Skip to main content

Browse the archive

Revision 1a3f2fd7fc4e8f24510830e265de2ffb8e3300d2 authored by Lu Baolu on 27 September 2020, 06:24:28 UTC, committed by Joerg Roedel on 01 October 2020, 12:54:17 UTC 
iommu/vt-d: Fix lockdep splat in iommu_flush_dev_iotlb()
 
Lock(&iommu->lock) without disabling irq causes lockdep warnings.

[   12.703950] ========================================================
[   12.703962] WARNING: possible irq lock inversion dependency detected
[   12.703975] 5.9.0-rc6+ #659 Not tainted
[   12.703983] --------------------------------------------------------
[   12.703995] systemd-udevd/284 just changed the state of lock:
[   12.704007] ffffffffbd6ff4d8 (device_domain_lock){..-.}-{2:2}, at:
               iommu_flush_dev_iotlb.part.57+0x2e/0x90
[   12.704031] but this lock took another, SOFTIRQ-unsafe lock in the past:
[   12.704043]  (&iommu->lock){+.+.}-{2:2}
[   12.704045]

               and interrupts could create inverse lock ordering between
               them.

[   12.704073]
               other info that might help us debug this:
[   12.704085]  Possible interrupt unsafe locking scenario:

[   12.704097]        CPU0                    CPU1
[   12.704106]        ----                    ----
[   12.704115]   lock(&iommu->lock);
[   12.704123]                                local_irq_disable();
[   12.704134]                                lock(device_domain_lock);
[   12.704146]                                lock(&iommu->lock);
[   12.704158]   <Interrupt>
[   12.704164]     lock(device_domain_lock);
[   12.704174]
                *** DEADLOCK ***

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20200927062428.13713-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
1 parent 0bbe4ce
Raw File
mmzone.c 
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/mm/mmzone.c
 *
 * management codes for pgdats, zones and page flags
 */


#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/mmzone.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)
{
	/*
	 * Find the next suitable zone to use for the allocation.
	 * Only filter based on nodemask if it's set
	 */
	if (unlikely(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++;

	return z;
}

#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
bool memmap_valid_within(unsigned long pfn,
					struct page *page, struct zone *zone)
{
	if (page_to_pfn(page) != pfn)
		return false;

	if (page_zone(page) != zone)
		return false;

	return true;
}
#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */

void lruvec_init(struct lruvec *lruvec)
{
	enum lru_list lru;

	memset(lruvec, 0, sizeof(struct lruvec));

	for_each_lru(lru)
		INIT_LIST_HEAD(&lruvec->lists[lru]);
}

#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
int page_cpupid_xchg_last(struct page *page, int cpupid)
{
	unsigned long old_flags, flags;
	int last_cpupid;

	do {
		old_flags = flags = page->flags;
		last_cpupid = page_cpupid_last(page);

		flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
		flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
	} while (unlikely(cmpxchg(&page->flags, old_flags, flags) != old_flags));

	return last_cpupid;
}
#endif
back to top