f0e9b7d640
When we do a device replace, for each device extent we find from the source device, we set the corresponding block group to readonly mode to prevent writes into it from happening while we are copying the device extent from the source to the target device. However just before we set the block group to readonly mode some concurrent task might have already allocated an extent from it or decided it could perform a nocow write into one of its extents, which can make the device replace process to miss copying an extent since it uses the extent tree's commit root to search for extents and only once it finishes searching for all extents belonging to the block group it does set the left cursor to the logical end address of the block group - this is a problem if the respective ordered extents finish while we are searching for extents using the extent tree's commit root and no transaction commit happens while we are iterating the tree, since it's the delayed references created by the ordered extents (when they complete) that insert the extent items into the extent tree (using the non-commit root of course). Example: CPU 1 CPU 2 btrfs_dev_replace_start() btrfs_scrub_dev() scrub_enumerate_chunks() --> finds device extent belonging to block group X <transaction N starts> starts buffered write against some inode writepages is run against that inode forcing dellaloc to run btrfs_writepages() extent_writepages() extent_write_cache_pages() __extent_writepage() writepage_delalloc() run_delalloc_range() cow_file_range() btrfs_reserve_extent() --> allocates an extent from block group X (which is not yet in RO mode) btrfs_add_ordered_extent() --> creates ordered extent Y flush_epd_write_bio() --> bio against the extent from block group X is submitted btrfs_inc_block_group_ro(bg X) --> sets block group X to readonly scrub_chunk(bg X) scrub_stripe(device extent from srcdev) --> keeps searching for extent items belonging to the block group using the extent tree's commit root --> it never blocks due to fs_info->scrub_pause_req as no one tries to commit transaction N --> copies all extents found from the source device into the target device --> finishes search loop bio completes ordered extent Y completes and creates delayed data reference which will add an extent item to the extent tree when run (typically at transaction commit time) --> so the task doing the scrub/device replace at CPU 1 misses this and does not copy this extent into the new/target device btrfs_dec_block_group_ro(bg X) --> turns block group X back to RW mode dev_replace->cursor_left is set to the logical end offset of block group X So fix this by waiting for all cow and nocow writes after setting a block group to readonly mode. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: Josef Bacik <jbacik@fb.com>
216 lines
7.1 KiB
C
216 lines
7.1 KiB
C
/*
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public
|
|
* License v2 as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public
|
|
* License along with this program; if not, write to the
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 021110-1307, USA.
|
|
*/
|
|
|
|
#ifndef __BTRFS_ORDERED_DATA__
|
|
#define __BTRFS_ORDERED_DATA__
|
|
|
|
/* 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 */
|
|
u32 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.
|
|
*/
|
|
#define BTRFS_ORDERED_IO_DONE 0 /* set when all the pages are written */
|
|
|
|
#define BTRFS_ORDERED_COMPLETE 1 /* set when removed from the tree */
|
|
|
|
#define BTRFS_ORDERED_NOCOW 2 /* set when we want to write in place */
|
|
|
|
#define BTRFS_ORDERED_COMPRESSED 3 /* writing a zlib compressed extent */
|
|
|
|
#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to preallocated extent */
|
|
|
|
#define BTRFS_ORDERED_DIRECT 5 /* set when we're doing DIO with this extent */
|
|
|
|
#define BTRFS_ORDERED_IOERR 6 /* We had an io error when writing this out */
|
|
|
|
#define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent
|
|
* has done its due diligence in updating
|
|
* the isize. */
|
|
#define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered
|
|
ordered extent */
|
|
#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */
|
|
|
|
#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent
|
|
* in the logging code. */
|
|
#define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to
|
|
* complete in the current transaction. */
|
|
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 */
|
|
atomic_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_root *root,
|
|
unsigned long bytes)
|
|
{
|
|
int num_sectors = (int)DIV_ROUND_UP(bytes, root->sectorsize);
|
|
return sizeof(struct btrfs_ordered_sum) + num_sectors * sizeof(u32);
|
|
}
|
|
|
|
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 inode *inode,
|
|
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 inode *inode,
|
|
u64 file_offset,
|
|
u64 len);
|
|
bool btrfs_have_ordered_extents_in_range(struct 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,
|
|
u32 *sum, int len);
|
|
int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
|
|
const u64 range_start, const u64 range_len);
|
|
int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
|
|
const u64 range_start, const u64 range_len);
|
|
void btrfs_get_logged_extents(struct inode *inode,
|
|
struct list_head *logged_list,
|
|
const loff_t start,
|
|
const loff_t end);
|
|
void btrfs_put_logged_extents(struct list_head *logged_list);
|
|
void btrfs_submit_logged_extents(struct list_head *logged_list,
|
|
struct btrfs_root *log);
|
|
void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *log, u64 transid);
|
|
void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
|
|
int __init ordered_data_init(void);
|
|
void ordered_data_exit(void);
|
|
#endif
|