summaryrefslogtreecommitdiffstats
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/mib.c1
-rw-r--r--net/mptcp/mib.h1
-rw-r--r--net/mptcp/mptcp_diag.c6
-rw-r--r--net/mptcp/options.c19
-rw-r--r--net/mptcp/pm_netlink.c1
-rw-r--r--net/mptcp/protocol.c12
-rw-r--r--net/mptcp/protocol.h10
-rw-r--r--net/mptcp/sockopt.c68
-rw-r--r--net/mptcp/subflow.c11
-rw-r--r--net/mptcp/syncookies.c16
10 files changed, 102 insertions, 43 deletions
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 52ea2517e856..ff2cc0e3273d 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -44,6 +44,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
+ SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
SNMP_MIB_SENTINEL
};
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 193466c9b549..0663cb12b448 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -37,6 +37,7 @@ enum linux_mptcp_mib_field {
MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */
MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */
MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */
+ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */
__MPTCP_MIB_MAX
};
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 8f88ddeab6a2..f48eb6315bbb 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -57,10 +57,8 @@ static int mptcp_diag_dump_one(struct netlink_callback *cb,
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
sock_put(sk);
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index b5850afea343..4452455aef7f 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1035,7 +1035,8 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
return hmac == mp_opt->ahmac;
}
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
+/* Return false if a subflow has been reset, else return true */
+bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
@@ -1053,12 +1054,16 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
__mptcp_check_push(subflow->conn, sk);
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
- return;
+ return true;
}
mptcp_get_options(sk, skb, &mp_opt);
+
+ /* The subflow can be in close state only if check_fully_established()
+ * just sent a reset. If so, tell the caller to ignore the current packet.
+ */
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
- return;
+ return sk->sk_state != TCP_CLOSE;
if (mp_opt.fastclose &&
msk->local_key == mp_opt.rcvr_key) {
@@ -1100,7 +1105,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
}
if (!mp_opt.dss)
- return;
+ return true;
/* we can't wait for recvmsg() to update the ack_seq, otherwise
* monodirectional flows will stuck
@@ -1119,12 +1124,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
schedule_work(&msk->work))
sock_hold(subflow->conn);
- return;
+ return true;
}
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
- return;
+ return true;
memset(mpext, 0, sizeof(*mpext));
@@ -1153,6 +1158,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
if (mpext->csum_reqd)
mpext->csum = mp_opt.csum;
}
+
+ return true;
}
static void mptcp_set_rwin(const struct tcp_sock *tp)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index d2591ebf01d9..56263c2c4014 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -27,7 +27,6 @@ struct mptcp_pm_addr_entry {
struct mptcp_addr_info addr;
u8 flags;
int ifindex;
- struct rcu_head rcu;
struct socket *lsk;
};
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7a5afa8c6866..a88924947815 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -474,7 +474,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
bool cleanup, rx_empty;
cleanup = (space > 0) && (space >= (old_space << 1));
- rx_empty = !atomic_read(&sk->sk_rmem_alloc);
+ rx_empty = !__mptcp_rmem(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -720,8 +720,10 @@ 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 (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
+ if (__mptcp_rmem(sk) > sk_rbuf) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
return;
+ }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
@@ -1754,7 +1756,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
if (!(flags & MSG_PEEK)) {
/* we will bulk release the skb memory later */
skb->destructor = NULL;
- msk->rmem_released += skb->truesize;
+ WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
__skb_unlink(skb, &msk->receive_queue);
__kfree_skb(skb);
}
@@ -1873,7 +1875,7 @@ static void __mptcp_update_rmem(struct sock *sk)
atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
sk_mem_uncharge(sk, msk->rmem_released);
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
}
static void __mptcp_splice_receive_queue(struct sock *sk)
@@ -2380,7 +2382,7 @@ static int __mptcp_init_sock(struct sock *sk)
msk->out_of_order_queue = RB_ROOT;
msk->first_pending = NULL;
msk->wmem_reserved = 0;
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
msk->tx_pending_data = 0;
msk->first = NULL;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 426ed80fe72f..0f0c026c5f8b 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -296,9 +296,17 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
return (struct mptcp_sock *)sk;
}
+/* the msk socket don't use the backlog, also account for the bulk
+ * free memory
+ */
+static inline int __mptcp_rmem(const struct sock *sk)
+{
+ return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released);
+}
+
static inline int __mptcp_space(const struct sock *sk)
{
- return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released);
+ return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
}
static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 092d1f635d27..8c03afac5ca0 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -157,19 +157,7 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast(ssk);
- switch (optname) {
- case SO_TIMESTAMP_OLD:
- case SO_TIMESTAMP_NEW:
- case SO_TIMESTAMPNS_OLD:
- case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, optname, !!val);
- break;
- case SO_TIMESTAMPING_NEW:
- case SO_TIMESTAMPING_OLD:
- sock_set_timestamping(sk, optname, val);
- break;
- }
-
+ sock_set_timestamp(sk, optname, !!val);
unlock_sock_fast(ssk, slow);
}
@@ -178,7 +166,8 @@ static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optnam
}
static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
- sockptr_t optval, unsigned int optlen)
+ sockptr_t optval,
+ unsigned int optlen)
{
int val, ret;
@@ -205,14 +194,56 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
- case SO_TIMESTAMPING_OLD:
- case SO_TIMESTAMPING_NEW:
return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val);
}
return -ENOPROTOOPT;
}
+static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,
+ int optname,
+ sockptr_t optval,
+ unsigned int optlen)
+{
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ struct so_timestamping timestamping;
+ int ret;
+
+ if (optlen == sizeof(timestamping)) {
+ if (copy_from_sockptr(&timestamping, optval,
+ sizeof(timestamping)))
+ return -EFAULT;
+ } else if (optlen == sizeof(int)) {
+ memset(&timestamping, 0, sizeof(timestamping));
+
+ if (copy_from_sockptr(&timestamping.flags, optval, sizeof(int)))
+ return -EFAULT;
+ } else {
+ return -EINVAL;
+ }
+
+ ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
+ KERNEL_SOCKPTR(&timestamping),
+ sizeof(timestamping));
+ if (ret)
+ return ret;
+
+ lock_sock(sk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow = lock_sock_fast(ssk);
+
+ sock_set_timestamping(sk, optname, timestamping);
+ unlock_sock_fast(ssk, slow);
+ }
+
+ release_sock(sk);
+
+ return 0;
+}
+
static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval,
unsigned int optlen)
{
@@ -299,9 +330,12 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname,
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
+ return mptcp_setsockopt_sol_socket_int(msk, optname, optval,
+ optlen);
case SO_TIMESTAMPING_OLD:
case SO_TIMESTAMPING_NEW:
- return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen);
+ return mptcp_setsockopt_sol_socket_timestamping(msk, optname,
+ optval, optlen);
case SO_LINGER:
return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
case SO_RCVLOWAT:
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 66d0b1893d26..966f777d35ce 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -214,11 +214,6 @@ again:
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
- sock_put((struct sock *)subflow_req->msk);
- mptcp_token_destroy_request(req);
- tcp_request_sock_ops.destructor(req);
- subflow_req->msk = NULL;
- subflow_req->mp_join = 0;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
return -EPERM;
}
@@ -230,6 +225,8 @@ again:
if (unlikely(req->syncookie)) {
if (mptcp_can_accept_new_subflow(subflow_req->msk))
subflow_init_req_cookie_join_save(subflow_req, skb);
+ else
+ return -EPERM;
}
pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
@@ -269,9 +266,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
if (!mptcp_token_join_cookie_init_state(subflow_req, skb))
return -EINVAL;
- if (mptcp_can_accept_new_subflow(subflow_req->msk))
- subflow_req->mp_join = 1;
-
+ subflow_req->mp_join = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
}
diff --git a/net/mptcp/syncookies.c b/net/mptcp/syncookies.c
index abe0fd099746..37127781aee9 100644
--- a/net/mptcp/syncookies.c
+++ b/net/mptcp/syncookies.c
@@ -37,7 +37,21 @@ static spinlock_t join_entry_locks[COOKIE_JOIN_SLOTS] __cacheline_aligned_in_smp
static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net)
{
- u32 i = skb_get_hash(skb) ^ net_hash_mix(net);
+ static u32 mptcp_join_hash_secret __read_mostly;
+ struct tcphdr *th = tcp_hdr(skb);
+ u32 seq, i;
+
+ net_get_random_once(&mptcp_join_hash_secret,
+ sizeof(mptcp_join_hash_secret));
+
+ if (th->syn)
+ seq = TCP_SKB_CB(skb)->seq;
+ else
+ seq = TCP_SKB_CB(skb)->seq - 1;
+
+ i = jhash_3words(seq, net_hash_mix(net),
+ (__force __u32)th->source << 16 | (__force __u32)th->dest,
+ mptcp_join_hash_secret);
return i % ARRAY_SIZE(join_entries);
}
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-06 19:51:55 +0100