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
interval_tree.c 
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm/interval_tree.c - interval tree for mapping->i_mmap
 *
 * Copyright (C) 2012, Michel Lespinasse <walken@google.com>
 */

#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/rmap.h>
#include <linux/interval_tree_generic.h>

static inline unsigned long vma_start_pgoff(struct vm_area_struct *v)
{
	return v->vm_pgoff;
}

static inline unsigned long vma_last_pgoff(struct vm_area_struct *v)
{
	return v->vm_pgoff + vma_pages(v) - 1;
}

INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb,
		     unsigned long, shared.rb_subtree_last,
		     vma_start_pgoff, vma_last_pgoff,, vma_interval_tree)

/* Insert node immediately after prev in the interval tree */
void vma_interval_tree_insert_after(struct vm_area_struct *node,
				    struct vm_area_struct *prev,
				    struct rb_root_cached *root)
{
	struct rb_node **link;
	struct vm_area_struct *parent;
	unsigned long last = vma_last_pgoff(node);

	VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node);

	if (!prev->shared.rb.rb_right) {
		parent = prev;
		link = &prev->shared.rb.rb_right;
	} else {
		parent = rb_entry(prev->shared.rb.rb_right,
				  struct vm_area_struct, shared.rb);
		if (parent->shared.rb_subtree_last < last)
			parent->shared.rb_subtree_last = last;
		while (parent->shared.rb.rb_left) {
			parent = rb_entry(parent->shared.rb.rb_left,
				struct vm_area_struct, shared.rb);
			if (parent->shared.rb_subtree_last < last)
				parent->shared.rb_subtree_last = last;
		}
		link = &parent->shared.rb.rb_left;
	}

	node->shared.rb_subtree_last = last;
	rb_link_node(&node->shared.rb, &parent->shared.rb, link);
	rb_insert_augmented(&node->shared.rb, &root->rb_root,
			    &vma_interval_tree_augment);
}

static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc)
{
	return vma_start_pgoff(avc->vma);
}

static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc)
{
	return vma_last_pgoff(avc->vma);
}

INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last,
		     avc_start_pgoff, avc_last_pgoff,
		     static inline, __anon_vma_interval_tree)

void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
				   struct rb_root_cached *root)
{
#ifdef CONFIG_DEBUG_VM_RB
	node->cached_vma_start = avc_start_pgoff(node);
	node->cached_vma_last = avc_last_pgoff(node);
#endif
	__anon_vma_interval_tree_insert(node, root);
}

void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
				   struct rb_root_cached *root)
{
	__anon_vma_interval_tree_remove(node, root);
}

struct anon_vma_chain *
anon_vma_interval_tree_iter_first(struct rb_root_cached *root,
				  unsigned long first, unsigned long last)
{
	return __anon_vma_interval_tree_iter_first(root, first, last);
}

struct anon_vma_chain *
anon_vma_interval_tree_iter_next(struct anon_vma_chain *node,
				 unsigned long first, unsigned long last)
{
	return __anon_vma_interval_tree_iter_next(node, first, last);
}

#ifdef CONFIG_DEBUG_VM_RB
void anon_vma_interval_tree_verify(struct anon_vma_chain *node)
{
	WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node));
	WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node));
}
#endif
back to top