@@ -367,6 +367,31 @@ static enum mapping_status mptcp_get_mapping(struct sock *ssk)
return ret;
}
+static void mptcp_wait_data(struct sock *sk, long *timeo)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ int data_ready;
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+
+ release_sock(sk);
+
+ smp_mb__before_atomic();
+ data_ready = test_and_clear_bit(MPTCP_DATA_READY, &msk->flags);
+ smp_mb__after_atomic();
+
+ if (!data_ready)
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
+
+ sched_annotate_sleep();
+ lock_sock(sk);
+
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+}
+
static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
@@ -423,6 +448,10 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
u64 old_ack;
u32 ssn;
+ smp_mb__before_atomic();
+ clear_bit(MPTCP_DATA_READY, &msk->flags);
+ smp_mb__after_atomic();
+
status = mptcp_get_mapping(ssk);
if (status == MAPPING_ADDED) {
@@ -550,7 +579,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
pr_debug("block");
release_sock(ssk);
- sk_wait_data(sk, &timeo, NULL);
+ mptcp_wait_data(sk, &timeo);
lock_sock(ssk);
}
@@ -74,6 +74,9 @@
#define MPTCP_ADDR_IPVERSION_4 4
#define MPTCP_ADDR_IPVERSION_6 6
+/* MPTCP socket flags */
+#define MPTCP_DATA_READY BIT(0)
+
static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
{
return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
@@ -117,6 +120,7 @@ struct mptcp_sock {
u64 write_seq;
u64 ack_seq;
u32 token;
+ unsigned long flags;
u16 dport;
struct list_head conn_list;
struct socket *subflow; /* outgoing connect/listener/!mp_capable */
@@ -311,6 +311,11 @@ static void subflow_data_ready(struct sock *sk)
if (parent) {
pr_debug("parent=%p", parent);
+
+ smp_mb__before_atomic();
+ set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags);
+ smp_mb__after_atomic();
+
parent->sk_data_ready(parent);
}
}
The MPTCP-level socket doesn't use sk_receive_queue, so it was possible for mptcp_recvmsg() to remain blocked when there was data ready for it to read. When the MPTCP socket is waiting for additional data and it releases the subflow socket lock, the subflow may have incoming packets ready to process and it sometimes called subflow_data_ready() before the MPTCP socket called sk_wait_data(). This change adds a new function for the MPTCP socket to use when waiting for a data ready signal. Atomic bitops with memory barriers are used to set, test, and clear a MPTCP socket flag that indicates waiting subflow data. This flag replaces the sk_receive_queue checks used by other socket types. Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> --- net/mptcp/protocol.c | 31 ++++++++++++++++++++++++++++++- net/mptcp/protocol.h | 4 ++++ net/mptcp/subflow.c | 5 +++++ 3 files changed, 39 insertions(+), 1 deletion(-)