Merge branch 'net-add-preliminary-netdev-refcount-tracking'

Eric Dumazet says:

====================
net: add preliminary netdev refcount tracking

Two first patches add a generic infrastructure, that will be used
to get tracking of refcount increments/decrements.

The general idea is to be able to precisely pair each decrement with
a corresponding prior increment. Both share a cookie, basically
a pointer to private data storing stack traces.

The third patch adds dev_hold_track() and dev_put_track() helpers
(CONFIG_NET_DEV_REFCNT_TRACKER)

Then a series of 20 patches converts some dev_hold()/dev_put()
pairs to new hepers : dev_hold_track() and dev_put_track().

Hopefully this will be used by developpers and syzbot to
root cause bugs that cause netdevice dismantles freezes.

With CONFIG_PCPU_DEV_REFCNT=n option, we were able to detect
some class of bugs, but too late (when too many dev_put()
were happening).

Another series will be sent after this one is merged.

v3: moved NET_DEV_REFCNT_TRACKER to net/Kconfig.debug
    added "depends on DEBUG_KERNEL && STACKTRACE_SUPPORT"
    to hopefully get rid of kbuild reports for ARCH=nios2
    Reworded patch 3 changelog.
    Added missing htmldocs (Jakub)

v2: added four additional patches,
    added netdev_tracker_alloc() and netdev_tracker_free()
    addressed build error (kernel bots),
    use GFP_ATOMIC in test_ref_tracker_timer_func()
====================

Link: https://lore.kernel.org/r/20211205042217.982127-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 15 insertions, 1 deletions

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 043fcec8b0aa..3276a29f2b81 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -664,13 +664,17 @@ struct devlink_health_reporter_ops {
  * @trap_name: Trap name.
  * @trap_group_name: Trap group name.
  * @input_dev: Input netdevice.
+ * @dev_tracker: refcount tracker for @input_dev.
  * @fa_cookie: Flow action user cookie.
  * @trap_type: Trap type.
  */
 struct devlink_trap_metadata {
 	const char *trap_name;
 	const char *trap_group_name;
+
 	struct net_device *input_dev;
+	netdevice_tracker dev_tracker;
+
 	const struct flow_action_cookie *fa_cookie;
 	enum devlink_trap_type trap_type;
 };
diff --git a/include/net/dst.h b/include/net/dst.h
index a057319aabef..6aa252c3fc55 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -77,6 +77,7 @@ struct dst_entry {
 #ifndef CONFIG_64BIT
 	atomic_t		__refcnt;	/* 32-bit offset 64 */
 #endif
+	netdevice_tracker	dev_tracker;
 };
 
 struct dst_metrics {
diff --git a/include/net/failover.h b/include/net/failover.h
index bb15438f39c7..f2b42b4b9cd6 100644
--- a/include/net/failover.h
+++ b/include/net/failover.h
@@ -25,6 +25,7 @@ struct failover_ops {
 struct failover {
 	struct list_head list;
 	struct net_device __rcu *failover_dev;
+	netdevice_tracker	dev_tracker;
 	struct failover_ops __rcu *ops;
 };
 
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 653e7d0f65cb..f026cf08a8e8 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -160,6 +160,7 @@ struct ipv6_devstat {
 
 struct inet6_dev {
 	struct net_device	*dev;
+	netdevice_tracker	dev_tracker;
 
 	struct list_head	addr_list;
 
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 028eaea1c854..a38c4f1e4e5c 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -46,6 +46,7 @@ struct __ip6_tnl_parm {
 struct ip6_tnl {
 	struct ip6_tnl __rcu *next;	/* next tunnel in list */
 	struct net_device *dev;	/* virtual device associated with tunnel */
+	netdevice_tracker dev_tracker;
 	struct net *net;	/* netns for packet i/o */
 	struct __ip6_tnl_parm parms;	/* tunnel configuration parameters */
 	struct flowi fl;	/* flowi template for xmit */
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index bc3b13ec93c9..0219fe907b26 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -104,7 +104,10 @@ struct metadata_dst;
 struct ip_tunnel {
 	struct ip_tunnel __rcu	*next;
 	struct hlist_node hash_node;
+
 	struct net_device	*dev;
+	netdevice_tracker	dev_tracker;
+
 	struct net		*net;	/* netns for packet i/o */
 
 	unsigned long	err_time;	/* Time when the last ICMP error
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 55af812c3ed5..937389e04c8e 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -70,6 +70,7 @@ enum {
 struct neigh_parms {
 	possible_net_t net;
 	struct net_device *dev;
+	netdevice_tracker dev_tracker;
 	struct list_head list;
 	int	(*neigh_setup)(struct neighbour *);
 	struct neigh_table *tbl;
@@ -158,6 +159,7 @@ struct neighbour {
 	struct list_head	managed_list;
 	struct rcu_head		rcu;
 	struct net_device	*dev;
+	netdevice_tracker	dev_tracker;
 	u8			primary_key[0];
 } __randomize_layout;
 
@@ -173,6 +175,7 @@ struct pneigh_entry {
 	struct pneigh_entry	*next;
 	possible_net_t		net;
 	struct net_device	*dev;
+	netdevice_tracker	dev_tracker;
 	u32			flags;
 	u8			protocol;
 	u8			key[];
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 22179b2fda72..dbf202bb1a0e 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -125,7 +125,7 @@ struct Qdisc {
 	spinlock_t		seqlock;
 
 	struct rcu_head		rcu;
-
+	netdevice_tracker	dev_tracker;
 	/* private data */
 	long privdata[] ____cacheline_aligned;
 };