aboutsummaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/mib.c6
-rw-r--r--net/mptcp/mib.h18
-rw-r--r--net/mptcp/options.c19
-rw-r--r--net/mptcp/pm.c70
-rw-r--r--net/mptcp/pm_netlink.c161
-rw-r--r--net/mptcp/pm_userspace.c53
-rw-r--r--net/mptcp/protocol.c225
-rw-r--r--net/mptcp/protocol.h26
-rw-r--r--net/mptcp/sockopt.c153
-rw-r--r--net/mptcp/subflow.c25
10 files changed, 514 insertions, 242 deletions
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 0dac2863c6e1..a0990c365a2e 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -34,7 +34,11 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW),
SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA),
SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR),
+ SNMP_MIB_ITEM("AddAddrTx", MPTCP_MIB_ADDADDRTX),
+ SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP),
SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD),
+ SNMP_MIB_ITEM("EchoAddTx", MPTCP_MIB_ECHOADDTX),
+ SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP),
SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD),
SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP),
SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX),
@@ -44,6 +48,8 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX),
SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR),
SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP),
+ SNMP_MIB_ITEM("RmAddrTx", MPTCP_MIB_RMADDRTX),
+ SNMP_MIB_ITEM("RmAddrTxDrop", MPTCP_MIB_RMADDRTXDROP),
SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 2be3596374f4..cae71d947252 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -27,7 +27,15 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_NODSSWINDOW, /* Segments not in MPTCP windows */
MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */
MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */
+ MPTCP_MIB_ADDADDRTX, /* Sent ADD_ADDR with echo-flag=0 */
+ MPTCP_MIB_ADDADDRTXDROP, /* ADD_ADDR with echo-flag=0 not send due to
+ * resource exhaustion
+ */
MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */
+ MPTCP_MIB_ECHOADDTX, /* Send ADD_ADDR with echo-flag=1 */
+ MPTCP_MIB_ECHOADDTXDROP, /* ADD_ADDR with echo-flag=1 not send due
+ * to resource exhaustion
+ */
MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */
MPTCP_MIB_ADDADDRDROP, /* Dropped incoming ADD_ADDR */
MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */
@@ -37,6 +45,8 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */
MPTCP_MIB_RMADDR, /* Received RM_ADDR */
MPTCP_MIB_RMADDRDROP, /* Dropped incoming RM_ADDR */
+ MPTCP_MIB_RMADDRTX, /* Sent RM_ADDR */
+ MPTCP_MIB_RMADDRTXDROP, /* RM_ADDR not sent due to resource exhaustion */
MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */
MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */
MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */
@@ -63,6 +73,14 @@ struct mptcp_mib {
unsigned long mibs[LINUX_MIB_MPTCP_MAX];
};
+static inline void MPTCP_ADD_STATS(struct net *net,
+ enum linux_mptcp_mib_field field,
+ int val)
+{
+ if (likely(net->mib.mptcp_statistics))
+ SNMP_ADD_STATS(net->mib.mptcp_statistics, field, val);
+}
+
static inline void MPTCP_INC_STATS(struct net *net,
enum linux_mptcp_mib_field field)
{
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 19a01b6566f1..c254accb14de 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -687,9 +687,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
}
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
if (!echo) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);
opts->ahmac = add_addr_generate_hmac(msk->local_key,
msk->remote_key,
&opts->addr);
+ } else {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
}
pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
@@ -723,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk,
for (i = 0; i < opts->rm_list.nr; i++)
pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]);
-
+ MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr);
return true;
}
@@ -1023,6 +1026,12 @@ u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq)
return cur_seq;
}
+static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una)
+{
+ msk->bytes_acked += new_snd_una - msk->snd_una;
+ msk->snd_una = new_snd_una;
+}
+
static void ack_update_msk(struct mptcp_sock *msk,
struct sock *ssk,
struct mptcp_options_received *mp_opt)
@@ -1054,7 +1063,7 @@ static void ack_update_msk(struct mptcp_sock *msk,
__mptcp_check_push(sk, ssk);
if (after64(new_snd_una, old_snd_una)) {
- msk->snd_una = new_snd_una;
+ __mptcp_snd_una_update(msk, new_snd_una);
__mptcp_data_acked(sk);
}
mptcp_data_unlock(sk);
@@ -1116,6 +1125,12 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
mptcp_data_lock(subflow->conn);
if (sk_stream_memory_free(sk))
__mptcp_check_push(subflow->conn, sk);
+
+ /* on fallback we just need to ignore the msk-level snd_una, as
+ * this is really plain TCP
+ */
+ __mptcp_snd_una_update(msk, READ_ONCE(msk->snd_nxt));
+
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
return true;
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 78c924506e83..7dbbad1e4f55 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -26,7 +26,8 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
if (add_addr &
(echo ? BIT(MPTCP_ADD_ADDR_ECHO) : BIT(MPTCP_ADD_ADDR_SIGNAL))) {
- pr_warn("addr_signal error, add_addr=%d, echo=%d", add_addr, echo);
+ MPTCP_INC_STATS(sock_net((struct sock *)msk),
+ echo ? MPTCP_MIB_ECHOADDTXDROP : MPTCP_MIB_ADDADDRTXDROP);
return -EINVAL;
}
@@ -48,7 +49,8 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
if (rm_addr) {
- pr_warn("addr_signal error, rm_addr=%d", rm_addr);
+ MPTCP_ADD_STATS(sock_net((struct sock *)msk),
+ MPTCP_MIB_RMADDRTXDROP, rm_list->nr);
return -EINVAL;
}
@@ -87,8 +89,15 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
unsigned int subflows_max;
int ret = 0;
- if (mptcp_pm_is_userspace(msk))
- return mptcp_userspace_pm_active(msk);
+ if (mptcp_pm_is_userspace(msk)) {
+ if (mptcp_userspace_pm_active(msk)) {
+ spin_lock_bh(&pm->lock);
+ pm->subflows++;
+ spin_unlock_bh(&pm->lock);
+ return true;
+ }
+ return false;
+ }
subflows_max = mptcp_pm_get_subflows_max(msk);
@@ -181,8 +190,16 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk,
struct mptcp_pm_data *pm = &msk->pm;
bool update_subflows;
- update_subflows = (subflow->request_join || subflow->mp_join) &&
- mptcp_pm_is_kernel(msk);
+ update_subflows = subflow->request_join || subflow->mp_join;
+ if (mptcp_pm_is_userspace(msk)) {
+ if (update_subflows) {
+ spin_lock_bh(&pm->lock);
+ pm->subflows--;
+ spin_unlock_bh(&pm->lock);
+ }
+ return;
+ }
+
if (!READ_ONCE(pm->work_pending) && !update_subflows)
return;
@@ -398,7 +415,46 @@ out_unlock:
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
{
- return mptcp_pm_nl_get_local_id(msk, skc);
+ struct mptcp_addr_info skc_local;
+ struct mptcp_addr_info msk_local;
+
+ if (WARN_ON_ONCE(!msk))
+ return -1;
+
+ /* The 0 ID mapping is defined by the first subflow, copied into the msk
+ * addr
+ */
+ mptcp_local_address((struct sock_common *)msk, &msk_local);
+ mptcp_local_address((struct sock_common *)skc, &skc_local);
+ if (mptcp_addresses_equal(&msk_local, &skc_local, false))
+ return 0;
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_get_local_id(msk, &skc_local);
+ return mptcp_pm_nl_get_local_id(msk, &skc_local);
+}
+
+int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
+ u8 *flags, int *ifindex)
+{
+ *flags = 0;
+ *ifindex = 0;
+
+ if (!id)
+ return 0;
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
+ return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
+}
+
+int mptcp_pm_set_flags(struct net *net, struct nlattr *token,
+ struct mptcp_pm_addr_entry *loc,
+ struct mptcp_pm_addr_entry *rem, u8 bkup)
+{
+ if (token)
+ return mptcp_userspace_pm_set_flags(net, token, loc, rem, bkup);
+ return mptcp_pm_nl_set_flags(net, loc, bkup);
}
void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index bc343dab5e3f..5692daf57a4d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -25,9 +25,9 @@ static int pm_nl_pernet_id;
struct mptcp_pm_add_entry {
struct list_head list;
struct mptcp_addr_info addr;
+ u8 retrans_times;
struct timer_list add_timer;
struct mptcp_sock *sock;
- u8 retrans_times;
};
struct pm_nl_pernet {
@@ -86,8 +86,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
return a->port == b->port;
}
-static void local_address(const struct sock_common *skc,
- struct mptcp_addr_info *addr)
+void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr)
{
addr->family = skc->skc_family;
addr->port = htons(skc->skc_num);
@@ -122,7 +121,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list,
list_for_each_entry(subflow, list, node) {
skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
- local_address(skc, &cur);
+ mptcp_local_address(skc, &cur);
if (mptcp_addresses_equal(&cur, saddr, saddr->port))
return true;
}
@@ -263,7 +262,7 @@ bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
struct mptcp_addr_info saddr;
bool ret = false;
- local_address((struct sock_common *)sk, &saddr);
+ mptcp_local_address((struct sock_common *)sk, &saddr);
spin_lock_bh(&msk->pm.lock);
list_for_each_entry(entry, &msk->pm.anno_list, list) {
@@ -342,7 +341,7 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
}
bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
- const struct mptcp_pm_addr_entry *entry)
+ const struct mptcp_addr_info *addr)
{
struct mptcp_pm_add_entry *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
@@ -350,7 +349,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
lockdep_assert_held(&msk->pm.lock);
- add_entry = mptcp_lookup_anno_list_by_saddr(msk, &entry->addr);
+ add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
if (add_entry) {
if (mptcp_pm_is_kernel(msk))
@@ -367,7 +366,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
list_add(&add_entry->list, &msk->pm.anno_list);
- add_entry->addr = entry->addr;
+ add_entry->addr = *addr;
add_entry->sock = msk;
add_entry->retrans_times = 0;
@@ -541,7 +540,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
struct mptcp_addr_info mpc_addr;
bool backup = false;
- local_address((struct sock_common *)msk->first, &mpc_addr);
+ mptcp_local_address((struct sock_common *)msk->first, &mpc_addr);
rcu_read_lock();
entry = __lookup_addr(pernet, &mpc_addr, false);
if (entry) {
@@ -577,7 +576,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
return;
if (local) {
- if (mptcp_pm_alloc_anno_list(msk, local)) {
+ if (mptcp_pm_alloc_anno_list(msk, &local->addr)) {
__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
msk->pm.add_addr_signaled++;
mptcp_pm_announce_addr(msk, &local->addr, false);
@@ -752,7 +751,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
struct mptcp_addr_info local, remote;
- local_address((struct sock_common *)ssk, &local);
+ mptcp_local_address((struct sock_common *)ssk, &local);
if (!mptcp_addresses_equal(&local, addr, addr->port))
continue;
@@ -1047,6 +1046,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
if (err)
return err;
+ inet_sk_state_store(newsk, TCP_LISTEN);
err = kernel_listen(ssock, backlog);
if (err)
return err;
@@ -1056,33 +1056,17 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
return 0;
}
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
+int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
{
struct mptcp_pm_addr_entry *entry;
- struct mptcp_addr_info skc_local;
- struct mptcp_addr_info msk_local;
struct pm_nl_pernet *pernet;
int ret = -1;
- if (WARN_ON_ONCE(!msk))
- return -1;
-
- /* The 0 ID mapping is defined by the first subflow, copied into the msk
- * addr
- */
- local_address((struct sock_common *)msk, &msk_local);
- local_address((struct sock_common *)skc, &skc_local);
- if (mptcp_addresses_equal(&msk_local, &skc_local, false))
- return 0;
-
- if (mptcp_pm_is_userspace(msk))
- return mptcp_userspace_pm_get_local_id(msk, &skc_local);
-
pernet = pm_nl_get_pernet_from_msk(msk);
rcu_read_lock();
list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
- if (mptcp_addresses_equal(&entry->addr, &skc_local, entry->addr.port)) {
+ if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
ret = entry->addr.id;
break;
}
@@ -1096,7 +1080,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
if (!entry)
return -ENOMEM;
- entry->addr = skc_local;
+ entry->addr = *skc;
entry->addr.id = 0;
entry->addr.port = 0;
entry->ifindex = 0;
@@ -1373,31 +1357,20 @@ out_free:
return ret;
}
-int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
- u8 *flags, int *ifindex)
+int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
+ u8 *flags, int *ifindex)
{
struct mptcp_pm_addr_entry *entry;
struct sock *sk = (struct sock *)msk;
struct net *net = sock_net(sk);
- *flags = 0;
- *ifindex = 0;
-
- if (id) {
- if (mptcp_pm_is_userspace(msk))
- return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk,
- id,
- flags,
- ifindex);
-
- rcu_read_lock();
- entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
- if (entry) {
- *flags = entry->flags;
- *ifindex = entry->ifindex;
- }
- rcu_read_unlock();
+ rcu_read_lock();
+ entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
+ if (entry) {
+ *flags = entry->flags;
+ *ifindex = entry->ifindex;
}
+ rcu_read_unlock();
return 0;
}
@@ -1491,7 +1464,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
goto next;
- local_address((struct sock_common *)msk, &msk_local);
+ mptcp_local_address((struct sock_common *)msk, &msk_local);
if (!mptcp_addresses_equal(&msk_local, addr, addr->port))
goto next;
@@ -1558,6 +1531,24 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
return ret;
}
+void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
+{
+ struct mptcp_rm_list alist = { .nr = 0 };
+ struct mptcp_pm_addr_entry *entry;
+
+ list_for_each_entry(entry, rm_list, list) {
+ remove_anno_list_by_saddr(msk, &entry->addr);
+ if (alist.nr < MPTCP_RM_IDS_MAX)
+ alist.ids[alist.nr++] = entry->addr.id;
+ }
+
+ if (alist.nr) {
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_pm_remove_addr(msk, &alist);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+}
+
void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct list_head *rm_list)
{
@@ -1892,18 +1883,50 @@ next:
return ret;
}
+int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
+ u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
+ MPTCP_PM_ADDR_FLAG_FULLMESH;
+ struct mptcp_pm_addr_entry *entry;
+ u8 lookup_by_id = 0;
+
+ if (addr->addr.family == AF_UNSPEC) {
+ lookup_by_id = 1;
+ if (!addr->addr.id)
+ return -EOPNOTSUPP;
+ }
+
+ spin_lock_bh(&pernet->lock);
+ entry = __lookup_addr(pernet, &addr->addr, lookup_by_id);
+ if (!entry) {
+ spin_unlock_bh(&pernet->lock);
+ return -EINVAL;
+ }
+ if ((addr->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
+ (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+ spin_unlock_bh(&pernet->lock);
+ return -EINVAL;
+ }
+
+ changed = (addr->flags ^ entry->flags) & mask;
+ entry->flags = (entry->flags & ~mask) | (addr->flags & mask);
+ *addr = *entry;
+ spin_unlock_bh(&pernet->lock);
+
+ mptcp_nl_set_flags(net, &addr->addr, bkup, changed);
+ return 0;
+}
+
static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
{
- struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry;
struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, };
+ struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, };
struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
- struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
- u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
- MPTCP_PM_ADDR_FLAG_FULLMESH;
struct net *net = sock_net(skb->sk);
- u8 bkup = 0, lookup_by_id = 0;
+ u8 bkup = 0;
int ret;
ret = mptcp_pm_parse_entry(attr, info, false, &addr);
@@ -1918,34 +1941,8 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
bkup = 1;
- if (addr.addr.family == AF_UNSPEC) {
- lookup_by_id = 1;
- if (!addr.addr.id)
- return -EOPNOTSUPP;
- }
- if (token)
- return mptcp_userspace_pm_set_flags(net, token, &addr, &remote, bkup);
-
- spin_lock_bh(&pernet->lock);
- entry = __lookup_addr(pernet, &addr.addr, lookup_by_id);
- if (!entry) {
- spin_unlock_bh(&pernet->lock);
- return -EINVAL;
- }
- if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
- (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
- spin_unlock_bh(&pernet->lock);
- return -EINVAL;
- }
-
- changed = (addr.flags ^ entry->flags) & mask;
- entry->flags = (entry->flags & ~mask) | (addr.flags & mask);
- addr = *entry;
- spin_unlock_bh(&pernet->lock);
-
- mptcp_nl_set_flags(net, &addr.addr, bkup, changed);
- return 0;
+ return mptcp_pm_set_flags(net, token, &addr, &remote, bkup);
}
static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp)
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 27a275805c06..b5a8aa4c1ebd 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -69,6 +69,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
MPTCP_PM_MAX_ADDR_ID + 1,
1);
list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list);
+ msk->pm.local_addr_used++;
ret = e->addr.id;
} else if (match) {
ret = entry->addr.id;
@@ -79,15 +80,37 @@ append_err:
return ret;
}
+/* If the subflow is closed from the other peer (not via a
+ * subflow destroy command then), we want to keep the entry
+ * not to assign the same ID to another address and to be
+ * able to send RM_ADDR after the removal of the subflow.
+ */
+static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk,
+ struct mptcp_pm_addr_entry *addr)
+{
+ struct mptcp_pm_addr_entry *entry, *tmp;
+
+ list_for_each_entry_safe(entry, tmp, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, &addr->addr, false)) {
+ /* TODO: a refcount is needed because the entry can
+ * be used multiple times (e.g. fullmesh mode).
+ */
+ list_del_rcu(&entry->list);
+ kfree(entry);
+ msk->pm.local_addr_used--;
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
+
int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
unsigned int id,
u8 *flags, int *ifindex)
{
struct mptcp_pm_addr_entry *entry, *match = NULL;
- *flags = 0;
- *ifindex = 0;
-
spin_lock_bh(&msk->pm.lock);
list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
if (id == entry->addr.id) {
@@ -170,7 +193,8 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info)
lock_sock((struct sock *)msk);
spin_lock_bh(&msk->pm.lock);
- if (mptcp_pm_alloc_anno_list(msk, &addr_val)) {
+ if (mptcp_pm_alloc_anno_list(msk, &addr_val.addr)) {
+ msk->pm.add_addr_signaled++;
mptcp_pm_announce_addr(msk, &addr_val.addr, false);
mptcp_pm_nl_addr_send_ack(msk);
}
@@ -232,7 +256,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info)
list_move(&match->list, &free_list);
- mptcp_pm_remove_addrs_and_subflows(msk, &free_list);
+ mptcp_pm_remove_addrs(msk, &free_list);
release_sock((struct sock *)msk);
@@ -251,6 +275,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
+ struct mptcp_pm_addr_entry local = { 0 };
struct mptcp_addr_info addr_r;
struct mptcp_addr_info addr_l;
struct mptcp_sock *msk;
@@ -302,12 +327,26 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
goto create_err;
}
+ local.addr = addr_l;
+ err = mptcp_userspace_pm_append_new_local_addr(msk, &local);
+ if (err < 0) {
+ GENL_SET_ERR_MSG(info, "did not match address and id");
+ goto create_err;
+ }
+
lock_sock(sk);
err = __mptcp_subflow_connect(sk, &addr_l, &addr_r);
release_sock(sk);
+ spin_lock_bh(&msk->pm.lock);
+ if (err)
+ mptcp_userspace_pm_delete_local_addr(msk, &local);
+ else
+ msk->pm.subflows++;
+ spin_unlock_bh(&msk->pm.lock);
+
create_err:
sock_put((struct sock *)msk);
return err;
@@ -420,7 +459,11 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info)
ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r);
if (ssk) {
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ struct mptcp_pm_addr_entry entry = { .addr = addr_l };
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_userspace_pm_delete_local_addr(msk, &entry);
+ spin_unlock_bh(&msk->pm.lock);
mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN);
mptcp_close_ssk(sk, ssk, subflow);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 67311e7d5b21..e892673deb73 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -44,7 +44,7 @@ enum {
static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp;
static void __mptcp_destroy_sock(struct sock *sk);
-static void __mptcp_check_send_data_fin(struct sock *sk);
+static void mptcp_check_send_data_fin(struct sock *sk);
DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
static struct net_device mptcp_napi_dev;
@@ -96,6 +96,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
list_add(&subflow->node, &msk->conn_list);
sock_hold(ssock->sk);
subflow->request_mptcp = 1;
+ subflow->subflow_id = msk->subflow_id++;
/* This is the first subflow, always with id 0 */
subflow->local_id_valid = 1;
@@ -377,6 +378,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
/* in sequence */
+ msk->bytes_received += copy_len;
WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
tail = skb_peek_tail(&sk->sk_receive_queue);
if (tail && mptcp_try_coalesce(sk, tail, skb))
@@ -424,8 +426,7 @@ static bool mptcp_pending_data_fin_ack(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- return !__mptcp_check_fallback(msk) &&
- ((1 << sk->sk_state) &
+ return ((1 << sk->sk_state) &
(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
msk->write_seq == READ_ONCE(msk->snd_una);
}
@@ -583,9 +584,6 @@ static bool mptcp_check_data_fin(struct sock *sk)
u64 rcv_data_fin_seq;
bool ret = false;
- if (__mptcp_check_fallback(msk))
- return ret;
-
/* Need to ack a DATA_FIN received from a peer while this side
* of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
* msk->rcv_data_fin was set when parsing the incoming options
@@ -623,7 +621,8 @@ static bool mptcp_check_data_fin(struct sock *sk)
}
ret = true;
- mptcp_send_ack(msk);
+ if (!__mptcp_check_fallback(msk))
+ mptcp_send_ack(msk);
mptcp_close_wake_up(sk);
}
return ret;
@@ -760,6 +759,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
MPTCP_SKB_CB(skb)->map_seq += delta;
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
+ msk->bytes_received += end_seq - msk->ack_seq;
msk->ack_seq = end_seq;
moved = true;
}
@@ -845,17 +845,18 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk)
if (sk->sk_socket && !ssk->sk_socket)
mptcp_sock_graft(ssk, sk->sk_socket);
+ mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++;
mptcp_sockopt_sync_locked(msk, ssk);
mptcp_subflow_joined(msk, ssk);
return true;
}
-static void __mptcp_flush_join_list(struct sock *sk)
+static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list)
{
struct mptcp_subflow_context *tmp, *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
- list_for_each_entry_safe(subflow, tmp, &msk->join_list, node) {
+ list_for_each_entry_safe(subflow, tmp, join_list, node) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast(ssk);
@@ -897,49 +898,6 @@ bool mptcp_schedule_work(struct sock *sk)
return false;
}
-void mptcp_subflow_eof(struct sock *sk)
-{
- if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
- mptcp_schedule_work(sk);
-}
-
-static void mptcp_check_for_eof(struct mptcp_sock *msk)
-{
- struct mptcp_subflow_context *subflow;
- struct sock *sk = (struct sock *)msk;
- int receivers = 0;
-
- mptcp_for_each_subflow(msk, subflow)
- receivers += !subflow->rx_eof;
- if (receivers)
- return;
-
- if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
- /* hopefully temporary hack: propagate shutdown status
- * to msk, when all subflows agree on it
- */
- WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN);
-
- smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
- sk->sk_data_ready(sk);
- }
-
- switch (sk->sk_state) {
- case TCP_ESTABLISHED:
- inet_sk_state_store(sk, TCP_CLOSE_WAIT);
- break;
- case TCP_FIN_WAIT1:
- inet_sk_state_store(sk, TCP_CLOSING);
- break;
- case TCP_FIN_WAIT2:
- inet_sk_state_store(sk, TCP_CLOSE);
- break;
- default:
- return;
- }
- mptcp_close_wake_up(sk);
-}
-
static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow;
@@ -1004,12 +962,6 @@ static void __mptcp_clean_una(struct sock *sk)
struct mptcp_data_frag *dtmp, *dfrag;
u64 snd_una;
- /* on fallback we just need to ignore snd_una, as this is really
- * plain TCP
- */
- if (__mptcp_check_fallback(msk))
- msk->snd_una = READ_ONCE(msk->snd_nxt);
-
snd_una = msk->snd_una;
list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
@@ -1537,8 +1489,10 @@ static void mptcp_update_post_push(struct mptcp_sock *msk,
* that has been handed to the subflow for transmission
* and skip update in case it was old dfrag.
*/
- if (likely(after64(snd_nxt_new, msk->snd_nxt)))
+ if (likely(after64(snd_nxt_new, msk->snd_nxt))) {
+ msk->bytes_sent += snd_nxt_new - msk->snd_nxt;
msk->snd_nxt = snd_nxt_new;
+ }
}
void mptcp_check_and_set_pending(struct sock *sk)
@@ -1609,7 +1563,7 @@ out:
if (!mptcp_timer_pending(sk))
mptcp_reset_timer(sk);
if (do_check_data_fin)
- __mptcp_check_send_data_fin(sk);
+ mptcp_check_send_data_fin(sk);
}
static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first)
@@ -1727,7 +1681,13 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
*copied_syn = 0;
} else if (ret && ret != -EINPROGRESS) {
- mptcp_disconnect(sk, 0);
+ /* The disconnect() op called by tcp_sendmsg_fastopen()/
+ * __inet_stream_connect() can fail, due to looking check,
+ * see mptcp_disconnect().
+ * Attempt it again outside the problematic scope.
+ */
+ if (!mptcp_disconnect(sk, 0))
+ sk->sk_socket->state = SS_UNCONNECTED;
}
inet_sk(sk)->defer_connect = 0;
@@ -2158,9 +2118,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
break;
}
- if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
- mptcp_check_for_eof(msk);
-
if (sk->sk_shutdown & RCV_SHUTDOWN) {
/* race breaker: the shutdown could be after the
* previous receive queue check
@@ -2389,7 +2346,10 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
if (!dispose_it) {
- tcp_disconnect(ssk, 0);
+ /* The MPTCP code never wait on the subflow sockets, TCP-level
+ * disconnect should never fail
+ */
+ WARN_ON_ONCE(tcp_disconnect(ssk, 0));
msk->subflow->state = SS_UNCONNECTED;
mptcp_subflow_ctx_reset(subflow);
release_sock(ssk);
@@ -2408,13 +2368,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
kfree_rcu(subflow, rcu);
} else {
/* otherwise tcp will dispose of the ssk and subflow ctx */
- if (ssk->sk_state == TCP_LISTEN) {
- tcp_set_state(ssk, TCP_CLOSE);
- mptcp_subflow_queue_clean(sk, ssk);
- inet_csk_listen_stop(ssk);
- mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
- }
-
__tcp_close(ssk, 0);
/* close acquired an extra ref */
@@ -2596,6 +2549,7 @@ static void __mptcp_retrans(struct sock *sk)
}
if (copied) {
dfrag->already_sent = max(dfrag->already_sent, info.sent);
+ msk->bytes_retrans += copied;
tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
info.size_goal);
WRITE_ONCE(msk->allow_infinite_fallback, false);
@@ -2654,6 +2608,7 @@ static void mptcp_do_fastclose(struct sock *sk)
struct mptcp_subflow_context *subflow, *tmp;
struct mptcp_sock *msk = mptcp_sk(sk);
+ inet_sk_state_store(sk, TCP_CLOSE);
mptcp_for_each_subflow_safe(msk, subflow, tmp)
__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow),
subflow, MPTCP_CF_FASTCLOSE);
@@ -2671,16 +2626,12 @@ static void mptcp_worker(struct work_struct *work)
if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN)))
goto unlock;
- mptcp_check_data_fin_ack(sk);
-
mptcp_check_fastclose(msk);
mptcp_pm_nl_work(msk);
- if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
- mptcp_check_for_eof(msk);
-
- __mptcp_check_send_data_fin(sk);
+ mptcp_check_send_data_fin(sk);
+ mptcp_check_data_fin_ack(sk);
mptcp_check_data_fin(sk);
if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
@@ -2691,10 +2642,9 @@ static void mptcp_worker(struct work_struct *work)
* even if it is orphaned and in FIN_WAIT2 state
*/
if (sock_flag(sk, SOCK_DEAD)) {
- if (mptcp_should_close(sk)) {
- inet_sk_state_store(sk, TCP_CLOSE);
+ if (mptcp_should_close(sk))
mptcp_do_fastclose(sk);
- }
+
if (sk->sk_state == TCP_CLOSE) {
__mptcp_destroy_sock(sk);
goto unlock;
@@ -2733,6 +2683,7 @@ static int __mptcp_init_sock(struct sock *sk)
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
WRITE_ONCE(msk->allow_infinite_fallback, true);
msk->recovery = false;
+ msk->subflow_id = 1;
mptcp_pm_data_init(msk);
@@ -2812,13 +2763,19 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
break;
fallthrough;
case TCP_SYN_SENT:
- tcp_disconnect(ssk, O_NONBLOCK);
+ WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK));
break;
default:
if (__mptcp_check_fallback(mptcp_sk(sk))) {
pr_debug("Fallback");
ssk->sk_shutdown |= how;
tcp_shutdown(ssk, how);
+
+ /* simulate the data_fin ack reception to let the state
+ * machine move forward
+ */
+ WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
+ mptcp_schedule_work(sk);
} else {
pr_debug("Sending DATA_FIN on subflow %p", ssk);
tcp_send_ack(ssk);
@@ -2858,7 +2815,7 @@ static int mptcp_close_state(struct sock *sk)
return next & TCP_ACTION_FIN;
}
-static void __mptcp_check_send_data_fin(struct sock *sk)
+static void mptcp_check_send_data_fin(struct sock *sk)
{
struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -2876,19 +2833,6 @@ static void __mptcp_check_send_data_fin(struct sock *sk)
WRITE_ONCE(msk->snd_nxt, msk->write_seq);
- /* fallback socket will not get data_fin/ack, can move to the next
- * state now
- */
- if (__mptcp_check_fallback(msk)) {
- WRITE_ONCE(msk->snd_una, msk->write_seq);
- if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
- inet_sk_state_store(sk, TCP_CLOSE);
- mptcp_close_wake_up(sk);
- } else if (sk->sk_state == TCP_FIN_WAIT1) {
- inet_sk_state_store(sk, TCP_FIN_WAIT2);
- }
- }
-
mptcp_for_each_subflow(msk, subflow) {
struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
@@ -2908,7 +2852,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
WRITE_ONCE(msk->snd_data_fin_enable, 1);
- __mptcp_check_send_data_fin(sk);
+ mptcp_check_send_data_fin(sk);
}
static void __mptcp_destroy_sock(struct sock *sk)
@@ -2936,7 +2880,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
void __mptcp_unaccepted_force_close(struct sock *sk)
{
sock_set_flag(sk, SOCK_DEAD);
- inet_sk_state_store(sk, TCP_CLOSE);
mptcp_do_fastclose(sk);
__mptcp_destroy_sock(sk);
}
@@ -2953,10 +2896,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
return EPOLLIN | EPOLLRDNORM;
}
-static void mptcp_listen_inuse_dec(struct sock *sk)
+static void mptcp_check_listen_stop(struct sock *sk)
{
- if (inet_sk_state_load(sk) == TCP_LISTEN)
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ struct sock *ssk;
+
+ if (inet_sk_state_load(sk) != TCP_LISTEN)
+ return;
+
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ ssk = mptcp_sk(sk)->first;
+ if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN))
+ return;
+
+ lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+ mptcp_subflow_queue_clean(sk, ssk);
+ inet_csk_listen_stop(ssk);
+ mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
+ tcp_set_state(ssk, TCP_CLOSE);
+ release_sock(ssk);
}
bool __mptcp_close(struct sock *sk, long timeout)
@@ -2969,7 +2926,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK);
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
- mptcp_listen_inuse_dec(sk);
+ mptcp_check_listen_stop(sk);
inet_sk_state_store(sk, TCP_CLOSE);
goto cleanup;
}
@@ -2978,7 +2935,6 @@ bool __mptcp_close(struct sock *sk, long timeout)
/* If the msk has read data, or the caller explicitly ask it,
* do the MPTCP equivalent of TCP reset, aka MPTCP fastclose
*/
- inet_sk_state_store(sk, TCP_CLOSE);
mptcp_do_fastclose(sk);
timeout = 0;
} else if (mptcp_close_state(sk)) {
@@ -3073,15 +3029,20 @@ static int mptcp_disconnect(struct sock *sk, int flags)
{
struct mptcp_sock *msk = mptcp_sk(sk);
+ /* Deny disconnect if other threads are blocked in sk_wait_event()
+ * or inet_wait_for_connect().
+ */
+ if (sk->sk_wait_pending)
+ return -EBUSY;
+
/* We are on the fastopen error path. We can't call straight into the
* subflows cleanup code due to lock nesting (we are already under
- * msk->firstsocket lock). Do nothing and leave the cleanup to the
- * caller.
+ * msk->firstsocket lock).
*/
if (msk->fastopening)
- return 0;
+ return -EBUSY;
- mptcp_listen_inuse_dec(sk);
+ mptcp_check_listen_stop(sk);
inet_sk_state_store(sk, TCP_CLOSE);
mptcp_stop_timer(sk);
@@ -3108,6 +3069,10 @@ static int mptcp_disconnect(struct sock *sk, int flags)
WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
mptcp_pm_data_reset(msk);
mptcp_ca_reset(sk);
+ msk->bytes_acked = 0;
+ msk->bytes_received = 0;
+ msk->bytes_sent = 0;
+ msk->bytes_retrans = 0;
WRITE_ONCE(sk->sk_shutdown, 0);
sk_error_report(sk);
@@ -3140,6 +3105,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
#endif
+ nsk->sk_wait_pending = 0;
__mptcp_init_sock(nsk);
msk = mptcp_sk(nsk);
@@ -3157,6 +3123,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
+ /* passive msk is created after the first/MPC subflow */
+ msk->subflow_id = 2;
+
sock_reset_flag(nsk, SOCK_RCU_FREE);
security_inet_csk_clone(nsk, req);
@@ -3327,9 +3296,14 @@ static void mptcp_release_cb(struct sock *sk)
for (;;) {
unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) |
msk->push_pending;
+ struct list_head join_list;
+
if (!flags)
break;
+ INIT_LIST_HEAD(&join_list);
+ list_splice_init(&msk->join_list, &join_list);
+
/* the following actions acquire the subflow socket lock
*
* 1) can't be invoked in atomic scope
@@ -3340,8 +3314,9 @@ static void mptcp_release_cb(struct sock *sk)
msk->push_pending = 0;
msk->cb_flags &= ~flags;
spin_unlock_bh(&sk->sk_lock.slock);
+
if (flags & BIT(MPTCP_FLUSH_JOIN_LIST))
- __mptcp_flush_join_list(sk);
+ __mptcp_flush_join_list(sk, &join_list);
if (flags & BIT(MPTCP_PUSH_PENDING))
__mptcp_push_pending(sk, 0);
if (flags & BIT(MPTCP_RETRANSMIT))
@@ -3570,11 +3545,10 @@ static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v)
return (int)delta;
}
-static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int mptcp_ioctl(struct sock *sk, int cmd, int *karg)
{
struct mptcp_sock *msk = mptcp_sk(sk);
bool slow;
- int answ;
switch (cmd) {
case SIOCINQ:
@@ -3583,24 +3557,24 @@ static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
lock_sock(sk);
__mptcp_move_skbs(msk);
- answ = mptcp_inq_hint(sk);
+ *karg = mptcp_inq_hint(sk);
release_sock(sk);
break;
case SIOCOUTQ:
slow = lock_sock_fast(sk);
- answ = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una));
+ *karg = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una));
unlock_sock_fast(sk, slow);
break;
case SIOCOUTQNSD:
slow = lock_sock_fast(sk);
- answ = mptcp_ioctl_outq(msk, msk->snd_nxt);
+ *karg = mptcp_ioctl_outq(msk, msk->snd_nxt);
unlock_sock_fast(sk, slow);
break;
default:
return -ENOIOCTLCMD;
}
- return put_user(answ, (int __user *)arg);
+ return 0;
}
static void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
@@ -3758,6 +3732,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
{
struct mptcp_sock *msk = mptcp_sk(sock->sk);
struct socket *ssock;
+ struct sock *newsk;
int err;
pr_debug("msk=%p", msk);
@@ -3769,17 +3744,20 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
if (!ssock)
return -EINVAL;
- err = ssock->ops->accept(sock, newsock, flags, kern);
- if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) {
- struct mptcp_sock *msk = mptcp_sk(newsock->sk);
+ newsk = mptcp_accept(sock->sk, flags, &err, kern);
+ if (!newsk)
+ return err;
+
+ lock_sock(newsk);
+
+ __inet_accept(sock, newsock, newsk);
+ if (!mptcp_is_tcpsk(newsock->sk)) {
+ struct mptcp_sock *msk = mptcp_sk(newsk);
struct mptcp_subflow_context *subflow;
- struct sock *newsk = newsock->sk;
set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags);
msk->in_accept_queue = 0;
- lock_sock(newsk);
-
/* set ssk->sk_socket of accept()ed flows to mptcp socket.
* This is needed so NOSPACE flag can be set from tcp stack.
*/
@@ -3800,11 +3778,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
if (unlikely(list_empty(&msk->conn_list)))
inet_sk_state_store(newsk, TCP_CLOSE);
}
-
- release_sock(newsk);
}
+ release_sock(newsk);
- return err;
+ return 0;
}
static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
@@ -3889,7 +3866,6 @@ static const struct proto_ops mptcp_stream_ops = {
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
};
static struct inet_protosw mptcp_protosw = {
@@ -3984,7 +3960,6 @@ static const struct proto_ops mptcp_v6_stream_ops = {
.sendmsg = inet6_sendmsg,
.recvmsg = inet6_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
.compat_ioctl = inet6_compat_ioctl,
#endif
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c5255258bfb3..37fbe22e2433 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -113,7 +113,6 @@
/* MPTCP socket atomic flags */
#define MPTCP_NOSPACE 1
#define MPTCP_WORK_RTX 2
-#define MPTCP_WORK_EOF 3
#define MPTCP_FALLBACK_DONE 4
#define MPTCP_WORK_CLOSE_SUBFLOW 5
@@ -262,10 +261,13 @@ struct mptcp_sock {
u64 local_key;
u64 remote_key;
u64 write_seq;
+ u64 bytes_sent;
u64 snd_nxt;
+ u64 bytes_received;
u64 ack_seq;
atomic64_t rcv_wnd_sent;
u64 rcv_data_fin_seq;
+ u64 bytes_retrans;
int rmem_fwd_alloc;
struct sock *last_snd;
int snd_burst;
@@ -274,6 +276,7 @@ struct mptcp_sock {
* recovery related fields are under data_lock
* protection
*/
+ u64 bytes_acked;
u64 snd_una;
u64 wnd_end;
unsigned long timer_ival;
@@ -319,7 +322,8 @@ struct mptcp_sock {
u64 rtt_us; /* last maximum rtt of subflows */
} rcvq_space;
- u32 setsockopt_seq;
+ u32 subflow_id;
+ u32 setsockopt_seq;
char ca_name[TCP_CA_NAME_MAX];
struct mptcp_sock *dl_next;
};
@@ -476,14 +480,13 @@ struct mptcp_subflow_context {
send_mp_fail : 1,
send_fastclose : 1,
send_infinite_map : 1,
- rx_eof : 1,
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 */
is_mptfo : 1, /* subflow is doing TFO */
- __unused : 8;
+ __unused : 9;
enum mptcp_data_avail data_avail;
u32 remote_nonce;
u64 thmac;
@@ -500,6 +503,8 @@ struct mptcp_subflow_context {
u8 reset_reason:4;
u8 stale_count;
+ u32 subflow_id;
+
long delegated_status;
unsigned long fail_tout;
@@ -638,6 +643,7 @@ 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);
+void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr);
/* called with sk socket lock held */
int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
@@ -720,7 +726,6 @@ static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit)
void __mptcp_check_push(struct sock *sk, struct sock *ssk);
void __mptcp_data_acked(struct sock *sk);
void __mptcp_error_report(struct sock *sk);
-void mptcp_subflow_eof(struct sock *sk);
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
{
@@ -809,7 +814,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct mptcp_addr_info *rem,
u8 bkup);
bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
- const struct mptcp_pm_addr_entry *entry);
+ const struct mptcp_addr_info *addr);
void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
struct mptcp_pm_add_entry *
@@ -821,9 +826,15 @@ mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
unsigned int id,
u8 *flags, int *ifindex);
+int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
+ u8 *flags, int *ifindex);
int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
unsigned int id,
u8 *flags, int *ifindex);
+int mptcp_pm_set_flags(struct net *net, struct nlattr *token,
+ struct mptcp_pm_addr_entry *loc,
+ struct mptcp_pm_addr_entry *rem, u8 bkup);
+int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup);
int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token,
struct mptcp_pm_addr_entry *loc,
struct mptcp_pm_addr_entry *rem, u8 bkup);
@@ -832,6 +843,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
bool echo);
int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
+void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);
void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct list_head *rm_list);
@@ -915,13 +927,13 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
struct mptcp_rm_list *rm_list);
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
+int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
const struct mptcp_rm_list *rm_list);
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index d4258869ac48..63f7a09335c5 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -14,7 +14,8 @@
#include <net/mptcp.h>
#include "protocol.h"
-#define MIN_INFO_OPTLEN_SIZE 16
+#define MIN_INFO_OPTLEN_SIZE 16
+#define MIN_FULL_INFO_OPTLEN_SIZE 40
static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk)
{
@@ -355,6 +356,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
case SO_BROADCAST:
case SO_BSDCOMPAT:
case SO_PASSCRED:
+ case SO_PASSPIDFD:
case SO_PASSSEC:
case SO_RXQ_OVFL:
case SO_WIFI_STATUS:
@@ -888,7 +890,9 @@ out:
void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
{
+ struct sock *sk = (struct sock *)msk;
u32 flags = 0;
+ bool slow;
memset(info, 0, sizeof(*info));
@@ -897,6 +901,9 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted);
info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used);
+ if (inet_sk_state_load(sk) == TCP_LISTEN)
+ return;
+
/* The following limits only make sense for the in-kernel PM */
if (mptcp_pm_is_kernel(msk)) {
info->mptcpi_subflows_max =
@@ -914,11 +921,21 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info)
if (READ_ONCE(msk->can_ack))
flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED;
info->mptcpi_flags = flags;
- info->mptcpi_token = READ_ONCE(msk->token);
- info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
- info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
- info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
- info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled);
+ mptcp_data_lock(sk);
+ info->mptcpi_snd_una = msk->snd_una;
+ info->mptcpi_rcv_nxt = msk->ack_seq;
+ info->mptcpi_bytes_acked = msk->bytes_acked;
+ mptcp_data_unlock(sk);
+
+ slow = lock_sock_fast(sk);
+ info->mptcpi_csum_enabled = msk->csum_enabled;
+ info->mptcpi_token = msk->token;
+ info->mptcpi_write_seq = msk->write_seq;
+ info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits;
+ info->mptcpi_bytes_sent = msk->bytes_sent;
+ info->mptcpi_bytes_received = msk->bytes_received;
+ info->mptcpi_bytes_retrans = msk->bytes_retrans;
+ unlock_sock_fast(sk, slow);
}
EXPORT_SYMBOL_GPL(mptcp_diag_fill_info);
@@ -965,7 +982,8 @@ static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd,
}
static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd,
- char __user *optval, int __user *optlen)
+ char __user *optval,
+ int __user *optlen)
{
int len, copylen;
@@ -1146,6 +1164,125 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *o
return 0;
}
+static int mptcp_get_full_info(struct mptcp_full_info *mfi,
+ char __user *optval,
+ int __user *optlen)
+{
+ int len;
+
+ BUILD_BUG_ON(offsetof(struct mptcp_full_info, mptcp_info) !=
+ MIN_FULL_INFO_OPTLEN_SIZE);
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ if (len < MIN_FULL_INFO_OPTLEN_SIZE)
+ return -EINVAL;
+
+ memset(mfi, 0, sizeof(*mfi));
+ if (copy_from_user(mfi, optval, MIN_FULL_INFO_OPTLEN_SIZE))
+ return -EFAULT;
+
+ if (mfi->size_tcpinfo_kernel ||
+ mfi->size_sfinfo_kernel ||
+ mfi->num_subflows)
+ return -EINVAL;
+
+ if (mfi->size_sfinfo_user > INT_MAX ||
+ mfi->size_tcpinfo_user > INT_MAX)
+ return -EINVAL;
+
+ return len - MIN_FULL_INFO_OPTLEN_SIZE;
+}
+
+static int mptcp_put_full_info(struct mptcp_full_info *mfi,
+ char __user *optval,
+ u32 copylen,
+ int __user *optlen)
+{
+ copylen += MIN_FULL_INFO_OPTLEN_SIZE;
+ if (put_user(copylen, optlen))
+ return -EFAULT;
+
+ if (copy_to_user(optval, mfi, copylen))
+ return -EFAULT;
+ return 0;
+}
+
+static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optval,
+ int __user *optlen)
+{
+ unsigned int sfcount = 0, copylen = 0;
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ void __user *tcpinfoptr, *sfinfoptr;
+ struct mptcp_full_info mfi;
+ int len;
+
+ len = mptcp_get_full_info(&mfi, optval, optlen);
+ if (len < 0)
+ return len;
+
+ /* don't bother filling the mptcp info if there is not enough
+ * user-space-provided storage
+ */
+ if (len > 0) {
+ mptcp_diag_fill_info(msk, &mfi.mptcp_info);
+ copylen += min_t(unsigned int, len, sizeof(struct mptcp_info));
+ }
+
+ mfi.size_tcpinfo_kernel = sizeof(struct tcp_info);
+ mfi.size_tcpinfo_user = min_t(unsigned int, mfi.size_tcpinfo_user,
+ sizeof(struct tcp_info));
+ sfinfoptr = u64_to_user_ptr(mfi.subflow_info);
+ mfi.size_sfinfo_kernel = sizeof(struct mptcp_subflow_info);
+ mfi.size_sfinfo_user = min_t(unsigned int, mfi.size_sfinfo_user,
+ sizeof(struct mptcp_subflow_info));
+ tcpinfoptr = u64_to_user_ptr(mfi.tcp_info);
+
+ lock_sock(sk);
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ struct mptcp_subflow_info sfinfo;
+ struct tcp_info tcp_info;
+
+ if (sfcount++ >= mfi.size_arrays_user)
+ continue;
+
+ /* fetch addr/tcp_info only if the user space buffers
+ * are wide enough
+ */
+ memset(&sfinfo, 0, sizeof(sfinfo));
+ sfinfo.id = subflow->subflow_id;
+ if (mfi.size_sfinfo_user >
+ offsetof(struct mptcp_subflow_info, addrs))
+ mptcp_get_sub_addrs(ssk, &sfinfo.addrs);
+ if (copy_to_user(sfinfoptr, &sfinfo, mfi.size_sfinfo_user))
+ goto fail_release;
+
+ if (mfi.size_tcpinfo_user) {
+ tcp_get_info(ssk, &tcp_info);
+ if (copy_to_user(tcpinfoptr, &tcp_info,
+ mfi.size_tcpinfo_user))
+ goto fail_release;
+ }
+
+ tcpinfoptr += mfi.size_tcpinfo_user;
+ sfinfoptr += mfi.size_sfinfo_user;
+ }
+ release_sock(sk);
+
+ mfi.num_subflows = sfcount;
+ if (mptcp_put_full_info(&mfi, optval, copylen, optlen))
+ return -EFAULT;
+
+ return 0;
+
+fail_release:
+ release_sock(sk);
+ return -EFAULT;
+}
+
static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
int __user *optlen, int val)
{
@@ -1219,6 +1356,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname,
switch (optname) {
case MPTCP_INFO:
return mptcp_getsockopt_info(msk, optval, optlen);
+ case MPTCP_FULL_INFO:
+ return mptcp_getsockopt_full_info(msk, optval, optlen);
case MPTCP_TCPINFO:
return mptcp_getsockopt_tcpinfo(msk, optval, optlen);
case MPTCP_SUBFLOW_ADDRS:
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 4688daa6b38b..9ee3b7abbaf6 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -819,6 +819,7 @@ create_child:
if (!ctx->conn)
goto fallback;
+ ctx->subflow_id = 1;
owner = mptcp_sk(ctx->conn);
mptcp_pm_new_connection(owner, child, 1);
@@ -1574,6 +1575,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
subflow->remote_id = remote_id;
subflow->request_join = 1;
subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ subflow->subflow_id = msk->subflow_id++;
mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
sock_hold(ssk);
@@ -1668,6 +1670,10 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING);
+ err = security_mptcp_add_subflow(sk, sf->sk);
+ if (err)
+ goto release_ssk;
+
/* the newly created socket has to be in the same cgroup as its parent */
mptcp_attach_cgroup(sk, sf->sk);
@@ -1680,6 +1686,8 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
sock_inuse_add(net, 1);
err = tcp_set_ulp(sf->sk, "mptcp");
+
+release_ssk:
release_sock(sf->sk);
if (err) {
@@ -1749,14 +1757,16 @@ static void subflow_state_change(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct sock *parent = subflow->conn;
+ struct mptcp_sock *msk;
__subflow_state_change(sk);
+ msk = mptcp_sk(parent);
if (subflow_simultaneous_connect(sk)) {
mptcp_propagate_sndbuf(parent, sk);
mptcp_do_fallback(sk);
- mptcp_rcv_space_init(mptcp_sk(parent), sk);
- pr_fallback(mptcp_sk(parent));
+ mptcp_rcv_space_init(msk, sk);
+ pr_fallback(msk);
subflow->conn_finished = 1;
mptcp_set_connected(parent);
}
@@ -1772,11 +1782,12 @@ static void subflow_state_change(struct sock *sk)
subflow_sched_work_if_closed(mptcp_sk(parent), sk);
- if (__mptcp_check_fallback(mptcp_sk(parent)) &&
- !subflow->rx_eof && subflow_is_done(sk)) {
- subflow->rx_eof = 1;
- mptcp_subflow_eof(parent);
- }
+ /* when the fallback subflow closes the rx side, trigger a 'dummy'
+ * ingress data fin, so that the msk state will follow along
+ */
+ if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
+ mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
+ mptcp_schedule_work(parent);
}
void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
Powered by cgit, Gruvboxed by Blaster4385.