Merge branch 'net-sysctl-avoid-using-current-nsproxy'

Matthieu Baerts says:

====================
net: sysctl: avoid using current->nsproxy

As pointed out by Al Viro and Eric Dumazet in [1], using the 'net'
structure via 'current' is not recommended for different reasons:

- Inconsistency: getting info from the reader's/writer's netns vs only
  from the opener's netns as it is usually done. This could cause
  unexpected issues when other operations are done on the wrong netns.

- current->nsproxy can be NULL in some cases, resulting in an 'Oops'
  (null-ptr-deref), e.g. when the current task is exiting, as spotted by
  syzbot [1] using acct(2).

The 'net' or 'pernet' structure can be obtained from the table->data
using container_of().

Note that table->data could also be used directly in more places, but
that would increase the size of this fix to replace all accesses via
'net'. Probably best to avoid that for fixes.

Patches 2-9 remove access of net via current->nsproxy in sysfs handlers
in MPTCP, SCTP and RDS. There are multiple patches doing almost the same
thing, but the reason is to ease the backports.

Patch 1 is not directly linked to this, but it is a small fix for MPTCP
available_schedulers sysctl knob to explicitly mark it as read-only.

Please note that this series does not address Al's comment [2]. In SCTP,
some sysctl knobs set other sysfs-exposed variables for the min/max: two
processes could then write two linked values at the same time, resulting
in new values being outside the new boundaries. It would be great if
SCTP developers can look at this problem.

Link: https://lore.kernel.org/67769ecb.050a0220.3a8527.003f.GAE@google.com [1]
Link: https://lore.kernel.org/20250105211158.GL1977892@ZenIV [2]
====================

Link: https://patch.msgid.link/20250108-net-sysctl-current-nsproxy-v1-0-5df34b2083e8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 49 insertions, 21 deletions

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 38d8121331d4..b0dd008e2114 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -102,16 +102,15 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 }
 
 #ifdef CONFIG_SYSCTL
-static int mptcp_set_scheduler(const struct net *net, const char *name)
+static int mptcp_set_scheduler(char *scheduler, const char *name)
 {
-	struct mptcp_pernet *pernet = mptcp_get_pernet(net);
 	struct mptcp_sched_ops *sched;
 	int ret = 0;
 
 	rcu_read_lock();
 	sched = mptcp_sched_find(name);
 	if (sched)
-		strscpy(pernet->scheduler, name, MPTCP_SCHED_NAME_MAX);
+		strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX);
 	else
 		ret = -ENOENT;
 	rcu_read_unlock();
@@ -122,7 +121,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name)
 static int proc_scheduler(const struct ctl_table *ctl, int write,
 			  void *buffer, size_t *lenp, loff_t *ppos)
 {
-	const struct net *net = current->nsproxy->net_ns;
+	char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data;
 	char val[MPTCP_SCHED_NAME_MAX];
 	struct ctl_table tbl = {
 		.data = val,
@@ -130,11 +129,11 @@ static int proc_scheduler(const struct ctl_table *ctl, int write,
 	};
 	int ret;
 
-	strscpy(val, mptcp_get_scheduler(net), MPTCP_SCHED_NAME_MAX);
+	strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX);
 
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
 	if (write && ret == 0)
-		ret = mptcp_set_scheduler(net, val);
+		ret = mptcp_set_scheduler(*scheduler, val);
 
 	return ret;
 }
@@ -161,7 +160,9 @@ static int proc_blackhole_detect_timeout(const struct ctl_table *table,
 					 int write, void *buffer, size_t *lenp,
 					 loff_t *ppos)
 {
-	struct mptcp_pernet *pernet = mptcp_get_pernet(current->nsproxy->net_ns);
+	struct mptcp_pernet *pernet = container_of(table->data,
+						   struct mptcp_pernet,
+						   blackhole_timeout);
 	int ret;
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
@@ -228,7 +229,7 @@ static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "available_schedulers",
 		.maxlen	= MPTCP_SCHED_BUF_MAX,
-		.mode = 0644,
+		.mode = 0444,
 		.proc_handler = proc_available_schedulers,
 	},
 	{
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 351ac1747224..0581c53e6517 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -61,8 +61,10 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0);
 
 static struct kmem_cache *rds_tcp_conn_slab;
 
-static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write,
-				 void *buffer, size_t *lenp, loff_t *fpos);
+static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos);
+static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos);
 
 static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF;
 static int rds_tcp_min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -74,7 +76,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
 		/* data is per-net pointer */
 		.maxlen         = sizeof(int),
 		.mode           = 0644,
-		.proc_handler   = rds_tcp_skbuf_handler,
+		.proc_handler   = rds_tcp_sndbuf_handler,
 		.extra1		= &rds_tcp_min_sndbuf,
 	},
 #define	RDS_TCP_RCVBUF	1
@@ -83,7 +85,7 @@ static struct ctl_table rds_tcp_sysctl_table[] = {
 		/* data is per-net pointer */
 		.maxlen         = sizeof(int),
 		.mode           = 0644,
-		.proc_handler   = rds_tcp_skbuf_handler,
+		.proc_handler   = rds_tcp_rcvbuf_handler,
 		.extra1		= &rds_tcp_min_rcvbuf,
 	},
 };
@@ -682,10 +684,10 @@ static void rds_tcp_sysctl_reset(struct net *net)
 	spin_unlock_irq(&rds_tcp_conn_lock);
 }
 
-static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write,
+static int rds_tcp_skbuf_handler(struct rds_tcp_net *rtn,
+				 const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *fpos)
 {
-	struct net *net = current->nsproxy->net_ns;
 	int err;
 
 	err = proc_dointvec_minmax(ctl, write, buffer, lenp, fpos);
@@ -694,11 +696,34 @@ static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write,
 			*(int *)(ctl->extra1));
 		return err;
 	}
-	if (write)
+
+	if (write && rtn->rds_tcp_listen_sock && rtn->rds_tcp_listen_sock->sk) {
+		struct net *net = sock_net(rtn->rds_tcp_listen_sock->sk);
+
 		rds_tcp_sysctl_reset(net);
+	}
+
 	return 0;
 }
 
+static int rds_tcp_sndbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos)
+{
+	struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net,
+					       sndbuf_size);
+
+	return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos);
+}
+
+static int rds_tcp_rcvbuf_handler(const struct ctl_table *ctl, int write,
+				  void *buffer, size_t *lenp, loff_t *fpos)
+{
+	struct rds_tcp_net *rtn = container_of(ctl->data, struct rds_tcp_net,
+					       rcvbuf_size);
+
+	return rds_tcp_skbuf_handler(rtn, ctl, write, buffer, lenp, fpos);
+}
+
 static void rds_tcp_exit(void)
 {
 	rds_tcp_set_unloading();
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index e5a5af343c4c..8e1e97be4df7 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -387,7 +387,8 @@ static struct ctl_table sctp_net_table[] = {
 static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net = current->nsproxy->net_ns;
+	struct net *net = container_of(ctl->data, struct net,
+				       sctp.sctp_hmac_alg);
 	struct ctl_table tbl;
 	bool changed = false;
 	char *none = "none";
@@ -432,7 +433,7 @@ static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write,
 static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net = current->nsproxy->net_ns;
+	struct net *net = container_of(ctl->data, struct net, sctp.rto_min);
 	unsigned int min = *(unsigned int *) ctl->extra1;
 	unsigned int max = *(unsigned int *) ctl->extra2;
 	struct ctl_table tbl;
@@ -460,7 +461,7 @@ static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write,
 static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net = current->nsproxy->net_ns;
+	struct net *net = container_of(ctl->data, struct net, sctp.rto_max);
 	unsigned int min = *(unsigned int *) ctl->extra1;
 	unsigned int max = *(unsigned int *) ctl->extra2;
 	struct ctl_table tbl;
@@ -498,7 +499,7 @@ static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write,
 static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net = current->nsproxy->net_ns;
+	struct net *net = container_of(ctl->data, struct net, sctp.auth_enable);
 	struct ctl_table tbl;
 	int new_value, ret;
 
@@ -527,7 +528,7 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
 static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net = current->nsproxy->net_ns;
+	struct net *net = container_of(ctl->data, struct net, sctp.udp_port);
 	unsigned int min = *(unsigned int *)ctl->extra1;
 	unsigned int max = *(unsigned int *)ctl->extra2;
 	struct ctl_table tbl;
@@ -568,7 +569,8 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write,
 				       void *buffer, size_t *lenp, loff_t *ppos)
 {
-	struct net *net = current->nsproxy->net_ns;
+	struct net *net = container_of(ctl->data, struct net,
+				       sctp.probe_interval);
 	struct ctl_table tbl;
 	int ret, new_value;