Revision 082cd4ec240b8734a82a89ffb890216ac98fec68 authored by Ye Bin on 06 May 2021, 14:10:42 UTC, committed by Theodore Ts'o on 06 June 2021, 14:09:55 UTC
We got follow bug_on when run fsstress with injecting IO fault:
[130747.323114] kernel BUG at fs/ext4/extents_status.c:762!
[130747.323117] Internal error: Oops - BUG: 0 [#1] SMP
......
[130747.334329] Call trace:
[130747.334553]  ext4_es_cache_extent+0x150/0x168 [ext4]
[130747.334975]  ext4_cache_extents+0x64/0xe8 [ext4]
[130747.335368]  ext4_find_extent+0x300/0x330 [ext4]
[130747.335759]  ext4_ext_map_blocks+0x74/0x1178 [ext4]
[130747.336179]  ext4_map_blocks+0x2f4/0x5f0 [ext4]
[130747.336567]  ext4_mpage_readpages+0x4a8/0x7a8 [ext4]
[130747.336995]  ext4_readpage+0x54/0x100 [ext4]
[130747.337359]  generic_file_buffered_read+0x410/0xae8
[130747.337767]  generic_file_read_iter+0x114/0x190
[130747.338152]  ext4_file_read_iter+0x5c/0x140 [ext4]
[130747.338556]  __vfs_read+0x11c/0x188
[130747.338851]  vfs_read+0x94/0x150
[130747.339110]  ksys_read+0x74/0xf0

This patch's modification is according to Jan Kara's suggestion in:
https://patchwork.ozlabs.org/project/linux-ext4/patch/20210428085158.3728201-1-yebin10@huawei.com/
"I see. Now I understand your patch. Honestly, seeing how fragile is trying
to fix extent tree after split has failed in the middle, I would probably
go even further and make sure we fix the tree properly in case of ENOSPC
and EDQUOT (those are easily user triggerable).  Anything else indicates a
HW problem or fs corruption so I'd rather leave the extent tree as is and
don't try to fix it (which also means we will not create overlapping
extents)."

Cc: stable@kernel.org
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20210506141042.3298679-1-yebin10@huawei.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
1 parent b45f189
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