forked from luck/tmp_suning_uos_patched
09a2a8f96e
A user sent me a btrfs-image of a file system that was panicing on mount during the log recovery. I had originally thought these problems were from a bug in the free space cache code, but that was just a symptom of the problem. The problem is if your application does something like this [prealloc][prealloc][prealloc] the internal extent maps will merge those all together into one extent map, even though on disk they are 3 separate extents. So if you go to write into one of these ranges the extent map will be right since we use the physical extent when doing the write, but when we log the extents they will use the wrong sizes for the remainder prealloc space. If this doesn't happen to trip up the free space cache (which it won't in a lot of cases) then you will get bogus entries in your extent tree which will screw stuff up later. The data and such will still work, but everything else is broken. This patch fixes this by not allowing extents that are on the modified list to be merged. This has the side effect that we are no longer adding everything to the modified list all the time, which means we now have to call btrfs_drop_extents every time we log an extent into the tree. So this allows me to drop all this speciality code I was using to get around calling btrfs_drop_extents. With this patch the testcase I've created no longer creates a bogus file system after replaying the log. Thanks, Signed-off-by: Josef Bacik <jbacik@fusionio.com>
77 lines
2.1 KiB
C
77 lines
2.1 KiB
C
#ifndef __EXTENTMAP__
|
|
#define __EXTENTMAP__
|
|
|
|
#include <linux/rbtree.h>
|
|
|
|
#define EXTENT_MAP_LAST_BYTE (u64)-4
|
|
#define EXTENT_MAP_HOLE (u64)-3
|
|
#define EXTENT_MAP_INLINE (u64)-2
|
|
#define EXTENT_MAP_DELALLOC (u64)-1
|
|
|
|
/* bits for the flags field */
|
|
#define EXTENT_FLAG_PINNED 0 /* this entry not yet on disk, don't free it */
|
|
#define EXTENT_FLAG_COMPRESSED 1
|
|
#define EXTENT_FLAG_VACANCY 2 /* no file extent item found */
|
|
#define EXTENT_FLAG_PREALLOC 3 /* pre-allocated extent */
|
|
#define EXTENT_FLAG_LOGGING 4 /* Logging this extent */
|
|
#define EXTENT_FLAG_FILLING 5 /* Filling in a preallocated extent */
|
|
|
|
struct extent_map {
|
|
struct rb_node rb_node;
|
|
|
|
/* all of these are in bytes */
|
|
u64 start;
|
|
u64 len;
|
|
u64 mod_start;
|
|
u64 mod_len;
|
|
u64 orig_start;
|
|
u64 orig_block_len;
|
|
u64 ram_bytes;
|
|
u64 block_start;
|
|
u64 block_len;
|
|
u64 generation;
|
|
unsigned long flags;
|
|
struct block_device *bdev;
|
|
atomic_t refs;
|
|
unsigned int in_tree;
|
|
unsigned int compress_type;
|
|
struct list_head list;
|
|
};
|
|
|
|
struct extent_map_tree {
|
|
struct rb_root map;
|
|
struct list_head modified_extents;
|
|
rwlock_t lock;
|
|
};
|
|
|
|
static inline u64 extent_map_end(struct extent_map *em)
|
|
{
|
|
if (em->start + em->len < em->start)
|
|
return (u64)-1;
|
|
return em->start + em->len;
|
|
}
|
|
|
|
static inline u64 extent_map_block_end(struct extent_map *em)
|
|
{
|
|
if (em->block_start + em->block_len < em->block_start)
|
|
return (u64)-1;
|
|
return em->block_start + em->block_len;
|
|
}
|
|
|
|
void extent_map_tree_init(struct extent_map_tree *tree);
|
|
struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree,
|
|
u64 start, u64 len);
|
|
int add_extent_mapping(struct extent_map_tree *tree,
|
|
struct extent_map *em, int modified);
|
|
int remove_extent_mapping(struct extent_map_tree *tree, struct extent_map *em);
|
|
|
|
struct extent_map *alloc_extent_map(void);
|
|
void free_extent_map(struct extent_map *em);
|
|
int __init extent_map_init(void);
|
|
void extent_map_exit(void);
|
|
int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen);
|
|
void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em);
|
|
struct extent_map *search_extent_mapping(struct extent_map_tree *tree,
|
|
u64 start, u64 len);
|
|
#endif
|