summaryrefslogtreecommitdiff
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/diag.c2
-rw-r--r--net/mptcp/mib.c2
-rw-r--r--net/mptcp/mib.h2
-rw-r--r--net/mptcp/options.c5
-rw-r--r--net/mptcp/pm.c12
-rw-r--r--net/mptcp/pm_netlink.c93
-rw-r--r--net/mptcp/pm_userspace.c18
-rw-r--r--net/mptcp/protocol.c18
-rw-r--r--net/mptcp/protocol.h4
-rw-r--r--net/mptcp/subflow.c26
10 files changed, 141 insertions, 41 deletions
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index 3ae46b545d2c..2d3efb405437 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk)
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
- nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
+ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */
nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index c30405e76833..7884217f33eb 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
+ SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
+ SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 2704afd0dfe4..66aa67f49d03 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -14,7 +14,9 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */
MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */
MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */
+ MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */
+ MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */
MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */
MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */
MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8e8dcfbc2993..ac2f1a54cc43 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
return true;
} else if (subflow_req->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
- opts->backup = subflow_req->backup;
+ opts->backup = subflow_req->request_bkup;
opts->join_id = subflow_req->local_id;
opts->thmac = subflow_req->thmac;
opts->nonce = subflow_req->local_nonce;
@@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
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))) {
+ ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) &&
+ (!mp_opt->echo || subflow->mp_join)))) {
/* subflows are fully established as soon as we get any
* additional ack, including ADD_ADDR.
*/
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 55406720c607..23bb89c94e90 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -426,6 +426,18 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
return mptcp_pm_nl_get_local_id(msk, &skc_local);
}
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
+{
+ struct mptcp_addr_info skc_local;
+
+ mptcp_local_address((struct sock_common *)skc, &skc_local);
+
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_is_backup(msk, &skc_local);
+
+ return mptcp_pm_nl_is_backup(msk, &skc_local);
+}
+
int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
u8 *flags, int *ifindex)
{
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index ea9e5817b9e9..4cae2aa7be5c 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -348,7 +348,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
if (add_entry) {
- if (mptcp_pm_is_kernel(msk))
+ if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
return false;
sk_reset_timer(sk, &add_entry->add_timer,
@@ -471,7 +471,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
slow = lock_sock_fast(ssk);
if (prio) {
subflow->send_mp_prio = 1;
- subflow->backup = backup;
subflow->request_bkup = backup;
}
@@ -513,8 +512,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
{
+ struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL;
struct sock *sk = (struct sock *)msk;
- struct mptcp_pm_addr_entry *local;
unsigned int add_addr_signal_max;
unsigned int local_addr_max;
struct pm_nl_pernet *pernet;
@@ -556,8 +555,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
/* check first for announce */
if (msk->pm.add_addr_signaled < add_addr_signal_max) {
- local = select_signal_address(pernet, msk);
-
/* due to racing events on both ends we can reach here while
* previous add address is still running: if we invoke now
* mptcp_pm_announce_addr(), that will fail and the
@@ -568,16 +565,26 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
return;
- if (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);
- mptcp_pm_nl_addr_send_ack(msk);
- }
- }
+ local = select_signal_address(pernet, msk);
+ if (!local)
+ goto subflow;
+
+ /* If the alloc fails, we are on memory pressure, not worth
+ * continuing, and trying to create subflows.
+ */
+ if (!mptcp_pm_alloc_anno_list(msk, &local->addr))
+ return;
+
+ __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+ msk->pm.add_addr_signaled++;
+ mptcp_pm_announce_addr(msk, &local->addr, false);
+ mptcp_pm_nl_addr_send_ack(msk);
+
+ if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+ signal_and_subflow = local;
}
+subflow:
/* check if should create a new subflow */
while (msk->pm.local_addr_used < local_addr_max &&
msk->pm.subflows < subflows_max) {
@@ -585,9 +592,14 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
bool fullmesh;
int i, nr;
- local = select_local_address(pernet, msk);
- if (!local)
- break;
+ if (signal_and_subflow) {
+ local = signal_and_subflow;
+ signal_and_subflow = NULL;
+ } else {
+ local = select_local_address(pernet, msk);
+ if (!local)
+ break;
+ }
fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
@@ -1102,6 +1114,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
return ret;
}
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+{
+ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return backup;
+}
+
#define MPTCP_PM_CMD_GRP_OFFSET 0
#define MPTCP_PM_EV_GRP_OFFSET 1
@@ -1311,8 +1341,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
if (ret < 0)
return ret;
- if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
- GENL_SET_ERR_MSG(info, "flags must have signal when using port");
+ if (addr.addr.port && !address_use_port(&addr)) {
+ GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port");
return -EINVAL;
}
@@ -1401,6 +1431,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
ret = remove_anno_list_by_saddr(msk, addr);
if (ret || force) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= ret;
mptcp_pm_remove_addr(msk, &list);
spin_unlock_bh(&msk->pm.lock);
}
@@ -1534,16 +1565,25 @@ 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;
+ int anno_nr = 0;
list_for_each_entry(entry, rm_list, list) {
- if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
- lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
- alist.nr < MPTCP_RM_IDS_MAX)
- alist.ids[alist.nr++] = entry->addr.id;
+ if (alist.nr >= MPTCP_RM_IDS_MAX)
+ break;
+
+ /* only delete if either announced or matching a subflow */
+ if (remove_anno_list_by_saddr(msk, &entry->addr))
+ anno_nr++;
+ else if (!lookup_subflow_by_saddr(&msk->conn_list,
+ &entry->addr))
+ continue;
+
+ alist.ids[alist.nr++] = entry->addr.id;
}
if (alist.nr) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= anno_nr;
mptcp_pm_remove_addr(msk, &alist);
spin_unlock_bh(&msk->pm.lock);
}
@@ -1556,17 +1596,18 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
struct mptcp_pm_addr_entry *entry;
list_for_each_entry(entry, rm_list, list) {
- if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
- slist.nr < MPTCP_RM_IDS_MAX)
+ if (slist.nr < MPTCP_RM_IDS_MAX &&
+ lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
slist.ids[slist.nr++] = entry->addr.id;
- if (remove_anno_list_by_saddr(msk, &entry->addr) &&
- alist.nr < MPTCP_RM_IDS_MAX)
+ if (alist.nr < MPTCP_RM_IDS_MAX &&
+ remove_anno_list_by_saddr(msk, &entry->addr))
alist.ids[alist.nr++] = entry->addr.id;
}
if (alist.nr) {
spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= alist.nr;
mptcp_pm_remove_addr(msk, &alist);
spin_unlock_bh(&msk->pm.lock);
}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index f0a4590506c6..8eaa9fbe3e34 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -165,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
}
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+ struct mptcp_addr_info *skc)
+{
+ struct mptcp_pm_addr_entry *entry;
+ bool backup = false;
+
+ spin_lock_bh(&msk->pm.lock);
+ list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+ if (mptcp_addresses_equal(&entry->addr, skc, false)) {
+ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+ break;
+ }
+ }
+ spin_unlock_bh(&msk->pm.lock);
+
+ return backup;
+}
+
int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index a26c2c840fd9..0d536b183a6c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
skb_orphan(skb);
/* try to fetch required memory from subflow */
- if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
+ if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
goto drop;
+ }
has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
@@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
- if (__mptcp_rmem(sk) > sk_rbuf) {
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+ if (__mptcp_rmem(sk) > sk_rbuf)
return;
- }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
@@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
mptcp_for_each_subflow(msk, subflow) {
+ bool backup = subflow->backup || subflow->request_bkup;
+
trace_mptcp_subflow_get_send(subflow);
ssk = mptcp_subflow_tcp_sock(subflow);
if (!mptcp_subflow_active(subflow))
continue;
tout = max(tout, mptcp_timeout_from_subflow(subflow));
- nr_active += !subflow->backup;
+ nr_active += !backup;
pace = subflow->avg_pacing_rate;
if (unlikely(!pace)) {
/* init pacing rate from socket */
@@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
}
linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
- if (linger_time < send_info[subflow->backup].linger_time) {
- send_info[subflow->backup].ssk = ssk;
- send_info[subflow->backup].linger_time = linger_time;
+ if (linger_time < send_info[backup].linger_time) {
+ send_info[backup].ssk = ssk;
+ send_info[backup].linger_time = linger_time;
}
}
__mptcp_set_timeout(sk, tout);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index b11a4e50d52b..60c6b073d65f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -448,6 +448,7 @@ struct mptcp_subflow_request_sock {
u16 mp_capable : 1,
mp_join : 1,
backup : 1,
+ request_bkup : 1,
csum_reqd : 1,
allow_join_id0 : 1;
u8 local_id;
@@ -1108,6 +1109,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
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);
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
struct netlink_callback *cb);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 39e2cbdf3801..a21c712350c3 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
return NULL;
}
subflow_req->local_id = local_id;
+ subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
return msk;
}
@@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req,
return 0;
} else if (opt_mp_join) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+
+ if (mp_opt.backup)
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
}
if (opt_mp_capable && listener->request_mptcp) {
@@ -577,6 +581,9 @@ 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->backup)
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
+
if (subflow_use_different_dport(msk, sk)) {
pr_debug("synack inet_dport=%d %d",
ntohs(inet_sk(sk)->inet_dport),
@@ -614,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk)
return err;
subflow_set_local_id(subflow, err);
+ subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
+
return 0;
}
@@ -1221,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
- u32 incr;
+ struct tcp_sock *tp = tcp_sk(ssk);
+ u32 offset, incr, avail_len;
- incr = limit >= skb->len ? skb->len + fin : limit;
+ offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
+ if (WARN_ON_ONCE(offset > skb->len))
+ goto out;
- pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
- subflow->map_subflow_seq);
+ avail_len = skb->len - offset;
+ incr = limit >= avail_len ? avail_len + fin : limit;
+
+ pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
+ offset, subflow->map_subflow_seq);
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
tcp_sk(ssk)->copied_seq += incr;
+
+out:
if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
sk_eat_skb(ssk, skb);
if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
@@ -2005,6 +2022,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
new_ctx->fully_established = 1;
new_ctx->remote_key_valid = 1;
new_ctx->backup = subflow_req->backup;
+ new_ctx->request_bkup = subflow_req->request_bkup;
WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
new_ctx->token = subflow_req->token;
new_ctx->thmac = subflow_req->thmac;
generated by cgit (git 2.34.1) at 2025-05-15 20:35:18 +0000