Merge branch 'mptcp-allow-privileged-operations-from-user-ns-cleanup'

Matthieu Baerts says:

====================
mptcp: allow privileged operations from user ns & cleanup

This series allows privileged Netlink operations from user namespaces. When a
non-root user configures MPTCP endpoints, the memory allocation is now accounted
to this user. See patches 4 and 5.

Apart from that, there are some cleanup:

 - Patch 1 adds a macro to improve code readability

 - Patch 2 regroups similar checks all together

 - Patch 3 uses an explicit boolean instead of a counter to do one more check
====================

Link: https://lore.kernel.org/r/20220906205545.1623193-1-matthieu.baerts@tessares.netSigned-off-by: Paolo Abeni <pabeni@redhat.com>

net/mptcp/pm_netlink.c

@@ -796,7 +796,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 		u8 rm_id = rm_list->ids[i];
 		bool removed = false;
 
-		list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
 			u8 id = subflow->local_id;
@@ -1327,7 +1327,7 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT);
 	if (!entry) {
 		GENL_SET_ERR_MSG(info, "can't allocate addr");
 		return -ENOMEM;
@@ -2218,17 +2218,17 @@ static const struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_ADD_ADDR,
 		.doit   = mptcp_nl_cmd_add_addr,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_DEL_ADDR,
 		.doit   = mptcp_nl_cmd_del_addr,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_FLUSH_ADDRS,
 		.doit   = mptcp_nl_cmd_flush_addrs,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_GET_ADDR,
@@ -2238,7 +2238,7 @@ static const struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_SET_LIMITS,
 		.doit   = mptcp_nl_cmd_set_limits,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_GET_LIMITS,
@@ -2247,27 +2247,27 @@ static const struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_SET_FLAGS,
 		.doit   = mptcp_nl_cmd_set_flags,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_ANNOUNCE,
 		.doit   = mptcp_nl_cmd_announce,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_REMOVE,
 		.doit   = mptcp_nl_cmd_remove,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_SUBFLOW_CREATE,
 		.doit   = mptcp_nl_cmd_sf_create,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd    = MPTCP_PM_CMD_SUBFLOW_DESTROY,
 		.doit   = mptcp_nl_cmd_sf_destroy,
-		.flags  = GENL_ADMIN_PERM,
+		.flags  = GENL_UNS_ADMIN_PERM,
 	},
 };
 

net/mptcp/protocol.c

@@ -1538,8 +1538,9 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 	struct mptcp_sendmsg_info info = {
 				.flags = flags,
 	};
+	bool do_check_data_fin = false;
 	struct mptcp_data_frag *dfrag;
-	int len, copied = 0;
+	int len;
 
 	while ((dfrag = mptcp_send_head(sk))) {
 		info.sent = dfrag->already_sent;
@@ -1574,8 +1575,8 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 				goto out;
 			}
 
+			do_check_data_fin = true;
 			info.sent += ret;
-			copied += ret;
 			len -= ret;
 
 			mptcp_update_post_push(msk, dfrag, ret);
@@ -1591,7 +1592,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 	/* ensure the rtx timer is running */
 	if (!mptcp_timer_pending(sk))
 		mptcp_reset_timer(sk);
-	if (copied)
+	if (do_check_data_fin)
 		__mptcp_check_send_data_fin(sk);
 }
 
@@ -2357,7 +2358,7 @@ static void __mptcp_close_subflow(struct mptcp_sock *msk)
 
 	might_sleep();
 
-	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+	mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
 		if (inet_sk_state_load(ssk) != TCP_CLOSE)
@@ -2400,7 +2401,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk)
 
 	mptcp_token_destroy(msk);
 
-	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+	mptcp_for_each_subflow_safe(msk, subflow, tmp) {
 		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
 		bool slow;
 
@@ -3047,7 +3048,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 	__mptcp_clear_xmit(sk);
 
 	/* join list will be eventually flushed (with rst) at sock lock release time */
-	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node)
+	mptcp_for_each_subflow_safe(msk, subflow, tmp)
 		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags);
 
 	/* move to sk_receive_queue, sk_stream_kill_queues will purge it */

net/mptcp/protocol.h

@@ -314,6 +314,8 @@ struct mptcp_sock {
 
 #define mptcp_for_each_subflow(__msk, __subflow)			\
 	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
+#define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp)			\
+	list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node)
 
 static inline void msk_owned_by_me(const struct mptcp_sock *msk)
 {

tools/testing/selftests/net/mptcp/mptcp_join.sh

@@ -706,6 +706,7 @@ do_transfer()
 		addr_nr_ns1=${addr_nr_ns1:10}
 	fi
 
+	local flags="subflow"
 	if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then
 		# disconnect
 		extra_args="$extra_args -I ${addr_nr_ns2:10}"
@@ -713,6 +714,9 @@ do_transfer()
 	elif [[ "${addr_nr_ns2}" = "userspace_"* ]]; then
 		userspace_pm=1
 		addr_nr_ns2=${addr_nr_ns2:10}
+	elif [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then
+		flags="${flags},fullmesh"
+		addr_nr_ns2=${addr_nr_ns2:9}
 	fi
 
 	if [ $userspace_pm -eq 1 ]; then
@@ -832,12 +836,6 @@ do_transfer()
 		fi
 	fi
 
-	local flags="subflow"
-	if [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then
-		flags="${flags},fullmesh"
-		addr_nr_ns2=${addr_nr_ns2:9}
-	fi
-
 	# if newly added endpoints must be deleted, give the background msk
 	# some time to created them
 	[ $addr_nr_ns1 -gt 0 ] && [ $addr_nr_ns2 -lt 0 ] && sleep 1