[v6,mptcp-next,1/5] mptcp: remote addresses fullmesh

Commit Message

Geliang Tang July 27, 2021, 1:24 p.m. UTC

From: Geliang Tang <[e-mail]>

This patch added and managed a new per endpoint flag, named
MPTCP_PM_ADDR_FLAG_FULLMESH.

In mptcp_pm_create_subflow_or_signal_addr(), if such flag is set, instead
of:

        remote_address((struct sock_common *)sk, &remote);

fill a temporary allocated array of all known remote address. After
releaseing the pm lock loop on such array and create a subflow for each
remote address from the given local.

Note that the we could still use an array even for non 'fullmesh'
endpoint: with a single entry corresponding to the primary MPC subflow
remote address.

Suggested-by: Paolo Abeni <[e-mail]>
Signed-off-by: Geliang Tang <[e-mail]>
---
 include/uapi/linux/mptcp.h |  1 +
 net/mptcp/pm_netlink.c     | 64 +++++++++++++++++++++++++++++++++++---
 2 files changed, 60 insertions(+), 5 deletions(-)

Patch

diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
index 7b05f7102321..f66038b9551f 100644
--- a/include/uapi/linux/mptcp.h
+++ b/include/uapi/linux/mptcp.h
@@ -73,6 +73,7 @@  enum {
 #define MPTCP_PM_ADDR_FLAG_SIGNAL			(1 << 0)
 #define MPTCP_PM_ADDR_FLAG_SUBFLOW			(1 << 1)
 #define MPTCP_PM_ADDR_FLAG_BACKUP			(1 << 2)
+#define MPTCP_PM_ADDR_FLAG_FULLMESH			(1 << 3)
 
 enum {
 	MPTCP_PM_CMD_UNSPEC,
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index ba0e1d71504d..ecf43d45711a 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -410,6 +410,56 @@  void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
 	}
 }
 
+static bool lookup_address_in_vec(struct mptcp_addr_info *addrs, unsigned int nr,
+				  struct mptcp_addr_info *addr)
+{
+	int i;
+
+	for (i = 0; i < nr; i++) {
+		if (addresses_equal(&addrs[i], addr, addr->port))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Fill all the remote addresses into the array addrs[],
+ * and return the array size.
+ */
+static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, bool fullmesh,
+					      struct mptcp_addr_info *addrs)
+{
+	struct sock *sk = (struct sock *)msk, *ssk;
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_addr_info remote = { 0 };
+	struct pm_nl_pernet *pernet;
+	unsigned int subflows_max;
+	int i = 0;
+
+	pernet = net_generic(sock_net(sk), pm_nl_pernet_id);
+	subflows_max = mptcp_pm_get_subflows_max(msk);
+
+	/* non-fullmesh, fill in the remote address */
+	if (!fullmesh) {
+		remote_address((struct sock_common *)sk, &remote);
+		msk->pm.subflows++;
+		addrs[i++] = remote;
+	} else {
+		mptcp_for_each_subflow(msk, subflow) {
+			ssk = mptcp_subflow_tcp_sock(subflow);
+			remote_address((struct sock_common *)ssk, &remote);
+			if (!lookup_address_in_vec(addrs, i, &remote) &&
+			    msk->pm.subflows < subflows_max) {
+				msk->pm.subflows++;
+				addrs[i++] = remote;
+			}
+		}
+	}
+
+	return i;
+}
+
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -455,15 +505,19 @@  static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 	    !READ_ONCE(msk->pm.remote_deny_join_id0)) {
 		local = select_local_address(pernet, msk);
 		if (local) {
-			struct mptcp_addr_info remote = { 0 };
+			struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
+			int i, nr;
 
 			msk->pm.local_addr_used++;
-			msk->pm.subflows++;
 			check_work_pending(msk);
-			remote_address((struct sock_common *)sk, &remote);
+			nr = fill_remote_addresses_vec(msk,
+						       local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH,
+						       addrs);
 			spin_unlock_bh(&msk->pm.lock);
-			__mptcp_subflow_connect(sk, &local->addr, &remote,
-						local->flags, local->ifindex);
+			for (i = 0; i < nr; i++) {
+				__mptcp_subflow_connect(sk, &local->addr, &addrs[i],
+							local->flags, local->ifindex);
+			}
 			spin_lock_bh(&msk->pm.lock);
 			return;
 		}