net: add option to not create fall-back tunnels in root-ns as well

The sysctl that was added  earlier by commit 79134e6c ("net: do
not create fallback tunnels for non-default namespaces") to create
fall-back only in root-ns. This patch enhances that behavior to provide
option not to create fallback tunnels in root-ns as well. Since modules
that create fallback tunnels could be built-in and setting the sysctl
value after booting is pointless, so added a kernel cmdline options to
change this default. The default setting is preseved for backward
compatibility. The kernel command line option of fb_tunnels=initns will
set the sysctl value to 1 and will create fallback tunnels only in initns
while kernel cmdline fb_tunnels=none will set the sysctl value to 2 and
fallback tunnels are skipped in every netns.
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Maciej Zenczykowski <maze@google.com>
Cc: Jian Yang <jianyang@google.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/admin-guide/kernel-parameters.txt

@@ -1338,6 +1338,11 @@
 			Format: <interval>,<probability>,<space>,<times>
 			See also Documentation/fault-injection/.
 
+	fb_tunnels=	[NET]
+			Format: { initns | none }
+			See Documentation/admin-guide/sysctl/net.rst for
+			fb_tunnels_only_for_init_ns
+
 	floppy=		[HW]
 			See Documentation/admin-guide/blockdev/floppy.rst.
 

Documentation/admin-guide/sysctl/net.rst

@@ -300,7 +300,6 @@ Note:
       0:    0     1     2     3     4     5     6     7
   RSS hash key:
   84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
-
 netdev_tstamp_prequeue
 ----------------------
 
@@ -321,11 +320,20 @@ fb_tunnels_only_for_init_net
 ----------------------------
 
 Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0,
-sit0, ip6tnl0, ip6gre0) are automatically created when a new
-network namespace is created, if corresponding tunnel is present
-in initial network namespace.
-If set to 1, these devices are not automatically created, and
-user space is responsible for creating them if needed.
+sit0, ip6tnl0, ip6gre0) are automatically created. There are 3 possibilities
+(a) value = 0; respective fallback tunnels are created when module is
+loaded in every net namespaces (backward compatible behavior).
+(b) value = 1; [kcmd value: initns] respective fallback tunnels are
+created only in init net namespace and every other net namespace will
+not have them.
+(c) value = 2; [kcmd value: none] fallback tunnels are not created
+when a module is loaded in any of the net namespace. Setting value to
+"2" is pointless after boot if these modules are built-in, so there is
+a kernel command-line option that can change this default. Please refer to
+Documentation/admin-guide/kernel-parameters.txt for additional details.
+
+Not creating fallback tunnels gives control to userspace to create
+whatever is needed only and avoid creating devices which are redundant.
 
 Default : 0  (for compatibility reasons)
 

include/linux/netdevice.h

@@ -640,10 +640,14 @@ struct netdev_queue {
 extern int sysctl_fb_tunnels_only_for_init_net;
 extern int sysctl_devconf_inherit_init_net;
 
+/*
+ * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns
+ *                                     == 1 : For initns only
+ *                                     == 2 : For none.
+ */
 static inline bool net_has_fallback_tunnels(const struct net *net)
 {
-	return net == &init_net ||
-	       !IS_ENABLED(CONFIG_SYSCTL) ||
+	return (net == &init_net && sysctl_fb_tunnels_only_for_init_net == 1) ||
 	       !sysctl_fb_tunnels_only_for_init_net;
 }
 

net/core/sysctl_net_core.c

@@ -22,7 +22,7 @@
 #include <net/busy_poll.h>
 #include <net/pkt_sched.h>
 
-static int two __maybe_unused = 2;
+static int two = 2;
 static int three = 3;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -546,7 +546,7 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
+		.extra2		= &two,
 	},
 	{
 		.procname	= "devconf_inherit_init_net",
@@ -587,6 +587,19 @@ static struct ctl_table netns_core_table[] = {
 	{ }
 };
 
+static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str)
+{
+	/* fallback tunnels for initns only */
+	if (!strncmp(str, "initns", 6))
+		sysctl_fb_tunnels_only_for_init_net = 1;
+	/* no fallback tunnels anywhere */
+	else if (!strncmp(str, "none", 4))
+		sysctl_fb_tunnels_only_for_init_net = 2;
+
+	return 1;
+}
+__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup);
+
 static __net_init int sysctl_core_net_init(struct net *net)
 {
 	struct ctl_table *tbl;