[PATCH v2] net: make unregister netdev warning timeout configurable

[Dmitry Vyukov]

netdev_wait_allrefs() issues a warning if refcount does not drop to 0
after 10 seconds. While 10 second wait generally should not happen
under normal workload in normal environment, it seems to fire falsely
very often during fuzzing and/or in qemu emulation (~10x slower).
At least it's not possible to understand if it's really a false
positive or not. Automated testing generally bumps all timeouts
to very high values to avoid flake failures.
Add net.core.netdev_unregister_timeout_secs sysctl to make
the timeout configurable for automated testing systems.
Lowering the timeout may also be useful for e.g. manual bisection.
The default value matches the current behavior.

Signed-off-by: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=211877
Cc: netdev@xxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx

---
Changes since v1:
 - use sysctl instead of a config
---
 Documentation/admin-guide/sysctl/net.rst | 11 +++++++++++
 include/linux/netdevice.h                |  1 +
 net/core/dev.c                           |  6 +++++-
 net/core/sysctl_net_core.c               | 10 ++++++++++
 4 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst
index f2ab8a5b6a4b8..2090bfc69aa50 100644
--- a/Documentation/admin-guide/sysctl/net.rst
+++ b/Documentation/admin-guide/sysctl/net.rst
@@ -311,6 +311,17 @@ permit to distribute the load on several cpus.
 If set to 1 (default), timestamps are sampled as soon as possible, before
 queueing.
 
+netdev_unregister_timeout_secs
+------------------------------
+
+Unregister network device timeout in seconds.
+This option controls the timeout (in seconds) used to issue a warning while
+waiting for a network device refcount to drop to 0 during device
+unregistration. A lower value may be useful during bisection to detect
+a leaked reference faster. A larger value may be useful to prevent false
+warnings on slow/loaded systems.
+Default value is 10, minimum 0, maximum 3600.
+
 optmem_max
 ----------
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 87a5d186faff4..179c5693f5119 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4611,6 +4611,7 @@ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
 
 extern int		netdev_max_backlog;
 extern int		netdev_tstamp_prequeue;
+extern int		netdev_unregister_timeout_secs;
 extern int		weight_p;
 extern int		dev_weight_rx_bias;
 extern int		dev_weight_tx_bias;
diff --git a/net/core/dev.c b/net/core/dev.c
index 0f72ff5d34ba0..7accbd4a3bec1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10344,6 +10344,8 @@ int netdev_refcnt_read(const struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_refcnt_read);
 
+int netdev_unregister_timeout_secs __read_mostly = 10;
+
 #define WAIT_REFS_MIN_MSECS 1
 #define WAIT_REFS_MAX_MSECS 250
 /**
@@ -10405,7 +10407,9 @@ static void netdev_wait_allrefs(struct net_device *dev)
 
 		refcnt = netdev_refcnt_read(dev);
 
-		if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) {
+		if (refcnt &&
+		    time_after(jiffies, warning_time +
+			       netdev_unregister_timeout_secs * HZ)) {
 			pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
 				 dev->name, refcnt);
 			warning_time = jiffies;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 4567de519603b..d84c8a1b280e2 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -24,6 +24,7 @@
 
 static int two = 2;
 static int three = 3;
+static int int_3600 = 3600;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
 static int max_skb_frags = MAX_SKB_FRAGS;
@@ -570,6 +571,15 @@ static struct ctl_table net_core_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ONE,
 	},
+	{
+		.procname	= "netdev_unregister_timeout_secs",
+		.data		= &netdev_unregister_timeout_secs,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &int_3600,
+	},
 	{ }
 };
 

base-commit: e0c755a45f6fb6e81e3a62a94db0400ef0cdc046
-- 
2.31.0.291.g576ba9dcdaf-goog