mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 10:00:51 +07:00
042528f8d8
When doing a device replace, while at scrub.c:scrub_enumerate_chunks(), we
set the block group to RO mode and then wait for any ongoing writes into
extents of the block group to complete. While doing that wait we overwrite
the value of the variable 'ret' and can break out of the loop if an error
happens without turning the block group back into RW mode. So what happens
is the following:
1) btrfs_inc_block_group_ro() returns 0, meaning it set the block group
to RO mode (its ->ro field set to 1 or incremented to some value > 1);
2) Then btrfs_wait_ordered_roots() returns a value > 0;
3) Then if either joining or committing the transaction fails, we break
out of the loop wihtout calling btrfs_dec_block_group_ro(), leaving
the block group in RO mode forever.
To fix this, just remove the code that waits for ongoing writes to extents
of the block group, since it's not needed because in the initial setup
phase of a device replace operation, before starting to find all chunks
and their extents, we set the target device for replace while holding
fs_info->dev_replace->rwsem, which ensures that after releasing that
semaphore, any writes into the source device are made to the target device
as well (__btrfs_map_block() guarantees that). So while at
scrub_enumerate_chunks() we only need to worry about finding and copying
extents (from the source device to the target device) that were written
before we started the device replace operation.
Fixes: f0e9b7d640
("Btrfs: fix race setting block group readonly during device replace")
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
199 lines
5.8 KiB
C
199 lines
5.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
*/
|
|
|
|
#ifndef BTRFS_ORDERED_DATA_H
|
|
#define BTRFS_ORDERED_DATA_H
|
|
|
|
/* one of these per inode */
|
|
struct btrfs_ordered_inode_tree {
|
|
spinlock_t lock;
|
|
struct rb_root tree;
|
|
struct rb_node *last;
|
|
};
|
|
|
|
struct btrfs_ordered_sum {
|
|
/* bytenr is the start of this extent on disk */
|
|
u64 bytenr;
|
|
|
|
/*
|
|
* this is the length in bytes covered by the sums array below.
|
|
*/
|
|
int len;
|
|
struct list_head list;
|
|
/* last field is a variable length array of csums */
|
|
u8 sums[];
|
|
};
|
|
|
|
/*
|
|
* bits for the flags field:
|
|
*
|
|
* BTRFS_ORDERED_IO_DONE is set when all of the blocks are written.
|
|
* It is used to make sure metadata is inserted into the tree only once
|
|
* per extent.
|
|
*
|
|
* BTRFS_ORDERED_COMPLETE is set when the extent is removed from the
|
|
* rbtree, just before waking any waiters. It is used to indicate the
|
|
* IO is done and any metadata is inserted into the tree.
|
|
*/
|
|
enum {
|
|
/* set when all the pages are written */
|
|
BTRFS_ORDERED_IO_DONE,
|
|
/* set when removed from the tree */
|
|
BTRFS_ORDERED_COMPLETE,
|
|
/* set when we want to write in place */
|
|
BTRFS_ORDERED_NOCOW,
|
|
/* writing a zlib compressed extent */
|
|
BTRFS_ORDERED_COMPRESSED,
|
|
/* set when writing to preallocated extent */
|
|
BTRFS_ORDERED_PREALLOC,
|
|
/* set when we're doing DIO with this extent */
|
|
BTRFS_ORDERED_DIRECT,
|
|
/* We had an io error when writing this out */
|
|
BTRFS_ORDERED_IOERR,
|
|
/*
|
|
* indicates whether this ordered extent has done its due diligence in
|
|
* updating the isize
|
|
*/
|
|
BTRFS_ORDERED_UPDATED_ISIZE,
|
|
/* Set when we have to truncate an extent */
|
|
BTRFS_ORDERED_TRUNCATED,
|
|
/* Regular IO for COW */
|
|
BTRFS_ORDERED_REGULAR,
|
|
};
|
|
|
|
struct btrfs_ordered_extent {
|
|
/* logical offset in the file */
|
|
u64 file_offset;
|
|
|
|
/* disk byte number */
|
|
u64 start;
|
|
|
|
/* ram length of the extent in bytes */
|
|
u64 len;
|
|
|
|
/* extent length on disk */
|
|
u64 disk_len;
|
|
|
|
/* number of bytes that still need writing */
|
|
u64 bytes_left;
|
|
|
|
/*
|
|
* the end of the ordered extent which is behind it but
|
|
* didn't update disk_i_size. Please see the comment of
|
|
* btrfs_ordered_update_i_size();
|
|
*/
|
|
u64 outstanding_isize;
|
|
|
|
/*
|
|
* If we get truncated we need to adjust the file extent we enter for
|
|
* this ordered extent so that we do not expose stale data.
|
|
*/
|
|
u64 truncated_len;
|
|
|
|
/* flags (described above) */
|
|
unsigned long flags;
|
|
|
|
/* compression algorithm */
|
|
int compress_type;
|
|
|
|
/* reference count */
|
|
refcount_t refs;
|
|
|
|
/* the inode we belong to */
|
|
struct inode *inode;
|
|
|
|
/* list of checksums for insertion when the extent io is done */
|
|
struct list_head list;
|
|
|
|
/* If we need to wait on this to be done */
|
|
struct list_head log_list;
|
|
|
|
/* If the transaction needs to wait on this ordered extent */
|
|
struct list_head trans_list;
|
|
|
|
/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
|
|
wait_queue_head_t wait;
|
|
|
|
/* our friendly rbtree entry */
|
|
struct rb_node rb_node;
|
|
|
|
/* a per root list of all the pending ordered extents */
|
|
struct list_head root_extent_list;
|
|
|
|
struct btrfs_work work;
|
|
|
|
struct completion completion;
|
|
struct btrfs_work flush_work;
|
|
struct list_head work_list;
|
|
};
|
|
|
|
/*
|
|
* calculates the total size you need to allocate for an ordered sum
|
|
* structure spanning 'bytes' in the file
|
|
*/
|
|
static inline int btrfs_ordered_sum_size(struct btrfs_fs_info *fs_info,
|
|
unsigned long bytes)
|
|
{
|
|
int num_sectors = (int)DIV_ROUND_UP(bytes, fs_info->sectorsize);
|
|
int csum_size = btrfs_super_csum_size(fs_info->super_copy);
|
|
|
|
return sizeof(struct btrfs_ordered_sum) + num_sectors * csum_size;
|
|
}
|
|
|
|
static inline void
|
|
btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t)
|
|
{
|
|
spin_lock_init(&t->lock);
|
|
t->tree = RB_ROOT;
|
|
t->last = NULL;
|
|
}
|
|
|
|
void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
|
|
void btrfs_remove_ordered_extent(struct inode *inode,
|
|
struct btrfs_ordered_extent *entry);
|
|
int btrfs_dec_test_ordered_pending(struct inode *inode,
|
|
struct btrfs_ordered_extent **cached,
|
|
u64 file_offset, u64 io_size, int uptodate);
|
|
int btrfs_dec_test_first_ordered_pending(struct inode *inode,
|
|
struct btrfs_ordered_extent **cached,
|
|
u64 *file_offset, u64 io_size,
|
|
int uptodate);
|
|
int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
|
|
u64 start, u64 len, u64 disk_len, int type);
|
|
int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
|
|
u64 start, u64 len, u64 disk_len, int type);
|
|
int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
|
|
u64 start, u64 len, u64 disk_len,
|
|
int type, int compress_type);
|
|
void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
|
|
struct btrfs_ordered_sum *sum);
|
|
struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
|
|
u64 file_offset);
|
|
void btrfs_start_ordered_extent(struct inode *inode,
|
|
struct btrfs_ordered_extent *entry, int wait);
|
|
int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
|
|
struct btrfs_ordered_extent *
|
|
btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset);
|
|
struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
|
|
struct btrfs_inode *inode,
|
|
u64 file_offset,
|
|
u64 len);
|
|
int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
|
|
struct btrfs_ordered_extent *ordered);
|
|
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
|
|
u8 *sum, int len);
|
|
u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
|
|
const u64 range_start, const u64 range_len);
|
|
void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
|
|
const u64 range_start, const u64 range_len);
|
|
void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree,
|
|
struct btrfs_inode *inode, u64 start,
|
|
u64 end,
|
|
struct extent_state **cached_state);
|
|
int __init ordered_data_init(void);
|
|
void __cold ordered_data_exit(void);
|
|
|
|
#endif
|