https://github.com/torvalds/linux
Revision 58ec3b4db9eb5a28e3aec5f407a54e28f7039c19 authored by Herbert Xu on 07 October 2008, 22:50:03 UTC, committed by David S. Miller on 07 October 2008, 22:50:03 UTC
Benjamin Thery tracked down a bug that explains many instances
of the error

unregister_netdevice: waiting for %s to become free. Usage count = %d

It turns out that netdev_run_todo can dead-lock with itself if
a second instance of it is run in a thread that will then free
a reference to the device waited on by the first instance.

The problem is really quite silly.  We were trying to create
parallelism where none was required.  As netdev_run_todo always
follows a RTNL section, and that todo tasks can only be added
with the RTNL held, by definition you should only need to wait
for the very ones that you've added and be done with it.

There is no need for a second mutex or spinlock.

This is exactly what the following patch does.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent 742201e
Raw File
Tip revision: 58ec3b4db9eb5a28e3aec5f407a54e28f7039c19 authored by Herbert Xu on 07 October 2008, 22:50:03 UTC
net: Fix netdev_run_todo dead-lock
Tip revision: 58ec3b4
mmzone.c
/*
 * linux/mm/mmzone.c
 *
 * management codes for pgdats and zones.
 */


#include <linux/stddef.h>
#include <linux/mmzone.h>
#include <linux/module.h>

struct pglist_data *first_online_pgdat(void)
{
	return NODE_DATA(first_online_node);
}

struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
{
	int nid = next_online_node(pgdat->node_id);

	if (nid == MAX_NUMNODES)
		return NULL;
	return NODE_DATA(nid);
}

/*
 * next_zone - helper magic for for_each_zone()
 */
struct zone *next_zone(struct zone *zone)
{
	pg_data_t *pgdat = zone->zone_pgdat;

	if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
		zone++;
	else {
		pgdat = next_online_pgdat(pgdat);
		if (pgdat)
			zone = pgdat->node_zones;
		else
			zone = NULL;
	}
	return zone;
}

static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
{
#ifdef CONFIG_NUMA
	return node_isset(zonelist_node_idx(zref), *nodes);
#else
	return 1;
#endif /* CONFIG_NUMA */
}

/* Returns the next zone at or below highest_zoneidx in a zonelist */
struct zoneref *next_zones_zonelist(struct zoneref *z,
					enum zone_type highest_zoneidx,
					nodemask_t *nodes,
					struct zone **zone)
{
	/*
	 * Find the next suitable zone to use for the allocation.
	 * Only filter based on nodemask if it's set
	 */
	if (likely(nodes == NULL))
		while (zonelist_zone_idx(z) > highest_zoneidx)
			z++;
	else
		while (zonelist_zone_idx(z) > highest_zoneidx ||
				(z->zone && !zref_in_nodemask(z, nodes)))
			z++;

	*zone = zonelist_zone(z);
	return z;
}
back to top