aboutsummaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/pm_netlink.c90
-rw-r--r--net/mptcp/protocol.c4
-rw-r--r--net/mptcp/protocol.h3
-rw-r--r--net/mptcp/subflow.c75
4 files changed, 122 insertions, 50 deletions
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 75a0a27547e6..800515fe5e1d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -83,16 +83,6 @@ static bool addresses_equal(const struct mptcp_addr_info *a,
return a->port == b->port;
}
-static bool address_zero(const struct mptcp_addr_info *addr)
-{
- struct mptcp_addr_info zero;
-
- memset(&zero, 0, sizeof(zero));
- zero.family = addr->family;
-
- return addresses_equal(addr, &zero, true);
-}
-
static void local_address(const struct sock_common *skc,
struct mptcp_addr_info *addr)
{
@@ -877,10 +867,18 @@ static bool address_use_port(struct mptcp_pm_addr_entry *entry)
MPTCP_PM_ADDR_FLAG_SIGNAL;
}
+/* caller must ensure the RCU grace period is already elapsed */
+static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
+{
+ if (entry->lsk)
+ sock_release(entry->lsk);
+ kfree(entry);
+}
+
static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
struct mptcp_pm_addr_entry *entry)
{
- struct mptcp_pm_addr_entry *cur;
+ struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
unsigned int addr_max;
int ret = -EINVAL;
@@ -901,8 +899,22 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
list_for_each_entry(cur, &pernet->local_addr_list, list) {
if (addresses_equal(&cur->addr, &entry->addr,
address_use_port(entry) &&
- address_use_port(cur)))
- goto out;
+ address_use_port(cur))) {
+ /* allow replacing the exiting endpoint only if such
+ * endpoint is an implicit one and the user-space
+ * did not provide an endpoint id
+ */
+ if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT))
+ goto out;
+ if (entry->addr.id)
+ goto out;
+
+ pernet->addrs--;
+ entry->addr.id = cur->addr.id;
+ list_del_rcu(&cur->list);
+ del_entry = cur;
+ break;
+ }
}
if (!entry->addr.id) {
@@ -938,6 +950,12 @@ find_next:
out:
spin_unlock_bh(&pernet->lock);
+
+ /* just replaced an existing entry, free it */
+ if (del_entry) {
+ synchronize_rcu();
+ __mptcp_pm_release_addr_entry(del_entry);
+ }
return ret;
}
@@ -1011,9 +1029,6 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
if (addresses_equal(&msk_local, &skc_local, false))
return 0;
- if (address_zero(&skc_local))
- return 0;
-
pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
rcu_read_lock();
@@ -1036,7 +1051,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
entry->addr.id = 0;
entry->addr.port = 0;
entry->ifindex = 0;
- entry->flags = 0;
+ entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
entry->lsk = NULL;
ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
if (ret < 0)
@@ -1249,6 +1264,17 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
}
+ if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL &&
+ addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) {
+ GENL_SET_ERR_MSG(info, "flags mustn't have both signal and fullmesh");
+ return -EINVAL;
+ }
+
+ if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) {
+ GENL_SET_ERR_MSG(info, "can't create IMPLICIT endpoint");
+ return -EINVAL;
+ }
+
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry) {
GENL_SET_ERR_MSG(info, "can't allocate addr");
@@ -1333,11 +1359,12 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
}
static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
- struct mptcp_addr_info *addr)
+ const struct mptcp_pm_addr_entry *entry)
{
- struct mptcp_sock *msk;
- long s_slot = 0, s_num = 0;
+ const struct mptcp_addr_info *addr = &entry->addr;
struct mptcp_rm_list list = { .nr = 0 };
+ long s_slot = 0, s_num = 0;
+ struct mptcp_sock *msk;
pr_debug("remove_id=%d", addr->id);
@@ -1354,7 +1381,8 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
lock_sock(sk);
remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
- mptcp_pm_remove_anno_addr(msk, addr, remove_subflow);
+ mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
+ !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
if (remove_subflow)
mptcp_pm_remove_subflow(msk, &list);
release_sock(sk);
@@ -1367,14 +1395,6 @@ next:
return 0;
}
-/* caller must ensure the RCU grace period is already elapsed */
-static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
-{
- if (entry->lsk)
- sock_release(entry->lsk);
- kfree(entry);
-}
-
static int mptcp_nl_remove_id_zero_address(struct net *net,
struct mptcp_addr_info *addr)
{
@@ -1451,7 +1471,7 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
__clear_bit(entry->addr.id, pernet->id_bitmap);
spin_unlock_bh(&pernet->lock);
- mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr);
+ mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry);
synchronize_rcu();
__mptcp_pm_release_addr_entry(entry);
@@ -1466,14 +1486,12 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
list_for_each_entry(entry, rm_list, list) {
if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
- alist.nr < MPTCP_RM_IDS_MAX &&
- slist.nr < MPTCP_RM_IDS_MAX) {
- alist.ids[alist.nr++] = entry->addr.id;
+ slist.nr < MPTCP_RM_IDS_MAX)
slist.ids[slist.nr++] = entry->addr.id;
- } else if (remove_anno_list_by_saddr(msk, &entry->addr) &&
- alist.nr < MPTCP_RM_IDS_MAX) {
+
+ if (remove_anno_list_by_saddr(msk, &entry->addr) &&
+ alist.nr < MPTCP_RM_IDS_MAX)
alist.ids[alist.nr++] = entry->addr.id;
- }
}
if (alist.nr) {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 1c72f25f083e..101aeebeb9eb 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -117,6 +117,9 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
list_add(&subflow->node, &msk->conn_list);
sock_hold(ssock->sk);
subflow->request_mptcp = 1;
+
+ /* This is the first subflow, always with id 0 */
+ subflow->local_id_valid = 1;
mptcp_sock_graft(msk->first, sk->sk_socket);
return 0;
@@ -1356,6 +1359,7 @@ alloc_skb:
out:
if (READ_ONCE(msk->csum_enabled))
mptcp_update_data_checksum(skb, copy);
+ trace_mptcp_sendmsg_frag(mpext);
mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
return copy;
}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 9d0ee6cee07f..3c1a3036550f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -442,7 +442,8 @@ struct mptcp_subflow_context {
rx_eof : 1,
can_ack : 1, /* only after processing the remote a key */
disposable : 1, /* ctx can be free at ulp release time */
- stale : 1; /* unable to snd/rcv data, do not use for xmit */
+ stale : 1, /* unable to snd/rcv data, do not use for xmit */
+ local_id_valid : 1; /* local_id is correctly initialized */
enum mptcp_data_avail data_avail;
u32 remote_nonce;
u64 thmac;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 45c004f87f5a..aba260f547da 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -481,6 +481,51 @@ do_reset:
mptcp_subflow_reset(sk);
}
+static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id)
+{
+ subflow->local_id = local_id;
+ subflow->local_id_valid = 1;
+}
+
+static int subflow_chk_local_id(struct sock *sk)
+{
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+ int err;
+
+ if (likely(subflow->local_id_valid))
+ return 0;
+
+ err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk);
+ if (err < 0)
+ return err;
+
+ subflow_set_local_id(subflow, err);
+ return 0;
+}
+
+static int subflow_rebuild_header(struct sock *sk)
+{
+ int err = subflow_chk_local_id(sk);
+
+ if (unlikely(err < 0))
+ return err;
+
+ return inet_sk_rebuild_header(sk);
+}
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+static int subflow_v6_rebuild_header(struct sock *sk)
+{
+ int err = subflow_chk_local_id(sk);
+
+ if (unlikely(err < 0))
+ return err;
+
+ return inet6_sk_rebuild_header(sk);
+}
+#endif
+
struct request_sock_ops mptcp_subflow_request_sock_ops;
static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init;
@@ -1104,7 +1149,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
struct sk_buff *skb;
if (!skb_peek(&ssk->sk_receive_queue))
- WRITE_ONCE(subflow->data_avail, 0);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
if (subflow->data_avail)
return true;
@@ -1169,7 +1214,7 @@ fallback:
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
tcp_send_active_reset(ssk, GFP_ATOMIC);
- WRITE_ONCE(subflow->data_avail, 0);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
return true;
}
@@ -1182,7 +1227,7 @@ fallback:
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMPTCP;
tcp_send_active_reset(ssk, GFP_ATOMIC);
- WRITE_ONCE(subflow->data_avail, 0);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
return false;
}
@@ -1204,7 +1249,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
if (subflow->map_valid &&
mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
subflow->map_valid = 0;
- WRITE_ONCE(subflow->data_avail, 0);
+ WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA);
pr_debug("Done with mapping: seq=%u data_len=%u",
subflow->map_subflow_seq,
@@ -1398,13 +1443,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
get_random_bytes(&subflow->local_nonce, sizeof(u32));
} while (!subflow->local_nonce);
- if (!local_id) {
- err = mptcp_pm_get_local_id(msk, (struct sock_common *)ssk);
- if (err < 0)
- goto failed;
-
- local_id = err;
- }
+ if (local_id)
+ subflow_set_local_id(subflow, local_id);
mptcp_pm_get_flags_and_ifindex_by_id(sock_net(sk), local_id,
&flags, &ifindex);
@@ -1429,7 +1469,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
remote_token, local_id, remote_id);
subflow->remote_token = remote_token;
- subflow->local_id = local_id;
subflow->remote_id = remote_id;
subflow->request_join = 1;
subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
@@ -1728,15 +1767,22 @@ static void subflow_ulp_clone(const struct request_sock *req,
new_ctx->token = subflow_req->token;
new_ctx->ssn_offset = subflow_req->ssn_offset;
new_ctx->idsn = subflow_req->idsn;
+
+ /* this is the first subflow, id is always 0 */
+ new_ctx->local_id_valid = 1;
} else if (subflow_req->mp_join) {
new_ctx->ssn_offset = subflow_req->ssn_offset;
new_ctx->mp_join = 1;
new_ctx->fully_established = 1;
new_ctx->backup = subflow_req->backup;
- new_ctx->local_id = subflow_req->local_id;
new_ctx->remote_id = subflow_req->remote_id;
new_ctx->token = subflow_req->token;
new_ctx->thmac = subflow_req->thmac;
+
+ /* the subflow req id is valid, fetched via subflow_check_req()
+ * and subflow_token_join_request()
+ */
+ subflow_set_local_id(new_ctx, subflow_req->local_id);
}
}
@@ -1789,6 +1835,7 @@ void __init mptcp_subflow_init(void)
subflow_specific.conn_request = subflow_v4_conn_request;
subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
subflow_specific.sk_rx_dst_set = subflow_finish_connect;
+ subflow_specific.rebuild_header = subflow_rebuild_header;
tcp_prot_override = tcp_prot;
tcp_prot_override.release_cb = tcp_release_cb_override;
@@ -1801,6 +1848,7 @@ void __init mptcp_subflow_init(void)
subflow_v6_specific.conn_request = subflow_v6_conn_request;
subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock;
subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect;
+ subflow_v6_specific.rebuild_header = subflow_v6_rebuild_header;
subflow_v6m_specific = subflow_v6_specific;
subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit;
@@ -1808,6 +1856,7 @@ void __init mptcp_subflow_init(void)
subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
subflow_v6m_specific.net_frag_header_len = 0;
+ subflow_v6m_specific.rebuild_header = subflow_rebuild_header;
tcpv6_prot_override = tcpv6_prot;
tcpv6_prot_override.release_cb = tcp_release_cb_override;
Powered by cgit, Gruvboxed by Blaster4385.