Merge branch 'mptcp-small-improvements-fix-and-clean-ups'

Mat Martineau says:

====================
mptcp: small improvements, fix and clean-ups

This series contain mostly unrelated patches:

- The two first patches can be seen as "fixes". They are part of this
  series for -next because it looks like the last batch of fixes for
  v6.9 has already been sent. These fixes are not urgent, so they can
  wait if an unlikely v6.9-rc8 is published. About the two patches:
    - Patch 1 fixes getsockopt(SO_KEEPALIVE) support on MPTCP sockets
    - Patch 2 makes sure the full TCP keep-alive feature is supported,
      not just SO_KEEPALIVE.

- Patch 3 is a small optimisation when getsockopt(MPTCP_INFO) is used
  without buffer, just to check if MPTCP is still being used: no
  fallback to TCP.

- Patch 4 adds net.mptcp.available_schedulers sysctl knob to list packet
  schedulers, similar to net.ipv4.tcp_available_congestion_control.

- Patch 5 and 6 fix CheckPatch warnings: "prefer strscpy over strcpy"
  and "else is not generally useful after a break or return".

- Patch 7 and 8 remove and add header includes to avoid unused ones, and
  add missing ones to be self-contained.
====================

Link: https://lore.kernel.org/r/20240514011335.176158-1-martineau@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/mptcp.h

@@ -97,6 +97,9 @@ struct mptcp_out_options {
 };
 
 #define MPTCP_SCHED_NAME_MAX	16
+#define MPTCP_SCHED_MAX		128
+#define MPTCP_SCHED_BUF_MAX	(MPTCP_SCHED_NAME_MAX * MPTCP_SCHED_MAX)
+
 #define MPTCP_SUBFLOWS_MAX	8
 
 struct mptcp_sched_data {

net/mptcp/ctrl.c

@@ -92,7 +92,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 	pernet->allow_join_initial_addr_port = 1;
 	pernet->stale_loss_cnt = 4;
 	pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
-	strcpy(pernet->scheduler, "default");
+	strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler));
 }
 
 #ifdef CONFIG_SYSCTL
@@ -133,6 +133,24 @@ static int proc_scheduler(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int proc_available_schedulers(struct ctl_table *ctl,
+				     int write, void *buffer,
+				     size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table tbl = { .maxlen = MPTCP_SCHED_BUF_MAX, };
+	int ret;
+
+	tbl.data = kmalloc(tbl.maxlen, GFP_USER);
+	if (!tbl.data)
+		return -ENOMEM;
+
+	mptcp_get_available_schedulers(tbl.data, MPTCP_SCHED_BUF_MAX);
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	kfree(tbl.data);
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -187,6 +205,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.mode = 0644,
 		.proc_handler = proc_scheduler,
 	},
+	{
+		.procname = "available_schedulers",
+		.maxlen	= MPTCP_SCHED_BUF_MAX,
+		.mode = 0644,
+		.proc_handler = proc_available_schedulers,
+	},
 	{
 		.procname = "close_timeout",
 		.maxlen = sizeof(unsigned int),
@@ -214,7 +238,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[4].data = &pernet->stale_loss_cnt;
 	table[5].data = &pernet->pm_type;
 	table[6].data = &pernet->scheduler;
-	table[7].data = &pernet->close_timeout;
+	/* table[7] is for available_schedulers which is read-only info */
+	table[8].data = &pernet->close_timeout;
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));

net/mptcp/mib.h

@@ -1,5 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 
+#include <net/inet_common.h>
+
 enum linux_mptcp_mib_field {
 	MPTCP_MIB_NUM = 0,
 	MPTCP_MIB_MPCAPABLEPASSIVE,	/* Received SYN with MP_CAPABLE */

net/mptcp/pm_netlink.c

@@ -14,6 +14,7 @@
 
 #include "protocol.h"
 #include "mib.h"
+#include "mptcp_pm_gen.h"
 
 static int pm_nl_pernet_id;
 

net/mptcp/pm_userspace.c

@@ -6,6 +6,7 @@
 
 #include "protocol.h"
 #include "mib.h"
+#include "mptcp_pm_gen.h"
 
 void mptcp_free_local_addr_list(struct mptcp_sock *msk)
 {

net/mptcp/protocol.c

@@ -2814,7 +2814,8 @@ static void mptcp_ca_reset(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_assign_congestion_control(sk);
-	strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name);
+	strscpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name,
+		sizeof(mptcp_sk(sk)->ca_name));
 
 	/* no need to keep a reference to the ops, the name will suffice */
 	tcp_cleanup_congestion_control(sk);
@@ -4169,7 +4170,7 @@ int __init mptcp_proto_v6_init(void)
 	int err;
 
 	mptcp_v6_prot = mptcp_prot;
-	strcpy(mptcp_v6_prot.name, "MPTCPv6");
+	strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name));
 	mptcp_v6_prot.slab = NULL;
 	mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock);
 	mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np);

net/mptcp/protocol.h

@@ -14,8 +14,6 @@
 #include <net/genetlink.h>
 #include <net/rstreason.h>
 
-#include "mptcp_pm_gen.h"
-
 #define MPTCP_SUPPORTED_VERSION	1
 
 /* MPTCP option bits */
@@ -312,6 +310,9 @@ struct mptcp_sock {
 			free_first:1,
 			rcvspace_init:1;
 	u32		notsent_lowat;
+	int		keepalive_cnt;
+	int		keepalive_idle;
+	int		keepalive_intvl;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
@@ -683,6 +684,7 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
 unsigned int mptcp_close_timeout(const struct sock *sk);
 int mptcp_get_pm_type(const struct net *net);
 const char *mptcp_get_scheduler(const struct net *net);
+void mptcp_get_available_schedulers(char *buf, size_t maxlen);
 void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
 				       struct mptcp_subflow_context *subflow,
 				       const struct mptcp_options_received *mp_opt);

net/mptcp/sched.c

@@ -51,6 +51,28 @@ struct mptcp_sched_ops *mptcp_sched_find(const char *name)
 	return ret;
 }
 
+/* Build string with list of available scheduler values.
+ * Similar to tcp_get_available_congestion_control()
+ */
+void mptcp_get_available_schedulers(char *buf, size_t maxlen)
+{
+	struct mptcp_sched_ops *sched;
+	size_t offs = 0;
+
+	rcu_read_lock();
+	spin_lock(&mptcp_sched_list_lock);
+	list_for_each_entry_rcu(sched, &mptcp_sched_list, list) {
+		offs += snprintf(buf + offs, maxlen - offs,
+				 "%s%s",
+				 offs == 0 ? "" : " ", sched->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
+	}
+	spin_unlock(&mptcp_sched_list_lock);
+	rcu_read_unlock();
+}
+
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
 {
 	if (!sched->get_subflow)

net/mptcp/sockopt.c

@@ -181,8 +181,6 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
 
 	switch (optname) {
 	case SO_KEEPALIVE:
-		mptcp_sol_socket_sync_intval(msk, optname, val);
-		return 0;
 	case SO_DEBUG:
 	case SO_MARK:
 	case SO_PRIORITY:
@@ -618,12 +616,37 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t
 	}
 
 	if (ret == 0)
-		strcpy(msk->ca_name, name);
+		strscpy(msk->ca_name, name, sizeof(msk->ca_name));
 
 	release_sock(sk);
 	return ret;
 }
 
+static int __mptcp_setsockopt_set_val(struct mptcp_sock *msk, int max,
+				      int (*set_val)(struct sock *, int),
+				      int *msk_val, int val)
+{
+	struct mptcp_subflow_context *subflow;
+	int err = 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int ret;
+
+		lock_sock(ssk);
+		ret = set_val(ssk, val);
+		err = err ? : ret;
+		release_sock(ssk);
+	}
+
+	if (!err) {
+		*msk_val = val;
+		sockopt_seq_inc(msk);
+	}
+
+	return err;
+}
+
 static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val)
 {
 	struct mptcp_subflow_context *subflow;
@@ -820,6 +843,22 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 	case TCP_NODELAY:
 		ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val);
 		break;
+	case TCP_KEEPIDLE:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPIDLE,
+						 &tcp_sock_set_keepidle_locked,
+						 &msk->keepalive_idle, val);
+		break;
+	case TCP_KEEPINTVL:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPINTVL,
+						 &tcp_sock_set_keepintvl,
+						 &msk->keepalive_intvl, val);
+		break;
+	case TCP_KEEPCNT:
+		ret = __mptcp_setsockopt_set_val(msk, MAX_TCP_KEEPCNT,
+						 &tcp_sock_set_keepcnt,
+						 &msk->keepalive_cnt,
+						 val);
+		break;
 	default:
 		ret = -ENOPROTOOPT;
 	}
@@ -960,6 +999,10 @@ static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, in
 	if (get_user(len, optlen))
 		return -EFAULT;
 
+	/* When used only to check if a fallback to TCP happened. */
+	if (len == 0)
+		return 0;
+
 	len = min_t(unsigned int, len, sizeof(struct mptcp_info));
 
 	mptcp_diag_fill_info(msk, &m_info);
@@ -1328,6 +1371,8 @@ static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval,
 static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 				    char __user *optval, int __user *optlen)
 {
+	struct sock *sk = (void *)msk;
+
 	switch (optname) {
 	case TCP_ULP:
 	case TCP_CONGESTION:
@@ -1346,6 +1391,18 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 		return mptcp_put_int_option(msk, optval, optlen, msk->cork);
 	case TCP_NODELAY:
 		return mptcp_put_int_option(msk, optval, optlen, msk->nodelay);
+	case TCP_KEEPIDLE:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_idle ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_time) / HZ);
+	case TCP_KEEPINTVL:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_intvl ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_intvl) / HZ);
+	case TCP_KEEPCNT:
+		return mptcp_put_int_option(msk, optval, optlen,
+					    msk->keepalive_cnt ? :
+					    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_keepalive_probes));
 	case TCP_NOTSENT_LOWAT:
 		return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat);
 	case TCP_IS_MPTCP:
@@ -1465,6 +1522,9 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 		tcp_set_congestion_control(ssk, msk->ca_name, false, true);
 	__tcp_sock_set_cork(ssk, !!msk->cork);
 	__tcp_sock_set_nodelay(ssk, !!msk->nodelay);
+	tcp_sock_set_keepidle_locked(ssk, msk->keepalive_idle);
+	tcp_sock_set_keepintvl(ssk, msk->keepalive_intvl);
+	tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt);
 
 	inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk));
 	inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk));

net/mptcp/subflow.c

@@ -1119,6 +1119,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 	}
 
 	if (mpext->data_fin == 1) {
+		u64 data_fin_seq;
+
 		if (data_len == 1) {
 			bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
 								 mpext->dsn64);
@@ -1131,26 +1133,26 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 				 */
 				skb_ext_del(skb, SKB_EXT_MPTCP);
 				return MAPPING_OK;
-			} else {
-				if (updated)
-					mptcp_schedule_work((struct sock *)msk);
-
-				return MAPPING_DATA_FIN;
 			}
-		} else {
-			u64 data_fin_seq = mpext->data_seq + data_len - 1;
 
-			/* If mpext->data_seq is a 32-bit value, data_fin_seq
-			 * must also be limited to 32 bits.
-			 */
-			if (!mpext->dsn64)
-				data_fin_seq &= GENMASK_ULL(31, 0);
+			if (updated)
+				mptcp_schedule_work((struct sock *)msk);
 
-			mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
-			pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
-				 data_fin_seq, mpext->dsn64);
+			return MAPPING_DATA_FIN;
 		}
 
+		data_fin_seq = mpext->data_seq + data_len - 1;
+
+		/* If mpext->data_seq is a 32-bit value, data_fin_seq must also
+		 * be limited to 32 bits.
+		 */
+		if (!mpext->dsn64)
+			data_fin_seq &= GENMASK_ULL(31, 0);
+
+		mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
+		pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
+			 data_fin_seq, mpext->dsn64);
+
 		/* Adjust for DATA_FIN using 1 byte of sequence space */
 		data_len--;
 	}