, resource_id, - occ_get, occ_get_priv); + int err; + + mutex_lock(&dsa2_mutex); + err = dsa_switch_probe(ds); + dsa_tree_put(ds->dst); + mutex_unlock(&dsa2_mutex); + + return err; } -EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_register); +EXPORT_SYMBOL_GPL(dsa_register_switch); -void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, - u64 resource_id) +static void dsa_switch_remove(struct dsa_switch *ds) { - devlink_resource_occ_get_unregister(ds->devlink, resource_id); + struct dsa_switch_tree *dst = ds->dst; + + dsa_tree_teardown(dst); + dsa_switch_release_ports(ds); + dsa_tree_put(dst); } -EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister); -struct devlink_region * -dsa_devlink_region_create(struct dsa_switch *ds, - const struct devlink_region_ops *ops, - u32 region_max_snapshots, u64 region_size) +void dsa_unregister_switch(struct dsa_switch *ds) { - return devlink_region_create(ds->devlink, ops, region_max_snapshots, - region_size); + mutex_lock(&dsa2_mutex); + dsa_switch_remove(ds); + mutex_unlock(&dsa2_mutex); } -EXPORT_SYMBOL_GPL(dsa_devlink_region_create); +EXPORT_SYMBOL_GPL(dsa_unregister_switch); -struct devlink_region * -dsa_devlink_port_region_create(struct dsa_switch *ds, - int port, - const struct devlink_port_region_ops *ops, - u32 region_max_snapshots, u64 region_size) +/* If the DSA master chooses to unregister its net_device on .shutdown, DSA is + * blocking that operation from completion, due to the dev_hold taken inside + * netdev_upper_dev_link. Unlink the DSA slave interfaces from being uppers of + * the DSA master, so that the system can reboot successfully. + */ +void dsa_switch_shutdown(struct dsa_switch *ds) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *master, *slave_dev; + struct dsa_port *dp; + + mutex_lock(&dsa2_mutex); + + if (!ds->setup) + goto out; + + rtnl_lock(); + + dsa_switch_for_each_user_port(dp, ds) { + master = dsa_port_to_master(dp); + slave_dev = dp->slave; + + netdev_upper_dev_unlink(master, slave_dev); + } + + /* Disconnect from further netdevice notifiers on the master, + * since netdev_uses_dsa() will now return false. + */ + dsa_switch_for_each_cpu_port(dp, ds) + dp->master->dsa_ptr = NULL; + + rtnl_unlock(); +out: + mutex_unlock(&dsa2_mutex); +} +EXPORT_SYMBOL_GPL(dsa_switch_shutdown); + +#ifdef CONFIG_PM_SLEEP +static bool dsa_port_is_initialized(const struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_USER && dp->slave; +} + +int dsa_switch_suspend(struct dsa_switch *ds) +{ + struct dsa_port *dp; + int ret = 0; + + /* Suspend slave network devices */ + dsa_switch_for_each_port(dp, ds) { + if (!dsa_port_is_initialized(dp)) + continue; + + ret = dsa_slave_suspend(dp->slave); + if (ret) + return ret; + } + + if (ds->ops->suspend) + ret = ds->ops->suspend(ds); - return devlink_port_region_create(&dp->devlink_port, ops, - region_max_snapshots, - region_size); + return ret; } -EXPORT_SYMBOL_GPL(dsa_devlink_port_region_create); +EXPORT_SYMBOL_GPL(dsa_switch_suspend); -void dsa_devlink_region_destroy(struct devlink_region *region) +int dsa_switch_resume(struct dsa_switch *ds) { - devlink_region_destroy(region); + struct dsa_port *dp; + int ret = 0; + + if (ds->ops->resume) + ret = ds->ops->resume(ds); + + if (ret) + return ret; + + /* Resume slave network devices */ + dsa_switch_for_each_port(dp, ds) { + if (!dsa_port_is_initialized(dp)) + continue; + + ret = dsa_slave_resume(dp->slave); + if (ret) + return ret; + } + + return 0; } -EXPORT_SYMBOL_GPL(dsa_devlink_region_destroy); +EXPORT_SYMBOL_GPL(dsa_switch_resume); +#endif struct dsa_port *dsa_port_from_netdev(struct net_device *netdev) { @@ -533,9 +1717,6 @@ static int __init dsa_init_module(void) dev_add_pack(&dsa_pack_type); - dsa_tag_driver_register(&DSA_TAG_DRIVER_NAME(none_ops), - THIS_MODULE); - rc = rtnl_link_register(&dsa_link_ops); if (rc) goto netlink_register_fail; @@ -543,7 +1724,6 @@ static int __init dsa_init_module(void) return 0; netlink_register_fail: - dsa_tag_driver_unregister(&DSA_TAG_DRIVER_NAME(none_ops)); dsa_slave_unregister_notifier(); dev_remove_pack(&dsa_pack_type); register_notifier_fail: @@ -556,7 +1736,6 @@ module_init(dsa_init_module); static void __exit dsa_cleanup_module(void) { rtnl_link_unregister(&dsa_link_ops); - dsa_tag_driver_unregister(&DSA_TAG_DRIVER_NAME(none_ops)); dsa_slave_unregister_notifier(); dev_remove_pack(&dsa_pack_type); diff --git a/net/dsa/dsa.h b/net/dsa/dsa.h new file mode 100644 index 000000000000..b7e17ae1094d --- /dev/null +++ b/net/dsa/dsa.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_H +#define __DSA_H + +#include <linux/list.h> +#include <linux/types.h> + +struct dsa_db; +struct dsa_device_ops; +struct dsa_lag; +struct dsa_switch_tree; +struct net_device; +struct work_struct; + +extern struct list_head dsa_tree_list; + +bool dsa_db_equal(const struct dsa_db *a, const struct dsa_db *b); +bool dsa_schedule_work(struct work_struct *work); +void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag); +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag); +struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, + const struct net_device *lag_dev); +struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst); +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops); +void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up); +void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up); +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num); +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br); + +#endif diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c deleted file mode 100644 index af0e2c0394ac..000000000000 --- a/net/dsa/dsa2.c +++ /dev/null @@ -1,1812 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/dsa/dsa2.c - Hardware switch handling, binding version 2 - * Copyright (c) 2008-2009 Marvell Semiconductor - * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> - * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> - */ - -#include <linux/device.h> -#include <linux/err.h> -#include <linux/list.h> -#include <linux/netdevice.h> -#include <linux/slab.h> -#include <linux/rtnetlink.h> -#include <linux/of.h> -#include <linux/of_mdio.h> -#include <linux/of_net.h> -#include <net/devlink.h> -#include <net/sch_generic.h> - -#include "dsa_priv.h" - -static DEFINE_MUTEX(dsa2_mutex); -LIST_HEAD(dsa_tree_list); - -/* Track the bridges with forwarding offload enabled */ -static unsigned long dsa_fwd_offloading_bridges; - -/** - * dsa_tree_notify - Execute code for all switches in a DSA switch tree. - * @dst: collection of struct dsa_switch devices to notify. - * @e: event, must be of type DSA_NOTIFIER_* - * @v: event-specific value. - * - * Given a struct dsa_switch_tree, this can be used to run a function once for - * each member DSA switch. The other alternative of traversing the tree is only - * through its ports list, which does not uniquely list the switches. - */ -int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v) -{ - struct raw_notifier_head *nh = &dst->nh; - int err; - - err = raw_notifier_call_chain(nh, e, v); - - return notifier_to_errno(err); -} - -/** - * dsa_broadcast - Notify all DSA trees in the system. - * @e: event, must be of type DSA_NOTIFIER_* - * @v: event-specific value. - * - * Can be used to notify the switching fabric of events such as cross-chip - * bridging between disjoint trees (such as islands of tagger-compatible - * switches bridged by an incompatible middle switch). - * - * WARNING: this function is not reliable during probe time, because probing - * between trees is asynchronous and not all DSA trees might have probed. - */ -int dsa_broadcast(unsigned long e, void *v) -{ - struct dsa_switch_tree *dst; - int err = 0; - - list_for_each_entry(dst, &dsa_tree_list, list) { - err = dsa_tree_notify(dst, e, v); - if (err) - break; - } - - return err; -} - -/** - * dsa_lag_map() - Map LAG structure to a linear LAG array - * @dst: Tree in which to record the mapping. - * @lag: LAG structure that is to be mapped to the tree's array. - * - * dsa_lag_id/dsa_lag_by_id can then be used to translate between the - * two spaces. The size of the mapping space is determined by the - * driver by setting ds->num_lag_ids. It is perfectly legal to leave - * it unset if it is not needed, in which case these functions become - * no-ops. - */ -void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag) -{ - unsigned int id; - - for (id = 1; id <= dst->lags_len; id++) { - if (!dsa_lag_by_id(dst, id)) { - dst->lags[id - 1] = lag; - lag->id = id; - return; - } - } - - /* No IDs left, which is OK. Some drivers do not need it. The - * ones that do, e.g. mv88e6xxx, will discover that dsa_lag_id - * returns an error for this device when joining the LAG. The - * driver can then return -EOPNOTSUPP back to DSA, which will - * fall back to a software LAG. - */ -} - -/** - * dsa_lag_unmap() - Remove a LAG ID mapping - * @dst: Tree in which the mapping is recorded. - * @lag: LAG structure that was mapped. - * - * As there may be multiple users of the mapping, it is only removed - * if there are no other references to it. - */ -void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag) -{ - unsigned int id; - - dsa_lags_foreach_id(id, dst) { - if (dsa_lag_by_id(dst, id) == lag) { - dst->lags[id - 1] = NULL; - lag->id = 0; - break; - } - } -} - -struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, - const struct net_device *lag_dev) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_lag_dev_get(dp) == lag_dev) - return dp->lag; - - return NULL; -} - -struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, - const struct net_device *br) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_bridge_dev_get(dp) == br) - return dp->bridge; - - return NULL; -} - -static int dsa_bridge_num_find(const struct net_device *bridge_dev) -{ - struct dsa_switch_tree *dst; - - list_for_each_entry(dst, &dsa_tree_list, list) { - struct dsa_bridge *bridge; - - bridge = dsa_tree_bridge_find(dst, bridge_dev); - if (bridge) - return bridge->num; - } - - return 0; -} - -unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) -{ - unsigned int bridge_num = dsa_bridge_num_find(bridge_dev); - - /* Switches without FDB isolation support don't get unique - * bridge numbering - */ - if (!max) - return 0; - - if (!bridge_num) { - /* First port that requests FDB isolation or TX forwarding - * offload for this bridge - */ - bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, - DSA_MAX_NUM_OFFLOADING_BRIDGES, - 1); - if (bridge_num >= max) - return 0; - - set_bit(bridge_num, &dsa_fwd_offloading_bridges); - } - - return bridge_num; -} - -void dsa_bridge_num_put(const struct net_device *bridge_dev, - unsigned int bridge_num) -{ - /* Since we refcount bridges, we know that when we call this function - * it is no longer in use, so we can just go ahead and remove it from - * the bit mask. - */ - clear_bit(bridge_num, &dsa_fwd_offloading_bridges); -} - -struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) -{ - struct dsa_switch_tree *dst; - struct dsa_port *dp; - - list_for_each_entry(dst, &dsa_tree_list, list) { - if (dst->index != tree_index) - continue; - - list_for_each_entry(dp, &dst->ports, list) { - if (dp->ds->index != sw_index) - continue; - - return dp->ds; - } - } - - return NULL; -} -EXPORT_SYMBOL_GPL(dsa_switch_find); - -static struct dsa_switch_tree *dsa_tree_find(int index) -{ - struct dsa_switch_tree *dst; - - list_for_each_entry(dst, &dsa_tree_list, list) - if (dst->index == index) - return dst; - - return NULL; -} - -static struct dsa_switch_tree *dsa_tree_alloc(int index) -{ - struct dsa_switch_tree *dst; - - dst = kzalloc(sizeof(*dst), GFP_KERNEL); - if (!dst) - return NULL; - - dst->index = index; - - INIT_LIST_HEAD(&dst->rtable); - - INIT_LIST_HEAD(&dst->ports); - - INIT_LIST_HEAD(&dst->list); - list_add_tail(&dst->list, &dsa_tree_list); - - kref_init(&dst->refcount); - - return dst; -} - -static void dsa_tree_free(struct dsa_switch_tree *dst) -{ - if (dst->tag_ops) - dsa_tag_driver_put(dst->tag_ops); - list_del(&dst->list); - kfree(dst); -} - -static struct dsa_switch_tree *dsa_tree_get(struct dsa_switch_tree *dst) -{ - if (dst) - kref_get(&dst->refcount); - - return dst; -} - -static struct dsa_switch_tree *dsa_tree_touch(int index) -{ - struct dsa_switch_tree *dst; - - dst = dsa_tree_find(index); - if (dst) - return dsa_tree_get(dst); - else - return dsa_tree_alloc(index); -} - -static void dsa_tree_release(struct kref *ref) -{ - struct dsa_switch_tree *dst; - - dst = container_of(ref, struct dsa_switch_tree, refcount); - - dsa_tree_free(dst); -} - -static void dsa_tree_put(struct dsa_switch_tree *dst) -{ - if (dst) - kref_put(&dst->refcount, dsa_tree_release); -} - -static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, - struct device_node *dn) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dp->dn == dn) - return dp; - - return NULL; -} - -static struct dsa_link *dsa_link_touch(struct dsa_port *dp, - struct dsa_port *link_dp) -{ - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst; - struct dsa_link *dl; - - dst = ds->dst; - - list_for_each_entry(dl, &dst->rtable, list) - if (dl->dp == dp && dl->link_dp == link_dp) - return dl; - - dl = kzalloc(sizeof(*dl), GFP_KERNEL); - if (!dl) - return NULL; - - dl->dp = dp; - dl->link_dp = link_dp; - - INIT_LIST_HEAD(&dl->list); - list_add_tail(&dl->list, &dst->rtable); - - return dl; -} - -static bool dsa_port_setup_routing_table(struct dsa_port *dp) -{ - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst = ds->dst; - struct device_node *dn = dp->dn; - struct of_phandle_iterator it; - struct dsa_port *link_dp; - struct dsa_link *dl; - int err; - - of_for_each_phandle(&it, err, dn, "link", NULL, 0) { - link_dp = dsa_tree_find_port_by_node(dst, it.node); - if (!link_dp) { - of_node_put(it.node); - return false; - } - - dl = dsa_link_touch(dp, link_dp); - if (!dl) { - of_node_put(it.node); - return false; - } - } - - return true; -} - -static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst) -{ - bool complete = true; - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) { - if (dsa_port_is_dsa(dp)) { - complete = dsa_port_setup_routing_table(dp); - if (!complete) - break; - } - } - - return complete; -} - -static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_cpu(dp)) - return dp; - - return NULL; -} - -struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst) -{ - struct device_node *ethernet; - struct net_device *master; - struct dsa_port *cpu_dp; - - cpu_dp = dsa_tree_find_first_cpu(dst); - ethernet = of_parse_phandle(cpu_dp->dn, "ethernet", 0); - master = of_find_net_device_by_node(ethernet); - of_node_put(ethernet); - - return master; -} - -/* Assign the default CPU port (the first one in the tree) to all ports of the - * fabric which don't already have one as part of their own switch. - */ -static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) -{ - struct dsa_port *cpu_dp, *dp; - - cpu_dp = dsa_tree_find_first_cpu(dst); - if (!cpu_dp) { - pr_err("DSA: tree %d has no CPU port\n", dst->index); - return -EINVAL; - } - - list_for_each_entry(dp, &dst->ports, list) { - if (dp->cpu_dp) - continue; - - if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) - dp->cpu_dp = cpu_dp; - } - - return 0; -} - -/* Perform initial assignment of CPU ports to user ports and DSA links in the - * fabric, giving preference to CPU ports local to each switch. Default to - * using the first CPU port in the switch tree if the port does not have a CPU - * port local to this switch. - */ -static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst) -{ - struct dsa_port *cpu_dp, *dp; - - list_for_each_entry(cpu_dp, &dst->ports, list) { - if (!dsa_port_is_cpu(cpu_dp)) - continue; - - /* Prefer a local CPU port */ - dsa_switch_for_each_port(dp, cpu_dp->ds) { - /* Prefer the first local CPU port found */ - if (dp->cpu_dp) - continue; - - if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) - dp->cpu_dp = cpu_dp; - } - } - - return dsa_tree_setup_default_cpu(dst); -} - -static void dsa_tree_teardown_cpu_ports(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) - dp->cpu_dp = NULL; -} - -static int dsa_port_devlink_setup(struct dsa_port *dp) -{ - struct devlink_port *dlp = &dp->devlink_port; - struct dsa_switch_tree *dst = dp->ds->dst; - struct devlink_port_attrs attrs = {}; - struct devlink *dl = dp->ds->devlink; - struct dsa_switch *ds = dp->ds; - const unsigned char *id; - unsigned char len; - int err; - - memset(dlp, 0, sizeof(*dlp)); - devlink_port_init(dl, dlp); - - if (ds->ops->port_setup) { - err = ds->ops->port_setup(ds, dp->index); - if (err) - return err; - } - - id = (const unsigned char *)&dst->index; - len = sizeof(dst->index); - - attrs.phys.port_number = dp->index; - memcpy(attrs.switch_id.id, id, len); - attrs.switch_id.id_len = len; - - switch (dp->type) { - case DSA_PORT_TYPE_UNUSED: - attrs.flavour = DEVLINK_PORT_FLAVOUR_UNUSED; - break; - case DSA_PORT_TYPE_CPU: - attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU; - break; - case DSA_PORT_TYPE_DSA: - attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA; - break; - case DSA_PORT_TYPE_USER: - attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - break; - } - - devlink_port_attrs_set(dlp, &attrs); - err = devlink_port_register(dl, dlp, dp->index); - if (err) { - if (ds->ops->port_teardown) - ds->ops->port_teardown(ds, dp->index); - return err; - } - - return 0; -} - -static void dsa_port_devlink_teardown(struct dsa_port *dp) -{ - struct devlink_port *dlp = &dp->devlink_port; - struct dsa_switch *ds = dp->ds; - - devlink_port_unregister(dlp); - - if (ds->ops->port_teardown) - ds->ops->port_teardown(ds, dp->index); - - devlink_port_fini(dlp); -} - -static int dsa_port_setup(struct dsa_port *dp) -{ - struct devlink_port *dlp = &dp->devlink_port; - bool dsa_port_link_registered = false; - struct dsa_switch *ds = dp->ds; - bool dsa_port_enabled = false; - int err = 0; - - if (dp->setup) - return 0; - - err = dsa_port_devlink_setup(dp); - if (err) - return err; - - switch (dp->type) { - case DSA_PORT_TYPE_UNUSED: - dsa_port_disable(dp); - break; - case DSA_PORT_TYPE_CPU: - if (dp->dn) { - err = dsa_shared_port_link_register_of(dp); - if (err) - break; - dsa_port_link_registered = true; - } else { - dev_warn(ds->dev, - "skipping link registration for CPU port %d\n", - dp->index); - } - - err = dsa_port_enable(dp, NULL); - if (err) - break; - dsa_port_enabled = true; - - break; - case DSA_PORT_TYPE_DSA: - if (dp->dn) { - err = dsa_shared_port_link_register_of(dp); - if (err) - break; - dsa_port_link_registered = true; - } else { - dev_warn(ds->dev, - "skipping link registration for DSA port %d\n", - dp->index); - } - - err = dsa_port_enable(dp, NULL); - if (err) - break; - dsa_port_enabled = true; - - break; - case DSA_PORT_TYPE_USER: - of_get_mac_address(dp->dn, dp->mac); - err = dsa_slave_create(dp); - if (err) - break; - - devlink_port_type_eth_set(dlp, dp->slave); - break; - } - - if (err && dsa_port_enabled) - dsa_port_disable(dp); - if (err && dsa_port_link_registered) - dsa_shared_port_link_unregister_of(dp); - if (err) { - dsa_port_devlink_teardown(dp); - return err; - } - - dp->setup = true; - - return 0; -} - -static void dsa_port_teardown(struct dsa_port *dp) -{ - struct devlink_port *dlp = &dp->devlink_port; - - if (!dp->setup) - return; - - devlink_port_type_clear(dlp); - - switch (dp->type) { - case DSA_PORT_TYPE_UNUSED: - break; - case DSA_PORT_TYPE_CPU: - dsa_port_disable(dp); - if (dp->dn) - dsa_shared_port_link_unregister_of(dp); - break; - case DSA_PORT_TYPE_DSA: - dsa_port_disable(dp); - if (dp->dn) - dsa_shared_port_link_unregister_of(dp); - break; - case DSA_PORT_TYPE_USER: - if (dp->slave) { - dsa_slave_destroy(dp->slave); - dp->slave = NULL; - } - break; - } - - dsa_port_devlink_teardown(dp); - - dp->setup = false; -} - -static int dsa_port_setup_as_unused(struct dsa_port *dp) -{ - dp->type = DSA_PORT_TYPE_UNUSED; - return dsa_port_setup(dp); -} - -static int dsa_devlink_info_get(struct devlink *dl, - struct devlink_info_req *req, - struct netlink_ext_ack *extack) -{ - struct dsa_switch *ds = dsa_devlink_to_ds(dl); - - if (ds->ops->devlink_info_get) - return ds->ops->devlink_info_get(ds, req, extack); - - return -EOPNOTSUPP; -} - -static int dsa_devlink_sb_pool_get(struct devlink *dl, - unsigned int sb_index, u16 pool_index, - struct devlink_sb_pool_info *pool_info) -{ - struct dsa_switch *ds = dsa_devlink_to_ds(dl); - - if (!ds->ops->devlink_sb_pool_get) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_pool_get(ds, sb_index, pool_index, - pool_info); -} - -static int dsa_devlink_sb_pool_set(struct devlink *dl, unsigned int sb_index, - u16 pool_index, u32 size, - enum devlink_sb_threshold_type threshold_type, - struct netlink_ext_ack *extack) -{ - struct dsa_switch *ds = dsa_devlink_to_ds(dl); - - if (!ds->ops->devlink_sb_pool_set) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_pool_set(ds, sb_index, pool_index, size, - threshold_type, extack); -} - -static int dsa_devlink_sb_port_pool_get(struct devlink_port *dlp, - unsigned int sb_index, u16 pool_index, - u32 *p_threshold) -{ - struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); - int port = dsa_devlink_port_to_port(dlp); - - if (!ds->ops->devlink_sb_port_pool_get) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_port_pool_get(ds, port, sb_index, - pool_index, p_threshold); -} - -static int dsa_devlink_sb_port_pool_set(struct devlink_port *dlp, - unsigned int sb_index, u16 pool_index, - u32 threshold, - struct netlink_ext_ack *extack) -{ - struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); - int port = dsa_devlink_port_to_port(dlp); - - if (!ds->ops->devlink_sb_port_pool_set) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_port_pool_set(ds, port, sb_index, - pool_index, threshold, extack); -} - -static int -dsa_devlink_sb_tc_pool_bind_get(struct devlink_port *dlp, - unsigned int sb_index, u16 tc_index, - enum devlink_sb_pool_type pool_type, - u16 *p_pool_index, u32 *p_threshold) -{ - struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); - int port = dsa_devlink_port_to_port(dlp); - - if (!ds->ops->devlink_sb_tc_pool_bind_get) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_tc_pool_bind_get(ds, port, sb_index, - tc_index, pool_type, - p_pool_index, p_threshold); -} - -static int -dsa_devlink_sb_tc_pool_bind_set(struct devlink_port *dlp, - unsigned int sb_index, u16 tc_index, - enum devlink_sb_pool_type pool_type, - u16 pool_index, u32 threshold, - struct netlink_ext_ack *extack) -{ - struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); - int port = dsa_devlink_port_to_port(dlp); - - if (!ds->ops->devlink_sb_tc_pool_bind_set) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_tc_pool_bind_set(ds, port, sb_index, - tc_index, pool_type, - pool_index, threshold, - extack); -} - -static int dsa_devlink_sb_occ_snapshot(struct devlink *dl, - unsigned int sb_index) -{ - struct dsa_switch *ds = dsa_devlink_to_ds(dl); - - if (!ds->ops->devlink_sb_occ_snapshot) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_occ_snapshot(ds, sb_index); -} - -static int dsa_devlink_sb_occ_max_clear(struct devlink *dl, - unsigned int sb_index) -{ - struct dsa_switch *ds = dsa_devlink_to_ds(dl); - - if (!ds->ops->devlink_sb_occ_max_clear) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_occ_max_clear(ds, sb_index); -} - -static int dsa_devlink_sb_occ_port_pool_get(struct devlink_port *dlp, - unsigned int sb_index, - u16 pool_index, u32 *p_cur, - u32 *p_max) -{ - struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); - int port = dsa_devlink_port_to_port(dlp); - - if (!ds->ops->devlink_sb_occ_port_pool_get) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_occ_port_pool_get(ds, port, sb_index, - pool_index, p_cur, p_max); -} - -static int -dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port *dlp, - unsigned int sb_index, u16 tc_index, - enum devlink_sb_pool_type pool_type, - u32 *p_cur, u32 *p_max) -{ - struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); - int port = dsa_devlink_port_to_port(dlp); - - if (!ds->ops->devlink_sb_occ_tc_port_bind_get) - return -EOPNOTSUPP; - - return ds->ops->devlink_sb_occ_tc_port_bind_get(ds, port, - sb_index, tc_index, - pool_type, p_cur, - p_max); -} - -static const struct devlink_ops dsa_devlink_ops = { - .info_get = dsa_devlink_info_get, - .sb_pool_get = dsa_devlink_sb_pool_get, - .sb_pool_set = dsa_devlink_sb_pool_set, - .sb_port_pool_get = dsa_devlink_sb_port_pool_get, - .sb_port_pool_set = dsa_devlink_sb_port_pool_set, - .sb_tc_pool_bind_get = dsa_devlink_sb_tc_pool_bind_get, - .sb_tc_pool_bind_set = dsa_devlink_sb_tc_pool_bind_set, - .sb_occ_snapshot = dsa_devlink_sb_occ_snapshot, - .sb_occ_max_clear = dsa_devlink_sb_occ_max_clear, - .sb_occ_port_pool_get = dsa_devlink_sb_occ_port_pool_get, - .sb_occ_tc_port_bind_get = dsa_devlink_sb_occ_tc_port_bind_get, -}; - -static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds) -{ - const struct dsa_device_ops *tag_ops = ds->dst->tag_ops; - struct dsa_switch_tree *dst = ds->dst; - int err; - - if (tag_ops->proto == dst->default_proto) - goto connect; - - rtnl_lock(); - err = ds->ops->change_tag_protocol(ds, tag_ops->proto); - rtnl_unlock(); - if (err) { - dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n", - tag_ops->name, ERR_PTR(err)); - return err; - } - -connect: - if (tag_ops->connect) { - err = tag_ops->connect(ds); - if (err) - return err; - } - - if (ds->ops->connect_tag_protocol) { - err = ds->ops->connect_tag_protocol(ds, tag_ops->proto); - if (err) { - dev_err(ds->dev, - "Unable to connect to tag protocol \"%s\": %pe\n", - tag_ops->name, ERR_PTR(err)); - goto disconnect; - } - } - - return 0; - -disconnect: - if (tag_ops->disconnect) - tag_ops->disconnect(ds); - - return err; -} - -static int dsa_switch_setup(struct dsa_switch *ds) -{ - struct dsa_devlink_priv *dl_priv; - struct device_node *dn; - int err; - - if (ds->setup) - return 0; - - /* Initialize ds->phys_mii_mask before registering the slave MDIO bus - * driver and before ops->setup() has run, since the switch drivers and - * the slave MDIO bus driver rely on these values for probing PHY - * devices or not - */ - ds->phys_mii_mask |= dsa_user_ports(ds); - - /* Add the switch to devlink before calling setup, so that setup can - * add dpipe tables - */ - ds->devlink = - devlink_alloc(&dsa_devlink_ops, sizeof(*dl_priv), ds->dev); - if (!ds->devlink) - return -ENOMEM; - dl_priv = devlink_priv(ds->devlink); - dl_priv->ds = ds; - - err = dsa_switch_register_notifier(ds); - if (err) - goto devlink_free; - - ds->configure_vlan_while_not_filtering = true; - - err = ds->ops->setup(ds); - if (err < 0) - goto unregister_notifier; - - err = dsa_switch_setup_tag_protocol(ds); - if (err) - goto teardown; - - if (!ds->slave_mii_bus && ds->ops->phy_read) { - ds->slave_mii_bus = mdiobus_alloc(); - if (!ds->slave_mii_bus) { - err = -ENOMEM; - goto teardown; - } - - dsa_slave_mii_bus_init(ds); - - dn = of_get_child_by_name(ds->dev->of_node, "mdio"); - - err = of_mdiobus_register(ds->slave_mii_bus, dn); - of_node_put(dn); - if (err < 0) - goto free_slave_mii_bus; - } - - ds->setup = true; - devlink_register(ds->devlink); - return 0; - -free_slave_mii_bus: - if (ds->slave_mii_bus && ds->ops->phy_read) - mdiobus_free(ds->slave_mii_bus); -teardown: - if (ds->ops->teardown) - ds->ops->teardown(ds); -unregister_notifier: - dsa_switch_unregister_notifier(ds); -devlink_free: - devlink_free(ds->devlink); - ds->devlink = NULL; - return err; -} - -static void dsa_switch_teardown(struct dsa_switch *ds) -{ - if (!ds->setup) - return; - - if (ds->devlink) - devlink_unregister(ds->devlink); - - if (ds->slave_mii_bus && ds->ops->phy_read) { - mdiobus_unregister(ds->slave_mii_bus); - mdiobus_free(ds->slave_mii_bus); - ds->slave_mii_bus = NULL; - } - - if (ds->ops->teardown) - ds->ops->teardown(ds); - - dsa_switch_unregister_notifier(ds); - - if (ds->devlink) { - devlink_free(ds->devlink); - ds->devlink = NULL; - } - - ds->setup = false; -} - -/* First tear down the non-shared, then the shared ports. This ensures that - * all work items scheduled by our switchdev handlers for user ports have - * completed before we destroy the refcounting kept on the shared ports. - */ -static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) - dsa_port_teardown(dp); - - dsa_flush_workqueue(); - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) - dsa_port_teardown(dp); -} - -static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); -} - -/* Bring shared ports up first, then non-shared ports */ -static int dsa_tree_setup_ports(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - int err = 0; - - list_for_each_entry(dp, &dst->ports, list) { - if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) { - err = dsa_port_setup(dp); - if (err) - goto teardown; - } - } - - list_for_each_entry(dp, &dst->ports, list) { - if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) { - err = dsa_port_setup(dp); - if (err) { - err = dsa_port_setup_as_unused(dp); - if (err) - goto teardown; - } - } - } - - return 0; - -teardown: - dsa_tree_teardown_ports(dst); - - return err; -} - -static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - int err = 0; - - list_for_each_entry(dp, &dst->ports, list) { - err = dsa_switch_setup(dp->ds); - if (err) { - dsa_tree_teardown_switches(dst); - break; - } - } - - return err; -} - -static int dsa_tree_setup_master(struct dsa_switch_tree *dst) -{ - struct dsa_port *cpu_dp; - int err = 0; - - rtnl_lock(); - - dsa_tree_for_each_cpu_port(cpu_dp, dst) { - struct net_device *master = cpu_dp->master; - bool admin_up = (master->flags & IFF_UP) && - !qdisc_tx_is_noop(master); - - err = dsa_master_setup(master, cpu_dp); - if (err) - break; - - /* Replay master state event */ - dsa_tree_master_admin_state_change(dst, master, admin_up); - dsa_tree_master_oper_state_change(dst, master, - netif_oper_up(master)); - } - - rtnl_unlock(); - - return err; -} - -static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) -{ - struct dsa_port *cpu_dp; - - rtnl_lock(); - - dsa_tree_for_each_cpu_port(cpu_dp, dst) { - struct net_device *master = cpu_dp->master; - - /* Synthesizing an "admin down" state is sufficient for - * the switches to get a notification if the master is - * currently up and running. - */ - dsa_tree_master_admin_state_change(dst, master, false); - - dsa_master_teardown(master); - } - - rtnl_unlock(); -} - -static int dsa_tree_setup_lags(struct dsa_switch_tree *dst) -{ - unsigned int len = 0; - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) { - if (dp->ds->num_lag_ids > len) - len = dp->ds->num_lag_ids; - } - - if (!len) - return 0; - - dst->lags = kcalloc(len, sizeof(*dst->lags), GFP_KERNEL); - if (!dst->lags) - return -ENOMEM; - - dst->lags_len = len; - return 0; -} - -static void dsa_tree_teardown_lags(struct dsa_switch_tree *dst) -{ - kfree(dst->lags); -} - -static int dsa_tree_setup(struct dsa_switch_tree *dst) -{ - bool complete; - int err; - - if (dst->setup) { - pr_err("DSA: tree %d already setup! Disjoint trees?\n", - dst->index); - return -EEXIST; - } - - complete = dsa_tree_setup_routing_table(dst); - if (!complete) - return 0; - - err = dsa_tree_setup_cpu_ports(dst); - if (err) - return err; - - err = dsa_tree_setup_switches(dst); - if (err) - goto teardown_cpu_ports; - - err = dsa_tree_setup_ports(dst); - if (err) - goto teardown_switches; - - err = dsa_tree_setup_master(dst); - if (err) - goto teardown_ports; - - err = dsa_tree_setup_lags(dst); - if (err) - goto teardown_master; - - dst->setup = true; - - pr_info("DSA: tree %d setup\n", dst->index); - - return 0; - -teardown_master: - dsa_tree_teardown_master(dst); -teardown_ports: - dsa_tree_teardown_ports(dst); -teardown_switches: - dsa_tree_teardown_switches(dst); -teardown_cpu_ports: - dsa_tree_teardown_cpu_ports(dst); - - return err; -} - -static void dsa_tree_teardown(struct dsa_switch_tree *dst) -{ - struct dsa_link *dl, *next; - - if (!dst->setup) - return; - - dsa_tree_teardown_lags(dst); - - dsa_tree_teardown_master(dst); - - dsa_tree_teardown_ports(dst); - - dsa_tree_teardown_switches(dst); - - dsa_tree_teardown_cpu_ports(dst); - - list_for_each_entry_safe(dl, next, &dst->rtable, list) { - list_del(&dl->list); - kfree(dl); - } - - pr_info("DSA: tree %d torn down\n", dst->index); - - dst->setup = false; -} - -static int dsa_tree_bind_tag_proto(struct dsa_switch_tree *dst, - const struct dsa_device_ops *tag_ops) -{ - const struct dsa_device_ops *old_tag_ops = dst->tag_ops; - struct dsa_notifier_tag_proto_info info; - int err; - - dst->tag_ops = tag_ops; - - /* Notify the switches from this tree about the connection - * to the new tagger - */ - info.tag_ops = tag_ops; - err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_CONNECT, &info); - if (err && err != -EOPNOTSUPP) - goto out_disconnect; - - /* Notify the old tagger about the disconnection from this tree */ - info.tag_ops = old_tag_ops; - dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); - - return 0; - -out_disconnect: - info.tag_ops = tag_ops; - dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); - dst->tag_ops = old_tag_ops; - - return err; -} - -/* Since the dsa/tagging sysfs device attribute is per master, the assumption - * is that all DSA switches within a tree share the same tagger, otherwise - * they would have formed disjoint trees (different "dsa,member" values). - */ -int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, - const struct dsa_device_ops *tag_ops, - const struct dsa_device_ops *old_tag_ops) -{ - struct dsa_notifier_tag_proto_info info; - struct dsa_port *dp; - int err = -EBUSY; - - if (!rtnl_trylock()) - return restart_syscall(); - - /* At the moment we don't allow changing the tag protocol under - * traffic. The rtnl_mutex also happens to serialize concurrent - * attempts to change the tagging protocol. If we ever lift the IFF_UP - * restriction, there needs to be another mutex which serializes this. - */ - dsa_tree_for_each_user_port(dp, dst) { - if (dsa_port_to_master(dp)->flags & IFF_UP) - goto out_unlock; - - if (dp->slave->flags & IFF_UP) - goto out_unlock; - } - - /* Notify the tag protocol change */ - info.tag_ops = tag_ops; - err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); - if (err) - goto out_unwind_tagger; - - err = dsa_tree_bind_tag_proto(dst, tag_ops); - if (err) - goto out_unwind_tagger; - - rtnl_unlock(); - - return 0; - -out_unwind_tagger: - info.tag_ops = old_tag_ops; - dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); -out_unlock: - rtnl_unlock(); - return err; -} - -static void dsa_tree_master_state_change(struct dsa_switch_tree *dst, - struct net_device *master) -{ - struct dsa_notifier_master_state_info info; - struct dsa_port *cpu_dp = master->dsa_ptr; - - info.master = master; - info.operational = dsa_port_master_is_operational(cpu_dp); - - dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info); -} - -void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up) -{ - struct dsa_port *cpu_dp = master->dsa_ptr; - bool notify = false; - - /* Don't keep track of admin state on LAG DSA masters, - * but rather just of physical DSA masters - */ - if (netif_is_lag_master(master)) - return; - - if ((dsa_port_master_is_operational(cpu_dp)) != - (up && cpu_dp->master_oper_up)) - notify = true; - - cpu_dp->master_admin_up = up; - - if (notify) - dsa_tree_master_state_change(dst, master); -} - -void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up) -{ - struct dsa_port *cpu_dp = master->dsa_ptr; - bool notify = false; - - /* Don't keep track of oper state on LAG DSA masters, - * but rather just of physical DSA masters - */ - if (netif_is_lag_master(master)) - return; - - if ((dsa_port_master_is_operational(cpu_dp)) != - (cpu_dp->master_admin_up && up)) - notify = true; - - cpu_dp->master_oper_up = up; - - if (notify) - dsa_tree_master_state_change(dst, master); -} - -static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) -{ - struct dsa_switch_tree *dst = ds->dst; - struct dsa_port *dp; - - dsa_switch_for_each_port(dp, ds) - if (dp->index == index) - return dp; - - dp = kzalloc(sizeof(*dp), GFP_KERNEL); - if (!dp) - return NULL; - - dp->ds = ds; - dp->index = index; - - mutex_init(&dp->addr_lists_lock); - mutex_init(&dp->vlans_lock); - INIT_LIST_HEAD(&dp->fdbs); - INIT_LIST_HEAD(&dp->mdbs); - INIT_LIST_HEAD(&dp->vlans); - INIT_LIST_HEAD(&dp->list); - list_add_tail(&dp->list, &dst->ports); - - return dp; -} - -static int dsa_port_parse_user(struct dsa_port *dp, const char *name) -{ - if (!name) - name = "eth%d"; - - dp->type = DSA_PORT_TYPE_USER; - dp->name = name; - - return 0; -} - -static int dsa_port_parse_dsa(struct dsa_port *dp) -{ - dp->type = DSA_PORT_TYPE_DSA; - - return 0; -} - -static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, - struct net_device *master) -{ - enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; - struct dsa_switch *mds, *ds = dp->ds; - unsigned int mdp_upstream; - struct dsa_port *mdp; - - /* It is possible to stack DSA switches onto one another when that - * happens the switch driver may want to know if its tagging protocol - * is going to work in such a configuration. - */ - if (dsa_slave_dev_check(master)) { - mdp = dsa_slave_to_port(master); - mds = mdp->ds; - mdp_upstream = dsa_upstream_port(mds, mdp->index); - tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, - DSA_TAG_PROTO_NONE); - } - - /* If the master device is not itself a DSA slave in a disjoint DSA - * tree, then return immediately. - */ - return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); -} - -static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, - const char *user_protocol) -{ - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst = ds->dst; - const struct dsa_device_ops *tag_ops; - enum dsa_tag_protocol default_proto; - - /* Find out which protocol the switch would prefer. */ - default_proto = dsa_get_tag_protocol(dp, master); - if (dst->default_proto) { - if (dst->default_proto != default_proto) { - dev_err(ds->dev, - "A DSA switch tree can have only one tagging protocol\n"); - return -EINVAL; - } - } else { - dst->default_proto = default_proto; - } - - /* See if the user wants to override that preference. */ - if (user_protocol) { - if (!ds->ops->change_tag_protocol) { - dev_err(ds->dev, "Tag protocol cannot be modified\n"); - return -EINVAL; - } - - tag_ops = dsa_find_tagger_by_name(user_protocol); - } else { - tag_ops = dsa_tag_driver_get(default_proto); - } - - if (IS_ERR(tag_ops)) { - if (PTR_ERR(tag_ops) == -ENOPROTOOPT) - return -EPROBE_DEFER; - - dev_warn(ds->dev, "No tagger for this switch\n"); - return PTR_ERR(tag_ops); - } - - if (dst->tag_ops) { - if (dst->tag_ops != tag_ops) { - dev_err(ds->dev, - "A DSA switch tree can have only one tagging protocol\n"); - - dsa_tag_driver_put(tag_ops); - return -EINVAL; - } - - /* In the case of multiple CPU ports per switch, the tagging - * protocol is still reference-counted only per switch tree. - */ - dsa_tag_driver_put(tag_ops); - } else { - dst->tag_ops = tag_ops; - } - - dp->master = master; - dp->type = DSA_PORT_TYPE_CPU; - dsa_port_set_tag_protocol(dp, dst->tag_ops); - dp->dst = dst; - - /* At this point, the tree may be configured to use a different - * tagger than the one chosen by the switch driver during - * .setup, in the case when a user selects a custom protocol - * through the DT. - * - * This is resolved by syncing the driver with the tree in - * dsa_switch_setup_tag_protocol once .setup has run and the - * driver is ready to accept calls to .change_tag_protocol. If - * the driver does not support the custom protocol at that - * point, the tree is wholly rejected, thereby ensuring that the - * tree and driver are always in agreement on the protocol to - * use. - */ - return 0; -} - -static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) -{ - struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0); - const char *name = of_get_property(dn, "label", NULL); - bool link = of_property_read_bool(dn, "link"); - - dp->dn = dn; - - if (ethernet) { - struct net_device *master; - const char *user_protocol; - - master = of_find_net_device_by_node(ethernet); - of_node_put(ethernet); - if (!master) - return -EPROBE_DEFER; - - user_protocol = of_get_property(dn, "dsa-tag-protocol", NULL); - return dsa_port_parse_cpu(dp, master, user_protocol); - } - - if (link) - return dsa_port_parse_dsa(dp); - - return dsa_port_parse_user(dp, name); -} - -static int dsa_switch_parse_ports_of(struct dsa_switch *ds, - struct device_node *dn) -{ - struct device_node *ports, *port; - struct dsa_port *dp; - int err = 0; - u32 reg; - - ports = of_get_child_by_name(dn, "ports"); - if (!ports) { - /* The second possibility is "ethernet-ports" */ - ports = of_get_child_by_name(dn, "ethernet-ports"); - if (!ports) { - dev_err(ds->dev, "no ports child node found\n"); - return -EINVAL; - } - } - - for_each_available_child_of_node(ports, port) { - err = of_property_read_u32(port, "reg", ®); - if (err) { - of_node_put(port); - goto out_put_node; - } - - if (reg >= ds->num_ports) { - dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%u)\n", - port, reg, ds->num_ports); - of_node_put(port); - err = -EINVAL; - goto out_put_node; - } - - dp = dsa_to_port(ds, reg); - - err = dsa_port_parse_of(dp, port); - if (err) { - of_node_put(port); - goto out_put_node; - } - } - -out_put_node: - of_node_put(ports); - return err; -} - -static int dsa_switch_parse_member_of(struct dsa_switch *ds, - struct device_node *dn) -{ - u32 m[2] = { 0, 0 }; - int sz; - - /* Don't error out if this optional property isn't found */ - sz = of_property_read_variable_u32_array(dn, "dsa,member", m, 2, 2); - if (sz < 0 && sz != -EINVAL) - return sz; - - ds->index = m[1]; - - ds->dst = dsa_tree_touch(m[0]); - if (!ds->dst) - return -ENOMEM; - - if (dsa_switch_find(ds->dst->index, ds->index)) { - dev_err(ds->dev, - "A DSA switch with index %d already exists in tree %d\n", - ds->index, ds->dst->index); - return -EEXIST; - } - - if (ds->dst->last_switch < ds->index) - ds->dst->last_switch = ds->index; - - return 0; -} - -static int dsa_switch_touch_ports(struct dsa_switch *ds) -{ - struct dsa_port *dp; - int port; - - for (port = 0; port < ds->num_ports; port++) { - dp = dsa_port_touch(ds, port); - if (!dp) - return -ENOMEM; - } - - return 0; -} - -static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn) -{ - int err; - - err = dsa_switch_parse_member_of(ds, dn); - if (err) - return err; - - err = dsa_switch_touch_ports(ds); - if (err) - return err; - - return dsa_switch_parse_ports_of(ds, dn); -} - -static int dsa_port_parse(struct dsa_port *dp, const char *name, - struct device *dev) -{ - if (!strcmp(name, "cpu")) { - struct net_device *master; - - master = dsa_dev_to_net_device(dev); - if (!master) - return -EPROBE_DEFER; - - dev_put(master); - - return dsa_port_parse_cpu(dp, master, NULL); - } - - if (!strcmp(name, "dsa")) - return dsa_port_parse_dsa(dp); - - return dsa_port_parse_user(dp, name); -} - -static int dsa_switch_parse_ports(struct dsa_switch *ds, - struct dsa_chip_data *cd) -{ - bool valid_name_found = false; - struct dsa_port *dp; - struct device *dev; - const char *name; - unsigned int i; - int err; - - for (i = 0; i < DSA_MAX_PORTS; i++) { - name = cd->port_names[i]; - dev = cd->netdev[i]; - dp = dsa_to_port(ds, i); - - if (!name) - continue; - - err = dsa_port_parse(dp, name, dev); - if (err) - return err; - - valid_name_found = true; - } - - if (!valid_name_found && i == DSA_MAX_PORTS) - return -EINVAL; - - return 0; -} - -static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd) -{ - int err; - - ds->cd = cd; - - /* We don't support interconnected switches nor multiple trees via - * platform data, so this is the unique switch of the tree. - */ - ds->index = 0; - ds->dst = dsa_tree_touch(0); - if (!ds->dst) - return -ENOMEM; - - err = dsa_switch_touch_ports(ds); - if (err) - return err; - - return dsa_switch_parse_ports(ds, cd); -} - -static void dsa_switch_release_ports(struct dsa_switch *ds) -{ - struct dsa_port *dp, *next; - - dsa_switch_for_each_port_safe(dp, next, ds) { - WARN_ON(!list_empty(&dp->fdbs)); - WARN_ON(!list_empty(&dp->mdbs)); - WARN_ON(!list_empty(&dp->vlans)); - list_del(&dp->list); - kfree(dp); - } -} - -static int dsa_switch_probe(struct dsa_switch *ds) -{ - struct dsa_switch_tree *dst; - struct dsa_chip_data *pdata; - struct device_node *np; - int err; - - if (!ds->dev) - return -ENODEV; - - pdata = ds->dev->platform_data; - np = ds->dev->of_node; - - if (!ds->num_ports) - return -EINVAL; - - if (np) { - err = dsa_switch_parse_of(ds, np); - if (err) - dsa_switch_release_ports(ds); - } else if (pdata) { - err = dsa_switch_parse(ds, pdata); - if (err) - dsa_switch_release_ports(ds); - } else { - err = -ENODEV; - } - - if (err) - return err; - - dst = ds->dst; - dsa_tree_get(dst); - err = dsa_tree_setup(dst); - if (err) { - dsa_switch_release_ports(ds); - dsa_tree_put(dst); - } - - return err; -} - -int dsa_register_switch(struct dsa_switch *ds) -{ - int err; - - mutex_lock(&dsa2_mutex); - err = dsa_switch_probe(ds); - dsa_tree_put(ds->dst); - mutex_unlock(&dsa2_mutex); - - return err; -} -EXPORT_SYMBOL_GPL(dsa_register_switch); - -static void dsa_switch_remove(struct dsa_switch *ds) -{ - struct dsa_switch_tree *dst = ds->dst; - - dsa_tree_teardown(dst); - dsa_switch_release_ports(ds); - dsa_tree_put(dst); -} - -void dsa_unregister_switch(struct dsa_switch *ds) -{ - mutex_lock(&dsa2_mutex); - dsa_switch_remove(ds); - mutex_unlock(&dsa2_mutex); -} -EXPORT_SYMBOL_GPL(dsa_unregister_switch); - -/* If the DSA master chooses to unregister its net_device on .shutdown, DSA is - * blocking that operation from completion, due to the dev_hold taken inside - * netdev_upper_dev_link. Unlink the DSA slave interfaces from being uppers of - * the DSA master, so that the system can reboot successfully. - */ -void dsa_switch_shutdown(struct dsa_switch *ds) -{ - struct net_device *master, *slave_dev; - struct dsa_port *dp; - - mutex_lock(&dsa2_mutex); - - if (!ds->setup) - goto out; - - rtnl_lock(); - - dsa_switch_for_each_user_port(dp, ds) { - master = dsa_port_to_master(dp); - slave_dev = dp->slave; - - netdev_upper_dev_unlink(master, slave_dev); - } - - /* Disconnect from further netdevice notifiers on the master, - * since netdev_uses_dsa() will now return false. - */ - dsa_switch_for_each_cpu_port(dp, ds) - dp->master->dsa_ptr = NULL; - - rtnl_unlock(); -out: - mutex_unlock(&dsa2_mutex); -} -EXPORT_SYMBOL_GPL(dsa_switch_shutdown); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h deleted file mode 100644 index 6e65c7ffd6f3..000000000000 --- a/net/dsa/dsa_priv.h +++ /dev/null @@ -1,587 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * net/dsa/dsa_priv.h - Hardware switch handling - * Copyright (c) 2008-2009 Marvell Semiconductor - */ - -#ifndef __DSA_PRIV_H -#define __DSA_PRIV_H - -#include <linux/if_bridge.h> -#include <linux/if_vlan.h> -#include <linux/phy.h> -#include <linux/netdevice.h> -#include <linux/netpoll.h> -#include <net/dsa.h> -#include <net/gro_cells.h> - -#define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG - -enum { - DSA_NOTIFIER_AGEING_TIME, - DSA_NOTIFIER_BRIDGE_JOIN, - DSA_NOTIFIER_BRIDGE_LEAVE, - DSA_NOTIFIER_FDB_ADD, - DSA_NOTIFIER_FDB_DEL, - DSA_NOTIFIER_HOST_FDB_ADD, - DSA_NOTIFIER_HOST_FDB_DEL, - DSA_NOTIFIER_LAG_FDB_ADD, - DSA_NOTIFIER_LAG_FDB_DEL, - DSA_NOTIFIER_LAG_CHANGE, - DSA_NOTIFIER_LAG_JOIN, - DSA_NOTIFIER_LAG_LEAVE, - DSA_NOTIFIER_MDB_ADD, - DSA_NOTIFIER_MDB_DEL, - DSA_NOTIFIER_HOST_MDB_ADD, - DSA_NOTIFIER_HOST_MDB_DEL, - DSA_NOTIFIER_VLAN_ADD, - DSA_NOTIFIER_VLAN_DEL, - DSA_NOTIFIER_HOST_VLAN_ADD, - DSA_NOTIFIER_HOST_VLAN_DEL, - DSA_NOTIFIER_MTU, - DSA_NOTIFIER_TAG_PROTO, - DSA_NOTIFIER_TAG_PROTO_CONNECT, - DSA_NOTIFIER_TAG_PROTO_DISCONNECT, - DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, - DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, - DSA_NOTIFIER_MASTER_STATE_CHANGE, -}; - -/* DSA_NOTIFIER_AGEING_TIME */ -struct dsa_notifier_ageing_time_info { - unsigned int ageing_time; -}; - -/* DSA_NOTIFIER_BRIDGE_* */ -struct dsa_notifier_bridge_info { - const struct dsa_port *dp; - struct dsa_bridge bridge; - bool tx_fwd_offload; - struct netlink_ext_ack *extack; -}; - -/* DSA_NOTIFIER_FDB_* */ -struct dsa_notifier_fdb_info { - const struct dsa_port *dp; - const unsigned char *addr; - u16 vid; - struct dsa_db db; -}; - -/* DSA_NOTIFIER_LAG_FDB_* */ -struct dsa_notifier_lag_fdb_info { - struct dsa_lag *lag; - const unsigned char *addr; - u16 vid; - struct dsa_db db; -}; - -/* DSA_NOTIFIER_MDB_* */ -struct dsa_notifier_mdb_info { - const struct dsa_port *dp; - const struct switchdev_obj_port_mdb *mdb; - struct dsa_db db; -}; - -/* DSA_NOTIFIER_LAG_* */ -struct dsa_notifier_lag_info { - const struct dsa_port *dp; - struct dsa_lag lag; - struct netdev_lag_upper_info *info; - struct netlink_ext_ack *extack; -}; - -/* DSA_NOTIFIER_VLAN_* */ -struct dsa_notifier_vlan_info { - const struct dsa_port *dp; - const struct switchdev_obj_port_vlan *vlan; - struct netlink_ext_ack *extack; -}; - -/* DSA_NOTIFIER_MTU */ -struct dsa_notifier_mtu_info { - const struct dsa_port *dp; - int mtu; -}; - -/* DSA_NOTIFIER_TAG_PROTO_* */ -struct dsa_notifier_tag_proto_info { - const struct dsa_device_ops *tag_ops; -}; - -/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */ -struct dsa_notifier_tag_8021q_vlan_info { - const struct dsa_port *dp; - u16 vid; -}; - -/* DSA_NOTIFIER_MASTER_STATE_CHANGE */ -struct dsa_notifier_master_state_info { - const struct net_device *master; - bool operational; -}; - -struct dsa_switchdev_event_work { - struct net_device *dev; - struct net_device *orig_dev; - struct work_struct work; - unsigned long event; - /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and - * SWITCHDEV_FDB_DEL_TO_DEVICE - */ - unsigned char addr[ETH_ALEN]; - u16 vid; - bool host_addr; -}; - -enum dsa_standalone_event { - DSA_UC_ADD, - DSA_UC_DEL, - DSA_MC_ADD, - DSA_MC_DEL, -}; - -struct dsa_standalone_event_work { - struct work_struct work; - struct net_device *dev; - enum dsa_standalone_event event; - unsigned char addr[ETH_ALEN]; - u16 vid; -}; - -struct dsa_slave_priv { - /* Copy of CPU port xmit for faster access in slave transmit hot path */ - struct sk_buff * (*xmit)(struct sk_buff *skb, - struct net_device *dev); - - struct gro_cells gcells; - - /* DSA port data, such as switch, port index, etc. */ - struct dsa_port *dp; - -#ifdef CONFIG_NET_POLL_CONTROLLER - struct netpoll *netpoll; -#endif - - /* TC context */ - struct list_head mall_tc_list; -}; - -/* dsa.c */ -const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol); -void dsa_tag_driver_put(const struct dsa_device_ops *ops); -const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); - -bool dsa_db_equal(const struct dsa_db *a, const struct dsa_db *b); - -bool dsa_schedule_work(struct work_struct *work); -const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); - -static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) -{ - return ops->needed_headroom + ops->needed_tailroom; -} - -/* master.c */ -int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); -void dsa_master_teardown(struct net_device *dev); -int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack); -void dsa_master_lag_teardown(struct net_device *lag_dev, - struct dsa_port *cpu_dp); - -static inline struct net_device *dsa_master_find_slave(struct net_device *dev, - int device, int port) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - struct dsa_switch_tree *dst = cpu_dp->dst; - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dp->ds->index == device && dp->index == port && - dp->type == DSA_PORT_TYPE_USER) - return dp->slave; - - return NULL; -} - -/* netlink.c */ -extern struct rtnl_link_ops dsa_link_ops __read_mostly; - -/* port.c */ -void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, - const struct dsa_device_ops *tag_ops); -int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age); -int dsa_port_set_mst_state(struct dsa_port *dp, - const struct switchdev_mst_state *state, - struct netlink_ext_ack *extack); -int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); -int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); -void dsa_port_disable_rt(struct dsa_port *dp); -void dsa_port_disable(struct dsa_port *dp); -int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, - struct netlink_ext_ack *extack); -void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br); -void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); -int dsa_port_lag_change(struct dsa_port *dp, - struct netdev_lag_lower_state_info *linfo); -int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack); -void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); -void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); -int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, - struct netlink_ext_ack *extack); -bool dsa_port_skip_vlan_configuration(struct dsa_port *dp); -int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock); -int dsa_port_mst_enable(struct dsa_port *dp, bool on, - struct netlink_ext_ack *extack); -int dsa_port_vlan_msti(struct dsa_port *dp, - const struct switchdev_vlan_msti *msti); -int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu); -int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, - u16 vid); -int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, - u16 vid); -int dsa_port_standalone_host_fdb_add(struct dsa_port *dp, - const unsigned char *addr, u16 vid); -int dsa_port_standalone_host_fdb_del(struct dsa_port *dp, - const unsigned char *addr, u16 vid); -int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, - u16 vid); -int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, - u16 vid); -int dsa_port_lag_fdb_add(struct dsa_port *dp, const unsigned char *addr, - u16 vid); -int dsa_port_lag_fdb_del(struct dsa_port *dp, const unsigned char *addr, - u16 vid); -int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); -int dsa_port_mdb_add(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb); -int dsa_port_mdb_del(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb); -int dsa_port_standalone_host_mdb_add(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb); -int dsa_port_standalone_host_mdb_del(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb); -int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb); -int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb); -int dsa_port_pre_bridge_flags(const struct dsa_port *dp, - struct switchdev_brport_flags flags, - struct netlink_ext_ack *extack); -int dsa_port_bridge_flags(struct dsa_port *dp, - struct switchdev_brport_flags flags, - struct netlink_ext_ack *extack); -int dsa_port_vlan_add(struct dsa_port *dp, - const struct switchdev_obj_port_vlan *vlan, - struct netlink_ext_ack *extack); -int dsa_port_vlan_del(struct dsa_port *dp, - const struct switchdev_obj_port_vlan *vlan); -int dsa_port_host_vlan_add(struct dsa_port *dp, - const struct switchdev_obj_port_vlan *vlan, - struct netlink_ext_ack *extack); -int dsa_port_host_vlan_del(struct dsa_port *dp, - const struct switchdev_obj_port_vlan *vlan); -int dsa_port_mrp_add(const struct dsa_port *dp, - const struct switchdev_obj_mrp *mrp); -int dsa_port_mrp_del(const struct dsa_port *dp, - const struct switchdev_obj_mrp *mrp); -int dsa_port_mrp_add_ring_role(const struct dsa_port *dp, - const struct switchdev_obj_ring_role_mrp *mrp); -int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, - const struct switchdev_obj_ring_role_mrp *mrp); -int dsa_port_phylink_create(struct dsa_port *dp); -void dsa_port_phylink_destroy(struct dsa_port *dp); -int dsa_shared_port_link_register_of(struct dsa_port *dp); -void dsa_shared_port_link_unregister_of(struct dsa_port *dp); -int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); -void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); -int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast); -void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast); -void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc); -int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, - struct netlink_ext_ack *extack); - -/* slave.c */ -extern const struct dsa_device_ops notag_netdev_ops; -extern struct notifier_block dsa_slave_switchdev_notifier; -extern struct notifier_block dsa_slave_switchdev_blocking_notifier; - -void dsa_slave_mii_bus_init(struct dsa_switch *ds); -int dsa_slave_create(struct dsa_port *dp); -void dsa_slave_destroy(struct net_device *slave_dev); -int dsa_slave_suspend(struct net_device *slave_dev); -int dsa_slave_resume(struct net_device *slave_dev); -int dsa_slave_register_notifier(void); -void dsa_slave_unregister_notifier(void); -void dsa_slave_sync_ha(struct net_device *dev); -void dsa_slave_unsync_ha(struct net_device *dev); -void dsa_slave_setup_tagger(struct net_device *slave); -int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); -int dsa_slave_change_master(struct net_device *dev, struct net_device *master, - struct netlink_ext_ack *extack); -int dsa_slave_manage_vlan_filtering(struct net_device *dev, - bool vlan_filtering); - -static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - - return p->dp; -} - -static inline struct net_device * -dsa_slave_to_master(const struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_to_master(dp); -} - -/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged - * frames as untagged, since the bridge will not untag them. - */ -static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) -{ - struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *dev = skb->dev; - struct net_device *upper_dev; - u16 vid, pvid, proto; - int err; - - if (!br || br_vlan_enabled(br)) - return skb; - - err = br_vlan_get_proto(br, &proto); - if (err) - return skb; - - /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { - skb = skb_vlan_untag(skb); - if (!skb) - return NULL; - } - - if (!skb_vlan_tag_present(skb)) - return skb; - - vid = skb_vlan_tag_get_id(skb); - - /* We already run under an RCU read-side critical section since - * we are called from netif_receive_skb_list_internal(). - */ - err = br_vlan_get_pvid_rcu(dev, &pvid); - if (err) - return skb; - - if (vid != pvid) - return skb; - - /* The sad part about attempting to untag from DSA is that we - * don't know, unless we check, if the skb will end up in - * the bridge's data path - br_allowed_ingress() - or not. - * For example, there might be an 8021q upper for the - * default_pvid of the bridge, which will steal VLAN-tagged traffic - * from the bridge's data path. This is a configuration that DSA - * supports because vlan_filtering is 0. In that case, we should - * definitely keep the tag, to make sure it keeps working. - */ - upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); - if (upper_dev) - return skb; - - __vlan_hwaccel_clear_tag(skb); - - return skb; -} - -/* For switches without hardware support for DSA tagging to be able - * to support termination through the bridge. - */ -static inline struct net_device * -dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) -{ - struct dsa_port *cpu_dp = master->dsa_ptr; - struct dsa_switch_tree *dst = cpu_dp->dst; - struct bridge_vlan_info vinfo; - struct net_device *slave; - struct dsa_port *dp; - int err; - - list_for_each_entry(dp, &dst->ports, list) { - if (dp->type != DSA_PORT_TYPE_USER) - continue; - - if (!dp->bridge) - continue; - - if (dp->stp_state != BR_STATE_LEARNING && - dp->stp_state != BR_STATE_FORWARDING) - continue; - - /* Since the bridge might learn this packet, keep the CPU port - * affinity with the port that will be used for the reply on - * xmit. - */ - if (dp->cpu_dp != cpu_dp) - continue; - - slave = dp->slave; - - err = br_vlan_get_info_rcu(slave, vid, &vinfo); - if (err) - continue; - - return slave; - } - - return NULL; -} - -/* If the ingress port offloads the bridge, we mark the frame as autonomously - * forwarded by hardware, so the software bridge doesn't forward in twice, back - * to us, because we already did. However, if we're in fallback mode and we do - * software bridging, we are not offloading it, therefore the dp->bridge - * pointer is not populated, and flooding needs to be done by software (we are - * effectively operating in standalone ports mode). - */ -static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) -{ - struct dsa_port *dp = dsa_slave_to_port(skb->dev); - - skb->offload_fwd_mark = !!(dp->bridge); -} - -/* Helper for removing DSA header tags from packets in the RX path. - * Must not be called before skb_pull(len). - * skb->data - * | - * v - * | | | | | | | | | | | | | | | | | | | - * +-----------------------+-----------------------+---------------+-------+ - * | Destination MAC | Source MAC | DSA header | EType | - * +-----------------------+-----------------------+---------------+-------+ - * | | - * <----- len -----> <----- len -----> - * | - * >>>>>>> v - * >>>>>>> | | | | | | | | | | | | | | | - * >>>>>>> +-----------------------+-----------------------+-------+ - * >>>>>>> | Destination MAC | Source MAC | EType | - * +-----------------------+-----------------------+-------+ - * ^ - * | - * skb->data - */ -static inline void dsa_strip_etype_header(struct sk_buff *skb, int len) -{ - memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - len, 2 * ETH_ALEN); -} - -/* Helper for creating space for DSA header tags in TX path packets. - * Must not be called before skb_push(len). - * - * Before: - * - * <<<<<<< | | | | | | | | | | | | | | | - * ^ <<<<<<< +-----------------------+-----------------------+-------+ - * | <<<<<<< | Destination MAC | Source MAC | EType | - * | +-----------------------+-----------------------+-------+ - * <----- len -----> - * | - * | - * skb->data - * - * After: - * - * | | | | | | | | | | | | | | | | | | | - * +-----------------------+-----------------------+---------------+-------+ - * | Destination MAC | Source MAC | DSA header | EType | - * +-----------------------+-----------------------+---------------+-------+ - * ^ | | - * | <----- len -----> - * skb->data - */ -static inline void dsa_alloc_etype_header(struct sk_buff *skb, int len) -{ - memmove(skb->data, skb->data + len, 2 * ETH_ALEN); -} - -/* On RX, eth_type_trans() on the DSA master pulls ETH_HLEN bytes starting from - * skb_mac_header(skb), which leaves skb->data pointing at the first byte after - * what the DSA master perceives as the EtherType (the beginning of the L3 - * protocol). Since DSA EtherType header taggers treat the EtherType as part of - * the DSA tag itself, and the EtherType is 2 bytes in length, the DSA header - * is located 2 bytes behind skb->data. Note that EtherType in this context - * means the first 2 bytes of the DSA header, not the encapsulated EtherType - * that will become visible after the DSA header is stripped. - */ -static inline void *dsa_etype_header_pos_rx(struct sk_buff *skb) -{ - return skb->data - 2; -} - -/* On TX, skb->data points to skb_mac_header(skb), which means that EtherType - * header taggers start exactly where the EtherType is (the EtherType is - * treated as part of the DSA header). - */ -static inline void *dsa_etype_header_pos_tx(struct sk_buff *skb) -{ - return skb->data + 2 * ETH_ALEN; -} - -/* switch.c */ -int dsa_switch_register_notifier(struct dsa_switch *ds); -void dsa_switch_unregister_notifier(struct dsa_switch *ds); - -static inline bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) -{ - return ds->ops->port_fdb_add && ds->ops->port_fdb_del && - ds->fdb_isolation && !ds->vlan_filtering_is_global && - !ds->needs_standalone_vlan_filtering; -} - -static inline bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) -{ - return ds->ops->port_mdb_add && ds->ops->port_mdb_del && - ds->fdb_isolation && !ds->vlan_filtering_is_global && - !ds->needs_standalone_vlan_filtering; -} - -/* dsa2.c */ -void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag); -void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag); -struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, - const struct net_device *lag_dev); -struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst); -int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); -int dsa_broadcast(unsigned long e, void *v); -int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, - const struct dsa_device_ops *tag_ops, - const struct dsa_device_ops *old_tag_ops); -void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up); -void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up); -unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); -void dsa_bridge_num_put(const struct net_device *bridge_dev, - unsigned int bridge_num); -struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, - const struct net_device *br); - -/* tag_8021q.c */ -int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, - struct dsa_notifier_tag_8021q_vlan_info *info); -int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, - struct dsa_notifier_tag_8021q_vlan_info *info); - -extern struct list_head dsa_tree_list; - -#endif diff --git a/net/dsa/master.c b/net/dsa/master.c index 40367ab41cf8..26d90140d271 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -6,7 +6,15 @@ * Vivien Didelot <vivien.didelot@savoirfairelinux.com> */ -#include "dsa_priv.h" +#include <linux/ethtool.h> +#include <linux/netdevice.h> +#include <linux/netlink.h> +#include <net/dsa.h> + +#include "dsa.h" +#include "master.h" +#include "port.h" +#include "tag.h" static int dsa_master_get_regs_len(struct net_device *dev) { @@ -204,8 +212,7 @@ static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) * switch in the tree that is PTP capable. */ list_for_each_entry(dp, &dst->ports, list) - if (dp->ds->ops->port_hwtstamp_get || - dp->ds->ops->port_hwtstamp_set) + if (dsa_port_supports_hwtstamp(dp, ifr)) return -EBUSY; break; } @@ -300,13 +307,24 @@ static ssize_t tagging_store(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { const struct dsa_device_ops *new_tag_ops, *old_tag_ops; + const char *end = strchrnul(buf, '\n'), *name; struct net_device *dev = to_net_dev(d); struct dsa_port *cpu_dp = dev->dsa_ptr; + size_t len = end - buf; int err; + /* Empty string passed */ + if (!len) + return -ENOPROTOOPT; + + name = kstrndup(buf, len, GFP_KERNEL); + if (!name) + return -ENOMEM; + old_tag_ops = cpu_dp->tag_ops; - new_tag_ops = dsa_find_tagger_by_name(buf); - /* Bad tagger name, or module is not loaded? */ + new_tag_ops = dsa_tag_driver_get_by_name(name); + kfree(name); + /* Bad tagger name? */ if (IS_ERR(new_tag_ops)) return PTR_ERR(new_tag_ops); diff --git a/net/dsa/master.h b/net/dsa/master.h new file mode 100644 index 000000000000..3fc0e610b5b5 --- /dev/null +++ b/net/dsa/master.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_MASTER_H +#define __DSA_MASTER_H + +struct dsa_port; +struct net_device; +struct netdev_lag_upper_info; +struct netlink_ext_ack; + +int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); +void dsa_master_teardown(struct net_device *dev); +int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack); +void dsa_master_lag_teardown(struct net_device *lag_dev, + struct dsa_port *cpu_dp); + +#endif diff --git a/net/dsa/netlink.c b/net/dsa/netlink.c index ecf9ed1de185..bd4bbaf851de 100644 --- a/net/dsa/netlink.c +++ b/net/dsa/netlink.c @@ -4,7 +4,8 @@ #include <linux/netdevice.h> #include <net/rtnetlink.h> -#include "dsa_priv.h" +#include "netlink.h" +#include "slave.h" static const struct nla_policy dsa_policy[IFLA_DSA_MAX + 1] = { [IFLA_DSA_MASTER] = { .type = NLA_U32 }, diff --git a/net/dsa/netlink.h b/net/dsa/netlink.h new file mode 100644 index 000000000000..7eda2fa15722 --- /dev/null +++ b/net/dsa/netlink.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_NETLINK_H +#define __DSA_NETLINK_H + +extern struct rtnl_link_ops dsa_link_ops __read_mostly; + +#endif diff --git a/net/dsa/port.c b/net/dsa/port.c index 208168276995..67ad1adec2a2 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -12,7 +12,11 @@ #include <linux/of_mdio.h> #include <linux/of_net.h> -#include "dsa_priv.h" +#include "dsa.h" +#include "port.h" +#include "slave.h" +#include "switch.h" +#include "tag_8021q.h" /** * dsa_port_notify - Notify the switching fabric of changes to a port @@ -110,6 +114,22 @@ static bool dsa_port_can_configure_learning(struct dsa_port *dp) return !err; } +bool dsa_port_supports_hwtstamp(struct dsa_port *dp, struct ifreq *ifr) +{ + struct dsa_switch *ds = dp->ds; + int err; + + if (!ds->ops->port_hwtstamp_get || !ds->ops->port_hwtstamp_set) + return false; + + /* "See through" shim implementations of the "get" method. + * This will clobber the ifreq structure, but we will either return an + * error, or the master will overwrite it with proper values. + */ + err = ds->ops->port_hwtstamp_get(ds, dp->index, ifr); + return err != -EOPNOTSUPP; +} + int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age) { struct dsa_switch *ds = dp->ds; @@ -1536,16 +1556,14 @@ static void dsa_port_phylink_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_validate) { - if (config->mac_capabilities) - phylink_generic_validate(config, supported, state); - return; - } - - ds->ops->phylink_validate(ds, dp->index, supported, state); + /* Skip call for drivers which don't yet set mac_capabilities, + * since validating in that case would mean their PHY will advertise + * nothing. In turn, skipping validation makes them advertise + * everything that the PHY supports, so those drivers should be + * converted ASAP. + */ + if (config->mac_capabilities) + phylink_generic_validate(config, supported, state); } static void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, diff --git a/net/dsa/port.h b/net/dsa/port.h new file mode 100644 index 000000000000..9c218660d223 --- /dev/null +++ b/net/dsa/port.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_PORT_H +#define __DSA_PORT_H + +#include <linux/types.h> +#include <net/dsa.h> + +struct ifreq; +struct netdev_lag_lower_state_info; +struct netdev_lag_upper_info; +struct netlink_ext_ack; +struct switchdev_mst_state; +struct switchdev_obj_port_mdb; +struct switchdev_vlan_msti; +struct phy_device; + +bool dsa_port_supports_hwtstamp(struct dsa_port *dp, struct ifreq *ifr); +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops); +int dsa_port_set_state(struct dsa_port *dp, u8 state, bool do_fast_age); +int dsa_port_set_mst_state(struct dsa_port *dp, + const struct switchdev_mst_state *state, + struct netlink_ext_ack *extack); +int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); +int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); +void dsa_port_disable_rt(struct dsa_port *dp); +void dsa_port_disable(struct dsa_port *dp); +int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack); +void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br); +void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); +int dsa_port_lag_change(struct dsa_port *dp, + struct netdev_lag_lower_state_info *linfo); +int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack); +void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); +void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); +int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, + struct netlink_ext_ack *extack); +bool dsa_port_skip_vlan_configuration(struct dsa_port *dp); +int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock); +int dsa_port_mst_enable(struct dsa_port *dp, bool on, + struct netlink_ext_ack *extack); +int dsa_port_vlan_msti(struct dsa_port *dp, + const struct switchdev_vlan_msti *msti); +int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu); +int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_standalone_host_fdb_add(struct dsa_port *dp, + const unsigned char *addr, u16 vid); +int dsa_port_standalone_host_fdb_del(struct dsa_port *dp, + const unsigned char *addr, u16 vid); +int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_lag_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_lag_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); +int dsa_port_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_standalone_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_standalone_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_pre_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int dsa_port_bridge_flags(struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int dsa_port_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack); +int dsa_port_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan); +int dsa_port_host_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack); +int dsa_port_host_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan); +int dsa_port_mrp_add(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp); +int dsa_port_mrp_del(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp); +int dsa_port_mrp_add_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp); +int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp); +int dsa_port_phylink_create(struct dsa_port *dp); +void dsa_port_phylink_destroy(struct dsa_port *dp); +int dsa_shared_port_link_register_of(struct dsa_port *dp); +void dsa_shared_port_link_unregister_of(struct dsa_port *dp); +int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); +void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); +int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast); +void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast); +void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc); +int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, + struct netlink_ext_ack *extack); + +#endif diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1a59918d3b30..aab79c355224 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -22,7 +22,54 @@ #include <net/dcbnl.h> #include <linux/netpoll.h> -#include "dsa_priv.h" +#include "dsa.h" +#include "port.h" +#include "master.h" +#include "netlink.h" +#include "slave.h" +#include "tag.h" + +struct dsa_switchdev_event_work { + struct net_device *dev; + struct net_device *orig_dev; + struct work_struct work; + unsigned long event; + /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and + * SWITCHDEV_FDB_DEL_TO_DEVICE + */ + unsigned char addr[ETH_ALEN]; + u16 vid; + bool host_addr; +}; + +enum dsa_standalone_event { + DSA_UC_ADD, + DSA_UC_DEL, + DSA_MC_ADD, + DSA_MC_DEL, +}; + +struct dsa_standalone_event_work { + struct work_struct work; + struct net_device *dev; + enum dsa_standalone_event event; + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) +{ + return ds->ops->port_fdb_add && ds->ops->port_fdb_del && + ds->fdb_isolation && !ds->vlan_filtering_is_global && + !ds->needs_standalone_vlan_filtering; +} + +static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) +{ + return ds->ops->port_mdb_add && ds->ops->port_mdb_del && + ds->fdb_isolation && !ds->vlan_filtering_is_global && + !ds->needs_standalone_vlan_filtering; +} static void dsa_slave_standalone_event_work(struct work_struct *work) { @@ -976,12 +1023,12 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, s = per_cpu_ptr(dev->tstats, i); do { - start = u64_stats_fetch_begin_irq(&s->syncp); + start = u64_stats_fetch_begin(&s->syncp); tx_packets = u64_stats_read(&s->tx_packets); tx_bytes = u64_stats_read(&s->tx_bytes); rx_packets = u64_stats_read(&s->rx_packets); rx_bytes = u64_stats_read(&s->rx_bytes); - } while (u64_stats_fetch_retry_irq(&s->syncp, start)); + } while (u64_stats_fetch_retry(&s->syncp, start)); data[0] += tx_packets; data[1] += tx_bytes; data[2] += rx_packets; @@ -2165,13 +2212,6 @@ static const struct dcbnl_rtnl_ops __maybe_unused dsa_slave_dcbnl_ops = { .ieee_delapp = dsa_slave_dcbnl_ieee_delapp, }; -static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return &dp->devlink_port; -} - static void dsa_slave_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { @@ -2219,7 +2259,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_get_stats64 = dsa_slave_get_stats64, .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, - .ndo_get_devlink_port = dsa_slave_get_devlink_port, .ndo_change_mtu = dsa_slave_change_mtu, .ndo_fill_forward_path = dsa_slave_fill_forward_path, }; @@ -2374,16 +2413,25 @@ int dsa_slave_create(struct dsa_port *port) { struct net_device *master = dsa_port_to_master(port); struct dsa_switch *ds = port->ds; - const char *name = port->name; struct net_device *slave_dev; struct dsa_slave_priv *p; + const char *name; + int assign_type; int ret; if (!ds->num_tx_queues) ds->num_tx_queues = 1; + if (port->name) { + name = port->name; + assign_type = NET_NAME_PREDICTABLE; + } else { + name = "eth%d"; + assign_type = NET_NAME_ENUM; + } + slave_dev = alloc_netdev_mqs(sizeof(struct dsa_slave_priv), name, - NET_NAME_UNKNOWN, ether_setup, + assign_type, ether_setup, ds->num_tx_queues, 1); if (slave_dev == NULL) return -ENOMEM; @@ -2406,6 +2454,7 @@ int dsa_slave_create(struct dsa_port *port) SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); SET_NETDEV_DEV(slave_dev, port->ds->dev); + SET_NETDEV_DEVLINK_PORT(slave_dev, &port->devlink_port); slave_dev->dev.of_node = port->dn; slave_dev->vlan_features = master->vlan_features; @@ -3145,7 +3194,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, case NETDEV_CHANGELOWERSTATE: { struct netdev_notifier_changelowerstate_info *info = ptr; struct dsa_port *dp; - int err; + int err = 0; if (dsa_slave_dev_check(dev)) { dp = dsa_slave_to_port(dev); diff --git a/net/dsa/slave.h b/net/dsa/slave.h new file mode 100644 index 000000000000..d0abe609e00d --- /dev/null +++ b/net/dsa/slave.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_SLAVE_H +#define __DSA_SLAVE_H + +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/list.h> +#include <linux/netpoll.h> +#include <linux/types.h> +#include <net/dsa.h> +#include <net/gro_cells.h> + +struct net_device; +struct netlink_ext_ack; + +extern struct notifier_block dsa_slave_switchdev_notifier; +extern struct notifier_block dsa_slave_switchdev_blocking_notifier; + +struct dsa_slave_priv { + /* Copy of CPU port xmit for faster access in slave transmit hot path */ + struct sk_buff * (*xmit)(struct sk_buff *skb, + struct net_device *dev); + + struct gro_cells gcells; + + /* DSA port data, such as switch, port index, etc. */ + struct dsa_port *dp; + +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif + + /* TC context */ + struct list_head mall_tc_list; +}; + +void dsa_slave_mii_bus_init(struct dsa_switch *ds); +int dsa_slave_create(struct dsa_port *dp); +void dsa_slave_destroy(struct net_device *slave_dev); +int dsa_slave_suspend(struct net_device *slave_dev); +int dsa_slave_resume(struct net_device *slave_dev); +int dsa_slave_register_notifier(void); +void dsa_slave_unregister_notifier(void); +void dsa_slave_sync_ha(struct net_device *dev); +void dsa_slave_unsync_ha(struct net_device *dev); +void dsa_slave_setup_tagger(struct net_device *slave); +int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); +int dsa_slave_change_master(struct net_device *dev, struct net_device *master, + struct netlink_ext_ack *extack); +int dsa_slave_manage_vlan_filtering(struct net_device *dev, + bool vlan_filtering); + +static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + + return p->dp; +} + +static inline struct net_device * +dsa_slave_to_master(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return dsa_port_to_master(dp); +} + +#endif diff --git a/net/dsa/switch.c b/net/dsa/switch.c index ce56acdba203..d5bc4bb7310d 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -12,7 +12,12 @@ #include <linux/if_vlan.h> #include <net/switchdev.h> -#include "dsa_priv.h" +#include "dsa.h" +#include "netlink.h" +#include "port.h" +#include "slave.h" +#include "switch.h" +#include "tag_8021q.h" static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) @@ -1013,6 +1018,52 @@ static int dsa_switch_event(struct notifier_block *nb, return notifier_from_errno(err); } +/** + * dsa_tree_notify - Execute code for all switches in a DSA switch tree. + * @dst: collection of struct dsa_switch devices to notify. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Given a struct dsa_switch_tree, this can be used to run a function once for + * each member DSA switch. The other alternative of traversing the tree is only + * through its ports list, which does not uniquely list the switches. + */ +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v) +{ + struct raw_notifier_head *nh = &dst->nh; + int err; + + err = raw_notifier_call_chain(nh, e, v); + + return notifier_to_errno(err); +} + +/** + * dsa_broadcast - Notify all DSA trees in the system. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Can be used to notify the switching fabric of events such as cross-chip + * bridging between disjoint trees (such as islands of tagger-compatible + * switches bridged by an incompatible middle switch). + * + * WARNING: this function is not reliable during probe time, because probing + * between trees is asynchronous and not all DSA trees might have probed. + */ +int dsa_broadcast(unsigned long e, void *v) +{ + struct dsa_switch_tree *dst; + int err = 0; + + list_for_each_entry(dst, &dsa_tree_list, list) { + err = dsa_tree_notify(dst, e, v); + if (err) + break; + } + + return err; +} + int dsa_switch_register_notifier(struct dsa_switch *ds) { ds->nb.notifier_call = dsa_switch_event; diff --git a/net/dsa/switch.h b/net/dsa/switch.h new file mode 100644 index 000000000000..15e67b95eb6e --- /dev/null +++ b/net/dsa/switch.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_SWITCH_H +#define __DSA_SWITCH_H + +#include <net/dsa.h> + +struct netlink_ext_ack; + +enum { + DSA_NOTIFIER_AGEING_TIME, + DSA_NOTIFIER_BRIDGE_JOIN, + DSA_NOTIFIER_BRIDGE_LEAVE, + DSA_NOTIFIER_FDB_ADD, + DSA_NOTIFIER_FDB_DEL, + DSA_NOTIFIER_HOST_FDB_ADD, + DSA_NOTIFIER_HOST_FDB_DEL, + DSA_NOTIFIER_LAG_FDB_ADD, + DSA_NOTIFIER_LAG_FDB_DEL, + DSA_NOTIFIER_LAG_CHANGE, + DSA_NOTIFIER_LAG_JOIN, + DSA_NOTIFIER_LAG_LEAVE, + DSA_NOTIFIER_MDB_ADD, + DSA_NOTIFIER_MDB_DEL, + DSA_NOTIFIER_HOST_MDB_ADD, + DSA_NOTIFIER_HOST_MDB_DEL, + DSA_NOTIFIER_VLAN_ADD, + DSA_NOTIFIER_VLAN_DEL, + DSA_NOTIFIER_HOST_VLAN_ADD, + DSA_NOTIFIER_HOST_VLAN_DEL, + DSA_NOTIFIER_MTU, + DSA_NOTIFIER_TAG_PROTO, + DSA_NOTIFIER_TAG_PROTO_CONNECT, + DSA_NOTIFIER_TAG_PROTO_DISCONNECT, + DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, + DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, + DSA_NOTIFIER_MASTER_STATE_CHANGE, +}; + +/* DSA_NOTIFIER_AGEING_TIME */ +struct dsa_notifier_ageing_time_info { + unsigned int ageing_time; +}; + +/* DSA_NOTIFIER_BRIDGE_* */ +struct dsa_notifier_bridge_info { + const struct dsa_port *dp; + struct dsa_bridge bridge; + bool tx_fwd_offload; + struct netlink_ext_ack *extack; +}; + +/* DSA_NOTIFIER_FDB_* */ +struct dsa_notifier_fdb_info { + const struct dsa_port *dp; + const unsigned char *addr; + u16 vid; + struct dsa_db db; +}; + +/* DSA_NOTIFIER_LAG_FDB_* */ +struct dsa_notifier_lag_fdb_info { + struct dsa_lag *lag; + const unsigned char *addr; + u16 vid; + struct dsa_db db; +}; + +/* DSA_NOTIFIER_MDB_* */ +struct dsa_notifier_mdb_info { + const struct dsa_port *dp; + const struct switchdev_obj_port_mdb *mdb; + struct dsa_db db; +}; + +/* DSA_NOTIFIER_LAG_* */ +struct dsa_notifier_lag_info { + const struct dsa_port *dp; + struct dsa_lag lag; + struct netdev_lag_upper_info *info; + struct netlink_ext_ack *extack; +}; + +/* DSA_NOTIFIER_VLAN_* */ +struct dsa_notifier_vlan_info { + const struct dsa_port *dp; + const struct switchdev_obj_port_vlan *vlan; + struct netlink_ext_ack *extack; +}; + +/* DSA_NOTIFIER_MTU */ +struct dsa_notifier_mtu_info { + const struct dsa_port *dp; + int mtu; +}; + +/* DSA_NOTIFIER_TAG_PROTO_* */ +struct dsa_notifier_tag_proto_info { + const struct dsa_device_ops *tag_ops; +}; + +/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */ +struct dsa_notifier_tag_8021q_vlan_info { + const struct dsa_port *dp; + u16 vid; +}; + +/* DSA_NOTIFIER_MASTER_STATE_CHANGE */ +struct dsa_notifier_master_state_info { + const struct net_device *master; + bool operational; +}; + +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); +int dsa_broadcast(unsigned long e, void *v); + +int dsa_switch_register_notifier(struct dsa_switch *ds); +void dsa_switch_unregister_notifier(struct dsa_switch *ds); + +#endif diff --git a/net/dsa/tag.c b/net/dsa/tag.c new file mode 100644 index 000000000000..383721e167d6 --- /dev/null +++ b/net/dsa/tag.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * DSA tagging protocol handling + * + * Copyright (c) 2008-2009 Marvell Semiconductor + * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> + * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> + */ + +#include <linux/netdevice.h> +#include <linux/ptp_classify.h> +#include <linux/skbuff.h> +#include <net/dsa.h> +#include <net/dst_metadata.h> + +#include "slave.h" +#include "tag.h" + +static LIST_HEAD(dsa_tag_drivers_list); +static DEFINE_MUTEX(dsa_tag_drivers_lock); + +/* Determine if we should defer delivery of skb until we have a rx timestamp. + * + * Called from dsa_switch_rcv. For now, this will only work if tagging is + * enabled on the switch. Normally the MAC driver would retrieve the hardware + * timestamp when it reads the packet out of the hardware. However in a DSA + * switch, the DSA driver owning the interface to which the packet is + * delivered is never notified unless we do so here. + */ +static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p, + struct sk_buff *skb) +{ + struct dsa_switch *ds = p->dp->ds; + unsigned int type; + + if (skb_headroom(skb) < ETH_HLEN) + return false; + + __skb_push(skb, ETH_HLEN); + + type = ptp_classify_raw(skb); + + __skb_pull(skb, ETH_HLEN); + + if (type == PTP_CLASS_NONE) + return false; + + if (likely(ds->ops->port_rxtstamp)) + return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); + + return false; +} + +static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *unused) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct sk_buff *nskb = NULL; + struct dsa_slave_priv *p; + + if (unlikely(!cpu_dp)) { + kfree_skb(skb); + return 0; + } + + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + return 0; + + if (md_dst && md_dst->type == METADATA_HW_PORT_MUX) { + unsigned int port = md_dst->u.port_info.port_id; + + skb_dst_drop(skb); + if (!skb_has_extensions(skb)) + skb->slow_gro = 0; + + skb->dev = dsa_master_find_slave(dev, 0, port); + if (likely(skb->dev)) { + dsa_default_offload_fwd_mark(skb); + nskb = skb; + } + } else { + nskb = cpu_dp->rcv(skb, dev); + } + + if (!nskb) { + kfree_skb(skb); + return 0; + } + + skb = nskb; + skb_push(skb, ETH_HLEN); + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, skb->dev); + + if (unlikely(!dsa_slave_dev_check(skb->dev))) { + /* Packet is to be injected directly on an upper + * device, e.g. a team/bond, so skip all DSA-port + * specific actions. + */ + netif_rx(skb); + return 0; + } + + p = netdev_priv(skb->dev); + + if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { + nskb = dsa_untag_bridge_pvid(skb); + if (!nskb) { + kfree_skb(skb); + return 0; + } + skb = nskb; + } + + dev_sw_netstats_rx_add(skb->dev, skb->len); + + if (dsa_skb_defer_rx_timestamp(p, skb)) + return 0; + + gro_cells_receive(&p->gcells, skb); + + return 0; +} + +struct packet_type dsa_pack_type __read_mostly = { + .type = cpu_to_be16(ETH_P_XDSA), + .func = dsa_switch_rcv, +}; + +static void dsa_tag_driver_register(struct dsa_tag_driver *dsa_tag_driver, + struct module *owner) +{ + dsa_tag_driver->owner = owner; + + mutex_lock(&dsa_tag_drivers_lock); + list_add_tail(&dsa_tag_driver->list, &dsa_tag_drivers_list); + mutex_unlock(&dsa_tag_drivers_lock); +} + +void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count, struct module *owner) +{ + unsigned int i; + + for (i = 0; i < count; i++) + dsa_tag_driver_register(dsa_tag_driver_array[i], owner); +} + +static void dsa_tag_driver_unregister(struct dsa_tag_driver *dsa_tag_driver) +{ + mutex_lock(&dsa_tag_drivers_lock); + list_del(&dsa_tag_driver->list); + mutex_unlock(&dsa_tag_drivers_lock); +} +EXPORT_SYMBOL_GPL(dsa_tag_drivers_register); + +void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count) +{ + unsigned int i; + + for (i = 0; i < count; i++) + dsa_tag_driver_unregister(dsa_tag_driver_array[i]); +} +EXPORT_SYMBOL_GPL(dsa_tag_drivers_unregister); + +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) +{ + return ops->name; +}; + +/* Function takes a reference on the module owning the tagger, + * so dsa_tag_driver_put must be called afterwards. + */ +const struct dsa_device_ops *dsa_tag_driver_get_by_name(const char *name) +{ + const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); + struct dsa_tag_driver *dsa_tag_driver; + + request_module("%s%s", DSA_TAG_DRIVER_ALIAS, name); + + mutex_lock(&dsa_tag_drivers_lock); + list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { + const struct dsa_device_ops *tmp = dsa_tag_driver->ops; + + if (strcmp(name, tmp->name)) + continue; + + if (!try_module_get(dsa_tag_driver->owner)) + break; + + ops = tmp; + break; + } + mutex_unlock(&dsa_tag_drivers_lock); + + return ops; +} + +const struct dsa_device_ops *dsa_tag_driver_get_by_id(int tag_protocol) +{ + struct dsa_tag_driver *dsa_tag_driver; + const struct dsa_device_ops *ops; + bool found = false; + + request_module("%sid-%d", DSA_TAG_DRIVER_ALIAS, tag_protocol); + + mutex_lock(&dsa_tag_drivers_lock); + list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { + ops = dsa_tag_driver->ops; + if (ops->proto == tag_protocol) { + found = true; + break; + } + } + + if (found) { + if (!try_module_get(dsa_tag_driver->owner)) + ops = ERR_PTR(-ENOPROTOOPT); + } else { + ops = ERR_PTR(-ENOPROTOOPT); + } + + mutex_unlock(&dsa_tag_drivers_lock); + + return ops; +} + +void dsa_tag_driver_put(const struct dsa_device_ops *ops) +{ + struct dsa_tag_driver *dsa_tag_driver; + + mutex_lock(&dsa_tag_drivers_lock); + list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { + if (dsa_tag_driver->ops == ops) { + module_put(dsa_tag_driver->owner); + break; + } + } + mutex_unlock(&dsa_tag_drivers_lock); +} diff --git a/net/dsa/tag.h b/net/dsa/tag.h new file mode 100644 index 000000000000..7cfbca824f1c --- /dev/null +++ b/net/dsa/tag.h @@ -0,0 +1,310 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_TAG_H +#define __DSA_TAG_H + +#include <linux/if_vlan.h> +#include <linux/list.h> +#include <linux/types.h> +#include <net/dsa.h> + +#include "port.h" +#include "slave.h" + +struct dsa_tag_driver { + const struct dsa_device_ops *ops; + struct list_head list; + struct module *owner; +}; + +extern struct packet_type dsa_pack_type; + +const struct dsa_device_ops *dsa_tag_driver_get_by_id(int tag_protocol); +const struct dsa_device_ops *dsa_tag_driver_get_by_name(const char *name); +void dsa_tag_driver_put(const struct dsa_device_ops *ops); +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); + +static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) +{ + return ops->needed_headroom + ops->needed_tailroom; +} + +static inline struct net_device *dsa_master_find_slave(struct net_device *dev, + int device, int port) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dp->ds->index == device && dp->index == port && + dp->type == DSA_PORT_TYPE_USER) + return dp->slave; + + return NULL; +} + +/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged + * frames as untagged, since the bridge will not untag them. + */ +static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + struct net_device *dev = skb->dev; + struct net_device *upper_dev; + u16 vid, pvid, proto; + int err; + + if (!br || br_vlan_enabled(br)) + return skb; + + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + /* We already run under an RCU read-side critical section since + * we are called from netif_receive_skb_list_internal(). + */ + err = br_vlan_get_pvid_rcu(dev, &pvid); + if (err) + return skb; + + if (vid != pvid) + return skb; + + /* The sad part about attempting to untag from DSA is that we + * don't know, unless we check, if the skb will end up in + * the bridge's data path - br_allowed_ingress() - or not. + * For example, there might be an 8021q upper for the + * default_pvid of the bridge, which will steal VLAN-tagged traffic + * from the bridge's data path. This is a configuration that DSA + * supports because vlan_filtering is 0. In that case, we should + * definitely keep the tag, to make sure it keeps working. + */ + upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); + if (upper_dev) + return skb; + + __vlan_hwaccel_clear_tag(skb); + + return skb; +} + +/* For switches without hardware support for DSA tagging to be able + * to support termination through the bridge. + */ +static inline struct net_device * +dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct bridge_vlan_info vinfo; + struct net_device *slave; + struct dsa_port *dp; + int err; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->type != DSA_PORT_TYPE_USER) + continue; + + if (!dp->bridge) + continue; + + if (dp->stp_state != BR_STATE_LEARNING && + dp->stp_state != BR_STATE_FORWARDING) + continue; + + /* Since the bridge might learn this packet, keep the CPU port + * affinity with the port that will be used for the reply on + * xmit. + */ + if (dp->cpu_dp != cpu_dp) + continue; + + slave = dp->slave; + + err = br_vlan_get_info_rcu(slave, vid, &vinfo); + if (err) + continue; + + return slave; + } + + return NULL; +} + +/* If the ingress port offloads the bridge, we mark the frame as autonomously + * forwarded by hardware, so the software bridge doesn't forward in twice, back + * to us, because we already did. However, if we're in fallback mode and we do + * software bridging, we are not offloading it, therefore the dp->bridge + * pointer is not populated, and flooding needs to be done by software (we are + * effectively operating in standalone ports mode). + */ +static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + + skb->offload_fwd_mark = !!(dp->bridge); +} + +/* Helper for removing DSA header tags from packets in the RX path. + * Must not be called before skb_pull(len). + * skb->data + * | + * v + * | | | | | | | | | | | | | | | | | | | + * +-----------------------+-----------------------+---------------+-------+ + * | Destination MAC | Source MAC | DSA header | EType | + * +-----------------------+-----------------------+---------------+-------+ + * | | + * <----- len -----> <----- len -----> + * | + * >>>>>>> v + * >>>>>>> | | | | | | | | | | | | | | | + * >>>>>>> +-----------------------+-----------------------+-------+ + * >>>>>>> | Destination MAC | Source MAC | EType | + * +-----------------------+-----------------------+-------+ + * ^ + * | + * skb->data + */ +static inline void dsa_strip_etype_header(struct sk_buff *skb, int len) +{ + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - len, 2 * ETH_ALEN); +} + +/* Helper for creating space for DSA header tags in TX path packets. + * Must not be called before skb_push(len). + * + * Before: + * + * <<<<<<< | | | | | | | | | | | | | | | + * ^ <<<<<<< +-----------------------+-----------------------+-------+ + * | <<<<<<< | Destination MAC | Source MAC | EType | + * | +-----------------------+-----------------------+-------+ + * <----- len -----> + * | + * | + * skb->data + * + * After: + * + * | | | | | | | | | | | | | | | | | | | + * +-----------------------+-----------------------+---------------+-------+ + * | Destination MAC | Source MAC | DSA header | EType | + * +-----------------------+-----------------------+---------------+-------+ + * ^ | | + * | <----- len -----> + * skb->data + */ +static inline void dsa_alloc_etype_header(struct sk_buff *skb, int len) +{ + memmove(skb->data, skb->data + len, 2 * ETH_ALEN); +} + +/* On RX, eth_type_trans() on the DSA master pulls ETH_HLEN bytes starting from + * skb_mac_header(skb), which leaves skb->data pointing at the first byte after + * what the DSA master perceives as the EtherType (the beginning of the L3 + * protocol). Since DSA EtherType header taggers treat the EtherType as part of + * the DSA tag itself, and the EtherType is 2 bytes in length, the DSA header + * is located 2 bytes behind skb->data. Note that EtherType in this context + * means the first 2 bytes of the DSA header, not the encapsulated EtherType + * that will become visible after the DSA header is stripped. + */ +static inline void *dsa_etype_header_pos_rx(struct sk_buff *skb) +{ + return skb->data - 2; +} + +/* On TX, skb->data points to skb_mac_header(skb), which means that EtherType + * header taggers start exactly where the EtherType is (the EtherType is + * treated as part of the DSA header). + */ +static inline void *dsa_etype_header_pos_tx(struct sk_buff *skb) +{ + return skb->data + 2 * ETH_ALEN; +} + +/* Create 2 modaliases per tagging protocol, one to auto-load the module + * given the ID reported by get_tag_protocol(), and the other by name. + */ +#define DSA_TAG_DRIVER_ALIAS "dsa_tag:" +#define MODULE_ALIAS_DSA_TAG_DRIVER(__proto, __name) \ + MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __name); \ + MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS "id-" \ + __stringify(__proto##_VALUE)) + +void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count, + struct module *owner); +void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count); + +#define dsa_tag_driver_module_drivers(__dsa_tag_drivers_array, __count) \ +static int __init dsa_tag_driver_module_init(void) \ +{ \ + dsa_tag_drivers_register(__dsa_tag_drivers_array, __count, \ + THIS_MODULE); \ + return 0; \ +} \ +module_init(dsa_tag_driver_module_init); \ + \ +static void __exit dsa_tag_driver_module_exit(void) \ +{ \ + dsa_tag_drivers_unregister(__dsa_tag_drivers_array, __count); \ +} \ +module_exit(dsa_tag_driver_module_exit) + +/** + * module_dsa_tag_drivers() - Helper macro for registering DSA tag + * drivers + * @__ops_array: Array of tag driver structures + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_drivers(__ops_array) \ +dsa_tag_driver_module_drivers(__ops_array, ARRAY_SIZE(__ops_array)) + +#define DSA_TAG_DRIVER_NAME(__ops) dsa_tag_driver ## _ ## __ops + +/* Create a static structure we can build a linked list of dsa_tag + * drivers + */ +#define DSA_TAG_DRIVER(__ops) \ +static struct dsa_tag_driver DSA_TAG_DRIVER_NAME(__ops) = { \ + .ops = &__ops, \ +} + +/** + * module_dsa_tag_driver() - Helper macro for registering a single DSA tag + * driver + * @__ops: Single tag driver structures + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_driver(__ops) \ +DSA_TAG_DRIVER(__ops); \ + \ +static struct dsa_tag_driver *dsa_tag_driver_array[] = { \ + &DSA_TAG_DRIVER_NAME(__ops) \ +}; \ +module_dsa_tag_drivers(dsa_tag_driver_array) + +#endif diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 34e5ec5d3e23..b1263917fcb2 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -7,7 +7,10 @@ #include <linux/if_vlan.h> #include <linux/dsa/8021q.h> -#include "dsa_priv.h" +#include "port.h" +#include "switch.h" +#include "tag.h" +#include "tag_8021q.h" /* Binary structure of the fake 12-bit VID field (when the TPID is * ETH_P_DSA_8021Q): @@ -60,6 +63,20 @@ #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ DSA_8021Q_PORT_MASK) +struct dsa_tag_8021q_vlan { + struct list_head list; + int port; + u16 vid; + refcount_t refcount; +}; + +struct dsa_8021q_context { + struct dsa_switch *ds; + struct list_head vlans; + /* EtherType of RX VID, used for filtering on master interface */ + __be16 proto; +}; + u16 dsa_tag_8021q_bridge_vid(unsigned int bridge_num) { /* The VBID value of 0 is reserved for precise TX, but it is also diff --git a/net/dsa/tag_8021q.h b/net/dsa/tag_8021q.h new file mode 100644 index 000000000000..b75cbaa028ef --- /dev/null +++ b/net/dsa/tag_8021q.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_TAG_8021Q_H +#define __DSA_TAG_8021Q_H + +#include <net/dsa.h> + +#include "switch.h" + +struct sk_buff; +struct net_device; + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci); + +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *vbid); + +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, + int vbid); + +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); + +#endif diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 8a02ac44282f..7f3b7d730b85 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -7,7 +7,9 @@ #include <linux/bitfield.h> #include <linux/etherdevice.h> -#include "dsa_priv.h" +#include "tag.h" + +#define AR9331_NAME "ar9331" #define AR9331_HDR_LEN 2 #define AR9331_HDR_VERSION 1 @@ -80,7 +82,7 @@ static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops ar9331_netdev_ops = { - .name = "ar9331", + .name = AR9331_NAME, .proto = DSA_TAG_PROTO_AR9331, .xmit = ar9331_tag_xmit, .rcv = ar9331_tag_rcv, @@ -88,5 +90,5 @@ static const struct dsa_device_ops ar9331_netdev_ops = { }; MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_AR9331); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_AR9331, AR9331_NAME); module_dsa_tag_driver(ar9331_netdev_ops); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 16889ea3e0a7..10239daa5745 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -10,7 +10,11 @@ #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" + +#define BRCM_NAME "brcm" +#define BRCM_LEGACY_NAME "brcm-legacy" +#define BRCM_PREPEND_NAME "brcm-prepend" /* Legacy Broadcom tag (6 bytes) */ #define BRCM_LEG_TAG_LEN 6 @@ -196,7 +200,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops brcm_netdev_ops = { - .name = "brcm", + .name = BRCM_NAME, .proto = DSA_TAG_PROTO_BRCM, .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, @@ -204,7 +208,7 @@ static const struct dsa_device_ops brcm_netdev_ops = { }; DSA_TAG_DRIVER(brcm_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM, BRCM_NAME); #endif #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) @@ -273,7 +277,7 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops brcm_legacy_netdev_ops = { - .name = "brcm-legacy", + .name = BRCM_LEGACY_NAME, .proto = DSA_TAG_PROTO_BRCM_LEGACY, .xmit = brcm_leg_tag_xmit, .rcv = brcm_leg_tag_rcv, @@ -281,7 +285,7 @@ static const struct dsa_device_ops brcm_legacy_netdev_ops = { }; DSA_TAG_DRIVER(brcm_legacy_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY, BRCM_LEGACY_NAME); #endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY */ #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND) @@ -300,7 +304,7 @@ static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb, } static const struct dsa_device_ops brcm_prepend_netdev_ops = { - .name = "brcm-prepend", + .name = BRCM_PREPEND_NAME, .proto = DSA_TAG_PROTO_BRCM_PREPEND, .xmit = brcm_tag_xmit_prepend, .rcv = brcm_tag_rcv_prepend, @@ -308,7 +312,7 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = { }; DSA_TAG_DRIVER(brcm_prepend_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_PREPEND); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_PREPEND, BRCM_PREPEND_NAME); #endif static struct dsa_tag_driver *dsa_tag_driver_array[] = { diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index e4b6e3f2a3db..1fd7fa26db64 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -50,7 +50,10 @@ #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" + +#define DSA_NAME "dsa" +#define EDSA_NAME "edsa" #define DSA_HLEN 4 @@ -339,7 +342,7 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops dsa_netdev_ops = { - .name = "dsa", + .name = DSA_NAME, .proto = DSA_TAG_PROTO_DSA, .xmit = dsa_xmit, .rcv = dsa_rcv, @@ -347,7 +350,7 @@ static const struct dsa_device_ops dsa_netdev_ops = { }; DSA_TAG_DRIVER(dsa_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA, DSA_NAME); #endif /* CONFIG_NET_DSA_TAG_DSA */ #if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA) @@ -381,7 +384,7 @@ static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops edsa_netdev_ops = { - .name = "edsa", + .name = EDSA_NAME, .proto = DSA_TAG_PROTO_EDSA, .xmit = edsa_xmit, .rcv = edsa_rcv, @@ -389,7 +392,7 @@ static const struct dsa_device_ops edsa_netdev_ops = { }; DSA_TAG_DRIVER(edsa_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA, EDSA_NAME); #endif /* CONFIG_NET_DSA_TAG_EDSA */ static struct dsa_tag_driver *dsa_tag_drivers[] = { diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index df7140984da3..e279cd9057b0 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -10,7 +10,9 @@ #include <linux/skbuff.h> #include <net/dsa.h> -#include "dsa_priv.h" +#include "tag.h" + +#define GSWIP_NAME "gswip" #define GSWIP_TX_HEADER_LEN 4 @@ -98,7 +100,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops gswip_netdev_ops = { - .name = "gswip", + .name = GSWIP_NAME, .proto = DSA_TAG_PROTO_GSWIP, .xmit = gswip_tag_xmit, .rcv = gswip_tag_rcv, @@ -106,6 +108,6 @@ static const struct dsa_device_ops gswip_netdev_ops = { }; MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_GSWIP); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_GSWIP, GSWIP_NAME); module_dsa_tag_driver(gswip_netdev_ops); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index 846588c0070a..71884296fc70 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -11,7 +11,9 @@ #include <linux/skbuff.h> #include <net/dsa.h> -#include "dsa_priv.h" +#include "tag.h" + +#define HELLCREEK_NAME "hellcreek" #define HELLCREEK_TAG_LEN 1 @@ -57,7 +59,7 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, } static const struct dsa_device_ops hellcreek_netdev_ops = { - .name = "hellcreek", + .name = HELLCREEK_NAME, .proto = DSA_TAG_PROTO_HELLCREEK, .xmit = hellcreek_xmit, .rcv = hellcreek_rcv, @@ -65,6 +67,6 @@ static const struct dsa_device_ops hellcreek_netdev_ops = { }; MODULE_LICENSE("Dual MIT/GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK, HELLCREEK_NAME); module_dsa_tag_driver(hellcreek_netdev_ops); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 38fa19c1e2d5..0f6ae143afc9 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -7,7 +7,13 @@ #include <linux/etherdevice.h> #include <linux/list.h> #include <net/dsa.h> -#include "dsa_priv.h" + +#include "tag.h" + +#define KSZ8795_NAME "ksz8795" +#define KSZ9477_NAME "ksz9477" +#define KSZ9893_NAME "ksz9893" +#define LAN937X_NAME "lan937x" /* Typically only one byte is used for tail tag. */ #define KSZ_EGRESS_TAG_LEN 1 @@ -74,7 +80,7 @@ static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops ksz8795_netdev_ops = { - .name = "ksz8795", + .name = KSZ8795_NAME, .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, @@ -82,7 +88,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { }; DSA_TAG_DRIVER(ksz8795_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME); /* * For Ingress (Host -> KSZ9477), 2 bytes are added before FCS. @@ -147,7 +153,7 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops ksz9477_netdev_ops = { - .name = "ksz9477", + .name = KSZ9477_NAME, .proto = DSA_TAG_PROTO_KSZ9477, .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, @@ -155,7 +161,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = { }; DSA_TAG_DRIVER(ksz9477_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9477); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9477, KSZ9477_NAME); #define KSZ9893_TAIL_TAG_OVERRIDE BIT(5) #define KSZ9893_TAIL_TAG_LOOKUP BIT(6) @@ -183,7 +189,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, } static const struct dsa_device_ops ksz9893_netdev_ops = { - .name = "ksz9893", + .name = KSZ9893_NAME, .proto = DSA_TAG_PROTO_KSZ9893, .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, @@ -191,7 +197,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = { }; DSA_TAG_DRIVER(ksz9893_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893, KSZ9893_NAME); /* For xmit, 2 bytes are added before FCS. * --------------------------------------------------------------------------- @@ -241,7 +247,7 @@ static struct sk_buff *lan937x_xmit(struct sk_buff *skb, } static const struct dsa_device_ops lan937x_netdev_ops = { - .name = "lan937x", + .name = LAN937X_NAME, .proto = DSA_TAG_PROTO_LAN937X, .xmit = lan937x_xmit, .rcv = ksz9477_rcv, @@ -249,7 +255,7 @@ static const struct dsa_device_ops lan937x_netdev_ops = { }; DSA_TAG_DRIVER(lan937x_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN937X); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN937X, LAN937X_NAME); static struct dsa_tag_driver *dsa_tag_driver_array[] = { &DSA_TAG_DRIVER_NAME(ksz8795_netdev_ops), diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index 98d7d7120bab..c25f5536706b 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -7,7 +7,7 @@ #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" /* To define the outgoing port and to discover the incoming port a regular * VLAN tag is used by the LAN9303. But its VID meaning is 'special': @@ -30,6 +30,8 @@ * Required when no forwarding between the external ports should happen. */ +#define LAN9303_NAME "lan9303" + #define LAN9303_TAG_LEN 4 # define LAN9303_TAG_TX_USE_ALR BIT(3) # define LAN9303_TAG_TX_STP_OVERRIDE BIT(4) @@ -110,7 +112,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops lan9303_netdev_ops = { - .name = "lan9303", + .name = LAN9303_NAME, .proto = DSA_TAG_PROTO_LAN9303, .xmit = lan9303_xmit, .rcv = lan9303_rcv, @@ -118,6 +120,6 @@ static const struct dsa_device_ops lan9303_netdev_ops = { }; MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN9303); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN9303, LAN9303_NAME); module_dsa_tag_driver(lan9303_netdev_ops); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 415d8ece242a..40af80452747 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -8,7 +8,9 @@ #include <linux/etherdevice.h> #include <linux/if_vlan.h> -#include "dsa_priv.h" +#include "tag.h" + +#define MTK_NAME "mtk" #define MTK_HDR_LEN 4 #define MTK_HDR_XMIT_UNTAGGED 0 @@ -25,6 +27,8 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, u8 xmit_tpid; u8 *mtk_tag; + skb_set_queue_mapping(skb, dp->index); + /* Build the special tag after the MAC Source Address. If VLAN header * is present, it's required that VLAN header and special tag is * being combined. Only in this way we can allow the switch can parse @@ -91,7 +95,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops mtk_netdev_ops = { - .name = "mtk", + .name = MTK_NAME, .proto = DSA_TAG_PROTO_MTK, .xmit = mtk_tag_xmit, .rcv = mtk_tag_rcv, @@ -99,6 +103,6 @@ static const struct dsa_device_ops mtk_netdev_ops = { }; MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MTK); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MTK, MTK_NAME); module_dsa_tag_driver(mtk_netdev_ops); diff --git a/net/dsa/tag_none.c b/net/dsa/tag_none.c new file mode 100644 index 000000000000..d2fd179c4227 --- /dev/null +++ b/net/dsa/tag_none.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * net/dsa/tag_none.c - Traffic handling for switches with no tag + * Copyright (c) 2008-2009 Marvell Semiconductor + * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> + * + * WARNING: do not use this for new switches. In case of no hardware + * tagging support, look at tag_8021q.c instead. + */ + +#include "tag.h" + +#define NONE_NAME "none" + +static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* Just return the original SKB */ + return skb; +} + +static const struct dsa_device_ops none_ops = { + .name = NONE_NAME, + .proto = DSA_TAG_PROTO_NONE, + .xmit = dsa_slave_notag_xmit, +}; + +module_dsa_tag_driver(none_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_NONE, NONE_NAME); +MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 0d81f172b7a6..28ebecafdd24 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -2,7 +2,11 @@ /* Copyright 2019 NXP */ #include <linux/dsa/ocelot.h> -#include "dsa_priv.h" + +#include "tag.h" + +#define OCELOT_NAME "ocelot" +#define SEVILLE_NAME "seville" /* If the port is under a VLAN-aware bridge, remove the VLAN header from the * payload and move it into the DSA tag, which will make the switch classify @@ -183,7 +187,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, } static const struct dsa_device_ops ocelot_netdev_ops = { - .name = "ocelot", + .name = OCELOT_NAME, .proto = DSA_TAG_PROTO_OCELOT, .xmit = ocelot_xmit, .rcv = ocelot_rcv, @@ -192,10 +196,10 @@ static const struct dsa_device_ops ocelot_netdev_ops = { }; DSA_TAG_DRIVER(ocelot_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT, OCELOT_NAME); static const struct dsa_device_ops seville_netdev_ops = { - .name = "seville", + .name = SEVILLE_NAME, .proto = DSA_TAG_PROTO_SEVILLE, .xmit = seville_xmit, .rcv = ocelot_rcv, @@ -204,7 +208,7 @@ static const struct dsa_device_ops seville_netdev_ops = { }; DSA_TAG_DRIVER(seville_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SEVILLE); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SEVILLE, SEVILLE_NAME); static struct dsa_tag_driver *ocelot_tag_driver_array[] = { &DSA_TAG_DRIVER_NAME(ocelot_netdev_ops), diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 37ccf00404ea..1f0b8c20eba5 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -10,7 +10,11 @@ */ #include <linux/dsa/8021q.h> #include <linux/dsa/ocelot.h> -#include "dsa_priv.h" + +#include "tag.h" +#include "tag_8021q.h" + +#define OCELOT_8021Q_NAME "ocelot-8021q" struct ocelot_8021q_tagger_private { struct ocelot_8021q_tagger_data data; /* Must be first */ @@ -119,7 +123,7 @@ static int ocelot_connect(struct dsa_switch *ds) } static const struct dsa_device_ops ocelot_8021q_netdev_ops = { - .name = "ocelot-8021q", + .name = OCELOT_8021Q_NAME, .proto = DSA_TAG_PROTO_OCELOT_8021Q, .xmit = ocelot_xmit, .rcv = ocelot_rcv, @@ -130,6 +134,6 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = { }; MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT_8021Q); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT_8021Q, OCELOT_8021Q_NAME); module_dsa_tag_driver(ocelot_8021q_netdev_ops); diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 57d2e00f1e5d..e757c8de06f1 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -8,7 +8,9 @@ #include <net/dsa.h> #include <linux/dsa/tag_qca.h> -#include "dsa_priv.h" +#include "tag.h" + +#define QCA_NAME "qca" static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -107,7 +109,7 @@ static void qca_tag_disconnect(struct dsa_switch *ds) } static const struct dsa_device_ops qca_netdev_ops = { - .name = "qca", + .name = QCA_NAME, .proto = DSA_TAG_PROTO_QCA, .connect = qca_tag_connect, .disconnect = qca_tag_disconnect, @@ -118,6 +120,6 @@ static const struct dsa_device_ops qca_netdev_ops = { }; MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_QCA); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_QCA, QCA_NAME); module_dsa_tag_driver(qca_netdev_ops); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index 6d928ee3ef7a..c327314b95e3 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -18,7 +18,9 @@ #include <linux/etherdevice.h> #include <linux/bits.h> -#include "dsa_priv.h" +#include "tag.h" + +#define RTL4_A_NAME "rtl4a" #define RTL4_A_HDR_LEN 4 #define RTL4_A_ETHERTYPE 0x8899 @@ -112,7 +114,7 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops rtl4a_netdev_ops = { - .name = "rtl4a", + .name = RTL4_A_NAME, .proto = DSA_TAG_PROTO_RTL4_A, .xmit = rtl4a_tag_xmit, .rcv = rtl4a_tag_rcv, @@ -121,4 +123,4 @@ static const struct dsa_device_ops rtl4a_netdev_ops = { module_dsa_tag_driver(rtl4a_netdev_ops); MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL4_A); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL4_A, RTL4_A_NAME); diff --git a/net/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c index a593ead7ff26..4f67834fd121 100644 --- a/net/dsa/tag_rtl8_4.c +++ b/net/dsa/tag_rtl8_4.c @@ -77,13 +77,16 @@ #include <linux/bits.h> #include <linux/etherdevice.h> -#include "dsa_priv.h" +#include "tag.h" /* Protocols supported: * * 0x04 = RTL8365MB DSA protocol */ +#define RTL8_4_NAME "rtl8_4" +#define RTL8_4T_NAME "rtl8_4t" + #define RTL8_4_TAG_LEN 8 #define RTL8_4_PROTOCOL GENMASK(15, 8) @@ -234,7 +237,7 @@ static const struct dsa_device_ops rtl8_4_netdev_ops = { DSA_TAG_DRIVER(rtl8_4_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4, RTL8_4_NAME); /* Tail version */ static const struct dsa_device_ops rtl8_4t_netdev_ops = { @@ -247,7 +250,7 @@ static const struct dsa_device_ops rtl8_4t_netdev_ops = { DSA_TAG_DRIVER(rtl8_4t_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4T); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4T, RTL8_4T_NAME); static struct dsa_tag_driver *dsa_tag_drivers[] = { &DSA_TAG_DRIVER_NAME(rtl8_4_netdev_ops), diff --git a/net/dsa/tag_rzn1_a5psw.c b/net/dsa/tag_rzn1_a5psw.c index e2a5ee6ae688..437a6820ac42 100644 --- a/net/dsa/tag_rzn1_a5psw.c +++ b/net/dsa/tag_rzn1_a5psw.c @@ -10,7 +10,7 @@ #include <linux/if_ether.h> #include <net/dsa.h> -#include "dsa_priv.h" +#include "tag.h" /* To define the outgoing port and to discover the incoming port a TAG is * inserted after Src MAC : @@ -22,6 +22,8 @@ * See struct a5psw_tag for layout */ +#define A5PSW_NAME "a5psw" + #define ETH_P_DSA_A5PSW 0xE001 #define A5PSW_TAG_LEN 8 #define A5PSW_CTRL_DATA_FORCE_FORWARD BIT(0) @@ -101,7 +103,7 @@ static struct sk_buff *a5psw_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops a5psw_netdev_ops = { - .name = "a5psw", + .name = A5PSW_NAME, .proto = DSA_TAG_PROTO_RZN1_A5PSW, .xmit = a5psw_tag_xmit, .rcv = a5psw_tag_rcv, @@ -109,5 +111,5 @@ static const struct dsa_device_ops a5psw_netdev_ops = { }; MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_A5PSW); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_A5PSW, A5PSW_NAME); module_dsa_tag_driver(a5psw_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 83e4136516b0..f14f51b41491 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -5,7 +5,12 @@ #include <linux/dsa/sja1105.h> #include <linux/dsa/8021q.h> #include <linux/packing.h> -#include "dsa_priv.h" + +#include "tag.h" +#include "tag_8021q.h" + +#define SJA1105_NAME "sja1105" +#define SJA1110_NAME "sja1110" /* Is this a TX or an RX header? */ #define SJA1110_HEADER_HOST_TO_SWITCH BIT(15) @@ -786,7 +791,7 @@ static int sja1105_connect(struct dsa_switch *ds) } static const struct dsa_device_ops sja1105_netdev_ops = { - .name = "sja1105", + .name = SJA1105_NAME, .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, @@ -798,10 +803,10 @@ static const struct dsa_device_ops sja1105_netdev_ops = { }; DSA_TAG_DRIVER(sja1105_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105, SJA1105_NAME); static const struct dsa_device_ops sja1110_netdev_ops = { - .name = "sja1110", + .name = SJA1110_NAME, .proto = DSA_TAG_PROTO_SJA1110, .xmit = sja1110_xmit, .rcv = sja1110_rcv, @@ -813,7 +818,7 @@ static const struct dsa_device_ops sja1110_netdev_ops = { }; DSA_TAG_DRIVER(sja1110_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110, SJA1110_NAME); static struct dsa_tag_driver *sja1105_tag_driver_array[] = { &DSA_TAG_DRIVER_NAME(sja1105_netdev_ops), diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 5749ba85c2b8..7361b9106382 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -8,7 +8,9 @@ #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" + +#define TRAILER_NAME "trailer" static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -50,7 +52,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops trailer_netdev_ops = { - .name = "trailer", + .name = TRAILER_NAME, .proto = DSA_TAG_PROTO_TRAILER, .xmit = trailer_xmit, .rcv = trailer_rcv, @@ -58,6 +60,6 @@ static const struct dsa_device_ops trailer_netdev_ops = { }; MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_TRAILER); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_TRAILER, TRAILER_NAME); module_dsa_tag_driver(trailer_netdev_ops); diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c index ff442b8af636..af19969f9bc4 100644 --- a/net/dsa/tag_xrs700x.c +++ b/net/dsa/tag_xrs700x.c @@ -7,7 +7,9 @@ #include <linux/bitops.h> -#include "dsa_priv.h" +#include "tag.h" + +#define XRS700X_NAME "xrs700x" static struct sk_buff *xrs700x_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -51,7 +53,7 @@ static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev) } static const struct dsa_device_ops xrs700x_netdev_ops = { - .name = "xrs700x", + .name = XRS700X_NAME, .proto = DSA_TAG_PROTO_XRS700X, .xmit = xrs700x_xmit, .rcv = xrs700x_rcv, @@ -59,6 +61,6 @@ static const struct dsa_device_ops xrs700x_netdev_ops = { }; MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_XRS700X); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_XRS700X, XRS700X_NAME); module_dsa_tag_driver(xrs700x_netdev_ops); diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 403158862011..c7e37130647e 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -116,9 +116,10 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) struct ethtool_channels channels = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; - u32 err_attr, max_rx_in_use = 0; + u32 err_attr, max_rxfh_in_use; const struct ethtool_ops *ops; struct net_device *dev; + u64 max_rxnfc_in_use; int ret; ret = ethnl_parse_header_dev_get(&req_info, @@ -189,15 +190,23 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) } /* ensure the new Rx count fits within the configured Rx flow - * indirection table settings + * indirection table/rxnfc settings */ - if (netif_is_rxfh_configured(dev) && - !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && - (channels.combined_count + channels.rx_count) <= max_rx_in_use) { + if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) + max_rxnfc_in_use = 0; + if (!netif_is_rxfh_configured(dev) || + ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use)) + max_rxfh_in_use = 0; + if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { ret = -EINVAL; GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing indirection table settings"); goto out_ops; } + if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { + ret = -EINVAL; + GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); + goto out_ops; + } /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 566adf85e658..21cfe8557205 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -202,6 +202,12 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(100, FX, Half), __DEFINE_LINK_MODE_NAME(100, FX, Full), __DEFINE_LINK_MODE_NAME(10, T1L, Full), + __DEFINE_LINK_MODE_NAME(800000, CR8, Full), + __DEFINE_LINK_MODE_NAME(800000, KR8, Full), + __DEFINE_LINK_MODE_NAME(800000, DR8, Full), + __DEFINE_LINK_MODE_NAME(800000, DR8_2, Full), + __DEFINE_LINK_MODE_NAME(800000, SR8, Full), + __DEFINE_LINK_MODE_NAME(800000, VR8, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -238,6 +244,8 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_X 1 #define __LINK_MODE_LANES_FX 1 #define __LINK_MODE_LANES_T1L 1 +#define __LINK_MODE_LANES_VR8 8 +#define __LINK_MODE_LANES_DR8_2 8 #define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ @@ -352,6 +360,12 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(100, FX, Half), __DEFINE_LINK_MODE_PARAMS(100, FX, Full), __DEFINE_LINK_MODE_PARAMS(10, T1L, Full), + __DEFINE_LINK_MODE_PARAMS(800000, CR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, KR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, DR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, DR8_2, Full), + __DEFINE_LINK_MODE_PARAMS(800000, SR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, VR8, Full), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -498,6 +512,72 @@ int __ethtool_get_link(struct net_device *dev) return netif_running(dev) && dev->ethtool_ops->get_link(dev); } +static int ethtool_get_rxnfc_rule_count(struct net_device *dev) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxnfc info = { + .cmd = ETHTOOL_GRXCLSRLCNT, + }; + int err; + + err = ops->get_rxnfc(dev, &info, NULL); + if (err) + return err; + + return info.rule_cnt; +} + +int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxnfc *info; + int err, i, rule_cnt; + u64 max_ring = 0; + + if (!ops->get_rxnfc) + return -EOPNOTSUPP; + + rule_cnt = ethtool_get_rxnfc_rule_count(dev); + if (rule_cnt <= 0) + return -EINVAL; + + info = kvzalloc(struct_size(info, rule_locs, rule_cnt), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->cmd = ETHTOOL_GRXCLSRLALL; + info->rule_cnt = rule_cnt; + err = ops->get_rxnfc(dev, info, info->rule_locs); + if (err) + goto err_free_info; + + for (i = 0; i < rule_cnt; i++) { + struct ethtool_rxnfc rule_info = { + .cmd = ETHTOOL_GRXCLSRULE, + .fs.location = info->rule_locs[i], + }; + + err = ops->get_rxnfc(dev, &rule_info, NULL); + if (err) + goto err_free_info; + + if (rule_info.fs.ring_cookie != RX_CLS_FLOW_DISC && + rule_info.fs.ring_cookie != RX_CLS_FLOW_WAKE && + !(rule_info.flow_type & FLOW_RSS) && + !ethtool_get_flow_spec_ring_vf(rule_info.fs.ring_cookie)) + max_ring = + max_t(u64, max_ring, rule_info.fs.ring_cookie); + } + + kvfree(info); + *max = max_ring; + return 0; + +err_free_info: + kvfree(info); + return err; +} + int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) { u32 dev_size, current_max = 0; diff --git a/net/ethtool/common.h b/net/ethtool/common.h index c1779657e074..b1b9db810eca 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -43,6 +43,7 @@ bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings); int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max); +int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max); int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info); extern const struct ethtool_phy_ops *ethtool_phy_ops; diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 1c94bb8ea03f..49c0a2a77f02 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -124,7 +124,7 @@ static int eeprom_prepare_data(const struct ethnl_req_info *req_base, if (ret) goto err_free; - ret = get_module_eeprom_by_page(dev, &page_data, info->extack); + ret = get_module_eeprom_by_page(dev, &page_data, info ? info->extack : NULL); if (ret < 0) goto err_ops; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 57e7238a4136..c2f1a542e6fa 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -44,16 +44,9 @@ struct ethtool_devlink_compat { static struct devlink *netdev_to_devlink_get(struct net_device *dev) { - struct devlink_port *devlink_port; - - if (!dev->netdev_ops->ndo_get_devlink_port) - return NULL; - - devlink_port = dev->netdev_ops->ndo_get_devlink_port(dev); - if (!devlink_port) + if (!dev->devlink_port) return NULL; - - return devlink_try_get(devlink_port->devlink); + return devlink_try_get(dev->devlink_port->devlink); } /* @@ -713,15 +706,22 @@ static int ethtool_get_drvinfo(struct net_device *dev, struct ethtool_devlink_compat *rsp) { const struct ethtool_ops *ops = dev->ethtool_ops; + struct device *parent = dev->dev.parent; rsp->info.cmd = ETHTOOL_GDRVINFO; strscpy(rsp->info.version, UTS_RELEASE, sizeof(rsp->info.version)); if (ops->get_drvinfo) { ops->get_drvinfo(dev, &rsp->info); - } else if (dev->dev.parent && dev->dev.parent->driver) { - strscpy(rsp->info.bus_info, dev_name(dev->dev.parent), + if (!rsp->info.bus_info[0] && parent) + strscpy(rsp->info.bus_info, dev_name(parent), + sizeof(rsp->info.bus_info)); + if (!rsp->info.driver[0] && parent && parent->driver) + strscpy(rsp->info.driver, parent->driver->name, + sizeof(rsp->info.driver)); + } else if (parent && parent->driver) { + strscpy(rsp->info.bus_info, dev_name(parent), sizeof(rsp->info.bus_info)); - strscpy(rsp->info.driver, dev->dev.parent->driver->name, + strscpy(rsp->info.driver, parent->driver->name, sizeof(rsp->info.driver)); } else if (dev->rtnl_link_ops) { strscpy(rsp->info.driver, dev->rtnl_link_ops->kind, @@ -1796,7 +1796,8 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, { struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS }; u16 from_channel, to_channel; - u32 max_rx_in_use = 0; + u64 max_rxnfc_in_use; + u32 max_rxfh_in_use; unsigned int i; int ret; @@ -1827,11 +1828,15 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, return -EINVAL; /* ensure the new Rx count fits within the configured Rx flow - * indirection table settings */ - if (netif_is_rxfh_configured(dev) && - !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && - (channels.combined_count + channels.rx_count) <= max_rx_in_use) - return -EINVAL; + * indirection table/rxnfc settings */ + if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) + max_rxnfc_in_use = 0; + if (!netif_is_rxfh_configured(dev) || + ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use)) + max_rxfh_in_use = 0; + if (channels.combined_count + channels.rx_count <= + max_t(u64, max_rxnfc_in_use, max_rxfh_in_use)) + return -EINVAL; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + @@ -2008,7 +2013,8 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) } else { /* Driver expects to be called at twice the frequency in rc */ int n = rc * 2, interval = HZ / n; - u64 count = n * id.data, i = 0; + u64 count = mul_u32_u32(n, id.data); + u64 i = 0; do { rtnl_lock(); diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index fb676f349455..2158c17a0b32 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -13,6 +13,7 @@ struct linkstate_reply_data { int link; int sqi; int sqi_max; + struct ethtool_link_ext_stats link_stats; bool link_ext_state_provided; struct ethtool_link_ext_state_info ethtool_link_ext_state_info; }; @@ -22,7 +23,7 @@ struct linkstate_reply_data { const struct nla_policy ethnl_linkstate_get_policy[] = { [ETHTOOL_A_LINKSTATE_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int linkstate_get_sqi(struct net_device *dev) @@ -107,6 +108,19 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, goto out; } + ethtool_stats_init((u64 *)&data->link_stats, + sizeof(data->link_stats) / 8); + + if (req_base->flags & ETHTOOL_FLAG_STATS) { + if (dev->phydev) + data->link_stats.link_down_events = + READ_ONCE(dev->phydev->link_down_events); + + if (dev->ethtool_ops->get_link_ext_stats) + dev->ethtool_ops->get_link_ext_stats(dev, + &data->link_stats); + } + ret = 0; out: ethnl_ops_complete(dev); @@ -134,6 +148,9 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, if (data->ethtool_link_ext_state_info.__link_ext_substate) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */ + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + len += nla_total_size(sizeof(u32)); + return len; } @@ -166,6 +183,11 @@ static int linkstate_fill_reply(struct sk_buff *skb, return -EMSGSIZE; } + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, + data->link_stats.link_down_events)) + return -EMSGSIZE; + return 0; } diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index 5a471e115b66..e8683e485dc9 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -64,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; - ret = pse_get_pse_attributes(dev, info->extack, data); + ret = pse_get_pse_attributes(dev, info ? info->extack : NULL, data); ethnl_ops_complete(dev); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 5bf357734b11..56bb27d67a2e 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -150,15 +150,15 @@ struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port) { if (!frame->skb_std) { - if (frame->skb_hsr) { + if (frame->skb_hsr) frame->skb_std = create_stripped_skb_hsr(frame->skb_hsr, frame); - } else { - /* Unexpected */ - WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", - __FILE__, __LINE__, port->dev->name); + else + netdev_warn_once(port->dev, + "Unexpected frame received in hsr_get_untagged_frame()\n"); + + if (!frame->skb_std) return NULL; - } } return skb_clone(frame->skb_std, GFP_ATOMIC); @@ -351,17 +351,18 @@ static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev, struct hsr_node *node_src) { bool was_multicast_frame; - int res; + int res, recv_len; was_multicast_frame = (skb->pkt_type == PACKET_MULTICAST); hsr_addr_subst_source(node_src, skb); skb_pull(skb, ETH_HLEN); + recv_len = skb->len; res = netif_rx(skb); if (res == NET_RX_DROP) { dev->stats.rx_dropped++; } else { dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->stats.rx_bytes += recv_len; if (was_multicast_frame) dev->stats.multicast++; } diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index de259b5170ab..57546e07e06a 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -129,6 +129,9 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) wpan_phy_net_set(&rdev->wpan_phy, &init_net); init_waitqueue_head(&rdev->dev_wait); + init_waitqueue_head(&rdev->wpan_phy.sync_txq); + + spin_lock_init(&rdev->wpan_phy.queue_lock); return &rdev->wpan_phy; } diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 38c4f3cb010e..b33d1b5eda87 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -2157,7 +2157,8 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, #define NL802154_FLAG_CHECK_NETDEV_UP 0x08 #define NL802154_FLAG_NEED_WPAN_DEV 0x10 -static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int nl802154_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev; @@ -2219,7 +2220,8 @@ static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, return 0; } -static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void nl802154_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { if (info->user_ptr[1]) { diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 6e55fae4c686..1fa2fe041ec0 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -502,8 +502,10 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) if (err < 0) goto out; - if (addr->family != AF_IEEE802154) + if (addr->family != AF_IEEE802154) { + err = -EINVAL; goto out; + } ieee802154_addr_from_sa(&haddr, &addr->addr); dev = ieee802154_get_dev(sock_net(sk), &haddr); diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index e983bb0c5012..2dfb12230f08 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -402,6 +402,16 @@ config INET_IPCOMP If unsure, say Y. +config INET_TABLE_PERTURB_ORDER + int "INET: Source port perturbation table size (as power of 2)" if EXPERT + default 16 + help + Source port perturbation table size (as power of 2) for + RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm. + + The default is almost always what you want. + Only change this if you know what you are doing. + config INET_XFRM_TUNNEL tristate select INET_TUNNEL diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index bbdd9c44f14e..af7d2cf490fb 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -10,7 +10,7 @@ obj-y := route.o inetpeer.o protocol.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ tcp_rate.o tcp_recovery.o tcp_ulp.o \ - tcp_offload.o datagram.o raw.o udp.o udplite.o \ + tcp_offload.o tcp_plb.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3dd02396517d..ab4a06be489b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -522,9 +522,9 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { - if (sk->sk_prot->get_port(sk, snum)) { + err = sk->sk_prot->get_port(sk, snum); + if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; - err = -EADDRINUSE; goto out_release_sock; } if (!(flags & BIND_FROM_BPF)) { @@ -754,6 +754,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags, (TCPF_ESTABLISHED | TCPF_SYN_RECV | TCPF_CLOSE_WAIT | TCPF_CLOSE))); + if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) + set_bit(SOCK_SUPPORT_ZC, &newsock->flags); sock_graft(sk2, newsock); newsock->state = SS_CONNECTED; @@ -1228,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { - struct inet_bind_hashbucket *prev_addr_hashbucket; struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; @@ -1258,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; } - prev_addr_hashbucket = - inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk, - sock_net(sk), inet->inet_num); - - inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; - - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { - inet->inet_saddr = old_saddr; - inet->inet_rcv_saddr = old_saddr; ip_rt_put(rt); return err; } @@ -1706,9 +1699,9 @@ u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, bhptr = per_cpu_ptr(mib, cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { - start = u64_stats_fetch_begin_irq(syncp); + start = u64_stats_fetch_begin(syncp); v = *(((u64 *)bhptr) + offt); - } while (u64_stats_fetch_retry_irq(syncp, start)); + } while (u64_stats_fetch_retry(syncp, start)); return v; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 6da16ae6a962..4517d2bd186a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -61,7 +61,9 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; - if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) + if (base_type(info->reg_type) == PTR_TO_BTF_ID && + !bpf_type_has_unsafe_modifiers(info->reg_type) && + info->btf_id == sock_id) /* promote it to tcp_sock */ info->btf_id = tcp_sock_id; @@ -69,18 +71,17 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, } static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { + const struct btf_type *t; size_t end; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); + t = btf_type_by_id(reg->btf, reg->btf_id); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); return -EACCES; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 405a8c2aea64..4d1af0cd7d99 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -70,10 +70,10 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = prandom_u32(); + inet->inet_id = get_random_u16(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 170152772d33..3969fa805679 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); ip_hdr(skb)->tot_len = htons(skb->len); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 943edf4ad4db..f361d3d56be2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { - ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) @@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) - ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e9a7f70a54df..19a662003eef 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -888,9 +888,11 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, return 1; } - /* cannot match on nexthop object attributes */ - if (fi->nh) - return 1; + if (fi->nh) { + if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp) + return 1; + return 0; + } if (cfg->fc_oif || cfg->fc_gw_family) { struct fib_nh *nh; @@ -1231,7 +1233,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, nh->fib_nh_dev = in_dev->dev; netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); - nh->fib_nh_scope = RT_SCOPE_LINK; + nh->fib_nh_scope = RT_SCOPE_HOST; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = 0; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 452ff177e4da..74d403dbd2b4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -126,7 +126,7 @@ struct key_vector { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ - struct key_vector __rcu *tnode[0]; + DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; @@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index df0660d818ac..81be3e0f0e70 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -213,7 +213,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv = prandom_u32() % max_delay; + int tv = prandom_u32_max(max_delay); im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) @@ -222,7 +222,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) static void igmp_gq_start_timer(struct in_device *in_dev) { - int tv = prandom_u32() % in_dev->mr_maxdelay; + int tv = prandom_u32_max(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && @@ -236,7 +236,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev) static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = prandom_u32() % delay; + int tv = prandom_u32_max(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ebca860e113f..4a34bc7cb15e 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -314,7 +314,7 @@ other_half_scan: if (likely(remaining > 1)) remaining &= ~1U; - offset = prandom_u32() % remaining; + offset = prandom_u32_max(remaining); /* __inet_hash_connect() favors ports having @low parity * We do the opposite to not pollute connect() users. */ @@ -471,11 +471,11 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; + int ret = -EADDRINUSE, port = snum, l3mdev; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; struct inet_bind_bucket *tb = NULL; bool head2_lock_acquired = false; - int ret = 1, port = snum, l3mdev; struct net *net = sock_net(sk); l3mdev = inet_sk_bound_l3mdev(sk); @@ -1186,7 +1186,7 @@ int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - int err = -EADDRINUSE; + int err; reqsk_queue_alloc(&icsk->icsk_accept_queue); @@ -1202,7 +1202,8 @@ int inet_csk_listen_start(struct sock *sk) * after validation is complete. */ inet_sk_state_store(sk, TCP_LISTEN); - if (!sk->sk_prot->get_port(sk, inet->inet_num)) { + err = sk->sk_prot->get_port(sk, inet->inet_num); + if (!err) { inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9f9ac5013a7..7072fc0783ef 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -133,6 +133,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) count = del_timer_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); + fq->flags |= INET_FRAG_DROP; if (!(fq->flags & INET_FRAG_COMPLETE)) { fq->flags |= INET_FRAG_COMPLETE; count++; @@ -260,7 +261,8 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } -unsigned int inet_frag_rbtree_purge(struct rb_root *root) +unsigned int inet_frag_rbtree_purge(struct rb_root *root, + enum skb_drop_reason reason) { struct rb_node *p = rb_first(root); unsigned int sum = 0; @@ -274,7 +276,7 @@ unsigned int inet_frag_rbtree_purge(struct rb_root *root) struct sk_buff *next = FRAG_CB(skb)->next_frag; sum += skb->truesize; - kfree_skb(skb); + kfree_skb_reason(skb, reason); skb = next; } } @@ -284,17 +286,21 @@ EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { - struct fqdir *fqdir; unsigned int sum, sum_truesize = 0; + enum skb_drop_reason reason; struct inet_frags *f; + struct fqdir *fqdir; WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); + reason = (q->flags & INET_FRAG_DROP) ? + SKB_DROP_REASON_FRAG_REASM_TIMEOUT : + SKB_CONSUMED; WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ fqdir = q->fqdir; f = fqdir->f; - sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments); + sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments, reason); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index a0ad34e4f044..3cec471a2cd2 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk) +static void inet_update_saddr(struct sock *sk, void *saddr, int family) +{ + if (family == AF_INET) { + inet_sk(sk)->inet_saddr = *(__be32 *)saddr; + sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr); + } +#if IS_ENABLED(CONFIG_IPV6) + else { + sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr; + } +#endif +} + +static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); - struct inet_bind_hashbucket *head2; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); + int bhash; + + if (!inet_csk(sk)->icsk_bind2_hash) { + /* Not bind()ed before. */ + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + return 0; + } /* Allocate a bind2 bucket ahead of time to avoid permanently putting * the bhash2 table in an inconsistent state if a new tb2 bucket * allocation fails. */ new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC); - if (!new_tb2) + if (!new_tb2) { + if (reset) { + /* The (INADDR_ANY, port) bucket might have already + * been freed, then we cannot fixup icsk_bind2_hash, + * so we give up and unlink sk from bhash/bhash2 not + * to leave inconsistency in bhash2. + */ + inet_put_port(sk); + inet_reset_saddr(sk); + } + return -ENOMEM; + } + bhash = inet_bhashfn(net, port, hinfo->bhash_size); + head = &hinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); - if (prev_saddr) { - spin_lock_bh(&prev_saddr->lock); - __sk_del_bind2_node(sk); - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - inet_csk(sk)->icsk_bind2_hash); - spin_unlock_bh(&prev_saddr->lock); - } + /* If we change saddr locklessly, another thread + * iterating over bhash might see corrupted address. + */ + spin_lock_bh(&head->lock); - spin_lock_bh(&head2->lock); + spin_lock(&head2->lock); + __sk_del_bind2_node(sk); + inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); + spin_unlock(&head2->lock); + + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); + + spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; @@ -893,26 +939,40 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc } sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; - spin_unlock_bh(&head2->lock); + spin_unlock(&head2->lock); + + spin_unlock_bh(&head->lock); if (tb2 != new_tb2) kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2); return 0; } + +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) +{ + return __inet_bhash2_update_saddr(sk, saddr, family, false); +} EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); +void inet_bhash2_reset_saddr(struct sock *sk) +{ + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + __inet_bhash2_update_saddr(sk, NULL, 0, true); +} +EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); + /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this * property might be used by clever attacker. + * * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though - * attacks were since demonstrated, thus we use 65536 instead to really - * give more isolation and privacy, at the expense of 256kB of kernel - * memory. + * attacks were since demonstrated, thus we use 65536 by default instead + * to really give more isolation and privacy, at the expense of 256kB + * of kernel memory. */ -#define INET_TABLE_PERTURB_SHIFT 16 -#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT) +#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER) static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, @@ -1037,7 +1097,7 @@ ok: * on low contention the randomness is maximal and on high contention * it may be inexistent. */ - i = max_t(int, i, (prandom_u32() & 7) * 2); + i = max_t(int, i, prandom_u32_max(8) * 2); WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fb153569889e..69c00ffdcf3e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -153,6 +153,7 @@ static void ip_expire(struct timer_list *t) if (qp->q.flags & INET_FRAG_COMPLETE) goto out; + qp->q.flags |= INET_FRAG_DROP; ipq_kill(qp); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); @@ -194,7 +195,7 @@ out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); - kfree_skb(head); + kfree_skb_reason(head, SKB_DROP_REASON_FRAG_REASM_TIMEOUT); ipq_put(qp); } @@ -254,7 +255,8 @@ static int ip_frag_reinit(struct ipq *qp) return -ETIMEDOUT; } - sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments); + sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, + SKB_DROP_REASON_FRAG_TOO_FAR); sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; @@ -278,10 +280,14 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) struct net_device *dev; unsigned int fragsize; int err = -ENOENT; + SKB_DR(reason); u8 ecn; - if (qp->q.flags & INET_FRAG_COMPLETE) + /* If reassembly is already done, @skb must be a duplicate frag. */ + if (qp->q.flags & INET_FRAG_COMPLETE) { + SKB_DR_SET(reason, DUP_FRAG); goto err; + } if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && unlikely(ip_frag_too_far(qp)) && @@ -382,8 +388,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) insert_error: if (err == IPFRAG_DUP) { - kfree_skb(skb); - return -EINVAL; + SKB_DR_SET(reason, DUP_FRAG); + err = -EINVAL; + goto err; } err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); @@ -391,7 +398,7 @@ discard_qp: inet_frag_kill(&qp->q); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return err; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f866d6282b2b..a4ccef3e6935 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -510,7 +510,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, err_free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) @@ -592,7 +592,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) err_free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) @@ -663,7 +663,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -717,7 +717,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -745,7 +745,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, free_skb: kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -1665,7 +1665,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, if (err) goto out; - err = rtnl_configure_link(dev, NULL); + err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto out; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1b512390b3cf..e880ce77322a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, iph->tos, dev); if (unlikely(err)) goto drop_error; + } else { + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY)) + IPCB(skb)->flags |= IPSKB_NOPOLICY; } #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1ae83ad629b2..922c87ef1ab5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -172,7 +172,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, * Avoid using the hashed IP ident generator. */ if (sk->sk_protocol == IPPROTO_TCP) - iph->id = (__force __be16)prandom_u32(); + iph->id = (__force __be16)get_random_u16(); else __ip_select_ident(net, iph, 1); } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6e19cad154f5..9f92ae35bb01 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -267,7 +267,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, } #endif if (cmsg->cmsg_level == SOL_SOCKET) { - err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc); + err = __sock_cmsg_send(sk, cmsg, &ipc->sockc); if (err) return err; continue; @@ -433,6 +433,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, } kfree_skb(skb); } +EXPORT_SYMBOL_GPL(ip_icmp_error); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 019f3b0839c5..de90b09dfe78 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -368,23 +368,23 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { - tunnel->dev->stats.multicast++; + DEV_STATS_INC(tunnel->dev, multicast); skb->pkt_type = PACKET_BROADCAST; } #endif if ((!(tpi->flags&TUNNEL_CSUM) && (tunnel->parms.i_flags&TUNNEL_CSUM)) || ((tpi->flags&TUNNEL_CSUM) && !(tunnel->parms.i_flags&TUNNEL_CSUM))) { - tunnel->dev->stats.rx_crc_errors++; - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_crc_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (tunnel->parms.i_flags&TUNNEL_SEQ) { if (!(tpi->flags&TUNNEL_SEQ) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { - tunnel->dev->stats.rx_fifo_errors++; - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_fifo_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; @@ -398,8 +398,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { - ++tunnel->dev->stats.rx_frame_errors; - ++tunnel->dev->stats.rx_errors; + DEV_STATS_INC(tunnel->dev, rx_frame_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } @@ -581,7 +581,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) @@ -590,7 +590,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } if (rt->dst.dev == dev) { ip_rt_put(rt); - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); goto tx_error; } @@ -625,10 +625,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, df, !net_eq(tunnel->net, dev_net(dev))); return; tx_error: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); goto kfree; tx_dropped: - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); kfree: kfree_skb(skb); } @@ -662,7 +662,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, /* NBMA tunnel */ if (!skb_dst(skb)) { - dev->stats.tx_fifo_errors++; + DEV_STATS_INC(dev, tx_fifo_errors); goto tx_error; } @@ -749,7 +749,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, rt = ip_route_output_key(tunnel->net, &fl4); if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error; } if (use_cache) @@ -762,7 +762,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (rt->dst.dev == dev) { ip_rt_put(rt); - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); goto tx_error; } @@ -805,7 +805,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (skb_cow_head(skb, dev->needed_headroom)) { ip_rt_put(rt); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return; } @@ -819,7 +819,7 @@ tx_error_icmp: dst_link_failure(skb); #endif tx_error: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_tunnel_xmit); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 8c2bd1d9ddce..53bfd8af6920 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -107,8 +107,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err) dev = tunnel->dev; if (err) { - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_dropped); return 0; } @@ -183,7 +183,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } dst = &rt->dst; @@ -198,14 +198,14 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (dst->error) { dst_release(dst); dst = NULL; - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } skb_dst_set(skb, dst); break; #endif default: - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } } @@ -213,7 +213,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, dst_hold(dst); dst = xfrm_lookup_route(tunnel->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } @@ -221,7 +221,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto xmit; if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_release(dst); goto tx_error_icmp; } @@ -230,7 +230,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (tdev == dev) { dst_release(dst); - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); goto tx_error; } @@ -267,7 +267,7 @@ xmit: tx_error_icmp: dst_link_failure(skb); tx_error: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } @@ -304,7 +304,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) return vti_xmit(skb, dev, &fl); tx_err: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 180f9daf5bec..abea77759b7e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -310,7 +310,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, tx_error: kfree_skb(skb); - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e04544ac4b45..b58df3c1bf7d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -506,8 +506,8 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) return err; } - dev->stats.tx_bytes += skb->len; - dev->stats.tx_packets++; + DEV_STATS_ADD(dev, tx_bytes, skb->len); + DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ @@ -1839,8 +1839,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (vif->flags & VIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); - vif_dev->stats.tx_bytes += skb->len; - vif_dev->stats.tx_packets++; + DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); + DEV_STATS_INC(vif_dev, tx_packets); ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } @@ -1898,8 +1898,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (vif->flags & VIFF_TUNNEL) { ip_encap(net, skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ - vif_dev->stats.tx_packets++; - vif_dev->stats.tx_bytes += skb->len; + DEV_STATS_INC(vif_dev, tx_packets); + DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); } IPCB(skb)->flags |= IPSKB_FORWARDED; diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 25ea6ac44db9..7fcfdfd8f9de 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -14,9 +14,6 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, struct nlattr *nla; int remaining; - if (!fc_mx) - return 0; - nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) { int type = nla_type(nla); u32 val; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index f8e176c77d1c..b3cc416ed292 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) switch (ctinfo) { case IP_CT_NEW: - ct->mark = hash; + WRITE_ONCE(ct->mark, hash); break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: @@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) #ifdef DEBUG nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); if (!clusterip_responsible(cipinfo->config, hash)) { pr_debug("not responsible\n"); return NF_DROP; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index ff85db52b2e5..ded5bef02f77 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); + flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index 0bcd6aee6000..a522c3a3be52 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -52,7 +52,8 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, return err; } -static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dup_ipv4_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index e886147eed11..9eee535c64dd 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -65,6 +65,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi4 fl4 = { .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_uid = sock_net_uid(nft_net(pkt), NULL), }; const struct net_device *oif; const struct net_device *found; @@ -137,12 +138,11 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, break; } - if (!oif) { - found = FIB_RES_DEV(res); + if (!oif) { + found = FIB_RES_DEV(res); } else { if (!fib_info_nh_uses_dev(res.fi, oif)) return; - found = oif; } diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 853a75a8fbaf..d8ef05347fd9 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2534,7 +2534,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, - fib_nh->fib_nh_scope); + !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1); } else { fib_nh_release(net, fib_nh); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index bde333b24837..bb9854c2b7a1 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -138,7 +138,7 @@ next_port: fail: spin_unlock(&ping_table.lock); - return 1; + return -EADDRINUSE; } EXPORT_SYMBOL_GPL(ping_get_port); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5386f460bd20..f88daace9de3 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -297,6 +297,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), + SNMP_MIB_ITEM("TCPPLBRehash", LINUX_MIB_TCPPLBREHASH), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 795cbe1de912..cd1fa9f70f1a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3664,7 +3664,7 @@ static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); - atomic_set(&net->ipv4.dev_addr_genid, get_random_int()); + atomic_set(&net->ipv4.dev_addr_genid, get_random_u32()); return 0; } @@ -3719,7 +3719,7 @@ int __init ip_rt_init(void) ip_idents = idents_hash; - prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); + get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 9b8a6db7a66b..0d0cc4ef2b85 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -40,6 +40,9 @@ static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; +static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; +static int tcp_plb_max_rounds = 31; +static int tcp_plb_max_cong_thresh = 256; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -400,12 +403,36 @@ static int proc_tcp_ehash_entries(struct ctl_table *table, int write, if (!net_eq(net, &init_net) && !hinfo->pernet) tcp_ehash_entries *= -1; + memset(&tbl, 0, sizeof(tbl)); tbl.data = &tcp_ehash_entries; tbl.maxlen = sizeof(int); return proc_dointvec(&tbl, write, buffer, lenp, ppos); } +static int proc_udp_hash_entries(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_udp_child_hash_entries); + int udp_hash_entries; + struct ctl_table tbl; + + udp_hash_entries = net->ipv4.udp_table->mask + 1; + + /* A negative number indicates that the child netns + * shares the global udp_table. + */ + if (!net_eq(net, &init_net) && net->ipv4.udp_table == &udp_table) + udp_hash_entries *= -1; + + memset(&tbl, 0, sizeof(tbl)); + tbl.data = &udp_hash_entries; + tbl.maxlen = sizeof(int); + + return proc_dointvec(&tbl, write, buffer, lenp, ppos); +} + #ifdef CONFIG_IP_ROUTE_MULTIPATH static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, @@ -1360,6 +1387,21 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &tcp_child_ehash_entries_max, }, { + .procname = "udp_hash_entries", + .data = &init_net.ipv4.sysctl_udp_child_hash_entries, + .mode = 0444, + .proc_handler = proc_udp_hash_entries, + }, + { + .procname = "udp_child_hash_entries", + .data = &init_net.ipv4.sysctl_udp_child_hash_entries, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &udp_child_hash_entries_max, + }, + { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), @@ -1384,6 +1426,47 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, + { + .procname = "tcp_plb_enabled", + .data = &init_net.ipv4.sysctl_tcp_plb_enabled, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "tcp_plb_idle_rehash_rounds", + .data = &init_net.ipv4.sysctl_tcp_plb_idle_rehash_rounds, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra2 = &tcp_plb_max_rounds, + }, + { + .procname = "tcp_plb_rehash_rounds", + .data = &init_net.ipv4.sysctl_tcp_plb_rehash_rounds, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra2 = &tcp_plb_max_rounds, + }, + { + .procname = "tcp_plb_suspend_rto_sec", + .data = &init_net.ipv4.sysctl_tcp_plb_suspend_rto_sec, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + }, + { + .procname = "tcp_plb_cong_thresh", + .data = &init_net.ipv4.sysctl_tcp_plb_cong_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_plb_max_cong_thresh, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f8232811a5be..24602a5184b0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk) WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); } EXPORT_SYMBOL(tcp_init_sock); @@ -3113,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); @@ -3175,6 +3175,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; + tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rack.mstamp = 0; @@ -3646,7 +3647,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; - else if (sk->sk_state == TCP_ESTABLISHED) + else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; @@ -3938,6 +3939,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; + info->tcpi_rcv_wnd = tp->rcv_wnd; + info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } @@ -3972,6 +3975,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } @@ -4048,6 +4052,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); + nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); return stats; } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index a1626afe87a1..cf9c3e8f7ccb 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, { bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; - u32 tosend, delta = 0; + u32 tosend, origsize, sent, delta = 0; u32 eval = __SK_NONE; int ret; @@ -333,10 +333,12 @@ more_data: cork = true; psock->cork = NULL; } - sk_msg_return(sk, msg, msg->sg.size); + sk_msg_return(sk, msg, tosend); release_sock(sk); + origsize = msg->sg.size; ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) sock_put(sk_redir); @@ -375,7 +377,7 @@ more_data: msg->sg.data[msg->sg.start].page_link && msg->sg.data[msg->sg.start].length) { if (eval == __SK_REDIRECT) - sk_mem_charge(sk, msg->sg.size); + sk_mem_charge(sk, tosend - sent); goto more_data; } } @@ -607,7 +609,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) } else { sk->sk_write_space = psock->saved_write_space; /* Pairs with lockless read in sk_clone_lock() */ - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); } return 0; } @@ -620,7 +622,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) } /* Pairs with lockless read in sk_clone_lock() */ - WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]); + sock_replace_proto(sk, &tcp_bpf_prots[family][config]); return 0; } EXPORT_SYMBOL_GPL(tcp_bpf_update_proto); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 112f28f93693..ba4d98e510e0 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -243,7 +243,7 @@ static bool tcp_cdg_backoff(struct sock *sk, u32 grad) struct cdg *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - if (prandom_u32() <= nexp_u32(grad * backoff_factor)) + if (get_random_u32() <= nexp_u32(grad * backoff_factor)) return false; if (use_ineff) { diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 2a6c0dd665a4..e0a2ca7456ff 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -54,6 +54,7 @@ struct dctcp { u32 next_seq; u32 ce_state; u32 loss_cwnd; + struct tcp_plb_state plb; }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ @@ -91,6 +92,8 @@ static void dctcp_init(struct sock *sk) ca->ce_state = 0; dctcp_reset(tp, ca); + tcp_plb_init(sk, &ca->plb); + return; } @@ -117,14 +120,28 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) /* Expired RTT */ if (!before(tp->snd_una, ca->next_seq)) { + u32 delivered = tp->delivered - ca->old_delivered; u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; u32 alpha = ca->dctcp_alpha; + u32 ce_ratio = 0; + + if (delivered > 0) { + /* dctcp_alpha keeps EWMA of fraction of ECN marked + * packets. Because of EWMA smoothing, PLB reaction can + * be slow so we use ce_ratio which is an instantaneous + * measure of congestion. ce_ratio is the fraction of + * ECN marked packets in the previous RTT. + */ + if (delivered_ce > 0) + ce_ratio = (delivered_ce << TCP_PLB_SCALE) / delivered; + tcp_plb_update_state(sk, &ca->plb, (int)ce_ratio); + tcp_plb_check_rehash(sk, &ca->plb); + } /* alpha = (1 - g) * alpha + g * F */ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); if (delivered_ce) { - u32 delivered = tp->delivered - ca->old_delivered; /* If dctcp_shift_g == 1, a 32bit value would overflow * after 8 M packets. @@ -172,8 +189,12 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); break; case CA_EVENT_LOSS: + tcp_plb_update_state_upon_rto(sk, &ca->plb); dctcp_react_to_loss(sk); break; + case CA_EVENT_TX_START: + tcp_plb_check_rehash(sk, &ca->plb); /* Maybe rehash when inflight is 0 */ + break; default: /* Don't care for the rest. */ break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bc2ea12221f9..1efacbe948da 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2192,7 +2192,8 @@ void tcp_enter_loss(struct sock *sk) */ static bool tcp_check_sack_reneging(struct sock *sk, int flag) { - if (flag & FLAG_SACK_RENEGING) { + if (flag & FLAG_SACK_RENEGING && + flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); @@ -4763,8 +4764,8 @@ static void tcp_ofo_queue(struct sock *sk) } } -static bool tcp_prune_ofo_queue(struct sock *sk); -static int tcp_prune_queue(struct sock *sk); +static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb); +static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb); static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size) @@ -4772,11 +4773,11 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, size)) { - if (tcp_prune_queue(sk) < 0) + if (tcp_prune_queue(sk, skb) < 0) return -1; while (!sk_rmem_schedule(sk, skb, size)) { - if (!tcp_prune_ofo_queue(sk)) + if (!tcp_prune_ofo_queue(sk, skb)) return -1; } } @@ -5328,6 +5329,8 @@ new_range: * Clean the out-of-order queue to make room. * We drop high sequences packets to : * 1) Let a chance for holes to be filled. + * This means we do not drop packets from ooo queue if their sequence + * is before incoming packet sequence. * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) @@ -5335,24 +5338,31 @@ new_range: * * Return true if queue has shrunk. */ -static bool tcp_prune_ofo_queue(struct sock *sk) +static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + bool pruned = false; int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; - NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; + do { + struct sk_buff *skb = rb_to_skb(node); + + /* If incoming skb would land last in ofo queue, stop pruning. */ + if (after(TCP_SKB_CB(in_skb)->seq, TCP_SKB_CB(skb)->seq)) + break; + pruned = true; prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); - goal -= rb_to_skb(node)->truesize; - tcp_drop_reason(sk, rb_to_skb(node), - SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE); + goal -= skb->truesize; + tcp_drop_reason(sk, skb, SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE); + tp->ooo_last_skb = rb_to_skb(prev); if (!prev || goal <= 0) { if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) @@ -5361,16 +5371,18 @@ static bool tcp_prune_ofo_queue(struct sock *sk) } node = prev; } while (node); - tp->ooo_last_skb = rb_to_skb(prev); - /* Reset SACK state. A conforming SACK implementation will - * do the same at a timeout based retransmit. When a connection - * is in a sad state like this, we care only about integrity - * of the connection not performance. - */ - if (tp->rx_opt.sack_ok) - tcp_sack_reset(&tp->rx_opt); - return true; + if (pruned) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + /* Reset SACK state. A conforming SACK implementation will + * do the same at a timeout based retransmit. When a connection + * is in a sad state like this, we care only about integrity + * of the connection not performance. + */ + if (tp->rx_opt.sack_ok) + tcp_sack_reset(&tp->rx_opt); + } + return pruned; } /* Reduce allocated memory if we can, trying to get @@ -5380,7 +5392,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk) * until the socket owning process reads some of the data * to stabilize the situation. */ -static int tcp_prune_queue(struct sock *sk) +static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -5407,7 +5419,7 @@ static int tcp_prune_queue(struct sock *sk) /* Collapsing did not help, destructive actions follow. * This must not ever occur. */ - tcp_prune_ofo_queue(sk); + tcp_prune_ofo_queue(sk, in_skb); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) return 0; @@ -6829,10 +6841,18 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) #endif __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - if (!queue->synflood_warned && syncookies != 2 && - xchg(&queue->synflood_warned, 1) == 0) - net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, sk->sk_num, msg); + if (!READ_ONCE(queue->synflood_warned) && syncookies != 2 && + xchg(&queue->synflood_warned, 1) == 0) { + if (IS_ENABLED(CONFIG_IPV6) && sk->sk_family == AF_INET6) { + net_info_ratelimited("%s: Possible SYN flooding on port [%pI6c]:%u. %s.\n", + proto, inet6_rcv_saddr(sk), + sk->sk_num, msg); + } else { + net_info_ratelimited("%s: Possible SYN flooding on port %pI4:%u. %s.\n", + proto, &sk->sk_rcv_saddr, + sk->sk_num, msg); + } + } return want_cookie; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6376ad915765..1215fa4c1b9f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { @@ -323,7 +311,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr); } - inet->inet_id = prandom_u32(); + inet->inet_id = get_random_u16(); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -343,6 +331,7 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; @@ -1543,7 +1532,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = prandom_u32(); + newinet->inet_id = get_random_u16(); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). @@ -1874,11 +1863,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, __skb_push(skb, hdrlen); no_coalesce: + limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1); + /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ - limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf) + 64*1024; + limit += 64 * 1024; if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); @@ -2478,7 +2469,6 @@ static void *tcp_seek_last_pos(struct seq_file *seq) case TCP_SEQ_STATE_LISTENING: if (st->bucket > hinfo->lhash2_mask) break; - st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); @@ -3216,6 +3206,14 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); + /* Set default values for PLB */ + net->ipv4.sysctl_tcp_plb_enabled = 0; /* Disabled by default */ + net->ipv4.sysctl_tcp_plb_idle_rehash_rounds = 3; + net->ipv4.sysctl_tcp_plb_rehash_rounds = 12; + net->ipv4.sysctl_tcp_plb_suspend_rto_sec = 60; + /* Default congestion threshold for PLB to mark a round is 50% */ + net->ipv4.sysctl_tcp_plb_cong_thresh = (1 << TCP_PLB_SCALE) / 2; + /* Reno is always built in */ if (!net_eq(net, &init_net) && bpf_try_module_get(init_net.ipv4.tcp_congestion_control, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c69f4d966024..894410dc9293 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1077,15 +1077,15 @@ static void tcp_tasklet_func(struct tasklet_struct *t) */ void tcp_release_cb(struct sock *sk) { - unsigned long flags, nflags; + unsigned long flags = smp_load_acquire(&sk->sk_tsq_flags); + unsigned long nflags; /* perform an atomic operation only if at least one flag is set */ do { - flags = sk->sk_tsq_flags; if (!(flags & TCP_DEFERRED_ALL)) return; nflags = flags & ~TCP_DEFERRED_ALL; - } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); + } while (!try_cmpxchg(&sk->sk_tsq_flags, &flags, nflags)); if (flags & TCPF_TSQ_DEFERRED) { tcp_tsq_write(sk); @@ -1139,6 +1139,8 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; + struct tsq_tasklet *tsq; + bool empty; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() @@ -1155,28 +1157,23 @@ void tcp_wfree(struct sk_buff *skb) if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; - for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { - struct tsq_tasklet *tsq; - bool empty; - + oval = smp_load_acquire(&sk->sk_tsq_flags); + do { if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; - nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); - if (nval != oval) - continue; + } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval)); - /* queue this socket to tasklet queue */ - local_irq_save(flags); - tsq = this_cpu_ptr(&tsq_tasklet); - empty = list_empty(&tsq->head); - list_add(&tp->tsq_node, &tsq->head); - if (empty) - tasklet_schedule(&tsq->tasklet); - local_irq_restore(flags); - return; - } + /* queue this socket to tasklet queue */ + local_irq_save(flags); + tsq = this_cpu_ptr(&tsq_tasklet); + empty = list_empty(&tsq->head); + list_add(&tp->tsq_node, &tsq->head); + if (empty) + tasklet_schedule(&tsq->tasklet); + local_irq_restore(flags); + return; out: sk_free(sk); } diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c new file mode 100644 index 000000000000..bb1a08fda113 --- /dev/null +++ b/net/ipv4/tcp_plb.c @@ -0,0 +1,109 @@ +/* Protective Load Balancing (PLB) + * + * PLB was designed to reduce link load imbalance across datacenter + * switches. PLB is a host-based optimization; it leverages congestion + * signals from the transport layer to randomly change the path of the + * connection experiencing sustained congestion. PLB prefers to repath + * after idle periods to minimize packet reordering. It repaths by + * changing the IPv6 Flow Label on the packets of a connection, which + * datacenter switches include as part of ECMP/WCMP hashing. + * + * PLB is described in detail in: + * + * Mubashir Adnan Qureshi, Yuchung Cheng, Qianwen Yin, Qiaobin Fu, + * Gautam Kumar, Masoud Moshref, Junhua Yan, Van Jacobson, + * David Wetherall,Abdul Kabbani: + * "PLB: Congestion Signals are Simple and Effective for + * Network Load Balancing" + * In ACM SIGCOMM 2022, Amsterdam Netherlands. + * + */ + +#include <net/tcp.h> + +/* Called once per round-trip to update PLB state for a connection. */ +void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, + const int cong_ratio) +{ + struct net *net = sock_net(sk); + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + if (cong_ratio >= 0) { + if (cong_ratio < READ_ONCE(net->ipv4.sysctl_tcp_plb_cong_thresh)) + plb->consec_cong_rounds = 0; + else if (plb->consec_cong_rounds < + READ_ONCE(net->ipv4.sysctl_tcp_plb_rehash_rounds)) + plb->consec_cong_rounds++; + } +} +EXPORT_SYMBOL_GPL(tcp_plb_update_state); + +/* Check whether recent congestion has been persistent enough to warrant + * a load balancing decision that switches the connection to another path. + */ +void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb) +{ + struct net *net = sock_net(sk); + u32 max_suspend; + bool forced_rehash = false, idle_rehash = false; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + forced_rehash = plb->consec_cong_rounds >= + READ_ONCE(net->ipv4.sysctl_tcp_plb_rehash_rounds); + /* If sender goes idle then we check whether to rehash. */ + idle_rehash = READ_ONCE(net->ipv4.sysctl_tcp_plb_idle_rehash_rounds) && + !tcp_sk(sk)->packets_out && + plb->consec_cong_rounds >= + READ_ONCE(net->ipv4.sysctl_tcp_plb_idle_rehash_rounds); + + if (!forced_rehash && !idle_rehash) + return; + + /* Note that tcp_jiffies32 can wrap; we detect wraps by checking for + * cases where the max suspension end is before the actual suspension + * end. We clear pause_until to 0 to indicate there is no recent + * RTO event that constrains PLB rehashing. + */ + max_suspend = 2 * READ_ONCE(net->ipv4.sysctl_tcp_plb_suspend_rto_sec) * HZ; + if (plb->pause_until && + (!before(tcp_jiffies32, plb->pause_until) || + before(tcp_jiffies32 + max_suspend, plb->pause_until))) + plb->pause_until = 0; + + if (plb->pause_until) + return; + + sk_rethink_txhash(sk); + plb->consec_cong_rounds = 0; + tcp_sk(sk)->plb_rehash++; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPLBREHASH); +} +EXPORT_SYMBOL_GPL(tcp_plb_check_rehash); + +/* Upon RTO, disallow load balancing for a while, to avoid having load + * balancing decisions switch traffic to a black-holed path that was + * previously avoided with a sk_rethink_txhash() call at RTO time. + */ +void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb) +{ + struct net *net = sock_net(sk); + u32 pause; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + pause = READ_ONCE(net->ipv4.sysctl_tcp_plb_suspend_rto_sec) * HZ; + pause += prandom_u32_max(pause); + plb->pause_until = tcp_jiffies32 + pause; + + /* Reset PLB state upon RTO, since an RTO causes a sk_rethink_txhash() call + * that may switch this connection to a path with completely different + * congestion characteristics. + */ + plb->consec_cong_rounds = 0; +} +EXPORT_SYMBOL_GPL(tcp_plb_update_state_upon_rto); diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 7c27aa629af1..9ae50b1bd844 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -136,6 +136,9 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops) if (icsk->icsk_ulp_ops) goto out_err; + if (sk->sk_socket) + clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + err = ulp_ops->init(sk); if (err) goto out_err; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8126f67d18b3..9592fe3e444a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -129,7 +129,12 @@ DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); #define MAX_UDP_PORTS 65536 -#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN_PERNET) + +static struct udp_table *udp_get_table_prot(struct sock *sk) +{ + return sk->sk_prot->h.udp_table ? : sock_net(sk)->ipv4.udp_table; +} static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, @@ -232,21 +237,21 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr) { + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; - struct udp_table *udptable = sk->sk_prot->h.udp_table; - int error = 1; struct net *net = sock_net(sk); + int error = -EADDRINUSE; if (!snum) { + DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); + unsigned short first, last; int low, high, remaining; unsigned int rand; - unsigned short first, last; - DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rand = prandom_u32(); + rand = get_random_u32(); first = reciprocal_scale(rand, remaining) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE @@ -448,7 +453,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; @@ -467,7 +472,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, struct sock *sk, *reuse_sk; bool no_reuseport; - if (udptable != &udp_table) + if (udptable != net->ipv4.udp_table) return NULL; /* only UDP is supported */ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, @@ -548,10 +553,11 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); - return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + return __udp4_lib_lookup(net, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), &udp_table, NULL); + inet_sdif(skb), net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). @@ -564,7 +570,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, struct sock *sk; sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, - dif, 0, &udp_table, NULL); + dif, 0, net->ipv4.udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; @@ -784,7 +790,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ if (udp_sk(sk)->encap_err_rcv) - udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, info, + (u8 *)(uh+1)); goto out; } if (!inet->recverr) { @@ -801,7 +808,7 @@ out: int udp_err(struct sk_buff *skb, u32 info) { - return __udp4_lib_err(skb, info, &udp_table); + return __udp4_lib_err(skb, info, dev_net(skb->dev)->ipv4.udp_table); } /* @@ -1448,7 +1455,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2) && + if (size < READ_ONCE(up->forward_threshold) && !skb_queue_empty(&up->reader_queue)) return; } else { @@ -1622,8 +1629,9 @@ static void udp_destruct_sock(struct sock *sk) int udp_init_sock(struct sock *sk) { - skb_queue_head_init(&udp_sk(sk)->reader_queue); + udp_lib_init_sock(sk); sk->sk_destruct = udp_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } @@ -1997,7 +2005,7 @@ EXPORT_SYMBOL(udp_disconnect); void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; hslot = udp_hashslot(udptable, sock_net(sk), @@ -2028,7 +2036,7 @@ EXPORT_SYMBOL(udp_lib_unhash); void udp_lib_rehash(struct sock *sk, u16 newhash) { if (sk_hashed(sk)) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2, *nhslot2; hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); @@ -2517,10 +2525,14 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { - struct sock *sk, *result; + struct udp_table *udptable = net->ipv4.udp_table; unsigned short hnum = ntohs(loc_port); - unsigned int slot = udp_hashfn(net, hnum, udp_table.mask); - struct udp_hslot *hslot = &udp_table.hash[slot]; + struct sock *sk, *result; + struct udp_hslot *hslot; + unsigned int slot; + + slot = udp_hashfn(net, hnum, udptable->mask); + hslot = &udptable->hash[slot]; /* Do not bother scanning a too big list */ if (hslot->count > 10) @@ -2548,14 +2560,19 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { - unsigned short hnum = ntohs(loc_port); - unsigned int hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); - unsigned int slot2 = hash2 & udp_table.mask; - struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; + struct udp_table *udptable = net->ipv4.udp_table; INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); - const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); + unsigned short hnum = ntohs(loc_port); + unsigned int hash2, slot2; + struct udp_hslot *hslot2; + __portpair ports; struct sock *sk; + hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + ports = INET_COMBINED_PORTS(rmt_port, hnum); + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (inet_match(net, sk, acookie, ports, dif, sdif)) return sk; @@ -2635,7 +2652,7 @@ int udp_v4_early_demux(struct sk_buff *skb) int udp_rcv(struct sk_buff *skb) { - return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); + return __udp4_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP); } void udp_destroy_sock(struct sock *sk) @@ -2671,6 +2688,18 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, int err = 0; int is_udplite = IS_UDPLITE(sk); + if (level == SOL_SOCKET) { + err = sk_setsockopt(sk, level, optname, optval, optlen); + + if (optname == SO_RCVBUF || optname == SO_RCVBUFFORCE) { + sockopt_lock_sock(sk); + /* paired with READ_ONCE in udp_rmem_release() */ + WRITE_ONCE(up->forward_threshold, sk->sk_rcvbuf >> 2); + sockopt_release_sock(sk); + } + return err; + } + if (optlen < sizeof(int)) return -EINVAL; @@ -2784,7 +2813,7 @@ EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_push_pending_frames); @@ -2946,7 +2975,7 @@ struct proto udp_prot = { .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 = &udp_table, + .h.udp_table = NULL, .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); @@ -2954,21 +2983,30 @@ EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS +static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo, + struct net *net) +{ + return afinfo->udp_table ? : net->ipv4.udp_table; +} + static struct sock *udp_get_first(struct seq_file *seq, int start) { - struct sock *sk; - struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct udp_seq_afinfo *afinfo; + struct udp_table *udptable; + struct sock *sk; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = pde_data(file_inode(seq->file)); - for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; + udptable = udp_get_table_afinfo(afinfo, net); + + for (state->bucket = start; state->bucket <= udptable->mask; ++state->bucket) { - struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket]; + struct udp_hslot *hslot = &udptable->hash[state->bucket]; if (hlist_empty(&hslot->head)) continue; @@ -2990,9 +3028,10 @@ found: static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { - struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct udp_seq_afinfo *afinfo; + struct udp_table *udptable; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; @@ -3006,8 +3045,11 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) sk->sk_family != afinfo->family))); if (!sk) { - if (state->bucket <= afinfo->udp_table->mask) - spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); + udptable = udp_get_table_afinfo(afinfo, net); + + if (state->bucket <= udptable->mask) + spin_unlock_bh(&udptable->hash[state->bucket].lock); + return udp_get_first(seq, state->bucket + 1); } return sk; @@ -3048,16 +3090,19 @@ EXPORT_SYMBOL(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { - struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; + struct udp_seq_afinfo *afinfo; + struct udp_table *udptable; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = pde_data(file_inode(seq->file)); - if (state->bucket <= afinfo->udp_table->mask) - spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); + udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq)); + + if (state->bucket <= udptable->mask) + spin_unlock_bh(&udptable->hash[state->bucket].lock); } EXPORT_SYMBOL(udp_seq_stop); @@ -3170,7 +3215,7 @@ EXPORT_SYMBOL(udp_seq_ops); static struct udp_seq_afinfo udp4_seq_afinfo = { .family = AF_INET, - .udp_table = &udp_table, + .udp_table = NULL, }; static int __net_init udp4_proc_init_net(struct net *net) @@ -3232,7 +3277,7 @@ void __init udp_table_init(struct udp_table *table, const char *name) &table->log, &table->mask, UDP_HTABLE_SIZE_MIN, - 64 * 1024); + UDP_HTABLE_SIZE_MAX); table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { @@ -3257,7 +3302,7 @@ u32 udp_flow_hashrnd(void) } EXPORT_SYMBOL(udp_flow_hashrnd); -static int __net_init udp_sysctl_init(struct net *net) +static void __net_init udp_sysctl_init(struct net *net) { net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; @@ -3265,12 +3310,103 @@ static int __net_init udp_sysctl_init(struct net *net) #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_udp_l3mdev_accept = 0; #endif +} + +static struct udp_table __net_init *udp_pernet_table_alloc(unsigned int hash_entries) +{ + struct udp_table *udptable; + int i; + + udptable = kmalloc(sizeof(*udptable), GFP_KERNEL); + if (!udptable) + goto out; + + udptable->hash = vmalloc_huge(hash_entries * 2 * sizeof(struct udp_hslot), + GFP_KERNEL_ACCOUNT); + if (!udptable->hash) + goto free_table; + + udptable->hash2 = udptable->hash + hash_entries; + udptable->mask = hash_entries - 1; + udptable->log = ilog2(hash_entries); + + for (i = 0; i < hash_entries; i++) { + INIT_HLIST_HEAD(&udptable->hash[i].head); + udptable->hash[i].count = 0; + spin_lock_init(&udptable->hash[i].lock); + + INIT_HLIST_HEAD(&udptable->hash2[i].head); + udptable->hash2[i].count = 0; + spin_lock_init(&udptable->hash2[i].lock); + } + + return udptable; + +free_table: + kfree(udptable); +out: + return NULL; +} + +static void __net_exit udp_pernet_table_free(struct net *net) +{ + struct udp_table *udptable = net->ipv4.udp_table; + + if (udptable == &udp_table) + return; + + kvfree(udptable->hash); + kfree(udptable); +} + +static void __net_init udp_set_table(struct net *net) +{ + struct udp_table *udptable; + unsigned int hash_entries; + struct net *old_net; + + if (net_eq(net, &init_net)) + goto fallback; + + old_net = current->nsproxy->net_ns; + hash_entries = READ_ONCE(old_net->ipv4.sysctl_udp_child_hash_entries); + if (!hash_entries) + goto fallback; + + /* Set min to keep the bitmap on stack in udp_lib_get_port() */ + if (hash_entries < UDP_HTABLE_SIZE_MIN_PERNET) + hash_entries = UDP_HTABLE_SIZE_MIN_PERNET; + else + hash_entries = roundup_pow_of_two(hash_entries); + + udptable = udp_pernet_table_alloc(hash_entries); + if (udptable) { + net->ipv4.udp_table = udptable; + } else { + pr_warn("Failed to allocate UDP hash table (entries: %u) " + "for a netns, fallback to the global one\n", + hash_entries); +fallback: + net->ipv4.udp_table = &udp_table; + } +} + +static int __net_init udp_pernet_init(struct net *net) +{ + udp_sysctl_init(net); + udp_set_table(net); return 0; } +static void __net_exit udp_pernet_exit(struct net *net) +{ + udp_pernet_table_free(net); +} + static struct pernet_operations __net_initdata udp_sysctl_ops = { - .init = udp_sysctl_init, + .init = udp_pernet_init, + .exit = udp_pernet_exit, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) @@ -3288,7 +3424,7 @@ static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) return -ENOMEM; afinfo->family = AF_UNSPEC; - afinfo->udp_table = &udp_table; + afinfo->udp_table = NULL; st->bpf_seq_afinfo = afinfo; ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index ff15918b7bdc..e5dc91d0e079 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -141,14 +141,14 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) if (restore) { sk->sk_write_space = psock->saved_write_space; - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); return 0; } if (sk->sk_family == AF_INET6) udp_bpf_check_v6_needs_rebuild(psock->sk_proto); - WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]); + sock_replace_proto(sk, &udp_bpf_prots[family]); return 0; } EXPORT_SYMBOL_GPL(udp_bpf_update_proto); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 1ed8c4d78e5c..de3f2d31f510 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -147,13 +147,13 @@ done: static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { - udp_dump(&udp_table, skb, cb, r); + udp_dump(sock_net(cb->skb->sk)->ipv4.udp_table, skb, cb, r); } static int udp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return udp_dump_one(&udp_table, cb, req); + return udp_dump_one(sock_net(cb->skb->sk)->ipv4.udp_table, cb, req); } static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, @@ -225,7 +225,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, static int udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { - return __udp_diag_destroy(in_skb, req, &udp_table); + return __udp_diag_destroy(in_skb, req, sock_net(in_skb->sk)->ipv4.udp_table); } static int udplite_diag_destroy(struct sk_buff *in_skb, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6d1a4bec2614..aedde65e2268 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -600,10 +600,11 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); + struct net *net = dev_net(skb->dev); - return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + return __udp4_lib_lookup(net, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), - inet_sdif(skb), &udp_table, NULL); + inet_sdif(skb), net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index bc3a043a5d5c..029219749785 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -624,6 +624,8 @@ __udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, continue; nest = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_ENTRY); + if (!nest) + return -EMSGSIZE; if (nla_put_be16(skb, ETHTOOL_A_TUNNEL_UDP_ENTRY_PORT, utn->entries[table][j].port) || diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 10ce86bf228e..9c3f5202a97b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -104,7 +104,7 @@ static inline u32 cstamp_delta(unsigned long cstamp) static inline s32 rfc3315_s14_backoff_init(s32 irt) { /* multiply 'initial retransmission time' by 0.9 .. 1.1 */ - u64 tmp = (900000 + prandom_u32() % 200001) * (u64)irt; + u64 tmp = (900000 + prandom_u32_max(200001)) * (u64)irt; do_div(tmp, 1000000); return (s32)tmp; } @@ -112,11 +112,11 @@ static inline s32 rfc3315_s14_backoff_init(s32 irt) static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt) { /* multiply 'retransmission timeout' by 1.9 .. 2.1 */ - u64 tmp = (1900000 + prandom_u32() % 200001) * (u64)rt; + u64 tmp = (1900000 + prandom_u32_max(200001)) * (u64)rt; do_div(tmp, 1000000); if ((s32)tmp > mrt) { /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */ - tmp = (900000 + prandom_u32() % 200001) * (u64)mrt; + tmp = (900000 + prandom_u32_max(200001)) * (u64)mrt; do_div(tmp, 1000000); } return (s32)tmp; @@ -3967,7 +3967,7 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else - rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); + rand_num = prandom_u32_max(idev->cnf.rtr_solicit_delay ?: 1); nonce = 0; if (idev->cnf.enhanced_dad || @@ -7214,9 +7214,11 @@ err_reg_dflt: __addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(dflt); + net->ipv6.devconf_dflt = NULL; #endif err_alloc_dflt: kfree(all); + net->ipv6.devconf_all = NULL; err_alloc_all: kfree(net->ipv6.inet6_addr_lst); err_alloc_addr: diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 8a22486cf270..17ac45aa7194 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -437,6 +437,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, { struct ifaddrlblmsg *ifal = nlmsg_data(nlh); ifal->ifal_family = AF_INET6; + ifal->__ifal_reserved = 0; ifal->ifal_prefixlen = prefixlen; ifal->ifal_flags = 0; ifal->ifal_index = ifindex; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 024191004982..fee9163382c2 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -114,6 +114,7 @@ void inet6_sock_destruct(struct sock *sk) inet6_cleanup_sock(sk); inet_sock_destruct(sk); } +EXPORT_SYMBOL_GPL(inet6_sock_destruct); static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) @@ -409,10 +410,10 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { - if (sk->sk_prot->get_port(sk, snum)) { + err = sk->sk_prot->get_port(sk, snum); + if (err) { sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); - err = -EADDRINUSE; goto out; } if (!(flags & BIND_FROM_BPF)) { @@ -489,7 +490,7 @@ int inet6_release(struct socket *sock) } EXPORT_SYMBOL(inet6_release); -void inet6_destroy_sock(struct sock *sk) +void inet6_cleanup_sock(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -514,12 +515,6 @@ void inet6_destroy_sock(struct sock *sk) txopt_put(opt); } } -EXPORT_SYMBOL_GPL(inet6_destroy_sock); - -void inet6_cleanup_sock(struct sock *sk) -{ - inet6_destroy_sock(sk); -} EXPORT_SYMBOL_GPL(inet6_cleanup_sock); /* diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index df665d4e8f0f..7c7155b48f17 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -256,7 +256,7 @@ ipv4_connected: goto out; } - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: @@ -334,6 +334,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } +EXPORT_SYMBOL_GPL(ipv6_icmp_error); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { @@ -771,7 +772,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, } if (cmsg->cmsg_level == SOL_SOCKET) { - err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc); + err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc); if (err) return err; continue; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 97edf461bc72..75c02992c520 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -345,6 +345,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); len = skb->len - sizeof(struct ipv6hdr); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 413f66781e50..2438da5ff6da 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -91,13 +91,12 @@ static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) static int fib6_new_sernum(struct net *net) { - int new, old; + int new, old = atomic_read(&net->ipv6.fib6_sernum); do { - old = atomic_read(&net->ipv6.fib6_sernum); new = old < INT_MAX ? old + 1 : 1; - } while (atomic_cmpxchg(&net->ipv6.fib6_sernum, - old, new) != old); + } while (!atomic_try_cmpxchg(&net->ipv6.fib6_sernum, &old, new)); + return new; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index ceb85c67ce39..18481eb76a0a 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -220,7 +220,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { - fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; + fl->label = htonl(get_random_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); if (!lfl) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 02b1b54165e8..89f5f0f3f5d6 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -895,7 +895,6 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net_device_stats *stats = &t->dev->stats; __be16 payload_protocol; int ret; @@ -925,8 +924,8 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, tx_err: if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } @@ -937,7 +936,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); - struct net_device_stats *stats; bool truncate = false; int encap_limit = -1; __u8 dsfield = false; @@ -1086,10 +1084,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - stats = &t->dev->stats; if (!IS_ERR(tun_info)) - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } @@ -1155,14 +1152,16 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, dev->needed_headroom = dst_len; if (set_mtu) { - dev->mtu = rt->dst.dev->mtu - t_hlen; + int mtu = rt->dst.dev->mtu - t_hlen; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; if (dev->type == ARPHRD_ETHER) - dev->mtu -= ETH_HLEN; + mtu -= ETH_HLEN; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } ip6_rt_put(rt); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index cc5d5e75b658..47b6607a1370 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -803,8 +803,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, (tunnel->parms.i_flags & TUNNEL_CSUM)) || ((tpi->flags & TUNNEL_CSUM) && !(tunnel->parms.i_flags & TUNNEL_CSUM))) { - tunnel->dev->stats.rx_crc_errors++; - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_crc_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } @@ -812,8 +812,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, if (!(tpi->flags & TUNNEL_SEQ) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { - tunnel->dev->stats.rx_fifo_errors++; - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_fifo_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; @@ -824,8 +824,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { - tunnel->dev->stats.rx_length_errors++; - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } @@ -849,8 +849,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, &ipv6h->saddr, ipv6_get_dsfield(ipv6h)); if (err > 1) { - ++tunnel->dev->stats.rx_frame_errors; - ++tunnel->dev->stats.rx_errors; + DEV_STATS_INC(tunnel->dev, rx_frame_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } @@ -1071,7 +1071,6 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; - struct net_device_stats *stats = &t->dev->stats; struct ipv6hdr *ipv6h; struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; @@ -1166,7 +1165,7 @@ route_lookup: tdev = dst->dev; if (tdev == dev) { - stats->collisions++; + DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; @@ -1265,7 +1264,7 @@ route_lookup: ip6tunnel_xmit(NULL, skb, dev); return 0; tx_err_link_failure: - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); @@ -1408,7 +1407,6 @@ static netdev_tx_t ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net_device_stats *stats = &t->dev->stats; u8 ipproto; int ret; @@ -1438,8 +1436,8 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_err: - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } @@ -1450,8 +1448,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct net_device *tdev = NULL; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; - unsigned int mtu; int t_hlen; + int mtu; __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); @@ -1498,12 +1496,13 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) dev->hard_header_len = tdev->hard_header_len + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); - dev->mtu = mtu - t_hlen; + mtu = mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 151337d7f67b..10b222865d46 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -317,7 +317,7 @@ static int vti6_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { - t->dev->stats.rx_dropped++; + DEV_STATS_INC(t->dev, rx_dropped); rcu_read_unlock(); goto discard; } @@ -359,8 +359,8 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err) dev = t->dev; if (err) { - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_dropped); return 0; } @@ -446,7 +446,6 @@ static int vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip6_tnl *t = netdev_priv(dev); - struct net_device_stats *stats = &t->dev->stats; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; struct xfrm_state *x; @@ -506,7 +505,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) tdev = dst->dev; if (tdev == dev) { - stats->collisions++; + DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; @@ -544,7 +543,7 @@ xmit: return 0; tx_err_link_failure: - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); @@ -555,7 +554,6 @@ static netdev_tx_t vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net_device_stats *stats = &t->dev->stats; struct flowi fl; int ret; @@ -591,8 +589,8 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_err: - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index facdc78a43e5..23e766597f36 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -608,8 +608,8 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) goto tx_err; - dev->stats.tx_bytes += skb->len; - dev->stats.tx_packets++; + DEV_STATS_ADD(dev, tx_bytes, skb->len); + DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); ip6mr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), MRT6MSG_WHOLEPKT); @@ -618,7 +618,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } @@ -2044,8 +2044,8 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, if (vif->flags & MIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); - vif_dev->stats.tx_bytes += skb->len; - vif_dev->stats.tx_packets++; + DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); + DEV_STATS_INC(vif_dev, tx_packets); ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); goto out_free; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 532f4478c884..9ce51680290b 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1005,10 +1005,8 @@ unlock: return retv; e_inval: - sockopt_release_sock(sk); - if (needs_rtnl) - rtnl_unlock(); - return -EINVAL; + retv = -EINVAL; + goto unlock; } int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 0566ab03ddbe..7860383295d8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1050,7 +1050,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, /* called with mc_lock */ static void mld_gq_start_work(struct inet6_dev *idev) { - unsigned long tv = prandom_u32() % idev->mc_maxdelay; + unsigned long tv = prandom_u32_max(idev->mc_maxdelay); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) @@ -1068,7 +1068,7 @@ static void mld_gq_stop_work(struct inet6_dev *idev) /* called with mc_lock */ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = prandom_u32() % delay; + unsigned long tv = prandom_u32_max(delay); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); @@ -1085,7 +1085,7 @@ static void mld_ifc_stop_work(struct inet6_dev *idev) /* called with mc_lock */ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = prandom_u32() % delay; + unsigned long tv = prandom_u32_max(delay); if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) in6_dev_hold(idev); @@ -1130,7 +1130,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) } if (delay >= resptime) - delay = prandom_u32() % resptime; + delay = prandom_u32_max(resptime); if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); @@ -2574,7 +2574,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = prandom_u32() % unsolicited_report_interval(ma->idev); + delay = prandom_u32_max(unsolicited_report_interval(ma->idev)); if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 69d86b040a6a..a01d9b842bd0 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -40,6 +40,7 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, .flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev), .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, .flowi6_proto = iph->nexthdr, + .flowi6_uid = sock_net_uid(net, NULL), .daddr = iph->saddr, }; int lookup_flags; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 38db0064d661..d13240f13607 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -253,7 +253,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, if (err) { if (err == IPFRAG_DUP) { /* No error for duplicates, pretend they got queued. */ - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_DUP_FRAG); return -EINPROGRESS; } goto insert_error; diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 70a405b4006f..c82f3fdd4a65 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -50,7 +50,8 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, return err; } -static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dup_ipv6_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_dup_ipv6 *priv = nft_expr_priv(expr); diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 91faac610e03..36dc14b34388 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -66,6 +66,7 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; u32 ret = 0; @@ -163,6 +164,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; struct rt6_info *rt; int lookup_flags; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 2880dc7d9a49..2685c3f15e9d 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -18,7 +18,7 @@ static u32 __ipv6_select_ident(struct net *net, u32 id; do { - id = prandom_u32(); + id = get_random_u32(); } while (!id); return id; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 86c26e48d065..808983bc2ec9 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -23,11 +23,6 @@ #include <linux/bpf-cgroup.h> #include <net/ping.h> -static void ping_v6_destroy(struct sock *sk) -{ - inet6_destroy_sock(sk); -} - /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) @@ -205,7 +200,6 @@ struct proto pingv6_prot = { .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, - .destroy = ping_v6_destroy, .pre_connect = ping_v6_pre_connect, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 722de9dd0ff7..a06a9f847db5 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1173,8 +1173,6 @@ static void raw6_destroy(struct sock *sk) lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - - inet6_destroy_sock(sk); } static int rawv6_init_sk(struct sock *sk) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index ff866f2a879e..5bc8a28e67f9 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -112,10 +112,14 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail; struct net_device *dev; int err = -ENOENT; + SKB_DR(reason); u8 ecn; - if (fq->q.flags & INET_FRAG_COMPLETE) + /* If reassembly is already done, @skb must be a duplicate frag. */ + if (fq->q.flags & INET_FRAG_COMPLETE) { + SKB_DR_SET(reason, DUP_FRAG); goto err; + } err = -EINVAL; offset = ntohs(fhdr->frag_off) & ~0x7; @@ -226,8 +230,9 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, insert_error: if (err == IPFRAG_DUP) { - kfree_skb(skb); - return -EINVAL; + SKB_DR_SET(reason, DUP_FRAG); + err = -EINVAL; + goto err; } err = -EINVAL; __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), @@ -237,7 +242,7 @@ discard_fq: __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); err: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return err; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 69252eb462b2..2f355f0ec32a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6555,10 +6555,16 @@ static void __net_exit ip6_route_net_exit(struct net *net) static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, - sizeof(struct ipv6_route_iter)); - proc_create_net_single("rt6_stats", 0444, net->proc_net, - rt6_stats_seq_show, NULL); + if (!proc_create_net("ipv6_route", 0, net->proc_net, + &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter))) + return -ENOMEM; + + if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, + rt6_stats_seq_show, NULL)) { + remove_proc_entry("ipv6_route", net->proc_net); + return -ENOMEM; + } #endif return 0; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 8370726ae7bf..487f8e98deaa 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -1644,13 +1644,13 @@ static int put_nla_counters(struct sk_buff *skb, struct seg6_local_lwt *slwt) pcounters = per_cpu_ptr(slwt->pcpu_counters, i); do { - start = u64_stats_fetch_begin_irq(&pcounters->syncp); + start = u64_stats_fetch_begin(&pcounters->syncp); packets = u64_stats_read(&pcounters->packets); bytes = u64_stats_read(&pcounters->bytes); errors = u64_stats_read(&pcounters->errors); - } while (u64_stats_fetch_retry_irq(&pcounters->syncp, start)); + } while (u64_stats_fetch_retry(&pcounters->syncp, start)); counters.packets += packets; counters.bytes += bytes; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d27683e3fc97..70d81bba5093 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -694,7 +694,7 @@ static int ipip6_rcv(struct sk_buff *skb) skb->dev = tunnel->dev; if (packet_is_spoofed(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; + DEV_STATS_INC(tunnel->dev, rx_errors); goto out; } @@ -714,8 +714,8 @@ static int ipip6_rcv(struct sk_buff *skb) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { - ++tunnel->dev->stats.rx_frame_errors; - ++tunnel->dev->stats.rx_errors; + DEV_STATS_INC(tunnel->dev, rx_frame_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); goto out; } } @@ -942,7 +942,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (!rt) { rt = ip_route_output_flow(tunnel->net, &fl4, NULL); if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); @@ -950,14 +950,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); - dev->stats.tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); goto tx_error; } @@ -970,7 +970,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, mtu = dst_mtu(&rt->dst) - t_hlen; if (mtu < IPV4_MIN_MTU) { - dev->stats.collisions++; + DEV_STATS_INC(dev, collisions); ip_rt_put(rt); goto tx_error; } @@ -1009,7 +1009,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } @@ -1039,7 +1039,7 @@ tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } @@ -1058,7 +1058,7 @@ static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb, return NETDEV_TX_OK; tx_error: kfree_skb(skb); - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } @@ -1087,7 +1087,7 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, return NETDEV_TX_OK; tx_err: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; @@ -1124,10 +1124,12 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int mtu; - dev->mtu = tdev->mtu - t_hlen; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + mtu = tdev->mtu - t_hlen; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2a3f9296df1e..f52b6f271a24 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -292,24 +292,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -359,6 +346,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; @@ -1966,12 +1954,6 @@ static int tcp_v6_init_sock(struct sock *sk) return 0; } -static void tcp_v6_destroy_sock(struct sock *sk) -{ - tcp_v4_destroy_sock(sk); - inet6_destroy_sock(sk); -} - #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, @@ -2164,7 +2146,7 @@ struct proto tcpv6_prot = { .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, - .destroy = tcp_v6_destroy_sock, + .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8d09f0ea5b8c..9fb2f33ee3a7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -64,8 +64,9 @@ static void udpv6_destruct_sock(struct sock *sk) int udpv6_init_sock(struct sock *sk) { - skb_queue_head_init(&udp_sk(sk)->reader_queue); + udp_lib_init_sock(sk); sk->sk_destruct = udpv6_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } @@ -195,7 +196,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; @@ -216,7 +217,7 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, struct sock *sk, *reuse_sk; bool no_reuseport; - if (udptable != &udp_table) + if (udptable != net->ipv4.udp_table) return NULL; /* only UDP is supported */ no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport, @@ -297,10 +298,11 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = ipv6_hdr(skb); + struct net *net = dev_net(skb->dev); - return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, + return __udp6_lib_lookup(net, &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), &udp_table, NULL); + inet6_sdif(skb), net->ipv4.udp_table, NULL); } /* Must be called under rcu_read_lock(). @@ -313,7 +315,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be struct sock *sk; sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, - dif, 0, &udp_table, NULL); + dif, 0, net->ipv4.udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; @@ -631,7 +633,8 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Tunnels don't have an application socket: don't pass errors back */ if (tunnel) { if (udp_sk(sk)->encap_err_rcv) - udp_sk(sk)->encap_err_rcv(sk, skb, offset); + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, + ntohl(info), (u8 *)(uh+1)); goto out; } @@ -687,7 +690,8 @@ static __inline__ int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); + return __udp6_lib_err(skb, opt, type, code, offset, info, + dev_net(skb->dev)->ipv4.udp_table); } static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) @@ -1061,13 +1065,18 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, __be16 rmt_port, const struct in6_addr *rmt_addr, int dif, int sdif) { + struct udp_table *udptable = net->ipv4.udp_table; unsigned short hnum = ntohs(loc_port); - unsigned int hash2 = ipv6_portaddr_hash(net, loc_addr, hnum); - unsigned int slot2 = hash2 & udp_table.mask; - struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; - const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); + unsigned int hash2, slot2; + struct udp_hslot *hslot2; + __portpair ports; struct sock *sk; + hash2 = ipv6_portaddr_hash(net, loc_addr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + ports = INET_COMBINED_PORTS(rmt_port, hnum); + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (sk->sk_state == TCP_ESTABLISHED && inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif)) @@ -1121,7 +1130,7 @@ void udp_v6_early_demux(struct sk_buff *skb) INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb) { - return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP); + return __udp6_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP); } /* @@ -1638,6 +1647,7 @@ do_confirm: err = 0; goto out; } +EXPORT_SYMBOL(udpv6_sendmsg); void udpv6_destroy_sock(struct sock *sk) { @@ -1661,8 +1671,6 @@ void udpv6_destroy_sock(struct sock *sk) udp_encap_disable(); } } - - inet6_destroy_sock(sk); } /* @@ -1671,7 +1679,7 @@ void udpv6_destroy_sock(struct sock *sk) int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_v6_push_pending_frames); @@ -1719,7 +1727,7 @@ EXPORT_SYMBOL(udp6_seq_ops); static struct udp_seq_afinfo udp6_seq_afinfo = { .family = AF_INET6, - .udp_table = &udp_table, + .udp_table = NULL, }; int __net_init udp6_proc_init(struct net *net) @@ -1769,7 +1777,7 @@ struct proto udpv6_prot = { .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 = &udp_table, + .h.udp_table = NULL, .diag_destroy = udp_abort, }; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 7720d04ed396..e0e10f6bcdc1 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -116,10 +116,11 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = skb_gro_network_header(skb); + struct net *net = dev_net(skb->dev); - return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, + return __udp6_lib_lookup(net, &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), &udp_table, NULL); + inet6_sdif(skb), net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 4a4b0e49ec92..ea435eba3053 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -287,9 +287,13 @@ int __init xfrm6_init(void) if (ret) goto out_state; - register_pernet_subsys(&xfrm6_net_ops); + ret = register_pernet_subsys(&xfrm6_net_ops); + if (ret) + goto out_protocol; out: return ret; +out_protocol: + xfrm6_protocol_fini(); out_state: xfrm6_state_fini(); out_policy: diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 27725464ec08..890a2423f559 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -162,7 +162,8 @@ static void kcm_rcv_ready(struct kcm_sock *kcm) /* Buffer limit is okay now, add to ready list */ list_add_tail(&kcm->wait_rx_list, &kcm->mux->kcm_rx_waiters); - kcm->rx_wait = true; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, true); } static void kcm_rfree(struct sk_buff *skb) @@ -178,7 +179,7 @@ static void kcm_rfree(struct sk_buff *skb) /* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic(); - if (!kcm->rx_wait && !kcm->rx_psock && + if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) && sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); @@ -221,7 +222,7 @@ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) struct sk_buff *skb; struct kcm_sock *kcm; - while ((skb = __skb_dequeue(head))) { + while ((skb = skb_dequeue(head))) { /* Reset destructor to avoid calling kcm_rcv_ready */ skb->destructor = sock_rfree; skb_orphan(skb); @@ -237,7 +238,8 @@ try_again: if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); /* Commit rx_wait to read in kcm_free */ smp_wmb(); @@ -280,10 +282,12 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); psock->rx_kcm = kcm; - kcm->rx_psock = psock; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_psock, psock); spin_unlock_bh(&mux->rx_lock); @@ -310,7 +314,8 @@ static void unreserve_rx_kcm(struct kcm_psock *psock, spin_lock_bh(&mux->rx_lock); psock->rx_kcm = NULL; - kcm->rx_psock = NULL; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_psock, NULL); /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with * kcm_rfree @@ -834,7 +839,7 @@ static ssize_t kcm_sendpage(struct socket *sock, struct page *page, } get_page(page); - skb_fill_page_desc(skb, i, page, offset, size); + skb_fill_page_desc_noacc(skb, i, page, offset, size); skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; coalesced: @@ -1080,53 +1085,17 @@ out_error: return err; } -static struct sk_buff *kcm_wait_data(struct sock *sk, int flags, - long timeo, int *err) -{ - struct sk_buff *skb; - - while (!(skb = skb_peek(&sk->sk_receive_queue))) { - if (sk->sk_err) { - *err = sock_error(sk); - return NULL; - } - - if (sock_flag(sk, SOCK_DONE)) - return NULL; - - if ((flags & MSG_DONTWAIT) || !timeo) { - *err = -EAGAIN; - return NULL; - } - - sk_wait_data(sk, &timeo, NULL); - - /* Handle signals */ - if (signal_pending(current)) { - *err = sock_intr_errno(timeo); - return NULL; - } - } - - return skb; -} - static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); int err = 0; - long timeo; struct strp_msg *stm; int copied = 0; struct sk_buff *skb; - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - skb = kcm_wait_data(sk, flags, timeo, &err); + skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; @@ -1157,14 +1126,11 @@ msg_finished: /* Finished with message */ msg->msg_flags |= MSG_EOR; KCM_STATS_INCR(kcm->stats.rx_msgs); - skb_unlink(skb, &sk->sk_receive_queue); - kfree_skb(skb); } } out: - release_sock(sk); - + skb_free_datagram(sk, skb); return copied ? : err; } @@ -1174,7 +1140,6 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); - long timeo; struct strp_msg *stm; int err = 0; ssize_t copied; @@ -1182,11 +1147,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, /* Only support splice for SOCKSEQPACKET */ - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - skb = kcm_wait_data(sk, flags, timeo, &err); + skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto err_out; @@ -1214,13 +1175,11 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, * finish reading the message. */ - release_sock(sk); - + skb_free_datagram(sk, skb); return copied; err_out: - release_sock(sk); - + skb_free_datagram(sk, skb); return err; } @@ -1240,7 +1199,8 @@ static void kcm_recv_disable(struct kcm_sock *kcm) if (!kcm->rx_psock) { if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); } requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); @@ -1793,7 +1753,8 @@ static void kcm_done(struct kcm_sock *kcm) if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); } /* Move any pending receive messages to other kcm sockets */ requeue_rx_msgs(mux, &sk->sk_receive_queue); diff --git a/net/key/af_key.c b/net/key/af_key.c index e1d2155605aa..2bdbcec781cd 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2905,7 +2905,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2923,7 +2923,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { @@ -2934,16 +2934,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } -static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -2971,13 +2972,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } -static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -3019,8 +3024,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) @@ -3150,6 +3158,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; + int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -3161,16 +3170,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) - size += count_ah_combs(t); + alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) - size += count_esp_combs(t); + alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } - skb = alloc_skb(size + 16, GFP_ATOMIC); + skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -3224,10 +3233,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ + alg_size = 0; if (x->id.proto == IPPROTO_AH) - dump_ah_combs(skb, t); + alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) - dump_esp_combs(skb, t); + alg_size = dump_esp_combs(skb, t); + + hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { @@ -3382,7 +3394,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; - hdr->sadb_msg_seq = x->km.seq = get_acqseq(); + hdr->sadb_msg_seq = x->km.seq; hdr->sadb_msg_pid = 0; /* SA */ diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 7499c51b1850..9a1415fe3fa7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1150,8 +1150,10 @@ static void l2tp_tunnel_destruct(struct sock *sk) } /* Remove hooks into tunnel socket */ + write_lock_bh(&sk->sk_callback_lock); sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; + write_unlock_bh(&sk->sk_callback_lock); /* Call the original destructor */ if (sk->sk_destruct) @@ -1469,16 +1471,19 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; - - ret = l2tp_validate_socket(sock->sk, net, tunnel->encap); - if (ret < 0) - goto err_sock; } + sk = sock->sk; + write_lock_bh(&sk->sk_callback_lock); + ret = l2tp_validate_socket(sk, net, tunnel->encap); + if (ret < 0) + goto err_inval_sock; + rcu_assign_sk_user_data(sk, tunnel); + write_unlock_bh(&sk->sk_callback_lock); + tunnel->l2tp_net = net; pn = l2tp_pernet(net); - sk = sock->sk; sock_hold(sk); tunnel->sock = sk; @@ -1503,8 +1508,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); - } else { - sk->sk_user_data = tunnel; } tunnel->old_sk_destruct = sk->sk_destruct; @@ -1521,6 +1524,11 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, return 0; err_sock: + write_lock_bh(&sk->sk_callback_lock); + rcu_assign_sk_user_data(sk, NULL); +err_inval_sock: + write_unlock_bh(&sk->sk_callback_lock); + if (tunnel->fd < 0) sock_release(sock); else diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9dbd801ddb98..2478aa60145f 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -257,8 +257,6 @@ static void l2tp_ip6_destroy_sock(struct sock *sk) if (tunnel) l2tp_tunnel_delete(tunnel); - - inet6_destroy_sock(sk); } static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 9414d3bbd65f..c6fa53230450 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -183,34 +183,15 @@ static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, const struct ieee80211_addba_ext_ie *req, u16 buf_size) { - struct ieee80211_supported_band *sband; struct ieee80211_addba_ext_ie *resp; - const struct ieee80211_sta_he_cap *he_cap; - u8 frag_level, cap_frag_level; u8 *pos; - sband = ieee80211_get_sband(sdata); - if (!sband) - return; - he_cap = ieee80211_get_he_iftype_cap(sband, - ieee80211_vif_type_p2p(&sdata->vif)); - if (!he_cap) - return; - pos = skb_put_zero(skb, 2 + sizeof(struct ieee80211_addba_ext_ie)); *pos++ = WLAN_EID_ADDBA_EXT; *pos++ = sizeof(struct ieee80211_addba_ext_ie); resp = (struct ieee80211_addba_ext_ie *)pos; resp->data = req->data & IEEE80211_ADDBA_EXT_NO_FRAG; - frag_level = u32_get_bits(req->data, - IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); - cap_frag_level = u32_get_bits(he_cap->he_cap_elem.mac_cap_info[0], - IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK); - if (frag_level > cap_frag_level) - frag_level = cap_frag_level; - resp->data |= u8_encode_bits(frag_level, - IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK); resp->data |= u8_encode_bits(buf_size >> IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT, IEEE80211_ADDBA_EXT_BUF_SIZE_MASK); } @@ -242,7 +223,7 @@ static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid, sdata->vif.type == NL80211_IFTYPE_MESH_POINT) memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); else if (sdata->vif.type == NL80211_IFTYPE_STATION) - memcpy(mgmt->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN); + memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN); @@ -297,9 +278,9 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta, } if (!sta->sta.deflink.ht_cap.ht_supported && - sta->sdata->vif.bss_conf.chandef.chan->band != NL80211_BAND_6GHZ) { + !sta->sta.deflink.he_cap.has_he) { ht_dbg(sta->sdata, - "STA %pM erroneously requests BA session on tid %d w/o QoS\n", + "STA %pM erroneously requests BA session on tid %d w/o HT\n", sta->sta.addr, tid); /* send a response anyway, it's an error case if we get here */ goto end; diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 07c892aa8c73..9c40f8d3bce8 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -82,7 +82,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, sdata->vif.type == NL80211_IFTYPE_MESH_POINT) memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); else if (sdata->vif.type == NL80211_IFTYPE_STATION) - memcpy(mgmt->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN); + memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN); diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 2e66598fac79..e8ebd343e2bf 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -452,6 +452,9 @@ static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, (status->encoding == RX_ENC_HE && streams > 8))) return 0; + if (idx >= MCS_GROUP_RATES) + return 0; + duration = airtime_mcs_groups[group].duration[idx]; duration <<= airtime_mcs_groups[group].shift; *overhead = 36 + (streams << 2); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 687b4c878d4a..c848fe04dd44 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2554,47 +2554,50 @@ static int ieee80211_change_bss(struct wiphy *wiphy, struct bss_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_link_data *link; struct ieee80211_supported_band *sband; u32 changed = 0; - if (!sdata_dereference(sdata->deflink.u.ap.beacon, sdata)) + link = ieee80211_link_or_deflink(sdata, params->link_id, true); + if (IS_ERR(link)) + return PTR_ERR(link); + + if (!sdata_dereference(link->u.ap.beacon, sdata)) return -ENOENT; - sband = ieee80211_get_sband(sdata); + sband = ieee80211_get_link_sband(link); if (!sband) return -EINVAL; if (params->use_cts_prot >= 0) { - sdata->vif.bss_conf.use_cts_prot = params->use_cts_prot; + link->conf->use_cts_prot = params->use_cts_prot; changed |= BSS_CHANGED_ERP_CTS_PROT; } if (params->use_short_preamble >= 0) { - sdata->vif.bss_conf.use_short_preamble = - params->use_short_preamble; + link->conf->use_short_preamble = params->use_short_preamble; changed |= BSS_CHANGED_ERP_PREAMBLE; } - if (!sdata->vif.bss_conf.use_short_slot && + if (!link->conf->use_short_slot && (sband->band == NL80211_BAND_5GHZ || sband->band == NL80211_BAND_6GHZ)) { - sdata->vif.bss_conf.use_short_slot = true; + link->conf->use_short_slot = true; changed |= BSS_CHANGED_ERP_SLOT; } if (params->use_short_slot_time >= 0) { - sdata->vif.bss_conf.use_short_slot = - params->use_short_slot_time; + link->conf->use_short_slot = params->use_short_slot_time; changed |= BSS_CHANGED_ERP_SLOT; } if (params->basic_rates) { - ieee80211_parse_bitrates(sdata->vif.bss_conf.chandef.width, + ieee80211_parse_bitrates(link->conf->chandef.width, wiphy->bands[sband->band], params->basic_rates, params->basic_rates_len, - &sdata->vif.bss_conf.basic_rates); + &link->conf->basic_rates); changed |= BSS_CHANGED_BASIC_RATES; - ieee80211_check_rate_mask(&sdata->deflink); + ieee80211_check_rate_mask(link); } if (params->ap_isolate >= 0) { @@ -2606,30 +2609,29 @@ static int ieee80211_change_bss(struct wiphy *wiphy, } if (params->ht_opmode >= 0) { - sdata->vif.bss_conf.ht_operation_mode = - (u16) params->ht_opmode; + link->conf->ht_operation_mode = (u16)params->ht_opmode; changed |= BSS_CHANGED_HT; } if (params->p2p_ctwindow >= 0) { - sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow &= + link->conf->p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_CTWINDOW_MASK; - sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow |= + link->conf->p2p_noa_attr.oppps_ctwindow |= params->p2p_ctwindow & IEEE80211_P2P_OPPPS_CTWINDOW_MASK; changed |= BSS_CHANGED_P2P_PS; } if (params->p2p_opp_ps > 0) { - sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow |= + link->conf->p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } else if (params->p2p_opp_ps == 0) { - sdata->vif.bss_conf.p2p_noa_attr.oppps_ctwindow &= + link->conf->p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } - ieee80211_link_info_change_notify(sdata, &sdata->deflink, changed); + ieee80211_link_info_change_notify(sdata, link, changed); return 0; } @@ -4338,9 +4340,6 @@ static int ieee80211_get_txq_stats(struct wiphy *wiphy, struct ieee80211_sub_if_data *sdata; int ret = 0; - if (!local->ops->wake_tx_queue) - return 1; - spin_lock_bh(&local->fq.lock); rcu_read_lock(); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 78c7d60e8667..dfb9f55e2685 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -663,9 +663,7 @@ void debugfs_hw_add(struct ieee80211_local *local) DEBUGFS_ADD_MODE(force_tx_status, 0600); DEBUGFS_ADD_MODE(aql_enable, 0600); DEBUGFS_ADD(aql_pending); - - if (local->ops->wake_tx_queue) - DEBUGFS_ADD_MODE(aqm, 0600); + DEBUGFS_ADD_MODE(aqm, 0600); DEBUGFS_ADD_MODE(airtime_flags, 0600); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 5b014786fd2d..c87e1137e5da 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -677,8 +677,7 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz); DEBUGFS_ADD(hw_queues); - if (sdata->local->ops->wake_tx_queue && - sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && + if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && sdata->vif.type != NL80211_IFTYPE_NAN) DEBUGFS_ADD(aqm); } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index d3397c1248d3..7a3d7893e19d 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2021 Intel Corporation + * Copyright (C) 2018 - 2022 Intel Corporation */ #include <linux/debugfs.h> @@ -435,8 +435,29 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu } STA_OPS_RW(agg_status); -static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +/* link sta attributes */ +#define LINK_STA_OPS(name) \ +static const struct file_operations link_sta_ ##name## _ops = { \ + .read = link_sta_##name##_read, \ + .open = simple_open, \ + .llseek = generic_file_llseek, \ +} + +static ssize_t link_sta_addr_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct link_sta_info *link_sta = file->private_data; + u8 mac[3 * ETH_ALEN + 1]; + + snprintf(mac, sizeof(mac), "%pM\n", link_sta->pub->addr); + + return simple_read_from_buffer(userbuf, count, ppos, mac, 3 * ETH_ALEN); +} + +LINK_STA_OPS(addr); + +static ssize_t link_sta_ht_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) { #define PRINT_HT_CAP(_cond, _str) \ do { \ @@ -446,8 +467,8 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, char *buf, *p; int i; ssize_t bufsz = 512; - struct sta_info *sta = file->private_data; - struct ieee80211_sta_ht_cap *htc = &sta->sta.deflink.ht_cap; + struct link_sta_info *link_sta = file->private_data; + struct ieee80211_sta_ht_cap *htc = &link_sta->pub->ht_cap; ssize_t ret; buf = kzalloc(bufsz, GFP_KERNEL); @@ -524,14 +545,14 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, kfree(buf); return ret; } -STA_OPS(ht_capa); +LINK_STA_OPS(ht_capa); -static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +static ssize_t link_sta_vht_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) { char *buf, *p; - struct sta_info *sta = file->private_data; - struct ieee80211_sta_vht_cap *vhtc = &sta->sta.deflink.vht_cap; + struct link_sta_info *link_sta = file->private_data; + struct ieee80211_sta_vht_cap *vhtc = &link_sta->pub->vht_cap; ssize_t ret; ssize_t bufsz = 512; @@ -638,15 +659,15 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, kfree(buf); return ret; } -STA_OPS(vht_capa); +LINK_STA_OPS(vht_capa); -static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +static ssize_t link_sta_he_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) { char *buf, *p; size_t buf_sz = PAGE_SIZE; - struct sta_info *sta = file->private_data; - struct ieee80211_sta_he_cap *hec = &sta->sta.deflink.he_cap; + struct link_sta_info *link_sta = file->private_data; + struct ieee80211_sta_he_cap *hec = &link_sta->pub->he_cap; struct ieee80211_he_mcs_nss_supp *nss = &hec->he_mcs_nss_supp; u8 ppe_size; u8 *cap; @@ -1011,7 +1032,7 @@ out: kfree(buf); return ret; } -STA_OPS(he_capa); +LINK_STA_OPS(he_capa); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ @@ -1048,18 +1069,11 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(num_ps_buf_frames); DEBUGFS_ADD(last_seq_ctrl); DEBUGFS_ADD(agg_status); - DEBUGFS_ADD(ht_capa); - DEBUGFS_ADD(vht_capa); - DEBUGFS_ADD(he_capa); - - DEBUGFS_ADD_COUNTER(rx_duplicates, deflink.rx_stats.num_duplicates); - DEBUGFS_ADD_COUNTER(rx_fragments, deflink.rx_stats.fragments); + /* FIXME: Kept here as the statistics are only done on the deflink */ DEBUGFS_ADD_COUNTER(tx_filtered, deflink.status_stats.filtered); - if (local->ops->wake_tx_queue) { - DEBUGFS_ADD(aqm); - DEBUGFS_ADD(airtime); - } + DEBUGFS_ADD(aqm); + DEBUGFS_ADD(airtime); if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) @@ -1076,3 +1090,85 @@ void ieee80211_sta_debugfs_remove(struct sta_info *sta) debugfs_remove_recursive(sta->debugfs_dir); sta->debugfs_dir = NULL; } + +#undef DEBUGFS_ADD +#undef DEBUGFS_ADD_COUNTER + +#define DEBUGFS_ADD(name) \ + debugfs_create_file(#name, 0400, \ + link_sta->debugfs_dir, link_sta, &link_sta_ ##name## _ops) +#define DEBUGFS_ADD_COUNTER(name, field) \ + debugfs_create_ulong(#name, 0400, link_sta->debugfs_dir, &link_sta->field) + +void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta) +{ + if (WARN_ON(!link_sta->sta->debugfs_dir)) + return; + + /* For non-MLO, leave the files in the main directory. */ + if (link_sta->sta->sta.valid_links) { + char link_dir_name[10]; + + snprintf(link_dir_name, sizeof(link_dir_name), + "link-%d", link_sta->link_id); + + link_sta->debugfs_dir = + debugfs_create_dir(link_dir_name, + link_sta->sta->debugfs_dir); + + DEBUGFS_ADD(addr); + } else { + if (WARN_ON(link_sta != &link_sta->sta->deflink)) + return; + + link_sta->debugfs_dir = link_sta->sta->debugfs_dir; + } + + DEBUGFS_ADD(ht_capa); + DEBUGFS_ADD(vht_capa); + DEBUGFS_ADD(he_capa); + + DEBUGFS_ADD_COUNTER(rx_duplicates, rx_stats.num_duplicates); + DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); +} + +void ieee80211_link_sta_debugfs_remove(struct link_sta_info *link_sta) +{ + if (!link_sta->debugfs_dir || !link_sta->sta->debugfs_dir) { + link_sta->debugfs_dir = NULL; + return; + } + + if (link_sta->debugfs_dir == link_sta->sta->debugfs_dir) { + WARN_ON(link_sta != &link_sta->sta->deflink); + link_sta->sta->debugfs_dir = NULL; + return; + } + + debugfs_remove_recursive(link_sta->debugfs_dir); + link_sta->debugfs_dir = NULL; +} + +void ieee80211_link_sta_debugfs_drv_add(struct link_sta_info *link_sta) +{ + if (WARN_ON(!link_sta->debugfs_dir)) + return; + + drv_link_sta_add_debugfs(link_sta->sta->local, link_sta->sta->sdata, + link_sta->pub, link_sta->debugfs_dir); +} + +void ieee80211_link_sta_debugfs_drv_remove(struct link_sta_info *link_sta) +{ + if (!link_sta->debugfs_dir) + return; + + if (WARN_ON(link_sta->debugfs_dir == link_sta->sta->debugfs_dir)) + return; + + /* Recreate the directory excluding the driver data */ + debugfs_remove_recursive(link_sta->debugfs_dir); + link_sta->debugfs_dir = NULL; + + ieee80211_link_sta_debugfs_add(link_sta); +} diff --git a/net/mac80211/debugfs_sta.h b/net/mac80211/debugfs_sta.h index d2e7c27ad6d1..cde8148bdb18 100644 --- a/net/mac80211/debugfs_sta.h +++ b/net/mac80211/debugfs_sta.h @@ -7,9 +7,21 @@ #ifdef CONFIG_MAC80211_DEBUGFS void ieee80211_sta_debugfs_add(struct sta_info *sta); void ieee80211_sta_debugfs_remove(struct sta_info *sta); + +void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta); +void ieee80211_link_sta_debugfs_remove(struct link_sta_info *link_sta); + +void ieee80211_link_sta_debugfs_drv_add(struct link_sta_info *link_sta); +void ieee80211_link_sta_debugfs_drv_remove(struct link_sta_info *link_sta); #else static inline void ieee80211_sta_debugfs_add(struct sta_info *sta) {} static inline void ieee80211_sta_debugfs_remove(struct sta_info *sta) {} + +static inline void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta) {} +static inline void ieee80211_link_sta_debugfs_remove(struct link_sta_info *link_sta) {} + +static inline void ieee80211_link_sta_debugfs_drv_add(struct link_sta_info *link_sta) {} +static inline void ieee80211_link_sta_debugfs_drv_remove(struct link_sta_info *link_sta) {} #endif #endif /* __MAC80211_DEBUGFS_STA_H */ diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 5392ffa18270..d737db4e07e2 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -7,6 +7,7 @@ #include "ieee80211_i.h" #include "trace.h" #include "driver-ops.h" +#include "debugfs_sta.h" int drv_start(struct ieee80211_local *local) { @@ -497,6 +498,11 @@ int drv_change_sta_links(struct ieee80211_local *local, struct ieee80211_sta *sta, u16 old_links, u16 new_links) { + struct sta_info *info = container_of(sta, struct sta_info, sta); + struct link_sta_info *link_sta; + unsigned long links_to_add; + unsigned long links_to_rem; + unsigned int link_id; int ret = -EOPNOTSUPP; might_sleep(); @@ -510,11 +516,30 @@ int drv_change_sta_links(struct ieee80211_local *local, if (old_links == new_links) return 0; + links_to_add = ~old_links & new_links; + links_to_rem = old_links & ~new_links; + + for_each_set_bit(link_id, &links_to_rem, IEEE80211_MLD_MAX_NUM_LINKS) { + link_sta = rcu_dereference_protected(info->link[link_id], + lockdep_is_held(&local->sta_mtx)); + + ieee80211_link_sta_debugfs_drv_remove(link_sta); + } + trace_drv_change_sta_links(local, sdata, sta, old_links, new_links); if (local->ops->change_sta_links) ret = local->ops->change_sta_links(&local->hw, &sdata->vif, sta, old_links, new_links); trace_drv_return_int(local, ret); - return ret; + if (ret) + return ret; + + for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { + link_sta = rcu_dereference_protected(info->link[link_id], + lockdep_is_held(&local->sta_mtx)); + ieee80211_link_sta_debugfs_drv_add(link_sta); + } + + return 0; } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 81e40b0a3b16..809bad53e15b 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -480,6 +480,22 @@ static inline void drv_sta_add_debugfs(struct ieee80211_local *local, local->ops->sta_add_debugfs(&local->hw, &sdata->vif, sta, dir); } + +static inline void drv_link_sta_add_debugfs(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_link_sta *link_sta, + struct dentry *dir) +{ + might_sleep(); + + sdata = get_bss_sdata(sdata); + if (!check_sdata_in_driver(sdata)) + return; + + if (local->ops->link_sta_add_debugfs) + local->ops->link_sta_add_debugfs(&local->hw, &sdata->vif, + link_sta, dir); +} #endif static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a842f2e1c230..63ff0d2524b6 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -390,6 +390,7 @@ struct ieee80211_mgd_auth_data { bool done, waiting; bool peer_confirmed; bool timeout_started; + int link_id; u8 ap_addr[ETH_ALEN] __aligned(2); @@ -412,6 +413,8 @@ struct ieee80211_mgd_assoc_data { u8 *elems; /* pointing to inside ie[] below */ ieee80211_conn_flags_t conn_flags; + + u16 status; } link[IEEE80211_MLD_MAX_NUM_LINKS]; u8 ap_addr[ETH_ALEN] __aligned(2); @@ -1707,6 +1710,17 @@ struct ieee802_11_elems { u8 tx_pwr_env_num; u8 eht_cap_len; + /* mult-link element can be de-fragmented and thus u8 is not sufficient */ + size_t multi_link_len; + + /* + * store the per station profile pointer and length in case that the + * parsing also handled Multi-Link element parsing for a specific link + * ID. + */ + struct ieee80211_mle_per_sta_profile *prof; + size_t sta_prof_len; + /* whether a parse error occurred while retrieving these elements */ bool parse_error; @@ -2205,9 +2219,13 @@ static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, * represent a non-transmitting BSS in which case the data * for that non-transmitting BSS is returned * @link_id: the link ID to parse elements for, if a STA profile - * is present in the multi-link element, or -1 to ignore + * is present in the multi-link element, or -1 to ignore; + * note that the code currently assumes parsing an association + * (or re-association) response frame if this is given * @from_ap: frame is received from an AP (currently used only * for EHT capabilities parsing) + * @scratch_len: if non zero, specifies the requested length of the scratch + * buffer; otherwise, 'len' is used. */ struct ieee80211_elems_parse_params { const u8 *start; @@ -2218,6 +2236,7 @@ struct ieee80211_elems_parse_params { struct cfg80211_bss *bss; int link_id; bool from_ap; + size_t scratch_len; }; struct ieee802_11_elems * @@ -2288,7 +2307,6 @@ void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted); -void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue); void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); void ieee80211_add_pending_skbs(struct ieee80211_local *local, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index dd9ac1f7d2ea..7c4ce716c939 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -458,12 +458,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do if (cancel_scan) ieee80211_scan_cancel(local); - /* - * Stop TX on this interface first. - */ - if (!local->ops->wake_tx_queue && sdata->dev) - netif_tx_stop_all_queues(sdata->dev); - ieee80211_roc_purge(local, sdata); switch (sdata->vif.type) { @@ -811,13 +805,6 @@ static void ieee80211_uninit(struct net_device *dev) ieee80211_teardown_sdata(IEEE80211_DEV_TO_SUB_IF(dev)); } -static u16 ieee80211_netdev_select_queue(struct net_device *dev, - struct sk_buff *skb, - struct net_device *sb_dev) -{ - return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); -} - static void ieee80211_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { @@ -831,7 +818,6 @@ static const struct net_device_ops ieee80211_dataif_ops = { .ndo_start_xmit = ieee80211_subif_start_xmit, .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, - .ndo_select_queue = ieee80211_netdev_select_queue, .ndo_get_stats64 = ieee80211_get_stats64, }; @@ -939,7 +925,6 @@ static const struct net_device_ops ieee80211_dataif_8023_ops = { .ndo_start_xmit = ieee80211_subif_start_xmit_8023, .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, - .ndo_select_queue = ieee80211_netdev_select_queue, .ndo_get_stats64 = ieee80211_get_stats64, .ndo_fill_forward_path = ieee80211_netdev_fill_forward_path, }; @@ -1441,35 +1426,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) ieee80211_recalc_ps(local); - if (sdata->vif.type == NL80211_IFTYPE_MONITOR || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - local->ops->wake_tx_queue) { - /* XXX: for AP_VLAN, actually track AP queues */ - if (dev) - netif_tx_start_all_queues(dev); - } else if (dev) { - unsigned long flags; - int n_acs = IEEE80211_NUM_ACS; - int ac; - - if (local->hw.queues < IEEE80211_NUM_ACS) - n_acs = 1; - - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - if (sdata->vif.cab_queue == IEEE80211_INVAL_HW_QUEUE || - (local->queue_stop_reasons[sdata->vif.cab_queue] == 0 && - skb_queue_empty(&local->pending[sdata->vif.cab_queue]))) { - for (ac = 0; ac < n_acs; ac++) { - int ac_queue = sdata->vif.hw_queue[ac]; - - if (local->queue_stop_reasons[ac_queue] == 0 && - skb_queue_empty(&local->pending[ac_queue])) - netif_start_subqueue(dev, ac); - } - } - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - } - set_bit(SDATA_STATE_RUNNING, &sdata->state); return 0; @@ -1499,17 +1455,12 @@ static void ieee80211_if_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_NO_QUEUE; dev->netdev_ops = &ieee80211_dataif_ops; dev->needs_free_netdev = true; dev->priv_destructor = ieee80211_if_free; } -static void ieee80211_if_setup_no_queue(struct net_device *dev) -{ - ieee80211_if_setup(dev); - dev->priv_flags |= IFF_NO_QUEUE; -} - static void ieee80211_iface_process_skb(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) @@ -2094,9 +2045,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, struct net_device *ndev = NULL; struct ieee80211_sub_if_data *sdata = NULL; struct txq_info *txqi; - void (*if_setup)(struct net_device *dev); int ret, i; - int txqs = 1; ASSERT_RTNL(); @@ -2119,30 +2068,18 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sizeof(void *)); int txq_size = 0; - if (local->ops->wake_tx_queue && - type != NL80211_IFTYPE_AP_VLAN && + if (type != NL80211_IFTYPE_AP_VLAN && (type != NL80211_IFTYPE_MONITOR || (params->flags & MONITOR_FLAG_ACTIVE))) txq_size += sizeof(struct txq_info) + local->hw.txq_data_size; - if (local->ops->wake_tx_queue) { - if_setup = ieee80211_if_setup_no_queue; - } else { - if_setup = ieee80211_if_setup; - if (local->hw.queues >= IEEE80211_NUM_ACS) - txqs = IEEE80211_NUM_ACS; - } - ndev = alloc_netdev_mqs(size + txq_size, name, name_assign_type, - if_setup, txqs, 1); + ieee80211_if_setup, 1, 1); if (!ndev) return -ENOMEM; - if (!local->ops->wake_tx_queue && local->hw.wiphy->tx_queue_len) - ndev->tx_queue_len = local->hw.wiphy->tx_queue_len; - dev_net_set(ndev, wiphy_net(local->hw.wiphy)); ndev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); diff --git a/net/mac80211/link.c b/net/mac80211/link.c index e309708abae8..d1f5a9f7c647 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -357,6 +357,11 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; + + /* this is very temporary, but do it anyway */ + __ieee80211_sta_recalc_aggregates(sta, + old_active | active_links); + ret = drv_change_sta_links(local, sdata, &sta->sta, old_active, old_active | active_links); @@ -369,10 +374,22 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata) continue; + + __ieee80211_sta_recalc_aggregates(sta, active_links); + ret = drv_change_sta_links(local, sdata, &sta->sta, old_active | active_links, active_links); WARN_ON_ONCE(ret); + + /* + * Do it again, just in case - the driver might very + * well have called ieee80211_sta_recalc_aggregates() + * from there when filling in the new links, which + * would set it wrong since the vif's active links are + * not switched yet... + */ + __ieee80211_sta_recalc_aggregates(sta, active_links); } for_each_set_bit(link_id, &add, IEEE80211_MLD_MAX_NUM_LINKS) { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 46f3eddc2388..846528850612 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -630,7 +630,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, if (WARN_ON(!ops->tx || !ops->start || !ops->stop || !ops->config || !ops->add_interface || !ops->remove_interface || - !ops->configure_filter)) + !ops->configure_filter || !ops->wake_tx_queue)) return NULL; if (WARN_ON(ops->sta_state && (ops->sta_add || ops->sta_remove))) @@ -719,9 +719,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, if (!ops->set_key) wiphy->flags |= WIPHY_FLAG_IBSS_RSN; - if (ops->wake_tx_queue) - wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_TXQS); - + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_TXQS); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_RRM); wiphy->bss_priv_size = sizeof(struct ieee80211_bss); @@ -834,10 +832,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, atomic_set(&local->agg_queue_stop[i], 0); } tasklet_setup(&local->tx_pending_tasklet, ieee80211_tx_pending); - - if (ops->wake_tx_queue) - tasklet_setup(&local->wake_txqs_tasklet, ieee80211_wake_txqs); - + tasklet_setup(&local->wake_txqs_tasklet, ieee80211_wake_txqs); tasklet_setup(&local->tasklet, ieee80211_tasklet_handler); skb_queue_head_init(&local->skb_queue); @@ -1087,6 +1082,16 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) channels += sband->n_channels; + /* + * Due to the way the aggregation code handles this and it + * being an HT capability, we can't really support delayed + * BA in MLO (yet). + */ + if (WARN_ON(sband->ht_cap.ht_supported && + (sband->ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA) && + hw->wiphy->flags & WIPHY_FLAG_SUPPORTS_MLO)) + return -EINVAL; + if (max_bitrates < sband->n_bitrates) max_bitrates = sband->n_bitrates; supp_ht = supp_ht || sband->ht_cap.ht_supported; @@ -1155,6 +1160,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->int_scan_req) return -ENOMEM; + eth_broadcast_addr(local->int_scan_req->bssid); + for (band = 0; band < NUM_NL80211_BANDS; band++) { if (!local->hw.wiphy->bands[band]) continue; @@ -1439,8 +1446,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: - if (local->wiphy_ciphers_allocated) + if (local->wiphy_ciphers_allocated) { kfree(local->hw.wiphy->cipher_suites); + local->wiphy_ciphers_allocated = false; + } kfree(local->int_scan_req); return result; } @@ -1508,8 +1517,10 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) mutex_destroy(&local->iflist_mtx); mutex_destroy(&local->mtx); - if (local->wiphy_ciphers_allocated) + if (local->wiphy_ciphers_allocated) { kfree(local->hw.wiphy->cipher_suites); + local->wiphy_ciphers_allocated = false; + } idr_for_each(&local->ack_status_frames, ieee80211_free_ack_frame, NULL); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index acc1c299f1ae..69d5e1ec6ede 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -710,7 +710,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { - kfree_skb(skb); + ieee80211_free_txskb(&sdata->local->hw, skb); sdata->u.mesh.mshstats.dropped_frames_no_route++; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index d8484cd870de..a804e0220ed7 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2717,18 +2717,10 @@ static u32 ieee80211_link_set_associated(struct ieee80211_link_data *link, } if (link->u.mgd.have_beacon) { - /* - * If the AP is buggy we may get here with no DTIM period - * known, so assume it's 1 which is the only safe assumption - * in that case, although if the TIM IE is broken powersave - * probably just won't work at all. - */ - bss_conf->dtim_period = link->u.mgd.dtim_period ?: 1; bss_conf->beacon_rate = bss->beacon_rate; changed |= BSS_CHANGED_BEACON_INFO; } else { bss_conf->beacon_rate = NULL; - bss_conf->dtim_period = 0; } /* Tell the driver to monitor connection quality (if supported) */ @@ -2754,7 +2746,8 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; struct ieee80211_link_data *link; - if (!cbss) + if (!cbss || + assoc_data->link[link_id].status != WLAN_STATUS_SUCCESS) continue; link = sdata_dereference(sdata->link[link_id], sdata); @@ -2782,7 +2775,8 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link; struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; - if (!cbss) + if (!cbss || + assoc_data->link[link_id].status != WLAN_STATUS_SUCCESS) continue; link = sdata_dereference(sdata->link[link_id], sdata); @@ -3868,9 +3862,15 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband, } } -static bool ieee80211_twt_req_supported(const struct link_sta_info *link_sta, +static bool ieee80211_twt_req_supported(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + const struct link_sta_info *link_sta, const struct ieee802_11_elems *elems) { + const struct ieee80211_sta_he_cap *own_he_cap = + ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); + if (elems->ext_capab_len < 10) return false; @@ -3878,14 +3878,19 @@ static bool ieee80211_twt_req_supported(const struct link_sta_info *link_sta, return false; return link_sta->pub->he_cap.he_cap_elem.mac_cap_info[0] & - IEEE80211_HE_MAC_CAP0_TWT_RES; + IEEE80211_HE_MAC_CAP0_TWT_RES && + own_he_cap && + (own_he_cap->he_cap_elem.mac_cap_info[0] & + IEEE80211_HE_MAC_CAP0_TWT_REQ); } -static int ieee80211_recalc_twt_req(struct ieee80211_link_data *link, +static int ieee80211_recalc_twt_req(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct ieee80211_link_data *link, struct link_sta_info *link_sta, struct ieee802_11_elems *elems) { - bool twt = ieee80211_twt_req_supported(link_sta, elems); + bool twt = ieee80211_twt_req_supported(sdata, sband, link_sta, elems); if (link->conf->twt_requester != twt) { link->conf->twt_requester = twt; @@ -3923,11 +3928,12 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data; struct ieee80211_bss_conf *bss_conf = link->conf; struct ieee80211_local *local = sdata->local; + unsigned int link_id = link->link_id; struct ieee80211_elems_parse_params parse_params = { .start = elem_start, .len = elem_len, .bss = cbss, - .link_id = link == &sdata->deflink ? -1 : link->link_id, + .link_id = link_id == assoc_data->assoc_link_id ? -1 : link_id, .from_ap = true, }; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; @@ -3942,8 +3948,35 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, if (!elems) return false; - /* FIXME: use from STA profile element after parsing that */ - capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); + if (link_id == assoc_data->assoc_link_id) { + capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); + + /* + * we should not get to this flow unless the association was + * successful, so set the status directly to success + */ + assoc_data->link[link_id].status = WLAN_STATUS_SUCCESS; + } else if (!elems->prof) { + ret = false; + goto out; + } else { + const u8 *ptr = elems->prof->variable + + elems->prof->sta_info_len - 1; + + /* + * During parsing, we validated that these fields exist, + * otherwise elems->prof would have been set to NULL. + */ + capab_info = get_unaligned_le16(ptr); + assoc_data->link[link_id].status = get_unaligned_le16(ptr + 2); + + if (assoc_data->link[link_id].status != WLAN_STATUS_SUCCESS) { + link_info(link, "association response status code=%u\n", + assoc_data->link[link_id].status); + ret = true; + goto out; + } + } if (!is_s1g && !elems->supp_rates) { sdata_info(sdata, "no SuppRates element in AssocResp\n"); @@ -4099,7 +4132,8 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, else bss_conf->twt_protected = false; - *changed |= ieee80211_recalc_twt_req(link, link_sta, elems); + *changed |= ieee80211_recalc_twt_req(sdata, sband, link, + link_sta, elems); if (elems->eht_operation && elems->eht_cap && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_EHT)) { @@ -4864,6 +4898,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, unsigned int link_id; struct sta_info *sta; u64 changed[IEEE80211_MLD_MAX_NUM_LINKS] = {}; + u16 valid_links = 0; int err; mutex_lock(&sdata->local->sta_mtx); @@ -4876,8 +4911,6 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, goto out_err; if (sdata->vif.valid_links) { - u16 valid_links = 0; - for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { if (!assoc_data->link[link_id].bss) continue; @@ -4894,10 +4927,11 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; struct ieee80211_link_data *link; struct link_sta_info *link_sta; - if (!assoc_data->link[link_id].bss) + if (!cbss) continue; link = sdata_dereference(sdata->link[link_id], sdata); @@ -4906,28 +4940,36 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (sdata->vif.valid_links) link_info(link, - "local address %pM, AP link address %pM\n", + "local address %pM, AP link address %pM%s\n", link->conf->addr, - assoc_data->link[link_id].bss->bssid); + assoc_data->link[link_id].bss->bssid, + link_id == assoc_data->assoc_link_id ? + " (assoc)" : ""); link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&local->sta_mtx)); if (WARN_ON(!link_sta)) goto out_err; - if (link_id != assoc_data->assoc_link_id) { - struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; + if (!link->u.mgd.have_beacon) { const struct cfg80211_bss_ies *ies; rcu_read_lock(); - ies = rcu_dereference(cbss->ies); + ies = rcu_dereference(cbss->beacon_ies); + if (ies) + link->u.mgd.have_beacon = true; + else + ies = rcu_dereference(cbss->ies); ieee80211_get_dtim(ies, &link->conf->sync_dtim_count, &link->u.mgd.dtim_period); - link->conf->dtim_period = link->u.mgd.dtim_period ?: 1; link->conf->beacon_int = cbss->beacon_interval; rcu_read_unlock(); + } + + link->conf->dtim_period = link->u.mgd.dtim_period ?: 1; + if (link_id != assoc_data->assoc_link_id) { err = ieee80211_prep_channel(sdata, link, cbss, &link->u.mgd.conn_flags); if (err) { @@ -4947,6 +4989,12 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, &changed[link_id])) goto out_err; + if (assoc_data->link[link_id].status != WLAN_STATUS_SUCCESS) { + valid_links &= ~BIT(link_id); + ieee80211_sta_remove_link(sta, link_id); + continue; + } + if (link_id != assoc_data->assoc_link_id) { err = ieee80211_sta_activate_link(sta, link_id); if (err) @@ -4954,6 +5002,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } } + /* links might have changed due to rejected ones, set them again */ + ieee80211_vif_set_links(sdata, valid_links); + rate_control_rate_init(sta); if (ifmgd->flags & IEEE80211_STA_MFP_ENABLED) { @@ -5033,6 +5084,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, struct cfg80211_rx_assoc_resp resp = { .uapsd_queues = -1, }; + u8 ap_mld_addr[ETH_ALEN] __aligned(2); unsigned int link_id; sdata_assert_lock(sdata); @@ -5187,10 +5239,13 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; + if (!assoc_data->link[link_id].bss) continue; + resp.links[link_id].bss = assoc_data->link[link_id].bss; resp.links[link_id].addr = link->conf->addr; + resp.links[link_id].status = assoc_data->link[link_id].status; /* get uapsd queues configuration - same for all links */ resp.uapsd_queues = 0; @@ -5199,6 +5254,11 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, resp.uapsd_queues |= ieee80211_ac_to_qos_mask[ac]; } + if (sdata->vif.valid_links) { + ether_addr_copy(ap_mld_addr, sdata->vif.cfg.ap_addr); + resp.ap_mld_addr = ap_mld_addr; + } + ieee80211_destroy_assoc_data(sdata, status_code == WLAN_STATUS_SUCCESS ? ASSOC_SUCCESS : @@ -5208,8 +5268,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, resp.len = len; resp.req_ies = ifmgd->assoc_req_ies; resp.req_ies_len = ifmgd->assoc_req_ies_len; - if (sdata->vif.valid_links) - resp.ap_mld_addr = sdata->vif.cfg.ap_addr; cfg80211_rx_assoc_resp(sdata->dev, &resp); notify_driver: drv_mgd_complete_tx(sdata->local, sdata, &info); @@ -5432,6 +5490,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, struct ieee802_11_elems *elems; struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; struct link_sta_info *link_sta; struct sta_info *sta; @@ -5694,7 +5753,12 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, goto free; } - changed |= ieee80211_recalc_twt_req(link, link_sta, elems); + if (WARN_ON(!link->conf->chandef.chan)) + goto free; + + sband = local->hw.wiphy->bands[link->conf->chandef.chan->band]; + + changed |= ieee80211_recalc_twt_req(sdata, sband, link, link_sta, elems); if (ieee80211_config_bw(link, elems->ht_cap_elem, elems->vht_cap_elem, elems->ht_operation, @@ -6640,6 +6704,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, req->ap_mld_addr ?: req->bss->bssid, ETH_ALEN); auth_data->bss = req->bss; + auth_data->link_id = req->link_id; if (req->auth_data_len >= 4) { if (req->auth_type == NL80211_AUTHTYPE_SAE) { @@ -6658,7 +6723,8 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, * removal and re-addition of the STA entry in * ieee80211_prep_connection(). */ - cont_auth = ifmgd->auth_data && req->bss == ifmgd->auth_data->bss; + cont_auth = ifmgd->auth_data && req->bss == ifmgd->auth_data->bss && + ifmgd->auth_data->link_id == req->link_id; if (req->ie && req->ie_len) { memcpy(&auth_data->data[auth_data->data_len], @@ -6982,7 +7048,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, /* keep sta info, bssid if matching */ match = ether_addr_equal(ifmgd->auth_data->ap_addr, - assoc_data->ap_addr); + assoc_data->ap_addr) && + ifmgd->auth_data->link_id == req->link_id; ieee80211_destroy_auth_data(sdata, match); } diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 7f3f5f51081d..762346598338 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1963,9 +1963,6 @@ minstrel_ht_alloc(struct ieee80211_hw *hw) /* safe default, does not necessarily have to match hw properties */ mp->max_retry = 7; - if (hw->max_rates >= 4) - mp->has_mrr = true; - mp->hw = hw; mp->update_interval = HZ / 20; @@ -2036,7 +2033,7 @@ static void __init init_sample_table(void) memset(sample_table, 0xff, sizeof(sample_table)); for (col = 0; col < SAMPLE_COLUMNS; col++) { - prandom_bytes(rnd, sizeof(rnd)); + get_random_bytes(rnd, sizeof(rnd)); for (i = 0; i < MCS_GROUP_RATES; i++) { new_idx = (i + rnd[i]) % MCS_GROUP_RATES; while (sample_table[col][new_idx] != 0xff) diff --git a/net/mac80211/rc80211_minstrel_ht.h b/net/mac80211/rc80211_minstrel_ht.h index 1766ff0c78d3..4be0401f7721 100644 --- a/net/mac80211/rc80211_minstrel_ht.h +++ b/net/mac80211/rc80211_minstrel_ht.h @@ -74,7 +74,6 @@ struct minstrel_priv { struct ieee80211_hw *hw; - bool has_mrr; unsigned int cw_min; unsigned int cw_max; unsigned int max_retry; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index f99416d2e144..c28c6fbf786e 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1571,9 +1571,6 @@ static void sta_ps_start(struct sta_info *sta) ieee80211_clear_fast_xmit(sta); - if (!sta->sta.txq[0]) - return; - for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { struct ieee80211_txq *txq = sta->sta.txq[tid]; struct txq_info *txqi = to_txq_info(txq); diff --git a/net/mac80211/s1g.c b/net/mac80211/s1g.c index 8ca7d45d6daa..c1f964e9991c 100644 --- a/net/mac80211/s1g.c +++ b/net/mac80211/s1g.c @@ -112,6 +112,9 @@ ieee80211_s1g_rx_twt_setup(struct ieee80211_sub_if_data *sdata, goto out; } + /* TWT Information not supported yet */ + twt->control |= IEEE80211_TWT_CONTROL_RX_DISABLED; + drv_add_twt_setup(sdata->local, sdata, &sta->sta, twt); out: ieee80211_s1g_send_twt_setup(sdata, mgmt->sa, sdata->vif.addr, twt); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 0e8c4f48c36d..dc3cdee51e66 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -641,7 +641,7 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) { struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - u16 sn = get_random_u32(); + u16 sn = get_random_u16(); info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO; hdr->seq_ctrl = diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index cebfd148bb40..04e0f132b1d9 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -140,17 +140,15 @@ static void __cleanup_single_sta(struct sta_info *sta) atomic_dec(&ps->num_sta_ps); } - if (sta->sta.txq[0]) { - for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { - struct txq_info *txqi; + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + struct txq_info *txqi; - if (!sta->sta.txq[i]) - continue; + if (!sta->sta.txq[i]) + continue; - txqi = to_txq_info(sta->sta.txq[i]); + txqi = to_txq_info(sta->sta.txq[i]); - ieee80211_txq_purge(local, txqi); - } + ieee80211_txq_purge(local, txqi); } for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { @@ -366,6 +364,9 @@ static void sta_remove_link(struct sta_info *sta, unsigned int link_id, if (unhash) link_sta_info_hash_del(sta->local, link_sta); + if (test_sta_flag(sta, WLAN_STA_INSERTED)) + ieee80211_link_sta_debugfs_remove(link_sta); + if (link_sta != &sta->deflink) alloc = container_of(link_sta, typeof(*alloc), info); @@ -425,8 +426,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); - if (sta->sta.txq[0]) - kfree(to_txq_info(sta->sta.txq[0])); + kfree(to_txq_info(sta->sta.txq[0])); kfree(rcu_dereference_raw(sta->sta.rates)); #ifdef CONFIG_MAC80211_MESH kfree(sta->mesh); @@ -511,6 +511,7 @@ static void sta_info_add_link(struct sta_info *sta, link_info->sta = sta; link_info->link_id = link_id; link_info->pub = link_sta; + link_info->pub->sta = &sta->sta; link_sta->link_id = link_id; rcu_assign_pointer(sta->link[link_id], link_info); rcu_assign_pointer(sta->sta.link[link_id], link_sta); @@ -527,6 +528,8 @@ __sta_info_alloc(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_hw *hw = &local->hw; struct sta_info *sta; + void *txq_data; + int size; int i; sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp); @@ -596,21 +599,18 @@ __sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->last_connected = ktime_get_seconds(); - if (local->ops->wake_tx_queue) { - void *txq_data; - int size = sizeof(struct txq_info) + - ALIGN(hw->txq_data_size, sizeof(void *)); + size = sizeof(struct txq_info) + + ALIGN(hw->txq_data_size, sizeof(void *)); - txq_data = kcalloc(ARRAY_SIZE(sta->sta.txq), size, gfp); - if (!txq_data) - goto free; + txq_data = kcalloc(ARRAY_SIZE(sta->sta.txq), size, gfp); + if (!txq_data) + goto free; - for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { - struct txq_info *txq = txq_data + i * size; + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + struct txq_info *txq = txq_data + i * size; - /* might not do anything for the bufferable MMPDU TXQ */ - ieee80211_txq_init(sdata, sta, txq, i); - } + /* might not do anything for the (bufferable) MMPDU TXQ */ + ieee80211_txq_init(sdata, sta, txq, i); } if (sta_prepare_rate_control(local, sta, gfp)) @@ -684,8 +684,7 @@ __sta_info_alloc(struct ieee80211_sub_if_data *sdata, return sta; free_txq: - if (sta->sta.txq[0]) - kfree(to_txq_info(sta->sta.txq[0])); + kfree(to_txq_info(sta->sta.txq[0])); free: sta_info_free_link(&sta->deflink); #ifdef CONFIG_MAC80211_MESH @@ -874,6 +873,26 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) ieee80211_sta_debugfs_add(sta); rate_control_add_sta_debugfs(sta); + if (sta->sta.valid_links) { + int i; + + for (i = 0; i < ARRAY_SIZE(sta->link); i++) { + struct link_sta_info *link_sta; + + link_sta = rcu_dereference_protected(sta->link[i], + lockdep_is_held(&local->sta_mtx)); + + if (!link_sta) + continue; + + ieee80211_link_sta_debugfs_add(link_sta); + if (sdata->vif.active_links & BIT(i)) + ieee80211_link_sta_debugfs_drv_add(link_sta); + } + } else { + ieee80211_link_sta_debugfs_add(&sta->deflink); + ieee80211_link_sta_debugfs_drv_add(&sta->deflink); + } sinfo->generation = local->sta_generation; cfg80211_new_sta(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); @@ -1958,9 +1977,6 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, * TIM recalculation. */ - if (!sta->sta.txq[0]) - return; - for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { if (!sta->sta.txq[tid] || !(driver_release_tids & BIT(tid)) || @@ -2127,22 +2143,30 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, } EXPORT_SYMBOL(ieee80211_sta_register_airtime); -void ieee80211_sta_recalc_aggregates(struct ieee80211_sta *pubsta) +void __ieee80211_sta_recalc_aggregates(struct sta_info *sta, u16 active_links) { - struct sta_info *sta = container_of(pubsta, struct sta_info, sta); - struct ieee80211_link_sta *link_sta; - int link_id, i; bool first = true; + int link_id; - if (!pubsta->valid_links || !pubsta->mlo) { - pubsta->cur = &pubsta->deflink.agg; + if (!sta->sta.valid_links || !sta->sta.mlo) { + sta->sta.cur = &sta->sta.deflink.agg; return; } rcu_read_lock(); - for_each_sta_active_link(&sta->sdata->vif, pubsta, link_sta, link_id) { + for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) { + struct ieee80211_link_sta *link_sta; + int i; + + if (!(active_links & BIT(link_id))) + continue; + + link_sta = rcu_dereference(sta->sta.link[link_id]); + if (!link_sta) + continue; + if (first) { - sta->cur = pubsta->deflink.agg; + sta->cur = sta->sta.deflink.agg; first = false; continue; } @@ -2161,7 +2185,14 @@ void ieee80211_sta_recalc_aggregates(struct ieee80211_sta *pubsta) } rcu_read_unlock(); - pubsta->cur = &sta->cur; + sta->sta.cur = &sta->cur; +} + +void ieee80211_sta_recalc_aggregates(struct ieee80211_sta *pubsta) +{ + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + + __ieee80211_sta_recalc_aggregates(sta, sta->sdata->vif.active_links); } EXPORT_SYMBOL(ieee80211_sta_recalc_aggregates); @@ -2396,9 +2427,9 @@ static inline u64 sta_get_tidstats_msdu(struct ieee80211_sta_rx_stats *rxstats, u64 value; do { - start = u64_stats_fetch_begin_irq(&rxstats->syncp); + start = u64_stats_fetch_begin(&rxstats->syncp); value = rxstats->msdu[tid]; - } while (u64_stats_fetch_retry_irq(&rxstats->syncp, start)); + } while (u64_stats_fetch_retry(&rxstats->syncp, start)); return value; } @@ -2445,7 +2476,7 @@ static void sta_set_tidstats(struct sta_info *sta, tidstats->tx_msdu_failed = sta->deflink.status_stats.msdu_failed[tid]; } - if (local->ops->wake_tx_queue && tid < IEEE80211_NUM_TIDS) { + if (tid < IEEE80211_NUM_TIDS) { spin_lock_bh(&local->fq.lock); rcu_read_lock(); @@ -2464,9 +2495,9 @@ static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats) u64 value; do { - start = u64_stats_fetch_begin_irq(&rxstats->syncp); + start = u64_stats_fetch_begin(&rxstats->syncp); value = rxstats->bytes; - } while (u64_stats_fetch_retry_irq(&rxstats->syncp, start)); + } while (u64_stats_fetch_retry(&rxstats->syncp, start)); return value; } @@ -2773,9 +2804,6 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta) static void sta_update_codel_params(struct sta_info *sta, u32 thr) { - if (!sta->sdata->local->ops->wake_tx_queue) - return; - if (thr && thr < STA_SLOW_THRESHOLD * sta->local->num_sta) { sta->cparams.target = MS2TIME(50); sta->cparams.interval = MS2TIME(300); @@ -2823,6 +2851,8 @@ int ieee80211_sta_allocate_link(struct sta_info *sta, unsigned int link_id) sta_info_add_link(sta, link_id, &alloc->info, &alloc->sta); + ieee80211_link_sta_debugfs_add(&alloc->info); + return 0; } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 2517ea714dc4..69820b551668 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -513,6 +513,7 @@ struct ieee80211_fragment_cache { * @status_stats.avg_ack_signal: average ACK signal * @cur_max_bandwidth: maximum bandwidth to use for TX to the station, * taken from HT/VHT capabilities or VHT operating mode notification + * @debugfs_dir: debug filesystem directory dentry * @pub: public (driver visible) link STA data * TODO Move other link params from sta_info as required for MLD operation */ @@ -560,6 +561,10 @@ struct link_sta_info { enum ieee80211_sta_rx_bandwidth cur_max_bandwidth; +#ifdef CONFIG_MAC80211_DEBUGFS + struct dentry *debugfs_dir; +#endif + struct ieee80211_link_sta *pub; }; @@ -922,6 +927,8 @@ void ieee80211_sta_set_max_amsdu_subframes(struct sta_info *sta, const u8 *ext_capab, unsigned int ext_capab_len); +void __ieee80211_sta_recalc_aggregates(struct sta_info *sta, u16 active_links); + enum sta_stats_type { STA_STATS_RATE_TYPE_INVALID = 0, STA_STATS_RATE_TYPE_LEGACY, diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index f4b4d25eef95..b255f3b5bf01 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1016,7 +1016,6 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, skb->priority = 256 + 5; break; } - skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, skb)); /* * Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress. diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a364148149f9..165ac0711d71 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1599,9 +1599,6 @@ int ieee80211_txq_setup_flows(struct ieee80211_local *local) bool supp_vht = false; enum nl80211_band band; - if (!local->ops->wake_tx_queue) - return 0; - ret = fq_init(fq, 4096); if (ret) return ret; @@ -1649,9 +1646,6 @@ void ieee80211_txq_teardown_flows(struct ieee80211_local *local) { struct fq *fq = &local->fq; - if (!local->ops->wake_tx_queue) - return; - kfree(local->cvars); local->cvars = NULL; @@ -1668,8 +1662,7 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, struct ieee80211_vif *vif; struct txq_info *txqi; - if (!local->ops->wake_tx_queue || - sdata->vif.type == NL80211_IFTYPE_MONITOR) + if (sdata->vif.type == NL80211_IFTYPE_MONITOR) return false; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) @@ -2973,7 +2966,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, if (pre_conf_link_id != link_id && link_id != IEEE80211_LINK_UNSPECIFIED) { -#ifdef CPTCFG_MAC80211_VERBOSE_DEBUG +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG net_info_ratelimited("%s: dropped frame to %pM with bad link ID request (%d vs. %d)\n", sdata->name, hdr.addr1, pre_conf_link_id, link_id); @@ -4184,12 +4177,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (IS_ERR(sta)) sta = NULL; - if (local->ops->wake_tx_queue) { - u16 queue = __ieee80211_select_queue(sdata, sta, skb); - skb_set_queue_mapping(skb, queue); - skb_get_hash(skb); - } - + skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, sta, skb)); ieee80211_aggr_check(sdata, sta, skb); sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); @@ -4418,6 +4406,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, if (likely(!is_multicast_ether_addr(eth->h_dest))) goto normal; + if (unlikely(!ieee80211_sdata_running(sdata))) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + if (unlikely(ieee80211_multicast_to_unicast(skb, dev))) { struct sk_buff_head queue; @@ -4495,11 +4488,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, struct tid_ampdu_tx *tid_tx; u8 tid; - if (local->ops->wake_tx_queue) { - u16 queue = __ieee80211_select_queue(sdata, sta, skb); - skb_set_queue_mapping(skb, queue); - skb_get_hash(skb); - } + skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, sta, skb)); if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning)) && test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) @@ -4753,9 +4742,6 @@ void ieee80211_tx_pending(struct tasklet_struct *t) if (!txok) break; } - - if (skb_queue_empty(&local->pending[i])) - ieee80211_propagate_queue_wake(local, i); } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); @@ -5948,10 +5934,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, } if (!IS_ERR(sta)) { - u16 queue = __ieee80211_select_queue(sdata, sta, skb); + u16 queue = ieee80211_select_queue(sdata, sta, skb); skb_set_queue_mapping(skb, queue); - skb_get_hash(skb); /* * for MLO STA, the SA should be the AP MLD address, but diff --git a/net/mac80211/util.c b/net/mac80211/util.c index b512cb37aafb..6f5407038459 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -288,6 +288,52 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_ctstoself_duration); +static void wake_tx_push_queue(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_txq *queue) +{ + int q = sdata->vif.hw_queue[queue->ac]; + struct ieee80211_tx_control control = { + .sta = queue->sta, + }; + struct sk_buff *skb; + unsigned long flags; + bool q_stopped; + + while (1) { + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + q_stopped = local->queue_stop_reasons[q]; + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + if (q_stopped) + break; + + skb = ieee80211_tx_dequeue(&local->hw, queue); + if (!skb) + break; + + drv_tx(local, &control, skb); + } +} + +/* wake_tx_queue handler for driver not implementing a custom one*/ +void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif); + struct ieee80211_txq *queue; + + /* Use ieee80211_next_txq() for airtime fairness accounting */ + ieee80211_txq_schedule_start(hw, txq->ac); + while ((queue = ieee80211_next_txq(hw, txq->ac))) { + wake_tx_push_queue(local, sdata, queue); + ieee80211_return_txq(hw, queue, false); + } + ieee80211_txq_schedule_end(hw, txq->ac); +} +EXPORT_SYMBOL(ieee80211_handle_wake_tx_queue); + static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) { struct ieee80211_local *local = sdata->local; @@ -400,39 +446,6 @@ void ieee80211_wake_txqs(struct tasklet_struct *t) spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } -void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) -{ - struct ieee80211_sub_if_data *sdata; - int n_acs = IEEE80211_NUM_ACS; - - if (local->ops->wake_tx_queue) - return; - - if (local->hw.queues < IEEE80211_NUM_ACS) - n_acs = 1; - - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - int ac; - - if (!sdata->dev) - continue; - - if (sdata->vif.cab_queue != IEEE80211_INVAL_HW_QUEUE && - local->queue_stop_reasons[sdata->vif.cab_queue] != 0) - continue; - - for (ac = 0; ac < n_acs; ac++) { - int ac_queue = sdata->vif.hw_queue[ac]; - - if (ac_queue == queue || - (sdata->vif.cab_queue == queue && - local->queue_stop_reasons[ac_queue] == 0 && - skb_queue_empty(&local->pending[ac_queue]))) - netif_wake_subqueue(sdata->dev, ac); - } - } -} - static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted, @@ -463,11 +476,7 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, /* someone still has this queue stopped */ return; - if (skb_queue_empty(&local->pending[queue])) { - rcu_read_lock(); - ieee80211_propagate_queue_wake(local, queue); - rcu_read_unlock(); - } else + if (!skb_queue_empty(&local->pending[queue])) tasklet_schedule(&local->tx_pending_tasklet); /* @@ -477,12 +486,10 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, * release someone's lock, but it is fine because all the callers of * __ieee80211_wake_queue call it right before releasing the lock. */ - if (local->ops->wake_tx_queue) { - if (reason == IEEE80211_QUEUE_STOP_REASON_DRIVER) - tasklet_schedule(&local->wake_txqs_tasklet); - else - _ieee80211_wake_txqs(local, flags); - } + if (reason == IEEE80211_QUEUE_STOP_REASON_DRIVER) + tasklet_schedule(&local->wake_txqs_tasklet); + else + _ieee80211_wake_txqs(local, flags); } void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, @@ -539,10 +546,6 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, for (ac = 0; ac < n_acs; ac++) { if (sdata->vif.hw_queue[ac] == queue || sdata->vif.cab_queue == queue) { - if (!local->ops->wake_tx_queue) { - netif_stop_subqueue(sdata->dev, ac); - continue; - } spin_lock(&local->fq.lock); sdata->vif.txqs_stopped[ac] = true; spin_unlock(&local->fq.lock); @@ -1026,8 +1029,10 @@ ieee80211_parse_extension_element(u32 *crc, elems->eht_operation = data; break; case WLAN_EID_EXT_EHT_MULTI_LINK: - if (ieee80211_mle_size_ok(data, len)) + if (ieee80211_mle_size_ok(data, len)) { elems->multi_link = (void *)data; + elems->multi_link_len = len; + } break; } } @@ -1499,6 +1504,145 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, return found ? profile_len : 0; } +static void ieee80211_defragment_element(struct ieee802_11_elems *elems, + void **elem_ptr, size_t *len, + size_t total_len, u8 frag_id) +{ + u8 *data = *elem_ptr, *pos, *start; + const struct element *elem; + + /* + * Since 'data' points to the data of the element, not the element + * itself, allow 254 in case it was an extended element where the + * extended ID isn't part of the data we see here and thus not part of + * 'len' either. + */ + if (!data || (*len != 254 && *len != 255)) + return; + + start = elems->scratch_pos; + + if (WARN_ON(*len > (elems->scratch + elems->scratch_len - + elems->scratch_pos))) + return; + + memcpy(elems->scratch_pos, data, *len); + elems->scratch_pos += *len; + + pos = data + *len; + total_len -= *len; + for_each_element(elem, pos, total_len) { + if (elem->id != frag_id) + break; + + if (WARN_ON(elem->datalen > + (elems->scratch + elems->scratch_len - + elems->scratch_pos))) + return; + + memcpy(elems->scratch_pos, elem->data, elem->datalen); + elems->scratch_pos += elem->datalen; + + *len += elem->datalen; + } + + *elem_ptr = start; +} + +static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems, + u8 link_id) +{ + const struct ieee80211_multi_link_elem *ml = elems->multi_link; + size_t ml_len = elems->multi_link_len; + const struct element *sub; + + if (!ml || !ml_len) + return; + + if (le16_get_bits(ml->control, IEEE80211_ML_CONTROL_TYPE) != + IEEE80211_ML_CONTROL_TYPE_BASIC) + return; + + for_each_mle_subelement(sub, (u8 *)ml, ml_len) { + struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; + u16 control; + + if (sub->id != IEEE80211_MLE_SUBELEM_PER_STA_PROFILE) + continue; + + if (!ieee80211_mle_sta_prof_size_ok(sub->data, sub->datalen)) + return; + + control = le16_to_cpu(prof->control); + + if (link_id != u16_get_bits(control, + IEEE80211_MLE_STA_CONTROL_LINK_ID)) + continue; + + if (!(control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE)) + return; + + elems->prof = prof; + elems->sta_prof_len = sub->datalen; + + /* the sub element can be fragmented */ + ieee80211_defragment_element(elems, (void **)&elems->prof, + &elems->sta_prof_len, + ml_len - (sub->data - (u8 *)ml), + IEEE80211_MLE_SUBELEM_FRAGMENT); + return; + } +} + +static void ieee80211_mle_parse_link(struct ieee802_11_elems *elems, + struct ieee80211_elems_parse_params *params) +{ + struct ieee80211_mle_per_sta_profile *prof; + struct ieee80211_elems_parse_params sub = { + .action = params->action, + .from_ap = params->from_ap, + .link_id = -1, + }; + const struct element *non_inherit = NULL; + const u8 *end; + + if (params->link_id == -1) + return; + + ieee80211_defragment_element(elems, (void **)&elems->multi_link, + &elems->multi_link_len, + elems->total_len - ((u8 *)elems->multi_link - + elems->ie_start), + WLAN_EID_FRAGMENT); + + ieee80211_mle_get_sta_prof(elems, params->link_id); + prof = elems->prof; + + if (!prof) + return; + + /* check if we have the 4 bytes for the fixed part in assoc response */ + if (elems->sta_prof_len < sizeof(*prof) + prof->sta_info_len - 1 + 4) { + elems->prof = NULL; + elems->sta_prof_len = 0; + return; + } + + /* + * Skip the capability information and the status code that are expected + * as part of the station profile in association response frames. Note + * the -1 is because the 'sta_info_len' is accounted to as part of the + * per-STA profile, but not part of the 'u8 variable[]' portion. + */ + sub.start = prof->variable + prof->sta_info_len - 1 + 4; + end = (const u8 *)prof + elems->sta_prof_len; + sub.len = end - sub.start; + + non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + sub.start, sub.len); + _ieee802_11_parse_elems_full(&sub, elems, non_inherit); +} + struct ieee802_11_elems * ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) { @@ -1506,7 +1650,7 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) const struct element *non_inherit = NULL; u8 *nontransmitted_profile; int nontransmitted_profile_len = 0; - size_t scratch_len = params->len; + size_t scratch_len = params->scratch_len ?: 3 * params->len; elems = kzalloc(sizeof(*elems) + scratch_len, GFP_ATOMIC); if (!elems) @@ -1541,6 +1685,8 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) _ieee802_11_parse_elems_full(&sub, elems, NULL); } + ieee80211_mle_parse_link(elems, params); + if (elems->tim && !elems->parse_error) { const struct ieee80211_tim_ie *tim_ie = elems->tim; diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index ecc1de2e68a5..a12c63638680 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -122,6 +122,9 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); u8 *p; + /* Ensure hash is set prior to potential SW encryption */ + skb_get_hash(skb); + if ((info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER) || local->hw.queues < IEEE80211_NUM_ACS) return 0; @@ -141,12 +144,15 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, return ieee80211_downgrade_queue(sdata, NULL, skb); } -u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, struct sk_buff *skb) +u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, struct sk_buff *skb) { struct mac80211_qos_map *qos_map; bool qos; + /* Ensure hash is set prior to potential SW encryption */ + skb_get_hash(skb); + /* all mesh/ocb stations are required to support WME */ if (sta && (sdata->vif.type == NL80211_IFTYPE_MESH_POINT || sdata->vif.type == NL80211_IFTYPE_OCB)) @@ -176,59 +182,6 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, return ieee80211_downgrade_queue(sdata, sta, skb); } - -/* Indicate which queue to use. */ -u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb) -{ - struct ieee80211_local *local = sdata->local; - struct sta_info *sta = NULL; - const u8 *ra = NULL; - u16 ret; - - /* when using iTXQ, we can do this later */ - if (local->ops->wake_tx_queue) - return 0; - - if (local->hw.queues < IEEE80211_NUM_ACS || skb->len < 6) { - skb->priority = 0; /* required for correct WPA/11i MIC */ - return 0; - } - - rcu_read_lock(); - switch (sdata->vif.type) { - case NL80211_IFTYPE_AP_VLAN: - sta = rcu_dereference(sdata->u.vlan.sta); - if (sta) - break; - fallthrough; - case NL80211_IFTYPE_AP: - ra = skb->data; - break; - case NL80211_IFTYPE_STATION: - /* might be a TDLS station */ - sta = sta_info_get(sdata, skb->data); - if (sta) - break; - - ra = sdata->deflink.u.mgd.bssid; - break; - case NL80211_IFTYPE_ADHOC: - ra = skb->data; - break; - default: - break; - } - - if (!sta && ra && !is_multicast_ether_addr(ra)) - sta = sta_info_get(sdata, ra); - - ret = __ieee80211_select_queue(sdata, sta, skb); - - rcu_read_unlock(); - return ret; -} - /** * ieee80211_set_qos_hdr - Fill in the QoS header if there is one. * diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h index 2e3dec0b6087..81f0039527a9 100644 --- a/net/mac80211/wme.h +++ b/net/mac80211/wme.h @@ -13,10 +13,8 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct ieee80211_hdr *hdr); -u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, struct sk_buff *skb); u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb); + struct sta_info *sta, struct sk_buff *skb); void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 1e4a9f74ed43..dc2d918fac68 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -46,7 +46,7 @@ static int ieee802154_suspend(struct wpan_phy *wpan_phy) if (!local->open_count) goto suspend; - ieee802154_stop_queue(&local->hw); + ieee802154_sync_and_hold_queue(local); synchronize_net(); /* stop hardware - this must stop RX */ @@ -67,12 +67,12 @@ static int ieee802154_resume(struct wpan_phy *wpan_phy) goto wake_up; /* restart hardware */ - ret = drv_start(local); + ret = drv_start(local, local->phy->filtering, &local->addr_filt); if (ret) return ret; wake_up: - ieee802154_wake_queue(&local->hw); + ieee802154_release_queue(local); local->suspended = false; return 0; } diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h index d23f0db98015..a7af3f0ddb3e 100644 --- a/net/mac802154/driver-ops.h +++ b/net/mac802154/driver-ops.h @@ -24,203 +24,290 @@ drv_xmit_sync(struct ieee802154_local *local, struct sk_buff *skb) return local->ops->xmit_sync(&local->hw, skb); } -static inline int drv_start(struct ieee802154_local *local) +static inline int drv_set_pan_id(struct ieee802154_local *local, __le16 pan_id) { + struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); - trace_802154_drv_start(local); - local->started = true; - smp_mb(); - ret = local->ops->start(&local->hw); + if (!local->ops->set_hw_addr_filt) { + WARN_ON(1); + return -EOPNOTSUPP; + } + + filt.pan_id = pan_id; + + trace_802154_drv_set_pan_id(local, pan_id); + ret = local->ops->set_hw_addr_filt(&local->hw, &filt, + IEEE802154_AFILT_PANID_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } -static inline void drv_stop(struct ieee802154_local *local) +static inline int +drv_set_extended_addr(struct ieee802154_local *local, __le64 extended_addr) { - might_sleep(); + struct ieee802154_hw_addr_filt filt; + int ret; - trace_802154_drv_stop(local); - local->ops->stop(&local->hw); - trace_802154_drv_return_void(local); + might_sleep(); - /* sync away all work on the tasklet before clearing started */ - tasklet_disable(&local->tasklet); - tasklet_enable(&local->tasklet); + if (!local->ops->set_hw_addr_filt) { + WARN_ON(1); + return -EOPNOTSUPP; + } - barrier(); + filt.ieee_addr = extended_addr; - local->started = false; + trace_802154_drv_set_extended_addr(local, extended_addr); + ret = local->ops->set_hw_addr_filt(&local->hw, &filt, + IEEE802154_AFILT_IEEEADDR_CHANGED); + trace_802154_drv_return_int(local, ret); + return ret; } static inline int -drv_set_channel(struct ieee802154_local *local, u8 page, u8 channel) +drv_set_short_addr(struct ieee802154_local *local, __le16 short_addr) { + struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); - trace_802154_drv_set_channel(local, page, channel); - ret = local->ops->set_channel(&local->hw, page, channel); + if (!local->ops->set_hw_addr_filt) { + WARN_ON(1); + return -EOPNOTSUPP; + } + + filt.short_addr = short_addr; + + trace_802154_drv_set_short_addr(local, short_addr); + ret = local->ops->set_hw_addr_filt(&local->hw, &filt, + IEEE802154_AFILT_SADDR_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } -static inline int drv_set_tx_power(struct ieee802154_local *local, s32 mbm) +static inline int +drv_set_pan_coord(struct ieee802154_local *local, bool is_coord) { + struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); - if (!local->ops->set_txpower) { + if (!local->ops->set_hw_addr_filt) { WARN_ON(1); return -EOPNOTSUPP; } - trace_802154_drv_set_tx_power(local, mbm); - ret = local->ops->set_txpower(&local->hw, mbm); + filt.pan_coord = is_coord; + + trace_802154_drv_set_pan_coord(local, is_coord); + ret = local->ops->set_hw_addr_filt(&local->hw, &filt, + IEEE802154_AFILT_PANC_CHANGED); trace_802154_drv_return_int(local, ret); return ret; } -static inline int drv_set_cca_mode(struct ieee802154_local *local, - const struct wpan_phy_cca *cca) +static inline int +drv_set_promiscuous_mode(struct ieee802154_local *local, bool on) { int ret; might_sleep(); - if (!local->ops->set_cca_mode) { + if (!local->ops->set_promiscuous_mode) { WARN_ON(1); return -EOPNOTSUPP; } - trace_802154_drv_set_cca_mode(local, cca); - ret = local->ops->set_cca_mode(&local->hw, cca); + trace_802154_drv_set_promiscuous_mode(local, on); + ret = local->ops->set_promiscuous_mode(&local->hw, on); trace_802154_drv_return_int(local, ret); return ret; } -static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode) +static inline int drv_start(struct ieee802154_local *local, + enum ieee802154_filtering_level level, + const struct ieee802154_hw_addr_filt *addr_filt) { int ret; might_sleep(); - if (!local->ops->set_lbt) { + /* setup receive mode parameters e.g. address mode */ + if (local->hw.flags & IEEE802154_HW_AFILT) { + ret = drv_set_pan_id(local, addr_filt->pan_id); + if (ret < 0) + return ret; + + ret = drv_set_short_addr(local, addr_filt->short_addr); + if (ret < 0) + return ret; + + ret = drv_set_extended_addr(local, addr_filt->ieee_addr); + if (ret < 0) + return ret; + } + + switch (level) { + case IEEE802154_FILTERING_NONE: + fallthrough; + case IEEE802154_FILTERING_1_FCS: + fallthrough; + case IEEE802154_FILTERING_2_PROMISCUOUS: + /* TODO: Requires a different receive mode setup e.g. + * at86rf233 hardware. + */ + fallthrough; + case IEEE802154_FILTERING_3_SCAN: + if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { + ret = drv_set_promiscuous_mode(local, true); + if (ret < 0) + return ret; + } else { + return -EOPNOTSUPP; + } + + /* In practice other filtering levels can be requested, but as + * for now most hardware/drivers only support + * IEEE802154_FILTERING_NONE, we fallback to this actual + * filtering level in hardware and make our own additional + * filtering in mac802154 receive path. + * + * TODO: Move this logic to the device drivers as hardware may + * support more higher level filters. Hardware may also require + * a different order how register are set, which could currently + * be buggy, so all received parameters need to be moved to the + * start() callback and let the driver go into the mode before + * it will turn on receive handling. + */ + local->phy->filtering = IEEE802154_FILTERING_NONE; + break; + case IEEE802154_FILTERING_4_FRAME_FIELDS: + /* Do not error out if IEEE802154_HW_PROMISCUOUS because we + * expect the hardware to operate at the level + * IEEE802154_FILTERING_4_FRAME_FIELDS anyway. + */ + if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { + ret = drv_set_promiscuous_mode(local, false); + if (ret < 0) + return ret; + } + + local->phy->filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; + break; + default: WARN_ON(1); - return -EOPNOTSUPP; + return -EINVAL; } - trace_802154_drv_set_lbt_mode(local, mode); - ret = local->ops->set_lbt(&local->hw, mode); + trace_802154_drv_start(local); + local->started = true; + smp_mb(); + ret = local->ops->start(&local->hw); trace_802154_drv_return_int(local, ret); return ret; } +static inline void drv_stop(struct ieee802154_local *local) +{ + might_sleep(); + + trace_802154_drv_stop(local); + local->ops->stop(&local->hw); + trace_802154_drv_return_void(local); + + /* sync away all work on the tasklet before clearing started */ + tasklet_disable(&local->tasklet); + tasklet_enable(&local->tasklet); + + barrier(); + + local->started = false; +} + static inline int -drv_set_cca_ed_level(struct ieee802154_local *local, s32 mbm) +drv_set_channel(struct ieee802154_local *local, u8 page, u8 channel) { int ret; might_sleep(); - if (!local->ops->set_cca_ed_level) { - WARN_ON(1); - return -EOPNOTSUPP; - } - - trace_802154_drv_set_cca_ed_level(local, mbm); - ret = local->ops->set_cca_ed_level(&local->hw, mbm); + trace_802154_drv_set_channel(local, page, channel); + ret = local->ops->set_channel(&local->hw, page, channel); trace_802154_drv_return_int(local, ret); return ret; } -static inline int drv_set_pan_id(struct ieee802154_local *local, __le16 pan_id) +static inline int drv_set_tx_power(struct ieee802154_local *local, s32 mbm) { - struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); - if (!local->ops->set_hw_addr_filt) { + if (!local->ops->set_txpower) { WARN_ON(1); return -EOPNOTSUPP; } - filt.pan_id = pan_id; - - trace_802154_drv_set_pan_id(local, pan_id); - ret = local->ops->set_hw_addr_filt(&local->hw, &filt, - IEEE802154_AFILT_PANID_CHANGED); + trace_802154_drv_set_tx_power(local, mbm); + ret = local->ops->set_txpower(&local->hw, mbm); trace_802154_drv_return_int(local, ret); return ret; } -static inline int -drv_set_extended_addr(struct ieee802154_local *local, __le64 extended_addr) +static inline int drv_set_cca_mode(struct ieee802154_local *local, + const struct wpan_phy_cca *cca) { - struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); - if (!local->ops->set_hw_addr_filt) { + if (!local->ops->set_cca_mode) { WARN_ON(1); return -EOPNOTSUPP; } - filt.ieee_addr = extended_addr; - - trace_802154_drv_set_extended_addr(local, extended_addr); - ret = local->ops->set_hw_addr_filt(&local->hw, &filt, - IEEE802154_AFILT_IEEEADDR_CHANGED); + trace_802154_drv_set_cca_mode(local, cca); + ret = local->ops->set_cca_mode(&local->hw, cca); trace_802154_drv_return_int(local, ret); return ret; } -static inline int -drv_set_short_addr(struct ieee802154_local *local, __le16 short_addr) +static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode) { - struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); - if (!local->ops->set_hw_addr_filt) { + if (!local->ops->set_lbt) { WARN_ON(1); return -EOPNOTSUPP; } - filt.short_addr = short_addr; - - trace_802154_drv_set_short_addr(local, short_addr); - ret = local->ops->set_hw_addr_filt(&local->hw, &filt, - IEEE802154_AFILT_SADDR_CHANGED); + trace_802154_drv_set_lbt_mode(local, mode); + ret = local->ops->set_lbt(&local->hw, mode); trace_802154_drv_return_int(local, ret); return ret; } static inline int -drv_set_pan_coord(struct ieee802154_local *local, bool is_coord) +drv_set_cca_ed_level(struct ieee802154_local *local, s32 mbm) { - struct ieee802154_hw_addr_filt filt; int ret; might_sleep(); - if (!local->ops->set_hw_addr_filt) { + if (!local->ops->set_cca_ed_level) { WARN_ON(1); return -EOPNOTSUPP; } - filt.pan_coord = is_coord; - - trace_802154_drv_set_pan_coord(local, is_coord); - ret = local->ops->set_hw_addr_filt(&local->hw, &filt, - IEEE802154_AFILT_PANC_CHANGED); + trace_802154_drv_set_cca_ed_level(local, mbm); + ret = local->ops->set_cca_ed_level(&local->hw, mbm); trace_802154_drv_return_int(local, ret); return ret; } @@ -264,22 +351,4 @@ drv_set_max_frame_retries(struct ieee802154_local *local, s8 max_frame_retries) return ret; } -static inline int -drv_set_promiscuous_mode(struct ieee802154_local *local, bool on) -{ - int ret; - - might_sleep(); - - if (!local->ops->set_promiscuous_mode) { - WARN_ON(1); - return -EOPNOTSUPP; - } - - trace_802154_drv_set_promiscuous_mode(local, on); - ret = local->ops->set_promiscuous_mode(&local->hw, on); - trace_802154_drv_return_int(local, ret); - return ret; -} - #endif /* __MAC802154_DRIVER_OPS */ diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 1381e6a5e180..509e0172fe82 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -26,6 +26,8 @@ struct ieee802154_local { struct ieee802154_hw hw; const struct ieee802154_ops *ops; + /* hardware address filter */ + struct ieee802154_hw_addr_filt addr_filt; /* ieee802154 phy */ struct wpan_phy *phy; @@ -55,7 +57,7 @@ struct ieee802154_local { struct sk_buff_head skb_queue; struct sk_buff *tx_skb; - struct work_struct tx_work; + struct work_struct sync_tx_work; /* A negative Linux error code or a null/positive MLME error status */ int tx_result; }; @@ -82,6 +84,16 @@ struct ieee802154_sub_if_data { struct ieee802154_local *local; struct net_device *dev; + /* Each interface starts and works in nominal state at a given filtering + * level given by iface_default_filtering, which is set once for all at + * the interface creation and should not evolve over time. For some MAC + * operations however, the filtering level may change temporarily, as + * reflected in the required_filtering field. The actual filtering at + * the PHY level may be different and is shown in struct wpan_phy. + */ + enum ieee802154_filtering_level iface_default_filtering; + enum ieee802154_filtering_level required_filtering; + unsigned long state; char name[IFNAMSIZ]; @@ -123,13 +135,53 @@ ieee802154_sdata_running(struct ieee802154_sub_if_data *sdata) extern struct ieee802154_mlme_ops mac802154_mlme_wpan; void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb); -void ieee802154_xmit_worker(struct work_struct *work); +void ieee802154_xmit_sync_worker(struct work_struct *work); +int ieee802154_sync_and_hold_queue(struct ieee802154_local *local); +int ieee802154_mlme_op_pre(struct ieee802154_local *local); +int ieee802154_mlme_tx(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata, + struct sk_buff *skb); +void ieee802154_mlme_op_post(struct ieee802154_local *local); +int ieee802154_mlme_tx_one(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata, + struct sk_buff *skb); netdev_tx_t ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer); +/** + * ieee802154_hold_queue - hold ieee802154 queue + * @local: main mac object + * + * Hold a queue by incrementing an atomic counter and requesting the netif + * queues to be stopped. The queues cannot be woken up while the counter has not + * been reset with as any ieee802154_release_queue() calls as needed. + */ +void ieee802154_hold_queue(struct ieee802154_local *local); + +/** + * ieee802154_release_queue - release ieee802154 queue + * @local: main mac object + * + * Release a queue which is held by decrementing an atomic counter and wake it + * up only if the counter reaches 0. + */ +void ieee802154_release_queue(struct ieee802154_local *local); + +/** + * ieee802154_disable_queue - disable ieee802154 queue + * @local: main mac object + * + * When trying to sync the Tx queue, we cannot just stop the queue + * (which is basically a bit being set without proper lock handling) + * because it would be racy. We actually need to call netif_tx_disable() + * instead, which is done by this helper. Restarting the queue can + * however still be done with a regular wake call. + */ +void ieee802154_disable_queue(struct ieee802154_local *local); + /* MIB callbacks */ void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan); diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 500ed1b81250..d9b50884d34e 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -147,25 +147,12 @@ static int ieee802154_setup_hw(struct ieee802154_sub_if_data *sdata) struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; - if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { - ret = drv_set_promiscuous_mode(local, - wpan_dev->promiscuous_mode); - if (ret < 0) - return ret; - } + sdata->required_filtering = sdata->iface_default_filtering; if (local->hw.flags & IEEE802154_HW_AFILT) { - ret = drv_set_pan_id(local, wpan_dev->pan_id); - if (ret < 0) - return ret; - - ret = drv_set_extended_addr(local, wpan_dev->extended_addr); - if (ret < 0) - return ret; - - ret = drv_set_short_addr(local, wpan_dev->short_addr); - if (ret < 0) - return ret; + local->addr_filt.pan_id = wpan_dev->pan_id; + local->addr_filt.ieee_addr = wpan_dev->extended_addr; + local->addr_filt.short_addr = wpan_dev->short_addr; } if (local->hw.flags & IEEE802154_HW_LBT) { @@ -206,7 +193,8 @@ static int mac802154_slave_open(struct net_device *dev) if (res) goto err; - res = drv_start(local); + res = drv_start(local, sdata->required_filtering, + &local->addr_filt); if (res) goto err; } @@ -223,15 +211,16 @@ err: static int ieee802154_check_mac_settings(struct ieee802154_local *local, - struct wpan_dev *wpan_dev, - struct wpan_dev *nwpan_dev) + struct ieee802154_sub_if_data *sdata, + struct ieee802154_sub_if_data *nsdata) { + struct wpan_dev *nwpan_dev = &nsdata->wpan_dev; + struct wpan_dev *wpan_dev = &sdata->wpan_dev; + ASSERT_RTNL(); - if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { - if (wpan_dev->promiscuous_mode != nwpan_dev->promiscuous_mode) - return -EBUSY; - } + if (sdata->iface_default_filtering != nsdata->iface_default_filtering) + return -EBUSY; if (local->hw.flags & IEEE802154_HW_AFILT) { if (wpan_dev->pan_id != nwpan_dev->pan_id || @@ -285,8 +274,7 @@ ieee802154_check_concurrent_iface(struct ieee802154_sub_if_data *sdata, /* check all phy mac sublayer settings are the same. * We have only one phy, different values makes trouble. */ - ret = ieee802154_check_mac_settings(local, wpan_dev, - &nsdata->wpan_dev); + ret = ieee802154_check_mac_settings(local, sdata, nsdata); if (ret < 0) return ret; } @@ -586,7 +574,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, sdata->dev->priv_destructor = mac802154_wpan_free; sdata->dev->netdev_ops = &mac802154_wpan_ops; sdata->dev->ml_priv = &mac802154_mlme_wpan; - wpan_dev->promiscuous_mode = false; + sdata->iface_default_filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; wpan_dev->header_ops = &ieee802154_header_ops; mutex_init(&sdata->sec_mtx); @@ -600,7 +588,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, case NL802154_IFTYPE_MONITOR: sdata->dev->needs_free_netdev = true; sdata->dev->netdev_ops = &mac802154_monitor_ops; - wpan_dev->promiscuous_mode = true; + sdata->iface_default_filtering = IEEE802154_FILTERING_NONE; break; default: BUG(); diff --git a/net/mac802154/main.c b/net/mac802154/main.c index bd7bdb1219dd..40fab08df24b 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -95,7 +95,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) skb_queue_head_init(&local->skb_queue); - INIT_WORK(&local->tx_work, ieee802154_xmit_worker); + INIT_WORK(&local->sync_tx_work, ieee802154_xmit_sync_worker); /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c439125ef2b9..0724aac8f48c 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -34,6 +34,7 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, struct sk_buff *skb, const struct ieee802154_hdr *hdr) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; + struct wpan_phy *wpan_phy = sdata->local->hw.phy; __le16 span, sshort; int rc; @@ -42,6 +43,17 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, span = wpan_dev->pan_id; sshort = wpan_dev->short_addr; + /* Level 3 filtering: Only beacons are accepted during scans */ + if (sdata->required_filtering == IEEE802154_FILTERING_3_SCAN && + sdata->required_filtering > wpan_phy->filtering) { + if (mac_cb(skb)->type != IEEE802154_FC_TYPE_BEACON) { + dev_dbg(&sdata->dev->dev, + "drop non-beacon frame (0x%x) during scan\n", + mac_cb(skb)->type); + goto fail; + } + } + switch (mac_cb(skb)->dest.mode) { case IEEE802154_ADDR_NONE: if (hdr->source.mode != IEEE802154_ADDR_NONE) @@ -114,8 +126,10 @@ fail: static void ieee802154_print_addr(const char *name, const struct ieee802154_addr *addr) { - if (addr->mode == IEEE802154_ADDR_NONE) + if (addr->mode == IEEE802154_ADDR_NONE) { pr_debug("%s not present\n", name); + return; + } pr_debug("%s PAN ID: %04x\n", name, le16_to_cpu(addr->pan_id)); if (addr->mode == IEEE802154_ADDR_SHORT) { @@ -132,7 +146,7 @@ static int ieee802154_parse_frame_start(struct sk_buff *skb, struct ieee802154_hdr *hdr) { int hlen; - struct ieee802154_mac_cb *cb = mac_cb_init(skb); + struct ieee802154_mac_cb *cb = mac_cb(skb); skb_reset_mac_header(skb); @@ -209,6 +223,13 @@ __ieee802154_rx_handle_packet(struct ieee802154_local *local, if (!ieee802154_sdata_running(sdata)) continue; + /* Do not deliver packets received on interfaces expecting + * AACK=1 if the address filters where disabled. + */ + if (local->hw.phy->filtering < IEEE802154_FILTERING_4_FRAME_FIELDS && + sdata->required_filtering == IEEE802154_FILTERING_4_FRAME_FIELDS) + continue; + ieee802154_subif_frame(sdata, skb, &hdr); skb = NULL; break; @@ -268,10 +289,8 @@ void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb) ieee802154_monitors_rx(local, skb); - /* Check if transceiver doesn't validate the checksum. - * If not we validate the checksum here. - */ - if (local->hw.flags & IEEE802154_HW_RX_DROP_BAD_CKSUM) { + /* Level 1 filtering: Check the FCS by software when relevant */ + if (local->hw.phy->filtering == IEEE802154_FILTERING_NONE) { crc = crc_ccitt(0, skb->data, skb->len); if (crc) { rcu_read_unlock(); @@ -294,8 +313,9 @@ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi) { struct ieee802154_local *local = hw_to_local(hw); + struct ieee802154_mac_cb *cb = mac_cb_init(skb); - mac_cb(skb)->lqi = lqi; + cb->lqi = lqi; skb->pkt_type = IEEE802154_RX_MSG; skb_queue_tail(&local->skb_queue, skb); tasklet_schedule(&local->tasklet); diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index c829e4a75325..9d8d43cf1e64 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -22,10 +22,10 @@ #include "ieee802154_i.h" #include "driver-ops.h" -void ieee802154_xmit_worker(struct work_struct *work) +void ieee802154_xmit_sync_worker(struct work_struct *work) { struct ieee802154_local *local = - container_of(work, struct ieee802154_local, tx_work); + container_of(work, struct ieee802154_local, sync_tx_work); struct sk_buff *skb = local->tx_skb; struct net_device *dev = skb->dev; int res; @@ -43,7 +43,9 @@ void ieee802154_xmit_worker(struct work_struct *work) err_tx: /* Restart the netif queue on each sub_if_data object. */ - ieee802154_wake_queue(&local->hw); + ieee802154_release_queue(local); + if (atomic_dec_and_test(&local->phy->ongoing_txs)) + wake_up(&local->phy->sync_txq); kfree_skb(skb); netdev_dbg(dev, "transmission failed\n"); } @@ -65,7 +67,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) consume_skb(skb); skb = nskb; } else { - goto err_tx; + goto err_free_skb; } } @@ -74,32 +76,134 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) } /* Stop the netif queue on each sub_if_data object. */ - ieee802154_stop_queue(&local->hw); + ieee802154_hold_queue(local); + atomic_inc(&local->phy->ongoing_txs); - /* async is priority, otherwise sync is fallback */ + /* Drivers should preferably implement the async callback. In some rare + * cases they only provide a sync callback which we will use as a + * fallback. + */ if (local->ops->xmit_async) { unsigned int len = skb->len; ret = drv_xmit_async(local, skb); - if (ret) { - ieee802154_wake_queue(&local->hw); - goto err_tx; - } + if (ret) + goto err_wake_netif_queue; dev->stats.tx_packets++; dev->stats.tx_bytes += len; } else { local->tx_skb = skb; - queue_work(local->workqueue, &local->tx_work); + queue_work(local->workqueue, &local->sync_tx_work); } return NETDEV_TX_OK; -err_tx: +err_wake_netif_queue: + ieee802154_release_queue(local); + if (atomic_dec_and_test(&local->phy->ongoing_txs)) + wake_up(&local->phy->sync_txq); +err_free_skb: kfree_skb(skb); return NETDEV_TX_OK; } +static int ieee802154_sync_queue(struct ieee802154_local *local) +{ + int ret; + + ieee802154_hold_queue(local); + ieee802154_disable_queue(local); + wait_event(local->phy->sync_txq, !atomic_read(&local->phy->ongoing_txs)); + ret = local->tx_result; + ieee802154_release_queue(local); + + return ret; +} + +int ieee802154_sync_and_hold_queue(struct ieee802154_local *local) +{ + int ret; + + ieee802154_hold_queue(local); + ret = ieee802154_sync_queue(local); + set_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); + + return ret; +} + +int ieee802154_mlme_op_pre(struct ieee802154_local *local) +{ + return ieee802154_sync_and_hold_queue(local); +} + +int ieee802154_mlme_tx(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata, + struct sk_buff *skb) +{ + int ret; + + /* Avoid possible calls to ->ndo_stop() when we asynchronously perform + * MLME transmissions. + */ + rtnl_lock(); + + /* Ensure the device was not stopped, otherwise error out */ + if (!local->open_count) { + rtnl_unlock(); + return -ENETDOWN; + } + + /* Warn if the ieee802154 core thinks MLME frames can be sent while the + * net interface expects this cannot happen. + */ + if (WARN_ON_ONCE(!netif_running(sdata->dev))) { + rtnl_unlock(); + return -ENETDOWN; + } + + ieee802154_tx(local, skb); + ret = ieee802154_sync_queue(local); + + rtnl_unlock(); + + return ret; +} + +void ieee802154_mlme_op_post(struct ieee802154_local *local) +{ + ieee802154_release_queue(local); +} + +int ieee802154_mlme_tx_one(struct ieee802154_local *local, + struct ieee802154_sub_if_data *sdata, + struct sk_buff *skb) +{ + int ret; + + ieee802154_mlme_op_pre(local); + ret = ieee802154_mlme_tx(local, sdata, skb); + ieee802154_mlme_op_post(local); + + return ret; +} + +static bool ieee802154_queue_is_stopped(struct ieee802154_local *local) +{ + return test_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); +} + +static netdev_tx_t +ieee802154_hot_tx(struct ieee802154_local *local, struct sk_buff *skb) +{ + /* Warn if the net interface tries to transmit frames while the + * ieee802154 core assumes the queue is stopped. + */ + WARN_ON_ONCE(ieee802154_queue_is_stopped(local)); + + return ieee802154_tx(local, skb); +} + netdev_tx_t ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -107,7 +211,7 @@ ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev) skb->skb_iif = dev->ifindex; - return ieee802154_tx(sdata->local, skb); + return ieee802154_hot_tx(sdata->local, skb); } netdev_tx_t @@ -129,5 +233,5 @@ ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev) skb->skb_iif = dev->ifindex; - return ieee802154_tx(sdata->local, skb); + return ieee802154_hot_tx(sdata->local, skb); } diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 9f024d85563b..ebc9a8521765 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -13,12 +13,23 @@ /* privid for wpan_phys to determine whether they belong to us or not */ const void *const mac802154_wpan_phy_privid = &mac802154_wpan_phy_privid; -void ieee802154_wake_queue(struct ieee802154_hw *hw) +/** + * ieee802154_wake_queue - wake ieee802154 queue + * @hw: main hardware object + * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we had to stop the queue to + * avoid new skb to come during the transmission. The queue then needs to be + * woken up after the operation. + */ +static void ieee802154_wake_queue(struct ieee802154_hw *hw) { struct ieee802154_local *local = hw_to_local(hw); struct ieee802154_sub_if_data *sdata; rcu_read_lock(); + clear_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (!sdata->dev) continue; @@ -27,9 +38,18 @@ void ieee802154_wake_queue(struct ieee802154_hw *hw) } rcu_read_unlock(); } -EXPORT_SYMBOL(ieee802154_wake_queue); -void ieee802154_stop_queue(struct ieee802154_hw *hw) +/** + * ieee802154_stop_queue - stop ieee802154 queue + * @hw: main hardware object + * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we need to tell upper layers to + * stop giving us new skbs while we are busy with the transmitted one. The queue + * must then be stopped before transmitting. + */ +static void ieee802154_stop_queue(struct ieee802154_hw *hw) { struct ieee802154_local *local = hw_to_local(hw); struct ieee802154_sub_if_data *sdata; @@ -43,14 +63,47 @@ void ieee802154_stop_queue(struct ieee802154_hw *hw) } rcu_read_unlock(); } -EXPORT_SYMBOL(ieee802154_stop_queue); + +void ieee802154_hold_queue(struct ieee802154_local *local) +{ + unsigned long flags; + + spin_lock_irqsave(&local->phy->queue_lock, flags); + if (!atomic_fetch_inc(&local->phy->hold_txs)) + ieee802154_stop_queue(&local->hw); + spin_unlock_irqrestore(&local->phy->queue_lock, flags); +} + +void ieee802154_release_queue(struct ieee802154_local *local) +{ + unsigned long flags; + + spin_lock_irqsave(&local->phy->queue_lock, flags); + if (atomic_dec_and_test(&local->phy->hold_txs)) + ieee802154_wake_queue(&local->hw); + spin_unlock_irqrestore(&local->phy->queue_lock, flags); +} + +void ieee802154_disable_queue(struct ieee802154_local *local) +{ + struct ieee802154_sub_if_data *sdata; + + rcu_read_lock(); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (!sdata->dev) + continue; + + netif_tx_disable(sdata->dev); + } + rcu_read_unlock(); +} enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer) { struct ieee802154_local *local = container_of(timer, struct ieee802154_local, ifs_timer); - ieee802154_wake_queue(&local->hw); + ieee802154_release_queue(local); return HRTIMER_NORESTART; } @@ -84,10 +137,12 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, hw->phy->sifs_period * NSEC_PER_USEC, HRTIMER_MODE_REL); } else { - ieee802154_wake_queue(hw); + ieee802154_release_queue(local); } dev_consume_skb_any(skb); + if (atomic_dec_and_test(&hw->phy->ongoing_txs)) + wake_up(&hw->phy->sync_txq); } EXPORT_SYMBOL(ieee802154_xmit_complete); @@ -97,8 +152,10 @@ void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, struct ieee802154_local *local = hw_to_local(hw); local->tx_result = reason; - ieee802154_wake_queue(hw); + ieee802154_release_queue(local); dev_kfree_skb_any(skb); + if (atomic_dec_and_test(&hw->phy->ongoing_txs)) + wake_up(&hw->phy->sync_txq); } EXPORT_SYMBOL(ieee802154_xmit_error); diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index b6b5e496fa40..fc9e728b6333 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -665,12 +665,14 @@ static __init int mctp_init(void) rc = mctp_neigh_init(); if (rc) - goto err_unreg_proto; + goto err_unreg_routes; mctp_device_init(); return 0; +err_unreg_routes: + mctp_routes_exit(); err_unreg_proto: proto_unregister(&mctp_proto); err_unreg_sock: diff --git a/net/mctp/route.c b/net/mctp/route.c index 2155f15a074c..f9a80b82dc51 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -1400,7 +1400,7 @@ int __init mctp_routes_init(void) return register_pernet_subsys(&mctp_net_ops); } -void __exit mctp_routes_exit(void) +void mctp_routes_exit(void) { unregister_pernet_subsys(&mctp_net_ops); rtnl_unregister(PF_MCTP, RTM_DELROUTE); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index b52afe316dc4..35b5f806fdda 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1079,9 +1079,9 @@ static void mpls_get_stats(struct mpls_dev *mdev, p = per_cpu_ptr(mdev->stats, i); do { - start = u64_stats_fetch_begin_irq(&p->syncp); + start = u64_stats_fetch_begin(&p->syncp); local = p->stats; - } while (u64_stats_fetch_retry_irq(&p->syncp, start)); + } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += local.rx_packets; stats->rx_bytes += local.rx_bytes; diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index 6e7df47c9584..a3829ce548f9 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ - mib.o pm_netlink.o sockopt.o pm_userspace.o + mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c new file mode 100644 index 000000000000..d237d142171c --- /dev/null +++ b/net/mptcp/fastopen.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* MPTCP Fast Open Mechanism + * + * Copyright (c) 2021-2022, Dmytro SHYTYI + */ + +#include "protocol.h" + +void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, + struct request_sock *req) +{ + struct sock *ssk = subflow->tcp_sock; + struct sock *sk = subflow->conn; + struct sk_buff *skb; + struct tcp_sock *tp; + + tp = tcp_sk(ssk); + + subflow->is_mptfo = 1; + + skb = skb_peek(&ssk->sk_receive_queue); + if (WARN_ON_ONCE(!skb)) + return; + + /* dequeue the skb from sk receive queue */ + __skb_unlink(skb, &ssk->sk_receive_queue); + skb_ext_reset(skb); + skb_orphan(skb); + + /* We copy the fastopen data, but that don't belong to the mptcp sequence + * space, need to offset it in the subflow sequence, see mptcp_subflow_get_map_offset() + */ + tp->copied_seq += skb->len; + subflow->ssn_offset += skb->len; + + /* initialize a dummy sequence number, we will update it at MPC + * completion, if needed + */ + MPTCP_SKB_CB(skb)->map_seq = -skb->len; + MPTCP_SKB_CB(skb)->end_seq = 0; + MPTCP_SKB_CB(skb)->offset = 0; + MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; + + mptcp_data_lock(sk); + + mptcp_set_owner_r(skb, sk); + __skb_queue_tail(&sk->sk_receive_queue, skb); + + sk->sk_data_ready(sk); + + mptcp_data_unlock(sk); +} + +void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) +{ + struct sock *sk = (struct sock *)msk; + struct sk_buff *skb; + + mptcp_data_lock(sk); + skb = skb_peek_tail(&sk->sk_receive_queue); + if (skb) { + WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); + pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk, + MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq, + MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq); + MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq; + MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq; + } + + pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); + mptcp_data_unlock(sk); +} diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 30d289044e71..5ded85e2c374 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -26,6 +26,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, { u8 subtype = *ptr >> 4; int expected_opsize; + u16 subopt; u8 version; u8 flags; u8 i; @@ -38,11 +39,15 @@ static void mptcp_parse_option(const struct sk_buff *skb, expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA; else expected_opsize = TCPOLEN_MPTCP_MPC_ACK; + subopt = OPTION_MPTCP_MPC_ACK; } else { - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) { expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK; - else + subopt = OPTION_MPTCP_MPC_SYNACK; + } else { expected_opsize = TCPOLEN_MPTCP_MPC_SYN; + subopt = OPTION_MPTCP_MPC_SYN; + } } /* Cfr RFC 8684 Section 3.3.0: @@ -85,7 +90,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0); - mp_opt->suboptions |= OPTIONS_MPTCP_MPC; + mp_opt->suboptions |= subopt; if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) { mp_opt->sndr_key = get_unaligned_be64(ptr); ptr += 8; @@ -934,7 +939,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) && !subflow->request_join) tcp_send_ack(ssk); - goto fully_established; + goto check_notify; } /* we must process OoO packets before the first subflow is fully @@ -945,17 +950,20 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) { if (subflow->mp_join) goto reset; + if (subflow->is_mptfo && mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) + goto set_fully_established; return subflow->mp_capable; } - if (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || - ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo)) { + if (subflow->remote_key_valid && + (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || + ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) { /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ subflow->fully_established = 1; WRITE_ONCE(msk->fully_established, true); - goto fully_established; + goto check_notify; } /* If the first established packet does not contain MP_CAPABLE + data @@ -974,11 +982,12 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (mp_opt->deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); +set_fully_established: if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); mptcp_subflow_fully_established(subflow, mp_opt); -fully_established: +check_notify: /* if the subflow is not already linked into the conn_list, we can't * notify the PM: this subflow is still on the listener queue * and the PM possibly acquiring the subflow lock could race with diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 9813ed0fde9b..d66fbd558263 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -912,10 +912,14 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, */ if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID) pernet->next_id = 1; - if (pernet->addrs >= MPTCP_PM_ADDR_MAX) + if (pernet->addrs >= MPTCP_PM_ADDR_MAX) { + ret = -ERANGE; goto out; - if (test_bit(entry->addr.id, pernet->id_bitmap)) + } + if (test_bit(entry->addr.id, pernet->id_bitmap)) { + ret = -EBUSY; goto out; + } /* do not insert duplicate address, differentiate on port only * singled addresses @@ -929,8 +933,10 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, * endpoint is an implicit one and the user-space * did not provide an endpoint id */ - if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) + if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) { + ret = -EEXIST; goto out; + } if (entry->addr.id) goto out; @@ -1003,16 +1009,12 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, return err; msk = mptcp_sk(entry->lsk->sk); - if (!msk) { - err = -EINVAL; - goto out; - } + if (!msk) + return -EINVAL; ssock = __mptcp_nmpc_socket(msk); - if (!ssock) { - err = -EINVAL; - goto out; - } + if (!ssock) + return -EINVAL; mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1020,22 +1022,14 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, addrlen = sizeof(struct sockaddr_in6); #endif err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen); - if (err) { - pr_warn("kernel_bind error, err=%d", err); - goto out; - } + if (err) + return err; err = kernel_listen(ssock, backlog); - if (err) { - pr_warn("kernel_listen error, err=%d", err); - goto out; - } + if (err) + return err; return 0; - -out: - sock_release(entry->lsk); - return err; } int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) @@ -1327,7 +1321,7 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } - entry = kmalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT); + entry = kzalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT); if (!entry) { GENL_SET_ERR_MSG(info, "can't allocate addr"); return -ENOMEM; @@ -1337,23 +1331,22 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) if (entry->addr.port) { ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry); if (ret) { - GENL_SET_ERR_MSG(info, "create listen socket error"); - kfree(entry); - return ret; + GENL_SET_ERR_MSG_FMT(info, "create listen socket error: %d", ret); + goto out_free; } } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) { - GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); - if (entry->lsk) - sock_release(entry->lsk); - kfree(entry); - return ret; + GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); + goto out_free; } mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk)); - return 0; + +out_free: + __mptcp_pm_release_addr_entry(entry); + return ret; } int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 9e82250cbb70..5cb65f0928f4 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -291,7 +291,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) goto create_err; } - sk = &msk->sk.icsk_inet.sk; + sk = (struct sock *)msk; lock_sock(sk); err = __mptcp_subflow_connect(sk, &addr_l, &addr_r); @@ -403,7 +403,7 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) goto destroy_err; } - sk = &msk->sk.icsk_inet.sk; + sk = (struct sock *)msk; lock_sock(sk); ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r); if (ssk) { diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f599ad44ed24..b0d387be500a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -36,15 +36,6 @@ struct mptcp6_sock { }; #endif -struct mptcp_skb_cb { - u64 map_seq; - u64 end_seq; - u32 offset; - u8 has_rxtstamp:1; -}; - -#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) - enum { MPTCP_CMSG_TS = BIT(0), MPTCP_CMSG_INQ = BIT(1), @@ -200,7 +191,7 @@ static void mptcp_rfree(struct sk_buff *skb) mptcp_rmem_uncharge(sk, len); } -static void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk) +void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; @@ -1602,7 +1593,7 @@ out: __mptcp_check_send_data_fin(sk); } -static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) +static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = { @@ -1611,7 +1602,6 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) struct mptcp_data_frag *dfrag; struct sock *xmit_ssk; int len, copied = 0; - bool first = true; info.flags = 0; while ((dfrag = mptcp_send_head(sk))) { @@ -1621,11 +1611,10 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) while (len > 0) { int ret = 0; - /* the caller already invoked the packet scheduler, - * check for a different subflow usage only after + /* check for a different subflow usage only after * spooling the first chunk of data */ - xmit_ssk = first ? ssk : mptcp_subflow_get_send(mptcp_sk(sk)); + xmit_ssk = first ? ssk : mptcp_subflow_get_send(msk); if (!xmit_ssk) goto out; if (xmit_ssk != ssk) { @@ -1673,6 +1662,37 @@ static void mptcp_set_nospace(struct sock *sk) set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags); } +static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg, + size_t len, int *copied_syn) +{ + unsigned int saved_flags = msg->msg_flags; + struct mptcp_sock *msk = mptcp_sk(sk); + int ret; + + lock_sock(ssk); + msg->msg_flags |= MSG_DONTWAIT; + msk->connect_flags = O_NONBLOCK; + msk->is_sendmsg = 1; + ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); + msk->is_sendmsg = 0; + msg->msg_flags = saved_flags; + release_sock(ssk); + + /* do the blocking bits of inet_stream_connect outside the ssk socket lock */ + if (ret == -EINPROGRESS && !(msg->msg_flags & MSG_DONTWAIT)) { + ret = __inet_stream_connect(sk->sk_socket, msg->msg_name, + msg->msg_namelen, msg->msg_flags, 1); + + /* Keep the same behaviour of plain TCP: zero the copied bytes in + * case of any error, except timeout or signal + */ + if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR) + *copied_syn = 0; + } + + return ret; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1682,34 +1702,22 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int ret = 0; long timeo; - /* we don't support FASTOPEN yet */ - if (msg->msg_flags & MSG_FASTOPEN) - return -EOPNOTSUPP; - /* silently ignore everything else */ - msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL; + msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN; lock_sock(sk); ssock = __mptcp_nmpc_socket(msk); - if (unlikely(ssock && inet_sk(ssock->sk)->defer_connect)) { - struct sock *ssk = ssock->sk; + if (unlikely(ssock && (inet_sk(ssock->sk)->defer_connect || + msg->msg_flags & MSG_FASTOPEN))) { int copied_syn = 0; - lock_sock(ssk); - - ret = tcp_sendmsg_fastopen(ssk, msg, &copied_syn, len, NULL); + ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn); copied += copied_syn; - if (ret == -EINPROGRESS && copied_syn > 0) { - /* reflect the new state on the MPTCP socket */ - inet_sk_state_store(sk, inet_sk_state_load(ssk)); - release_sock(ssk); + if (ret == -EINPROGRESS && copied_syn > 0) goto out; - } else if (ret) { - release_sock(ssk); + else if (ret) goto do_error; - } - release_sock(ssk); } timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); @@ -2253,7 +2261,7 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) struct mptcp_data_frag *cur, *rtx_head; struct mptcp_sock *msk = mptcp_sk(sk); - if (__mptcp_check_fallback(mptcp_sk(sk))) + if (__mptcp_check_fallback(msk)) return false; if (tcp_rtx_and_write_queues_empty(sk)) @@ -2332,12 +2340,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, goto out; } - /* if we are invoked by the msk cleanup code, the subflow is - * already orphaned - */ - if (ssk->sk_socket) - sock_orphan(ssk); - + sock_orphan(ssk); subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops @@ -2434,7 +2437,7 @@ static bool mptcp_check_close_timeout(const struct sock *sk) static void mptcp_check_fastclose(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; - struct sock *sk = &msk->sk.icsk_inet.sk; + struct sock *sk = (struct sock *)msk; if (likely(!READ_ONCE(msk->rcv_fastclose))) return; @@ -2596,7 +2599,7 @@ static void mptcp_do_fastclose(struct sock *sk) static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); - struct sock *sk = &msk->sk.icsk_inet.sk; + struct sock *sk = (struct sock *)msk; unsigned long fail_tout; int state; @@ -2708,6 +2711,8 @@ static int mptcp_init_sock(struct sock *sk) if (ret) return ret; + set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); + /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will * propagate the correct value */ @@ -2918,14 +2923,18 @@ cleanup: if (ssk == msk->first) subflow->fail_tout = 0; - sock_orphan(ssk); + /* detach from the parent socket, but allow data_ready to + * push incoming data into the mptcp stack, to properly ack it + */ + ssk->sk_socket = NULL; + ssk->sk_wq = NULL; unlock_sock_fast(ssk, slow); } sock_orphan(sk); sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); - if (mptcp_sk(sk)->token) + if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); if (sk->sk_state == TCP_CLOSE) { @@ -2952,7 +2961,7 @@ static void mptcp_close(struct sock *sk, long timeout) sock_put(sk); } -static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +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); @@ -2984,8 +2993,8 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_stop_timer(sk); sk_stop_timer(sk, &sk->sk_timer); - if (mptcp_sk(sk)->token) - mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL); + if (msk->token) + mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); /* msk->subflow is still intact, the following will not free the first * subflow @@ -3027,7 +3036,6 @@ struct sock *mptcp_sk_clone(const struct sock *sk, struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); struct mptcp_sock *msk; - u64 ack_seq; if (!nsk) return NULL; @@ -3053,15 +3061,6 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; - if (mp_opt->suboptions & OPTIONS_MPTCP_MPC) { - msk->can_ack = true; - msk->remote_key = mp_opt->sndr_key; - mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); - ack_seq++; - WRITE_ONCE(msk->ack_seq, ack_seq); - atomic64_set(&msk->rcv_wnd_sent, ack_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); @@ -3196,16 +3195,10 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) if (!mptcp_send_head(sk)) return; - if (!sock_owned_by_user(sk)) { - struct sock *xmit_ssk = mptcp_subflow_get_send(mptcp_sk(sk)); - - if (xmit_ssk == ssk) - __mptcp_subflow_push_pending(sk, ssk); - else if (xmit_ssk) - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND); - } else { + if (!sock_owned_by_user(sk)) + __mptcp_subflow_push_pending(sk, ssk, false); + else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); - } } #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \ @@ -3296,7 +3289,7 @@ void mptcp_subflow_process_delegated(struct sock *ssk) if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) - __mptcp_subflow_push_pending(sk, ssk); + __mptcp_subflow_push_pending(sk, ssk, true); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); @@ -3340,7 +3333,6 @@ void mptcp_finish_connect(struct sock *ssk) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; struct sock *sk; - u64 ack_seq; subflow = mptcp_subflow_ctx(ssk); sk = subflow->conn; @@ -3348,22 +3340,16 @@ void mptcp_finish_connect(struct sock *ssk) pr_debug("msk=%p, token=%u", sk, subflow->token); - mptcp_crypto_key_sha(subflow->remote_key, NULL, &ack_seq); - ack_seq++; - subflow->map_seq = ack_seq; + subflow->map_seq = subflow->iasn; subflow->map_subflow_seq = 1; /* the socket is not connected yet, no msk/subflow ops can access/race * accessing the field below */ - WRITE_ONCE(msk->remote_key, subflow->remote_key); WRITE_ONCE(msk->local_key, subflow->local_key); WRITE_ONCE(msk->write_seq, subflow->idsn + 1); WRITE_ONCE(msk->snd_nxt, msk->write_seq); - WRITE_ONCE(msk->ack_seq, ack_seq); - WRITE_ONCE(msk->can_ack, 1); WRITE_ONCE(msk->snd_una, msk->write_seq); - atomic64_set(&msk->rcv_wnd_sent, ack_seq); mptcp_pm_new_connection(msk, ssk, 0); @@ -3507,10 +3493,73 @@ static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg) return put_user(answ, (int __user *)arg); } +static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow) +{ + subflow->request_mptcp = 0; + __mptcp_do_fallback(msk); +} + +static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + struct socket *ssock; + int err = -EINVAL; + + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) + return -EINVAL; + + mptcp_token_destroy(msk); + inet_sk_state_store(sk, TCP_SYN_SENT); + subflow = mptcp_subflow_ctx(ssock->sk); +#ifdef CONFIG_TCP_MD5SIG + /* no MPTCP if MD5SIG is enabled on this socket or we may run out of + * TCP option space. + */ + if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info)) + mptcp_subflow_early_fallback(msk, subflow); +#endif + if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) { + MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT); + mptcp_subflow_early_fallback(msk, subflow); + } + if (likely(!__mptcp_check_fallback(msk))) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); + + /* if reaching here via the fastopen/sendmsg path, the caller already + * acquired the subflow socket lock, too. + */ + if (msk->is_sendmsg) + err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1); + else + err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags); + inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; + + /* on successful connect, the msk state will be moved to established by + * subflow_finish_connect() + */ + if (unlikely(err && err != -EINPROGRESS)) { + inet_sk_state_store(sk, inet_sk_state_load(ssock->sk)); + return err; + } + + mptcp_copy_inaddrs(sk, ssock->sk); + + /* unblocking connect, mptcp-level inet_stream_connect will error out + * without changing the socket state, update it here. + */ + if (err == -EINPROGRESS) + sk->sk_socket->state = ssock->state; + return err; +} + static struct proto mptcp_prot = { .name = "MPTCP", .owner = THIS_MODULE, .init = mptcp_init_sock, + .connect = mptcp_connect, .disconnect = mptcp_disconnect, .close = mptcp_close, .accept = mptcp_accept, @@ -3562,78 +3611,16 @@ unlock: return err; } -static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, - struct mptcp_subflow_context *subflow) -{ - subflow->request_mptcp = 0; - __mptcp_do_fallback(msk); -} - static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { - struct mptcp_sock *msk = mptcp_sk(sock->sk); - struct mptcp_subflow_context *subflow; - struct socket *ssock; - int err = -EINVAL; + int ret; lock_sock(sock->sk); - if (uaddr) { - if (addr_len < sizeof(uaddr->sa_family)) - goto unlock; - - if (uaddr->sa_family == AF_UNSPEC) { - err = mptcp_disconnect(sock->sk, flags); - sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; - goto unlock; - } - } - - if (sock->state != SS_UNCONNECTED && msk->subflow) { - /* pending connection or invalid state, let existing subflow - * cope with that - */ - ssock = msk->subflow; - goto do_connect; - } - - ssock = __mptcp_nmpc_socket(msk); - if (!ssock) - goto unlock; - - mptcp_token_destroy(msk); - inet_sk_state_store(sock->sk, TCP_SYN_SENT); - subflow = mptcp_subflow_ctx(ssock->sk); -#ifdef CONFIG_TCP_MD5SIG - /* no MPTCP if MD5SIG is enabled on this socket or we may run out of - * TCP option space. - */ - if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info)) - mptcp_subflow_early_fallback(msk, subflow); -#endif - if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) { - MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT); - mptcp_subflow_early_fallback(msk, subflow); - } - if (likely(!__mptcp_check_fallback(msk))) - MPTCP_INC_STATS(sock_net(sock->sk), MPTCP_MIB_MPCAPABLEACTIVE); - -do_connect: - err = ssock->ops->connect(ssock, uaddr, addr_len, flags); - inet_sk(sock->sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; - sock->state = ssock->state; - - /* on successful connect, the msk state will be moved to established by - * subflow_finish_connect() - */ - if (!err || err == -EINPROGRESS) - mptcp_copy_inaddrs(sock->sk, ssock->sk); - else - inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); - -unlock: + mptcp_sk(sock->sk)->connect_flags = flags; + ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); release_sock(sock->sk); - return err; + return ret; } static int mptcp_listen(struct socket *sock, int backlog) @@ -3684,6 +3671,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct mptcp_subflow_context *subflow; struct sock *newsk = newsock->sk; + set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); + lock_sock(newsk); /* PM/worker can now acquire the first subflow socket @@ -3699,7 +3688,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (mptcp_is_fully_established(newsk)) mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL); - mptcp_copy_inaddrs(newsk, msk->first); mptcp_rcv_space_init(msk, msk->first); mptcp_propagate_sndbuf(newsk, msk->first); @@ -3898,12 +3886,6 @@ static const struct proto_ops mptcp_v6_stream_ops = { static struct proto mptcp_v6_prot; -static void mptcp_v6_destroy(struct sock *sk) -{ - mptcp_destroy(sk); - inet6_destroy_sock(sk); -} - static struct inet_protosw mptcp_v6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, @@ -3919,7 +3901,6 @@ int __init mptcp_proto_v6_init(void) mptcp_v6_prot = mptcp_prot; strcpy(mptcp_v6_prot.name, "MPTCPv6"); mptcp_v6_prot.slab = NULL; - mptcp_v6_prot.destroy = mptcp_v6_destroy; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); err = proto_register(&mptcp_v6_prot, 1); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index c0b5b4628f65..8b4379a2cd85 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -126,6 +126,15 @@ #define MPTCP_CONNECTED 6 #define MPTCP_RESET_SCHEDULER 7 +struct mptcp_skb_cb { + u64 map_seq; + u64 end_seq; + u32 offset; + u8 has_rxtstamp:1; +}; + +#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) + static inline bool before64(__u64 seq1, __u64 seq2) { return (__s64)(seq1 - seq2) < 0; @@ -285,7 +294,9 @@ struct mptcp_sock { u8 mpc_endpoint_id; u8 recvmsg_inq:1, cork:1, - nodelay:1; + nodelay:1, + is_sendmsg:1; + int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -465,17 +476,22 @@ struct mptcp_subflow_context { send_fastclose : 1, send_infinite_map : 1, rx_eof : 1, - can_ack : 1, /* only after processing the remote a key */ + remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ local_id_valid : 1, /* local_id is correctly initialized */ - valid_csum_seen : 1; /* at least one csum validated */ + valid_csum_seen : 1, /* at least one csum validated */ + is_mptfo : 1, /* subflow is doing TFO */ + __unused : 8; enum mptcp_data_avail data_avail; u32 remote_nonce; u64 thmac; u32 local_nonce; u32 remote_token; - u8 hmac[MPTCPOPT_HMAC_LEN]; + union { + u8 hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */ + u64 iasn; /* initial ack sequence number, MPC subflows only */ + }; u8 local_id; u8 remote_id; u8 reset_seen:1; @@ -599,8 +615,9 @@ 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, - struct mptcp_options_received *mp_opt); + const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); void mptcp_check_and_set_pending(struct sock *sk); void __mptcp_push_pending(struct sock *sk, unsigned int flags); @@ -616,6 +633,7 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); void mptcp_cancel_work(struct sock *sk); +void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, const struct mptcp_addr_info *b, bool use_port); @@ -823,6 +841,11 @@ void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_ void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); +void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); +void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, + struct request_sock *req); + static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) { return READ_ONCE(msk->pm.addr_signal) & diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index c7cb68c725b2..a47423ebb33a 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -559,7 +559,10 @@ static bool mptcp_supported_sockopt(int level, int optname) case TCP_NOTSENT_LOWAT: case TCP_TX_DELAY: case TCP_INQ: + case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: + case TCP_FASTOPEN_KEY: + case TCP_FASTOPEN_NO_COOKIE: return true; } @@ -568,9 +571,6 @@ static bool mptcp_supported_sockopt(int level, int optname) /* TCP_REPAIR, TCP_REPAIR_QUEUE, TCP_QUEUE_SEQ, TCP_REPAIR_OPTIONS, * TCP_REPAIR_WINDOW are not supported, better avoid this mess */ - /* TCP_FASTOPEN_KEY, TCP_FASTOPEN, TCP_FASTOPEN_NO_COOKIE, - * are not supported fastopen is currently unsupported - */ } return false; } @@ -757,29 +757,17 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, return -EOPNOTSUPP; } -static int mptcp_setsockopt_sol_tcp_defer(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) -{ - struct socket *listener; - - listener = __mptcp_nmpc_socket(msk); - if (!listener) - return 0; /* TCP_DEFER_ACCEPT does not fail */ - - return tcp_setsockopt(listener->sk, SOL_TCP, TCP_DEFER_ACCEPT, optval, optlen); -} - -static int mptcp_setsockopt_sol_tcp_fastopen_connect(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) +static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, + sockptr_t optval, unsigned int optlen) { struct socket *sock; - /* Limit to first subflow */ + /* Limit to first subflow, before the connection establishment */ sock = __mptcp_nmpc_socket(msk); if (!sock) return -EINVAL; - return tcp_setsockopt(sock->sk, SOL_TCP, TCP_FASTOPEN_CONNECT, optval, optlen); + return tcp_setsockopt(sock->sk, level, optname, optval, optlen); } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, @@ -809,9 +797,15 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, case TCP_NODELAY: return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen); case TCP_DEFER_ACCEPT: - return mptcp_setsockopt_sol_tcp_defer(msk, optval, optlen); + /* See tcp.c: TCP_DEFER_ACCEPT does not fail */ + mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); + return 0; + case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: - return mptcp_setsockopt_sol_tcp_fastopen_connect(msk, optval, optlen); + case TCP_FASTOPEN_KEY: + case TCP_FASTOPEN_NO_COOKIE: + return mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, + optval, optlen); } return -EOPNOTSUPP; @@ -994,7 +988,7 @@ static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, int __user *optlen) { struct mptcp_subflow_context *subflow; - struct sock *sk = &msk->sk.icsk_inet.sk; + struct sock *sk = (struct sock *)msk; unsigned int sfcount = 0, copied = 0; struct mptcp_subflow_data sfd; char __user *infoptr; @@ -1085,8 +1079,8 @@ static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addr static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *optval, int __user *optlen) { - struct sock *sk = &msk->sk.icsk_inet.sk; struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; unsigned int sfcount = 0, copied = 0; struct mptcp_subflow_data sfd; char __user *addrptr; @@ -1173,7 +1167,10 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, case TCP_INFO: case TCP_CC_INFO: case TCP_DEFER_ACCEPT: + case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: + case TCP_FASTOPEN_KEY: + case TCP_FASTOPEN_NO_COOKIE: return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); case TCP_INQ: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 07dd23d0fe04..29904303f5c2 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -307,7 +307,48 @@ static struct dst_entry *subflow_v4_route_req(const struct sock *sk, return NULL; } +static void subflow_prep_synack(const struct sock *sk, struct request_sock *req, + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct inet_request_sock *ireq = inet_rsk(req); + + /* clear tstamp_ok, as needed depending on cookie */ + if (foc && foc->len > -1) + ireq->tstamp_ok = 0; + + if (synack_type == TCP_SYNACK_FASTOPEN) + mptcp_fastopen_subflow_synack_set_params(subflow, req); +} + +static int subflow_v4_send_synack(const struct sock *sk, struct dst_entry *dst, + struct flowi *fl, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) +{ + subflow_prep_synack(sk, req, foc, synack_type); + + return tcp_request_sock_ipv4_ops.send_synack(sk, dst, fl, req, foc, + synack_type, syn_skb); +} + #if IS_ENABLED(CONFIG_MPTCP_IPV6) +static int subflow_v6_send_synack(const struct sock *sk, struct dst_entry *dst, + struct flowi *fl, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type, + struct sk_buff *syn_skb) +{ + subflow_prep_synack(sk, req, foc, synack_type); + + return tcp_request_sock_ipv6_ops.send_synack(sk, dst, fl, req, foc, + synack_type, syn_skb); +} + static struct dst_entry *subflow_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, @@ -392,11 +433,33 @@ static void mptcp_set_connected(struct sock *sk) mptcp_data_unlock(sk); } +static void subflow_set_remote_key(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) +{ + /* active MPC subflow will reach here multiple times: + * at subflow_finish_connect() time and at 4th ack time + */ + if (subflow->remote_key_valid) + return; + + subflow->remote_key_valid = 1; + subflow->remote_key = mp_opt->sndr_key; + mptcp_crypto_key_sha(subflow->remote_key, NULL, &subflow->iasn); + subflow->iasn++; + + WRITE_ONCE(msk->remote_key, subflow->remote_key); + WRITE_ONCE(msk->ack_seq, subflow->iasn); + WRITE_ONCE(msk->can_ack, true); + atomic64_set(&msk->rcv_wnd_sent, subflow->iasn); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_options_received mp_opt; struct sock *parent = subflow->conn; + struct mptcp_sock *msk; subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); @@ -404,6 +467,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (subflow->conn_finished) return; + msk = mptcp_sk(parent); mptcp_propagate_sndbuf(parent, sk); subflow->rel_write_seq = 1; subflow->conn_finished = 1; @@ -416,19 +480,16 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEFALLBACK); mptcp_do_fallback(sk); - pr_fallback(mptcp_sk(subflow->conn)); + pr_fallback(msk); goto fallback; } if (mp_opt.suboptions & OPTION_MPTCP_CSUMREQD) - WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true); + WRITE_ONCE(msk->csum_enabled, true); if (mp_opt.deny_join_id0) - WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true); + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; - subflow->can_ack = 1; - subflow->remote_key = mp_opt.sndr_key; - pr_debug("subflow=%p, remote_key=%llu", subflow, - subflow->remote_key); + subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); mptcp_set_connected(parent); @@ -466,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); - if (subflow_use_different_dport(mptcp_sk(parent), sk)) { + if (subflow_use_different_dport(msk, sk)) { pr_debug("synack inet_dport=%d %d", ntohs(inet_sk(sk)->inet_dport), ntohs(inet_sk(parent)->inet_dport)); @@ -474,7 +535,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_rcv_space_init(mptcp_sk(parent), sk); + mptcp_rcv_space_init(msk, sk); mptcp_set_connected(parent); } return; @@ -637,14 +698,16 @@ static void subflow_drop_ctx(struct sock *ssk) } void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - struct mptcp_options_received *mp_opt) + const struct mptcp_options_received *mp_opt) { struct mptcp_sock *msk = mptcp_sk(subflow->conn); - subflow->remote_key = mp_opt->sndr_key; + subflow_set_remote_key(msk, subflow, mp_opt); subflow->fully_established = 1; - subflow->can_ack = 1; WRITE_ONCE(msk->fully_established, true); + + if (subflow->is_mptfo) + mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } static struct sock *subflow_syn_recv_sock(const struct sock *sk, @@ -723,6 +786,8 @@ create_child: goto dispose_child; } + if (new_msk) + mptcp_copy_inaddrs(new_msk, child); subflow_drop_ctx(child); goto out; } @@ -750,10 +815,15 @@ create_child: ctx->conn = new_msk; new_msk = NULL; + /* set msk addresses early to ensure mptcp_pm_get_local_id() + * uses the correct data + */ + mptcp_copy_inaddrs(ctx->conn, child); + /* with OoO packets we can reach here without ingress * mpc option */ - if (mp_opt.suboptions & OPTIONS_MPTCP_MPC) + if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) mptcp_subflow_fully_established(ctx, &mp_opt); } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -1191,16 +1261,8 @@ static bool subflow_check_data_avail(struct sock *ssk) if (WARN_ON_ONCE(!skb)) goto no_data; - /* if msk lacks the remote key, this subflow must provide an - * MP_CAPABLE-based mapping - */ - if (unlikely(!READ_ONCE(msk->can_ack))) { - if (!subflow->mpc_map) - goto fallback; - WRITE_ONCE(msk->remote_key, subflow->remote_key); - WRITE_ONCE(msk->ack_seq, subflow->map_seq); - WRITE_ONCE(msk->can_ack, true); - } + if (unlikely(!READ_ONCE(msk->can_ack))) + goto fallback; old_ack = READ_ONCE(msk->ack_seq); ack_seq = mptcp_subflow_get_mapped_dsn(subflow); @@ -1473,6 +1535,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, mptcp_pm_get_flags_and_ifindex_by_id(msk, local_id, &flags, &ifindex); + subflow->remote_key_valid = 1; subflow->remote_key = msk->remote_key; subflow->local_key = msk->local_key; subflow->token = msk->token; @@ -1595,7 +1658,9 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) /* kernel sockets do not by default acquire net ref, but TCP timer * needs it. + * Update ns_tracker to current stack trace and refcounted tracker. */ + __netns_tracker_free(net, &sf->sk->ns_tracker, false); sf->sk->sk_net_refcnt = 1; get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); @@ -1738,16 +1803,16 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk) for (msk = head; msk; msk = next) { struct sock *sk = (struct sock *)msk; - bool slow, do_cancel_work; + bool do_cancel_work; sock_hold(sk); - slow = lock_sock_fast_nested(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); next = msk->dl_next; msk->first = NULL; msk->dl_next = NULL; do_cancel_work = __mptcp_close(sk, 0); - unlock_sock_fast(sk, slow); + release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); sock_put(sk); @@ -1864,6 +1929,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; + new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; new_ctx->remote_id = subflow_req->remote_id; new_ctx->token = subflow_req->token; @@ -1920,6 +1986,7 @@ void __init mptcp_subflow_init(void) subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops; subflow_request_sock_ipv4_ops.route_req = subflow_v4_route_req; + subflow_request_sock_ipv4_ops.send_synack = subflow_v4_send_synack; subflow_specific = ipv4_specific; subflow_specific.conn_request = subflow_v4_conn_request; @@ -1933,6 +2000,7 @@ void __init mptcp_subflow_init(void) #if IS_ENABLED(CONFIG_MPTCP_IPV6) subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops; subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req; + subflow_request_sock_ipv6_ops.send_synack = subflow_v6_send_synack; subflow_v6_specific = ipv6_specific; subflow_v6_specific.conn_request = subflow_v6_conn_request; diff --git a/net/mptcp/token.c b/net/mptcp/token.c index f52ee7b26aed..65430f314a68 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -287,8 +287,8 @@ EXPORT_SYMBOL_GPL(mptcp_token_get_sock); * This function returns the first mptcp connection structure found inside the * token container starting from the specified position, or NULL. * - * On successful iteration, the iterator is move to the next position and the - * the acquires a reference to the returned socket. + * On successful iteration, the iterator is moved to the next position and + * a reference to the returned socket is acquired. */ struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, long *s_num) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 4b8d04640ff3..0846bd75b1da 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -568,12 +568,6 @@ config NFT_TUNNEL This option adds the "tunnel" expression that you can use to set tunneling policies. -config NFT_OBJREF - tristate "Netfilter nf_tables stateful object reference module" - help - This option adds the "objref" expression that allows you to refer to - stateful objects, such as counters and quotas. - config NFT_QUEUE depends on NETFILTER_NETLINK_QUEUE tristate "Netfilter nf_tables queue module" diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 0f060d100880..1d4db1943936 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -86,7 +86,8 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o nft_last.o \ - nft_counter.o nft_chain_route.o nf_tables_offload.o \ + nft_counter.o nft_objref.o nft_inner.o \ + nft_chain_route.o nf_tables_offload.o \ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \ nft_set_pipapo.o @@ -104,7 +105,6 @@ obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_FLOW_OFFLOAD) += nft_flow_offload.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o -obj-$(CONFIG_NFT_OBJREF) += nft_objref.o obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 6e391308431d..7499192af586 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -42,31 +42,8 @@ #define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE) /* Max muber of elements in the array block when tuned */ #define AHASH_MAX_TUNED 64 - #define AHASH_MAX(h) ((h)->bucketsize) -/* Max number of elements can be tuned */ -#ifdef IP_SET_HASH_WITH_MULTI -static u8 -tune_bucketsize(u8 curr, u32 multi) -{ - u32 n; - - if (multi < curr) - return curr; - - n = curr + AHASH_INIT_SIZE; - /* Currently, at listing one hash bucket must fit into a message. - * Therefore we have a hard limit here. - */ - return n > curr && n <= AHASH_MAX_TUNED ? n : curr; -} -#define TUNE_BUCKETSIZE(h, multi) \ - ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi)) -#else -#define TUNE_BUCKETSIZE(h, multi) -#endif - /* A hash bucket */ struct hbucket { struct rcu_head rcu; /* for call_rcu */ @@ -936,7 +913,12 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto set_full; /* Create a new slot */ if (n->pos >= n->size) { - TUNE_BUCKETSIZE(h, multi); +#ifdef IP_SET_HASH_WITH_MULTI + if (h->bucketsize >= AHASH_MAX_TUNED) + goto set_full; + else if (h->bucketsize <= multi) + h->bucketsize += AHASH_INIT_SIZE; +#endif if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index dd30c03d5a23..75d556d71652 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -151,18 +151,16 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE) return -ERANGE; - if (retried) { + if (retried) ip = ntohl(h->next.ip); - e.ip = htonl(ip); - } for (; ip <= ip_to;) { + e.ip = htonl(ip); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ip += hosts; - e.ip = htonl(ip); - if (e.ip == 0) + if (ip == 0) return 0; ret = 0; diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index f9b16f2b2219..fdacbc3c15be 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -599,13 +599,19 @@ static const struct seq_operations ip_vs_app_seq_ops = { int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->app_list); - proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops, - sizeof(struct seq_net_private)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, + &ip_vs_app_seq_ops, + sizeof(struct seq_net_private))) + return -ENOMEM; +#endif return 0; } void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { unregister_ip_vs_app(ipvs, NULL /* all */); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_app", ipvs->net->proc_net); +#endif } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index fb67f1ca2495..13534e02346c 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1265,8 +1265,8 @@ static inline int todrop_entry(struct ip_vs_conn *cp) * The drop rate array needs tuning for real environments. * Called from timer bh only => no locking */ - static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; - static char todrop_counter[9] = {0}; + static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; + static signed char todrop_counter[9] = {0}; int i; /* if the conn entry hasn't lasted for 60 seconds, don't drop it. @@ -1308,7 +1308,7 @@ void ip_vs_random_dropentry(struct netns_ipvs *ipvs) * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { - unsigned int hash = prandom_u32() & ip_vs_conn_tab_mask; + unsigned int hash = get_random_u32() & ip_vs_conn_tab_mask; hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->ipvs != ipvs) @@ -1447,20 +1447,36 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { atomic_set(&ipvs->conn_count, 0); - proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, - &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state)); - proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, - &ip_vs_conn_sync_seq_ops, - sizeof(struct ip_vs_iter_state)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, + &ip_vs_conn_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn; + + if (!proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, + &ip_vs_conn_sync_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn_sync; +#endif + return 0; + +#ifdef CONFIG_PROC_FS +err_conn_sync: + remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); +err_conn: + return -ENOMEM; +#endif } void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net); +#endif } int __init ip_vs_conn_init(void) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 988222fff9f0..4d62059a6021 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2296,13 +2296,13 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) u64 conns, inpkts, outpkts, inbytes, outbytes; do { - start = u64_stats_fetch_begin_irq(&u->syncp); + start = u64_stats_fetch_begin(&u->syncp); conns = u->cnt.conns; inpkts = u->cnt.inpkts; outpkts = u->cnt.outpkts; inbytes = u->cnt.inbytes; outbytes = u->cnt.outbytes; - } while (u64_stats_fetch_retry_irq(&u->syncp, start)); + } while (u64_stats_fetch_retry(&u->syncp, start)); seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n", i, (u64)conns, (u64)inpkts, diff --git a/net/netfilter/ipvs/ip_vs_twos.c b/net/netfilter/ipvs/ip_vs_twos.c index acb55d8393ef..f2579fc9c75b 100644 --- a/net/netfilter/ipvs/ip_vs_twos.c +++ b/net/netfilter/ipvs/ip_vs_twos.c @@ -71,8 +71,8 @@ static struct ip_vs_dest *ip_vs_twos_schedule(struct ip_vs_service *svc, * from 0 to total_weight */ total_weight += 1; - rweight1 = prandom_u32() % total_weight; - rweight2 = prandom_u32() % total_weight; + rweight1 = prandom_u32_max(total_weight); + rweight2 = prandom_u32_max(total_weight); /* Pick two weighted servers */ list_for_each_entry_rcu(dest, &svc->destinations, n_list) { diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 8639e7efd0e2..24002bc61e07 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -191,19 +191,16 @@ BTF_ID(struct, nf_conn___init) /* Check writes into `struct nf_conn` */ static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { - const struct btf_type *ncit; - const struct btf_type *nct; + const struct btf_type *ncit, *nct, *t; size_t end; - ncit = btf_type_by_id(btf, btf_nf_conn_ids[1]); - nct = btf_type_by_id(btf, btf_nf_conn_ids[0]); - + ncit = btf_type_by_id(reg->btf, btf_nf_conn_ids[1]); + nct = btf_type_by_id(reg->btf, btf_nf_conn_ids[0]); + t = btf_type_by_id(reg->btf, reg->btf_id); if (t != nct && t != ncit) { bpf_log(log, "only read is supported\n"); return -EACCES; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f97bda06d2a9..b96338b4bf36 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -211,28 +211,24 @@ static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, unsigned int zoneid, const struct net *net) { - struct { - struct nf_conntrack_man src; - union nf_inet_addr dst_addr; - unsigned int zone; - u32 net_mix; - u16 dport; - u16 proto; - } __aligned(SIPHASH_ALIGNMENT) combined; + u64 a, b, c, d; get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd)); - memset(&combined, 0, sizeof(combined)); + /* The direction must be ignored, handle usable tuplehash members manually */ + a = (u64)tuple->src.u3.all[0] << 32 | tuple->src.u3.all[3]; + b = (u64)tuple->dst.u3.all[0] << 32 | tuple->dst.u3.all[3]; - /* The direction must be ignored, so handle usable members manually. */ - combined.src = tuple->src; - combined.dst_addr = tuple->dst.u3; - combined.zone = zoneid; - combined.net_mix = net_hash_mix(net); - combined.dport = (__force __u16)tuple->dst.u.all; - combined.proto = tuple->dst.protonum; + c = (__force u64)tuple->src.u.all << 32 | (__force u64)tuple->dst.u.all << 16; + c |= tuple->dst.protonum; - return (u32)siphash(&combined, sizeof(combined), &nf_conntrack_hash_rnd); + d = (u64)zoneid << 32 | net_hash_mix(net); + + /* IPv4: u3.all[1,2,3] == 0 */ + c ^= (u64)tuple->src.u3.all[1] << 32 | tuple->src.u3.all[2]; + d += (u64)tuple->dst.u3.all[1] << 32 | tuple->dst.u3.all[2]; + + return (u32)siphash_4u64(a, b, c, d, &nf_conntrack_hash_rnd); } static u32 scale_hash(u32 hash) @@ -1781,7 +1777,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } #ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = READ_ONCE(exp->master->mark); #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK ct->secmark = exp->master->secmark; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ff737a76052e..48ea6d0264b5 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -26,7 +26,9 @@ #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_log.h> +#include <net/ip.h> static DEFINE_MUTEX(nf_ct_helper_mutex); struct hlist_head *nf_ct_helper_hash __read_mostly; @@ -240,6 +242,104 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); +/* 'skb' should already be pulled to nh_ofs. */ +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + unsigned int protoff; + int err; + + if (ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + if (helper->tuple.src.l3num != NFPROTO_UNSPEC && + helper->tuple.src.l3num != proto) + return NF_ACCEPT; + + switch (proto) { + case NFPROTO_IPV4: + protoff = ip_hdrlen(skb); + proto = ip_hdr(skb)->protocol; + break; + case NFPROTO_IPV6: { + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + int ofs; + + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + protoff = ofs; + proto = nexthdr; + break; + } + default: + WARN_ONCE(1, "helper invoked on non-IP family!"); + return NF_DROP; + } + + if (helper->tuple.dst.protonum != proto) + return NF_ACCEPT; + + err = helper->help(skb, protoff, ct, ctinfo); + if (err != NF_ACCEPT) + return err; + + /* Adjust seqs after helper. This is needed due to some helpers (e.g., + * FTP with NAT) adusting the TCP payload size when mangling IP + * addresses and/or port numbers in the text-based control connection. + */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) + return NF_DROP; + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_ct_helper); + +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + int ret = 0; + + helper = nf_conntrack_helper_try_module_get(name, family, proto); + if (!helper) + return -EINVAL; + + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (!help) { + nf_conntrack_helper_put(helper); + return -ENOMEM; + } +#if IS_ENABLED(CONFIG_NF_NAT) + if (nat) { + ret = nf_nat_helper_try_module_get(name, family, proto); + if (ret) { + nf_conntrack_helper_put(helper); + return ret; + } + } +#endif + rcu_assign_pointer(help->helper, helper); + *hp = helper; + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_add_helper); + /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7562b215b932..d71150a40fb0 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -328,9 +328,9 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +static int ctnetlink_dump_mark(struct sk_buff *skb, u32 mark) { - if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) + if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; @@ -543,7 +543,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_mark(skb, READ_ONCE(ct->mark)) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -722,6 +722,7 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; + u32 mark; int err; if (events & (1 << IPCT_DESTROY)) { @@ -826,8 +827,9 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((events & (1 << IPCT_MARK) || ct->mark) - && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if ((events & (1 << IPCT_MARK) || mark) && + ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -1154,7 +1156,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); @@ -2002,9 +2004,9 @@ static void ctnetlink_change_mark(struct nf_conn *ct, mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); - newmark = (ct->mark & mask) ^ mark; - if (newmark != ct->mark) - ct->mark = newmark; + newmark = (READ_ONCE(ct->mark) & mask) ^ mark; + if (newmark != READ_ONCE(ct->mark)) + WRITE_ONCE(ct->mark, newmark); } #endif @@ -2669,6 +2671,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; + u32 mark; zone = nf_ct_zone(ct); @@ -2730,7 +2733,8 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if (mark && ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ffe84c5a82c..bca839ab1ae8 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -366,7 +366,7 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) - seq_printf(s, "mark=%u ", ct->mark); + seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif ct_show_secctx(s, ct); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index b04645ced89b..00b522890d77 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -1098,6 +1098,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, struct flow_block_cb *block_cb, *next; int err = 0; + down_write(&flowtable->flow_block_lock); switch (cmd) { case FLOW_BLOCK_BIND: list_splice(&bo->cb_list, &flowtable->flow_block.cb_list); @@ -1112,6 +1113,7 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, WARN_ON_ONCE(1); err = -EOPNOTSUPP; } + up_write(&flowtable->flow_block_lock); return err; } @@ -1168,7 +1170,9 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable, extack); + down_write(&flowtable->flow_block_lock); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo); + up_write(&flowtable->flow_block_lock); if (err < 0) return err; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d8e6380f6337..e29e4ccb5c5a 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -468,7 +468,7 @@ find_free_id: if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) off = (ntohs(*keyptr) - ntohs(range->base_proto.all)); else - off = prandom_u32(); + off = get_random_u16(); attempts = range_size; if (attempts > max_attempts) @@ -490,7 +490,7 @@ another_round: if (attempts >= range_size || attempts < 16) return; attempts /= 2; - off = prandom_u32(); + off = get_random_u16(); goto another_round; } @@ -1152,7 +1152,16 @@ static int __init nf_nat_init(void) WARN_ON(nf_nat_hook != NULL); RCU_INIT_POINTER(nf_nat_hook, &nat_hook); - return register_nf_nat_bpf(); + ret = register_nf_nat_bpf(); + if (ret < 0) { + RCU_INIT_POINTER(nf_nat_hook, NULL); + nf_ct_helper_expectfn_unregister(&follow_master_nat); + synchronize_net(); + unregister_pernet_subsys(&nat_net_ops); + kvfree(nf_nat_bysource); + } + + return ret; } static void __exit nf_nat_cleanup(void) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a0653a8dfa82..6269b0d9977c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1534,10 +1534,10 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats) for_each_possible_cpu(cpu) { cpu_stats = per_cpu_ptr(stats, cpu); do { - seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + seq = u64_stats_fetch_begin(&cpu_stats->syncp); pkts = cpu_stats->pkts; bytes = cpu_stats->bytes; - } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq)); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, seq)); total.pkts += pkts; total.bytes += bytes; } @@ -2759,7 +2759,7 @@ static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = { }; static int nf_tables_fill_expr_info(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->type->name)) goto nla_put_failure; @@ -2769,7 +2769,7 @@ static int nf_tables_fill_expr_info(struct sk_buff *skb, NFTA_EXPR_DATA); if (data == NULL) goto nla_put_failure; - if (expr->ops->dump(skb, expr) < 0) + if (expr->ops->dump(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, data); } @@ -2781,14 +2781,14 @@ nla_put_failure: }; int nft_expr_dump(struct sk_buff *skb, unsigned int attr, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; - if (nf_tables_fill_expr_info(skb, expr) < 0) + if (nf_tables_fill_expr_info(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; @@ -2857,6 +2857,43 @@ err1: return err; } +int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, + struct nft_expr_info *info) +{ + struct nlattr *tb[NFTA_EXPR_MAX + 1]; + const struct nft_expr_type *type; + int err; + + err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla, + nft_expr_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_EXPR_DATA]) + return -EINVAL; + + type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); + if (IS_ERR(type)) + return PTR_ERR(type); + + if (!type->inner_ops) + return -EOPNOTSUPP; + + err = nla_parse_nested_deprecated(info->tb, type->maxattr, + tb[NFTA_EXPR_DATA], + type->policy, NULL); + if (err < 0) + goto err_nla_parse; + + info->attr = nla; + info->ops = type->inner_ops; + + return 0; + +err_nla_parse: + return err; +} + static int nf_tables_newexpr(const struct nft_ctx *ctx, const struct nft_expr_info *expr_info, struct nft_expr *expr) @@ -2997,7 +3034,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct nft_rule *rule, u64 handle) + const struct nft_rule *rule, u64 handle, + bool reset) { struct nlmsghdr *nlh; const struct nft_expr *expr, *next; @@ -3030,7 +3068,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, if (list == NULL) goto nla_put_failure; nft_rule_for_each_expr(expr, next, rule) { - if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, list); @@ -3081,7 +3119,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, - ctx->chain, rule, handle); + ctx->chain, rule, handle, false); if (err < 0) { kfree_skb(skb); goto err; @@ -3102,7 +3140,8 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, unsigned int *idx, struct netlink_callback *cb, const struct nft_table *table, - const struct nft_chain *chain) + const struct nft_chain *chain, + bool reset) { struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; @@ -3129,7 +3168,7 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, handle) < 0) + table, chain, rule, handle, reset) < 0) return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3152,6 +3191,10 @@ static int nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; + bool reset = false; + + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) + reset = true; rcu_read_lock(); nft_net = nft_pernet(net); @@ -3176,14 +3219,15 @@ static int nf_tables_dump_rules(struct sk_buff *skb, if (!nft_is_active(net, chain)) continue; __nf_tables_dump_rules(skb, &idx, - cb, table, chain); + cb, table, chain, reset); break; } goto done; } list_for_each_entry_rcu(chain, &table->chains, list) { - if (__nf_tables_dump_rules(skb, &idx, cb, table, chain)) + if (__nf_tables_dump_rules(skb, &idx, + cb, table, chain, reset)) goto done; } @@ -3254,6 +3298,7 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; + bool reset = false; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { @@ -3290,9 +3335,12 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, if (!skb2) return -ENOMEM; + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) + reset = true; + err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, - family, table, chain, rule, 0); + family, table, chain, rule, 0, reset); if (err < 0) goto err_fill_rule_info; @@ -4067,7 +4115,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (set->num_exprs == 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR); - if (nf_tables_fill_expr_info(skb, set->exprs[0]) < 0) + if (nf_tables_fill_expr_info(skb, set->exprs[0], false) < 0) goto nla_put_failure; nla_nest_end(skb, nest); @@ -4078,7 +4126,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, for (i = 0; i < set->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, - set->exprs[i]) < 0) + set->exprs[i], false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -4909,7 +4957,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, if (num_exprs == 1) { expr = nft_setelem_expr_at(elem_expr, 0); - if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr) < 0) + if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, false) < 0) return -1; return 0; @@ -4920,7 +4968,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, nft_setelem_expr_foreach(expr, elem_expr, size) { expr = nft_setelem_expr_at(elem_expr, size); - if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -5865,8 +5913,9 @@ static bool nft_setelem_valid_key_end(const struct nft_set *set, (NFT_SET_CONCAT | NFT_SET_INTERVAL)) { if (flags & NFT_SET_ELEM_INTERVAL_END) return false; - if (!nla[NFTA_SET_ELEM_KEY_END] && - !(flags & NFT_SET_ELEM_CATCHALL)) + + if (nla[NFTA_SET_ELEM_KEY_END] && + flags & NFT_SET_ELEM_CATCHALL) return false; } else { if (nla[NFTA_SET_ELEM_KEY_END]) @@ -5957,7 +6006,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, &timeout); if (err) return err; - } else if (set->flags & NFT_SET_TIMEOUT) { + } else if (set->flags & NFT_SET_TIMEOUT && + !(flags & NFT_SET_ELEM_INTERVAL_END)) { timeout = set->timeout; } @@ -6023,7 +6073,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EOPNOTSUPP; goto err_set_elem_expr; } - } else if (set->num_exprs > 0) { + } else if (set->num_exprs > 0 && + !(flags & NFT_SET_ELEM_INTERVAL_END)) { err = nft_set_elem_expr_clone(ctx, set, expr_array); if (err < 0) goto err_set_elem_expr_clone; @@ -8273,6 +8324,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, + [NFT_MSG_GETRULE_RESET] = { + .call = nf_tables_getrule, + .type = NFNL_CB_RCU, + .attr_count = NFTA_RULE_MAX, + .policy = nft_rule_policy, + }, [NFT_MSG_DELRULE] = { .call = nf_tables_delrule, .type = NFNL_CB_BATCH, @@ -8464,9 +8521,6 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); - nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: @@ -8972,6 +9026,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); + + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -10029,6 +10086,8 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, nft_net = nft_pernet(net); deleted = 0; mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nf_tables_destroy_list)) + rcu_barrier(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && @@ -10087,7 +10146,8 @@ static void __net_exit nf_tables_exit_net(struct net *net) struct nftables_pernet *nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); - if (!list_empty(&nft_net->commit_list)) + if (!list_empty(&nft_net->commit_list) || + !list_empty(&nft_net->module_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); mutex_unlock(&nft_net->commit_mutex); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index cee3e4e905ec..709a736c301c 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -340,6 +340,8 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_exthdr_type, &nft_last_type, &nft_counter_type, + &nft_objref_type, + &nft_inner_type, }; static struct nft_object_type *nft_basic_objects[] = { diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 9c44518cb70f..6d18fb346868 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -294,6 +294,7 @@ replay: nfnl_lock(subsys_id); if (nfnl_dereference_protected(subsys_id) != ss || nfnetlink_find_client(type, ss) != nc) { + nfnl_unlock(subsys_id); err = -EAGAIN; break; } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index e6e402b247d0..84eae7cabc67 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -232,7 +232,8 @@ static int nft_bitwise_dump_shift(struct sk_buff *skb, return 0; } -static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_bitwise_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_bitwise *priv = nft_expr_priv(expr); int err = 0; @@ -393,7 +394,8 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx, } static int -nft_bitwise_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +nft_bitwise_fast_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); struct nft_data data; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index f952a80275a8..b66647a5a171 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -148,7 +148,8 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, priv->len); } -static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_byteorder_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_byteorder *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 963cf831799c..6eb21a4f5698 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -92,7 +92,8 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return 0; } -static int nft_cmp_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_cmp_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_cmp_expr *priv = nft_expr_priv(expr); @@ -253,7 +254,8 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx, return __nft_cmp_offload(ctx, flow, &cmp); } -static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_cmp_fast_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ; @@ -347,7 +349,8 @@ static int nft_cmp16_fast_offload(struct nft_offload_ctx *ctx, return __nft_cmp_offload(ctx, flow, &cmp); } -static int nft_cmp16_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_cmp16_fast_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index c16172427622..5284cd2ad532 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -324,7 +324,8 @@ static int nft_extension_dump_info(struct sk_buff *skb, int attr, return 0; } -static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_target_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); @@ -572,12 +573,14 @@ nla_put_failure: return -1; } -static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_match_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { return __nft_match_dump(skb, expr, nft_expr_priv(expr)); } -static int nft_match_large_dump(struct sk_buff *skb, const struct nft_expr *e) +static int nft_match_large_dump(struct sk_buff *skb, + const struct nft_expr *e, bool reset) { struct nft_xt_match_priv *priv = nft_expr_priv(e); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index d657f999a11b..de9d1980df69 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -185,7 +185,8 @@ static void nft_connlimit_eval(const struct nft_expr *expr, nft_connlimit_do_eval(priv, regs, pkt, NULL); } -static int nft_connlimit_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_connlimit_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_connlimit *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index f4d3573e8782..dccc68a5135a 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -201,11 +201,12 @@ void nft_counter_eval(const struct nft_expr *expr, struct nft_regs *regs, nft_counter_do_eval(priv, regs, pkt); } -static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_counter_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - return nft_counter_do_dump(skb, priv, false); + return nft_counter_do_dump(skb, priv, reset); } static int nft_counter_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a3f01f209a53..c68e2151defe 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -98,7 +98,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - *dest = ct->mark; + *dest = READ_ONCE(ct->mark); return; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -297,8 +297,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr, switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - if (ct->mark != value) { - ct->mark = value; + if (READ_ONCE(ct->mark) != value) { + WRITE_ONCE(ct->mark, value); nf_conntrack_event_cache(IPCT_MARK, ct); } break; @@ -641,7 +641,8 @@ static void nft_ct_set_destroy(const struct nft_ctx *ctx, nf_ct_netns_put(ctx->net, ctx->family); } -static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ct_get_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ct *priv = nft_expr_priv(expr); @@ -703,7 +704,8 @@ static bool nft_ct_get_reduce(struct nft_regs_track *track, return nft_expr_reduce_bitwise(track, expr); } -static int nft_ct_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ct_set_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ct *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index 63507402716d..e5739a59ebf1 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -44,7 +44,8 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx, sizeof(int)); } -static int nft_dup_netdev_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dup_netdev_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_dup_netdev *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 6983e6ddeef9..274579b1696e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -357,7 +357,8 @@ static void nft_dynset_destroy(const struct nft_ctx *ctx, nf_tables_destroy_set(ctx, priv->set); } -static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dynset_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_dynset *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_DYNSET_F_INV : 0; @@ -379,7 +380,7 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) if (priv->set->num_exprs == 0) { if (priv->num_exprs == 1) { if (nft_expr_dump(skb, NFTA_DYNSET_EXPR, - priv->expr_array[0])) + priv->expr_array[0], reset)) goto nla_put_failure; } else if (priv->num_exprs > 1) { struct nlattr *nest; @@ -390,7 +391,7 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) for (i = 0; i < priv->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, - priv->expr_array[i])) + priv->expr_array[i], reset)) goto nla_put_failure; } nla_nest_end(skb, nest); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a67ea9c3ae57..a54a7f772cec 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -13,7 +13,6 @@ #include <linux/sctp.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> -#include <net/sctp/sctp.h> #include <net/tcp.h> struct nft_exthdr { @@ -576,7 +575,8 @@ nla_put_failure: return -1; } -static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_exthdr_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_exthdr *priv = nft_expr_priv(expr); @@ -586,7 +586,8 @@ static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } -static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_exthdr_dump_set(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_exthdr *priv = nft_expr_priv(expr); @@ -596,7 +597,8 @@ static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } -static int nft_exthdr_dump_strip(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_exthdr_dump_strip(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_exthdr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 1f12d7ade606..6e049fd48760 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -118,7 +118,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } EXPORT_SYMBOL_GPL(nft_fib_init); -int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr) +int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_fib *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a25c88bc8b75..e860d8fe0e5e 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -433,7 +433,8 @@ static void nft_flow_offload_destroy(const struct nft_ctx *ctx, nf_ct_netns_put(ctx->net, ctx->family); } -static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_flow_offload_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_flow_offload *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 7c5876dc9ff2..7b9d4d1bd17c 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -56,7 +56,8 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx, sizeof(int)); } -static int nft_fwd_netdev_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_fwd_netdev_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_fwd_netdev *priv = nft_expr_priv(expr); @@ -186,7 +187,8 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, addr_len); } -static int nft_fwd_neigh_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_fwd_neigh_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_fwd_neigh *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index e5631e88b285..ee8d487b69c0 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -139,7 +139,7 @@ static int nft_symhash_init(const struct nft_ctx *ctx, } static int nft_jhash_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_jhash *priv = nft_expr_priv(expr); @@ -176,7 +176,7 @@ static bool nft_jhash_reduce(struct nft_regs_track *track, } static int nft_symhash_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_symhash *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 5f28b21abc7d..c9d2f7c29f53 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -147,7 +147,8 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, } } -static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_immediate_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c new file mode 100644 index 000000000000..28e2873ba24e --- /dev/null +++ b/net/netfilter/nft_inner.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 Pablo Neira Ayuso <pablo@netfilter.org> + */ + +#include <linux/kernel.h> +#include <linux/if_vlan.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_meta.h> +#include <net/netfilter/nf_tables_offload.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <net/gre.h> +#include <net/geneve.h> +#include <net/ip.h> +#include <linux/icmpv6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> + +static DEFINE_PER_CPU(struct nft_inner_tun_ctx, nft_pcpu_tun_ctx); + +/* Same layout as nft_expr but it embeds the private expression data area. */ +struct __nft_expr { + const struct nft_expr_ops *ops; + union { + struct nft_payload payload; + struct nft_meta meta; + } __attribute__((aligned(__alignof__(u64)))); +}; + +enum { + NFT_INNER_EXPR_PAYLOAD, + NFT_INNER_EXPR_META, +}; + +struct nft_inner { + u8 flags; + u8 hdrsize; + u8 type; + u8 expr_type; + + struct __nft_expr expr; +}; + +static int nft_inner_parse_l2l3(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx, u32 off) +{ + __be16 llproto, outer_llproto; + u32 nhoff, thoff; + + if (priv->flags & NFT_INNER_LL) { + struct vlan_ethhdr *veth, _veth; + struct ethhdr *eth, _eth; + u32 hdrsize; + + eth = skb_header_pointer(pkt->skb, off, sizeof(_eth), &_eth); + if (!eth) + return -1; + + switch (eth->h_proto) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + llproto = eth->h_proto; + hdrsize = sizeof(_eth); + break; + case htons(ETH_P_8021Q): + veth = skb_header_pointer(pkt->skb, off, sizeof(_veth), &_veth); + if (!veth) + return -1; + + outer_llproto = veth->h_vlan_encapsulated_proto; + llproto = veth->h_vlan_proto; + hdrsize = sizeof(_veth); + break; + default: + return -1; + } + + ctx->inner_lloff = off; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_LL; + off += hdrsize; + } else { + struct iphdr *iph; + u32 _version; + + iph = skb_header_pointer(pkt->skb, off, sizeof(_version), &_version); + if (!iph) + return -1; + + switch (iph->version) { + case 4: + llproto = htons(ETH_P_IP); + break; + case 6: + llproto = htons(ETH_P_IPV6); + break; + default: + return -1; + } + } + + ctx->llproto = llproto; + if (llproto == htons(ETH_P_8021Q)) + llproto = outer_llproto; + + nhoff = off; + + switch (llproto) { + case htons(ETH_P_IP): { + struct iphdr *iph, _iph; + + iph = skb_header_pointer(pkt->skb, nhoff, sizeof(_iph), &_iph); + if (!iph) + return -1; + + if (iph->ihl < 5 || iph->version != 4) + return -1; + + ctx->inner_nhoff = nhoff; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_NH; + + thoff = nhoff + (iph->ihl * 4); + if ((ntohs(iph->frag_off) & IP_OFFSET) == 0) { + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; + ctx->inner_thoff = thoff; + ctx->l4proto = iph->protocol; + } + } + break; + case htons(ETH_P_IPV6): { + struct ipv6hdr *ip6h, _ip6h; + int fh_flags = IP6_FH_F_AUTH; + unsigned short fragoff; + int l4proto; + + ip6h = skb_header_pointer(pkt->skb, nhoff, sizeof(_ip6h), &_ip6h); + if (!ip6h) + return -1; + + if (ip6h->version != 6) + return -1; + + ctx->inner_nhoff = nhoff; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_NH; + + thoff = nhoff; + l4proto = ipv6_find_hdr(pkt->skb, &thoff, -1, &fragoff, &fh_flags); + if (l4proto < 0 || thoff > U16_MAX) + return -1; + + if (fragoff == 0) { + thoff = nhoff + sizeof(_ip6h); + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; + ctx->inner_thoff = thoff; + ctx->l4proto = l4proto; + } + } + break; + default: + return -1; + } + + return 0; +} + +static int nft_inner_parse_tunhdr(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx, u32 *off) +{ + if (pkt->tprot == IPPROTO_GRE) { + ctx->inner_tunoff = pkt->thoff; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TUN; + return 0; + } + + if (pkt->tprot != IPPROTO_UDP) + return -1; + + ctx->inner_tunoff = *off; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TUN; + *off += priv->hdrsize; + + switch (priv->type) { + case NFT_INNER_GENEVE: { + struct genevehdr *gnvh, _gnvh; + + gnvh = skb_header_pointer(pkt->skb, pkt->inneroff, + sizeof(_gnvh), &_gnvh); + if (!gnvh) + return -1; + + *off += gnvh->opt_len * 4; + } + break; + default: + break; + } + + return 0; +} + +static int nft_inner_parse(const struct nft_inner *priv, + struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + struct nft_inner_tun_ctx ctx = {}; + u32 off = pkt->inneroff; + + if (priv->flags & NFT_INNER_HDRSIZE && + nft_inner_parse_tunhdr(priv, pkt, &ctx, &off) < 0) + return -1; + + if (priv->flags & (NFT_INNER_LL | NFT_INNER_NH)) { + if (nft_inner_parse_l2l3(priv, pkt, &ctx, off) < 0) + return -1; + } else if (priv->flags & NFT_INNER_TH) { + ctx.inner_thoff = off; + ctx.flags |= NFT_PAYLOAD_CTX_INNER_TH; + } + + *tun_ctx = ctx; + tun_ctx->type = priv->type; + pkt->flags |= NFT_PKTINFO_INNER_FULL; + + return 0; +} + +static bool nft_inner_parse_needed(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + const struct nft_inner_tun_ctx *tun_ctx) +{ + if (!(pkt->flags & NFT_PKTINFO_INNER_FULL)) + return true; + + if (priv->type != tun_ctx->type) + return true; + + return false; +} + +static void nft_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_inner_tun_ctx *tun_ctx = this_cpu_ptr(&nft_pcpu_tun_ctx); + const struct nft_inner *priv = nft_expr_priv(expr); + + if (nft_payload_inner_offset(pkt) < 0) + goto err; + + if (nft_inner_parse_needed(priv, pkt, tun_ctx) && + nft_inner_parse(priv, (struct nft_pktinfo *)pkt, tun_ctx) < 0) + goto err; + + switch (priv->expr_type) { + case NFT_INNER_EXPR_PAYLOAD: + nft_payload_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, tun_ctx); + break; + case NFT_INNER_EXPR_META: + nft_meta_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, tun_ctx); + break; + default: + WARN_ON_ONCE(1); + goto err; + } + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_inner_policy[NFTA_INNER_MAX + 1] = { + [NFTA_INNER_NUM] = { .type = NLA_U32 }, + [NFTA_INNER_FLAGS] = { .type = NLA_U32 }, + [NFTA_INNER_HDRSIZE] = { .type = NLA_U32 }, + [NFTA_INNER_TYPE] = { .type = NLA_U32 }, + [NFTA_INNER_EXPR] = { .type = NLA_NESTED }, +}; + +struct nft_expr_info { + const struct nft_expr_ops *ops; + const struct nlattr *attr; + struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; +}; + +static int nft_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_inner *priv = nft_expr_priv(expr); + u32 flags, hdrsize, type, num; + struct nft_expr_info expr_info; + int err; + + if (!tb[NFTA_INNER_FLAGS] || + !tb[NFTA_INNER_HDRSIZE] || + !tb[NFTA_INNER_TYPE] || + !tb[NFTA_INNER_EXPR]) + return -EINVAL; + + flags = ntohl(nla_get_be32(tb[NFTA_INNER_FLAGS])); + if (flags & ~NFT_INNER_MASK) + return -EOPNOTSUPP; + + num = ntohl(nla_get_be32(tb[NFTA_INNER_NUM])); + if (num != 0) + return -EOPNOTSUPP; + + hdrsize = ntohl(nla_get_be32(tb[NFTA_INNER_HDRSIZE])); + type = ntohl(nla_get_be32(tb[NFTA_INNER_TYPE])); + + if (type > U8_MAX) + return -EINVAL; + + if (flags & NFT_INNER_HDRSIZE) { + if (hdrsize == 0 || hdrsize > 64) + return -EOPNOTSUPP; + } + + priv->flags = flags; + priv->hdrsize = hdrsize; + priv->type = type; + + err = nft_expr_inner_parse(ctx, tb[NFTA_INNER_EXPR], &expr_info); + if (err < 0) + return err; + + priv->expr.ops = expr_info.ops; + + if (!strcmp(expr_info.ops->type->name, "payload")) + priv->expr_type = NFT_INNER_EXPR_PAYLOAD; + else if (!strcmp(expr_info.ops->type->name, "meta")) + priv->expr_type = NFT_INNER_EXPR_META; + else + return -EINVAL; + + err = expr_info.ops->init(ctx, (struct nft_expr *)&priv->expr, + (const struct nlattr * const*)expr_info.tb); + if (err < 0) + return err; + + return 0; +} + +static int nft_inner_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) +{ + const struct nft_inner *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_INNER_NUM, htonl(0)) || + nla_put_be32(skb, NFTA_INNER_TYPE, htonl(priv->type)) || + nla_put_be32(skb, NFTA_INNER_FLAGS, htonl(priv->flags)) || + nla_put_be32(skb, NFTA_INNER_HDRSIZE, htonl(priv->hdrsize))) + goto nla_put_failure; + + if (nft_expr_dump(skb, NFTA_INNER_EXPR, + (struct nft_expr *)&priv->expr, reset) < 0) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static const struct nft_expr_ops nft_inner_ops = { + .type = &nft_inner_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_inner)), + .eval = nft_inner_eval, + .init = nft_inner_init, + .dump = nft_inner_dump, +}; + +struct nft_expr_type nft_inner_type __read_mostly = { + .name = "inner", + .ops = &nft_inner_ops, + .policy = nft_inner_policy, + .maxattr = NFTA_INNER_MAX, + .owner = THIS_MODULE, +}; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index bb15a55dad5c..7f2bda6641bd 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -65,7 +65,8 @@ static void nft_last_eval(const struct nft_expr *expr, WRITE_ONCE(last->set, 1); } -static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_last_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_last_priv *priv = nft_expr_priv(expr); struct nft_last *last = priv->last; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 981addb2d051..145dc62c6247 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -193,7 +193,8 @@ static int nft_limit_pkts_init(const struct nft_ctx *ctx, return 0; } -static int nft_limit_pkts_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_limit_pkts_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_limit_priv_pkts *priv = nft_expr_priv(expr); @@ -251,7 +252,7 @@ static int nft_limit_bytes_init(const struct nft_ctx *ctx, } static int nft_limit_bytes_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_limit_priv *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 0e13c003f0c1..5defe6e4fd98 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -241,7 +241,8 @@ static void nft_log_destroy(const struct nft_ctx *ctx, nf_logger_put(ctx->family, li->type); } -static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_log_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_log *priv = nft_expr_priv(expr); const struct nf_loginfo *li = &priv->loginfo; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index dfae12759c7c..cae5a6724163 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -178,7 +178,8 @@ static void nft_lookup_destroy(const struct nft_ctx *ctx, nf_tables_destroy_set(ctx, priv->set); } -static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_lookup_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_lookup *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_LOOKUP_F_INV : 0; diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 2a0adc497bbb..e55e455275c4 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -73,7 +73,8 @@ static int nft_masq_init(const struct nft_ctx *ctx, return nf_ct_netns_get(ctx->net, ctx->family); } -static int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_masq_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_masq *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 55d2d49c3425..e384e0de7a54 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -669,7 +669,7 @@ int nft_meta_set_init(const struct nft_ctx *ctx, EXPORT_SYMBOL_GPL(nft_meta_set_init); int nft_meta_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -684,7 +684,8 @@ nla_put_failure: } EXPORT_SYMBOL_GPL(nft_meta_get_dump); -int nft_meta_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +int nft_meta_set_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -831,9 +832,71 @@ nft_meta_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EINVAL); } +static int nft_meta_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_meta *priv = nft_expr_priv(expr); + unsigned int len; + + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); + switch (priv->key) { + case NFT_META_PROTOCOL: + len = sizeof(u16); + break; + case NFT_META_L4PROTO: + len = sizeof(u32); + break; + default: + return -EOPNOTSUPP; + } + priv->len = len; + + return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); +} + +void nft_meta_inner_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + + switch (priv->key) { + case NFT_META_PROTOCOL: + nft_reg_store16(dest, (__force u16)tun_ctx->llproto); + break; + case NFT_META_L4PROTO: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH)) + goto err; + + nft_reg_store8(dest, tun_ctx->l4proto); + break; + default: + WARN_ON_ONCE(1); + goto err; + } + return; + +err: + regs->verdict.code = NFT_BREAK; +} +EXPORT_SYMBOL_GPL(nft_meta_inner_eval); + +static const struct nft_expr_ops nft_meta_inner_ops = { + .type = &nft_meta_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .init = nft_meta_inner_init, + .dump = nft_meta_get_dump, + /* direct call to nft_meta_inner_eval(). */ +}; + struct nft_expr_type nft_meta_type __read_mostly = { .name = "meta", .select_ops = nft_meta_select_ops, + .inner_ops = &nft_meta_inner_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index e5fd6995e4bf..047999150390 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -255,7 +255,8 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return nf_ct_netns_get(ctx->net, family); } -static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_nat_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_nat *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 45d3dc9e96f2..7d29db7c2ac0 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -112,7 +112,8 @@ nla_put_failure: return -1; } -static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ng_inc_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ng_inc *priv = nft_expr_priv(expr); @@ -168,7 +169,8 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NULL, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ng_random_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ng_random *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 5d8d91b3904d..7b01aa2ef653 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -47,7 +47,8 @@ static int nft_objref_init(const struct nft_ctx *ctx, return 0; } -static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_objref_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_object *obj = nft_objref_priv(expr); @@ -82,7 +83,6 @@ static void nft_objref_activate(const struct nft_ctx *ctx, obj->use++; } -static struct nft_expr_type nft_objref_type; static const struct nft_expr_ops nft_objref_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_object *)), @@ -156,7 +156,8 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, return 0; } -static int nft_objref_map_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_objref_map_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_objref_map *priv = nft_expr_priv(expr); @@ -195,7 +196,6 @@ static void nft_objref_map_destroy(const struct nft_ctx *ctx, nf_tables_destroy_set(ctx, priv->set); } -static struct nft_expr_type nft_objref_type; static const struct nft_expr_ops nft_objref_map_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), @@ -233,28 +233,10 @@ static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = { [NFTA_OBJREF_SET_ID] = { .type = NLA_U32 }, }; -static struct nft_expr_type nft_objref_type __read_mostly = { +struct nft_expr_type nft_objref_type __read_mostly = { .name = "objref", .select_ops = nft_objref_select_ops, .policy = nft_objref_policy, .maxattr = NFTA_OBJREF_MAX, .owner = THIS_MODULE, }; - -static int __init nft_objref_module_init(void) -{ - return nft_register_expr(&nft_objref_type); -} - -static void __exit nft_objref_module_exit(void) -{ - nft_unregister_expr(&nft_objref_type); -} - -module_init(nft_objref_module_init); -module_exit(nft_objref_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); -MODULE_ALIAS_NFT_EXPR("objref"); -MODULE_DESCRIPTION("nftables stateful object reference module"); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index adacf95b6e2b..70820c66b591 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -92,7 +92,8 @@ static int nft_osf_init(const struct nft_ctx *ctx, return 0; } -static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_osf_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_osf *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 088244f9d838..17b418a5a593 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -19,6 +19,7 @@ /* For layer 4 checksum field offset. */ #include <linux/tcp.h> #include <linux/udp.h> +#include <net/gre.h> #include <linux/icmpv6.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -100,6 +101,41 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) pkt->inneroff = thoff + __tcp_hdrlen(th); } break; + case IPPROTO_GRE: { + u32 offset = sizeof(struct gre_base_hdr); + struct gre_base_hdr *gre, _gre; + __be16 version; + + gre = skb_header_pointer(pkt->skb, thoff, sizeof(_gre), &_gre); + if (!gre) + return -1; + + version = gre->flags & GRE_VERSION; + switch (version) { + case GRE_VERSION_0: + if (gre->flags & GRE_ROUTING) + return -1; + + if (gre->flags & GRE_CSUM) { + offset += sizeof_field(struct gre_full_hdr, csum) + + sizeof_field(struct gre_full_hdr, reserved1); + } + if (gre->flags & GRE_KEY) + offset += sizeof_field(struct gre_full_hdr, key); + + if (gre->flags & GRE_SEQ) + offset += sizeof_field(struct gre_full_hdr, seq); + break; + default: + return -1; + } + + pkt->inneroff = thoff + offset; + } + break; + case IPPROTO_IPIP: + pkt->inneroff = thoff; + break; default: return -1; } @@ -109,7 +145,7 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) return 0; } -static int nft_payload_inner_offset(const struct nft_pktinfo *pkt) +int nft_payload_inner_offset(const struct nft_pktinfo *pkt) { if (!(pkt->flags & NFT_PKTINFO_INNER) && __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0) @@ -173,10 +209,10 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = { [NFTA_PAYLOAD_SREG] = { .type = NLA_U32 }, [NFTA_PAYLOAD_DREG] = { .type = NLA_U32 }, [NFTA_PAYLOAD_BASE] = { .type = NLA_U32 }, - [NFTA_PAYLOAD_OFFSET] = NLA_POLICY_MAX_BE(NLA_U32, 255), - [NFTA_PAYLOAD_LEN] = NLA_POLICY_MAX_BE(NLA_U32, 255), + [NFTA_PAYLOAD_OFFSET] = NLA_POLICY_MAX(NLA_BE32, 255), + [NFTA_PAYLOAD_LEN] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_PAYLOAD_CSUM_TYPE] = { .type = NLA_U32 }, - [NFTA_PAYLOAD_CSUM_OFFSET] = NLA_POLICY_MAX_BE(NLA_U32, 255), + [NFTA_PAYLOAD_CSUM_OFFSET] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_PAYLOAD_CSUM_FLAGS] = { .type = NLA_U32 }, }; @@ -195,7 +231,8 @@ static int nft_payload_init(const struct nft_ctx *ctx, priv->len); } -static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_payload_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_payload *priv = nft_expr_priv(expr); @@ -552,6 +589,92 @@ const struct nft_expr_ops nft_payload_fast_ops = { .offload = nft_payload_offload, }; +void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + const struct nft_payload *priv = nft_expr_priv(expr); + const struct sk_buff *skb = pkt->skb; + u32 *dest = ®s->data[priv->dreg]; + int offset; + + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; + + switch (priv->base) { + case NFT_PAYLOAD_TUN_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TUN)) + goto err; + + offset = tun_ctx->inner_tunoff; + break; + case NFT_PAYLOAD_LL_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_LL)) + goto err; + + offset = tun_ctx->inner_lloff; + break; + case NFT_PAYLOAD_NETWORK_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_NH)) + goto err; + + offset = tun_ctx->inner_nhoff; + break; + case NFT_PAYLOAD_TRANSPORT_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH)) + goto err; + + offset = tun_ctx->inner_thoff; + break; + default: + WARN_ON_ONCE(1); + goto err; + } + offset += priv->offset; + + if (skb_copy_bits(skb, offset, dest, priv->len) < 0) + goto err; + + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static int nft_payload_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_payload *priv = nft_expr_priv(expr); + u32 base; + + base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); + switch (base) { + case NFT_PAYLOAD_TUN_HEADER: + case NFT_PAYLOAD_LL_HEADER: + case NFT_PAYLOAD_NETWORK_HEADER: + case NFT_PAYLOAD_TRANSPORT_HEADER: + break; + default: + return -EOPNOTSUPP; + } + + priv->base = base; + priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); + priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + + return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); +} + +static const struct nft_expr_ops nft_payload_inner_ops = { + .type = &nft_payload_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_payload)), + .init = nft_payload_inner_init, + .dump = nft_payload_dump, + /* direct call to nft_payload_inner_eval(). */ +}; + static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum) { *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), fsum), tsum)); @@ -665,6 +788,16 @@ static int nft_payload_csum_inet(struct sk_buff *skb, const u32 *src, return 0; } +struct nft_payload_set { + enum nft_payload_bases base:8; + u8 offset; + u8 len; + u8 sreg; + u8 csum_type; + u8 csum_offset; + u8 csum_flags; +}; + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -787,7 +920,8 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->len); } -static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_payload_set_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_payload_set *priv = nft_expr_priv(expr); @@ -885,6 +1019,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, struct nft_expr_type nft_payload_type __read_mostly = { .name = "payload", .select_ops = nft_payload_select_ops, + .inner_ops = &nft_payload_inner_ops, .policy = nft_payload_policy, .maxattr = NFTA_PAYLOAD_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index da29e92c03e2..b2b8127c8d43 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -152,7 +152,8 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx, return 0; } -static int nft_queue_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_queue_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_queue *priv = nft_expr_priv(expr); @@ -168,7 +169,8 @@ nla_put_failure: } static int -nft_queue_sreg_dump(struct sk_buff *skb, const struct nft_expr *expr) +nft_queue_sreg_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_queue *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index e6b0df68feea..123578e28917 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -217,11 +217,12 @@ static int nft_quota_init(const struct nft_ctx *ctx, return nft_quota_do_init(tb, priv); } -static int nft_quota_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_quota_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_quota *priv = nft_expr_priv(expr); - return nft_quota_do_dump(skb, priv, false); + return nft_quota_do_dump(skb, priv, reset); } static void nft_quota_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 832f0d725a9e..0566d6aaf1e5 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -111,7 +111,8 @@ err1: return err; } -static int nft_range_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_range_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_range_expr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 5086adfe731c..5f7739987559 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -75,7 +75,8 @@ static int nft_redir_init(const struct nft_ctx *ctx, return nf_ct_netns_get(ctx->net, ctx->family); } -static int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_redir_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_redir *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 927ff8459bd9..f2addc844dd2 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -69,7 +69,8 @@ int nft_reject_init(const struct nft_ctx *ctx, } EXPORT_SYMBOL_GPL(nft_reject_init); -int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) +int nft_reject_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_reject *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 71931ec91721..5990fdd7b3cc 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -146,7 +146,7 @@ static int nft_rt_get_init(const struct nft_ctx *ctx, } static int nft_rt_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_rt *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 49a5348a6a14..85f8df87efda 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -199,7 +199,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, } static int nft_socket_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_socket *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 6cf9a04fbfe2..13da882669a4 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -272,7 +272,8 @@ static void nft_synproxy_destroy(const struct nft_ctx *ctx, nft_synproxy_do_destroy(ctx); } -static int nft_synproxy_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_synproxy_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_synproxy *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 62da25ad264b..ea83f661417e 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -294,7 +294,7 @@ static void nft_tproxy_destroy(const struct nft_ctx *ctx, } static int nft_tproxy_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_tproxy *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 983ade4be3b3..b059aa541798 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -108,7 +108,7 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, } static int nft_tunnel_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_tunnel *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index 1c5343c936a8..c88fd078a9ae 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -212,7 +212,7 @@ static void nft_xfrm_get_eval(const struct nft_expr *expr, } static int nft_xfrm_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_xfrm *priv = nft_expr_priv(expr); diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index e5ebc0810675..ad3c033db64e 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -30,6 +30,7 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; + u_int32_t oldmark; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) @@ -37,14 +38,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) switch (info->mode) { case XT_CONNMARK_SET: - newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; + oldmark = READ_ONCE(ct->mark); + newmark = (oldmark & ~info->ctmask) ^ info->ctmark; if (info->shift_dir == D_SHIFT_RIGHT) newmark >>= info->shift_bits; else newmark <<= info->shift_bits; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; @@ -55,15 +57,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) else new_targetmark <<= info->shift_bits; - newmark = (ct->mark & ~info->ctmask) ^ + newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^ new_targetmark; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - new_targetmark = (ct->mark & info->ctmask); + new_targetmark = (READ_ONCE(ct->mark) & info->ctmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else @@ -126,7 +128,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL) return false; - return ((ct->mark & info->mask) == info->mark) ^ info->invert; + return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert; } static int connmark_mt_check(const struct xt_mtchk_param *par) diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 680015ba7cb6..e8961094a282 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -4,7 +4,6 @@ #include <linux/skbuff.h> #include <net/ip.h> #include <net/ipv6.h> -#include <net/sctp/sctp.h> #include <linux/sctp.h> #include <linux/netfilter/x_tables.h> diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c index 203e24ae472c..b26c1dcfc27b 100644 --- a/net/netfilter/xt_statistic.c +++ b/net/netfilter/xt_statistic.c @@ -34,7 +34,7 @@ statistic_mt(const struct sk_buff *skb, struct xt_action_param *par) switch (info->mode) { case XT_STATISTIC_MODE_RANDOM: - if ((prandom_u32() & 0x7FFFFFFF) < info->u.random.probability) + if ((get_random_u32() & 0x7FFFFFFF) < info->u.random.probability) ret = !ret; break; case XT_STATISTIC_MODE_NTH: diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a662e8a5ff84..d73091f6bb0f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -812,6 +812,17 @@ static int netlink_release(struct socket *sock) } sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); + + /* Because struct net might disappear soon, do not keep a pointer. */ + if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) { + __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); + /* Because of deferred_put_nlk_sk and use of work queue, + * it is possible netns will be freed before this socket. + */ + sock_net_set(sk, &init_net); + __netns_tracker_alloc(&init_net, &sk->ns_tracker, + false, GFP_KERNEL); + } call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } @@ -2488,19 +2499,24 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); - if (!skb) { - NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; - sk_error_report(NETLINK_CB(in_skb).sk); - return; - } + if (!skb) + goto err_skb; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - NLMSG_ERROR, payload, flags); + NLMSG_ERROR, sizeof(*errmsg), flags); + if (!rep) + goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; - unsafe_memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) - ? nlh->nlmsg_len : sizeof(*nlh), - /* Bounds checked by the skb layer. */); + errmsg->msg = *nlh; + + if (!(flags & NLM_F_CAPPED)) { + if (!nlmsg_append(skb, nlmsg_len(nlh))) + goto err_bad_put; + + memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), + nlmsg_len(nlh)); + } if (tlvlen) netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack); @@ -2508,6 +2524,14 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); + + return; + +err_bad_put: + nlmsg_free(skb); +err_skb: + NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 39b7c00e4cef..600993c80050 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -78,10 +78,40 @@ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; +/* We need the last attribute with non-zero ID therefore a 2-entry array */ +static struct nla_policy genl_policy_reject_all[] = { + { .type = NLA_REJECT }, + { .type = NLA_REJECT }, +}; + static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); +static void +genl_op_fill_in_reject_policy(const struct genl_family *family, + struct genl_ops *op) +{ + BUILD_BUG_ON(ARRAY_SIZE(genl_policy_reject_all) - 1 != 1); + + if (op->policy || op->cmd < family->resv_start_op) + return; + + op->policy = genl_policy_reject_all; + op->maxattr = 1; +} + +static void +genl_op_fill_in_reject_policy_split(const struct genl_family *family, + struct genl_split_ops *op) +{ + if (op->policy) + return; + + op->policy = genl_policy_reject_all; + op->maxattr = 1; +} + static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); @@ -99,10 +129,15 @@ static const struct genl_family *genl_family_find_byname(char *name) return NULL; } -static int genl_get_cmd_cnt(const struct genl_family *family) -{ - return family->n_ops + family->n_small_ops; -} +struct genl_op_iter { + const struct genl_family *family; + struct genl_split_ops doit; + struct genl_split_ops dumpit; + int cmd_idx; + int entry_idx; + u32 cmd; + u8 flags; +}; static void genl_op_from_full(const struct genl_family *family, unsigned int i, struct genl_ops *op) @@ -113,6 +148,8 @@ static void genl_op_from_full(const struct genl_family *family, op->maxattr = family->maxattr; if (!op->policy) op->policy = family->policy; + + genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, @@ -142,6 +179,8 @@ static void genl_op_from_small(const struct genl_family *family, op->maxattr = family->maxattr; op->policy = family->policy; + + genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, @@ -158,24 +197,187 @@ static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, return -ENOENT; } -static int genl_get_cmd(u32 cmd, const struct genl_family *family, - struct genl_ops *op) +static void genl_op_from_split(struct genl_op_iter *iter) { - if (!genl_get_cmd_full(cmd, family, op)) - return 0; - return genl_get_cmd_small(cmd, family, op); + const struct genl_family *family = iter->family; + int i, cnt = 0; + + i = iter->entry_idx - family->n_ops - family->n_small_ops; + + if (family->split_ops[i + cnt].flags & GENL_CMD_CAP_DO) { + iter->doit = family->split_ops[i + cnt]; + genl_op_fill_in_reject_policy_split(family, &iter->doit); + cnt++; + } else { + memset(&iter->doit, 0, sizeof(iter->doit)); + } + + if (i + cnt < family->n_split_ops && + family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP) { + iter->dumpit = family->split_ops[i + cnt]; + genl_op_fill_in_reject_policy_split(family, &iter->dumpit); + cnt++; + } else { + memset(&iter->dumpit, 0, sizeof(iter->dumpit)); + } + + WARN_ON(!cnt); + iter->entry_idx += cnt; } -static void genl_get_cmd_by_index(unsigned int i, - const struct genl_family *family, - struct genl_ops *op) +static int +genl_get_cmd_split(u32 cmd, u8 flag, const struct genl_family *family, + struct genl_split_ops *op) { - if (i < family->n_ops) - genl_op_from_full(family, i, op); - else if (i < family->n_ops + family->n_small_ops) - genl_op_from_small(family, i - family->n_ops, op); - else - WARN_ON_ONCE(1); + int i; + + for (i = 0; i < family->n_split_ops; i++) + if (family->split_ops[i].cmd == cmd && + family->split_ops[i].flags & flag) { + *op = family->split_ops[i]; + return 0; + } + + return -ENOENT; +} + +static int +genl_cmd_full_to_split(struct genl_split_ops *op, + const struct genl_family *family, + const struct genl_ops *full, u8 flags) +{ + if ((flags & GENL_CMD_CAP_DO && !full->doit) || + (flags & GENL_CMD_CAP_DUMP && !full->dumpit)) { + memset(op, 0, sizeof(*op)); + return -ENOENT; + } + + if (flags & GENL_CMD_CAP_DUMP) { + op->start = full->start; + op->dumpit = full->dumpit; + op->done = full->done; + } else { + op->pre_doit = family->pre_doit; + op->doit = full->doit; + op->post_doit = family->post_doit; + } + + if (flags & GENL_CMD_CAP_DUMP && + full->validate & GENL_DONT_VALIDATE_DUMP) { + op->policy = NULL; + op->maxattr = 0; + } else { + op->policy = full->policy; + op->maxattr = full->maxattr; + } + + op->cmd = full->cmd; + op->internal_flags = full->internal_flags; + op->flags = full->flags; + op->validate = full->validate; + + /* Make sure flags include the GENL_CMD_CAP_DO / GENL_CMD_CAP_DUMP */ + op->flags |= flags; + + return 0; +} + +/* Must make sure that op is initialized to 0 on failure */ +static int +genl_get_cmd(u32 cmd, u8 flags, const struct genl_family *family, + struct genl_split_ops *op) +{ + struct genl_ops full; + int err; + + err = genl_get_cmd_full(cmd, family, &full); + if (err == -ENOENT) + err = genl_get_cmd_small(cmd, family, &full); + /* Found one of legacy forms */ + if (err == 0) + return genl_cmd_full_to_split(op, family, &full, flags); + + err = genl_get_cmd_split(cmd, flags, family, op); + if (err) + memset(op, 0, sizeof(*op)); + return err; +} + +/* For policy dumping only, get ops of both do and dump. + * Fail if both are missing, genl_get_cmd() will zero-init in case of failure. + */ +static int +genl_get_cmd_both(u32 cmd, const struct genl_family *family, + struct genl_split_ops *doit, struct genl_split_ops *dumpit) +{ + int err1, err2; + + err1 = genl_get_cmd(cmd, GENL_CMD_CAP_DO, family, doit); + err2 = genl_get_cmd(cmd, GENL_CMD_CAP_DUMP, family, dumpit); + + return err1 && err2 ? -ENOENT : 0; +} + +static bool +genl_op_iter_init(const struct genl_family *family, struct genl_op_iter *iter) +{ + iter->family = family; + iter->cmd_idx = 0; + iter->entry_idx = 0; + + iter->flags = 0; + + return iter->family->n_ops + + iter->family->n_small_ops + + iter->family->n_split_ops; +} + +static bool genl_op_iter_next(struct genl_op_iter *iter) +{ + const struct genl_family *family = iter->family; + bool legacy_op = true; + struct genl_ops op; + + if (iter->entry_idx < family->n_ops) { + genl_op_from_full(family, iter->entry_idx, &op); + } else if (iter->entry_idx < family->n_ops + family->n_small_ops) { + genl_op_from_small(family, iter->entry_idx - family->n_ops, + &op); + } else if (iter->entry_idx < + family->n_ops + family->n_small_ops + family->n_split_ops) { + legacy_op = false; + /* updates entry_idx */ + genl_op_from_split(iter); + } else { + return false; + } + + iter->cmd_idx++; + + if (legacy_op) { + iter->entry_idx++; + + genl_cmd_full_to_split(&iter->doit, family, + &op, GENL_CMD_CAP_DO); + genl_cmd_full_to_split(&iter->dumpit, family, + &op, GENL_CMD_CAP_DUMP); + } + + iter->cmd = iter->doit.cmd | iter->dumpit.cmd; + iter->flags = iter->doit.flags | iter->dumpit.flags; + + return true; +} + +static void +genl_op_iter_copy(struct genl_op_iter *dst, struct genl_op_iter *src) +{ + *dst = *src; +} + +static unsigned int genl_op_iter_idx(struct genl_op_iter *iter) +{ + return iter->cmd_idx; } static int genl_allocate_reserve_groups(int n_groups, int *first_id) @@ -343,29 +545,72 @@ static void genl_unregister_mc_groups(const struct genl_family *family) } } +static bool genl_split_op_check(const struct genl_split_ops *op) +{ + if (WARN_ON(hweight8(op->flags & (GENL_CMD_CAP_DO | + GENL_CMD_CAP_DUMP)) != 1)) + return true; + return false; +} + static int genl_validate_ops(const struct genl_family *family) { - int i, j; + struct genl_op_iter i, j; + unsigned int s; if (WARN_ON(family->n_ops && !family->ops) || - WARN_ON(family->n_small_ops && !family->small_ops)) + WARN_ON(family->n_small_ops && !family->small_ops) || + WARN_ON(family->n_split_ops && !family->split_ops)) return -EINVAL; - for (i = 0; i < genl_get_cmd_cnt(family); i++) { - struct genl_ops op; + for (genl_op_iter_init(family, &i); genl_op_iter_next(&i); ) { + if (!(i.flags & (GENL_CMD_CAP_DO | GENL_CMD_CAP_DUMP))) + return -EINVAL; - genl_get_cmd_by_index(i, family, &op); - if (op.dumpit == NULL && op.doit == NULL) + if (WARN_ON(i.cmd >= family->resv_start_op && + (i.doit.validate || i.dumpit.validate))) return -EINVAL; - for (j = i + 1; j < genl_get_cmd_cnt(family); j++) { - struct genl_ops op2; - genl_get_cmd_by_index(j, family, &op2); - if (op.cmd == op2.cmd) + genl_op_iter_copy(&j, &i); + while (genl_op_iter_next(&j)) { + if (i.cmd == j.cmd) return -EINVAL; } } + if (family->n_split_ops) { + if (genl_split_op_check(&family->split_ops[0])) + return -EINVAL; + } + + for (s = 1; s < family->n_split_ops; s++) { + const struct genl_split_ops *a, *b; + + a = &family->split_ops[s - 1]; + b = &family->split_ops[s]; + + if (genl_split_op_check(b)) + return -EINVAL; + + /* Check sort order */ + if (a->cmd < b->cmd) + continue; + + if (a->internal_flags != b->internal_flags || + ((a->flags ^ b->flags) & ~(GENL_CMD_CAP_DO | + GENL_CMD_CAP_DUMP))) { + WARN_ON(1); + return -EINVAL; + } + + if ((a->flags & GENL_CMD_CAP_DO) && + (b->flags & GENL_CMD_CAP_DUMP)) + continue; + + WARN_ON(1); + return -EINVAL; + } + return 0; } @@ -519,7 +764,7 @@ static struct nlattr ** genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, enum genl_validate_flags no_strict_flag) { @@ -555,22 +800,21 @@ struct genl_start_context { const struct genl_family *family; struct nlmsghdr *nlh; struct netlink_ext_ack *extack; - const struct genl_ops *ops; + const struct genl_split_ops *ops; int hdrlen; }; static int genl_start(struct netlink_callback *cb) { struct genl_start_context *ctx = cb->data; - const struct genl_ops *ops = ctx->ops; + const struct genl_split_ops *ops; struct genl_dumpit_info *info; struct nlattr **attrs = NULL; int rc = 0; - if (ops->validate & GENL_DONT_VALIDATE_DUMP) - goto no_attrs; - - if (ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen)) + ops = ctx->ops; + if (!(ops->validate & GENL_DONT_VALIDATE_DUMP) && + ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen)) return -EINVAL; attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack, @@ -579,7 +823,6 @@ static int genl_start(struct netlink_callback *cb) if (IS_ERR(attrs)) return PTR_ERR(attrs); -no_attrs: info = genl_dumpit_info_alloc(); if (!info) { genl_family_rcv_msg_attrs_free(attrs); @@ -608,7 +851,7 @@ no_attrs: static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - const struct genl_ops *ops = &genl_dumpit_info(cb)->op; + const struct genl_split_ops *ops = &genl_dumpit_info(cb)->op; int rc; genl_lock(); @@ -620,7 +863,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int genl_lock_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = &info->op; + const struct genl_split_ops *ops = &info->op; int rc = 0; if (ops->done) { @@ -636,7 +879,7 @@ static int genl_lock_done(struct netlink_callback *cb) static int genl_parallel_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = &info->op; + const struct genl_split_ops *ops = &info->op; int rc = 0; if (ops->done) @@ -650,15 +893,12 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct genl_start_context ctx; int err; - if (!ops->dumpit) - return -EOPNOTSUPP; - ctx.family = family; ctx.nlh = nlh; ctx.extack = extack; @@ -696,16 +936,13 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct nlattr **attrbuf; struct genl_info info; int err; - if (!ops->doit) - return -EOPNOTSUPP; - attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack, ops, hdrlen, GENL_DONT_VALIDATE_STRICT); @@ -722,16 +959,16 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, genl_info_net_set(&info, net); memset(&info.user_ptr, 0, sizeof(info.user_ptr)); - if (family->pre_doit) { - err = family->pre_doit(ops, skb, &info); + if (ops->pre_doit) { + err = ops->pre_doit(ops, skb, &info); if (err) goto out; } err = ops->doit(skb, &info); - if (family->post_doit) - family->post_doit(ops, skb, &info); + if (ops->post_doit) + ops->post_doit(ops, skb, &info); out: genl_family_rcv_msg_attrs_free(attrbuf); @@ -776,8 +1013,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, { struct net *net = sock_net(skb->sk); struct genlmsghdr *hdr = nlmsg_data(nlh); - struct genl_ops op; + struct genl_split_ops op; int hdrlen; + u8 flags; /* this family doesn't exist in this netns */ if (!family->netnsok && !net_eq(net, &init_net)) @@ -790,7 +1028,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, if (genl_header_check(family, nlh, hdr, extack)) return -EINVAL; - if (genl_get_cmd(hdr->cmd, family, &op)) + flags = (nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP ? + GENL_CMD_CAP_DUMP : GENL_CMD_CAP_DO; + if (genl_get_cmd(hdr->cmd, flags, family, &op)) return -EOPNOTSUPP; if ((op.flags & GENL_ADMIN_PERM) && @@ -801,7 +1041,7 @@ static int genl_family_rcv_msg(const struct genl_family *family, !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) + if (flags & GENL_CMD_CAP_DUMP) return genl_family_rcv_msg_dumpit(family, skb, nlh, extack, &op, hdrlen, net); else @@ -846,6 +1086,7 @@ static struct genl_family genl_ctrl; static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { + struct genl_op_iter i; void *hdr; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); @@ -859,33 +1100,26 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) goto nla_put_failure; - if (genl_get_cmd_cnt(family)) { + if (genl_op_iter_init(family, &i)) { struct nlattr *nla_ops; - int i; nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS); if (nla_ops == NULL) goto nla_put_failure; - for (i = 0; i < genl_get_cmd_cnt(family); i++) { + while (genl_op_iter_next(&i)) { struct nlattr *nest; - struct genl_ops op; u32 op_flags; - genl_get_cmd_by_index(i, family, &op); - op_flags = op.flags; - if (op.dumpit) - op_flags |= GENL_CMD_CAP_DUMP; - if (op.doit) - op_flags |= GENL_CMD_CAP_DO; - if (op.policy) + op_flags = i.flags; + if (i.doit.policy || i.dumpit.policy) op_flags |= GENL_CMD_CAP_HASPOL; - nest = nla_nest_start_noflag(skb, i + 1); + nest = nla_nest_start_noflag(skb, genl_op_iter_idx(&i)); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) || + if (nla_put_u32(skb, CTRL_ATTR_OP_ID, i.cmd) || nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags)) goto nla_put_failure; @@ -1138,10 +1372,10 @@ static int genl_ctrl_event(int event, const struct genl_family *family, struct ctrl_dump_policy_ctx { struct netlink_policy_dump_state *state; const struct genl_family *rt; - unsigned int opidx; + struct genl_op_iter *op_iter; u32 op; u16 fam_id; - u8 policies:1, + u8 dump_map:1, single_op:1; }; @@ -1158,8 +1392,8 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr **tb = info->attrs; const struct genl_family *rt; - struct genl_ops op; - int err, i; + struct genl_op_iter i; + int err; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); @@ -1183,40 +1417,73 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) ctx->rt = rt; if (tb[CTRL_ATTR_OP]) { + struct genl_split_ops doit, dump; + ctx->single_op = true; ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]); - err = genl_get_cmd(ctx->op, rt, &op); + err = genl_get_cmd_both(ctx->op, rt, &doit, &dump); if (err) { NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); return err; } - if (!op.policy) + if (doit.policy) { + err = netlink_policy_dump_add_policy(&ctx->state, + doit.policy, + doit.maxattr); + if (err) + goto err_free_state; + } + if (dump.policy) { + err = netlink_policy_dump_add_policy(&ctx->state, + dump.policy, + dump.maxattr); + if (err) + goto err_free_state; + } + + if (!ctx->state) return -ENODATA; - return netlink_policy_dump_add_policy(&ctx->state, op.policy, - op.maxattr); + ctx->dump_map = 1; + return 0; } - for (i = 0; i < genl_get_cmd_cnt(rt); i++) { - genl_get_cmd_by_index(i, rt, &op); + ctx->op_iter = kmalloc(sizeof(*ctx->op_iter), GFP_KERNEL); + if (!ctx->op_iter) + return -ENOMEM; + + genl_op_iter_init(rt, ctx->op_iter); + ctx->dump_map = genl_op_iter_next(ctx->op_iter); - if (op.policy) { + for (genl_op_iter_init(rt, &i); genl_op_iter_next(&i); ) { + if (i.doit.policy) { + err = netlink_policy_dump_add_policy(&ctx->state, + i.doit.policy, + i.doit.maxattr); + if (err) + goto err_free_state; + } + if (i.dumpit.policy) { err = netlink_policy_dump_add_policy(&ctx->state, - op.policy, - op.maxattr); + i.dumpit.policy, + i.dumpit.maxattr); if (err) goto err_free_state; } } - if (!ctx->state) - return -ENODATA; + if (!ctx->state) { + err = -ENODATA; + goto err_free_op_iter; + } return 0; err_free_state: netlink_policy_dump_free(ctx->state); +err_free_op_iter: + kfree(ctx->op_iter); return err; } @@ -1240,7 +1507,8 @@ static void *ctrl_dumppolicy_prep(struct sk_buff *skb, static int ctrl_dumppolicy_put_op(struct sk_buff *skb, struct netlink_callback *cb, - struct genl_ops *op) + struct genl_split_ops *doit, + struct genl_split_ops *dumpit) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr *nest_pol, *nest_op; @@ -1248,10 +1516,7 @@ static int ctrl_dumppolicy_put_op(struct sk_buff *skb, int idx; /* skip if we have nothing to show */ - if (!op->policy) - return 0; - if (!op->doit && - (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP)) + if (!doit->policy && !dumpit->policy) return 0; hdr = ctrl_dumppolicy_prep(skb, cb); @@ -1262,21 +1527,26 @@ static int ctrl_dumppolicy_put_op(struct sk_buff *skb, if (!nest_pol) goto err; - nest_op = nla_nest_start(skb, op->cmd); + nest_op = nla_nest_start(skb, doit->cmd); if (!nest_op) goto err; - /* for now both do/dump are always the same */ - idx = netlink_policy_dump_get_policy_idx(ctx->state, - op->policy, - op->maxattr); + if (doit->policy) { + idx = netlink_policy_dump_get_policy_idx(ctx->state, + doit->policy, + doit->maxattr); - if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) - goto err; + if (nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) + goto err; + } + if (dumpit->policy) { + idx = netlink_policy_dump_get_policy_idx(ctx->state, + dumpit->policy, + dumpit->maxattr); - if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) && - nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) - goto err; + if (nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) + goto err; + } nla_nest_end(skb, nest_op); nla_nest_end(skb, nest_pol); @@ -1293,31 +1563,29 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; - if (!ctx->policies) { - while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) { - struct genl_ops op; + if (ctx->dump_map) { + if (ctx->single_op) { + struct genl_split_ops doit, dumpit; - if (ctx->single_op) { - int err; + if (WARN_ON(genl_get_cmd_both(ctx->op, ctx->rt, + &doit, &dumpit))) + return -ENOENT; - err = genl_get_cmd(ctx->op, ctx->rt, &op); - if (WARN_ON(err)) - return skb->len; + if (ctrl_dumppolicy_put_op(skb, cb, &doit, &dumpit)) + return skb->len; - /* break out of the loop after this one */ - ctx->opidx = genl_get_cmd_cnt(ctx->rt); - } else { - genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op); - } + /* done with the per-op policy index list */ + ctx->dump_map = 0; + } - if (ctrl_dumppolicy_put_op(skb, cb, &op)) + while (ctx->dump_map) { + if (ctrl_dumppolicy_put_op(skb, cb, + &ctx->op_iter->doit, + &ctx->op_iter->dumpit)) return skb->len; - ctx->opidx++; + ctx->dump_map = genl_op_iter_next(ctx->op_iter); } - - /* completed with the per-op policy index list */ - ctx->policies = true; } while (netlink_policy_dump_loop(ctx->state)) { @@ -1350,18 +1618,27 @@ static int ctrl_dumppolicy_done(struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; + kfree(ctx->op_iter); netlink_policy_dump_free(ctx->state); return 0; } -static const struct genl_ops genl_ctrl_ops[] = { +static const struct genl_split_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT, .policy = ctrl_policy_family, .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .doit = ctrl_getfamily, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = CTRL_CMD_GETFAMILY, + .validate = GENL_DONT_VALIDATE_DUMP, + .policy = ctrl_policy_family, + .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .dumpit = ctrl_dumpfamily, + .flags = GENL_CMD_CAP_DUMP, }, { .cmd = CTRL_CMD_GETPOLICY, @@ -1370,6 +1647,7 @@ static const struct genl_ops genl_ctrl_ops[] = { .start = ctrl_dumppolicy_start, .dumpit = ctrl_dumppolicy, .done = ctrl_dumppolicy_done, + .flags = GENL_CMD_CAP_DUMP, }, }; @@ -1379,8 +1657,8 @@ static const struct genl_multicast_group genl_ctrl_groups[] = { static struct genl_family genl_ctrl __ro_after_init = { .module = THIS_MODULE, - .ops = genl_ctrl_ops, - .n_ops = ARRAY_SIZE(genl_ctrl_ops), + .split_ops = genl_ctrl_ops, + .n_split_ops = ARRAY_SIZE(genl_ctrl_ops), .resv_start_op = CTRL_CMD_GETPOLICY + 1, .mcgrps = genl_ctrl_groups, .n_mcgrps = ARRAY_SIZE(genl_ctrl_groups), diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6a193cce2a75..fff755dde30d 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -24,6 +24,7 @@ #include <linux/sched.h> #include <linux/bitops.h> #include <linux/skbuff.h> +#include <linux/kcov.h> #include "../nfc.h" #include <net/nfc/nci.h> @@ -542,7 +543,7 @@ static int nci_open_device(struct nci_dev *ndev) skb_queue_purge(&ndev->tx_q); ndev->ops->close(ndev); - ndev->flags = 0; + ndev->flags &= BIT(NCI_UNREG); } done: @@ -1472,6 +1473,7 @@ static void nci_tx_work(struct work_struct *work) skb = skb_dequeue(&ndev->tx_q); if (!skb) return; + kcov_remote_start_common(skb_get_kcov_handle(skb)); /* Check if data flow control is used */ if (atomic_read(&conn_info->credits_cnt) != @@ -1487,6 +1489,7 @@ static void nci_tx_work(struct work_struct *work) mod_timer(&ndev->data_timer, jiffies + msecs_to_jiffies(NCI_DATA_TIMEOUT)); + kcov_remote_stop(); } } @@ -1497,7 +1500,8 @@ static void nci_rx_work(struct work_struct *work) struct nci_dev *ndev = container_of(work, struct nci_dev, rx_work); struct sk_buff *skb; - while ((skb = skb_dequeue(&ndev->rx_q))) { + for (; (skb = skb_dequeue(&ndev->rx_q)); kcov_remote_stop()) { + kcov_remote_start_common(skb_get_kcov_handle(skb)); /* Send copy to sniffer */ nfc_send_to_raw_sock(ndev->nfc_dev, skb, @@ -1551,6 +1555,7 @@ static void nci_cmd_work(struct work_struct *work) if (!skb) return; + kcov_remote_start_common(skb_get_kcov_handle(skb)); atomic_dec(&ndev->cmd_cnt); pr_debug("NCI TX: MT=cmd, PBF=%d, GID=0x%x, OID=0x%x, plen=%d\n", @@ -1563,6 +1568,7 @@ static void nci_cmd_work(struct work_struct *work) mod_timer(&ndev->cmd_timer, jiffies + msecs_to_jiffies(NCI_CMD_TIMEOUT)); + kcov_remote_stop(); } } diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index aa5e712adf07..3d36ea5701f0 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -279,8 +279,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) nci_plen(skb->data)); conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data)); - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return; + } /* strip the nci data header */ skb_pull(skb, NCI_DATA_HDR_SIZE); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 78c4b6addf15..de175318a3a0 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -14,6 +14,7 @@ #include <net/nfc/nci.h> #include <net/nfc/nci_core.h> #include <linux/nfc.h> +#include <linux/kcov.h> struct nci_data { u8 conn_id; @@ -409,7 +410,8 @@ static void nci_hci_msg_rx_work(struct work_struct *work) const struct nci_hcp_message *message; u8 pipe, type, instruction; - while ((skb = skb_dequeue(&hdev->msg_rx_queue)) != NULL) { + for (; (skb = skb_dequeue(&hdev->msg_rx_queue)); kcov_remote_stop()) { + kcov_remote_start_common(skb_get_kcov_handle(skb)); pipe = NCI_HCP_MSG_GET_PIPE(skb->data[0]); skb_pull(skb, NCI_HCI_HCP_PACKET_HEADER_LEN); message = (struct nci_hcp_message *)skb->data; diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 8dd569765f96..5125392bb68e 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -12,6 +12,7 @@ #include <net/tcp_states.h> #include <linux/nfc.h> #include <linux/export.h> +#include <linux/kcov.h> #include "nfc.h" @@ -189,6 +190,7 @@ static void rawsock_tx_work(struct work_struct *work) } skb = skb_dequeue(&sk->sk_write_queue); + kcov_remote_start_common(skb_get_kcov_handle(skb)); sock_hold(sk); rc = nfc_data_exchange(dev, target_idx, skb, @@ -197,6 +199,7 @@ static void rawsock_tx_work(struct work_struct *work) rawsock_report_error(sk, rc); sock_put(sk); } + kcov_remote_stop(); } static int rawsock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 868db4669a29..ca3ebfdb3023 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1033,7 +1033,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, actions = nla_next(sample_arg, &rem); if ((arg->probability != U32_MAX) && - (!arg->probability || prandom_u32() > arg->probability)) { + (!arg->probability || get_random_u32() > arg->probability)) { if (last) consume_skb(skb); return 0; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c7b10234cf7c..d78f0fc4337d 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -152,7 +152,7 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - return ct ? ct->mark : 0; + return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif @@ -340,9 +340,9 @@ static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; - new_mark = ct_mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; @@ -434,65 +434,6 @@ static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, return 0; } -/* 'skb' should already be pulled to nh_ofs. */ -static int ovs_ct_helper(struct sk_buff *skb, u16 proto) -{ - const struct nf_conntrack_helper *helper; - const struct nf_conn_help *help; - enum ip_conntrack_info ctinfo; - unsigned int protoff; - struct nf_conn *ct; - int err; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - switch (proto) { - case NFPROTO_IPV4: - protoff = ip_hdrlen(skb); - break; - case NFPROTO_IPV6: { - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - int ofs; - - ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - protoff = ofs; - break; - } - default: - WARN_ONCE(1, "helper invoked on non-IP family!"); - return NF_DROP; - } - - err = helper->help(skb, protoff, ct, ctinfo); - if (err != NF_ACCEPT) - return err; - - /* Adjust seqs after helper. This is needed due to some helpers (e.g., - * FTP with NAT) adusting the TCP payload size when mangling IP - * addresses and/or port numbers in the text-based control connection. - */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) - return NF_DROP; - return NF_ACCEPT; -} - /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */ @@ -1038,7 +979,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, */ if ((nf_ct_is_confirmed(ct) ? !cached || add_helper : info->commit) && - ovs_ct_helper(skb, info->family) != NF_ACCEPT) { + nf_ct_helper(skb, ct, ctinfo, info->family) != NF_ACCEPT) { return -EINVAL; } @@ -1350,43 +1291,6 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) return 0; } -static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, - const struct sw_flow_key *key, bool log) -{ - struct nf_conntrack_helper *helper; - struct nf_conn_help *help; - int ret = 0; - - helper = nf_conntrack_helper_try_module_get(name, info->family, - key->ip.proto); - if (!helper) { - OVS_NLERR(log, "Unknown helper \"%s\"", name); - return -EINVAL; - } - - help = nf_ct_helper_ext_add(info->ct, GFP_KERNEL); - if (!help) { - nf_conntrack_helper_put(helper); - return -ENOMEM; - } - -#if IS_ENABLED(CONFIG_NF_NAT) - if (info->nat) { - ret = nf_nat_helper_try_module_get(name, info->family, - key->ip.proto); - if (ret) { - nf_conntrack_helper_put(helper); - OVS_NLERR(log, "Failed to load \"%s\" NAT helper, error: %d", - name, ret); - return ret; - } - } -#endif - rcu_assign_pointer(help->helper, helper); - info->helper = helper; - return ret; -} - #if IS_ENABLED(CONFIG_NF_NAT) static int parse_nat(const struct nlattr *attr, struct ovs_conntrack_info *info, bool log) @@ -1720,9 +1624,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, } if (helper) { - err = ovs_ct_add_helper(&ct_info, helper, key, log); - if (err) + err = nf_ct_add_helper(ct_info.ct, helper, ct_info.family, + key->ip.proto, ct_info.nat, &ct_info.helper); + if (err) { + OVS_NLERR(log, "Failed to add %s helper %d", helper, err); goto err_free_ct; + } } err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info, diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c8a9075ddd0a..861dfb8daf4a 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -716,9 +716,9 @@ static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats, percpu_stats = per_cpu_ptr(dp->stats_percpu, i); do { - start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); + start = u64_stats_fetch_begin(&percpu_stats->syncp); local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); + } while (u64_stats_fetch_retry(&percpu_stats->syncp, start)); stats->n_hit += local_stats.n_hit; stats->n_missed += local_stats.n_missed; @@ -1616,7 +1616,8 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, if (IS_ERR(dp)) return; - WARN(dp->user_features, "Dropping previously announced user features\n"); + pr_warn("%s: Dropping previously announced user features\n", + ovs_dp_name(dp)); dp->user_features = 0; } @@ -2543,6 +2544,7 @@ struct genl_family dp_vport_genl_family __ro_after_init = { .parallel_ops = true, .small_ops = dp_vport_genl_ops, .n_small_ops = ARRAY_SIZE(dp_vport_genl_ops), + .resv_start_op = OVS_VPORT_CMD_SET + 1, .mcgrps = &ovs_dp_vport_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 4a07ab094a84..ead5418c126e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2309,7 +2309,7 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size) WARN_ON_ONCE(size > MAX_ACTIONS_BUFSIZE); - sfa = kmalloc(sizeof(*sfa) + size, GFP_KERNEL); + sfa = kmalloc(kmalloc_size_roundup(sizeof(*sfa) + size), GFP_KERNEL); if (!sfa) return ERR_PTR(-ENOMEM); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index d4a2db0b2299..0a0e4c283f02 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -205,9 +205,9 @@ static void tbl_mask_array_reset_counters(struct mask_array *ma) stats = per_cpu_ptr(ma->masks_usage_stats, cpu); do { - start = u64_stats_fetch_begin_irq(&stats->syncp); + start = u64_stats_fetch_begin(&stats->syncp); counter = stats->usage_cntrs[i]; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + } while (u64_stats_fetch_retry(&stats->syncp, start)); ma->masks_usage_zero_cntr[i] += counter; } @@ -1136,10 +1136,9 @@ void ovs_flow_masks_rebalance(struct flow_table *table) stats = per_cpu_ptr(ma->masks_usage_stats, cpu); do { - start = u64_stats_fetch_begin_irq(&stats->syncp); + start = u64_stats_fetch_begin(&stats->syncp); counter = stats->usage_cntrs[i]; - } while (u64_stats_fetch_retry_irq(&stats->syncp, - start)); + } while (u64_stats_fetch_retry(&stats->syncp, start)); masks_and_count[i].counter += counter; } diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 89a8e1501809..b10e1602c6b1 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -91,7 +91,7 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); if (err < 0) { - rtnl_delete_link(dev); + rtnl_delete_link(dev, 0, NULL); rtnl_unlock(); ovs_vport_free(vport); goto error; diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index e6b5e76a962a..4014c9b5eb79 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -57,7 +57,7 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); if (err < 0) { - rtnl_delete_link(dev); + rtnl_delete_link(dev, 0, NULL); rtnl_unlock(); ovs_vport_free(vport); return ERR_PTR(err); diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 2f61d5bdce1a..903537a5da22 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -172,7 +172,7 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) * if it's not already shutting down. */ if (vport->dev->reg_state == NETREG_REGISTERED) - rtnl_delete_link(vport->dev); + rtnl_delete_link(vport->dev, 0, NULL); netdev_put(vport->dev, &vport->dev_tracker); vport->dev = NULL; rtnl_unlock(); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 188e9c1360a1..0b881b043bcf 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -120,7 +120,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); if (err < 0) { - rtnl_delete_link(dev); + rtnl_delete_link(dev, 0, NULL); rtnl_unlock(); ovs_vport_free(vport); goto error; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d3f6db350de7..41c4ccc3a5d6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1350,7 +1350,7 @@ static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) if (READ_ONCE(history[i]) == rxhash) count++; - victim = prandom_u32() % ROLLOVER_HLEN; + victim = prandom_u32_max(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) @@ -1777,6 +1777,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; + match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; @@ -2293,8 +2294,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (snaplen > res) @@ -3277,7 +3277,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data) + 1]; + char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality @@ -3288,8 +3288,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); - name[sizeof(uaddr->sa_data)] = 0; + 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); } @@ -3520,8 +3520,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; aux.tp_len = origlen; @@ -3561,11 +3560,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); diff --git a/net/rds/bind.c b/net/rds/bind.c index 5b5fb4ca8d3e..97a29172a8ee 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -104,7 +104,7 @@ static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr, return -EINVAL; last = rover; } else { - rover = max_t(u16, prandom_u32(), 2); + rover = max_t(u16, get_random_u16(), 2); last = rover - 1; } diff --git a/net/rds/message.c b/net/rds/message.c index 44dbc612ef54..b47e4f0a1639 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -366,7 +366,6 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter * struct scatterlist *sg; int ret = 0; int length = iov_iter_count(from); - int total_copied = 0; struct rds_msg_zcopy_info *info; rm->m_inc.i_hdr.h_len = cpu_to_be32(iov_iter_count(from)); @@ -404,7 +403,6 @@ static int rds_message_zcopy_from_user(struct rds_message *rm, struct iov_iter * ret = -EFAULT; goto err; } - total_copied += copied; length -= copied; sg_set_page(sg, pages, copied, start); rm->data.op_nents++; diff --git a/net/rds/send.c b/net/rds/send.c index 0c5504068e3c..5e57a1581dc6 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1114,7 +1114,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) struct rds_conn_path *cpath; struct in6_addr daddr; __u32 scope_id = 0; - size_t total_payload_len = payload_len, rdma_payload_len = 0; + size_t rdma_payload_len = 0; bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = DIV_ROUND_UP(payload_len, PAGE_SIZE); @@ -1243,7 +1243,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (ret) goto out; - total_payload_len += rdma_payload_len; if (max_t(size_t, payload_len, rdma_payload_len) > RDS_MAX_MSG_SIZE) { ret = -EMSGSIZE; goto out; diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 4444fd82b66d..c5b86066ff66 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -503,6 +503,9 @@ bool rds_tcp_tune(struct socket *sock) release_sock(sk); return false; } + /* Update ns_tracker to current stack trace and refcounted tracker */ + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index 8b96a56d3a49..0f77ae8ef944 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -236,6 +236,9 @@ void rose_transmit_clear_request(struct rose_neigh *neigh, unsigned int lci, uns unsigned char *dptr; int len; + if (!neigh->dev) + return; + len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 3; if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index b11281bed2a4..fdeba488fc6e 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -30,6 +30,7 @@ rxrpc-y := \ sendmsg.o \ server_key.o \ skbuff.o \ + txbuf.o \ utils.o rxrpc-$(CONFIG_PROC_FS) += proc.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index ceba28e9dce6..aacdd96a9886 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -39,7 +39,7 @@ atomic_t rxrpc_debug_id; EXPORT_SYMBOL(rxrpc_debug_id); /* count of skbs currently in use */ -atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +atomic_t rxrpc_n_rx_skbs; struct workqueue_struct *rxrpc_workqueue; @@ -93,12 +93,11 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx, srx->transport_len > len) return -EINVAL; - if (srx->transport.family != rx->family && - srx->transport.family == AF_INET && rx->family != AF_INET6) - return -EAFNOSUPPORT; - switch (srx->transport.family) { case AF_INET: + if (rx->family != AF_INET && + rx->family != AF_INET6) + return -EAFNOSUPPORT; if (srx->transport_len < sizeof(struct sockaddr_in)) return -EINVAL; tail = offsetof(struct sockaddr_rxrpc, transport.sin.__pad); @@ -106,6 +105,8 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx, #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: + if (rx->family != AF_INET6) + return -EAFNOSUPPORT; if (srx->transport_len < sizeof(struct sockaddr_in6)) return -EINVAL; tail = offsetof(struct sockaddr_rxrpc, transport) + @@ -979,7 +980,7 @@ static int __init af_rxrpc_init(void) goto error_call_jar; } - rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1); + rxrpc_workqueue = alloc_workqueue("krxrpcd", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!rxrpc_workqueue) { pr_notice("Failed to allocate work queue\n"); goto error_work_queue; @@ -1059,7 +1060,6 @@ static void __exit af_rxrpc_exit(void) sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); unregister_pernet_device(&rxrpc_net_ops); - ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); /* Make sure the local and peer records pinned by any dying connections diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1ad0ec5afb50..f5c538ce3e23 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -29,6 +29,7 @@ struct rxrpc_crypt { struct key_preparsed_payload; struct rxrpc_connection; +struct rxrpc_txbuf; /* * Mark applied to socket buffers in skb->mark. skb->priority is used @@ -93,6 +94,22 @@ struct rxrpc_net { struct list_head peer_keepalive_new; struct timer_list peer_keepalive_timer; struct work_struct peer_keepalive_work; + + atomic_t stat_tx_data; + atomic_t stat_tx_data_retrans; + atomic_t stat_tx_data_send; + atomic_t stat_tx_data_send_frag; + atomic_t stat_rx_data; + atomic_t stat_rx_data_reqack; + atomic_t stat_rx_data_jumbo; + + atomic_t stat_tx_ack_fill; + atomic_t stat_tx_ack_send; + atomic_t stat_tx_ack_skip; + atomic_t stat_tx_acks[256]; + atomic_t stat_rx_acks[256]; + + atomic_t stat_why_req_ack[8]; }; /* @@ -178,20 +195,12 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - atomic_t nr_ring_pins; /* Number of rxtx ring pins */ - u8 nr_subpackets; /* Number of subpackets */ - u8 rx_flags; /* Received packet flags */ -#define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ -#define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */ - union { - int remain; /* amount of space remaining for next write */ - - /* List of requested ACKs on subpackets */ - unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) / - BITS_PER_LONG]; - }; + u16 offset; /* Offset of data */ + u16 len; /* Length of data */ + u8 flags; +#define RXRPC_RX_VERIFIED 0x01 - struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ + struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; #define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) @@ -233,19 +242,14 @@ struct rxrpc_security { size_t *, size_t *, size_t *); /* impose security on a packet */ - int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t); + int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); /* verify the security on a received packet */ - int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, - unsigned int, unsigned int, rxrpc_seq_t, u16); + int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); /* Free crypto request on a call */ void (*free_call_crypto)(struct rxrpc_call *); - /* Locate the data in a received packet that has been verified. */ - void (*locate_data)(struct rxrpc_call *, struct sk_buff *, - unsigned int *, unsigned int *); - /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); @@ -276,6 +280,8 @@ struct rxrpc_local { struct hlist_node link; struct socket *socket; /* my UDP socket */ struct work_struct processor; + struct list_head ack_tx_queue; /* List of ACKs that need sending */ + spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ @@ -326,7 +332,7 @@ struct rxrpc_peer { u32 rto_j; /* Retransmission timeout in jiffies */ u8 backoff; /* Backoff timeout */ - u8 cong_cwnd; /* Congestion window size */ + u8 cong_ssthresh; /* Congestion slow-start threshold */ }; /* @@ -399,6 +405,7 @@ enum rxrpc_conn_proto_state { struct rxrpc_bundle { struct rxrpc_conn_parameters params; refcount_t ref; + atomic_t active; /* Number of active users */ unsigned int debug_id; bool try_upgrade; /* True if the bundle is attempting upgrade */ bool alloc_conn; /* True if someone's getting a conn */ @@ -490,6 +497,7 @@ enum rxrpc_call_flag { RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ + RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ @@ -498,16 +506,16 @@ enum rxrpc_call_flag { RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ + RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ + RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { - RXRPC_CALL_EV_ACK, /* need to generate ACK */ RXRPC_CALL_EV_ABORT, /* need to generate abort */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ - RXRPC_CALL_EV_PING, /* Ping send required */ RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ }; @@ -566,7 +574,7 @@ struct rxrpc_call { struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ - unsigned long ack_at; /* When deferred ACK needs to happen */ + unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ unsigned long resend_at; /* When next resend needs to happen */ unsigned long ping_at; /* When next to send a ping */ @@ -576,7 +584,6 @@ struct rxrpc_call { unsigned long expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ - struct skcipher_request *cipher_req; /* Packet cipher request buffer */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ @@ -587,14 +594,12 @@ struct rxrpc_call { struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ - struct sk_buff *tx_pending; /* Tx socket buffer being filled */ + struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ - __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long flags; unsigned long events; - spinlock_t lock; spinlock_t notify_lock; /* Kernel notification lock */ rwlock_t state_lock; /* lock for state transition */ u32 abort_code; /* Local/remote abort code */ @@ -610,37 +615,27 @@ struct rxrpc_call { int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ - bool rx_pkt_last; /* Current recvmsg packet is last */ - - /* Rx/Tx circular buffer, depending on phase. - * - * In the Rx phase, packets are annotated with 0 or the number of the - * segment of a jumbo packet each buffer refers to. There can be up to - * 47 segments in a maximum-size UDP packet. - * - * In the Tx phase, packets are annotated with which buffers have been - * acked. - */ -#define RXRPC_RXTX_BUFF_SIZE 64 -#define RXRPC_RXTX_BUFF_MASK (RXRPC_RXTX_BUFF_SIZE - 1) -#define RXRPC_INIT_RX_WINDOW_SIZE 63 - struct sk_buff **rxtx_buffer; - u8 *rxtx_annotations; -#define RXRPC_TX_ANNO_ACK 0 -#define RXRPC_TX_ANNO_UNACK 1 -#define RXRPC_TX_ANNO_NAK 2 -#define RXRPC_TX_ANNO_RETRANS 3 -#define RXRPC_TX_ANNO_MASK 0x03 -#define RXRPC_TX_ANNO_LAST 0x04 -#define RXRPC_TX_ANNO_RESENT 0x08 - -#define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */ -#define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ - rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but - * not hard-ACK'd packet follows this. - */ + + /* Transmitted data tracking. */ + spinlock_t tx_lock; /* Transmit queue lock */ + struct list_head tx_buffer; /* Buffer of transmissible packets */ + rxrpc_seq_t tx_bottom; /* First packet in buffer */ + rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ + u8 tx_winsize; /* Maximum size of Tx window */ +#define RXRPC_TX_MAX_WINDOW 128 + ktime_t tx_last_sent; /* Last time a transmission occurred */ + + /* Received data tracking */ + struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ + struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ + + rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ + rxrpc_seq_t rx_consumed; /* Highest packet consumed */ + rxrpc_serial_t rx_serial; /* Highest serial received for this call */ + u8 rx_winsize; /* Size of Rx window */ + spinlock_t input_lock; /* Lock for packet input to this call */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA @@ -655,25 +650,17 @@ struct rxrpc_call { u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ - rxrpc_seq_t rx_hard_ack; /* Dead slot in buffer; the first received but not - * consumed packet follows this. - */ - rxrpc_seq_t rx_top; /* Highest Rx slot allocated. */ - rxrpc_seq_t rx_expect_next; /* Expected next packet sequence number */ - rxrpc_serial_t rx_serial; /* Highest serial received for this call */ - u8 rx_winsize; /* Size of Rx window */ - u8 tx_winsize; /* Maximum size of Tx window */ - bool tx_phase; /* T if transmission phase, F if receive phase */ - u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ - - spinlock_t input_lock; /* Lock for packet input to this call */ - /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ - rxrpc_seq_t ackr_highest_seq; /* Higest sequence number received */ + atomic64_t ackr_window; /* Base (in LSW) and top (in MSW) of SACK window */ atomic_t ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ + struct { +#define RXRPC_SACK_SIZE 256 + /* SACK table for soft-acked packets */ + u8 ackr_sack_table[RXRPC_SACK_SIZE]; + } __aligned(8); /* RTT management */ rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ @@ -687,21 +674,24 @@ struct rxrpc_call { ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ rxrpc_seq_t acks_first_seq; /* first sequence number received */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ + rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ + rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ + struct sk_buff *acks_soft_tbl; /* The last ACK packet with NAKs in it */ + spinlock_t acks_ack_lock; /* Access to ->acks_last_ack */ }; /* * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { + u16 nr_acks; /* Number of ACKs in packet */ + u16 nr_new_acks; /* Number of new ACKs in packet */ + u16 nr_rot_new_acks; /* Number of rotated new ACKs */ u8 ack_reason; - u8 nr_acks; /* Number of ACKs in packet */ - u8 nr_nacks; /* Number of NACKs in packet */ - u8 nr_new_acks; /* Number of new ACKs in packet */ - u8 nr_new_nacks; /* Number of new NACKs in packet */ - u8 nr_rot_new_acks; /* Number of rotated new ACKs */ + bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ u8 flight_size; /* Number of unreceived transmissions */ @@ -744,12 +734,58 @@ struct rxrpc_send_params { bool upgrade; /* If the connection is upgradeable */ }; +/* + * Buffer of data to be output as a packet. + */ +struct rxrpc_txbuf { + struct rcu_head rcu; + struct list_head call_link; /* Link in call->tx_queue */ + struct list_head tx_link; /* Link in live Enc queue or Tx queue */ + struct rxrpc_call *call; /* Call to which belongs */ + ktime_t last_sent; /* Time at which last transmitted */ + refcount_t ref; + rxrpc_seq_t seq; /* Sequence number of this packet */ + unsigned int call_debug_id; + unsigned int debug_id; + unsigned int len; /* Amount of data in buffer */ + unsigned int space; /* Remaining data space */ + unsigned int offset; /* Offset of fill point */ + unsigned long flags; +#define RXRPC_TXBUF_LAST 0 /* Set if last packet in Tx phase */ +#define RXRPC_TXBUF_RESENT 1 /* Set if has been resent */ + u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ + struct { + /* The packet for encrypting and DMA'ing. We align it such + * that data[] aligns correctly for any crypto blocksize. + */ + u8 pad[64 - sizeof(struct rxrpc_wire_header)]; + struct rxrpc_wire_header wire; /* Network-ready header */ + union { + u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + struct { + struct rxrpc_ackpacket ack; + u8 acks[0]; + }; + }; + } __aligned(64); +}; + +static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) +{ + return txb->wire.flags & RXRPC_CLIENT_INITIATED; +} + +static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) +{ + return !rxrpc_sending_to_server(txb); +} + #include <trace/events/rxrpc.h> /* * af_rxrpc.c */ -extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +extern atomic_t rxrpc_n_rx_skbs; extern struct workqueue_struct *rxrpc_workqueue; /* @@ -766,8 +802,12 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c */ -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, - enum rxrpc_propose_ack_trace); +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why); +void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); +void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, + enum rxrpc_propose_ack_trace); +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -949,15 +989,12 @@ static inline bool __rxrpc_use_local(struct rxrpc_local *local) * misc.c */ extern unsigned int rxrpc_max_backlog __read_mostly; -extern unsigned long rxrpc_requested_ack_delay; extern unsigned long rxrpc_soft_ack_delay; extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; -extern const s8 rxrpc_ack_priority[]; - /* * net_ns.c */ @@ -972,16 +1009,15 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *); +void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); -int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); +int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packets(struct rxrpc_local *); void rxrpc_send_keepalive(struct rxrpc_peer *); /* * peer_event.c */ -void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); void rxrpc_error_report(struct sock *); void rxrpc_peer_keepalive_worker(struct work_struct *); @@ -1092,6 +1128,15 @@ void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); /* + * stats.c + */ +int rxrpc_stats_show(struct seq_file *seq, void *v); +int rxrpc_stats_clear(struct file *file, char *buf, size_t size); + +#define rxrpc_inc_stat(rxnet, s) atomic_inc(&(rxnet)->s) +#define rxrpc_dec_stat(rxnet, s) atomic_dec(&(rxnet)->s) + +/* * sysctl.c */ #ifdef CONFIG_SYSCTL @@ -1103,6 +1148,16 @@ static inline void rxrpc_sysctl_exit(void) {} #endif /* + * txbuf.c + */ +extern atomic_t rxrpc_nr_txbuf; +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp); +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); + +/* * utils.c */ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 99e10eea3732..48790ee77019 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -248,9 +248,8 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) if (call->peer->rtt_count < 3 || ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); + rxrpc_send_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ack_ping_for_params); } /* @@ -325,7 +324,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, call->security = conn->security; call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->params.peer); - call->cong_cwnd = call->peer->cong_cwnd; + call->cong_ssthresh = call->peer->cong_ssthresh; + call->tx_last_sent = ktime_get_real(); return call; } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 2a93e7b5fbd0..1e21a708390e 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -20,127 +20,103 @@ /* * Propose a PING ACK be sent. */ -static void rxrpc_propose_ping(struct rxrpc_call *call, - bool immediate, bool background) +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why) { - if (immediate) { - if (background && - !test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies; - unsigned long ping_at = now + rxrpc_idle_ack_delay; - - if (time_before(ping_at, call->ping_at)) { - WRITE_ONCE(call->ping_at, ping_at); - rxrpc_reduce_call_timer(call, ping_at, now, - rxrpc_timer_set_for_ping); - } + unsigned long now = jiffies; + unsigned long ping_at = now + rxrpc_idle_ack_delay; + + if (time_before(ping_at, call->ping_at)) { + WRITE_ONCE(call->ping_at, ping_at); + rxrpc_reduce_call_timer(call, ping_at, now, + rxrpc_timer_set_for_ping); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); } } /* - * propose an ACK be sent + * Propose a DELAY ACK be sent in the future. */ -static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, - enum rxrpc_propose_ack_trace why) +void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_propose_ack_trace why) { - enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; unsigned long expiry = rxrpc_soft_ack_delay; - s8 prior = rxrpc_ack_priority[ack_reason]; - - /* Pings are handled specially because we don't want to accidentally - * lose a ping response by subsuming it into a ping. - */ - if (ack_reason == RXRPC_ACK_PING) { - rxrpc_propose_ping(call, immediate, background); - goto trace; + unsigned long now = jiffies, ack_at; + + call->ackr_serial = serial; + + if (rxrpc_soft_ack_delay < expiry) + expiry = rxrpc_soft_ack_delay; + if (call->peer->srtt_us != 0) + ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); + else + ack_at = expiry; + + ack_at += READ_ONCE(call->tx_backoff); + ack_at += now; + if (time_before(ack_at, call->delay_ack_at)) { + WRITE_ONCE(call->delay_ack_at, ack_at); + rxrpc_reduce_call_timer(call, ack_at, now, + rxrpc_timer_set_for_ack); } - /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial - * numbers, but we don't alter the timeout. - */ - _debug("prior %u %u vs %u %u", - ack_reason, prior, - call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]); - if (ack_reason == call->ackr_reason) { - if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { - outcome = rxrpc_propose_ack_update; - call->ackr_serial = serial; - } - if (!immediate) - goto trace; - } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { - call->ackr_reason = ack_reason; - call->ackr_serial = serial; - } else { - outcome = rxrpc_propose_ack_subsume; + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); +} + +/* + * Queue an ACK for immediate transmission. + */ +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) +{ + struct rxrpc_local *local = call->conn->params.local; + struct rxrpc_txbuf *txb; + + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + return; + if (ack_reason == RXRPC_ACK_DELAY && + test_and_set_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags)) { + trace_rxrpc_drop_ack(call, why, ack_reason, serial, false); + return; } - switch (ack_reason) { - case RXRPC_ACK_REQUESTED: - if (rxrpc_requested_ack_delay < expiry) - expiry = rxrpc_requested_ack_delay; - if (serial == 1) - immediate = false; - break; - - case RXRPC_ACK_DELAY: - if (rxrpc_soft_ack_delay < expiry) - expiry = rxrpc_soft_ack_delay; - break; - - case RXRPC_ACK_IDLE: - if (rxrpc_idle_ack_delay < expiry) - expiry = rxrpc_idle_ack_delay; - break; - - default: - immediate = true; - break; + rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); + + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK, + in_softirq() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS); + if (!txb) { + kleave(" = -ENOMEM"); + return; } - if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) { - _debug("already scheduled"); - } else if (immediate || expiry == 0) { - _debug("immediate ACK %lx", call->events); - if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) && - background) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies, ack_at; - - if (call->peer->srtt_us != 0) - ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); - else - ack_at = expiry; - - ack_at += READ_ONCE(call->tx_backoff); - ack_at += now; - if (time_before(ack_at, call->ack_at)) { - WRITE_ONCE(call->ack_at, ack_at); - rxrpc_reduce_call_timer(call, ack_at, now, - rxrpc_timer_set_for_ack); - } + txb->ack_why = why; + txb->wire.seq = 0; + txb->wire.type = RXRPC_PACKET_TYPE_ACK; + txb->wire.flags |= RXRPC_SLOW_START_OK; + txb->ack.bufferSpace = 0; + txb->ack.maxSkew = 0; + txb->ack.firstPacket = 0; + txb->ack.previousPacket = 0; + txb->ack.serial = htonl(serial); + txb->ack.reason = ack_reason; + txb->ack.nAcks = 0; + + if (!rxrpc_try_get_call(call, rxrpc_call_got)) { + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); + return; } -trace: - trace_rxrpc_propose_ack(call, why, ack_reason, serial, immediate, - background, outcome); -} + spin_lock_bh(&local->ack_tx_lock); + list_add_tail(&txb->tx_link, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + trace_rxrpc_send_ack(call, why, ack_reason, serial); -/* - * propose an ACK be sent, locking the call structure - */ -void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, - enum rxrpc_propose_ack_trace why) -{ - spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, serial, - immediate, background, why); - spin_unlock_bh(&call->lock); + if (in_task()) { + rxrpc_transmit_ack_packets(call->peer->local); + } else { + rxrpc_get_local(local); + rxrpc_queue_local(local); + } } /* @@ -156,62 +132,131 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) */ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { - struct sk_buff *skb; + struct rxrpc_ackpacket *ack = NULL; + struct rxrpc_txbuf *txb; + struct sk_buff *ack_skb = NULL; unsigned long resend_at; - rxrpc_seq_t cursor, seq, top; + rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; - int ix; - u8 annotation, anno_type, retrans = 0, unacked = 0; + bool unacked = false; + unsigned int i; + LIST_HEAD(retrans_queue); - _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); + _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); + oldest = now; + + /* See if there's an ACK saved with a soft-ACK table in it. */ + if (call->acks_soft_tbl) { + spin_lock_bh(&call->acks_ack_lock); + ack_skb = call->acks_soft_tbl; + if (ack_skb) { + rxrpc_get_skb(ack_skb, rxrpc_skb_ack); + ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); + } + spin_unlock_bh(&call->acks_ack_lock); + } - spin_lock_bh(&call->lock); + if (list_empty(&call->tx_buffer)) + goto no_resend; - cursor = call->tx_hard_ack; - top = call->tx_top; - ASSERT(before_eq(cursor, top)); - if (cursor == top) - goto out_unlock; + spin_lock(&call->tx_lock); - /* Scan the packet list without dropping the lock and decide which of - * the packets in the Tx buffer we're going to resend and what the new - * resend timeout will be. - */ - trace_rxrpc_resend(call, (cursor + 1) & RXRPC_RXTX_BUFF_MASK); - oldest = now; - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - if (anno_type == RXRPC_TX_ANNO_ACK) - continue; + if (list_empty(&call->tx_buffer)) + goto no_further_resend; + + trace_rxrpc_resend(call); + txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); - skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_seen); + /* Scan the soft ACK table without dropping the lock and resend any + * explicitly NAK'd packets. + */ + if (ack) { + for (i = 0; i < ack->nAcks; i++) { + rxrpc_seq_t seq; - if (anno_type == RXRPC_TX_ANNO_UNACK) { - if (ktime_after(skb->tstamp, max_age)) { - if (ktime_before(skb->tstamp, oldest)) - oldest = skb->tstamp; + if (ack->acks[i] & 1) continue; + seq = ntohl(ack->firstPacket) + i; + if (after(txb->seq, transmitted)) + break; + if (after(txb->seq, seq)) + continue; /* A new hard ACK probably came in */ + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (txb->seq == seq) + goto found_txb; + } + goto no_further_resend; + + found_txb: + if (after(ntohl(txb->wire.serial), call->acks_highest_serial)) + continue; /* Ack point not yet reached */ + + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); + + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + rxrpc_get_call(call, rxrpc_call_got_tx); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); } - if (!(annotation & RXRPC_TX_ANNO_RESENT)) - unacked++; + + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); + + if (list_is_last(&txb->call_link, &call->tx_buffer)) + goto no_further_resend; + txb = list_next_entry(txb, call_link); + } + } + + /* Fast-forward through the Tx queue to the point the peer says it has + * seen. Anything between the soft-ACK table and that point will get + * ACK'd or NACK'd in due course, so don't worry about it here; here we + * need to consider retransmitting anything beyond that point. + * + * Note that ACK for a packet can beat the update of tx_transmitted. + */ + if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted))) + goto no_further_resend; + + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq))) + continue; + if (after(txb->seq, READ_ONCE(call->tx_transmitted))) + break; /* Not transmitted yet */ + + if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && + before(ntohl(txb->wire.serial), ntohl(ack->serial))) + goto do_resend; /* Wasn't accounted for by a more recent ping. */ + + if (ktime_after(txb->last_sent, max_age)) { + if (ktime_before(txb->last_sent, oldest)) + oldest = txb->last_sent; + continue; } - /* Okay, we need to retransmit a packet. */ - call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS | annotation; - retrans++; - trace_rxrpc_retransmit(call, seq, annotation | anno_type, - ktime_to_ns(ktime_sub(skb->tstamp, max_age))); + do_resend: + unacked = true; + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + } } +no_further_resend: + spin_unlock(&call->tx_lock); +no_resend: + rxrpc_free_skb(ack_skb, rxrpc_skb_freed); + resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans); + resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, + !list_empty(&retrans_queue)); WRITE_ONCE(call->resend_at, resend_at); if (unacked) @@ -221,62 +266,28 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) * that an ACK got lost somewhere. Send a ping to find out instead of * retransmitting data. */ - if (!retrans) { + if (list_empty(&retrans_queue)) { rxrpc_reduce_call_timer(call, resend_at, now_j, rxrpc_timer_set_for_resend); - spin_unlock_bh(&call->lock); ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) goto out; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - rxrpc_send_ack_packet(call, true, NULL); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); goto out; } - /* Now go through the Tx window and perform the retransmissions. We - * have to drop the lock for each send. If an ACK comes in whilst the - * lock is dropped, it may clear some of the retransmission markers for - * packets that it soft-ACKs. - */ - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - if (anno_type != RXRPC_TX_ANNO_RETRANS) - continue; - - /* We need to reset the retransmission state, but we need to do - * so before we drop the lock as a new ACK/NAK may come in and - * confuse things - */ - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; - call->rxtx_annotations[ix] = annotation; - - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; - - rxrpc_get_skb(skb, rxrpc_skb_got); - spin_unlock_bh(&call->lock); - - if (rxrpc_send_data_packet(call, skb, true) < 0) { - rxrpc_free_skb(skb, rxrpc_skb_freed); - return; - } + while ((txb = list_first_entry_or_null(&retrans_queue, + struct rxrpc_txbuf, tx_link))) { + list_del_init(&txb->tx_link); + rxrpc_send_data_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); - if (rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - - rxrpc_free_skb(skb, rxrpc_skb_freed); - spin_lock_bh(&call->lock); - if (after(call->tx_hard_ack, seq)) - seq = call->tx_hard_ack; + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); } -out_unlock: - spin_unlock_bh(&call->lock); out: _leave(""); } @@ -288,9 +299,9 @@ void rxrpc_process_call(struct work_struct *work) { struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); - rxrpc_serial_t *send_ack; unsigned long now, next, t; unsigned int iterations = 0; + rxrpc_serial_t ackr_serial; rxrpc_see_call(call); @@ -309,6 +320,9 @@ recheck_state: goto recheck_state; } + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); + if (call->state == RXRPC_CALL_COMPLETE) { rxrpc_delete_call_timer(call); goto out_put; @@ -335,11 +349,13 @@ recheck_state: set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); } - t = READ_ONCE(call->ack_at); + t = READ_ONCE(call->delay_ack_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); - cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_ACK, &call->events); + cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); + ackr_serial = xchg(&call->ackr_serial, 0); + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial, + rxrpc_propose_ack_ping_for_lost_ack); } t = READ_ONCE(call->ack_lost_at); @@ -353,16 +369,16 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true, - rxrpc_propose_ack_ping_for_keepalive); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->ping_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now); cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->resend_at); @@ -385,25 +401,10 @@ recheck_state: goto recheck_state; } - send_ack = NULL; if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { call->acks_lost_top = call->tx_top; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - send_ack = &call->acks_lost_ping; - } - - if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) || - send_ack) { - if (call->ackr_reason) { - rxrpc_send_ack_packet(call, false, send_ack); - goto recheck_state; - } - } - - if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) { - rxrpc_send_ack_packet(call, true, NULL); - goto recheck_state; + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); } if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) && @@ -419,7 +420,7 @@ recheck_state: set(call->expect_req_by); set(call->expect_term_by); - set(call->ack_at); + set(call->delay_ack_at); set(call->ack_lost_at); set(call->resend_at); set(call->keepalive_at); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 6401cdf7a624..1befe22cd301 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -52,7 +52,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); if (call->state < RXRPC_CALL_COMPLETE) { - trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies); + trace_rxrpc_timer_expired(call, jiffies); __rxrpc_queue_call(call); } else { rxrpc_put_call(call, rxrpc_call_put); @@ -129,16 +129,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, if (!call) return NULL; - call->rxtx_buffer = kcalloc(RXRPC_RXTX_BUFF_SIZE, - sizeof(struct sk_buff *), - gfp); - if (!call->rxtx_buffer) - goto nomem; - - call->rxtx_annotations = kcalloc(RXRPC_RXTX_BUFF_SIZE, sizeof(u8), gfp); - if (!call->rxtx_annotations) - goto nomem_2; - mutex_init(&call->user_mutex); /* Prevent lockdep reporting a deadlock false positive between the afs @@ -155,37 +145,39 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + INIT_LIST_HEAD(&call->tx_buffer); + skb_queue_head_init(&call->recvmsg_queue); + skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); - spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); + spin_lock_init(&call->tx_lock); spin_lock_init(&call->input_lock); + spin_lock_init(&call->acks_ack_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; call->tx_total_len = -1; call->next_rx_timo = 20 * HZ; call->next_req_timo = 1 * HZ; + atomic64_set(&call->ackr_window, 0x100000001ULL); memset(&call->sock_node, 0xed, sizeof(call->sock_node)); - /* Leave space in the ring to handle a maxed-out jumbo packet */ call->rx_winsize = rxrpc_rx_window_size; call->tx_winsize = 16; - call->rx_expect_next = 1; - call->cong_cwnd = 2; - call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; + if (RXRPC_TX_SMSS > 2190) + call->cong_cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + call->cong_cwnd = 3; + else + call->cong_cwnd = 4; + call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; call->rxnet = rxnet; call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; atomic_inc(&rxnet->nr_calls); return call; - -nomem_2: - kfree(call->rxtx_buffer); -nomem: - kmem_cache_free(rxrpc_call_jar, call); - return NULL; } /* @@ -206,7 +198,6 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, return ERR_PTR(-ENOMEM); call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; call->service_id = srx->srx_service; - call->tx_phase = true; now = ktime_get_real(); call->acks_latest_ts = now; call->cong_tstamp = now; @@ -223,7 +214,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) unsigned long now = jiffies; unsigned long j = now + MAX_JIFFY_OFFSET; - call->ack_at = j; + call->delay_ack_at = j; call->ack_lost_at = j; call->resend_at = j; call->ping_at = j; @@ -510,16 +501,12 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* - * Clean up the RxTx skb ring. + * Clean up the Rx skb ring. */ static void rxrpc_cleanup_ring(struct rxrpc_call *call) { - int i; - - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { - rxrpc_free_skb(call->rxtx_buffer[i], rxrpc_skb_cleaned); - call->rxtx_buffer[i] = NULL; - } + skb_queue_purge(&call->recvmsg_queue); + skb_queue_purge(&call->rx_oos_queue); } /* @@ -539,10 +526,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - spin_lock_bh(&call->lock); if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); - spin_unlock_bh(&call->lock); rxrpc_put_call_slot(call); rxrpc_delete_call_timer(call); @@ -656,8 +641,6 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_put_connection(call->conn); rxrpc_put_peer(call->peer); - kfree(call->rxtx_buffer); - kfree(call->rxtx_annotations); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) wake_up_var(&rxnet->nr_calls); @@ -684,6 +667,8 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { + struct rxrpc_txbuf *txb; + _net("DESTROY CALL %d", call->debug_id); memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); @@ -692,7 +677,13 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); rxrpc_cleanup_ring(call); - rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned); + while ((txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); + } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3c9eeb5b750c..f11c97e28d2a 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -40,6 +40,8 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -123,6 +125,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, bundle->params = *cp; rxrpc_get_peer(bundle->params.peer); refcount_set(&bundle->ref, 1); + atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); } @@ -149,7 +152,7 @@ void rxrpc_put_bundle(struct rxrpc_bundle *bundle) dead = __refcount_dec_and_test(&bundle->ref, &r); - _debug("PUT B=%x %d", d, r); + _debug("PUT B=%x %d", d, r - 1); if (dead) rxrpc_free_bundle(bundle); } @@ -338,6 +341,7 @@ found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); + atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); return bundle; @@ -363,7 +367,8 @@ static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, if (!cp->peer) goto error; - call->cong_cwnd = cp->peer->cong_cwnd; + call->tx_last_sent = ktime_get_real(); + call->cong_ssthresh = cp->peer->cong_ssthresh; if (call->cong_cwnd >= call->cong_ssthresh) call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; else @@ -435,6 +440,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (old) trace_rxrpc_client(old, -1, rxrpc_client_replace); candidate->bundle_shift = shift; + atomic_inc(&bundle->active); bundle->conns[i] = candidate; for (j = 0; j < RXRPC_MAXCALLS; j++) set_bit(shift + j, &bundle->avail_chans); @@ -725,6 +731,7 @@ granted_channel: smp_rmb(); out_put_bundle: + rxrpc_deactivate_bundle(bundle); rxrpc_put_bundle(bundle); out: _leave(" = %d", ret); @@ -900,9 +907,8 @@ out: static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; - struct rxrpc_local *local = bundle->params.local; unsigned int bindex; - bool need_drop = false, need_put = false; + bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -921,15 +927,22 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) } spin_unlock(&bundle->channel_lock); - /* If there are no more connections, remove the bundle */ - if (!bundle->avail_chans) { - _debug("maybe unbundle"); - spin_lock(&local->client_bundles_lock); + if (need_drop) { + rxrpc_deactivate_bundle(bundle); + rxrpc_put_connection(conn); + } +} - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) - if (bundle->conns[i]) - break; - if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { +/* + * Drop the active count on a bundle. + */ +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +{ + struct rxrpc_local *local = bundle->params.local; + bool need_put = false; + + if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { + if (!bundle->params.exclusive) { _debug("erase bundle"); rb_erase(&bundle->local_node, &local->client_bundles); need_put = true; @@ -939,10 +952,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_put) rxrpc_put_bundle(bundle); } - - if (need_drop) - rxrpc_put_connection(conn); - _leave(""); } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 22089e37e97f..156bd26daf74 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -175,7 +175,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, trace_rxrpc_disconnect_call(call); switch (call->completion) { case RXRPC_CALL_SUCCEEDED: - chan->last_seq = call->rx_hard_ack; + chan->last_seq = call->rx_highest_seq; chan->last_type = RXRPC_PACKET_TYPE_ACK; break; case RXRPC_CALL_LOCALLY_ABORTED: @@ -207,7 +207,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; - call->peer->cong_cwnd = call->cong_cwnd; + call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 721d847ba92b..bdf70b81addc 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -7,20 +7,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/errqueue.h> -#include <linux/udp.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/icmp.h> -#include <linux/gfp.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include <net/ip.h> -#include <net/udp.h> -#include <net/net_namespace.h> #include "ar-internal.h" static void rxrpc_proto_abort(const char *why, @@ -46,7 +32,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, bool resend = false; summary->flight_size = - (call->tx_top - call->tx_hard_ack) - summary->nr_acks; + (call->tx_top - call->acks_hard_ack) - summary->nr_acks; if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) { summary->retrans_timeo = true; @@ -72,9 +58,28 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, summary->cumulative_acks = cumulative_acks; summary->dup_acks = call->cong_dup_acks; + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if ((call->cong_mode == RXRPC_CALL_SLOW_START || + call->cong_mode == RXRPC_CALL_CONGEST_AVOIDANCE) && + ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real()) + ) { + change = rxrpc_cong_idle_reset; + summary->mode = RXRPC_CALL_SLOW_START; + if (RXRPC_TX_SMSS > 2190) + summary->cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + summary->cwnd = 3; + else + summary->cwnd = 4; + } + switch (call->cong_mode) { case RXRPC_CALL_SLOW_START: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; if (summary->cumulative_acks > 0) cwnd += 1; @@ -85,7 +90,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_CONGEST_AVOIDANCE: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; /* We analyse the number of packets that get ACK'd per RTT @@ -104,7 +109,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_PACKET_LOSS: - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; if (summary->new_low_nack) { @@ -142,7 +147,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, } else { change = rxrpc_cong_progress; cwnd = call->cong_ssthresh; - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; } goto out; @@ -164,8 +169,8 @@ resume_normality: out: cumulative_acks = 0; out_no_clear_ca: - if (cwnd >= RXRPC_RXTX_BUFF_SIZE - 1) - cwnd = RXRPC_RXTX_BUFF_SIZE - 1; + if (cwnd >= RXRPC_TX_MAX_WINDOW) + cwnd = RXRPC_TX_MAX_WINDOW; call->cong_cwnd = cwnd; call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); @@ -183,9 +188,8 @@ send_extra_data: /* Send some previously unsent DATA if we have some to advance the ACK * state. */ - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST || - summary->nr_acks != call->tx_top - call->tx_hard_ack) { + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) || + summary->nr_acks != call->tx_top - call->acks_hard_ack) { call->cong_extra++; wake_up(&call->waitq); } @@ -198,53 +202,39 @@ send_extra_data: static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { - struct sk_buff *skb, *list = NULL; + struct rxrpc_txbuf *txb; bool rot_last = false; - int ix; - u8 annotation; - - if (call->acks_lowest_nak == call->tx_hard_ack) { - call->acks_lowest_nak = to; - } else if (before_eq(call->acks_lowest_nak, to)) { - summary->new_low_nack = true; - call->acks_lowest_nak = to; - } - - spin_lock(&call->lock); - - while (before(call->tx_hard_ack, to)) { - call->tx_hard_ack++; - ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - annotation = call->rxtx_annotations[ix]; - rxrpc_see_skb(skb, rxrpc_skb_rotated); - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; - skb->next = list; - list = skb; - if (annotation & RXRPC_TX_ANNO_LAST) { + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (before_eq(txb->seq, call->acks_hard_ack)) + continue; + summary->nr_rot_new_acks++; + if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } - if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) - summary->nr_rot_new_acks++; + if (txb->seq == to) + break; } - spin_unlock(&call->lock); + if (rot_last) + set_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags); - trace_rxrpc_transmit(call, (rot_last ? - rxrpc_transmit_rotate_last : - rxrpc_transmit_rotate)); - wake_up(&call->waitq); + _enter("%x,%x,%x,%d", to, call->acks_hard_ack, call->tx_top, rot_last); - while (list) { - skb = list; - list = skb->next; - skb_mark_not_on_list(skb); - rxrpc_free_skb(skb, rxrpc_skb_freed); + if (call->acks_lowest_nak == call->acks_hard_ack) { + call->acks_lowest_nak = to; + } else if (after(to, call->acks_lowest_nak)) { + summary->new_low_nack = true; + call->acks_lowest_nak = to; } + smp_store_release(&call->acks_hard_ack, to); + + trace_rxrpc_txqueue(call, (rot_last ? + rxrpc_txqueue_rotate_last : + rxrpc_txqueue_rotate)); + wake_up(&call->waitq); return rot_last; } @@ -284,9 +274,9 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, write_unlock(&call->state_lock); if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); + trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); else - trace_rxrpc_transmit(call, rxrpc_transmit_end); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); _leave(" = ok"); return true; @@ -307,13 +297,10 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) rxrpc_seq_t top = READ_ONCE(call->tx_top); if (call->ackr_reason) { - spin_lock_bh(&call->lock); - call->ackr_reason = 0; - spin_unlock_bh(&call->lock); now = jiffies; timo = now + MAX_JIFFY_OFFSET; WRITE_ONCE(call->resend_at, timo); - WRITE_ONCE(call->ack_at, timo); + WRITE_ONCE(call->delay_ack_at, timo); trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } @@ -323,85 +310,230 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) return false; } } - if (!rxrpc_end_tx_phase(call, true, "ETD")) - return false; - call->tx_phase = false; - return true; + return rxrpc_end_tx_phase(call, true, "ETD"); +} + +static void rxrpc_input_update_ack_window(struct rxrpc_call *call, + rxrpc_seq_t window, rxrpc_seq_t wtop) +{ + atomic64_set_release(&call->ackr_window, ((u64)wtop) << 32 | window); } /* - * Scan a data packet to validate its structure and to work out how many - * subpackets it contains. - * - * A jumbo packet is a collection of consecutive packets glued together with - * little headers between that indicate how to change the initial header for - * each subpacket. - * - * RXRPC_JUMBO_PACKET must be set on all but the last subpacket - and all but - * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any - * size. + * Push a DATA packet onto the Rx queue. */ -static bool rxrpc_validate_data(struct sk_buff *skb) +static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, + rxrpc_seq_t window, rxrpc_seq_t wtop, + enum rxrpc_receive_trace why) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len = skb->len; - u8 flags = sp->hdr.flags; + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; - for (;;) { - if (flags & RXRPC_REQUEST_ACK) - __set_bit(sp->nr_subpackets, sp->rx_req_ack); - sp->nr_subpackets++; + __skb_queue_tail(&call->recvmsg_queue, skb); + rxrpc_input_update_ack_window(call, window, wtop); - if (!(flags & RXRPC_JUMBO_PACKET)) - break; + trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); +} - if (len - offset < RXRPC_JUMBO_SUBPKTLEN) - goto protocol_error; - if (flags & RXRPC_LAST_PACKET) - goto protocol_error; - offset += RXRPC_JUMBO_DATALEN; - if (skb_copy_bits(skb, offset, &flags, 1) < 0) - goto protocol_error; - offset += sizeof(struct rxrpc_jumbo_header); +/* + * Process a DATA packet. + */ +static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct sk_buff *oos; + rxrpc_serial_t serial = sp->hdr.serial; + u64 win = atomic64_read(&call->ackr_window); + rxrpc_seq_t window = lower_32_bits(win); + rxrpc_seq_t wtop = upper_32_bits(win); + rxrpc_seq_t wlimit = window + call->rx_winsize - 1; + rxrpc_seq_t seq = sp->hdr.seq; + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; + int ack_reason = -1; + + rxrpc_inc_stat(call->rxnet, stat_rx_data); + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + rxrpc_inc_stat(call->rxnet, stat_rx_data_reqack); + if (sp->hdr.flags & RXRPC_JUMBO_PACKET) + rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); + + if (last) { + if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq + 1 != wtop) { + rxrpc_proto_abort("LSN", call, seq); + goto err_free; + } + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, wtop)) { + pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", + call->debug_id, seq, window, wtop, wlimit); + rxrpc_proto_abort("LSA", call, seq); + goto err_free; + } } - if (flags & RXRPC_LAST_PACKET) - sp->rx_flags |= RXRPC_SKB_INCL_LAST; - return true; + if (after(seq, call->rx_highest_seq)) + call->rx_highest_seq = seq; -protocol_error: - return false; + trace_rxrpc_rx_data(call->debug_id, seq, serial, sp->hdr.flags); + + if (before(seq, window)) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; + } + if (after(seq, wlimit)) { + ack_reason = RXRPC_ACK_EXCEEDS_WINDOW; + goto send_ack; + } + + /* Queue the packet. */ + if (seq == window) { + rxrpc_seq_t reset_from; + bool reset_sack = false; + + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + ack_reason = RXRPC_ACK_REQUESTED; + /* Send an immediate ACK if we fill in a hole */ + else if (!skb_queue_empty(&call->rx_oos_queue)) + ack_reason = RXRPC_ACK_DELAY; + + window++; + if (after(window, wtop)) + wtop = window; + + spin_lock(&call->recvmsg_queue.lock); + rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); + skb = NULL; + + while ((oos = skb_peek(&call->rx_oos_queue))) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); + + if (after(osp->hdr.seq, window)) + break; + + __skb_unlink(oos, &call->rx_oos_queue); + last = osp->hdr.flags & RXRPC_LAST_PACKET; + seq = osp->hdr.seq; + if (!reset_sack) { + reset_from = seq; + reset_sack = true; + } + + window++; + rxrpc_input_queue_data(call, oos, window, wtop, + rxrpc_receive_queue_oos); + } + + spin_unlock(&call->recvmsg_queue.lock); + + if (reset_sack) { + do { + call->ackr_sack_table[reset_from % RXRPC_SACK_SIZE] = 0; + } while (reset_from++, before(reset_from, window)); + } + } else { + bool keep = false; + + ack_reason = RXRPC_ACK_OUT_OF_SEQUENCE; + + if (!call->ackr_sack_table[seq % RXRPC_SACK_SIZE]) { + call->ackr_sack_table[seq % RXRPC_SACK_SIZE] = 1; + keep = 1; + } + + if (after(seq + 1, wtop)) { + wtop = seq + 1; + rxrpc_input_update_ack_window(call, window, wtop); + } + + if (!keep) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; + } + + skb_queue_walk(&call->rx_oos_queue, oos) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); + + if (after(osp->hdr.seq, seq)) { + __skb_queue_before(&call->rx_oos_queue, oos, skb); + goto oos_queued; + } + } + + __skb_queue_tail(&call->rx_oos_queue, skb); + oos_queued: + trace_rxrpc_receive(call, last ? rxrpc_receive_oos_last : rxrpc_receive_oos, + sp->hdr.serial, sp->hdr.seq); + skb = NULL; + } + +send_ack: + if (ack_reason < 0 && + atomic_inc_return(&call->ackr_nr_unacked) > 2 && + test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + ack_reason = RXRPC_ACK_IDLE; + } else if (ack_reason >= 0) { + set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); + } + + if (ack_reason >= 0) + rxrpc_send_ACK(call, ack_reason, serial, + rxrpc_propose_ack_input_data); + else + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_input_data); + +err_free: + rxrpc_free_skb(skb, rxrpc_skb_freed); } /* - * Handle reception of a duplicate packet. - * - * We have to take care to avoid an attack here whereby we're given a series of - * jumbograms, each with a sequence number one before the preceding one and - * filled up to maximum UDP size. If they never send us the first packet in - * the sequence, they can cause us to have to hold on to around 2MiB of kernel - * space until the call times out. - * - * We limit the space usage by only accepting three duplicate jumbo packets per - * call. After that, we tell the other side we're no longer accepting jumbos - * (that information is encoded in the ACK packet). + * Split a jumbo packet and file the bits separately. */ -static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, - bool is_jumbo, bool *_jumbo_bad) +static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb) { - /* Discard normal packets that are duplicates. */ - if (is_jumbo) - return; + struct rxrpc_jumbo_header jhdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb), *jsp; + struct sk_buff *jskb; + unsigned int offset = sizeof(struct rxrpc_wire_header); + unsigned int len = skb->len - offset; - /* Skip jumbo subpackets that are duplicates. When we've had three or - * more partially duplicate jumbo packets, we refuse to take any more - * jumbos for this call. - */ - if (!*_jumbo_bad) { - call->nr_jumbo_bad++; - *_jumbo_bad = true; + while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { + if (len < RXRPC_JUMBO_SUBPKTLEN) + goto protocol_error; + if (sp->hdr.flags & RXRPC_LAST_PACKET) + goto protocol_error; + if (skb_copy_bits(skb, offset + RXRPC_JUMBO_DATALEN, + &jhdr, sizeof(jhdr)) < 0) + goto protocol_error; + + jskb = skb_clone(skb, GFP_ATOMIC); + if (!jskb) { + kdebug("couldn't clone"); + return false; + } + rxrpc_new_skb(jskb, rxrpc_skb_cloned_jumbo); + jsp = rxrpc_skb(jskb); + jsp->offset = offset; + jsp->len = RXRPC_JUMBO_DATALEN; + rxrpc_input_data_one(call, jskb); + + sp->hdr.flags = jhdr.flags; + sp->hdr._rsvd = ntohs(jhdr._rsvd); + sp->hdr.seq++; + sp->hdr.serial++; + offset += RXRPC_JUMBO_SUBPKTLEN; + len -= RXRPC_JUMBO_SUBPKTLEN; } + + sp->offset = offset; + sp->len = len; + rxrpc_input_data_one(call, skb); + return true; + +protocol_error: + return false; } /* @@ -412,17 +544,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; - unsigned int j, nr_subpackets, nr_unacked = 0; - rxrpc_serial_t serial = sp->hdr.serial, ack_serial = serial; - rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; - bool immediate_ack = false, jumbo_bad = false; - u8 ack = 0; + rxrpc_serial_t serial = sp->hdr.serial; + rxrpc_seq_t seq0 = sp->hdr.seq; - _enter("{%u,%u},{%u,%u}", - call->rx_hard_ack, call->rx_top, skb->len, seq0); + _enter("{%llx,%x},{%u,%x}", + atomic64_read(&call->ackr_window), call->rx_highest_seq, + skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x n=%u }", - sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets); + _proto("Rx DATA %%%u { #%u f=%02x }", + sp->hdr.serial, seq0, sp->hdr.flags); state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { @@ -430,6 +560,24 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) return; } + /* Unshare the packet so that it can be modified for in-place + * decryption. + */ + if (sp->hdr.securityIndex != 0) { + struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); + if (!nskb) { + rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + return; + } + + if (nskb != skb) { + rxrpc_eaten_skb(skb, rxrpc_skb_received); + skb = nskb; + rxrpc_new_skb(skb, rxrpc_skb_unshared); + sp = rxrpc_skb(skb); + } + } + if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -451,166 +599,18 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - goto unlock; - - hard_ack = READ_ONCE(call->rx_hard_ack); - - nr_subpackets = sp->nr_subpackets; - if (nr_subpackets > 1) { - if (call->nr_jumbo_bad > 3) { - ack = RXRPC_ACK_NOSPACE; - ack_serial = serial; - goto ack; - } - } - - for (j = 0; j < nr_subpackets; j++) { - rxrpc_serial_t serial = sp->hdr.serial + j; - rxrpc_seq_t seq = seq0 + j; - unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; - bool terminal = (j == nr_subpackets - 1); - bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); - u8 flags, annotation = j; - - _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", - j, serial, seq, terminal, last); - - if (last) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { - rxrpc_proto_abort("LSN", call, seq); - goto unlock; - } - } else { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { - rxrpc_proto_abort("LSA", call, seq); - goto unlock; - } - } - - flags = 0; - if (last) - flags |= RXRPC_LAST_PACKET; - if (!terminal) - flags |= RXRPC_JUMBO_PACKET; - if (test_bit(j, sp->rx_req_ack)) - flags |= RXRPC_REQUEST_ACK; - trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - - if (before_eq(seq, hard_ack)) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - continue; - } - - if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, nr_subpackets > 1, - &jumbo_bad); - if (ack != RXRPC_ACK_DUPLICATE) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - } - immediate_ack = true; - continue; - } - - if (after(seq, hard_ack + call->rx_winsize)) { - ack = RXRPC_ACK_EXCEEDS_WINDOW; - ack_serial = serial; - if (flags & RXRPC_JUMBO_PACKET) { - if (!jumbo_bad) { - call->nr_jumbo_bad++; - jumbo_bad = true; - } - } - - goto ack; - } - - if (flags & RXRPC_REQUEST_ACK && !ack) { - ack = RXRPC_ACK_REQUESTED; - ack_serial = serial; - } - - if (after(seq0, call->ackr_highest_seq)) - call->ackr_highest_seq = seq0; - - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - if (!terminal) - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } - immediate_ack = true; - } - - if (terminal) { - /* From this point on, we're not allowed to touch the - * packet any longer as its ref now belongs to the Rx - * ring. - */ - skb = NULL; - sp = NULL; - } - - nr_unacked++; - - if (last) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); - } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } + goto out; - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - ack_serial = serial; - } - call->rx_expect_next = seq + 1; - } - if (!ack) - ack_serial = serial; + if (!rxrpc_input_split_jumbo(call, skb)) { + rxrpc_proto_abort("VLD", call, sp->hdr.seq); + goto out; } + skb = NULL; -ack: - if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2 && !ack) - ack = RXRPC_ACK_IDLE; - - if (ack) - rxrpc_propose_ACK(call, ack, ack_serial, - immediate_ack, true, - rxrpc_propose_ack_input_data); - else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, - false, true, - rxrpc_propose_ack_input_data); - +out: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); -unlock: spin_unlock(&call->input_lock); rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [queued]"); @@ -679,31 +679,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, */ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { - rxrpc_seq_t top, bottom, seq; - bool resend = false; - - spin_lock_bh(&call->lock); - - bottom = call->tx_hard_ack + 1; - top = call->acks_lost_top; - if (before(bottom, top)) { - for (seq = bottom; before_eq(seq, top); seq++) { - int ix = seq & RXRPC_RXTX_BUFF_MASK; - u8 annotation = call->rxtx_annotations[ix]; - u8 anno_type = annotation & RXRPC_TX_ANNO_MASK; - - if (anno_type != RXRPC_TX_ANNO_UNACK) - continue; - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_RETRANS; - call->rxtx_annotations[ix] = annotation; - resend = true; - } - } - - spin_unlock_bh(&call->lock); - - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) + if (after(call->acks_lost_top, call->acks_prev_seq) && + !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } @@ -736,8 +713,8 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; + if (rwind > RXRPC_TX_MAX_WINDOW) + rwind = RXRPC_TX_MAX_WINDOW; if (call->tx_winsize != rwind) { if (rwind > call->tx_winsize) wake = true; @@ -776,40 +753,19 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, rxrpc_seq_t seq, int nr_acks, struct rxrpc_ack_summary *summary) { - int ix; - u8 annotation, anno_type; - - for (; nr_acks > 0; nr_acks--, seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - switch (*acks++) { - case RXRPC_ACK_TYPE_ACK: + unsigned int i; + + for (i = 0; i < nr_acks; i++) { + if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; - if (anno_type == RXRPC_TX_ANNO_ACK) - continue; summary->nr_new_acks++; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_ACK | annotation; - break; - case RXRPC_ACK_TYPE_NACK: - if (!summary->nr_nacks && - call->acks_lowest_nak != seq) { - call->acks_lowest_nak = seq; + } else { + if (!summary->saw_nacks && + call->acks_lowest_nak != seq + i) { + call->acks_lowest_nak = seq + i; summary->new_low_nack = true; } - summary->nr_nacks++; - if (anno_type == RXRPC_TX_ANNO_NAK) - continue; - summary->nr_new_nacks++; - if (anno_type == RXRPC_TX_ANNO_RETRANS) - continue; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_NAK | annotation; - break; - default: - return rxrpc_proto_abort("SFT", call, 0); + summary->saw_nacks = true; } } } @@ -851,12 +807,10 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; + struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - union { - struct rxrpc_ackpacket ack; - struct rxrpc_ackinfo info; - u8 acks[RXRPC_MAXACKS]; - } buf; + struct rxrpc_ackinfo info; + struct sk_buff *skb_old = NULL, *skb_put = skb; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -864,29 +818,28 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) _enter(""); offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &buf.ack, sizeof(buf.ack)) < 0) { - _debug("extraction failure"); - return rxrpc_proto_abort("XAK", call, 0); + if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) { + rxrpc_proto_abort("XAK", call, 0); + goto out_not_locked; } - offset += sizeof(buf.ack); + offset += sizeof(ack); ack_serial = sp->hdr.serial; - acked_serial = ntohl(buf.ack.serial); - first_soft_ack = ntohl(buf.ack.firstPacket); - prev_pkt = ntohl(buf.ack.previousPacket); + acked_serial = ntohl(ack.serial); + first_soft_ack = ntohl(ack.firstPacket); + prev_pkt = ntohl(ack.previousPacket); hard_ack = first_soft_ack - 1; - nr_acks = buf.ack.nAcks; - summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? - buf.ack.reason : RXRPC_ACK__INVALID); + nr_acks = ack.nAcks; + summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? + ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); - switch (buf.ack.reason) { + switch (ack.reason) { case RXRPC_ACK_PING_RESPONSE: - rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - ack_serial); rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, rxrpc_rtt_rx_ping_response); break; @@ -901,22 +854,20 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) break; } - if (buf.ack.reason == RXRPC_ACK_PING) { + if (ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", ack_serial); - rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ping); + rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, + rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ack); + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, + rxrpc_propose_ack_respond_to_ack); } /* If we get an EXCEEDS_WINDOW ACK from the server, it probably * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && + if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && first_soft_ack == 1 && prev_pkt == 0 && rxrpc_is_client_call(call)) { @@ -929,10 +880,10 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicate a change of address. However, we can retransmit the call * if we still have it buffered to the beginning. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && - call->tx_hard_ack == 0 && + call->acks_hard_ack == 0 && rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); @@ -944,14 +895,19 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->acks_first_seq, prev_pkt, call->acks_prev_seq); - return; + goto out_not_locked; } - buf.info.rxMTU = 0; + info.rxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(buf.info) && - skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + if (skb->len >= ioffset + sizeof(info) && + skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) { + rxrpc_proto_abort("XAI", call, 0); + goto out_not_locked; + } + + if (nr_acks > 0) + skb_condense(skb); spin_lock(&call->input_lock); @@ -967,9 +923,22 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; + switch (ack.reason) { + case RXRPC_ACK_PING: + break; + case RXRPC_ACK_PING_RESPONSE: + rxrpc_input_ping_response(call, skb->tstamp, acked_serial, + ack_serial); + fallthrough; + default: + if (after(acked_serial, call->acks_highest_serial)) + call->acks_highest_serial = acked_serial; + break; + } + /* Parse rwind and mtu sizes if provided. */ - if (buf.info.rxMTU) - rxrpc_input_ackinfo(call, skb, &buf.info); + if (info.rxMTU) + rxrpc_input_ackinfo(call, skb, &info); if (first_soft_ack == 0) { rxrpc_proto_abort("AK0", call, 0); @@ -987,7 +956,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (before(hard_ack, call->tx_hard_ack) || + if (before(hard_ack, call->acks_hard_ack) || after(hard_ack, call->tx_top)) { rxrpc_proto_abort("AKW", call, 0); goto out; @@ -997,7 +966,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (after(hard_ack, call->tx_hard_ack)) { + if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, "ETA"); goto out; @@ -1005,25 +974,38 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } if (nr_acks > 0) { - if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) { + if (offset > (int)skb->len - nr_acks) { rxrpc_proto_abort("XSA", call, 0); goto out; } - rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, - &summary); + + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = skb; + spin_unlock(&call->acks_ack_lock); + + rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, + nr_acks, &summary); + skb_put = NULL; + } else if (call->acks_soft_tbl) { + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = NULL; + spin_unlock(&call->acks_ack_lock); } - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST && + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, - false, true, - rxrpc_propose_ack_ping_for_lost_reply); + rxrpc_propose_ping(call, ack_serial, + rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); out: spin_unlock(&call->input_lock); +out_not_locked: + rxrpc_free_skb(skb_put, rxrpc_skb_freed); + rxrpc_free_skb(skb_old, rxrpc_skb_freed); } /* @@ -1096,7 +1078,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, case RXRPC_PACKET_TYPE_ACK: rxrpc_input_ack(call, skb); - break; + goto no_free; case RXRPC_PACKET_TYPE_BUSY: _proto("Rx BUSY %%%u", sp->hdr.serial); @@ -1307,8 +1289,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.callNumber == 0 || sp->hdr.seq == 0) goto bad_message; - if (!rxrpc_validate_data(skb)) - goto bad_message; /* Unshare the packet so that it can be modified for in-place * decryption. @@ -1422,7 +1402,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) trace_rxrpc_rx_data(chan->call_debug_id, sp->hdr.seq, sp->hdr.serial, - sp->hdr.flags, 0); + sp->hdr.flags); rxrpc_post_packet_to_conn(conn, skb); goto out; } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 9aae99d67833..0eb8471bfc53 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -25,16 +25,16 @@ static int none_how_much_data(struct rxrpc_call *call, size_t remain, return 0; } -static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, - size_t data_size) +static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { return 0; } -static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + sp->flags |= RXRPC_RX_VERIFIED; return 0; } @@ -42,11 +42,6 @@ static void none_free_call_crypto(struct rxrpc_call *call) { } -static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ -} - static int none_respond_to_challenge(struct rxrpc_connection *conn, struct sk_buff *skb, u32 *_abort_code) @@ -95,7 +90,6 @@ const struct rxrpc_security rxrpc_no_security = { .how_much_data = none_how_much_data, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, - .locate_data = none_locate_data, .respond_to_challenge = none_respond_to_challenge, .verify_response = none_verify_response, .clear = none_clear, diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 38ea98ff426b..a943fdf91e24 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -24,6 +24,20 @@ static void rxrpc_local_processor(struct work_struct *); static void rxrpc_local_rcu(struct rcu_head *); /* + * Handle an ICMP/ICMP6 error turning up at the tunnel. Push it through the + * usual mechanism so that it gets parsed and presented through the UDP + * socket's error_report(). + */ +static void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) +{ + if (ip_hdr(skb)->version == IPVERSION) + return ip_icmp_error(sk, skb, err, port, info, payload); + if (IS_ENABLED(CONFIG_AF_RXRPC_IPV6)) + return ipv6_icmp_error(sk, skb, err, port, info, payload); +} + +/* * Compare a local to an address. Return -ve, 0 or +ve to indicate less than, * same or greater than. * @@ -84,6 +98,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); + INIT_LIST_HEAD(&local->ack_tx_queue); + spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); @@ -419,6 +435,11 @@ static void rxrpc_local_processor(struct work_struct *work) break; } + if (!list_empty(&local->ack_tx_queue)) { + rxrpc_transmit_ack_packets(local); + again = true; + } + if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); again = true; diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index d4144fd86f84..056c428d8bf3 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -17,12 +17,6 @@ unsigned int rxrpc_max_backlog __read_mostly = 10; /* - * How long to wait before scheduling ACK generation after seeing a - * packet with RXRPC_REQUEST_ACK set (in jiffies). - */ -unsigned long rxrpc_requested_ack_delay = 1; - -/* * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). * * We use this when we've received new data packets. If those packets aren't @@ -46,10 +40,7 @@ unsigned long rxrpc_idle_ack_delay = HZ / 2; * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further * packets. */ -unsigned int rxrpc_rx_window_size = RXRPC_INIT_RX_WINDOW_SIZE; -#if (RXRPC_RXTX_BUFF_SIZE - 1) < RXRPC_INIT_RX_WINDOW_SIZE -#error Need to reduce RXRPC_INIT_RX_WINDOW_SIZE -#endif +unsigned int rxrpc_rx_window_size = 255; /* * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet @@ -62,15 +53,3 @@ unsigned int rxrpc_rx_mtu = 5692; * sender that we're willing to handle. */ unsigned int rxrpc_rx_jumbo_max = 4; - -const s8 rxrpc_ack_priority[] = { - [0] = 0, - [RXRPC_ACK_DELAY] = 1, - [RXRPC_ACK_REQUESTED] = 2, - [RXRPC_ACK_IDLE] = 3, - [RXRPC_ACK_DUPLICATE] = 4, - [RXRPC_ACK_OUT_OF_SEQUENCE] = 5, - [RXRPC_ACK_EXCEEDS_WINDOW] = 6, - [RXRPC_ACK_NOSPACE] = 7, - [RXRPC_ACK_PING_RESPONSE] = 8, -}; diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index bb4c25d6df64..84242c0e467c 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -101,6 +101,8 @@ static __net_init int rxrpc_init_net(struct net *net) proc_create_net("locals", 0444, rxnet->proc_net, &rxrpc_local_seq_ops, sizeof(struct seq_net_private)); + proc_create_net_single_write("stats", S_IFREG | 0644, rxnet->proc_net, + rxrpc_stats_show, rxrpc_stats_clear, NULL); return 0; err_proc: diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 9683617db704..c5eed0e83e47 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -13,15 +13,27 @@ #include <linux/export.h> #include <net/sock.h> #include <net/af_rxrpc.h> +#include <net/udp.h> #include "ar-internal.h" -struct rxrpc_ack_buffer { - struct rxrpc_wire_header whdr; - struct rxrpc_ackpacket ack; - u8 acks[255]; - u8 pad[3]; - struct rxrpc_ackinfo ackinfo; -}; +extern int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); + +static ssize_t do_udp_sendmsg(struct socket *socket, struct msghdr *msg, size_t len) +{ + struct sockaddr *sa = msg->msg_name; + struct sock *sk = socket->sk; + + if (IS_ENABLED(CONFIG_AF_RXRPC_IPV6)) { + if (sa->sa_family == AF_INET6) { + if (sk->sk_family != AF_INET6) { + pr_warn("AF_INET6 address on AF_INET socket\n"); + return -ENOPROTOOPT; + } + return udpv6_sendmsg(sk, msg, len); + } + } + return udp_sendmsg(sk, msg, len); +} struct rxrpc_abort_buffer { struct rxrpc_wire_header whdr; @@ -68,66 +80,83 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_ack_buffer *pkt, - rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top, - u8 reason) + struct rxrpc_txbuf *txb) { - rxrpc_serial_t serial; - unsigned int tmp; - rxrpc_seq_t hard_ack, top, seq; - int ix; + struct rxrpc_ackinfo ackinfo; + unsigned int qsize; + rxrpc_seq_t window, wtop, wrap_point, ix, first; + int rsize; + u64 wtmp; u32 mtu, jmax; - u8 *ackp = pkt->acks; + u8 *ackp = txb->acks; + u8 sack_buffer[sizeof(call->ackr_sack_table)] __aligned(8); - tmp = atomic_xchg(&call->ackr_nr_unacked, 0); - tmp |= atomic_xchg(&call->ackr_nr_consumed, 0); - if (!tmp && (reason == RXRPC_ACK_DELAY || - reason == RXRPC_ACK_IDLE)) - return 0; + atomic_set(&call->ackr_nr_unacked, 0); + atomic_set(&call->ackr_nr_consumed, 0); + rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); /* Barrier against rxrpc_input_data(). */ - serial = call->ackr_serial; - hard_ack = READ_ONCE(call->rx_hard_ack); - top = smp_load_acquire(&call->rx_top); - *_hard_ack = hard_ack; - *_top = top; - - pkt->ack.bufferSpace = htons(8); - pkt->ack.maxSkew = htons(0); - pkt->ack.firstPacket = htonl(hard_ack + 1); - pkt->ack.previousPacket = htonl(call->ackr_highest_seq); - pkt->ack.serial = htonl(serial); - pkt->ack.reason = reason; - pkt->ack.nAcks = top - hard_ack; - - if (reason == RXRPC_ACK_PING) - pkt->whdr.flags |= RXRPC_REQUEST_ACK; - - if (after(top, hard_ack)) { - seq = hard_ack + 1; - do { - ix = seq & RXRPC_RXTX_BUFF_MASK; - if (call->rxtx_buffer[ix]) - *ackp++ = RXRPC_ACK_TYPE_ACK; - else - *ackp++ = RXRPC_ACK_TYPE_NACK; - seq++; - } while (before_eq(seq, top)); +retry: + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + txb->ack.firstPacket = htonl(window); + txb->ack.nAcks = 0; + + if (after(wtop, window)) { + /* Try to copy the SACK ring locklessly. We can use the copy, + * only if the now-current top of the window didn't go past the + * previously read base - otherwise we can't know whether we + * have old data or new data. + */ + memcpy(sack_buffer, call->ackr_sack_table, sizeof(sack_buffer)); + wrap_point = window + RXRPC_SACK_SIZE - 1; + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + if (after(wtop, wrap_point)) { + cond_resched(); + goto retry; + } + + /* The buffer is maintained as a ring with an invariant mapping + * between bit position and sequence number, so we'll probably + * need to rotate it. + */ + txb->ack.nAcks = wtop - window; + ix = window % RXRPC_SACK_SIZE; + first = sizeof(sack_buffer) - ix; + + if (ix + txb->ack.nAcks <= RXRPC_SACK_SIZE) { + memcpy(txb->acks, sack_buffer + ix, txb->ack.nAcks); + } else { + memcpy(txb->acks, sack_buffer + ix, first); + memcpy(txb->acks + first, sack_buffer, + txb->ack.nAcks - first); + } + + ackp += txb->ack.nAcks; + } else if (before(wtop, window)) { + pr_warn("ack window backward %x %x", window, wtop); + } else if (txb->ack.reason == RXRPC_ACK_DELAY) { + txb->ack.reason = RXRPC_ACK_IDLE; } mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; - jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; - pkt->ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - pkt->ackinfo.maxMTU = htonl(mtu); - pkt->ackinfo.rwind = htonl(call->rx_winsize); - pkt->ackinfo.jumbo_max = htonl(jmax); + jmax = rxrpc_rx_jumbo_max; + qsize = (window - 1) - call->rx_consumed; + rsize = max_t(int, call->rx_winsize - qsize, 0); + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.maxMTU = htonl(mtu); + ackinfo.rwind = htonl(rsize); + ackinfo.jumbo_max = htonl(jmax); *ackp++ = 0; *ackp++ = 0; *ackp++ = 0; - return top - hard_ack + 3; + memcpy(ackp, &ackinfo, sizeof(ackinfo)); + return txb->ack.nAcks + 3 + sizeof(ackinfo); } /* @@ -176,26 +205,19 @@ static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, /* * Send an ACK call packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, - rxrpc_serial_t *_serial) +static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf *txb) { struct rxrpc_connection *conn; - struct rxrpc_ack_buffer *pkt; + struct rxrpc_call *call = txb->call; struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; size_t len, n; int ret, rtt_slot = -1; - u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; - pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - conn = call->conn; msg.msg_name = &call->peer->srx.transport; @@ -204,83 +226,97 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, msg.msg_controllen = 0; msg.msg_flags = 0; - pkt->whdr.epoch = htonl(conn->proto.epoch); - pkt->whdr.cid = htonl(call->cid); - pkt->whdr.callNumber = htonl(call->call_id); - pkt->whdr.seq = 0; - pkt->whdr.type = RXRPC_PACKET_TYPE_ACK; - pkt->whdr.flags = RXRPC_SLOW_START_OK | conn->out_clientflag; - pkt->whdr.userStatus = 0; - pkt->whdr.securityIndex = call->security_ix; - pkt->whdr._rsvd = 0; - pkt->whdr.serviceId = htons(call->service_id); - - spin_lock_bh(&call->lock); - if (ping) { - reason = RXRPC_ACK_PING; - } else { - reason = call->ackr_reason; - if (!call->ackr_reason) { - spin_unlock_bh(&call->lock); - ret = 0; - goto out; - } - call->ackr_reason = 0; - } - n = rxrpc_fill_out_ack(conn, call, pkt, &hard_ack, &top, reason); + if (txb->ack.reason == RXRPC_ACK_PING) + txb->wire.flags |= RXRPC_REQUEST_ACK; + + if (txb->ack.reason == RXRPC_ACK_DELAY) + clear_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags); + if (txb->ack.reason == RXRPC_ACK_IDLE) + clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); - spin_unlock_bh(&call->lock); - if (n == 0) { - kfree(pkt); + n = rxrpc_fill_out_ack(conn, call, txb); + if (n == 0) return 0; - } - iov[0].iov_base = pkt; - iov[0].iov_len = sizeof(pkt->whdr) + sizeof(pkt->ack) + n; - iov[1].iov_base = &pkt->ackinfo; - iov[1].iov_len = sizeof(pkt->ackinfo); - len = iov[0].iov_len + iov[1].iov_len; + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; + len = iov[0].iov_len; serial = atomic_inc_return(&conn->serial); - pkt->whdr.serial = htonl(serial); + txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, - ntohl(pkt->ack.firstPacket), - ntohl(pkt->ack.serial), - pkt->ack.reason, pkt->ack.nAcks); - if (_serial) - *_serial = serial; + ntohl(txb->ack.firstPacket), + ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); + if (txb->ack_why == rxrpc_propose_ack_ping_for_lost_ack) + call->acks_lost_ping = serial; - if (ping) + if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); - ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); + rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); + + /* Grab the highest received seq as late as possible */ + txb->ack.previousPacket = htonl(call->rx_highest_seq); + + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); + call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); else - trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_ack); rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { - if (ret < 0) { + if (ret < 0) rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - rxrpc_propose_ACK(call, pkt->ack.reason, - ntohl(pkt->ack.serial), - false, true, - rxrpc_propose_ack_retry_tx); - } - rxrpc_set_keepalive(call); } -out: - kfree(pkt); return ret; } /* + * ACK transmitter for a local endpoint. The UDP socket locks around each + * transmission, so we can only transmit one packet at a time, ACK, DATA or + * otherwise. + */ +void rxrpc_transmit_ack_packets(struct rxrpc_local *local) +{ + LIST_HEAD(queue); + int ret; + + trace_rxrpc_local(local->debug_id, rxrpc_local_tx_ack, + refcount_read(&local->ref), NULL); + + if (list_empty(&local->ack_tx_queue)) + return; + + spin_lock_bh(&local->ack_tx_lock); + list_splice_tail_init(&local->ack_tx_queue, &queue); + spin_unlock_bh(&local->ack_tx_lock); + + while (!list_empty(&queue)) { + struct rxrpc_txbuf *txb = + list_entry(queue.next, struct rxrpc_txbuf, tx_link); + + ret = rxrpc_send_ack_packet(local, txb); + if (ret < 0 && ret != -ECONNRESET) { + spin_lock_bh(&local->ack_tx_lock); + list_splice_init(&queue, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + break; + } + + list_del_init(&txb->tx_link); + rxrpc_put_call(txb->call, rxrpc_call_put); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + } +} + +/* * Send an ABORT call packet. */ int rxrpc_send_abort_packet(struct rxrpc_call *call) @@ -299,7 +335,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) * channel instead, thereby closing off this call. */ if (rxrpc_is_client_call(call) && - test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) return 0; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -331,8 +367,8 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) serial = atomic_inc_return(&conn->serial); pkt.whdr.serial = htonl(serial); - ret = kernel_sendmsg(conn->params.local->socket, - &msg, iov, 1, sizeof(pkt)); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt)); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, sizeof(pkt)); conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, @@ -347,19 +383,17 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) /* * send a packet through the transport endpoint */ -int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, - bool retrans) +int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { + enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct rxrpc_wire_header whdr; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; size_t len; int ret, rtt_slot = -1; - _enter(",{%d}", skb->len); + _enter("%x,{%d}", txb->seq, txb->len); if (hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); @@ -369,28 +403,16 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* Each transmission of a Tx packet needs a new serial number */ serial = atomic_inc_return(&conn->serial); - - whdr.epoch = htonl(conn->proto.epoch); - whdr.cid = htonl(call->cid); - whdr.callNumber = htonl(call->call_id); - whdr.seq = htonl(sp->hdr.seq); - whdr.serial = htonl(serial); - whdr.type = RXRPC_PACKET_TYPE_DATA; - whdr.flags = sp->hdr.flags; - whdr.userStatus = 0; - whdr.securityIndex = call->security_ix; - whdr._rsvd = htons(sp->hdr._rsvd); - whdr.serviceId = htons(call->service_id); + txb->wire.serial = htonl(serial); if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && - sp->hdr.seq == 1) - whdr.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; + txb->seq == 1) + txb->wire.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = skb->head; - iov[1].iov_len = skb->len; - len = iov[0].iov_len + iov[1].iov_len; + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + txb->len; + len = iov[0].iov_len; + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; @@ -405,41 +427,56 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) || - rxrpc_to_server(sp) - ) && - (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) || - retrans || - call->cong_mode == RXRPC_CALL_SLOW_START || - (call->peer->rtt_count < 3 && sp->hdr.seq & 1) || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), - ktime_get_real()))) - whdr.flags |= RXRPC_REQUEST_ACK; + if (txb->wire.flags & RXRPC_REQUEST_ACK) + why = rxrpc_reqack_already_on; + else if (test_bit(RXRPC_TXBUF_LAST, &txb->flags) && rxrpc_sending_to_client(txb)) + why = rxrpc_reqack_no_srv_last; + else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) + why = rxrpc_reqack_ack_lost; + else if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) + why = rxrpc_reqack_retrans; + else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) + why = rxrpc_reqack_slow_start; + else if (call->tx_winsize <= 2) + why = rxrpc_reqack_small_txwin; + else if (call->peer->rtt_count < 3 && txb->seq & 1) + why = rxrpc_reqack_more_rtt; + else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), ktime_get_real())) + why = rxrpc_reqack_old_rtt; + else + goto dont_set_request_ack; + + rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); + trace_rxrpc_req_ack(call->debug_id, txb->seq, why); + if (why != rxrpc_reqack_no_srv_last) + txb->wire.flags |= RXRPC_REQUEST_ACK; +dont_set_request_ack: if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { ret = 0; - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, - whdr.flags, retrans, true); + trace_rxrpc_tx_data(call, txb->seq, serial, + txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), + true); goto done; } } - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, retrans, - false); + trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (iov[1].iov_len >= call->peer->maxdata) + if (txb->len >= call->peer->maxdata) goto send_fragmentable; down_read(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP @@ -448,7 +485,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * - in which case, we'll have processed the ICMP error * message and update the peer record */ - ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + rxrpc_inc_stat(call->rxnet, stat_tx_data_send); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); @@ -457,7 +495,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_nofrag); } @@ -467,8 +505,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, done: if (ret >= 0) { - if (whdr.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = skb->tstamp; + call->tx_last_sent = txb->last_sent; + if (txb->wire.flags & RXRPC_REQUEST_ACK) { + call->peer->rtt_last_req = txb->last_sent; if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -480,7 +519,7 @@ done: } } - if (sp->hdr.seq == 1 && + if (txb->seq == 1 && !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { unsigned long nowj = jiffies, expect_rx_by; @@ -512,23 +551,21 @@ send_fragmentable: down_write(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: case AF_INET: ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DONT); - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); + IP_PMTUDISC_DONT); + rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); conn->params.peer->last_tx_at = ktime_get_seconds(); ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DO); + IP_PMTUDISC_DO); break; default: @@ -540,7 +577,7 @@ send_fragmentable: trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_frag); } rxrpc_tx_backoff(call, ret); @@ -610,8 +647,8 @@ void rxrpc_reject_packets(struct rxrpc_local *local) whdr.flags ^= RXRPC_CLIENT_INITIATED; whdr.flags &= RXRPC_CLIENT_INITIATED; - ret = kernel_sendmsg(local->socket, &msg, - iov, ioc, size); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); + ret = do_udp_sendmsg(local->socket, &msg, size); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, rxrpc_tx_point_reject); @@ -666,7 +703,8 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) _proto("Tx VERSION (keepalive)"); - ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + ret = do_udp_sendmsg(peer->local->socket, &msg, len); if (ret < 0) trace_rxrpc_tx_fail(peer->debug_id, 0, ret, rxrpc_tx_point_version_keepalive); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 32561e9567fe..cda3890657a9 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -16,258 +16,13 @@ #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> -#include <net/icmp.h> #include "ar-internal.h" -static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int); static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); static void rxrpc_distribute_error(struct rxrpc_peer *, int, enum rxrpc_call_completion); /* - * Find the peer associated with an ICMPv4 packet. - */ -static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, - struct sk_buff *skb, - unsigned int udp_offset, - unsigned int *info, - struct sockaddr_rxrpc *srx) -{ - struct iphdr *ip, *ip0 = ip_hdr(skb); - struct icmphdr *icmp = icmp_hdr(skb); - struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset); - - _enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code); - - switch (icmp->type) { - case ICMP_DEST_UNREACH: - *info = ntohs(icmp->un.frag.mtu); - fallthrough; - case ICMP_TIME_EXCEEDED: - case ICMP_PARAMETERPROB: - ip = (struct iphdr *)((void *)icmp + 8); - break; - default: - return NULL; - } - - memset(srx, 0, sizeof(*srx)); - srx->transport_type = local->srx.transport_type; - srx->transport_len = local->srx.transport_len; - srx->transport.family = local->srx.transport.family; - - /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice - * versa? - */ - switch (srx->transport.family) { - case AF_INET: - srx->transport_len = sizeof(srx->transport.sin); - srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin.sin_addr, &ip->daddr, - sizeof(struct in_addr)); - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - srx->transport_len = sizeof(srx->transport.sin); - srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin.sin_addr, &ip->daddr, - sizeof(struct in_addr)); - break; -#endif - - default: - WARN_ON_ONCE(1); - return NULL; - } - - _net("ICMP {%pISp}", &srx->transport); - return rxrpc_lookup_peer_rcu(local, srx); -} - -#ifdef CONFIG_AF_RXRPC_IPV6 -/* - * Find the peer associated with an ICMPv6 packet. - */ -static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local, - struct sk_buff *skb, - unsigned int udp_offset, - unsigned int *info, - struct sockaddr_rxrpc *srx) -{ - struct icmp6hdr *icmp = icmp6_hdr(skb); - struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb); - struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset); - - _enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code); - - switch (icmp->icmp6_type) { - case ICMPV6_DEST_UNREACH: - *info = ntohl(icmp->icmp6_mtu); - fallthrough; - case ICMPV6_PKT_TOOBIG: - case ICMPV6_TIME_EXCEED: - case ICMPV6_PARAMPROB: - ip = (struct ipv6hdr *)((void *)icmp + 8); - break; - default: - return NULL; - } - - memset(srx, 0, sizeof(*srx)); - srx->transport_type = local->srx.transport_type; - srx->transport_len = local->srx.transport_len; - srx->transport.family = local->srx.transport.family; - - /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice - * versa? - */ - switch (srx->transport.family) { - case AF_INET: - _net("Rx ICMP6 on v4 sock"); - srx->transport_len = sizeof(srx->transport.sin); - srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin.sin_addr, - &ip->daddr.s6_addr32[3], sizeof(struct in_addr)); - break; - case AF_INET6: - _net("Rx ICMP6"); - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr, - sizeof(struct in6_addr)); - break; - default: - WARN_ON_ONCE(1); - return NULL; - } - - _net("ICMP {%pISp}", &srx->transport); - return rxrpc_lookup_peer_rcu(local, srx); -} -#endif /* CONFIG_AF_RXRPC_IPV6 */ - -/* - * Handle an error received on the local endpoint as a tunnel. - */ -void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, - unsigned int udp_offset) -{ - struct sock_extended_err ee; - struct sockaddr_rxrpc srx; - struct rxrpc_local *local; - struct rxrpc_peer *peer; - unsigned int info = 0; - int err; - u8 version = ip_hdr(skb)->version; - u8 type = icmp_hdr(skb)->type; - u8 code = icmp_hdr(skb)->code; - - rcu_read_lock(); - local = rcu_dereference_sk_user_data(sk); - if (unlikely(!local)) { - rcu_read_unlock(); - return; - } - - rxrpc_new_skb(skb, rxrpc_skb_received); - - switch (ip_hdr(skb)->version) { - case IPVERSION: - peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset, - &info, &srx); - break; -#ifdef CONFIG_AF_RXRPC_IPV6 - case 6: - peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset, - &info, &srx); - break; -#endif - default: - rcu_read_unlock(); - return; - } - - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (!peer) { - rcu_read_unlock(); - return; - } - - memset(&ee, 0, sizeof(ee)); - - switch (version) { - case IPVERSION: - switch (type) { - case ICMP_DEST_UNREACH: - switch (code) { - case ICMP_FRAG_NEEDED: - rxrpc_adjust_mtu(peer, info); - rcu_read_unlock(); - rxrpc_put_peer(peer); - return; - default: - break; - } - - err = EHOSTUNREACH; - if (code <= NR_ICMP_UNREACH) { - /* Might want to do something different with - * non-fatal errors - */ - //harderr = icmp_err_convert[code].fatal; - err = icmp_err_convert[code].errno; - } - break; - - case ICMP_TIME_EXCEEDED: - err = EHOSTUNREACH; - break; - default: - err = EPROTO; - break; - } - - ee.ee_origin = SO_EE_ORIGIN_ICMP; - ee.ee_type = type; - ee.ee_code = code; - ee.ee_errno = err; - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case 6: - switch (type) { - case ICMPV6_PKT_TOOBIG: - rxrpc_adjust_mtu(peer, info); - rcu_read_unlock(); - rxrpc_put_peer(peer); - return; - } - - icmpv6_err_convert(type, code, &err); - - if (err == EACCES) - err = EHOSTUNREACH; - - ee.ee_origin = SO_EE_ORIGIN_ICMP6; - ee.ee_type = type; - ee.ee_code = code; - ee.ee_errno = err; - break; -#endif - } - - trace_rxrpc_rx_icmp(peer, &ee, &srx); - - rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR); - rcu_read_unlock(); - rxrpc_put_peer(peer); -} - -/* * Find the peer associated with a local error. */ static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local, @@ -283,6 +38,9 @@ static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local, srx->transport_len = local->srx.transport_len; srx->transport.family = local->srx.transport.family; + /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice + * versa? + */ switch (srx->transport.family) { case AF_INET: srx->transport_len = sizeof(srx->transport.sin); @@ -412,20 +170,38 @@ void rxrpc_error_report(struct sock *sk) } rxrpc_new_skb(skb, rxrpc_skb_received); serr = SKB_EXT_ERR(skb); + if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { + _leave("UDP empty message"); + rcu_read_unlock(); + rxrpc_free_skb(skb, rxrpc_skb_freed); + return; + } - if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) { - peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx); - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (peer) { - trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); - rxrpc_store_error(peer, serr); - } + peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx); + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) { + rcu_read_unlock(); + rxrpc_free_skb(skb, rxrpc_skb_freed); + _leave(" [no peer]"); + return; } + trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); + + if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && + serr->ee.ee_type == ICMP_DEST_UNREACH && + serr->ee.ee_code == ICMP_FRAG_NEEDED)) { + rxrpc_adjust_mtu(peer, serr->ee.ee_info); + goto out; + } + + rxrpc_store_error(peer, serr); +out: rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_freed); rxrpc_put_peer(peer); + _leave(""); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 26d2ae9baaf2..041a51225c5f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -227,12 +227,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) rxrpc_peer_init_rtt(peer); - if (RXRPC_TX_SMSS > 2190) - peer->cong_cwnd = 2; - else if (RXRPC_TX_SMSS > 1095) - peer->cong_cwnd = 3; - else - peer->cong_cwnd = 4; + peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; trace_rxrpc_peer(peer->debug_id, rxrpc_peer_new, 1, here); } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 245418943e01..fae22a8b38d6 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -54,8 +54,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; - rxrpc_seq_t tx_hard_ack, rx_hard_ack; + rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; + u64 wtmp; if (v == &rxnet->calls) { seq_puts(seq, @@ -90,8 +91,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) timeout -= jiffies; } - tx_hard_ack = READ_ONCE(call->tx_hard_ack); - rx_hard_ack = READ_ONCE(call->rx_hard_ack); + acks_hard_ack = READ_ONCE(call->acks_hard_ack); + wtmp = atomic64_read_acquire(&call->ackr_window); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", @@ -105,8 +106,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) rxrpc_call_states[call->state], call->abort_code, call->debug_id, - tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, - rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack, + acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, + lower_32_bits(wtmp), upper_32_bits(wtmp) - lower_32_bits(wtmp), call->rx_serial, timeout); @@ -216,7 +217,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "Proto Local " " Remote " - " Use CW MTU LastUse RTT RTO\n" + " Use SST MTU LastUse RTT RTO\n" ); return 0; } @@ -234,7 +235,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) lbuff, rbuff, refcount_read(&peer->ref), - peer->cong_cwnd, + peer->cong_ssthresh, peer->mtu, now - peer->last_tx_at, peer->srtt_us >> 3, @@ -397,3 +398,98 @@ const struct seq_operations rxrpc_local_seq_ops = { .stop = rxrpc_local_seq_stop, .show = rxrpc_local_seq_show, }; + +/* + * Display stats in /proc/net/rxrpc/stats + */ +int rxrpc_stats_show(struct seq_file *seq, void *v) +{ + struct rxrpc_net *rxnet = rxrpc_net(seq_file_single_net(seq)); + + seq_printf(seq, + "Data : send=%u sendf=%u\n", + atomic_read(&rxnet->stat_tx_data_send), + atomic_read(&rxnet->stat_tx_data_send_frag)); + seq_printf(seq, + "Data-Tx : nr=%u retrans=%u\n", + atomic_read(&rxnet->stat_tx_data), + atomic_read(&rxnet->stat_tx_data_retrans)); + seq_printf(seq, + "Data-Rx : nr=%u reqack=%u jumbo=%u\n", + atomic_read(&rxnet->stat_rx_data), + atomic_read(&rxnet->stat_rx_data_reqack), + atomic_read(&rxnet->stat_rx_data_jumbo)); + seq_printf(seq, + "Ack : fill=%u send=%u skip=%u\n", + atomic_read(&rxnet->stat_tx_ack_fill), + atomic_read(&rxnet->stat_tx_ack_send), + atomic_read(&rxnet->stat_tx_ack_skip)); + seq_printf(seq, + "Ack-Tx : req=%u dup=%u oos=%u exw=%u nos=%u png=%u prs=%u dly=%u idl=%u\n", + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_REQUESTED]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_DUPLICATE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_OUT_OF_SEQUENCE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_EXCEEDS_WINDOW]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_NOSPACE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_PING]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_PING_RESPONSE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_DELAY]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_IDLE])); + seq_printf(seq, + "Ack-Rx : req=%u dup=%u oos=%u exw=%u nos=%u png=%u prs=%u dly=%u idl=%u\n", + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_REQUESTED]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DUPLICATE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_OUT_OF_SEQUENCE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_EXCEEDS_WINDOW]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_NOSPACE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING_RESPONSE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DELAY]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE])); + seq_printf(seq, + "Why-Req-A: acklost=%u already=%u mrtt=%u ortt=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_ack_lost]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_already_on]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_more_rtt]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt])); + seq_printf(seq, + "Why-Req-A: nolast=%u retx=%u slows=%u smtxw=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_no_srv_last]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_retrans]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); + seq_printf(seq, + "Buffers : txb=%u rxb=%u\n", + atomic_read(&rxrpc_nr_txbuf), + atomic_read(&rxrpc_n_rx_skbs)); + return 0; +} + +/* + * Clear stats if /proc/net/rxrpc/stats is written to. + */ +int rxrpc_stats_clear(struct file *file, char *buf, size_t size) +{ + struct seq_file *m = file->private_data; + struct rxrpc_net *rxnet = rxrpc_net(seq_file_single_net(m)); + + if (size > 1 || (size == 1 && buf[0] != '\n')) + return -EINVAL; + + atomic_set(&rxnet->stat_tx_data, 0); + atomic_set(&rxnet->stat_tx_data_retrans, 0); + atomic_set(&rxnet->stat_tx_data_send, 0); + atomic_set(&rxnet->stat_tx_data_send_frag, 0); + atomic_set(&rxnet->stat_rx_data, 0); + atomic_set(&rxnet->stat_rx_data_reqack, 0); + atomic_set(&rxnet->stat_rx_data_jumbo, 0); + + atomic_set(&rxnet->stat_tx_ack_fill, 0); + atomic_set(&rxnet->stat_tx_ack_send, 0); + atomic_set(&rxnet->stat_tx_ack_skip, 0); + memset(&rxnet->stat_tx_acks, 0, sizeof(rxnet->stat_tx_acks)); + memset(&rxnet->stat_rx_acks, 0, sizeof(rxnet->stat_rx_acks)); + + memset(&rxnet->stat_why_req_ack, 0, sizeof(rxnet->stat_why_req_ack)); + return size; +} diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index d2cf8e1d218f..6760cb99c6d6 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -84,7 +84,7 @@ struct rxrpc_jumbo_header { __be16 _rsvd; /* reserved */ __be16 cksum; /* kerberos security checksum */ }; -}; +} __packed; #define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ #define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) @@ -132,13 +132,6 @@ struct rxrpc_ackpacket { } __packed; -/* Some ACKs refer to specific packets and some are general and can be updated. */ -#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \ - (1 << RXRPC_ACK_PING_RESPONSE) | \ - (1 << RXRPC_ACK_DELAY) | \ - (1 << RXRPC_ACK_IDLE)) - - /* * ACK packets can have a further piece of information tagged on the end */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7e39c262fd79..efb85f983657 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -173,8 +173,9 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) break; } - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, - call->rx_pkt_offset, call->rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, + lower_32_bits(atomic64_read(&call->ackr_window)) - 1, + call->rx_pkt_offset, call->rx_pkt_len, ret); return ret; } @@ -183,16 +184,14 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) */ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) { + rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); + _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); - trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); - ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); + trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); - if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true, - rxrpc_propose_ack_terminal_ack); - //rxrpc_send_ack_packet(call, false, NULL); - } + if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); write_lock_bh(&call->state_lock); @@ -203,12 +202,11 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) break; case RXRPC_CALL_SERVER_RECV_REQUEST: - call->tx_phase = true; call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, - rxrpc_propose_ack_processing_op); + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_processing_op); break; default: write_unlock_bh(&call->state_lock); @@ -224,126 +222,66 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) struct rxrpc_skb_priv *sp; struct sk_buff *skb; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; - bool last = false; - u8 subpacket; - int ix; + rxrpc_seq_t old_consumed = call->rx_consumed, tseq; + bool last; + int acked; _enter("%d", call->debug_id); - hard_ack = call->rx_hard_ack; - top = smp_load_acquire(&call->rx_top); - ASSERT(before(hard_ack, top)); - - hard_ack++; - ix = hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; +further_rotation: + skb = skb_dequeue(&call->recvmsg_queue); rxrpc_see_skb(skb, rxrpc_skb_rotated); - sp = rxrpc_skb(skb); - - subpacket = call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; - serial = sp->hdr.serial + subpacket; - if (subpacket == sp->nr_subpackets - 1 && - sp->rx_flags & RXRPC_SKB_INCL_LAST) - last = true; + sp = rxrpc_skb(skb); + tseq = sp->hdr.seq; + serial = sp->hdr.serial; + last = sp->hdr.flags & RXRPC_LAST_PACKET; - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; /* Barrier against rxrpc_input_data(). */ - smp_store_release(&call->rx_hard_ack, hard_ack); + if (after(tseq, call->rx_consumed)) + smp_store_release(&call->rx_consumed, tseq); rxrpc_free_skb(skb, rxrpc_skb_freed); - trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack); + trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, + serial, call->rx_consumed); if (last) { rxrpc_end_rx_phase(call, serial); - } else { - /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2) - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, - true, false, - rxrpc_propose_ack_rotate_rx); - if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY) - rxrpc_send_ack_packet(call, false, NULL); + return; } -} - -/* - * Decrypt and verify a (sub)packet. The packet's length may be changed due to - * padding, but if this is the case, the packet length will be resident in the - * socket buffer. Note that we can't modify the master skb info as the skb may - * be the home to multiple subpackets. - */ -static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - u8 annotation, - unsigned int offset, unsigned int len) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_seq_t seq = sp->hdr.seq; - u16 cksum = sp->hdr.cksum; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - _enter(""); - - /* For all but the head jumbo subpacket, the security checksum is in a - * jumbo header immediately prior to the data. + /* The next packet on the queue might entirely overlap with the one we + * just consumed; if so, rotate that away also. */ - if (subpacket > 0) { - __be16 tmp; - if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0) - BUG(); - cksum = ntohs(tmp); - seq += subpacket; + skb = skb_peek(&call->recvmsg_queue); + if (skb) { + sp = rxrpc_skb(skb); + if (sp->hdr.seq != call->rx_consumed && + after_eq(call->rx_consumed, sp->hdr.seq)) + goto further_rotation; } - return call->security->verify_packet(call, skb, offset, len, - seq, cksum); + /* Check to see if there's an ACK that needs sending. */ + acked = atomic_add_return(call->rx_consumed - old_consumed, + &call->ackr_nr_consumed); + if (acked > 2 && + !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_rotate_rx); + rxrpc_transmit_ack_packets(call->peer->local); + } } /* - * Locate the data within a packet. This is complicated by: - * - * (1) An skb may contain a jumbo packet - so we have to find the appropriate - * subpacket. - * - * (2) The (sub)packets may be encrypted and, if so, the encrypted portion - * contains an extra header which includes the true length of the data, - * excluding any encrypted padding. + * Decrypt and verify a DATA packet. */ -static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - u8 *_annotation, - unsigned int *_offset, unsigned int *_len, - bool *_last) +static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len; - bool last = false; - int ret; - u8 annotation = *_annotation; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - - /* Locate the subpacket */ - offset += subpacket * RXRPC_JUMBO_SUBPKTLEN; - len = skb->len - offset; - if (subpacket < sp->nr_subpackets - 1) - len = RXRPC_JUMBO_DATALEN; - else if (sp->rx_flags & RXRPC_SKB_INCL_LAST) - last = true; - - if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { - ret = rxrpc_verify_packet(call, skb, annotation, offset, len); - if (ret < 0) - return ret; - *_annotation |= RXRPC_RX_ANNO_VERIFIED; - } - *_offset = offset; - *_len = len; - *_last = last; - call->security->locate_data(call, skb, _offset, _len); - return 0; + if (sp->flags & RXRPC_RX_VERIFIED) + return 0; + return call->security->verify_packet(call, skb); } /* @@ -357,69 +295,55 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, { struct rxrpc_skb_priv *sp; struct sk_buff *skb; - rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top, seq; + rxrpc_seq_t seq = 0; size_t remain; - bool rx_pkt_last; unsigned int rx_pkt_offset, rx_pkt_len; - int ix, copy, ret = -EAGAIN, ret2; - - if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) && - call->ackr_reason) - rxrpc_send_ack_packet(call, false, NULL); + int copy, ret = -EAGAIN, ret2; rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; - rx_pkt_last = call->rx_pkt_last; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { - seq = call->rx_hard_ack; + seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; ret = 1; goto done; } - /* Barriers against rxrpc_input_data(). */ - hard_ack = call->rx_hard_ack; - seq = hard_ack + 1; - - while (top = smp_load_acquire(&call->rx_top), - before_eq(seq, top) - ) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - if (!skb) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq, - rx_pkt_offset, rx_pkt_len, 0); - break; - } - smp_rmb(); + /* No one else can be removing stuff from the queue, so we shouldn't + * need the Rx lock to walk it. + */ + skb = skb_peek(&call->recvmsg_queue); + while (skb) { rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); + seq = sp->hdr.seq; - if (!(flags & MSG_PEEK)) { - serial = sp->hdr.serial; - serial += call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; - trace_rxrpc_receive(call, rxrpc_receive_front, - serial, seq); + if (after_eq(call->rx_consumed, seq)) { + kdebug("obsolete %x %x", call->rx_consumed, seq); + goto skip_obsolete; } + if (!(flags & MSG_PEEK)) + trace_rxrpc_receive(call, rxrpc_receive_front, + sp->hdr.serial, seq); + if (msg) sock_recv_timestamp(msg, sock->sk, skb); if (rx_pkt_offset == 0) { - ret2 = rxrpc_locate_data(call, skb, - &call->rxtx_annotations[ix], - &rx_pkt_offset, &rx_pkt_len, - &rx_pkt_last); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq, - rx_pkt_offset, rx_pkt_len, ret2); + ret2 = rxrpc_verify_data(call, skb); + rx_pkt_offset = sp->offset; + rx_pkt_len = sp->len; + trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, + rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { ret = ret2; goto out; } + rxrpc_transmit_ack_packets(call->peer->local); } else { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_cont, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, + rx_pkt_offset, rx_pkt_len, 0); } /* We have to handle short, empty and used-up DATA packets. */ @@ -442,37 +366,34 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } if (rx_pkt_len > 0) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_full, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_full, seq, + rx_pkt_offset, rx_pkt_len, 0); ASSERTCMP(*_offset, ==, len); ret = 0; break; } + skip_obsolete: /* The whole packet has been transferred. */ - if (!(flags & MSG_PEEK)) - rxrpc_rotate_rx_window(call); + if (sp->hdr.flags & RXRPC_LAST_PACKET) + ret = 1; rx_pkt_offset = 0; rx_pkt_len = 0; - if (rx_pkt_last) { - ASSERTCMP(seq, ==, READ_ONCE(call->rx_top)); - ret = 1; - goto out; - } + skb = skb_peek_next(skb, &call->recvmsg_queue); - seq++; + if (!(flags & MSG_PEEK)) + rxrpc_rotate_rx_window(call); } out: if (!(flags & MSG_PEEK)) { call->rx_pkt_offset = rx_pkt_offset; call->rx_pkt_len = rx_pkt_len; - call->rx_pkt_last = rx_pkt_last; } done: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, - rx_pkt_offset, rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, + rx_pkt_offset, rx_pkt_len, ret); if (ret == -EAGAIN) set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags); return ret; @@ -495,7 +416,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, DEFINE_WAIT(wait); - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0); if (flags & (MSG_OOB | MSG_TRUNC)) return -EOPNOTSUPP; @@ -532,8 +453,7 @@ try_again: if (list_empty(&rx->recvmsg_q)) { if (signal_pending(current)) goto wait_interrupted; - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, - 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0); timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(&rx->sk), &wait); @@ -552,7 +472,7 @@ try_again: rxrpc_get_call(call, rxrpc_call_got); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0); /* We're going to drop the socket lock, so we need to lock the call * against interference by sendmsg. @@ -605,8 +525,8 @@ try_again: if (ret == -EAGAIN) ret = 0; - if (after(call->rx_top, call->rx_hard_ack) && - call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK]) + rxrpc_transmit_ack_packets(call->peer->local); + if (!skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); break; default: @@ -636,7 +556,7 @@ try_again: error_unlock_call: mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; error_requeue_call: @@ -644,14 +564,14 @@ error_requeue_call: write_lock_bh(&rx->recvmsg_lock); list_add(&call->recvmsg_link, &rx->recvmsg_q); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0); } else { rxrpc_put_call(call, rxrpc_call_put); } error_no_call: release_sock(&rx->sk); error_trace: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; wait_interrupted: @@ -735,17 +655,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: - switch (call->ackr_reason) { - case RXRPC_ACK_IDLE: - break; - case RXRPC_ACK_DELAY: - if (ret != -EAGAIN) - break; - fallthrough; - default: - rxrpc_send_ack_packet(call, false, NULL); - } - + rxrpc_transmit_ack_packets(call->peer->local); if (_service) *_service = call->service_id; mutex_unlock(&call->user_mutex); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 78fa0524156f..110a5550c0a6 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -233,16 +233,8 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn, static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call) { struct crypto_skcipher *tfm = &call->conn->rxkad.cipher->base; - struct skcipher_request *cipher_req = call->cipher_req; - if (!cipher_req) { - cipher_req = skcipher_request_alloc(tfm, GFP_NOFS); - if (!cipher_req) - return NULL; - call->cipher_req = cipher_req; - } - - return cipher_req; + return skcipher_request_alloc(tfm, GFP_NOFS); } /* @@ -250,20 +242,16 @@ static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call) */ static void rxkad_free_call_crypto(struct rxrpc_call *call) { - if (call->cipher_req) - skcipher_request_free(call->cipher_req); - call->cipher_req = NULL; } /* * partially encrypt a packet (level 1 security) */ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, - struct sk_buff *skb, u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxkad_level1_hdr hdr; + struct rxkad_level1_hdr *hdr = (void *)txb->data; struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -271,22 +259,22 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = sp->hdr.seq ^ call->call_id; - data_size |= (u32)check << 16; + check = txb->seq ^ ntohl(txb->wire.callNumber); + hdr->data_size = htonl((u32)check << 16 | txb->len); - hdr.data_size = htonl(data_size); - memcpy(skb->head, &hdr, sizeof(hdr)); - - pad = sizeof(struct rxkad_level1_hdr) + data_size; + txb->len += sizeof(struct rxkad_level1_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg, skb->head, 8); + sg_init_one(&sg, txb->data, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); @@ -301,87 +289,63 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, * wholly encrypt a packet (level 2 security) */ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, - struct sk_buff *skb, - u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr rxkhdr; - struct rxrpc_skb_priv *sp; + struct rxkad_level2_hdr *rxkhdr = (void *)txb->data; struct rxrpc_crypt iv; - struct scatterlist sg[16]; - unsigned int len; + struct scatterlist sg; size_t pad; u16 check; - int err; - - sp = rxrpc_skb(skb); + int ret; _enter(""); - check = sp->hdr.seq ^ call->call_id; + check = txb->seq ^ ntohl(txb->wire.callNumber); - rxkhdr.data_size = htonl(data_size | (u32)check << 16); - rxkhdr.checksum = 0; - memcpy(skb->head, &rxkhdr, sizeof(rxkhdr)); + rxkhdr->data_size = htonl(txb->len | (u32)check << 16); + rxkhdr->checksum = 0; - pad = sizeof(struct rxkad_level2_hdr) + data_size; + txb->len += sizeof(struct rxkad_level2_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* encrypt from the session key */ token = call->conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg[0], skb->head, sizeof(rxkhdr)); + sg_init_one(&sg, txb->data, txb->len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[0], &sg[0], sizeof(rxkhdr), iv.x); - crypto_skcipher_encrypt(req); - - /* we want to encrypt the skbuff in-place */ - err = -EMSGSIZE; - if (skb_shinfo(skb)->nr_frags > 16) - goto out; - - len = round_up(data_size, RXKAD_ALIGN); - - sg_init_table(sg, ARRAY_SIZE(sg)); - err = skb_to_sgvec(skb, sg, 8, len); - if (unlikely(err < 0)) - goto out; - skcipher_request_set_crypt(req, sg, sg, len, iv.x); - crypto_skcipher_encrypt(req); - - _leave(" = 0"); - err = 0; - -out: + skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); + ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); - return err; + return ret; } /* * checksum an RxRPC packet header */ -static int rxkad_secure_packet(struct rxrpc_call *call, - struct sk_buff *skb, - size_t data_size) +static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { - struct rxrpc_skb_priv *sp; struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; + union { + __be32 buf[2]; + } crypto __aligned(8); u32 x, y; int ret; - sp = rxrpc_skb(skb); - - _enter("{%d{%x}},{#%u},%zu,", + _enter("{%d{%x}},{#%u},%u,", call->debug_id, key_serial(call->conn->params.key), - sp->hdr.seq, data_size); + txb->seq, txb->len); if (!call->conn->rxkad.cipher) return 0; @@ -398,39 +362,40 @@ static int rxkad_secure_packet(struct rxrpc_call *call, memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); - x |= sp->hdr.seq & 0x3fffffff; - call->crypto_buf[0] = htonl(call->call_id); - call->crypto_buf[1] = htonl(x); + x = (ntohl(txb->wire.cid) & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); + x |= txb->seq & 0x3fffffff; + crypto.buf[0] = txb->wire.callNumber; + crypto.buf[1] = htonl(x); - sg_init_one(&sg, call->crypto_buf, 8); + sg_init_one(&sg, crypto.buf, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - y = ntohl(call->crypto_buf[1]); + y = ntohl(crypto.buf[1]); y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ - sp->hdr.cksum = y; + txb->wire.cksum = htons(y); switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: ret = 0; break; case RXRPC_SECURITY_AUTH: - ret = rxkad_secure_packet_auth(call, skb, data_size, req); + ret = rxkad_secure_packet_auth(call, txb, req); break; case RXRPC_SECURITY_ENCRYPT: - ret = rxkad_secure_packet_encrypt(call, skb, data_size, req); + ret = rxkad_secure_packet_encrypt(call, txb, req); break; default: ret = -EPERM; break; } + skcipher_request_free(req); _leave(" = %d [set %x]", ret, y); return ret; } @@ -439,11 +404,11 @@ static int rxkad_secure_packet(struct rxrpc_call *call, * decrypt partial encryption on a packet (level 1 security) */ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { struct rxkad_level1_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist sg[16]; bool aborted; @@ -453,9 +418,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, _enter(""); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H", - RXKADSEALEDINCON); + RXKADSEALEDINCON); goto protocol_error; } @@ -463,7 +428,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, * directly into the target buffer. */ sg_init_table(sg, ARRAY_SIZE(sg)); - ret = skb_to_sgvec(skb, sg, offset, 8); + ret = skb_to_sgvec(skb, sg, sp->offset, 8); if (unlikely(ret < 0)) return ret; @@ -477,12 +442,13 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_zero(req); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -496,11 +462,12 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -515,12 +482,12 @@ protocol_error: * wholly decrypt a packet (level 2 security) */ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { const struct rxrpc_key_token *token; struct rxkad_level2_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; bool aborted; @@ -528,9 +495,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, u16 check; int nsg, ret; - _enter(",{%d}", skb->len); + _enter(",{%d}", sp->len); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H", RXKADSEALEDINCON); goto protocol_error; @@ -550,7 +517,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } sg_init_table(sg, nsg); - ret = skb_to_sgvec(skb, sg, offset, len); + ret = skb_to_sgvec(skb, sg, sp->offset, sp->len); if (unlikely(ret < 0)) { if (sg != _sg) kfree(sg); @@ -563,19 +530,20 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, sg, sg, len, iv.x); + skcipher_request_set_crypt(req, sg, sg, sp->len, iv.x); crypto_skcipher_decrypt(req); skcipher_request_zero(req); if (sg != _sg) kfree(sg); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -589,12 +557,13 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -609,17 +578,20 @@ nomem: } /* - * Verify the security on a received packet or subpacket (if part of a - * jumbo packet). + * Verify the security on a received packet and the subpackets therein. */ -static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; + union { + __be32 buf[2]; + } crypto __aligned(8); + rxrpc_seq_t seq = sp->hdr.seq; bool aborted; + int ret; u16 cksum; u32 x, y; @@ -639,22 +611,22 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, /* validate the security checksum */ x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= seq & 0x3fffffff; - call->crypto_buf[0] = htonl(call->call_id); - call->crypto_buf[1] = htonl(x); + crypto.buf[0] = htonl(call->call_id); + crypto.buf[1] = htonl(x); - sg_init_one(&sg, call->crypto_buf, 8); + sg_init_one(&sg, crypto.buf, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - y = ntohl(call->crypto_buf[1]); + y = ntohl(crypto.buf[1]); cksum = (y >> 16) & 0xffff; if (cksum == 0) cksum = 1; /* zero checksums are not permitted */ - if (cksum != expected_cksum) { + if (cksum != sp->hdr.cksum) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK", RXKADSEALEDINCON); goto protocol_error; @@ -662,15 +634,22 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: - return 0; + ret = 0; + break; case RXRPC_SECURITY_AUTH: - return rxkad_verify_packet_1(call, skb, offset, len, seq, req); + ret = rxkad_verify_packet_1(call, skb, seq, req); + break; case RXRPC_SECURITY_ENCRYPT: - return rxkad_verify_packet_2(call, skb, offset, len, seq, req); + ret = rxkad_verify_packet_2(call, skb, seq, req); + break; default: - return -ENOANO; + ret = -ENOANO; + break; } + skcipher_request_free(req); + return ret; + protocol_error: if (aborted) rxrpc_send_abort_packet(call); @@ -678,52 +657,6 @@ protocol_error: } /* - * Locate the data contained in a packet that was partially encrypted. - */ -static void rxkad_locate_data_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level1_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in a packet that was completely encrypted. - */ -static void rxkad_locate_data_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level2_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in an already decrypted packet. - */ -static void rxkad_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - switch (call->conn->params.security_level) { - case RXRPC_SECURITY_AUTH: - rxkad_locate_data_1(call, skb, _offset, _len); - return; - case RXRPC_SECURITY_ENCRYPT: - rxkad_locate_data_2(call, skb, _offset, _len); - return; - default: - return; - } -} - -/* * issue a challenge */ static int rxkad_issue_challenge(struct rxrpc_connection *conn) @@ -1232,9 +1165,10 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, eproto = tracepoint_string("rxkad_tkt_short"); abort_code = RXKADPACKETSHORT; - if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), - ticket, ticket_len) < 0) - goto protocol_error_free; + ret = skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), + ticket, ticket_len); + if (ret < 0) + goto temporary_error_free_ticket; ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len, &session_key, &expiry, _abort_code); @@ -1397,7 +1331,6 @@ const struct rxrpc_security rxkad = { .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, - .locate_data = rxkad_locate_data, .issue_challenge = rxkad_issue_challenge, .respond_to_challenge = rxkad_respond_to_challenge, .verify_response = rxkad_verify_response, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 3c3a626459de..e5fd8a95bf71 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -22,10 +22,26 @@ */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { - unsigned int win_size = - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra); - rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack); + unsigned int win_size; + rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); + + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if (ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real())) { + if (RXRPC_TX_SMSS > 2190) + win_size = 2; + else if (RXRPC_TX_SMSS > 1095) + win_size = 3; + else + win_size = 4; + win_size += call->cong_extra; + } else { + win_size = min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + } if (_tx_win) *_tx_win = tx_win; @@ -50,7 +66,12 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (signal_pending(current)) return sock_intr_errno(*timeo); - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -71,12 +92,11 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, rtt = 2; timeout = rtt; - tx_start = READ_ONCE(call->tx_hard_ack); + tx_start = smp_load_acquire(&call->acks_hard_ack); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - tx_win = READ_ONCE(call->tx_hard_ack); if (rxrpc_check_tx_space(call, &tx_win)) return 0; @@ -87,12 +107,17 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, tx_win == tx_start && signal_pending(current)) return -EINTR; + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + if (tx_win != tx_start) { timeout = rtt; tx_start = tx_win; } - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); timeout = schedule_timeout(timeout); } } @@ -112,7 +137,12 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -129,8 +159,8 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, DECLARE_WAITQUEUE(myself, current); int ret; - _enter(",{%u,%u,%u}", - call->tx_hard_ack, call->tx_top, call->tx_winsize); + _enter(",{%u,%u,%u,%u}", + call->tx_bottom, call->acks_hard_ack, call->tx_top, call->tx_winsize); add_wait_queue(&call->waitq, &myself); @@ -155,24 +185,6 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, } /* - * Schedule an instant Tx resend. - */ -static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix) -{ - spin_lock_bh(&call->lock); - - if (call->state < RXRPC_CALL_COMPLETE) { - call->rxtx_annotations[ix] = - (call->rxtx_annotations[ix] & RXRPC_TX_ANNO_LAST) | - RXRPC_TX_ANNO_RETRANS; - if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); - } - - spin_unlock_bh(&call->lock); -} - -/* * Notify the owner of the call that the transmit phase is ended and the last * packet has been queued. */ @@ -188,38 +200,35 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call, * the packet immediately. Returns the error from rxrpc_send_data_packet() * in case the caller wants to do something with it. */ -static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, - struct sk_buff *skb, bool last, - rxrpc_notify_end_tx_t notify_end_tx) +static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, + struct rxrpc_txbuf *txb, + rxrpc_notify_end_tx_t notify_end_tx) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long now; - rxrpc_seq_t seq = sp->hdr.seq; - int ret, ix; - u8 annotation = RXRPC_TX_ANNO_UNACK; + rxrpc_seq_t seq = txb->seq; + bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); + int ret; - _net("queue skb %p [%d]", skb, seq); + rxrpc_inc_stat(call->rxnet, stat_tx_data); ASSERTCMP(seq, ==, call->tx_top + 1); - if (last) - annotation |= RXRPC_TX_ANNO_LAST; - /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. */ - skb->tstamp = ktime_get_real(); + txb->last_sent = ktime_get_real(); - ix = seq & RXRPC_RXTX_BUFF_MASK; - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; + /* Add the packet to the call's output buffer */ + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_buffer); + spin_lock(&call->tx_lock); + list_add_tail(&txb->call_link, &call->tx_buffer); call->tx_top = seq; + spin_unlock(&call->tx_lock); + if (last) - trace_rxrpc_transmit(call, rxrpc_transmit_queue_last); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else - trace_rxrpc_transmit(call, rxrpc_transmit_queue); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { _debug("________awaiting reply/ACK__________"); @@ -232,7 +241,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, case RXRPC_CALL_SERVER_ACK_REQUEST: call->state = RXRPC_CALL_SERVER_SEND_REPLY; now = jiffies; - WRITE_ONCE(call->ack_at, now + MAX_JIFFY_OFFSET); + WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); if (call->ackr_reason == RXRPC_ACK_DELAY) call->ackr_reason = 0; trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); @@ -252,7 +261,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, if (seq == 1 && rxrpc_is_client_call(call)) rxrpc_expose_client_call(call); - ret = rxrpc_send_data_packet(call, skb, false); + ret = rxrpc_send_data_packet(call, txb); if (ret < 0) { switch (ret) { case -ENETUNREACH: @@ -262,8 +271,6 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, 0, ret); goto out; } - _debug("need instant resend %d", ret); - rxrpc_instant_resend(call, ix); } else { unsigned long now = jiffies; unsigned long resend_at = now + call->peer->rto_j; @@ -274,9 +281,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, } out: - rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" = %d", ret); - return ret; + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); } /* @@ -290,8 +295,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, rxrpc_notify_end_tx_t notify_end_tx, bool *_dropped_lock) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + struct rxrpc_txbuf *txb; struct sock *sk = &rx->sk; enum rxrpc_call_state state; long timeo; @@ -325,16 +329,15 @@ reload: goto maybe_error; } - skb = call->tx_pending; + txb = call->tx_pending; call->tx_pending = NULL; - rxrpc_see_skb(skb, rxrpc_skb_seen); + if (txb) + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more); do { - /* Check to see if there's a ping ACK to reply to. */ - if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) - rxrpc_send_ack_packet(call, false, NULL); + rxrpc_transmit_ack_packets(call->peer->local); - if (!skb) { + if (!txb) { size_t remain, bufsize, chunk, offset; _debug("alloc"); @@ -355,53 +358,31 @@ reload: _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); /* create a buffer that we can retain until it's ACK'd */ - skb = sock_alloc_send_skb( - sk, bufsize, msg->msg_flags & MSG_DONTWAIT, &ret); - if (!skb) + ret = -ENOMEM; + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, + GFP_KERNEL); + if (!txb) goto maybe_error; - sp = rxrpc_skb(skb); - sp->rx_flags |= RXRPC_SKB_TX_BUFFER; - rxrpc_new_skb(skb, rxrpc_skb_new); - - _debug("ALLOC SEND %p", skb); - - ASSERTCMP(skb->mark, ==, 0); - - __skb_put(skb, offset); - - sp->remain = chunk; - if (sp->remain > skb_tailroom(skb)) - sp->remain = skb_tailroom(skb); - - _net("skb: hr %d, tr %d, hl %d, rm %d", - skb_headroom(skb), - skb_tailroom(skb), - skb_headlen(skb), - sp->remain); - - skb->ip_summed = CHECKSUM_UNNECESSARY; + txb->offset = offset; + txb->space -= offset; + txb->space = min_t(size_t, chunk, txb->space); } _debug("append"); - sp = rxrpc_skb(skb); /* append next segment of data to the current buffer */ if (msg_data_left(msg) > 0) { - int copy = skb_tailroom(skb); - ASSERTCMP(copy, >, 0); - if (copy > msg_data_left(msg)) - copy = msg_data_left(msg); - if (copy > sp->remain) - copy = sp->remain; - - _debug("add"); - ret = skb_add_data(skb, &msg->msg_iter, copy); - _debug("added"); - if (ret < 0) + size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); + + _debug("add %zu", copy); + if (!copy_from_iter_full(txb->data + txb->offset, copy, + &msg->msg_iter)) goto efault; - sp->remain -= copy; - skb->mark += copy; + _debug("added"); + txb->space -= copy; + txb->len += copy; + txb->offset += copy; copied += copy; if (call->tx_total_len != -1) call->tx_total_len -= copy; @@ -413,32 +394,22 @@ reload: goto call_terminated; /* add the packet to the send queue if it's now full */ - if (sp->remain <= 0 || + if (!txb->space || (msg_data_left(msg) == 0 && !more)) { - struct rxrpc_connection *conn = call->conn; - uint32_t seq; - - seq = call->tx_top + 1; - - sp->hdr.seq = seq; - sp->hdr._rsvd = 0; - sp->hdr.flags = conn->out_clientflag; - - if (msg_data_left(msg) == 0 && !more) - sp->hdr.flags |= RXRPC_LAST_PACKET; - else if (call->tx_top - call->tx_hard_ack < + if (msg_data_left(msg) == 0 && !more) { + txb->wire.flags |= RXRPC_LAST_PACKET; + __set_bit(RXRPC_TXBUF_LAST, &txb->flags); + } + else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) - sp->hdr.flags |= RXRPC_MORE_PACKETS; + txb->wire.flags |= RXRPC_MORE_PACKETS; - ret = call->security->secure_packet(call, skb, skb->mark); + ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; - ret = rxrpc_queue_packet(rx, call, skb, - !msg_data_left(msg) && !more, - notify_end_tx); - /* Should check for failure here */ - skb = NULL; + rxrpc_queue_packet(rx, call, txb, notify_end_tx); + txb = NULL; } } while (msg_data_left(msg) > 0); @@ -451,12 +422,12 @@ success: read_unlock_bh(&call->state_lock); } out: - call->tx_pending = skb; + call->tx_pending = txb; _leave(" = %d", ret); return ret; call_terminated: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_send_aborted); _leave(" = %d", call->error); return call->error; @@ -645,7 +616,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, */ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) - __releases(&call->user_mutex) { enum rxrpc_call_state state; struct rxrpc_call *call; diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 580a5acffee7..0c827d5bb2b8 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -14,8 +14,7 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -#define is_tx_skb(skb) (rxrpc_skb(skb)->rx_flags & RXRPC_SKB_TX_BUFFER) -#define select_skb_count(skb) (is_tx_skb(skb) ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) +#define select_skb_count(skb) (&rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. @@ -24,8 +23,7 @@ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } /* @@ -36,8 +34,7 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) const void *here = __builtin_return_address(0); if (skb) { int n = atomic_read(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } } @@ -48,8 +45,7 @@ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); skb_get(skb); } @@ -60,7 +56,7 @@ void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(&rxrpc_n_rx_skbs); - trace_rxrpc_skb(skb, op, 0, n, 0, here); + trace_rxrpc_skb(skb, op, 0, n, here); } /* @@ -72,8 +68,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) if (skb) { int n; n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); kfree_skb(skb); } } @@ -88,8 +83,7 @@ void rxrpc_purge_queue(struct sk_buff_head *list) while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, rxrpc_skb_purged, - refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + refcount_read(&skb->users), n, here); kfree_skb(skb); } } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 555e0910786b..cde3224a5cd2 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *rxrpc_sysctl_reg_table; static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; -static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1; +static const unsigned int n_max_acks = 255; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; @@ -27,15 +27,6 @@ static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; static struct ctl_table rxrpc_sysctl_table[] = { /* Values measured in milliseconds but used in jiffies */ { - .procname = "req_ack_delay", - .data = &rxrpc_requested_ack_delay, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, - }, - { .procname = "soft_ack_delay", .data = &rxrpc_soft_ack_delay, .maxlen = sizeof(unsigned long), diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c new file mode 100644 index 000000000000..96bfee89927b --- /dev/null +++ b/net/rxrpc/txbuf.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* RxRPC Tx data buffering. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> +#include "ar-internal.h" + +static atomic_t rxrpc_txbuf_debug_ids; +atomic_t rxrpc_nr_txbuf; + +/* + * Allocate and partially initialise an I/O request structure. + */ +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp) +{ + struct rxrpc_txbuf *txb; + + txb = kmalloc(sizeof(*txb), gfp); + if (txb) { + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->call = call; + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = sizeof(txb->data); + txb->len = 0; + txb->offset = 0; + txb->flags = 0; + txb->ack_why = 0; + txb->seq = call->tx_top + 1; + txb->wire.epoch = htonl(call->conn->proto.epoch); + txb->wire.cid = htonl(call->cid); + txb->wire.callNumber = htonl(call->call_id); + txb->wire.seq = htonl(txb->seq); + txb->wire.type = packet_type; + txb->wire.flags = call->conn->out_clientflag; + txb->wire.userStatus = 0; + txb->wire.securityIndex = call->security_ix; + txb->wire._rsvd = 0; + txb->wire.serviceId = htons(call->service_id); + + trace_rxrpc_txbuf(txb->debug_id, + txb->call_debug_id, txb->seq, 1, + packet_type == RXRPC_PACKET_TYPE_DATA ? + rxrpc_txbuf_alloc_data : + rxrpc_txbuf_alloc_ack); + atomic_inc(&rxrpc_nr_txbuf); + } + + return txb; +} + +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r; + + __refcount_inc(&txb->ref, &r); + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r + 1, what); +} + +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r = refcount_read(&txb->ref); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r, what); +} + +static void rxrpc_free_txbuf(struct rcu_head *rcu) +{ + struct rxrpc_txbuf *txb = container_of(rcu, struct rxrpc_txbuf, rcu); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, + rxrpc_txbuf_free); + kfree(txb); + atomic_dec(&rxrpc_nr_txbuf); +} + +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + unsigned int debug_id, call_debug_id; + rxrpc_seq_t seq; + bool dead; + int r; + + if (txb) { + debug_id = txb->debug_id; + call_debug_id = txb->call_debug_id; + seq = txb->seq; + dead = __refcount_dec_and_test(&txb->ref, &r); + trace_rxrpc_txbuf(debug_id, call_debug_id, seq, r - 1, what); + if (dead) + call_rcu(&txb->rcu, rxrpc_free_txbuf); + } +} + +/* + * Shrink the transmit buffer. + */ +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) +{ + struct rxrpc_txbuf *txb; + rxrpc_seq_t hard_ack = smp_load_acquire(&call->acks_hard_ack); + + _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); + + for (;;) { + spin_lock(&call->tx_lock); + txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link); + if (!txb) + break; + hard_ack = smp_load_acquire(&call->acks_hard_ack); + if (before(hard_ack, txb->seq)) + break; + + ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); + call->tx_bottom++; + list_del_rcu(&txb->call_link); + + trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); + + spin_unlock(&call->tx_lock); + + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); + } + + spin_unlock(&call->tx_lock); +} diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 1e8ab4749c6c..4662a6ce8a7e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -976,7 +976,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE + depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 66b143bb04ac..d41002e4613f 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -61,7 +61,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_get(skb, &ctinfo); if (c) { - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; goto out; @@ -81,7 +81,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_tuplehash_to_ctrack(thash); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); nf_ct_put(c); out: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b38d91d6b249..dd5ae7551956 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -33,6 +33,7 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_conntrack_act_ct.h> +#include <net/netfilter/nf_conntrack_seqadj.h> #include <uapi/linux/netfilter/nf_nat.h> static struct workqueue_struct *act_ct_wq; @@ -178,7 +179,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - entry->ct_metadata.mark = ct->mark; + entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : IP_CT_ESTABLISHED_REPLY; @@ -345,11 +346,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) module_put(THIS_MODULE); } -static void tcf_ct_flow_table_put(struct tcf_ct_params *params) +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) { - struct tcf_ct_flow_table *ct_ft = params->ct_ft; - - if (refcount_dec_and_test(¶ms->ct_ft->ref)) { + if (refcount_dec_and_test(&ct_ft->ref)) { rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); queue_rcu_work(act_ct_wq, &ct_ft->rwork); @@ -657,7 +656,7 @@ struct tc_ct_action_net { /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, - u16 zone_id, bool force) + struct tcf_ct_params *p) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -667,11 +666,19 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, return false; if (!net_eq(net, read_pnet(&ct->ct_net))) goto drop_ct; - if (nf_ct_zone(ct)->id != zone_id) + if (nf_ct_zone(ct)->id != p->zone) goto drop_ct; + if (p->helper) { + struct nf_conn_help *help; + + help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + if (help && rcu_access_pointer(help->helper) != p->helper) + goto drop_ct; + } /* Force conntrack entry direction. */ - if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { + if ((p->ct_action & TCA_CT_ACT_FORCE) && + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { if (nf_ct_is_confirmed(ct)) nf_ct_kill(ct); @@ -832,18 +839,30 @@ out_free: return err; } -static void tcf_ct_params_free(struct rcu_head *head) +static void tcf_ct_params_free(struct tcf_ct_params *params) { - struct tcf_ct_params *params = container_of(head, - struct tcf_ct_params, rcu); - - tcf_ct_flow_table_put(params); - + if (params->helper) { +#if IS_ENABLED(CONFIG_NF_NAT) + if (params->ct_action & TCA_CT_ACT_NAT) + nf_nat_helper_put(params->helper); +#endif + nf_conntrack_helper_put(params->helper); + } + if (params->ct_ft) + tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) nf_ct_put(params->tmpl); kfree(params); } +static void tcf_ct_params_free_rcu(struct rcu_head *head) +{ + struct tcf_ct_params *params; + + params = container_of(head, struct tcf_ct_params, rcu); + tcf_ct_params_free(params); +} + #if IS_ENABLED(CONFIG_NF_NAT) /* Modelled after nf_nat_ipv[46]_fn(). * range is only used for new, uninitialized NAT state. @@ -936,9 +955,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) if (!mask) return; - new_mark = mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } @@ -1023,13 +1042,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct net *net = dev_net(skb->dev); - bool cached, commit, clear, force; enum ip_conntrack_info ctinfo; struct tcf_ct *c = to_ct(a); struct nf_conn *tmpl = NULL; struct nf_hook_state state; + bool cached, commit, clear; int nh_ofs, err, retval; struct tcf_ct_params *p; + bool add_helper = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; @@ -1040,7 +1060,6 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, retval = READ_ONCE(c->tcf_action); commit = p->ct_action & TCA_CT_ACT_COMMIT; clear = p->ct_action & TCA_CT_ACT_CLEAR; - force = p->ct_action & TCA_CT_ACT_FORCE; tmpl = p->tmpl; tcf_lastuse_update(&c->tcf_tm); @@ -1083,7 +1102,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, * actually run the packet through conntrack twice unless it's for a * different zone. */ - cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force); + cached = tcf_ct_skb_nfct_cached(net, skb, p); if (!cached) { if (tcf_ct_flow_table_lookup(p, skb, family)) { skip_add = true; @@ -1116,6 +1135,22 @@ do_nat: if (err != NF_ACCEPT) goto drop; + if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { + err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); + if (err) + goto drop; + add_helper = true; + if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) { + if (!nfct_seqadj_ext_add(ct)) + goto drop; + } + } + + if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { + if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT) + goto drop; + } + if (commit) { tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); @@ -1164,6 +1199,9 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, + [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN }, + [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 }, + [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 }, }; static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, @@ -1253,8 +1291,9 @@ static int tcf_ct_fill_params(struct net *net, { struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); struct nf_conntrack_zone zone; + int err, family, proto, len; struct nf_conn *tmpl; - int err; + char *name; p->zone = NF_CT_DEFAULT_ZONE_ID; @@ -1315,10 +1354,31 @@ static int tcf_ct_fill_params(struct net *net, NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template"); return -ENOMEM; } - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); p->tmpl = tmpl; + if (tb[TCA_CT_HELPER_NAME]) { + name = nla_data(tb[TCA_CT_HELPER_NAME]); + len = nla_len(tb[TCA_CT_HELPER_NAME]); + if (len > 16 || name[len - 1] != '\0') { + NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name."); + err = -EINVAL; + goto err; + } + family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET; + proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP; + err = nf_ct_add_helper(tmpl, name, family, proto, + p->ct_action & TCA_CT_ACT_NAT, &p->helper); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to add helper"); + goto err; + } + } + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; +err: + nf_ct_put(p->tmpl); + p->tmpl = NULL; + return err; } static int tcf_ct_init(struct net *net, struct nlattr *nla, @@ -1390,7 +1450,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, err = tcf_ct_flow_table_get(net, params); if (err) - goto cleanup_params; + goto cleanup; spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -1401,17 +1461,15 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); return res; -cleanup_params: - if (params->tmpl) - nf_ct_put(params->tmpl); cleanup: if (goto_ch) tcf_chain_put_by_act(goto_ch); - kfree(params); + if (params) + tcf_ct_params_free(params); tcf_idr_release(*a, bind); return err; } @@ -1423,7 +1481,7 @@ static void tcf_ct_cleanup(struct tc_action *a) params = rcu_dereference_protected(c->params, 1); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); } static int tcf_ct_dump_key_val(struct sk_buff *skb, @@ -1489,6 +1547,19 @@ static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p) return 0; } +static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper) +{ + if (!helper) + return 0; + + if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) || + nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) || + nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum)) + return -1; + + return 0; +} + static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -1541,6 +1612,9 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, if (tcf_ct_dump_nat(skb, p)) goto nla_put_failure; + if (tcf_ct_dump_helper(skb, p->helper)) + goto nla_put_failure; + skip_dump: if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index d4102f0a9abd..eaa02f098d1c 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -32,7 +32,7 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, { u8 dscp, newdscp; - newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK; switch (proto) { @@ -72,7 +72,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct sk_buff *skb) { ca->stats_cpmark_set++; - skb->mark = ct->mark & cp->cpmarkmask; + skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, @@ -130,7 +130,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, } if (cp->mode & CTINFO_MODE_DSCP) - if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask)) + if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); if (cp->mode & CTINFO_MODE_CPMARK) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index abe1bcc5c797..62d682b96b88 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -25,7 +25,7 @@ static struct tc_action_ops act_gact_ops; static int gact_net_rand(struct tcf_gact *gact) { smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ - if (prandom_u32() % gact->tcfg_pval) + if (prandom_u32_max(gact->tcfg_pval)) return gact->tcf_action; return gact->tcfg_paction; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 5ba36f70e3a1..7a25477f5d99 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -168,7 +168,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, psample_group = rcu_dereference_bh(s->psample_group); /* randomly sample packets according to rate */ - if (psample_group && (prandom_u32() % s->rate == 0)) { + if (psample_group && (prandom_u32_max(s->rate) == 0)) { if (!skb_at_tc_ingress(skb)) { md.in_ifindex = skb->skb_iif; md.out_ifindex = skb->dev->ifindex; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 7f598784fd30..1710780c908a 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -148,6 +148,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) { + if (is_tcf_skbedit_ingress(act_flags) && + !(act_flags & TCA_ACT_FLAGS_SKIP_SW)) { + NL_SET_ERR_MSG_MOD(extack, "\"queue_mapping\" option on receive side is hardware only, use skip_sw"); + return -EOPNOTSUPP; + } flags |= SKBEDIT_F_QUEUE_MAPPING; queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]); } @@ -374,9 +379,12 @@ static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data } else if (is_tcf_skbedit_priority(act)) { entry->id = FLOW_ACTION_PRIORITY; entry->priority = tcf_skbedit_priority(act); - } else if (is_tcf_skbedit_queue_mapping(act)) { - NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used"); + } else if (is_tcf_skbedit_tx_queue_mapping(act)) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used on transmit side"); return -EOPNOTSUPP; + } else if (is_tcf_skbedit_rx_queue_mapping(act)) { + entry->id = FLOW_ACTION_RX_QUEUE_MAPPING; + entry->rx_queue = tcf_skbedit_rx_queue_mapping(act); } else if (is_tcf_skbedit_inheritdsfield(act)) { NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used"); return -EOPNOTSUPP; @@ -394,6 +402,8 @@ static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data fl_action->id = FLOW_ACTION_PTYPE; else if (is_tcf_skbedit_priority(act)) fl_action->id = FLOW_ACTION_PRIORITY; + else if (is_tcf_skbedit_rx_queue_mapping(act)) + fl_action->id = FLOW_ACTION_RX_QUEUE_MAPPING; else return -EOPNOTSUPP; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 50566db45949..23d1cfa4f58c 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1953,6 +1953,11 @@ static void tfilter_put(struct tcf_proto *tp, void *fh) tp->ops->put(tp, fh); } +static bool is_qdisc_ingress(__u32 classid) +{ + return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); +} + static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -2144,6 +2149,8 @@ replay: flags |= TCA_ACT_FLAGS_REPLACE; if (!rtnl_held) flags |= TCA_ACT_FLAGS_NO_RTNL; + if (is_qdisc_ingress(parent)) + flags |= TCA_ACT_FLAGS_AT_INGRESS; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, flags, extack); if (err == 0) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c98af0ada706..4a27dfb1ba0f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1099,12 +1099,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - rtnl_dereference(dev->qdisc), new); + old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + notify_and_destroy(net, skb, n, classid, old, new); + if (new && new->ops->attach) new->ops->attach(new); } else { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 55c6879d2c7e..3ed0c3342189 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -573,7 +573,7 @@ static bool cobalt_should_drop(struct cobalt_vars *vars, /* Simple BLUE implementation. Lack of ECN is deliberate. */ if (vars->p_drop) - drop |= (prandom_u32() < vars->p_drop); + drop |= (get_random_u32() < vars->p_drop); /* Overload the drop_next field as an activity timeout */ if (!vars->count) @@ -2092,11 +2092,11 @@ retry: WARN_ON(host_load > CAKE_QUEUES); - /* The shifted prandom_u32() is a way to apply dithering to - * avoid accumulating roundoff errors + /* The get_random_u16() is a way to apply dithering to avoid + * accumulating roundoff errors */ flow->deficit += (b->flow_quantum * quantum_div[host_load] + - (prandom_u32() >> 16)) >> 16; + get_random_u16()) >> 16; list_move_tail(&flow->flowchain, &b->old_flows); goto retry; @@ -2224,8 +2224,12 @@ retry: static void cake_reset(struct Qdisc *sch) { + struct cake_sched_data *q = qdisc_priv(sch); u32 c; + if (!q->tins) + return; + for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 99d318b60568..8c4fee063436 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -478,24 +478,26 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, if (opt) { err = fq_codel_change(sch, opt, extack); if (err) - return err; + goto init_failure; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) - return err; + goto init_failure; if (!q->flows) { q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_codel_flow), GFP_KERNEL); - if (!q->flows) - return -ENOMEM; - + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL); - if (!q->backlogs) - return -ENOMEM; - + if (!q->backlogs) { + err = -ENOMEM; + goto alloc_failure; + } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; @@ -508,6 +510,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; + +alloc_failure: + kvfree(q->flows); + q->flows = NULL; +init_failure: + q->flows_cnt = 0; + return err; } static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 18f4273a835b..fb00ac40ecb7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -171,7 +171,7 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; - state->last = prandom_u32(); + state->last = get_random_u32(); } /* get_crandom - correlated random number generator @@ -184,9 +184,9 @@ static u32 get_crandom(struct crndstate *state) unsigned long answer; if (!state || state->rho == 0) /* no correlation */ - return prandom_u32(); + return get_random_u32(); - value = prandom_u32(); + value = get_random_u32(); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; @@ -200,7 +200,7 @@ static u32 get_crandom(struct crndstate *state) static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; - u32 rnd = prandom_u32(); + u32 rnd = get_random_u32(); /* * Makes a comparison between rnd and the transition @@ -268,15 +268,15 @@ static bool loss_gilb_ell(struct netem_sched_data *q) switch (clg->state) { case GOOD_STATE: - if (prandom_u32() < clg->a1) + if (get_random_u32() < clg->a1) clg->state = BAD_STATE; - if (prandom_u32() < clg->a4) + if (get_random_u32() < clg->a4) return true; break; case BAD_STATE: - if (prandom_u32() < clg->a2) + if (get_random_u32() < clg->a2) clg->state = GOOD_STATE; - if (prandom_u32() > clg->a3) + if (get_random_u32() > clg->a3) return true; } @@ -513,8 +513,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto finish_segs; } - skb->data[prandom_u32() % skb_headlen(skb)] ^= - 1<<(prandom_u32() % 8); + skb->data[prandom_u32_max(skb_headlen(skb))] ^= + 1<<prandom_u32_max(8); } if (unlikely(sch->q.qlen >= sch->limit)) { @@ -632,7 +632,7 @@ static void get_slot_next(struct netem_sched_data *q, u64 now) if (!q->slot_dist) next_delay = q->slot_config.min_delay + - (prandom_u32() * + (get_random_u32() * (q->slot_config.max_delay - q->slot_config.min_delay) >> 32); else diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 974038ba6c7b..265c238047a4 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -72,7 +72,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, if (vars->accu_prob >= (MAX_PROB / 2) * 17) return true; - prandom_bytes(&rnd, 8); + get_random_bytes(&rnd, 8); if ((rnd >> BITS_PER_BYTE) < local_prob) { vars->accu_prob = 0; return true; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index a5a401f93c1a..98129324e157 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -72,6 +72,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; + unsigned int len; int ret; q->vars.qavg = red_calc_qavg(&q->parms, @@ -126,9 +127,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; } + len = qdisc_pkt_len(skb); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index e2389fa3cff8..1871a1c0224d 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -379,7 +379,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto enqueue; } - r = prandom_u32() & SFB_MAX_PROB; + r = get_random_u16() & SFB_MAX_PROB; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { @@ -455,7 +455,8 @@ static void sfb_reset(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - qdisc_reset(q->qdisc); + if (likely(q->qdisc)) + qdisc_reset(q->qdisc); q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 3460abceba44..63ba5551c13f 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -226,8 +226,7 @@ static struct sctp_association *sctp_association_init( /* Create an output queue. */ sctp_outq_init(asoc, &asoc->outqueue); - if (!sctp_ulpq_init(&asoc->ulpq, asoc)) - goto fail_init; + sctp_ulpq_init(&asoc->ulpq, asoc); if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp)) goto stream_free; @@ -277,7 +276,6 @@ static struct sctp_association *sctp_association_init( stream_free: sctp_stream_free(&asoc->stream); -fail_init: sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); return NULL; diff --git a/net/sctp/diag.c b/net/sctp/diag.c index d9c6d8f30f09..a557009e9832 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -426,6 +426,7 @@ static int sctp_diag_dump_one(struct netlink_callback *cb, struct net *net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; union sctp_addr laddr, paddr; + int dif = req->id.idiag_if; struct sctp_comm_param commp = { .skb = skb, .r = req, @@ -454,7 +455,7 @@ static int sctp_diag_dump_one(struct netlink_callback *cb, } return sctp_transport_lookup_process(sctp_sock_dump_one, - net, &laddr, &paddr, &commp); + net, &laddr, &paddr, &commp, dif); } static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index efffde7f2328..7e77b450697c 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -246,12 +246,15 @@ void sctp_endpoint_put(struct sctp_endpoint *ep) /* Is this the endpoint we are looking for? */ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, struct net *net, - const union sctp_addr *laddr) + const union sctp_addr *laddr, + int dif, int sdif) { + int bound_dev_if = READ_ONCE(ep->base.sk->sk_bound_dev_if); struct sctp_endpoint *retval = NULL; - if ((htons(ep->base.bind_addr.port) == laddr->v4.sin_port) && - net_eq(ep->base.net, net)) { + if (net_eq(ep->base.net, net) && + sctp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif) && + (htons(ep->base.bind_addr.port) == laddr->v4.sin_port)) { if (sctp_bind_addr_match(&ep->base.bind_addr, laddr, sctp_sk(ep->base.sk))) retval = ep; @@ -298,6 +301,7 @@ out: bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, const union sctp_addr *paddr) { + int bound_dev_if = READ_ONCE(ep->base.sk->sk_bound_dev_if); struct sctp_sockaddr_entry *addr; struct net *net = ep->base.net; struct sctp_bind_addr *bp; @@ -307,7 +311,8 @@ bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, * so the address_list can not change. */ list_for_each_entry(addr, &bp->address_list, list) { - if (sctp_has_association(net, &addr->a, paddr)) + if (sctp_has_association(net, &addr->a, paddr, + bound_dev_if, bound_dev_if)) return true; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 4f43afa8678f..bf70371301ff 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -50,16 +50,19 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, - struct sctp_transport **transportp); + struct sctp_transport **transportp, + int dif, int sdif); static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - const union sctp_addr *daddr); + const union sctp_addr *daddr, + int dif, int sdif); static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, - struct sctp_transport **pt); + struct sctp_transport **pt, + int dif, int sdif); static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb); @@ -92,11 +95,11 @@ int sctp_rcv(struct sk_buff *skb) struct sctp_chunk *chunk; union sctp_addr src; union sctp_addr dest; - int bound_dev_if; int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); + int dif, sdif; if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -141,6 +144,8 @@ int sctp_rcv(struct sk_buff *skb) /* Initialize local addresses for lookups. */ af->from_skb(&src, skb, 1); af->from_skb(&dest, skb, 0); + dif = af->skb_iif(skb); + sdif = af->skb_sdif(skb); /* If the packet is to or from a non-unicast address, * silently discard the packet. @@ -157,36 +162,16 @@ int sctp_rcv(struct sk_buff *skb) !af->addr_valid(&dest, NULL, skb)) goto discard_it; - asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport); + asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport, dif, sdif); if (!asoc) - ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src); + ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src, dif, sdif); /* Retrieve the common input handling substructure. */ rcvr = asoc ? &asoc->base : &ep->base; sk = rcvr->sk; /* - * If a frame arrives on an interface and the receiving socket is - * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB - */ - bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); - if (bound_dev_if && (bound_dev_if != af->skb_iif(skb))) { - if (transport) { - sctp_transport_put(transport); - asoc = NULL; - transport = NULL; - } else { - sctp_endpoint_put(ep); - ep = NULL; - } - sk = net->sctp.ctl_sock; - ep = sctp_sk(sk)->ep; - sctp_endpoint_hold(ep); - rcvr = &ep->base; - } - - /* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * An SCTP packet is called an "out of the blue" (OOTB) * packet if it is correctly formed, i.e., passed the @@ -485,6 +470,8 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, struct sctp_association *asoc; struct sctp_transport *transport = NULL; __u32 vtag = ntohl(sctphdr->vtag); + int sdif = inet_sdif(skb); + int dif = inet_iif(skb); *app = NULL; *tpp = NULL; @@ -500,7 +487,7 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, /* Look for an association that matches the incoming ICMP error * packet. */ - asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport); + asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport, dif, sdif); if (!asoc) return NULL; @@ -850,7 +837,8 @@ static inline __u32 sctp_hashfn(const struct net *net, __be16 lport, static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - const union sctp_addr *paddr) + const union sctp_addr *paddr, + int dif, int sdif) { struct sctp_hashbucket *head; struct sctp_endpoint *ep; @@ -863,7 +851,7 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); sctp_for_each_hentry(ep, &head->chain) { - if (sctp_endpoint_is_match(ep, net, laddr)) + if (sctp_endpoint_is_match(ep, net, laddr, dif, sdif)) goto hit; } @@ -990,14 +978,26 @@ void sctp_unhash_transport(struct sctp_transport *t) sctp_hash_params); } +bool sctp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) +{ + bool l3mdev_accept = true; + +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + l3mdev_accept = !!READ_ONCE(net->sctp.l3mdev_accept); +#endif + return inet_bound_dev_eq(l3mdev_accept, bound_dev_if, dif, sdif); +} + /* return a transport with holding it */ struct sctp_transport *sctp_addrs_lookup_transport( struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr) + const union sctp_addr *paddr, + int dif, int sdif) { struct rhlist_head *tmp, *list; struct sctp_transport *t; + int bound_dev_if; struct sctp_hash_cmp_arg arg = { .paddr = paddr, .net = net, @@ -1011,7 +1011,9 @@ struct sctp_transport *sctp_addrs_lookup_transport( if (!sctp_transport_hold(t)) continue; - if (sctp_bind_addr_match(&t->asoc->base.bind_addr, + bound_dev_if = READ_ONCE(t->asoc->base.sk->sk_bound_dev_if); + if (sctp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif) && + sctp_bind_addr_match(&t->asoc->base.bind_addr, laddr, sctp_sk(t->asoc->base.sk))) return t; sctp_transport_put(t); @@ -1048,12 +1050,13 @@ static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, - struct sctp_transport **pt) + struct sctp_transport **pt, + int dif, int sdif) { struct sctp_transport *t; struct sctp_association *asoc = NULL; - t = sctp_addrs_lookup_transport(net, local, peer); + t = sctp_addrs_lookup_transport(net, local, peer, dif, sdif); if (!t) goto out; @@ -1069,12 +1072,13 @@ static struct sctp_association *sctp_lookup_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc; rcu_read_lock(); - asoc = __sctp_lookup_association(net, laddr, paddr, transportp); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); rcu_read_unlock(); return asoc; @@ -1083,11 +1087,12 @@ struct sctp_association *sctp_lookup_association(struct net *net, /* Is there an association matching the given local and peer addresses? */ bool sctp_has_association(struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr) + const union sctp_addr *paddr, + int dif, int sdif) { struct sctp_transport *transport; - if (sctp_lookup_association(net, laddr, paddr, &transport)) { + if (sctp_lookup_association(net, laddr, paddr, &transport, dif, sdif)) { sctp_transport_put(transport); return true; } @@ -1115,7 +1120,8 @@ bool sctp_has_association(struct net *net, */ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, struct sk_buff *skb, - const union sctp_addr *laddr, struct sctp_transport **transportp) + const union sctp_addr *laddr, struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc; union sctp_addr addr; @@ -1154,7 +1160,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) continue; - asoc = __sctp_lookup_association(net, laddr, paddr, transportp); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) return asoc; } @@ -1181,7 +1187,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( struct sctp_chunkhdr *ch, const union sctp_addr *laddr, __be16 peer_port, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_addip_chunk *asconf = (struct sctp_addip_chunk *)ch; struct sctp_af *af; @@ -1201,7 +1208,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL; - return __sctp_lookup_association(net, laddr, &paddr, transportp); + return __sctp_lookup_association(net, laddr, &paddr, transportp, dif, sdif); } @@ -1217,7 +1224,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc = NULL; struct sctp_chunkhdr *ch; @@ -1260,7 +1268,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, asoc = __sctp_rcv_asconf_lookup( net, ch, laddr, sctp_hdr(skb)->source, - transportp); + transportp, dif, sdif); break; default: break; @@ -1285,7 +1293,8 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_chunkhdr *ch; @@ -1309,9 +1318,9 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, /* If this is INIT/INIT-ACK look inside the chunk too. */ if (ch->type == SCTP_CID_INIT || ch->type == SCTP_CID_INIT_ACK) - return __sctp_rcv_init_lookup(net, skb, laddr, transportp); + return __sctp_rcv_init_lookup(net, skb, laddr, transportp, dif, sdif); - return __sctp_rcv_walk_lookup(net, skb, laddr, transportp); + return __sctp_rcv_walk_lookup(net, skb, laddr, transportp, dif, sdif); } /* Lookup an association for an inbound skb. */ @@ -1319,11 +1328,12 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc; - asoc = __sctp_lookup_association(net, laddr, paddr, transportp); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) goto out; @@ -1331,7 +1341,7 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net, * SCTP Implementors Guide, 2.18 Handling of address * parameters within the INIT or INIT-ACK. */ - asoc = __sctp_rcv_lookup_harder(net, skb, laddr, transportp); + asoc = __sctp_rcv_lookup_harder(net, skb, laddr, transportp, dif, sdif); if (asoc) goto out; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index d081858c2d07..097bd60ce964 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -680,9 +680,11 @@ static int sctp_v6_is_any(const union sctp_addr *addr) /* Should this be available for binding? */ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) { - int type; - struct net *net = sock_net(&sp->inet.sk); const struct in6_addr *in6 = (const struct in6_addr *)&addr->v6.sin6_addr; + struct sock *sk = &sp->inet.sk; + struct net *net = sock_net(sk); + struct net_device *dev = NULL; + int type; type = ipv6_addr_type(in6); if (IPV6_ADDR_ANY == type) @@ -696,8 +698,14 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (!(type & IPV6_ADDR_UNICAST)) return 0; + if (sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) + return 0; + } + return ipv6_can_nonlocal_bind(net, &sp->inet) || - ipv6_chk_addr(net, in6, NULL, 0); + ipv6_chk_addr(net, in6, dev, 0); } /* This function checks if the address is a valid address to be used for @@ -834,7 +842,12 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) /* Where did this skb come from? */ static int sctp_v6_skb_iif(const struct sk_buff *skb) { - return IP6CB(skb)->iif; + return inet6_iif(skb); +} + +static int sctp_v6_skb_sdif(const struct sk_buff *skb) +{ + return inet6_sdif(skb); } /* Was this packet marked by Explicit Congestion Notification? */ @@ -1134,6 +1147,7 @@ static struct sctp_af sctp_af_inet6 = { .is_any = sctp_v6_is_any, .available = sctp_v6_available, .skb_iif = sctp_v6_skb_iif, + .skb_sdif = sctp_v6_skb_sdif, .is_ce = sctp_v6_is_ce, .seq_dump_addr = sctp_v6_seq_dump_addr, .ecn_capable = sctp_v6_ecn_capable, diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index e213aaf45d67..20831079fb09 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -384,6 +384,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, { struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; + struct sctp_stream_out *sout; q->sched->unsched_all(&asoc->stream); @@ -398,12 +399,14 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { - struct sctp_stream_out *streamout = - SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); - streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - } + sout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); + sout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + + /* clear out_curr if all frag chunks are pruned */ + if (asoc->stream.out_curr == sout && + list_is_last(&chk->frag_list, &chk->msg->chunks)) + asoc->stream.out_curr = NULL; msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); sctp_chunk_free(chk); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index bcd3384ab07a..909a89a1cff4 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -351,10 +351,13 @@ static int sctp_v4_addr_valid(union sctp_addr *addr, /* Should this be available for binding? */ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) { - struct net *net = sock_net(&sp->inet.sk); - int ret = inet_addr_type(net, addr->v4.sin_addr.s_addr); - + struct sock *sk = &sp->inet.sk; + struct net *net = sock_net(sk); + int tb_id = RT_TABLE_LOCAL; + int ret; + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ?: tb_id; + ret = inet_addr_type_table(net, addr->v4.sin_addr.s_addr, tb_id); if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && @@ -564,6 +567,11 @@ static int sctp_v4_skb_iif(const struct sk_buff *skb) return inet_iif(skb); } +static int sctp_v4_skb_sdif(const struct sk_buff *skb) +{ + return inet_sdif(skb); +} + /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v4_is_ce(const struct sk_buff *skb) { @@ -1182,6 +1190,7 @@ static struct sctp_af sctp_af_inet = { .available = sctp_v4_available, .scope = sctp_v4_scope, .skb_iif = sctp_v4_skb_iif, + .skb_sdif = sctp_v4_skb_sdif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, .ecn_capable = sctp_v4_ecn_capable, @@ -1385,6 +1394,10 @@ static int __net_init sctp_defaults_init(struct net *net) /* Initialize maximum autoclose timeout. */ net->sctp.max_autoclose = INT_MAX / HZ; +#ifdef CONFIG_NET_L3_MASTER_DEV + net->sctp.l3mdev_accept = 1; +#endif + status = sctp_sysctl_net_register(net); if (status) goto err_sysctl_register; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f6ee7f4040c1..ce5426171206 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4044,7 +4044,7 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, (void *)err_param, commands); if (last_asconf) { - addip_hdr = (struct sctp_addiphdr *)last_asconf->subh.addip_hdr; + addip_hdr = last_asconf->subh.addip_hdr; sent_serial = ntohl(addip_hdr->serial); } else { sent_serial = asoc->addip_serial - 1; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 171f1a35d205..5acbdf0d38f3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5098,13 +5098,17 @@ static void sctp_destroy_sock(struct sock *sk) } /* Triggered when there are no references on the socket anymore */ -static void sctp_destruct_sock(struct sock *sk) +static void sctp_destruct_common(struct sock *sk) { struct sctp_sock *sp = sctp_sk(sk); /* Free up the HMAC transform. */ crypto_free_shash(sp->hmac); +} +static void sctp_destruct_sock(struct sock *sk) +{ + sctp_destruct_common(sk); inet_sock_destruct(sk); } @@ -5311,14 +5315,14 @@ EXPORT_SYMBOL_GPL(sctp_for_each_endpoint); int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr, void *p) + const union sctp_addr *paddr, void *p, int dif) { struct sctp_transport *transport; struct sctp_endpoint *ep; int err = -ENOENT; rcu_read_lock(); - transport = sctp_addrs_lookup_transport(net, laddr, paddr); + transport = sctp_addrs_lookup_transport(net, laddr, paddr, dif, dif); if (!transport) { rcu_read_unlock(); return err; @@ -8319,7 +8323,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rover = prandom_u32() % remaining + low; + rover = prandom_u32_max(remaining) + low; do { rover++; @@ -8394,6 +8398,7 @@ pp_found: * in an endpoint. */ sk_for_each_bound(sk2, &pp->owner) { + int bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); struct sctp_sock *sp2 = sctp_sk(sk2); struct sctp_endpoint *ep2 = sp2->ep; @@ -8404,7 +8409,9 @@ pp_found: uid_eq(uid, sock_i_uid(sk2)))) continue; - if (sctp_bind_addr_conflict(&ep2->base.bind_addr, + if ((!sk->sk_bound_dev_if || !bound_dev_if2 || + sk->sk_bound_dev_if == bound_dev_if2) && + sctp_bind_addr_conflict(&ep2->base.bind_addr, addr, sp2, sp)) { ret = 1; goto fail_unlock; @@ -9427,7 +9434,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, sctp_sk(newsk)->reuse = sp->reuse; newsk->sk_shutdown = sk->sk_shutdown; - newsk->sk_destruct = sctp_destruct_sock; + newsk->sk_destruct = sk->sk_destruct; newsk->sk_family = sk->sk_family; newsk->sk_protocol = IPPROTO_SCTP; newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; @@ -9448,7 +9455,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = prandom_u32(); + newinet->inet_id = get_random_u16(); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; @@ -9662,11 +9669,20 @@ struct proto sctp_prot = { #if IS_ENABLED(CONFIG_IPV6) -#include <net/transp_v6.h> -static void sctp_v6_destroy_sock(struct sock *sk) +static void sctp_v6_destruct_sock(struct sock *sk) +{ + sctp_destruct_common(sk); + inet6_sock_destruct(sk); +} + +static int sctp_v6_init_sock(struct sock *sk) { - sctp_destroy_sock(sk); - inet6_destroy_sock(sk); + int ret = sctp_init_sock(sk); + + if (!ret) + sk->sk_destruct = sctp_v6_destruct_sock; + + return ret; } struct proto sctpv6_prot = { @@ -9676,8 +9692,8 @@ struct proto sctpv6_prot = { .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, - .init = sctp_init_sock, - .destroy = sctp_v6_destroy_sock, + .init = sctp_v6_init_sock, + .destroy = sctp_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, diff --git a/net/sctp/stream.c b/net/sctp/stream.c index ef9fceadef8d..ee6514af830f 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -52,6 +52,19 @@ static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) } } +static void sctp_stream_free_ext(struct sctp_stream *stream, __u16 sid) +{ + struct sctp_sched_ops *sched; + + if (!SCTP_SO(stream, sid)->ext) + return; + + sched = sctp_sched_ops_from_stream(stream); + sched->free_sid(stream, sid); + kfree(SCTP_SO(stream, sid)->ext); + SCTP_SO(stream, sid)->ext = NULL; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -70,16 +83,14 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, * sctp_stream_update will swap ->out pointers. */ for (i = 0; i < outcnt; i++) { - kfree(SCTP_SO(new, i)->ext); + sctp_stream_free_ext(new, i); SCTP_SO(new, i)->ext = SCTP_SO(stream, i)->ext; SCTP_SO(stream, i)->ext = NULL; } } - for (i = outcnt; i < stream->outcnt; i++) { - kfree(SCTP_SO(stream, i)->ext); - SCTP_SO(stream, i)->ext = NULL; - } + for (i = outcnt; i < stream->outcnt; i++) + sctp_stream_free_ext(stream, i); } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, @@ -174,9 +185,9 @@ void sctp_stream_free(struct sctp_stream *stream) struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i; - sched->free(stream); + sched->unsched_all(stream); for (i = 0; i < stream->outcnt; i++) - kfree(SCTP_SO(stream, i)->ext); + sctp_stream_free_ext(stream, i); genradix_free(&stream->out); genradix_free(&stream->in); } diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index bb22b71df7a3..94727feb07b3 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -490,11 +490,8 @@ static int sctp_enqueue_event(struct sctp_ulpq *ulpq, if (!sctp_ulpevent_is_enabled(event, ulpq->asoc->subscribe)) goto out_free; - if (skb_list) - skb_queue_splice_tail_init(skb_list, - &sk->sk_receive_queue); - else - __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_queue_splice_tail_init(skb_list, + &sk->sk_receive_queue); if (!sp->data_ready_signalled) { sp->data_ready_signalled = 1; @@ -504,10 +501,7 @@ static int sctp_enqueue_event(struct sctp_ulpq *ulpq, return 1; out_free: - if (skb_list) - sctp_queue_purge_ulpevents(skb_list); - else - sctp_ulpevent_free(event); + sctp_queue_purge_ulpevents(skb_list); return 0; } diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 1ad565ed5627..7c8f9d89e16a 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -46,6 +46,10 @@ static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid, return 0; } +static void sctp_sched_fcfs_free_sid(struct sctp_stream *stream, __u16 sid) +{ +} + static void sctp_sched_fcfs_free(struct sctp_stream *stream) { } @@ -96,6 +100,7 @@ static struct sctp_sched_ops sctp_sched_fcfs = { .get = sctp_sched_fcfs_get, .init = sctp_sched_fcfs_init, .init_sid = sctp_sched_fcfs_init_sid, + .free_sid = sctp_sched_fcfs_free_sid, .free = sctp_sched_fcfs_free, .enqueue = sctp_sched_fcfs_enqueue, .dequeue = sctp_sched_fcfs_dequeue, diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 80b5a2c4cbc7..4fc9f2923ed1 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -204,6 +204,24 @@ static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, return sctp_sched_prio_set(stream, sid, 0, gfp); } +static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid) +{ + struct sctp_stream_priorities *prio = SCTP_SO(stream, sid)->ext->prio_head; + int i; + + if (!prio) + return; + + SCTP_SO(stream, sid)->ext->prio_head = NULL; + for (i = 0; i < stream->outcnt; i++) { + if (SCTP_SO(stream, i)->ext && + SCTP_SO(stream, i)->ext->prio_head == prio) + return; + } + + kfree(prio); +} + static void sctp_sched_prio_free(struct sctp_stream *stream) { struct sctp_stream_priorities *prio, *n; @@ -323,6 +341,7 @@ static struct sctp_sched_ops sctp_sched_prio = { .get = sctp_sched_prio_get, .init = sctp_sched_prio_init, .init_sid = sctp_sched_prio_init_sid, + .free_sid = sctp_sched_prio_free_sid, .free = sctp_sched_prio_free, .enqueue = sctp_sched_prio_enqueue, .dequeue = sctp_sched_prio_dequeue, diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c index ff425aed62c7..cc444fe0d67c 100644 --- a/net/sctp/stream_sched_rr.c +++ b/net/sctp/stream_sched_rr.c @@ -90,6 +90,10 @@ static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid, return 0; } +static void sctp_sched_rr_free_sid(struct sctp_stream *stream, __u16 sid) +{ +} + static void sctp_sched_rr_free(struct sctp_stream *stream) { sctp_sched_rr_unsched_all(stream); @@ -177,6 +181,7 @@ static struct sctp_sched_ops sctp_sched_rr = { .get = sctp_sched_rr_get, .init = sctp_sched_rr_init, .init_sid = sctp_sched_rr_init_sid, + .free_sid = sctp_sched_rr_free_sid, .free = sctp_sched_rr_free, .enqueue = sctp_sched_rr_enqueue, .dequeue = sctp_sched_rr_dequeue, diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index b46a416787ec..7f40ed117fc7 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -347,6 +347,17 @@ static struct ctl_table sctp_net_table[] = { .extra1 = &max_autoclose_min, .extra2 = &max_autoclose_max, }, +#ifdef CONFIG_NET_L3_MASTER_DEV + { + .procname = "l3mdev_accept", + .data = &init_net.sctp.l3mdev_accept, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif { .procname = "pf_enable", .data = &init_net.sctp.pf_enable, diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 0a8510a0c5e6..b05daafd369a 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -38,8 +38,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq); /* 1st Level Abstractions */ /* Initialize a ULP queue from a block of memory. */ -struct sctp_ulpq *sctp_ulpq_init(struct sctp_ulpq *ulpq, - struct sctp_association *asoc) +void sctp_ulpq_init(struct sctp_ulpq *ulpq, struct sctp_association *asoc) { memset(ulpq, 0, sizeof(struct sctp_ulpq)); @@ -48,8 +47,6 @@ struct sctp_ulpq *sctp_ulpq_init(struct sctp_ulpq *ulpq, skb_queue_head_init(&ulpq->reasm_uo); skb_queue_head_init(&ulpq->lobby); ulpq->pd_mode = 0; - - return ulpq; } @@ -259,10 +256,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sk_buff_head *skb_list) return 1; out_free: - if (skb_list) - sctp_queue_purge_ulpevents(skb_list); - else - sctp_ulpevent_free(event); + sctp_queue_purge_ulpevents(skb_list); return 0; } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 3ccbf3c201cd..e12d4fa5aece 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3380,14 +3380,14 @@ static int __init smc_init(void) rc = register_pernet_subsys(&smc_net_stat_ops); if (rc) - return rc; + goto out_pernet_subsys; smc_ism_init(); smc_clc_init(); rc = smc_nl_init(); if (rc) - goto out_pernet_subsys; + goto out_pernet_subsys_stat; rc = smc_pnet_init(); if (rc) @@ -3480,6 +3480,8 @@ out_pnet: smc_pnet_exit(); out_nl: smc_nl_exit(); +out_pernet_subsys_stat: + unregister_pernet_subsys(&smc_net_stat_ops); out_pernet_subsys: unregister_pernet_subsys(&smc_net_ops); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index e6ee797640b4..c305d8dd23f8 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -896,7 +896,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) } memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); - if (smc_wr_alloc_lgr_mem(lgr)) + rc = smc_wr_alloc_lgr_mem(lgr); + if (rc) goto free_wq; smc_llc_lgr_init(lgr, smc); diff --git a/net/socket.c b/net/socket.c index 00da9ce3dba0..55c5d536e5f6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2199,13 +2199,7 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, static bool sock_use_custom_sol_socket(const struct socket *sock) { - const struct sock *sk = sock->sk; - - /* Use sock->ops->setsockopt() for MPTCP */ - return IS_ENABLED(CONFIG_MPTCP) && - sk->sk_protocol == IPPROTO_MPTCP && - sk->sk_type == SOCK_STREAM && - (sk->sk_family == AF_INET || sk->sk_family == AF_INET6); + return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); } /* diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index a31a27816cc0..7bb247c51e2f 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1989,7 +1989,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred, goto unwrap_failed; mic.len = len; mic.data = kmalloc(len, GFP_KERNEL); - if (!mic.data) + if (ZERO_OR_NULL_PTR(mic.data)) goto unwrap_failed; if (read_bytes_from_xdr_buf(rcv_buf, offset, mic.data, mic.len)) goto unwrap_failed; diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 5f96e75f9eec..48337687848c 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -130,8 +130,8 @@ gss_krb5_make_confounder(char *p, u32 conflen) /* initialize to random value */ if (i == 0) { - i = prandom_u32(); - i = (i << 32) | prandom_u32(); + i = get_random_u32(); + i = (i << 32) | get_random_u32(); } switch (conflen) { diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index c3c693b51c94..f075a9fb5ccc 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -677,7 +677,7 @@ static void cache_limit_defers(void) /* Consider removing either the first or the last */ if (cache_defer_cnt > DFR_MAX) { - if (prandom_u32() & 1) + if (prandom_u32_max(2)) discard = list_entry(cache_defer_list.next, struct cache_deferred_req, recent); else diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index c65c90ad626a..c1f559892ae8 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -518,13 +518,16 @@ void rpc_sysfs_client_setup(struct rpc_clnt *clnt, struct net *net) { struct rpc_sysfs_client *rpc_client; + struct rpc_sysfs_xprt_switch *xswitch = + (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; + + if (!xswitch) + return; rpc_client = rpc_sysfs_client_alloc(rpc_sunrpc_client_kobj, net, clnt->cl_clid); if (rpc_client) { char name[] = "switch"; - struct rpc_sysfs_xprt_switch *xswitch = - (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; int ret; clnt->cl_sysfs = rpc_client; @@ -558,6 +561,8 @@ void rpc_sysfs_xprt_switch_setup(struct rpc_xprt_switch *xprt_switch, rpc_xprt_switch->xprt_switch = xprt_switch; rpc_xprt_switch->xprt = xprt; kobject_uevent(&rpc_xprt_switch->kobject, KOBJ_ADD); + } else { + xprt_switch->xps_sysfs = NULL; } } @@ -569,6 +574,9 @@ void rpc_sysfs_xprt_setup(struct rpc_xprt_switch *xprt_switch, struct rpc_sysfs_xprt_switch *switch_obj = (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; + if (!switch_obj) + return; + rpc_xprt = rpc_sysfs_xprt_alloc(&switch_obj->kobject, xprt, gfp_flags); if (rpc_xprt) { xprt->xprt_sysfs = rpc_xprt; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 71dc26373444..656cec208371 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1865,7 +1865,7 @@ xprt_alloc_xid(struct rpc_xprt *xprt) static void xprt_init_xid(struct rpc_xprt *xprt) { - xprt->xid = prandom_u32(); + xprt->xid = get_random_u32(); } static void diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index f34d5427b66c..915b9902f673 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1619,7 +1619,7 @@ static int xs_get_random_port(void) if (max < min) return -EADDRINUSE; range = max - min + 1; - rand = (unsigned short) prandom_u32() % range; + rand = prandom_u32_max(range); return rand + min; } diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index f09316a9035f..d67440de011e 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1971,6 +1971,9 @@ rcv: /* Ok, everything's fine, try to synch own keys according to peers' */ tipc_crypto_key_synch(rx, *skb); + /* Re-fetch skb cb as skb might be changed in tipc_msg_validate */ + skb_cb = TIPC_SKB_CB(*skb); + /* Mark skb decrypted */ skb_cb->decrypted = 1; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index da69e1abf68f..e8dcdf267c0c 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -148,8 +148,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); - bool trial = time_before(jiffies, tn->addr_trial_end); u32 self = tipc_own_addr(net); + bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) @@ -211,7 +211,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err; - skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index fc68733673ba..dfea27a906f2 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -880,7 +880,7 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); - if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + if (TLV_GET_DATA_LEN(msg->req) < (int)sizeof(struct tipc_name_table_query)) return -EINVAL; depth = ntohl(ntq->depth); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f1c3b8eb4b3d..e902b01ea3cb 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3010,7 +3010,7 @@ static int tipc_sk_insert(struct tipc_sock *tsk) struct net *net = sock_net(sk); struct tipc_net *tn = net_generic(net, tipc_net_id); u32 remaining = (TIPC_MAX_PORT - TIPC_MIN_PORT) + 1; - u32 portid = prandom_u32() % remaining + TIPC_MIN_PORT; + u32 portid = prandom_u32_max(remaining) + TIPC_MIN_PORT; while (remaining--) { portid++; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5522865deae9..e3b427a70398 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -202,10 +202,12 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + conn_get(con); + spin_unlock_bh(&s->idr_lock); return con; } @@ -450,17 +452,24 @@ static void tipc_conn_data_ready(struct sock *sk) static void tipc_topsrv_accept(struct work_struct *work) { struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork); - struct socket *lsock = srv->listener; - struct socket *newsock; + struct socket *newsock, *lsock; struct tipc_conn *con; struct sock *newsk; int ret; + spin_lock_bh(&srv->idr_lock); + if (!srv->listener) { + spin_unlock_bh(&srv->idr_lock); + return; + } + lsock = srv->listener; + spin_unlock_bh(&srv->idr_lock); + while (1) { ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -472,11 +481,11 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); + conn_put(con); } } @@ -489,7 +498,7 @@ static void tipc_topsrv_listener_data_ready(struct sock *sk) read_lock_bh(&sk->sk_callback_lock); srv = sk->sk_user_data; - if (srv->listener) + if (srv) queue_work(srv->rcv_wq, &srv->awork); read_unlock_bh(&sk->sk_callback_lock); } @@ -568,19 +577,19 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; - *(u32 *)&sub.usr_handle = port; + *(u64 *)&sub.usr_handle = (u64)port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); - if (rc >= 0) - return true; + if (rc) + conn_put(con); + conn_put(con); - return false; + return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) @@ -699,8 +708,9 @@ static void tipc_topsrv_stop(struct net *net) __module_get(lsock->sk->sk_prot_creator->owner); srv->listener = NULL; spin_unlock_bh(&srv->idr_lock); - sock_release(lsock); + tipc_topsrv_work_stop(srv); + sock_release(lsock); idr_destroy(&srv->conn_idr); kfree(srv); } diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index cdb391a8754b..7fbb1d0b69b3 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -346,7 +346,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, salt = tls_ctx->crypto_send.aes_gcm_256.salt; break; default: - return NULL; + goto free_req; } cipher_sz = &tls_cipher_size_desc[tls_ctx->crypto_send.info.cipher_type]; buf_len = cipher_sz->salt + cipher_sz->iv + TLS_AAD_SPACE_SIZE + @@ -492,7 +492,8 @@ int tls_sw_fallback_init(struct sock *sk, key = ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->key; break; default: - return -EINVAL; + rc = -EINVAL; + goto free_aead; } cipher_sz = &tls_cipher_size_desc[crypto_info->cipher_type]; diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 9b79e334dbd9..955ac3e0bf4d 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -273,7 +273,7 @@ static int tls_strp_read_copyin(struct tls_strparser *strp) return desc.error; } -static int tls_strp_read_short(struct tls_strparser *strp) +static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) { struct skb_shared_info *shinfo; struct page *page; @@ -283,7 +283,7 @@ static int tls_strp_read_short(struct tls_strparser *strp) * to read the data out. Otherwise the connection will stall. * Without pressure threshold of INT_MAX will never be ready. */ - if (likely(!tcp_epollin_ready(strp->sk, INT_MAX))) + if (likely(qshort && !tcp_epollin_ready(strp->sk, INT_MAX))) return 0; shinfo = skb_shinfo(strp->anchor); @@ -315,6 +315,27 @@ static int tls_strp_read_short(struct tls_strparser *strp) return 0; } +static bool tls_strp_check_no_dup(struct tls_strparser *strp) +{ + unsigned int len = strp->stm.offset + strp->stm.full_len; + struct sk_buff *skb; + u32 seq; + + skb = skb_shinfo(strp->anchor)->frag_list; + seq = TCP_SKB_CB(skb)->seq; + + while (skb->len < len) { + seq += skb->len; + len -= skb->len; + skb = skb->next; + + if (TCP_SKB_CB(skb)->seq != seq) + return false; + } + + return true; +} + static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len) { struct tcp_sock *tp = tcp_sk(strp->sk); @@ -373,7 +394,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copyin(strp); if (inq < strp->stm.full_len) - return tls_strp_read_short(strp); + return tls_strp_read_copy(strp, true); if (!strp->stm.full_len) { tls_strp_load_anchor_with_queue(strp, inq); @@ -387,9 +408,12 @@ static int tls_strp_read_sock(struct tls_strparser *strp) strp->stm.full_len = sz; if (!strp->stm.full_len || inq < strp->stm.full_len) - return tls_strp_read_short(strp); + return tls_strp_read_copy(strp, true); } + if (!tls_strp_check_no_dup(strp)) + return tls_strp_read_copy(strp, false); + strp->msg_ready = 1; tls_rx_msg_ready(strp); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 15dbb392c875..b3545fc68097 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1147,7 +1147,7 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); - ordernum = prandom_u32(); + ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: ordernum = (ordernum + 1) & 0xFFFFF; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index d45d5366115a..dc2763540393 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -204,6 +204,7 @@ void wait_for_unix_gc(void) /* The external entry point: unix_gc() */ void unix_gc(void) { + struct sk_buff *next_skb, *skb; struct unix_sock *u; struct unix_sock *next; struct sk_buff_head hitlist; @@ -297,11 +298,30 @@ void unix_gc(void) spin_unlock(&unix_gc_lock); + /* We need io_uring to clean its registered files, ignore all io_uring + * originated skbs. It's fine as io_uring doesn't keep references to + * other io_uring instances and so killing all other files in the cycle + * will put all io_uring references forcing it to go through normal + * release.path eventually putting registered files. + */ + skb_queue_walk_safe(&hitlist, skb, next_skb) { + if (skb->scm_io_uring) { + __skb_unlink(skb, &hitlist); + skb_queue_tail(&skb->sk->sk_receive_queue, skb); + } + } + /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); spin_lock(&unix_gc_lock); + /* There could be io_uring registered files, just push them back to + * the inflight list + */ + list_for_each_entry_safe(u, next, &gc_candidates, link) + list_move_tail(&u->link, &gc_inflight_list); + /* All candidates should have been detached by now. */ BUG_ON(!list_empty(&gc_candidates)); diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index 7cf14c6b1725..e9bf15513961 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -145,12 +145,12 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re if (restore) { sk->sk_write_space = psock->saved_write_space; - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); return 0; } unix_dgram_bpf_check_needs_rebuild(psock->sk_proto); - WRITE_ONCE(sk->sk_prot, &unix_dgram_bpf_prot); + sock_replace_proto(sk, &unix_dgram_bpf_prot); return 0; } @@ -158,12 +158,12 @@ int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool r { if (restore) { sk->sk_write_space = psock->saved_write_space; - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); return 0; } unix_stream_bpf_check_needs_rebuild(psock->sk_proto); - WRITE_ONCE(sk->sk_prot, &unix_stream_bpf_prot); + sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ee418701cdee..884eca7f6743 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1905,8 +1905,11 @@ static int vsock_connectible_wait_data(struct sock *sk, err = 0; transport = vsk->transport; - while ((data = vsock_connectible_has_data(vsk)) == 0) { + while (1) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); + data = vsock_connectible_has_data(vsk); + if (data != 0) + break; if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) || @@ -2092,8 +2095,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, const struct vsock_transport *transport; int err; - DEFINE_WAIT(wait); - sk = sock->sk; vsk = vsock_sk(sk); err = 0; diff --git a/net/wireless/core.h b/net/wireless/core.h index 775e16cb99ed..af85d8909935 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -271,6 +271,8 @@ struct cfg80211_event { } ij; struct { u8 bssid[ETH_ALEN]; + const u8 *td_bitmap; + u8 td_bitmap_len; } pa; }; }; @@ -409,7 +411,8 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, bool wextev); void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info); -void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_autodisconnect_wk(struct work_struct *work); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 581df7f4c524..58e1fb18f85a 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -42,6 +42,10 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, unsigned int link_id; for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { + cr.links[link_id].status = data->links[link_id].status; + WARN_ON_ONCE(cr.links[link_id].status != WLAN_STATUS_SUCCESS && + (!cr.ap_mld_addr || !cr.links[link_id].bss)); + cr.links[link_id].bss = data->links[link_id].bss; if (!cr.links[link_id].bss) continue; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 597c52236514..1ad0326ff4dc 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7780,6 +7780,7 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) int err; memset(¶ms, 0, sizeof(params)); + params.link_id = nl80211_link_id_or_invalid(info->attrs); /* default to not changing parameters */ params.use_cts_prot = -1; params.use_short_preamble = -1; @@ -16139,7 +16140,8 @@ static u32 nl80211_internal_flags[] = { #undef SELECTOR }; -static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int nl80211_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = NULL; @@ -16240,7 +16242,8 @@ out_unlock: return err; } -static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void nl80211_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { u32 internal_flags = nl80211_internal_flags[ops->internal_flags]; @@ -16566,7 +16569,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_bss, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_GET_REG, @@ -17747,6 +17751,7 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, link_info_size += (cr->links[link].bssid || cr->links[link].bss) ? nla_total_size(ETH_ALEN) : 0; + link_info_size += nla_total_size(sizeof(u16)); } } @@ -17815,7 +17820,9 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, bssid)) || (cr->links[link].addr && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, - cr->links[link].addr))) + cr->links[link].addr)) || + nla_put_u16(msg, NL80211_ATTR_STATUS_CODE, + cr->links[link].status)) goto nla_put_failure; nla_nest_end(msg, nested_mlo_links); @@ -17939,7 +17946,8 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, } void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *bssid) + struct net_device *netdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len) { struct sk_buff *msg; void *hdr; @@ -17959,6 +17967,11 @@ void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) goto nla_put_failure; + if ((td_bitmap_len > 0) && td_bitmap) + if (nla_put(msg, NL80211_ATTR_TD_BITMAP, + td_bitmap_len, td_bitmap)) + goto nla_put_failure; + genlmsg_end(msg, hdr); genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 855d540ddfb9..ba9457e94c43 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -83,7 +83,8 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *bssid); + struct net_device *netdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index d5c7a5aa6853..c3d950d29432 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1084,6 +1084,8 @@ MODULE_FIRMWARE("regulatory.db"); static int query_regdb_file(const char *alpha2) { + int err; + ASSERT_RTNL(); if (regdb) @@ -1093,9 +1095,13 @@ static int query_regdb_file(const char *alpha2) if (!alpha2) return -ENOMEM; - return request_firmware_nowait(THIS_MODULE, true, "regulatory.db", - ®_pdev->dev, GFP_KERNEL, - (void *)alpha2, regdb_fw_cb); + err = request_firmware_nowait(THIS_MODULE, true, "regulatory.db", + ®_pdev->dev, GFP_KERNEL, + (void *)alpha2, regdb_fw_cb); + if (err) + kfree(alpha2); + + return err; } int reg_reload_regdb(void) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 806a5f1330ff..26c74f5b473c 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -330,7 +330,8 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, * determine if they are the same ie. */ if (tmp_old[0] == WLAN_EID_VENDOR_SPECIFIC) { - if (!memcmp(tmp_old + 2, tmp + 2, 5)) { + if (tmp_old[1] >= 5 && tmp[1] >= 5 && + !memcmp(tmp_old + 2, tmp + 2, 5)) { /* same vendor ie, copy from * subelement */ @@ -1674,7 +1675,9 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, if (old == rcu_access_pointer(known->pub.ies)) rcu_assign_pointer(known->pub.ies, new->pub.beacon_ies); - cfg80211_update_hidden_bsses(known, new->pub.beacon_ies, old); + cfg80211_update_hidden_bsses(known, + rcu_access_pointer(new->pub.beacon_ies), + old); if (old) kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); @@ -2524,10 +2527,15 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, const struct cfg80211_bss_ies *ies1, *ies2; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); - struct cfg80211_non_tx_bss non_tx_data; + struct cfg80211_non_tx_bss non_tx_data = {}; res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt, len, gfp); + + /* don't do any further MBSSID handling for S1G */ + if (ieee80211_is_s1g_beacon(mgmt->frame_control)) + return res; + if (!res || !wiphy->support_mbssid || !cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID, ie, ielen)) return res; @@ -3229,8 +3237,9 @@ static int ieee80211_scan_results(struct cfg80211_registered_device *rdev, int cfg80211_wext_giwscan(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *data = &wrqu->data; struct cfg80211_registered_device *rdev; int res; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d513536617bd..4b5b6ee0fe01 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -793,6 +793,10 @@ void __cfg80211_connect_result(struct net_device *dev, } for_each_valid_link(cr, link) { + /* don't do extra lookups for failures */ + if (cr->links[link].status != WLAN_STATUS_SUCCESS) + continue; + if (cr->links[link].bss) continue; @@ -829,6 +833,16 @@ void __cfg80211_connect_result(struct net_device *dev, } memset(wdev->links, 0, sizeof(wdev->links)); + for_each_valid_link(cr, link) { + if (cr->links[link].status == WLAN_STATUS_SUCCESS) + continue; + cr->valid_links &= ~BIT(link); + /* don't require bss pointer for failed links */ + if (!cr->links[link].bss) + continue; + cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); + cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); + } wdev->valid_links = cr->valid_links; for_each_valid_link(cr, link) wdev->links[link].client.current_bss = @@ -1237,7 +1251,8 @@ out: } EXPORT_SYMBOL(cfg80211_roamed); -void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len) { ASSERT_WDEV_LOCK(wdev); @@ -1250,11 +1265,11 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) return; nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, - bssid); + bssid, td_bitmap, td_bitmap_len); } void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, - gfp_t gfp) + const u8 *td_bitmap, u8 td_bitmap_len, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -1264,12 +1279,15 @@ void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, if (WARN_ON(!bssid)) return; - ev = kzalloc(sizeof(*ev), gfp); + ev = kzalloc(sizeof(*ev) + td_bitmap_len, gfp); if (!ev) return; ev->type = EVENT_PORT_AUTHORIZED; memcpy(ev->pa.bssid, bssid, ETH_ALEN); + ev->pa.td_bitmap = ((u8 *)ev) + sizeof(*ev); + ev->pa.td_bitmap_len = td_bitmap_len; + memcpy((void *)ev->pa.td_bitmap, td_bitmap, td_bitmap_len); /* * Use the wdev event list so that if there are pending diff --git a/net/wireless/util.c b/net/wireless/util.c index 1f285b515028..8f403f9fe816 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -990,7 +990,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; case EVENT_PORT_AUTHORIZED: - __cfg80211_port_authorized(wdev, ev->pa.bssid); + __cfg80211_port_authorized(wdev, ev->pa.bssid, + ev->pa.td_bitmap, + ev->pa.td_bitmap_len); break; } wdev_unlock(wdev); @@ -1557,10 +1559,12 @@ static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); - result = tmp; /* and take NSS */ - result = (result * rate->nss) / 8; + tmp *= rate->nss; + do_div(tmp, 8); + + result = tmp; return result / 10000; } diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index ddf340bfa07a..8a24dfca75af 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -25,16 +25,17 @@ int cfg80211_wext_giwname(struct net_device *dev, struct iw_request_info *info, - char *name, char *extra) + union iwreq_data *wrqu, char *extra) { - strcpy(name, "IEEE 802.11"); + strcpy(wrqu->name, "IEEE 802.11"); return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwname); int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, - u32 *mode, char *extra) + union iwreq_data *wrqu, char *extra) { + __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; struct vif_params vifparams; @@ -71,8 +72,9 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, EXPORT_WEXT_HANDLER(cfg80211_wext_siwmode); int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, - u32 *mode, char *extra) + union iwreq_data *wrqu, char *extra) { + __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; if (!wdev) @@ -108,8 +110,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_giwmode); int cfg80211_wext_giwrange(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_range *range = (struct iw_range *) extra; enum nl80211_band band; @@ -251,8 +254,9 @@ int cfg80211_wext_freq(struct iw_freq *freq) int cfg80211_wext_siwrts(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rts, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 orts = wdev->wiphy->rts_threshold; @@ -281,8 +285,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_siwrts); int cfg80211_wext_giwrts(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rts, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; rts->value = wdev->wiphy->rts_threshold; @@ -295,8 +300,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_giwrts); int cfg80211_wext_siwfrag(struct net_device *dev, struct iw_request_info *info, - struct iw_param *frag, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 ofrag = wdev->wiphy->frag_threshold; @@ -325,8 +331,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_siwfrag); int cfg80211_wext_giwfrag(struct net_device *dev, struct iw_request_info *info, - struct iw_param *frag, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; frag->value = wdev->wiphy->frag_threshold; @@ -339,8 +346,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_giwfrag); static int cfg80211_wext_siwretry(struct net_device *dev, struct iw_request_info *info, - struct iw_param *retry, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 changed = 0; @@ -378,8 +386,9 @@ static int cfg80211_wext_siwretry(struct net_device *dev, int cfg80211_wext_giwretry(struct net_device *dev, struct iw_request_info *info, - struct iw_param *retry, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; retry->disabled = 0; @@ -588,8 +597,9 @@ static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, static int cfg80211_wext_siwencode(struct net_device *dev, struct iw_request_info *info, - struct iw_point *erq, char *keybuf) + union iwreq_data *wrqu, char *keybuf) { + struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int idx, err; @@ -664,8 +674,9 @@ out: static int cfg80211_wext_siwencodeext(struct net_device *dev, struct iw_request_info *info, - struct iw_point *erq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct iw_encode_ext *ext = (struct iw_encode_ext *) extra; @@ -767,8 +778,9 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev, static int cfg80211_wext_giwencode(struct net_device *dev, struct iw_request_info *info, - struct iw_point *erq, char *keybuf) + union iwreq_data *wrqu, char *keybuf) { + struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; int idx; @@ -804,8 +816,9 @@ static int cfg80211_wext_giwencode(struct net_device *dev, static int cfg80211_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *wextfreq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_freq *wextfreq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = { @@ -870,8 +883,9 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, static int cfg80211_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_freq *freq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = {}; @@ -1147,8 +1161,9 @@ static int cfg80211_set_key_mgt(struct wireless_dev *wdev, u32 key_mgt) static int cfg80211_wext_siwauth(struct net_device *dev, struct iw_request_info *info, - struct iw_param *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *data = &wrqu->param; struct wireless_dev *wdev = dev->ieee80211_ptr; if (wdev->iftype != NL80211_IFTYPE_STATION) @@ -1180,7 +1195,7 @@ static int cfg80211_wext_siwauth(struct net_device *dev, static int cfg80211_wext_giwauth(struct net_device *dev, struct iw_request_info *info, - struct iw_param *data, char *extra) + union iwreq_data *wrqu, char *extra) { /* XXX: what do we need? */ @@ -1189,8 +1204,9 @@ static int cfg80211_wext_giwauth(struct net_device *dev, static int cfg80211_wext_siwpower(struct net_device *dev, struct iw_request_info *info, - struct iw_param *wrq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); bool ps; @@ -1238,8 +1254,9 @@ static int cfg80211_wext_siwpower(struct net_device *dev, static int cfg80211_wext_giwpower(struct net_device *dev, struct iw_request_info *info, - struct iw_param *wrq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; wrq->disabled = !wdev->ps; @@ -1249,8 +1266,9 @@ static int cfg80211_wext_giwpower(struct net_device *dev, static int cfg80211_wext_siwrate(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rate, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bitrate_mask mask; @@ -1307,8 +1325,9 @@ static int cfg80211_wext_siwrate(struct net_device *dev, static int cfg80211_wext_giwrate(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rate, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct station_info sinfo = {}; @@ -1430,8 +1449,9 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) static int cfg80211_wext_siwap(struct net_device *dev, struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) + union iwreq_data *wrqu, char *extra) { + struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1455,8 +1475,9 @@ static int cfg80211_wext_siwap(struct net_device *dev, static int cfg80211_wext_giwap(struct net_device *dev, struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) + union iwreq_data *wrqu, char *extra) { + struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1480,8 +1501,9 @@ static int cfg80211_wext_giwap(struct net_device *dev, static int cfg80211_wext_siwessid(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *ssid) + union iwreq_data *wrqu, char *ssid) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1505,8 +1527,9 @@ static int cfg80211_wext_siwessid(struct net_device *dev, static int cfg80211_wext_giwessid(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *ssid) + union iwreq_data *wrqu, char *ssid) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1533,7 +1556,7 @@ static int cfg80211_wext_giwessid(struct net_device *dev, static int cfg80211_wext_siwpmksa(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -1584,78 +1607,39 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev, return ret; } -#define DEFINE_WEXT_COMPAT_STUB(func, type) \ - static int __ ## func(struct net_device *dev, \ - struct iw_request_info *info, \ - union iwreq_data *wrqu, \ - char *extra) \ - { \ - return func(dev, info, (type *)wrqu, extra); \ - } - -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwname, char) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwfreq, struct iw_freq) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwfreq, struct iw_freq) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwmode, u32) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwmode, u32) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrange, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwap, struct sockaddr) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwap, struct sockaddr) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwmlme, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwscan, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwessid, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwessid, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwrate, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrate, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwrts, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrts, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwfrag, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwfrag, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwretry, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwretry, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwencode, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwencode, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwpower, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwpower, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwgenie, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwauth, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwauth, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwencodeext, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwpmksa, struct iw_point) - static const iw_handler cfg80211_handlers[] = { - [IW_IOCTL_IDX(SIOCGIWNAME)] = __cfg80211_wext_giwname, - [IW_IOCTL_IDX(SIOCSIWFREQ)] = __cfg80211_wext_siwfreq, - [IW_IOCTL_IDX(SIOCGIWFREQ)] = __cfg80211_wext_giwfreq, - [IW_IOCTL_IDX(SIOCSIWMODE)] = __cfg80211_wext_siwmode, - [IW_IOCTL_IDX(SIOCGIWMODE)] = __cfg80211_wext_giwmode, - [IW_IOCTL_IDX(SIOCGIWRANGE)] = __cfg80211_wext_giwrange, - [IW_IOCTL_IDX(SIOCSIWAP)] = __cfg80211_wext_siwap, - [IW_IOCTL_IDX(SIOCGIWAP)] = __cfg80211_wext_giwap, - [IW_IOCTL_IDX(SIOCSIWMLME)] = __cfg80211_wext_siwmlme, - [IW_IOCTL_IDX(SIOCSIWSCAN)] = cfg80211_wext_siwscan, - [IW_IOCTL_IDX(SIOCGIWSCAN)] = __cfg80211_wext_giwscan, - [IW_IOCTL_IDX(SIOCSIWESSID)] = __cfg80211_wext_siwessid, - [IW_IOCTL_IDX(SIOCGIWESSID)] = __cfg80211_wext_giwessid, - [IW_IOCTL_IDX(SIOCSIWRATE)] = __cfg80211_wext_siwrate, - [IW_IOCTL_IDX(SIOCGIWRATE)] = __cfg80211_wext_giwrate, - [IW_IOCTL_IDX(SIOCSIWRTS)] = __cfg80211_wext_siwrts, - [IW_IOCTL_IDX(SIOCGIWRTS)] = __cfg80211_wext_giwrts, - [IW_IOCTL_IDX(SIOCSIWFRAG)] = __cfg80211_wext_siwfrag, - [IW_IOCTL_IDX(SIOCGIWFRAG)] = __cfg80211_wext_giwfrag, - [IW_IOCTL_IDX(SIOCSIWTXPOW)] = cfg80211_wext_siwtxpower, - [IW_IOCTL_IDX(SIOCGIWTXPOW)] = cfg80211_wext_giwtxpower, - [IW_IOCTL_IDX(SIOCSIWRETRY)] = __cfg80211_wext_siwretry, - [IW_IOCTL_IDX(SIOCGIWRETRY)] = __cfg80211_wext_giwretry, - [IW_IOCTL_IDX(SIOCSIWENCODE)] = __cfg80211_wext_siwencode, - [IW_IOCTL_IDX(SIOCGIWENCODE)] = __cfg80211_wext_giwencode, - [IW_IOCTL_IDX(SIOCSIWPOWER)] = __cfg80211_wext_siwpower, - [IW_IOCTL_IDX(SIOCGIWPOWER)] = __cfg80211_wext_giwpower, - [IW_IOCTL_IDX(SIOCSIWGENIE)] = __cfg80211_wext_siwgenie, - [IW_IOCTL_IDX(SIOCSIWAUTH)] = __cfg80211_wext_siwauth, - [IW_IOCTL_IDX(SIOCGIWAUTH)] = __cfg80211_wext_giwauth, - [IW_IOCTL_IDX(SIOCSIWENCODEEXT)]= __cfg80211_wext_siwencodeext, - [IW_IOCTL_IDX(SIOCSIWPMKSA)] = __cfg80211_wext_siwpmksa, + IW_HANDLER(SIOCGIWNAME, cfg80211_wext_giwname), + IW_HANDLER(SIOCSIWFREQ, cfg80211_wext_siwfreq), + IW_HANDLER(SIOCGIWFREQ, cfg80211_wext_giwfreq), + IW_HANDLER(SIOCSIWMODE, cfg80211_wext_siwmode), + IW_HANDLER(SIOCGIWMODE, cfg80211_wext_giwmode), + IW_HANDLER(SIOCGIWRANGE, cfg80211_wext_giwrange), + IW_HANDLER(SIOCSIWAP, cfg80211_wext_siwap), + IW_HANDLER(SIOCGIWAP, cfg80211_wext_giwap), + IW_HANDLER(SIOCSIWMLME, cfg80211_wext_siwmlme), + IW_HANDLER(SIOCSIWSCAN, cfg80211_wext_siwscan), + IW_HANDLER(SIOCGIWSCAN, cfg80211_wext_giwscan), + IW_HANDLER(SIOCSIWESSID, cfg80211_wext_siwessid), + IW_HANDLER(SIOCGIWESSID, cfg80211_wext_giwessid), + IW_HANDLER(SIOCSIWRATE, cfg80211_wext_siwrate), + IW_HANDLER(SIOCGIWRATE, cfg80211_wext_giwrate), + IW_HANDLER(SIOCSIWRTS, cfg80211_wext_siwrts), + IW_HANDLER(SIOCGIWRTS, cfg80211_wext_giwrts), + IW_HANDLER(SIOCSIWFRAG, cfg80211_wext_siwfrag), + IW_HANDLER(SIOCGIWFRAG, cfg80211_wext_giwfrag), + IW_HANDLER(SIOCSIWTXPOW, cfg80211_wext_siwtxpower), + IW_HANDLER(SIOCGIWTXPOW, cfg80211_wext_giwtxpower), + IW_HANDLER(SIOCSIWRETRY, cfg80211_wext_siwretry), + IW_HANDLER(SIOCGIWRETRY, cfg80211_wext_giwretry), + IW_HANDLER(SIOCSIWENCODE, cfg80211_wext_siwencode), + IW_HANDLER(SIOCGIWENCODE, cfg80211_wext_giwencode), + IW_HANDLER(SIOCSIWPOWER, cfg80211_wext_siwpower), + IW_HANDLER(SIOCGIWPOWER, cfg80211_wext_giwpower), + IW_HANDLER(SIOCSIWGENIE, cfg80211_wext_siwgenie), + IW_HANDLER(SIOCSIWAUTH, cfg80211_wext_siwauth), + IW_HANDLER(SIOCGIWAUTH, cfg80211_wext_giwauth), + IW_HANDLER(SIOCSIWENCODEEXT, cfg80211_wext_siwencodeext), + IW_HANDLER(SIOCSIWPMKSA, cfg80211_wext_siwpmksa), }; const struct iw_handler_def cfg80211_wext_handler = { diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h index 8d3cc1552e2f..c02eb789e676 100644 --- a/net/wireless/wext-compat.h +++ b/net/wireless/wext-compat.h @@ -13,7 +13,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra); + struct iw_freq *wextfreq, char *extra); int cfg80211_ibss_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra); @@ -32,7 +32,7 @@ int cfg80211_ibss_wext_giwessid(struct net_device *dev, int cfg80211_mgd_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra); + struct iw_freq *wextfreq, char *extra); int cfg80211_mgd_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra); @@ -51,10 +51,10 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_freq(struct iw_freq *freq); diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 68f45afc352d..191c6d98c700 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -324,8 +324,9 @@ int cfg80211_mgd_wext_giwap(struct net_device *dev, int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *ie = extra; @@ -374,7 +375,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev, int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_mlme *mlme = (struct iw_mlme *)extra; diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 5259ef8f5242..748d8630ab58 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -117,7 +117,7 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, if (!pskb_may_pull(skb, 1)) { x25_neigh_put(nb); - return 0; + goto drop; } switch (skb->data[0]) { diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index acc8e52a4f5f..771d0fa90ef5 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -231,9 +231,9 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + return __bpf_xdp_redirect_map(map, index, flags, 0, __xsk_map_lookup_elem); } diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5f5aafd418af..21269e8f2db4 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -97,6 +97,18 @@ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) } } +static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + __u32 seq = xo->seq.low; + + seq += skb_shinfo(skb)->gso_segs; + if (unlikely(seq < xo->seq.low)) + return true; + + return false; +} + struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; @@ -134,7 +146,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 9f4d42eb090f..ce56d659c55a 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -714,7 +714,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff oseq += skb_shinfo(skb)->gso_segs; } - if (unlikely(oseq < replay_esn->oseq)) { + if (unlikely(xo->seq.low < replay_esn->oseq)) { XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; xo->seq.hi = oseq_hi; replay_esn->oseq_hi = oseq_hi; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d0ae17e3bb38..9ec481fbfb63 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2081,7 +2081,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { - spi = low + prandom_u32()%(high-low+1); + spi = low + prandom_u32_max(high - low + 1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { newspi = htonl(spi); |