Skip to content

C
clone-Linux

gsplhtlxg / clone-Linux

通知 2
Star 0
Fork 1
C
clone-Linux

体验新版 GitCode，发现更多精彩内容 >>

提交 97d0bf96 编写于 作者: L Linus Torvalds
浏览文件
操作

Merge tag 'for-5.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux 

Pull btrfs updates from David Sterba:
 "User visible changes:
   - new block group profiles: RAID1 with 3- and 4- copies
       - RAID1 in btrfs has always 2 copies, now add support for 3 and 4
       - this is an incompat feature (named RAID1C34)
       - recommended use of RAID1C3 is replacement of RAID6 profile on
         metadata, this brings a more reliable resiliency against 2
         device loss/damage

   - support for new checksums
       - per-filesystem, set at mkfs time
       - fast hash (crc32c successor): xxhash, 64bit digest
       - strong hashes (both 256bit): sha256 (slower, FIPS), blake2b
         (faster)
       - the blake2b module goes via the crypto tree, btrfs.ko has a
         soft dependency

   - speed up lseek, don't take inode locks unnecessarily, this can
     speed up parallel SEEK_CUR/SEEK_SET/SEEK_END by 80%

   - send:
       - allow clone operations within the same file
       - limit maximum number of sent clone references to avoid slow
         backref walking

   - error message improvements: device scan prints process name and PID

  Core changes:
   - cleanups
       - remove unique workqueue helpers, used to provide a way to avoid
         deadlocks in the workqueue code, now done in a simpler way
       - remove lots of indirect function calls in compression code
       - extent IO tree code moved out of extent_io.c
       - cleanup backup superblock handling at mount time
       - transaction life cycle documentation and cleanups
       - locking code cleanups, annotations and documentation
       - add more cold, const, pure function attributes
       - removal of unused or redundant struct members or variables

   - new tree-checker sanity tests
       - try to detect missing INODE_ITEM, cross-reference checks of
         DIR_ITEM, DIR_INDEX, INODE_REF, and XATTR_* items

   - remove own bio scheduling code (used to avoid checksum submissions
     being stuck behind other IO), replaced by cgroup controller-based
     code to allow better control and avoid priority inversions in cases
     where the custom and cgroup scheduling disagreed

  Fixes:
   - avoid getting stuck during cyclic writebacks

   - fix trimming of ranges crossing block group boundaries

   - fix rename exchange on subvolumes, all involved subvolumes need to
     be recorded in the transaction"

* tag 'for-5.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (137 commits)
  btrfs: drop bdev argument from submit_extent_page
  btrfs: remove extent_map::bdev
  btrfs: drop bio_set_dev where not needed
  btrfs: get bdev directly from fs_devices in submit_extent_page
  btrfs: record all roots for rename exchange on a subvol
  Btrfs: fix block group remaining RO forever after error during device replace
  btrfs: scrub: Don't check free space before marking a block group RO
  btrfs: change btrfs_fs_devices::rotating to bool
  btrfs: change btrfs_fs_devices::seeding to bool
  btrfs: rename btrfs_block_group_cache
  btrfs: block-group: Reuse the item key from caller of read_one_block_group()
  btrfs: block-group: Refactor btrfs_read_block_groups()
  btrfs: document extent buffer locking
  btrfs: access eb::blocking_writers according to ACCESS_ONCE policies
  btrfs: set blocking_writers directly, no increment or decrement
  btrfs: merge blocking_writers branches in btrfs_tree_read_lock
  btrfs: drop incompat bit for raid1c34 after last block group is gone
  btrfs: add incompat for raid1 with 3, 4 copies
  btrfs: add support for 4-copy replication (raid1c4)
  btrfs: add support for 3-copy replication (raid1c3)
  ...
上级 1b88176b fa17ed06
展开全部 隐藏空白更改
内联 并排
Showing with 2780 addition and 2619 deletion
fs/btrfs/Kconfig
浏览文件 @ 97d0bf96
......@@ -5,6 +5,8 @@ config BTRFS_FS
select CRYPTO
select CRYPTO_CRC32C
select LIBCRC32C
select CRYPTO_XXHASH
select CRYPTO_SHA256
select ZLIB_INFLATE
select ZLIB_DEFLATE
select LZO_COMPRESS
......
fs/btrfs/async-thread.c
浏览文件 @ 97d0bf96
......@@ -53,24 +53,12 @@ struct btrfs_workqueue {
struct __btrfs_workqueue *high;
};
static void normal_work_helper(struct btrfs_work *work);
#define BTRFS_WORK_HELPER(name) \
noinline_for_stack void btrfs_##name(struct work_struct *arg) \
{ \
struct btrfs_work *work = container_of(arg, struct btrfs_work, \
normal_work); \
normal_work_helper(work); \
}
struct btrfs_fs_info *
btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq)
{
return wq->fs_info;
}
struct btrfs_fs_info *
btrfs_work_owner(const struct btrfs_work *work)
struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work)
{
return work->wq->fs_info;
}
......@@ -89,29 +77,6 @@ bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq)
return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
}
BTRFS_WORK_HELPER(worker_helper);
BTRFS_WORK_HELPER(delalloc_helper);
BTRFS_WORK_HELPER(flush_delalloc_helper);
BTRFS_WORK_HELPER(cache_helper);
BTRFS_WORK_HELPER(submit_helper);
BTRFS_WORK_HELPER(fixup_helper);
BTRFS_WORK_HELPER(endio_helper);
BTRFS_WORK_HELPER(endio_meta_helper);
BTRFS_WORK_HELPER(endio_meta_write_helper);
BTRFS_WORK_HELPER(endio_raid56_helper);
BTRFS_WORK_HELPER(endio_repair_helper);
BTRFS_WORK_HELPER(rmw_helper);
BTRFS_WORK_HELPER(endio_write_helper);
BTRFS_WORK_HELPER(freespace_write_helper);
BTRFS_WORK_HELPER(delayed_meta_helper);
BTRFS_WORK_HELPER(readahead_helper);
BTRFS_WORK_HELPER(qgroup_rescan_helper);
BTRFS_WORK_HELPER(extent_refs_helper);
BTRFS_WORK_HELPER(scrub_helper);
BTRFS_WORK_HELPER(scrubwrc_helper);
BTRFS_WORK_HELPER(scrubnc_helper);
BTRFS_WORK_HELPER(scrubparity_helper);
static struct __btrfs_workqueue *
__btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info, const char *name,
unsigned int flags, int limit_active, int thresh)
......@@ -252,16 +217,16 @@ static inline void thresh_exec_hook(struct __btrfs_workqueue *wq)
}
}
static void run_ordered_work(struct __btrfs_workqueue *wq)
static void run_ordered_work(struct __btrfs_workqueue *wq,
struct btrfs_work *self)
{
struct list_head *list = &wq->ordered_list;
struct btrfs_work *work;
spinlock_t *lock = &wq->list_lock;
unsigned long flags;
bool free_self = false;
while (1) {
void *wtag;
spin_lock_irqsave(lock, flags);
if (list_empty(list))
break;
......@@ -287,22 +252,53 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
list_del(&work->ordered_list);
spin_unlock_irqrestore(lock, flags);
/*
* We don't want to call the ordered free functions with the
* lock held though. Save the work as tag for the trace event,
* because the callback could free the structure.
*/
wtag = work;
work->ordered_free(work);
trace_btrfs_all_work_done(wq->fs_info, wtag);
if (work == self) {
/*
* This is the work item that the worker is currently
* executing.
*
* The kernel workqueue code guarantees non-reentrancy
* of work items. I.e., if a work item with the same
* address and work function is queued twice, the second
* execution is blocked until the first one finishes. A
* work item may be freed and recycled with the same
* work function; the workqueue code assumes that the
* original work item cannot depend on the recycled work
* item in that case (see find_worker_executing_work()).
*
* Note that different types of Btrfs work can depend on
* each other, and one type of work on one Btrfs
* filesystem may even depend on the same type of work
* on another Btrfs filesystem via, e.g., a loop device.
* Therefore, we must not allow the current work item to
* be recycled until we are really done, otherwise we
* break the above assumption and can deadlock.
*/
free_self = true;
} else {
/*
* We don't want to call the ordered free functions with
* the lock held.
*/
work->ordered_free(work);
/* NB: work must not be dereferenced past this point. */
trace_btrfs_all_work_done(wq->fs_info, work);
}
}
spin_unlock_irqrestore(lock, flags);
if (free_self) {
self->ordered_free(self);
/* NB: self must not be dereferenced past this point. */
trace_btrfs_all_work_done(wq->fs_info, self);
}
}
static void normal_work_helper(struct btrfs_work *work)
static void btrfs_work_helper(struct work_struct *normal_work)
{
struct btrfs_work *work = container_of(normal_work, struct btrfs_work,
normal_work);
struct __btrfs_workqueue *wq;
void *wtag;
int need_order = 0;
/*
......@@ -316,29 +312,26 @@ static void normal_work_helper(struct btrfs_work *work)
if (work->ordered_func)
need_order = 1;
wq = work->wq;
/* Safe for tracepoints in case work gets freed by the callback */
wtag = work;
trace_btrfs_work_sched(work);
thresh_exec_hook(wq);
work->func(work);
if (need_order) {
set_bit(WORK_DONE_BIT, &work->flags);
run_ordered_work(wq);
run_ordered_work(wq, work);
} else {
/* NB: work must not be dereferenced past this point. */
trace_btrfs_all_work_done(wq->fs_info, work);
}
if (!need_order)
trace_btrfs_all_work_done(wq->fs_info, wtag);
}
void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
btrfs_func_t func,
btrfs_func_t ordered_func,
btrfs_func_t ordered_free)
void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
btrfs_func_t ordered_func, btrfs_func_t ordered_free)
{
work->func = func;
work->ordered_func = ordered_func;
work->ordered_free = ordered_free;
INIT_WORK(&work->normal_work, uniq_func);
INIT_WORK(&work->normal_work, btrfs_work_helper);
INIT_LIST_HEAD(&work->ordered_list);
work->flags = 0;
}
......
fs/btrfs/async-thread.h
浏览文件 @ 97d0bf96
......@@ -29,49 +29,20 @@ struct btrfs_work {
unsigned long flags;
};
#define BTRFS_WORK_HELPER_PROTO(name) \
void btrfs_##name(struct work_struct *arg)
BTRFS_WORK_HELPER_PROTO(worker_helper);
BTRFS_WORK_HELPER_PROTO(delalloc_helper);
BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
BTRFS_WORK_HELPER_PROTO(cache_helper);
BTRFS_WORK_HELPER_PROTO(submit_helper);
BTRFS_WORK_HELPER_PROTO(fixup_helper);
BTRFS_WORK_HELPER_PROTO(endio_helper);
BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
BTRFS_WORK_HELPER_PROTO(endio_repair_helper);
BTRFS_WORK_HELPER_PROTO(rmw_helper);
BTRFS_WORK_HELPER_PROTO(endio_write_helper);
BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
BTRFS_WORK_HELPER_PROTO(readahead_helper);
BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
BTRFS_WORK_HELPER_PROTO(scrub_helper);
BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
BTRFS_WORK_HELPER_PROTO(scrubparity_helper);
struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
const char *name,
unsigned int flags,
int limit_active,
int thresh);
void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
btrfs_func_t func,
btrfs_func_t ordered_func,
btrfs_func_t ordered_free);
void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
btrfs_func_t ordered_func, btrfs_func_t ordered_free);
void btrfs_queue_work(struct btrfs_workqueue *wq,
struct btrfs_work *work);
void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
void btrfs_set_work_high_priority(struct btrfs_work *work);
struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work);
struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work);
struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct __btrfs_workqueue *wq);
bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
#endif
fs/btrfs/block-group.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/block-group.h
浏览文件 @ 97d0bf96
......@@ -34,7 +34,7 @@ struct btrfs_caching_control {
struct mutex mutex;
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group_cache *block_group;
struct btrfs_block_group *block_group;
u64 progress;
refcount_t count;
};
......@@ -42,14 +42,15 @@ struct btrfs_caching_control {
/* Once caching_thread() finds this much free space, it will wake up waiters. */
#define CACHING_CTL_WAKE_UP SZ_2M
struct btrfs_block_group_cache {
struct btrfs_key key;
struct btrfs_block_group_item item;
struct btrfs_block_group {
struct btrfs_fs_info *fs_info;
struct inode *inode;
spinlock_t lock;
u64 start;
u64 length;
u64 pinned;
u64 reserved;
u64 used;
u64 delalloc_bytes;
u64 bytes_super;
u64 flags;
......@@ -159,7 +160,7 @@ struct btrfs_block_group_cache {
#ifdef CONFIG_BTRFS_DEBUG
static inline int btrfs_should_fragment_free_space(
struct btrfs_block_group_cache *block_group)
struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
......@@ -170,29 +171,29 @@ static inline int btrfs_should_fragment_free_space(
}
#endif
struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
struct btrfs_block_group *btrfs_lookup_first_block_group(
struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group_cache *btrfs_lookup_block_group(
struct btrfs_block_group *btrfs_lookup_block_group(
struct btrfs_fs_info *info, u64 bytenr);
struct btrfs_block_group_cache *btrfs_next_block_group(
struct btrfs_block_group_cache *cache);
void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
struct btrfs_block_group *btrfs_next_block_group(
struct btrfs_block_group *cache);
void btrfs_get_block_group(struct btrfs_block_group *cache);
void btrfs_put_block_group(struct btrfs_block_group *cache);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start);
void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
void btrfs_wait_block_group_reservations(struct btrfs_block_group *bg);
bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
void btrfs_wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes);
int btrfs_wait_block_group_cache_done(struct btrfs_block_group_cache *cache);
int btrfs_cache_block_group(struct btrfs_block_group_cache *cache,
int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
int btrfs_cache_block_group(struct btrfs_block_group *cache,
int load_cache_only);
void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
struct btrfs_caching_control *btrfs_get_caching_control(
struct btrfs_block_group_cache *cache);
u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
struct btrfs_block_group *cache);
u64 add_new_free_space(struct btrfs_block_group *block_group,
u64 start, u64 end);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
......@@ -200,21 +201,22 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
u64 group_start, struct extent_map *em);
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
void btrfs_mark_bg_unused(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
u64 type, u64 chunk_offset, u64 size);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
bool do_chunk_alloc);
void btrfs_dec_block_group_ro(struct btrfs_block_group *cache);
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans);
int btrfs_setup_space_cache(struct btrfs_trans_handle *trans);
int btrfs_update_block_group(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, int alloc);
int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
u64 ram_bytes, u64 num_bytes, int delalloc);
void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
u64 num_bytes, int delalloc);
int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
enum btrfs_chunk_alloc_enum force);
......@@ -239,8 +241,7 @@ static inline u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
return btrfs_get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
}
static inline int btrfs_block_group_cache_done(
struct btrfs_block_group_cache *cache)
static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
{
smp_mb();
return cache->cached == BTRFS_CACHE_FINISHED ||
......
fs/btrfs/btrfs_inode.h
浏览文件 @ 97d0bf96
......@@ -63,9 +63,6 @@ struct btrfs_inode {
/* held while logging the inode in tree-log.c */
struct mutex log_mutex;
/* held while doing delalloc reservations */
struct mutex delalloc_mutex;
/* used to order data wrt metadata */
struct btrfs_ordered_inode_tree ordered_tree;
......
fs/btrfs/compression.c
浏览文件 @ 97d0bf96
......@@ -29,6 +29,41 @@
#include "extent_io.h"
#include "extent_map.h"
int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
u64 start, struct page **pages, unsigned long *out_pages,
unsigned long *total_in, unsigned long *total_out);
int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int zlib_decompress(struct list_head *ws, unsigned char *data_in,
struct page *dest_page, unsigned long start_byte, size_t srclen,
size_t destlen);
struct list_head *zlib_alloc_workspace(unsigned int level);
void zlib_free_workspace(struct list_head *ws);
struct list_head *zlib_get_workspace(unsigned int level);
int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
u64 start, struct page **pages, unsigned long *out_pages,
unsigned long *total_in, unsigned long *total_out);
int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int lzo_decompress(struct list_head *ws, unsigned char *data_in,
struct page *dest_page, unsigned long start_byte, size_t srclen,
size_t destlen);
struct list_head *lzo_alloc_workspace(unsigned int level);
void lzo_free_workspace(struct list_head *ws);
int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
u64 start, struct page **pages, unsigned long *out_pages,
unsigned long *total_in, unsigned long *total_out);
int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb);
int zstd_decompress(struct list_head *ws, unsigned char *data_in,
struct page *dest_page, unsigned long start_byte, size_t srclen,
size_t destlen);
void zstd_init_workspace_manager(void);
void zstd_cleanup_workspace_manager(void);
struct list_head *zstd_alloc_workspace(unsigned int level);
void zstd_free_workspace(struct list_head *ws);
struct list_head *zstd_get_workspace(unsigned int level);
void zstd_put_workspace(struct list_head *ws);
static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
const char* btrfs_compress_type2str(enum btrfs_compression_type type)
......@@ -39,6 +74,8 @@ const char* btrfs_compress_type2str(enum btrfs_compression_type type)
case BTRFS_COMPRESS_ZSTD:
case BTRFS_COMPRESS_NONE:
return btrfs_compress_types[type];
default:
break;
}
return NULL;
......@@ -60,6 +97,70 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len)
return false;
}
static int compression_compress_pages(int type, struct list_head *ws,
struct address_space *mapping, u64 start, struct page **pages,
unsigned long *out_pages, unsigned long *total_in,
unsigned long *total_out)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB:
return zlib_compress_pages(ws, mapping, start, pages,
out_pages, total_in, total_out);
case BTRFS_COMPRESS_LZO:
return lzo_compress_pages(ws, mapping, start, pages,
out_pages, total_in, total_out);
case BTRFS_COMPRESS_ZSTD:
return zstd_compress_pages(ws, mapping, start, pages,
out_pages, total_in, total_out);
case BTRFS_COMPRESS_NONE:
default:
/*
* This can't happen, the type is validated several times
* before we get here. As a sane fallback, return what the
* callers will understand as 'no compression happened'.
*/
return -E2BIG;
}
}
static int compression_decompress_bio(int type, struct list_head *ws,
struct compressed_bio *cb)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB: return zlib_decompress_bio(ws, cb);
case BTRFS_COMPRESS_LZO: return lzo_decompress_bio(ws, cb);
case BTRFS_COMPRESS_ZSTD: return zstd_decompress_bio(ws, cb);
case BTRFS_COMPRESS_NONE:
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
static int compression_decompress(int type, struct list_head *ws,
unsigned char *data_in, struct page *dest_page,
unsigned long start_byte, size_t srclen, size_t destlen)
{
switch (type) {
case BTRFS_COMPRESS_ZLIB: return zlib_decompress(ws, data_in, dest_page,
start_byte, srclen, destlen);
case BTRFS_COMPRESS_LZO: return lzo_decompress(ws, data_in, dest_page,
start_byte, srclen, destlen);
case BTRFS_COMPRESS_ZSTD: return zstd_decompress(ws, data_in, dest_page,
start_byte, srclen, destlen);
case BTRFS_COMPRESS_NONE:
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
static int btrfs_decompress_bio(struct compressed_bio *cb);
static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
......@@ -311,7 +412,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long compressed_len,
struct page **compressed_pages,
unsigned long nr_pages,
unsigned int write_flags)
unsigned int write_flags,
struct cgroup_subsys_state *blkcg_css)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct bio *bio = NULL;
......@@ -320,7 +422,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
int pg_index = 0;
struct page *page;
u64 first_byte = disk_start;
struct block_device *bdev;
blk_status_t ret;
int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
......@@ -339,13 +440,15 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
cb->orig_bio = NULL;
cb->nr_pages = nr_pages;
bdev = fs_info->fs_devices->latest_bdev;
bio = btrfs_bio_alloc(first_byte);
bio_set_dev(bio, bdev);
bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
if (blkcg_css) {
bio->bi_opf |= REQ_CGROUP_PUNT;
bio_associate_blkg_from_css(bio, blkcg_css);
}
refcount_set(&cb->pending_bios, 1);
/* create and submit bios for the compressed pages */
......@@ -378,14 +481,13 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
BUG_ON(ret); /* -ENOMEM */
}
ret = btrfs_map_bio(fs_info, bio, 0, 1);
ret = btrfs_map_bio(fs_info, bio, 0);
if (ret) {
bio->bi_status = ret;
bio_endio(bio);
}
bio = btrfs_bio_alloc(first_byte);
bio_set_dev(bio, bdev);
bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
......@@ -409,7 +511,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
BUG_ON(ret); /* -ENOMEM */
}
ret = btrfs_map_bio(fs_info, bio, 0, 1);
ret = btrfs_map_bio(fs_info, bio, 0);
if (ret) {
bio->bi_status = ret;
bio_endio(bio);
......@@ -553,7 +655,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
unsigned long nr_pages;
unsigned long pg_index;
struct page *page;
struct block_device *bdev;
struct bio *comp_bio;
u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9;
u64 em_len;
......@@ -604,8 +705,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
if (!cb->compressed_pages)
goto fail1;
bdev = fs_info->fs_devices->latest_bdev;
for (pg_index = 0; pg_index < nr_pages; pg_index++) {
cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS |
__GFP_HIGHMEM);
......@@ -624,7 +723,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
cb->len = bio->bi_iter.bi_size;
comp_bio = btrfs_bio_alloc(cur_disk_byte);
bio_set_dev(comp_bio, bdev);
comp_bio->bi_opf = REQ_OP_READ;
comp_bio->bi_private = cb;
comp_bio->bi_end_io = end_compressed_bio_read;
......@@ -668,14 +766,13 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
fs_info->sectorsize);
sums += csum_size * nr_sectors;
ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
if (ret) {
comp_bio->bi_status = ret;
bio_endio(comp_bio);
}
comp_bio = btrfs_bio_alloc(cur_disk_byte);
bio_set_dev(comp_bio, bdev);
comp_bio->bi_opf = REQ_OP_READ;
comp_bio->bi_private = cb;
comp_bio->bi_end_io = end_compressed_bio_read;
......@@ -693,7 +790,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
BUG_ON(ret); /* -ENOMEM */
}
ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
if (ret) {
comp_bio->bi_status = ret;
bio_endio(comp_bio);
......@@ -764,26 +861,6 @@ struct heuristic_ws {
static struct workspace_manager heuristic_wsm;
static void heuristic_init_workspace_manager(void)
{
btrfs_init_workspace_manager(&heuristic_wsm, &btrfs_heuristic_compress);
}
static void heuristic_cleanup_workspace_manager(void)
{
btrfs_cleanup_workspace_manager(&heuristic_wsm);
}
static struct list_head *heuristic_get_workspace(unsigned int level)
{
return btrfs_get_workspace(&heuristic_wsm, level);
}
static void heuristic_put_workspace(struct list_head *ws)
{
btrfs_put_workspace(&heuristic_wsm, ws);
}
static void free_heuristic_ws(struct list_head *ws)
{
struct heuristic_ws *workspace;
......@@ -824,12 +901,7 @@ static struct list_head *alloc_heuristic_ws(unsigned int level)
}
const struct btrfs_compress_op btrfs_heuristic_compress = {
.init_workspace_manager = heuristic_init_workspace_manager,
.cleanup_workspace_manager = heuristic_cleanup_workspace_manager,
.get_workspace = heuristic_get_workspace,
.put_workspace = heuristic_put_workspace,
.alloc_workspace = alloc_heuristic_ws,
.free_workspace = free_heuristic_ws,
.workspace_manager = &heuristic_wsm,
};
static const struct btrfs_compress_op * const btrfs_compress_op[] = {
......@@ -840,13 +912,44 @@ static const struct btrfs_compress_op * const btrfs_compress_op[] = {
&btrfs_zstd_compress,
};
void btrfs_init_workspace_manager(struct workspace_manager *wsm,
const struct btrfs_compress_op *ops)
static struct list_head *alloc_workspace(int type, unsigned int level)
{
struct list_head *workspace;
switch (type) {
case BTRFS_COMPRESS_NONE: return alloc_heuristic_ws(level);
case BTRFS_COMPRESS_ZLIB: return zlib_alloc_workspace(level);
case BTRFS_COMPRESS_LZO: return lzo_alloc_workspace(level);
case BTRFS_COMPRESS_ZSTD: return zstd_alloc_workspace(level);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
wsm->ops = ops;
static void free_workspace(int type, struct list_head *ws)
{
switch (type) {
case BTRFS_COMPRESS_NONE: return free_heuristic_ws(ws);
case BTRFS_COMPRESS_ZLIB: return zlib_free_workspace(ws);
case BTRFS_COMPRESS_LZO: return lzo_free_workspace(ws);
case BTRFS_COMPRESS_ZSTD: return zstd_free_workspace(ws);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
static void btrfs_init_workspace_manager(int type)
{
struct workspace_manager *wsm;
struct list_head *workspace;
wsm = btrfs_compress_op[type]->workspace_manager;
INIT_LIST_HEAD(&wsm->idle_ws);
spin_lock_init(&wsm->ws_lock);
atomic_set(&wsm->total_ws, 0);
......@@ -856,7 +959,7 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
* Preallocate one workspace for each compression type so we can
* guarantee forward progress in the worst case
*/
workspace = wsm->ops->alloc_workspace(0);
workspace = alloc_workspace(type, 0);
if (IS_ERR(workspace)) {
pr_warn(
"BTRFS: cannot preallocate compression workspace, will try later\n");
......@@ -867,14 +970,16 @@ void btrfs_init_workspace_manager(struct workspace_manager *wsm,
}
}
void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
static void btrfs_cleanup_workspace_manager(int type)
{
struct workspace_manager *wsman;
struct list_head *ws;
wsman = btrfs_compress_op[type]->workspace_manager;
while (!list_empty(&wsman->idle_ws)) {
ws = wsman->idle_ws.next;
list_del(ws);
wsman->ops->free_workspace(ws);
free_workspace(type, ws);
atomic_dec(&wsman->total_ws);
}
}
......@@ -885,9 +990,9 @@ void btrfs_cleanup_workspace_manager(struct workspace_manager *wsman)
* Preallocation makes a forward progress guarantees and we do not return
* errors.
*/
struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
unsigned int level)
struct list_head *btrfs_get_workspace(int type, unsigned int level)
{
struct workspace_manager *wsm;
struct list_head *workspace;
int cpus = num_online_cpus();
unsigned nofs_flag;
......@@ -897,6 +1002,7 @@ struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
wait_queue_head_t *ws_wait;
int *free_ws;
wsm = btrfs_compress_op[type]->workspace_manager;
idle_ws = &wsm->idle_ws;
ws_lock = &wsm->ws_lock;
total_ws = &wsm->total_ws;
......@@ -932,7 +1038,7 @@ struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
* context of btrfs_compress_bio/btrfs_compress_pages
*/
nofs_flag = memalloc_nofs_save();
workspace = wsm->ops->alloc_workspace(level);
workspace = alloc_workspace(type, level);
memalloc_nofs_restore(nofs_flag);
if (IS_ERR(workspace)) {
......@@ -965,21 +1071,34 @@ struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
static struct list_head *get_workspace(int type, int level)
{
return btrfs_compress_op[type]->get_workspace(level);
switch (type) {
case BTRFS_COMPRESS_NONE: return btrfs_get_workspace(type, level);
case BTRFS_COMPRESS_ZLIB: return zlib_get_workspace(level);
case BTRFS_COMPRESS_LZO: return btrfs_get_workspace(type, level);
case BTRFS_COMPRESS_ZSTD: return zstd_get_workspace(level);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
/*
* put a workspace struct back on the list or free it if we have enough
* idle ones sitting around
*/
void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
void btrfs_put_workspace(int type, struct list_head *ws)
{
struct workspace_manager *wsm;
struct list_head *idle_ws;
spinlock_t *ws_lock;
atomic_t *total_ws;
wait_queue_head_t *ws_wait;
int *free_ws;
wsm = btrfs_compress_op[type]->workspace_manager;
idle_ws = &wsm->idle_ws;
ws_lock = &wsm->ws_lock;
total_ws = &wsm->total_ws;
......@@ -995,7 +1114,7 @@ void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
}
spin_unlock(ws_lock);
wsm->ops->free_workspace(ws);
free_workspace(type, ws);
atomic_dec(total_ws);
wake:
cond_wake_up(ws_wait);
......@@ -1003,7 +1122,18 @@ void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws)
static void put_workspace(int type, struct list_head *ws)
{
return btrfs_compress_op[type]->put_workspace(ws);
switch (type) {
case BTRFS_COMPRESS_NONE: return btrfs_put_workspace(type, ws);
case BTRFS_COMPRESS_ZLIB: return btrfs_put_workspace(type, ws);
case BTRFS_COMPRESS_LZO: return btrfs_put_workspace(type, ws);
case BTRFS_COMPRESS_ZSTD: return zstd_put_workspace(ws);
default:
/*
* This can't happen, the type is validated several times
* before we get here.
*/
BUG();
}
}
/*
......@@ -1042,10 +1172,8 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping,
level = btrfs_compress_set_level(type, level);
workspace = get_workspace(type, level);
ret = btrfs_compress_op[type]->compress_pages(workspace, mapping,
start, pages,
out_pages,
total_in, total_out);
ret = compression_compress_pages(type, workspace, mapping, start, pages,
out_pages, total_in, total_out);
put_workspace(type, workspace);
return ret;
}
......@@ -1071,7 +1199,7 @@ static int btrfs_decompress_bio(struct compressed_bio *cb)
int type = cb->compress_type;
workspace = get_workspace(type, 0);
ret = btrfs_compress_op[type]->decompress_bio(workspace, cb);
ret = compression_decompress_bio(type, workspace, cb);
put_workspace(type, workspace);
return ret;
......@@ -1089,9 +1217,8 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
int ret;
workspace = get_workspace(type, 0);
ret = btrfs_compress_op[type]->decompress(workspace, data_in,
dest_page, start_byte,
srclen, destlen);
ret = compression_decompress(type, workspace, data_in, dest_page,
start_byte, srclen, destlen);
put_workspace(type, workspace);
return ret;
......@@ -1099,18 +1226,18 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
void __init btrfs_init_compress(void)
{
int i;
for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
btrfs_compress_op[i]->init_workspace_manager();
btrfs_init_workspace_manager(BTRFS_COMPRESS_NONE);
btrfs_init_workspace_manager(BTRFS_COMPRESS_ZLIB);
btrfs_init_workspace_manager(BTRFS_COMPRESS_LZO);
zstd_init_workspace_manager();
}
void __cold btrfs_exit_compress(void)
{
int i;
for (i = 0; i < BTRFS_NR_WORKSPACE_MANAGERS; i++)
btrfs_compress_op[i]->cleanup_workspace_manager();
btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_NONE);
btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_ZLIB);
btrfs_cleanup_workspace_manager(BTRFS_COMPRESS_LZO);
zstd_cleanup_workspace_manager();
}
/*
......
fs/btrfs/compression.h
浏览文件 @ 97d0bf96
......@@ -93,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long compressed_len,
struct page **compressed_pages,
unsigned long nr_pages,
unsigned int write_flags);
unsigned int write_flags,
struct cgroup_subsys_state *blkcg_css);
blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
......@@ -104,11 +105,10 @@ enum btrfs_compression_type {
BTRFS_COMPRESS_ZLIB = 1,
BTRFS_COMPRESS_LZO = 2,
BTRFS_COMPRESS_ZSTD = 3,
BTRFS_COMPRESS_TYPES = 3,
BTRFS_NR_COMPRESS_TYPES = 4,
};
struct workspace_manager {
const struct btrfs_compress_op *ops;
struct list_head idle_ws;
spinlock_t ws_lock;
/* Number of free workspaces */
......@@ -119,50 +119,18 @@ struct workspace_manager {
wait_queue_head_t ws_wait;
};
void btrfs_init_workspace_manager(struct workspace_manager *wsm,
const struct btrfs_compress_op *ops);
struct list_head *btrfs_get_workspace(struct workspace_manager *wsm,
unsigned int level);
void btrfs_put_workspace(struct workspace_manager *wsm, struct list_head *ws);
void btrfs_cleanup_workspace_manager(struct workspace_manager *wsm);
struct list_head *btrfs_get_workspace(int type, unsigned int level);
void btrfs_put_workspace(int type, struct list_head *ws);
struct btrfs_compress_op {
void (*init_workspace_manager)(void);
void (*cleanup_workspace_manager)(void);
struct list_head *(*get_workspace)(unsigned int level);
void (*put_workspace)(struct list_head *ws);
struct list_head *(*alloc_workspace)(unsigned int level);
void (*free_workspace)(struct list_head *workspace);
int (*compress_pages)(struct list_head *workspace,
struct address_space *mapping,
u64 start,
struct page **pages,
unsigned long *out_pages,
unsigned long *total_in,
unsigned long *total_out);
int (*decompress_bio)(struct list_head *workspace,
struct compressed_bio *cb);
int (*decompress)(struct list_head *workspace,
unsigned char *data_in,
struct page *dest_page,
unsigned long start_byte,
size_t srclen, size_t destlen);
struct workspace_manager *workspace_manager;
/* Maximum level supported by the compression algorithm */
unsigned int max_level;
unsigned int default_level;
};
/* The heuristic workspaces are managed via the 0th workspace manager */
#define BTRFS_NR_WORKSPACE_MANAGERS (BTRFS_COMPRESS_TYPES + 1)
#define BTRFS_NR_WORKSPACE_MANAGERS BTRFS_NR_COMPRESS_TYPES
extern const struct btrfs_compress_op btrfs_heuristic_compress;
extern const struct btrfs_compress_op btrfs_zlib_compress;
......
fs/btrfs/ctree.c
浏览文件 @ 97d0bf96
......@@ -32,8 +32,13 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
static const struct btrfs_csums {
u16 size;
const char *name;
const char *driver;
} btrfs_csums[] = {
[BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" },
[BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" },
[BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" },
[BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b",
.driver = "blake2b-256" },
};
int btrfs_super_csum_size(const struct btrfs_super_block *s)
......@@ -51,34 +56,25 @@ const char *btrfs_super_csum_name(u16 csum_type)
return btrfs_csums[csum_type].name;
}
struct btrfs_path *btrfs_alloc_path(void)
/*
* Return driver name if defined, otherwise the name that's also a valid driver
* name
*/
const char *btrfs_super_csum_driver(u16 csum_type)
{
return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
/* csum type is validated at mount time */
return btrfs_csums[csum_type].driver ?:
btrfs_csums[csum_type].name;
}
/*
* set all locked nodes in the path to blocking locks. This should
* be done before scheduling
*/
noinline void btrfs_set_path_blocking(struct btrfs_path *p)
size_t __const btrfs_get_num_csums(void)
{
int i;
for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
if (!p->nodes[i] || !p->locks[i])
continue;
/*
* If we currently have a spinning reader or writer lock this
* will bump the count of blocking holders and drop the
* spinlock.
*/
if (p->locks[i] == BTRFS_READ_LOCK) {
btrfs_set_lock_blocking_read(p->nodes[i]);
p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
} else if (p->locks[i] == BTRFS_WRITE_LOCK) {
btrfs_set_lock_blocking_write(p->nodes[i]);
p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
}
}
return ARRAY_SIZE(btrfs_csums);
}
struct btrfs_path *btrfs_alloc_path(void)
{
return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
}
/* this also releases the path */
......@@ -1125,7 +1121,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
parent_start = buf->start;
extent_buffer_get(cow);
atomic_inc(&cow->refs);
ret = tree_mod_log_insert_root(root->node, cow, 1);
BUG_ON(ret < 0);
rcu_assign_pointer(root->node, cow);
......@@ -1563,7 +1559,7 @@ static int comp_keys(const struct btrfs_disk_key *disk,
/*
* same as comp_keys only with two btrfs_key's
*/
int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
{
if (k1->objectid > k2->objectid)
return 1;
......@@ -2036,7 +2032,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
/* update the path */
if (left) {
if (btrfs_header_nritems(left) > orig_slot) {
extent_buffer_get(left);
atomic_inc(&left->refs);
/* left was locked after cow */
path->nodes[level] = left;
path->slots[level + 1] -= 1;
......@@ -2378,32 +2374,6 @@ static noinline void unlock_up(struct btrfs_path *path, int level,
}
}
/*
* This releases any locks held in the path starting at level and
* going all the way up to the root.
*
* btrfs_search_slot will keep the lock held on higher nodes in a few
* corner cases, such as COW of the block at slot zero in the node. This
* ignores those rules, and it should only be called when there are no
* more updates to be done higher up in the tree.
*/
noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
{
int i;
if (path->keep_locks)
return;
for (i = level; i < BTRFS_MAX_LEVEL; i++) {
if (!path->nodes[i])
continue;
if (!path->locks[i])
continue;
btrfs_tree_unlock_rw(path->nodes[i], path->locks[i]);
path->locks[i] = 0;
}
}
/*
* helper function for btrfs_search_slot. The goal is to find a block
* in cache without setting the path to blocking. If we find the block
......@@ -2652,7 +2622,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
} else {
b = root->commit_root;
extent_buffer_get(b);
atomic_inc(&b->refs);
}
level = btrfs_header_level(b);
/*
......@@ -2785,12 +2755,10 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
}
while (b) {
int dec = 0;
level = btrfs_header_level(b);
/*
* setup the path here so we can release it under lock
* contention with the cow code
*/
if (cow) {
bool last_level = (level == (BTRFS_MAX_LEVEL - 1));
......@@ -2861,73 +2829,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
if (ret < 0)
goto done;
if (level != 0) {
int dec = 0;
if (ret && slot > 0) {
dec = 1;
slot -= 1;
}
p->slots[level] = slot;
err = setup_nodes_for_search(trans, root, p, b, level,
ins_len, &write_lock_level);
if (err == -EAGAIN)
goto again;
if (err) {
ret = err;
goto done;
}
b = p->nodes[level];
slot = p->slots[level];
/*
* slot 0 is special, if we change the key
* we have to update the parent pointer
* which means we must have a write lock
* on the parent
*/
if (slot == 0 && ins_len &&
write_lock_level < level + 1) {
write_lock_level = level + 1;
btrfs_release_path(p);
goto again;
}
unlock_up(p, level, lowest_unlock,
min_write_lock_level, &write_lock_level);
if (level == lowest_level) {
if (dec)
p->slots[level]++;
goto done;
}
err = read_block_for_search(root, p, &b, level,
slot, key);
if (err == -EAGAIN)
goto again;
if (err) {
ret = err;
goto done;
}
if (!p->skip_locking) {
level = btrfs_header_level(b);
if (level <= write_lock_level) {
if (!btrfs_try_tree_write_lock(b)) {
btrfs_set_path_blocking(p);
btrfs_tree_lock(b);
}
p->locks[level] = BTRFS_WRITE_LOCK;
} else {
if (!btrfs_tree_read_lock_atomic(b)) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
}
p->locks[level] = BTRFS_READ_LOCK;
}
p->nodes[level] = b;
}
} else {
if (level == 0) {
p->slots[level] = slot;
if (ins_len > 0 &&
btrfs_leaf_free_space(b) < ins_len) {
......@@ -2952,6 +2854,67 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
min_write_lock_level, NULL);
goto done;
}
if (ret && slot > 0) {
dec = 1;
slot--;
}
p->slots[level] = slot;
err = setup_nodes_for_search(trans, root, p, b, level, ins_len,
&write_lock_level);
if (err == -EAGAIN)
goto again;
if (err) {
ret = err;
goto done;
}
b = p->nodes[level];
slot = p->slots[level];
/*
* Slot 0 is special, if we change the key we have to update
* the parent pointer which means we must have a write lock on
* the parent
*/
if (slot == 0 && ins_len && write_lock_level < level + 1) {
write_lock_level = level + 1;
btrfs_release_path(p);
goto again;
}
unlock_up(p, level, lowest_unlock, min_write_lock_level,
&write_lock_level);
if (level == lowest_level) {
if (dec)
p->slots[level]++;
goto done;
}
err = read_block_for_search(root, p, &b, level, slot, key);
if (err == -EAGAIN)
goto again;
if (err) {
ret = err;
goto done;
}
if (!p->skip_locking) {
level = btrfs_header_level(b);
if (level <= write_lock_level) {
if (!btrfs_try_tree_write_lock(b)) {
btrfs_set_path_blocking(p);
btrfs_tree_lock(b);
}
p->locks[level] = BTRFS_WRITE_LOCK;
} else {
if (!btrfs_tree_read_lock_atomic(b)) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
}
p->locks[level] = BTRFS_READ_LOCK;
}
p->nodes[level] = b;
}
}
ret = 1;
done:
......@@ -3008,6 +2971,8 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
p->locks[level] = BTRFS_READ_LOCK;
while (b) {
int dec = 0;
level = btrfs_header_level(b);
p->nodes[level] = b;
......@@ -3028,47 +2993,45 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
if (ret < 0)
goto done;
if (level != 0) {
int dec = 0;
if (ret && slot > 0) {
dec = 1;
slot -= 1;
}
if (level == 0) {
p->slots[level] = slot;
unlock_up(p, level, lowest_unlock, 0, NULL);
goto done;
}
if (level == lowest_level) {
if (dec)
p->slots[level]++;
goto done;
}
if (ret && slot > 0) {
dec = 1;
slot--;
}
p->slots[level] = slot;
unlock_up(p, level, lowest_unlock, 0, NULL);
err = read_block_for_search(root, p, &b, level,
slot, key);
if (err == -EAGAIN)
goto again;
if (err) {
ret = err;
goto done;
}
if (level == lowest_level) {
if (dec)
p->slots[level]++;
goto done;
}
level = btrfs_header_level(b);
if (!btrfs_tree_read_lock_atomic(b)) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
}
b = tree_mod_log_rewind(fs_info, p, b, time_seq);
if (!b) {
ret = -ENOMEM;
goto done;
}
p->locks[level] = BTRFS_READ_LOCK;
p->nodes[level] = b;
} else {
p->slots[level] = slot;
unlock_up(p, level, lowest_unlock, 0, NULL);
err = read_block_for_search(root, p, &b, level, slot, key);
if (err == -EAGAIN)
goto again;
if (err) {
ret = err;
goto done;
}
level = btrfs_header_level(b);
if (!btrfs_tree_read_lock_atomic(b)) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
}
b = tree_mod_log_rewind(fs_info, p, b, time_seq);
if (!b) {
ret = -ENOMEM;
goto done;
}
p->locks[level] = BTRFS_READ_LOCK;
p->nodes[level] = b;
}
ret = 1;
done:
......@@ -3433,7 +3396,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
free_extent_buffer(old);
add_root_to_dirty_list(root);
extent_buffer_get(c);
atomic_inc(&c->refs);
path->nodes[level] = c;
path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
path->slots[level] = 0;
......@@ -4966,7 +4929,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans,
root_sub_used(root, leaf->len);
extent_buffer_get(leaf);
atomic_inc(&leaf->refs);
btrfs_free_tree_block(trans, root, leaf, 0, 1);
free_extent_buffer_stale(leaf);
}
......@@ -5047,7 +5010,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
* for possible call to del_ptr below
*/
slot = path->slots[1];
extent_buffer_get(leaf);
atomic_inc(&leaf->refs);
btrfs_set_path_blocking(path);
wret = push_leaf_left(trans, root, path, 1, 1,
......
fs/btrfs/ctree.h
浏览文件 @ 97d0bf96
......@@ -28,6 +28,7 @@
#include <linux/dynamic_debug.h>
#include <linux/refcount.h>
#include <linux/crc32c.h>
#include "extent-io-tree.h"
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
......@@ -38,7 +39,7 @@ struct btrfs_transaction;
struct btrfs_pending_snapshot;
struct btrfs_delayed_ref_root;
struct btrfs_space_info;
struct btrfs_block_group_cache;
struct btrfs_block_group;
extern struct kmem_cache *btrfs_trans_handle_cachep;
extern struct kmem_cache *btrfs_bit_radix_cachep;
extern struct kmem_cache *btrfs_path_cachep;
......@@ -56,9 +57,9 @@ struct btrfs_ref;
* filesystem data as well that can be used to read data in order to repair
* read errors on other disks.
*
* Current value is derived from RAID1 with 2 copies.
* Current value is derived from RAID1C4 with 4 copies.
*/
#define BTRFS_MAX_MIRRORS (2 + 1)
#define BTRFS_MAX_MIRRORS (4 + 1)
#define BTRFS_MAX_LEVEL 8
......@@ -291,7 +292,8 @@ struct btrfs_super_block {
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
BTRFS_FEATURE_INCOMPAT_NO_HOLES | \
BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \
BTRFS_FEATURE_INCOMPAT_RAID1C34)
#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \
(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
......@@ -413,7 +415,7 @@ struct btrfs_free_cluster {
/* We did a full search and couldn't create a cluster */
bool fragmented;
struct btrfs_block_group_cache *block_group;
struct btrfs_block_group *block_group;
/*
* when a cluster is allocated from a block group, we put the
* cluster onto a list in the block group so that it can
......@@ -476,8 +478,8 @@ struct btrfs_swapfile_pin {
void *ptr;
struct inode *inode;
/*
* If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
* ptr points to a struct btrfs_device.
* If true, ptr points to a struct btrfs_block_group. Otherwise, ptr
* points to a struct btrfs_device.
*/
bool is_block_group;
};
......@@ -722,7 +724,6 @@ struct btrfs_fs_info {
struct btrfs_workqueue *endio_meta_write_workers;
struct btrfs_workqueue *endio_write_workers;
struct btrfs_workqueue *endio_freespace_worker;
struct btrfs_workqueue *submit_workers;
struct btrfs_workqueue *caching_workers;
struct btrfs_workqueue *readahead_workers;
......@@ -1519,18 +1520,18 @@ static inline u64 btrfs_stripe_devid_nr(struct extent_buffer *eb,
}
/* struct btrfs_block_group_item */
BTRFS_SETGET_STACK_FUNCS(block_group_used, struct btrfs_block_group_item,
BTRFS_SETGET_STACK_FUNCS(stack_block_group_used, struct btrfs_block_group_item,
used, 64);
BTRFS_SETGET_FUNCS(disk_block_group_used, struct btrfs_block_group_item,
BTRFS_SETGET_FUNCS(block_group_used, struct btrfs_block_group_item,
used, 64);
BTRFS_SETGET_STACK_FUNCS(block_group_chunk_objectid,
BTRFS_SETGET_STACK_FUNCS(stack_block_group_chunk_objectid,
struct btrfs_block_group_item, chunk_objectid, 64);
BTRFS_SETGET_FUNCS(disk_block_group_chunk_objectid,
BTRFS_SETGET_FUNCS(block_group_chunk_objectid,
struct btrfs_block_group_item, chunk_objectid, 64);
BTRFS_SETGET_FUNCS(disk_block_group_flags,
BTRFS_SETGET_FUNCS(block_group_flags,
struct btrfs_block_group_item, flags, 64);
BTRFS_SETGET_STACK_FUNCS(block_group_flags,
BTRFS_SETGET_STACK_FUNCS(stack_block_group_flags,
struct btrfs_block_group_item, flags, 64);
/* struct btrfs_free_space_info */
......@@ -2163,6 +2164,9 @@ BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
int btrfs_super_csum_size(const struct btrfs_super_block *s);
const char *btrfs_super_csum_name(u16 csum_type);
const char *btrfs_super_csum_driver(u16 csum_type);
size_t __const btrfs_get_num_csums(void);
/*
* The leaf data grows from end-to-front in the node.
......@@ -2397,7 +2401,7 @@ static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 num_bytes);
void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache);
void btrfs_free_excluded_extents(struct btrfs_block_group *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
unsigned long count);
void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
......@@ -2453,8 +2457,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
struct btrfs_ref *generic_ref);
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
void btrfs_get_block_group_trimming(struct btrfs_block_group *cache);
void btrfs_put_block_group_trimming(struct btrfs_block_group *cache);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
enum btrfs_reserve_flush_enum {
......@@ -2507,7 +2511,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
int level, int *slot);
int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
int btrfs_previous_item(struct btrfs_root *root,
struct btrfs_path *path, u64 min_objectid,
int type);
......@@ -2567,8 +2571,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
void btrfs_release_path(struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_set_path_blocking(struct btrfs_path *p);
void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct btrfs_path *path, int slot, int nr);
......@@ -2870,10 +2872,9 @@ int btrfs_drop_inode(struct inode *inode);
int __init btrfs_init_cachep(void);
void __cold btrfs_destroy_cachep(void);
struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *new,
struct btrfs_path *path);
struct btrfs_root *root, struct btrfs_path *path);
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *was_new);
struct btrfs_root *root);
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 end, int create);
......@@ -2909,7 +2910,7 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int btrfs_ioctl_get_supported_features(void __user *arg);
void btrfs_sync_inode_flags_to_i_flags(struct inode *inode);
int btrfs_is_empty_uuid(u8 *uuid);
int __pure btrfs_is_empty_uuid(u8 *uuid);
int btrfs_defrag_file(struct inode *inode, struct file *file,
struct btrfs_ioctl_defrag_range_args *range,
u64 newer_than, unsigned long max_pages);
......@@ -3143,7 +3144,7 @@ __cold
void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
const char *btrfs_decode_error(int errno);
const char * __attribute_const__ btrfs_decode_error(int errno);
__cold
void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
......
fs/btrfs/delalloc-space.c
浏览文件 @ 97d0bf96
......@@ -307,7 +307,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
unsigned nr_extents;
enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
int ret = 0;
bool delalloc_lock = true;
/*
* If we are a free space inode we need to not flush since we will be in
......@@ -320,7 +319,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
*/
if (btrfs_is_free_space_inode(inode)) {
flush = BTRFS_RESERVE_NO_FLUSH;
delalloc_lock = false;
} else {
if (current->journal_info)
flush = BTRFS_RESERVE_FLUSH_LIMIT;
......@@ -329,9 +327,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
schedule_timeout(1);
}
if (delalloc_lock)
mutex_lock(&inode->delalloc_mutex);
num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
/*
......@@ -348,10 +343,12 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
&qgroup_reserve);
ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
if (ret)
goto out_fail;
return ret;
ret = btrfs_reserve_metadata_bytes(root, block_rsv, meta_reserve, flush);
if (ret)
goto out_qgroup;
if (ret) {
btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
return ret;
}
/*
* Now we need to update our outstanding extents and csum bytes _first_
......@@ -375,15 +372,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
block_rsv->qgroup_rsv_reserved += qgroup_reserve;
spin_unlock(&block_rsv->lock);
if (delalloc_lock)
mutex_unlock(&inode->delalloc_mutex);
return 0;
out_qgroup:
btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
out_fail:
if (delalloc_lock)
mutex_unlock(&inode->delalloc_mutex);
return ret;
}
/**
......
fs/btrfs/delayed-inode.c
浏览文件 @ 97d0bf96
......@@ -12,6 +12,7 @@
#include "transaction.h"
#include "ctree.h"
#include "qgroup.h"
#include "locking.h"
#define BTRFS_DELAYED_WRITEBACK 512
#define BTRFS_DELAYED_BACKGROUND 128
......@@ -1367,8 +1368,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
return -ENOMEM;
async_work->delayed_root = delayed_root;
btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
btrfs_async_run_delayed_root, NULL, NULL);
btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root, NULL,
NULL);
async_work->nr = nr;
btrfs_queue_work(fs_info->delayed_workers, &async_work->work);
......@@ -1949,12 +1950,19 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
}
inode_id = delayed_nodes[n - 1]->inode_id + 1;
for (i = 0; i < n; i++)
refcount_inc(&delayed_nodes[i]->refs);
for (i = 0; i < n; i++) {
/*
* Don't increase refs in case the node is dead and
* about to be removed from the tree in the loop below
*/
if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
delayed_nodes[i] = NULL;
}
spin_unlock(&root->inode_lock);
for (i = 0; i < n; i++) {
if (!delayed_nodes[i])
continue;
__btrfs_kill_delayed_node(delayed_nodes[i]);
btrfs_release_delayed_node(delayed_nodes[i]);
}
......
fs/btrfs/dev-replace.c
浏览文件 @ 97d0bf96
......@@ -986,7 +986,7 @@ static int btrfs_dev_replace_kthread(void *data)
return 0;
}
int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
{
if (!dev_replace->is_valid)
return 0;
......
fs/btrfs/dev-replace.h
浏览文件 @ 97d0bf96
......@@ -17,6 +17,6 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
#endif
fs/btrfs/disk-io.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/disk-io.h
浏览文件 @ 97d0bf96
......@@ -49,10 +49,10 @@ struct extent_buffer *btrfs_find_create_tree_block(
struct btrfs_fs_info *fs_info,
u64 bytenr);
void btrfs_clean_tree_block(struct extent_buffer *buf);
int open_ctree(struct super_block *sb,
int __cold open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options);
void close_ctree(struct btrfs_fs_info *fs_info);
void __cold close_ctree(struct btrfs_fs_info *fs_info);
int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
......
fs/btrfs/export.c
浏览文件 @ 97d0bf96
......@@ -87,7 +87,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
inode = btrfs_iget(sb, &key, root, NULL);
inode = btrfs_iget(sb, &key, root);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto fail;
......@@ -214,7 +214,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root, NULL));
return d_obtain_alias(btrfs_iget(fs_info->sb, &key, root));
fail:
btrfs_free_path(path);
return ERR_PTR(ret);
......
fs/btrfs/extent-io-tree.h 0 → 100644
浏览文件 @ 97d0bf96
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_EXTENT_IO_TREE_H
#define BTRFS_EXTENT_IO_TREE_H
struct extent_changeset;
struct io_failure_record;
/* Bits for the extent state */
#define EXTENT_DIRTY (1U << 0)
#define EXTENT_UPTODATE (1U << 1)
#define EXTENT_LOCKED (1U << 2)
#define EXTENT_NEW (1U << 3)
#define EXTENT_DELALLOC (1U << 4)
#define EXTENT_DEFRAG (1U << 5)
#define EXTENT_BOUNDARY (1U << 6)
#define EXTENT_NODATASUM (1U << 7)
#define EXTENT_CLEAR_META_RESV (1U << 8)
#define EXTENT_NEED_WAIT (1U << 9)
#define EXTENT_DAMAGED (1U << 10)
#define EXTENT_NORESERVE (1U << 11)
#define EXTENT_QGROUP_RESERVED (1U << 12)
#define EXTENT_CLEAR_DATA_RESV (1U << 13)
#define EXTENT_DELALLOC_NEW (1U << 14)
#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \
EXTENT_CLEAR_DATA_RESV)
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING)
/*
* Redefined bits above which are used only in the device allocation tree,
* shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
* / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
* manipulation functions
*/
#define CHUNK_ALLOCATED EXTENT_DIRTY
#define CHUNK_TRIMMED EXTENT_DEFRAG
enum {
IO_TREE_FS_INFO_FREED_EXTENTS0,
IO_TREE_FS_INFO_FREED_EXTENTS1,
IO_TREE_INODE_IO,
IO_TREE_INODE_IO_FAILURE,
IO_TREE_RELOC_BLOCKS,
IO_TREE_TRANS_DIRTY_PAGES,
IO_TREE_ROOT_DIRTY_LOG_PAGES,
IO_TREE_SELFTEST,
};
struct extent_io_tree {
struct rb_root state;
struct btrfs_fs_info *fs_info;
void *private_data;
u64 dirty_bytes;
bool track_uptodate;
/* Who owns this io tree, should be one of IO_TREE_* */
u8 owner;
spinlock_t lock;
const struct extent_io_ops *ops;
};
struct extent_state {
u64 start;
u64 end; /* inclusive */
struct rb_node rb_node;
/* ADD NEW ELEMENTS AFTER THIS */
wait_queue_head_t wq;
refcount_t refs;
unsigned state;
struct io_failure_record *failrec;
#ifdef CONFIG_BTRFS_DEBUG
struct list_head leak_list;
#endif
};
int __init extent_state_cache_init(void);
void __cold extent_state_cache_exit(void);
void extent_io_tree_init(struct btrfs_fs_info *fs_info,
struct extent_io_tree *tree, unsigned int owner,
void *private_data);
void extent_io_tree_release(struct extent_io_tree *tree);
int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached);
static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
{
return lock_extent_bits(tree, start, end, NULL);
}
int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
int __init extent_io_init(void);
void __cold extent_io_exit(void);
u64 count_range_bits(struct extent_io_tree *tree,
u64 *start, u64 search_end,
u64 max_bytes, unsigned bits, int contig);
void free_extent_state(struct extent_state *state);
int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int filled,
struct extent_state *cached_state);
int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, struct extent_changeset *changeset);
int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int wake, int delete,
struct extent_state **cached);
int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int wake, int delete,
struct extent_state **cached, gfp_t mask,
struct extent_changeset *changeset);
static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
{
return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
}
static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached)
{
return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
GFP_NOFS, NULL);
}
static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
u64 start, u64 end, struct extent_state **cached)
{
return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
GFP_ATOMIC, NULL);
}
static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
u64 end, unsigned bits)
{
int wake = 0;
if (bits & EXTENT_LOCKED)
wake = 1;
return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
}
int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, struct extent_changeset *changeset);
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, u64 *failed_start,
struct extent_state **cached_state, gfp_t mask);
int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits);
static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
u64 end, unsigned bits)
{
return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
}
static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state)
{
return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
cached_state, GFP_NOFS, NULL);
}
static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
u64 end, gfp_t mask)
{
return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
NULL, mask);
}
static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached)
{
return clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING, 0, 0, cached);
}
int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, unsigned clear_bits,
struct extent_state **cached_state);
static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
u64 end, unsigned int extra_bits,
struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
NULL, cached_state, GFP_NOFS);
}
static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
NULL, cached_state, GFP_NOFS);
}
static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
u64 end)
{
return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
GFP_NOFS);
}
static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state, gfp_t mask)
{
return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
cached_state, mask);
}
int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, unsigned bits,
struct extent_state **cached_state);
void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, unsigned bits);
int extent_invalidatepage(struct extent_io_tree *tree,
struct page *page, unsigned long offset);
bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
u64 *end, u64 max_bytes,
struct extent_state **cached_state);
/* This should be reworked in the future and put elsewhere. */
int get_state_failrec(struct extent_io_tree *tree, u64 start,
struct io_failure_record **failrec);
int set_state_failrec(struct extent_io_tree *tree, u64 start,
struct io_failure_record *failrec);
void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
u64 end);
int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
struct io_failure_record **failrec_ret);
int free_io_failure(struct extent_io_tree *failure_tree,
struct extent_io_tree *io_tree,
struct io_failure_record *rec);
int clean_io_failure(struct btrfs_fs_info *fs_info,
struct extent_io_tree *failure_tree,
struct extent_io_tree *io_tree, u64 start,
struct page *page, u64 ino, unsigned int pg_offset);
#endif /* BTRFS_EXTENT_IO_TREE_H */
fs/btrfs/extent-tree.c
浏览文件 @ 97d0bf96
......@@ -54,7 +54,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
static int find_next_key(struct btrfs_path *path, int level,
struct btrfs_key *key);
static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
static int block_group_bits(struct btrfs_block_group *cache, u64 bits)
{
return (cache->flags & bits) == bits;
}
......@@ -70,13 +70,13 @@ int btrfs_add_excluded_extent(struct btrfs_fs_info *fs_info,
return 0;
}
void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache)
void btrfs_free_excluded_extents(struct btrfs_block_group *cache)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
u64 start, end;
start = cache->key.objectid;
end = start + cache->key.offset - 1;
start = cache->start;
end = start + cache->length - 1;
clear_extent_bits(&fs_info->freed_extents[0],
start, end, EXTENT_UPTODATE);
......@@ -1306,8 +1306,10 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 num_bytes, u64 *actual_bytes)
{
int ret;
int ret = 0;
u64 discarded_bytes = 0;
u64 end = bytenr + num_bytes;
u64 cur = bytenr;
struct btrfs_bio *bbio = NULL;
......@@ -1316,15 +1318,23 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
* associated to its stripes that don't go away while we are discarding.
*/
btrfs_bio_counter_inc_blocked(fs_info);
/* Tell the block device(s) that the sectors can be discarded */
ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes,
&bbio, 0);
/* Error condition is -ENOMEM */
if (!ret) {
struct btrfs_bio_stripe *stripe = bbio->stripes;
while (cur < end) {
struct btrfs_bio_stripe *stripe;
int i;
num_bytes = end - cur;
/* Tell the block device(s) that the sectors can be discarded */
ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur,
&num_bytes, &bbio, 0);
/*
* Error can be -ENOMEM, -ENOENT (no such chunk mapping) or
* -EOPNOTSUPP. For any such error, @num_bytes is not updated,
* thus we can't continue anyway.
*/
if (ret < 0)
goto out;
stripe = bbio->stripes;
for (i = 0; i < bbio->num_stripes; i++, stripe++) {
u64 bytes;
struct request_queue *req_q;
......@@ -1341,10 +1351,19 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
stripe->physical,
stripe->length,
&bytes);
if (!ret)
if (!ret) {
discarded_bytes += bytes;
else if (ret != -EOPNOTSUPP)
break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
} else if (ret != -EOPNOTSUPP) {
/*
* Logic errors or -ENOMEM, or -EIO, but
* unlikely to happen.
*
* And since there are two loops, explicitly
* go to out to avoid confusion.
*/
btrfs_put_bbio(bbio);
goto out;
}
/*
* Just in case we get back EOPNOTSUPP for some reason,
......@@ -1354,7 +1373,9 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
ret = 0;
}
btrfs_put_bbio(bbio);
cur += num_bytes;
}
out:
btrfs_bio_counter_dec(fs_info);
if (actual_bytes)
......@@ -2516,7 +2537,7 @@ int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
{
struct btrfs_block_group_cache *block_group;
struct btrfs_block_group *block_group;
int readonly = 0;
block_group = btrfs_lookup_block_group(fs_info, bytenr);
......@@ -2546,7 +2567,7 @@ static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
{
struct btrfs_block_group_cache *cache;
struct btrfs_block_group *cache;
u64 bytenr;
spin_lock(&fs_info->block_group_cache_lock);
......@@ -2560,13 +2581,13 @@ static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
if (!cache)
return 0;
bytenr = cache->key.objectid;
bytenr = cache->start;
btrfs_put_block_group(cache);
return bytenr;
}
static int pin_down_extent(struct btrfs_block_group_cache *cache,
static int pin_down_extent(struct btrfs_block_group *cache,
u64 bytenr, u64 num_bytes, int reserved)
{
struct btrfs_fs_info *fs_info = cache->fs_info;
......@@ -2590,13 +2611,12 @@ static int pin_down_extent(struct btrfs_block_group_cache *cache,
return 0;
}
/*
* this function must be called within transaction
*/
int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes, int reserved)
{
struct btrfs_block_group_cache *cache;
struct btrfs_block_group *cache;
ASSERT(fs_info->running_transaction);
cache = btrfs_lookup_block_group(fs_info, bytenr);
BUG_ON(!cache); /* Logic error */
......@@ -2613,7 +2633,7 @@ int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes)
{
struct btrfs_block_group_cache *cache;
struct btrfs_block_group *cache;
int ret;
cache = btrfs_lookup_block_group(fs_info, bytenr);
......@@ -2640,7 +2660,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 num_bytes)
{
int ret;
struct btrfs_block_group_cache *block_group;
struct btrfs_block_group *block_group;
struct btrfs_caching_control *caching_ctl;
block_group = btrfs_lookup_block_group(fs_info, start);
......@@ -2652,7 +2672,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
if (!caching_ctl) {
/* Logic error */
BUG_ON(!btrfs_block_group_cache_done(block_group));
BUG_ON(!btrfs_block_group_done(block_group));
ret = btrfs_remove_free_space(block_group, start, num_bytes);
} else {
mutex_lock(&caching_ctl->mutex);
......@@ -2717,7 +2737,7 @@ int btrfs_exclude_logged_extents(struct extent_buffer *eb)
}
static void
btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
btrfs_inc_block_group_reservations(struct btrfs_block_group *bg)
{
atomic_inc(&bg->reservations);
}
......@@ -2726,14 +2746,14 @@ void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info)
{
struct btrfs_caching_control *next;
struct btrfs_caching_control *caching_ctl;
struct btrfs_block_group_cache *cache;
struct btrfs_block_group *cache;
down_write(&fs_info->commit_root_sem);
list_for_each_entry_safe(caching_ctl, next,
&fs_info->caching_block_groups, list) {
cache = caching_ctl->block_group;
if (btrfs_block_group_cache_done(cache)) {
if (btrfs_block_group_done(cache)) {
cache->last_byte_to_unpin = (u64)-1;
list_del_init(&caching_ctl->list);
btrfs_put_caching_control(caching_ctl);
......@@ -2785,7 +2805,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
u64 start, u64 end,
const bool return_free_space)
{
struct btrfs_block_group_cache *cache = NULL;
struct btrfs_block_group *cache = NULL;
struct btrfs_space_info *space_info;
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
struct btrfs_free_cluster *cluster = NULL;
......@@ -2797,7 +2817,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
while (start <= end) {
readonly = false;
if (!cache ||
start >= cache->key.objectid + cache->key.offset) {
start >= cache->start + cache->length) {
if (cache)
btrfs_put_block_group(cache);
total_unpinned = 0;
......@@ -2810,7 +2830,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
empty_cluster <<= 1;
}
len = cache->key.objectid + cache->key.offset - start;
len = cache->start + cache->length - start;
len = min(len, end + 1 - start);
if (start < cache->last_byte_to_unpin) {
......@@ -2880,7 +2900,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_block_group_cache *block_group, *tmp;
struct btrfs_block_group *block_group, *tmp;
struct list_head *deleted_bgs;
struct extent_io_tree *unpin;
u64 start;
......@@ -2926,8 +2946,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
ret = -EROFS;
if (!trans->aborted)
ret = btrfs_discard_extent(fs_info,
block_group->key.objectid,
block_group->key.offset,
block_group->start,
block_group->length,
&trimmed);
list_del_init(&block_group->bg_list);
......@@ -3262,7 +3282,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
}
if (last_ref && btrfs_header_generation(buf) == trans->transid) {
struct btrfs_block_group_cache *cache;
struct btrfs_block_group *cache;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
ret = check_ref_cleanup(trans, buf->start);
......@@ -3349,15 +3369,14 @@ enum btrfs_loop_type {
};
static inline void
btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
btrfs_lock_block_group(struct btrfs_block_group *cache,
int delalloc)
{
if (delalloc)
down_read(&cache->data_rwsem);
}
static inline void
btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
static inline void btrfs_grab_block_group(struct btrfs_block_group *cache,
int delalloc)
{
btrfs_get_block_group(cache);
......@@ -3365,12 +3384,12 @@ btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
down_read(&cache->data_rwsem);
}
static struct btrfs_block_group_cache *
btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
static struct btrfs_block_group *btrfs_lock_cluster(
struct btrfs_block_group *block_group,
struct btrfs_free_cluster *cluster,
int delalloc)
{
struct btrfs_block_group_cache *used_bg = NULL;
struct btrfs_block_group *used_bg = NULL;
spin_lock(&cluster->refill_lock);
while (1) {
......@@ -3404,7 +3423,7 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
}
static inline void
btrfs_release_block_group(struct btrfs_block_group_cache *cache,
btrfs_release_block_group(struct btrfs_block_group *cache,
int delalloc)
{
if (delalloc)
......@@ -3475,12 +3494,12 @@ struct find_free_extent_ctl {
* Return >0 to inform caller that we find nothing
* Return 0 means we have found a location and set ffe_ctl->found_offset.
*/
static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
static int find_free_extent_clustered(struct btrfs_block_group *bg,
struct btrfs_free_cluster *last_ptr,
struct find_free_extent_ctl *ffe_ctl,
struct btrfs_block_group_cache **cluster_bg_ret)
struct btrfs_block_group **cluster_bg_ret)
{
struct btrfs_block_group_cache *cluster_bg;
struct btrfs_block_group *cluster_bg;
u64 aligned_cluster;
u64 offset;
int ret;
......@@ -3493,7 +3512,7 @@ static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
goto release_cluster;
offset = btrfs_alloc_from_cluster(cluster_bg, last_ptr,
ffe_ctl->num_bytes, cluster_bg->key.objectid,
ffe_ctl->num_bytes, cluster_bg->start,
&ffe_ctl->max_extent_size);
if (offset) {
/* We have a block, we're done */
......@@ -3579,7 +3598,7 @@ static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
* Return 0 when we found an free extent and set ffe_ctrl->found_offset
* Return -EAGAIN to inform caller that we need to re-search this block group
*/
static int find_free_extent_unclustered(struct btrfs_block_group_cache *bg,
static int find_free_extent_unclustered(struct btrfs_block_group *bg,
struct btrfs_free_cluster *last_ptr,
struct find_free_extent_ctl *ffe_ctl)
{
......@@ -3781,7 +3800,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
{
int ret = 0;
struct btrfs_free_cluster *last_ptr = NULL;
struct btrfs_block_group_cache *block_group = NULL;
struct btrfs_block_group *block_group = NULL;
struct find_free_extent_ctl ffe_ctl = {0};
struct btrfs_space_info *space_info;
bool use_cluster = true;
......@@ -3904,7 +3923,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
continue;
btrfs_grab_block_group(block_group, delalloc);
ffe_ctl.search_start = block_group->key.objectid;
ffe_ctl.search_start = block_group->start;
/*
* this can happen if we end up cycling through all the
......@@ -3935,7 +3954,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
}
have_block_group:
ffe_ctl.cached = btrfs_block_group_cache_done(block_group);
ffe_ctl.cached = btrfs_block_group_done(block_group);
if (unlikely(!ffe_ctl.cached)) {
ffe_ctl.have_caching_bg = true;
ret = btrfs_cache_block_group(block_group, 0);
......@@ -3951,7 +3970,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
* lets look there
*/
if (last_ptr && use_cluster) {
struct btrfs_block_group_cache *cluster_bg = NULL;
struct btrfs_block_group *cluster_bg = NULL;
ret = find_free_extent_clustered(block_group, last_ptr,
&ffe_ctl, &cluster_bg);
......@@ -3984,7 +4003,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
/* move on to the next group */
if (ffe_ctl.search_start + num_bytes >
block_group->key.objectid + block_group->key.offset) {
block_group->start + block_group->length) {
btrfs_add_free_space(block_group, ffe_ctl.found_offset,
num_bytes);
goto loop;
......@@ -4133,7 +4152,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 len,
int pin, int delalloc)
{
struct btrfs_block_group_cache *cache;
struct btrfs_block_group *cache;
int ret = 0;
cache = btrfs_lookup_block_group(fs_info, start);
......@@ -4366,7 +4385,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
{
struct btrfs_fs_info *fs_info = trans->fs_info;
int ret;
struct btrfs_block_group_cache *block_group;
struct btrfs_block_group *block_group;
struct btrfs_space_info *space_info;
/*
......@@ -5436,7 +5455,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
btrfs_assert_tree_locked(parent);
parent_level = btrfs_header_level(parent);
extent_buffer_get(parent);
atomic_inc(&parent->refs);
path->nodes[parent_level] = parent;
path->slots[parent_level] = btrfs_header_nritems(parent);
......@@ -5480,7 +5499,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
*/
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
{
struct btrfs_block_group_cache *block_group;
struct btrfs_block_group *block_group;
u64 free_bytes = 0;
int factor;
......@@ -5498,9 +5517,8 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
}
factor = btrfs_bg_type_to_factor(block_group->flags);
free_bytes += (block_group->key.offset -
btrfs_block_group_used(&block_group->item)) *
factor;
free_bytes += (block_group->length -
block_group->used) * factor;
spin_unlock(&block_group->lock);
}
......@@ -5623,7 +5641,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
*/
int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
{
struct btrfs_block_group_cache *cache = NULL;
struct btrfs_block_group *cache = NULL;
struct btrfs_device *device;
struct list_head *devices;
u64 group_trimmed;
......@@ -5647,16 +5665,16 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
cache = btrfs_lookup_first_block_group(fs_info, range->start);
for (; cache; cache = btrfs_next_block_group(cache)) {
if (cache->key.objectid >= range_end) {
if (cache->start >= range_end) {
btrfs_put_block_group(cache);
break;
}
start = max(range->start, cache->key.objectid);
end = min(range_end, cache->key.objectid + cache->key.offset);
start = max(range->start, cache->start);
end = min(range_end, cache->start + cache->length);
if (end - start >= range->minlen) {
if (!btrfs_block_group_cache_done(cache)) {
if (!btrfs_block_group_done(cache)) {
ret = btrfs_cache_block_group(cache, 0);
if (ret) {
bg_failed++;
......
fs/btrfs/extent_io.c
浏览文件 @ 97d0bf96
......@@ -14,6 +14,7 @@
#include <linux/prefetch.h>
#include <linux/cleancache.h>
#include "extent_io.h"
#include "extent-io-tree.h"
#include "extent_map.h"
#include "ctree.h"
#include "btrfs_inode.h"
......@@ -59,12 +60,23 @@ void btrfs_leak_debug_del(struct list_head *entry)
spin_unlock_irqrestore(&leak_lock, flags);
}
static inline
void btrfs_leak_debug_check(void)
static inline void btrfs_extent_buffer_leak_debug_check(void)
{
struct extent_state *state;
struct extent_buffer *eb;
while (!list_empty(&buffers)) {
eb = list_entry(buffers.next, struct extent_buffer, leak_list);
pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
list_del(&eb->leak_list);
kmem_cache_free(extent_buffer_cache, eb);
}
}
static inline void btrfs_extent_state_leak_debug_check(void)
{
struct extent_state *state;
while (!list_empty(&states)) {
state = list_entry(states.next, struct extent_state, leak_list);
pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n",
......@@ -74,14 +86,6 @@ void btrfs_leak_debug_check(void)
list_del(&state->leak_list);
kmem_cache_free(extent_state_cache, state);
}
while (!list_empty(&buffers)) {
eb = list_entry(buffers.next, struct extent_buffer, leak_list);
pr_err("BTRFS: buffer leak start %llu len %lu refs %d bflags %lu\n",
eb->start, eb->len, atomic_read(&eb->refs), eb->bflags);
list_del(&eb->leak_list);
kmem_cache_free(extent_buffer_cache, eb);
}
}
#define btrfs_debug_check_extent_io_range(tree, start, end) \
......@@ -105,7 +109,8 @@ static inline void __btrfs_debug_check_extent_io_range(const char *caller,
#else
#define btrfs_leak_debug_add(new, head) do {} while (0)
#define btrfs_leak_debug_del(entry) do {} while (0)
#define btrfs_leak_debug_check() do {} while (0)
#define btrfs_extent_buffer_leak_debug_check() do {} while (0)
#define btrfs_extent_state_leak_debug_check() do {} while (0)
#define btrfs_debug_check_extent_io_range(c, s, e) do {} while (0)
#endif
......@@ -196,19 +201,23 @@ static int __must_check flush_write_bio(struct extent_page_data *epd)
return ret;
}
int __init extent_io_init(void)
int __init extent_state_cache_init(void)
{
extent_state_cache = kmem_cache_create("btrfs_extent_state",
sizeof(struct extent_state), 0,
SLAB_MEM_SPREAD, NULL);
if (!extent_state_cache)
return -ENOMEM;
return 0;
}
int __init extent_io_init(void)
{
extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
sizeof(struct extent_buffer), 0,
SLAB_MEM_SPREAD, NULL);
if (!extent_buffer_cache)
goto free_state_cache;
return -ENOMEM;
if (bioset_init(&btrfs_bioset, BIO_POOL_SIZE,
offsetof(struct btrfs_io_bio, bio),
......@@ -226,23 +235,24 @@ int __init extent_io_init(void)
free_buffer_cache:
kmem_cache_destroy(extent_buffer_cache);
extent_buffer_cache = NULL;
return -ENOMEM;
}
free_state_cache:
void __cold extent_state_cache_exit(void)
{
btrfs_extent_state_leak_debug_check();
kmem_cache_destroy(extent_state_cache);
extent_state_cache = NULL;
return -ENOMEM;
}
void __cold extent_io_exit(void)
{
btrfs_leak_debug_check();
btrfs_extent_buffer_leak_debug_check();
/*
* Make sure all delayed rcu free are flushed before we
* destroy caches.
*/
rcu_barrier();
kmem_cache_destroy(extent_state_cache);
kmem_cache_destroy(extent_buffer_cache);
bioset_exit(&btrfs_bioset);
}
......@@ -1676,9 +1686,9 @@ void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
*
* true is returned if we find something, false if nothing was in the tree
*/
static noinline bool find_delalloc_range(struct extent_io_tree *tree,
u64 *start, u64 *end, u64 max_bytes,
struct extent_state **cached_state)
bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
u64 *end, u64 max_bytes,
struct extent_state **cached_state)
{
struct rb_node *node;
struct extent_state *state;
......@@ -1796,8 +1806,8 @@ noinline_for_stack bool find_lock_delalloc_range(struct inode *inode,
/* step one, find a bunch of delalloc bytes starting at start */
delalloc_start = *start;
delalloc_end = 0;
found = find_delalloc_range(tree, &delalloc_start, &delalloc_end,
max_bytes, &cached_state);
found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end,
max_bytes, &cached_state);
if (!found || delalloc_end <= *start) {
*start = delalloc_start;
*end = delalloc_end;
......@@ -1899,7 +1909,7 @@ static int __process_pages_contig(struct address_space *mapping,
if (page_ops & PAGE_SET_PRIVATE2)
SetPagePrivate2(pages[i]);
if (pages[i] == locked_page) {
if (locked_page && pages[i] == locked_page) {
put_page(pages[i]);
pages_locked++;
continue;
......@@ -2014,8 +2024,8 @@ u64 count_range_bits(struct extent_io_tree *tree,
* set the private field for a given byte offset in the tree. If there isn't
* an extent_state there already, this does nothing.
*/
static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start,
struct io_failure_record *failrec)
int set_state_failrec(struct extent_io_tree *tree, u64 start,
struct io_failure_record *failrec)
{
struct rb_node *node;
struct extent_state *state;
......@@ -2042,8 +2052,8 @@ static noinline int set_state_failrec(struct extent_io_tree *tree, u64 start,
return ret;
}
static noinline int get_state_failrec(struct extent_io_tree *tree, u64 start,
struct io_failure_record **failrec)
int get_state_failrec(struct extent_io_tree *tree, u64 start,
struct io_failure_record **failrec)
{
struct rb_node *node;
struct extent_state *state;
......@@ -2534,7 +2544,6 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
bio = btrfs_io_bio_alloc(1);
bio->bi_end_io = endio_func;
bio->bi_iter.bi_sector = failrec->logical >> 9;
bio_set_dev(bio, fs_info->fs_devices->latest_bdev);
bio->bi_iter.bi_size = 0;
bio->bi_private = data;
......@@ -2920,7 +2929,6 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
* a contiguous page to the previous one
* @size: portion of page that we want to write
* @offset: starting offset in the page
* @bdev: attach newly created bios to this bdev
* @bio_ret: must be valid pointer, newly allocated bio will be stored there
* @end_io_func: end_io callback for new bio
* @mirror_num: desired mirror to read/write
......@@ -2931,7 +2939,6 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
struct writeback_control *wbc,
struct page *page, u64 offset,
size_t size, unsigned long pg_offset,
struct block_device *bdev,
struct bio **bio_ret,
bio_end_io_t end_io_func,
int mirror_num,
......@@ -2977,13 +2984,16 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
}
bio = btrfs_bio_alloc(offset);
bio_set_dev(bio, bdev);
bio_add_page(bio, page, page_size, pg_offset);
bio->bi_end_io = end_io_func;
bio->bi_private = tree;
bio->bi_write_hint = page->mapping->host->i_write_hint;
bio->bi_opf = opf;
if (wbc) {
struct block_device *bdev;
bdev = BTRFS_I(page->mapping->host)->root->fs_info->fs_devices->latest_bdev;
bio_set_dev(bio, bdev);
wbc_init_bio(wbc, bio);
wbc_account_cgroup_owner(wbc, page, page_size);
}
......@@ -3065,7 +3075,6 @@ static int __do_readpage(struct extent_io_tree *tree,
u64 block_start;
u64 cur_end;
struct extent_map *em;
struct block_device *bdev;
int ret = 0;
int nr = 0;
size_t pg_offset = 0;
......@@ -3142,7 +3151,6 @@ static int __do_readpage(struct extent_io_tree *tree,
offset = em->block_start + extent_offset;
disk_io_size = iosize;
}
bdev = em->bdev;
block_start = em->block_start;
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
block_start = EXTENT_MAP_HOLE;
......@@ -3232,7 +3240,7 @@ static int __do_readpage(struct extent_io_tree *tree,
ret = submit_extent_page(REQ_OP_READ | read_flags, tree, NULL,
page, offset, disk_io_size,
pg_offset, bdev, bio,
pg_offset, bio,
end_bio_extent_readpage, mirror_num,
*bio_flags,
this_bio_flag,
......@@ -3409,7 +3417,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
struct extent_page_data *epd,
loff_t i_size,
unsigned long nr_written,
unsigned int write_flags, int *nr_ret)
int *nr_ret)
{
struct extent_io_tree *tree = epd->tree;
u64 start = page_offset(page);
......@@ -3420,11 +3428,11 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
u64 block_start;
u64 iosize;
struct extent_map *em;
struct block_device *bdev;
size_t pg_offset = 0;
size_t blocksize;
int ret = 0;
int nr = 0;
const unsigned int write_flags = wbc_to_write_flags(wbc);
bool compressed;
ret = btrfs_writepage_cow_fixup(page, start, page_end);
......@@ -3478,7 +3486,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
iosize = min(em_end - cur, end - cur + 1);
iosize = ALIGN(iosize, blocksize);
offset = em->block_start + extent_offset;
bdev = em->bdev;
block_start = em->block_start;
compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
free_extent_map(em);
......@@ -3520,7 +3527,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
page, offset, iosize, pg_offset,
bdev, &epd->bio,
&epd->bio,
end_bio_extent_writepage,
0, 0, 0, false);
if (ret) {
......@@ -3558,11 +3565,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
size_t pg_offset = 0;
loff_t i_size = i_size_read(inode);
unsigned long end_index = i_size >> PAGE_SHIFT;
unsigned int write_flags = 0;
unsigned long nr_written = 0;
write_flags = wbc_to_write_flags(wbc);
trace___extent_writepage(page, inode, wbc);
WARN_ON(!PageLocked(page));
......@@ -3600,7 +3604,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
}
ret = __extent_writepage_io(inode, page, wbc, epd,
i_size, nr_written, write_flags, &nr);
i_size, nr_written, &nr);
if (ret == 1)
goto done_unlocked;
......@@ -3849,7 +3853,6 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
struct extent_page_data *epd)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct block_device *bdev = fs_info->fs_devices->latest_bdev;
struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
u64 offset = eb->start;
u32 nritems;
......@@ -3884,7 +3887,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
clear_page_dirty_for_io(p);
set_page_writeback(p);
ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc,
p, offset, PAGE_SIZE, 0, bdev,
p, offset, PAGE_SIZE, 0,
&epd->bio,
end_bio_extent_buffer_writepage,
0, 0, 0, false);
......@@ -4121,7 +4124,7 @@ static int extent_write_cache_pages(struct address_space *mapping,
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
done_index = page->index;
done_index = page->index + 1;
/*
* At this point we hold neither the i_pages lock nor
* the page lock: the page may be truncated or
......@@ -4156,16 +4159,6 @@ static int extent_write_cache_pages(struct address_space *mapping,
ret = __extent_writepage(page, wbc, epd);
if (ret < 0) {
/*
* done_index is set past this page,
* so media errors will not choke
* background writeout for the entire
* file. This has consequences for
* range_cyclic semantics (ie. it may
* not be suitable for data integrity
* writeout).
*/
done_index = page->index + 1;
done = 1;
break;
}
......@@ -4240,8 +4233,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
.nr_to_write = nr_pages * 2,
.range_start = start,
.range_end = end + 1,
/* We're called from an async helper function */
.punt_to_cgroup = 1,
.no_cgroup_owner = 1,
};
wbc_attach_fdatawrite_inode(&wbc_writepages, inode);
while (start <= end) {
page = find_get_page(mapping, start >> PAGE_SHIFT);
if (clear_page_dirty_for_io(page))
......@@ -4256,11 +4253,12 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
}
ASSERT(ret <= 0);
if (ret < 0) {
if (ret == 0)
ret = flush_write_bio(&epd);
else
end_write_bio(&epd, ret);
return ret;
}
ret = flush_write_bio(&epd);
wbc_detach_inode(&wbc_writepages);
return ret;
}
......
fs/btrfs/extent_io.h
浏览文件 @ 97d0bf96
......@@ -7,35 +7,6 @@
#include <linux/refcount.h>
#include "ulist.h"
/* bits for the extent state */
#define EXTENT_DIRTY (1U << 0)
#define EXTENT_UPTODATE (1U << 1)
#define EXTENT_LOCKED (1U << 2)
#define EXTENT_NEW (1U << 3)
#define EXTENT_DELALLOC (1U << 4)
#define EXTENT_DEFRAG (1U << 5)
#define EXTENT_BOUNDARY (1U << 6)
#define EXTENT_NODATASUM (1U << 7)
#define EXTENT_CLEAR_META_RESV (1U << 8)
#define EXTENT_NEED_WAIT (1U << 9)
#define EXTENT_DAMAGED (1U << 10)
#define EXTENT_NORESERVE (1U << 11)
#define EXTENT_QGROUP_RESERVED (1U << 12)
#define EXTENT_CLEAR_DATA_RESV (1U << 13)
#define EXTENT_DELALLOC_NEW (1U << 14)
#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \
EXTENT_CLEAR_DATA_RESV)
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING)
/*
* Redefined bits above which are used only in the device allocation tree,
* shouldn't be using EXTENT_LOCKED / EXTENT_BOUNDARY / EXTENT_CLEAR_META_RESV
* / EXTENT_CLEAR_DATA_RESV because they have special meaning to the bit
* manipulation functions
*/
#define CHUNK_ALLOCATED EXTENT_DIRTY
#define CHUNK_TRIMMED EXTENT_DEFRAG
/*
* flags for bio submission. The high bits indicate the compression
* type for this bio
......@@ -89,12 +60,11 @@ enum {
#define BITMAP_LAST_BYTE_MASK(nbits) \
(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
struct extent_state;
struct btrfs_root;
struct btrfs_inode;
struct btrfs_io_bio;
struct io_failure_record;
struct extent_io_tree;
typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
struct bio *bio, u64 bio_offset);
......@@ -111,47 +81,6 @@ struct extent_io_ops {
int mirror);
};
enum {
IO_TREE_FS_INFO_FREED_EXTENTS0,
IO_TREE_FS_INFO_FREED_EXTENTS1,
IO_TREE_INODE_IO,
IO_TREE_INODE_IO_FAILURE,
IO_TREE_RELOC_BLOCKS,
IO_TREE_TRANS_DIRTY_PAGES,
IO_TREE_ROOT_DIRTY_LOG_PAGES,
IO_TREE_SELFTEST,
};
struct extent_io_tree {
struct rb_root state;
struct btrfs_fs_info *fs_info;
void *private_data;
u64 dirty_bytes;
bool track_uptodate;
/* Who owns this io tree, should be one of IO_TREE_* */
u8 owner;
spinlock_t lock;
const struct extent_io_ops *ops;
};
struct extent_state {
u64 start;
u64 end; /* inclusive */
struct rb_node rb_node;
/* ADD NEW ELEMENTS AFTER THIS */
wait_queue_head_t wq;
refcount_t refs;
unsigned state;
struct io_failure_record *failrec;
#ifdef CONFIG_BTRFS_DEBUG
struct list_head leak_list;
#endif
};
#define INLINE_EXTENT_BUFFER_PAGES 16
#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
......@@ -259,152 +188,11 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
u64 start, u64 len,
int create);
void extent_io_tree_init(struct btrfs_fs_info *fs_info,
struct extent_io_tree *tree, unsigned int owner,
void *private_data);
void extent_io_tree_release(struct extent_io_tree *tree);
int try_release_extent_mapping(struct page *page, gfp_t mask);
int try_release_extent_buffer(struct page *page);
int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached);
static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
{
return lock_extent_bits(tree, start, end, NULL);
}
int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end);
int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
get_extent_t *get_extent, int mirror_num);
int __init extent_io_init(void);
void __cold extent_io_exit(void);
u64 count_range_bits(struct extent_io_tree *tree,
u64 *start, u64 search_end,
u64 max_bytes, unsigned bits, int contig);
void free_extent_state(struct extent_state *state);
int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int filled,
struct extent_state *cached_state);
int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, struct extent_changeset *changeset);
int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int wake, int delete,
struct extent_state **cached);
int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int wake, int delete,
struct extent_state **cached, gfp_t mask,
struct extent_changeset *changeset);
static inline int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
{
return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL);
}
static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached)
{
return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
GFP_NOFS, NULL);
}
static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
u64 start, u64 end, struct extent_state **cached)
{
return __clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
GFP_ATOMIC, NULL);
}
static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
u64 end, unsigned bits)
{
int wake = 0;
if (bits & EXTENT_LOCKED)
wake = 1;
return clear_extent_bit(tree, start, end, bits, wake, 0, NULL);
}
int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, struct extent_changeset *changeset);
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, u64 *failed_start,
struct extent_state **cached_state, gfp_t mask);
int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits);
static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
u64 end, unsigned bits)
{
return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
}
static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state)
{
return __clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
cached_state, GFP_NOFS, NULL);
}
static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
u64 end, gfp_t mask)
{
return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
NULL, mask);
}
static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached)
{
return clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING, 0, 0, cached);
}
int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, unsigned clear_bits,
struct extent_state **cached_state);
static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
u64 end, unsigned int extra_bits,
struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
NULL, cached_state, GFP_NOFS);
}
static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
NULL, cached_state, GFP_NOFS);
}
static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
u64 end)
{
return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
GFP_NOFS);
}
static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state, gfp_t mask)
{
return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
cached_state, mask);
}
int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, unsigned bits,
struct extent_state **cached_state);
void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
u64 *start_ret, u64 *end_ret, unsigned bits);
int extent_invalidatepage(struct extent_io_tree *tree,
struct page *page, unsigned long offset);
int extent_write_full_page(struct page *page, struct writeback_control *wbc);
int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
int mode);
......@@ -442,11 +230,6 @@ static inline int num_extent_pages(const struct extent_buffer *eb)
(eb->start >> PAGE_SHIFT);
}
static inline void extent_buffer_get(struct extent_buffer *eb)
{
atomic_inc(&eb->refs);
}
static inline int extent_buffer_uptodate(struct extent_buffer *eb)
{
return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
......@@ -508,10 +291,6 @@ struct btrfs_inode;
int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
u64 length, u64 logical, struct page *page,
unsigned int pg_offset, int mirror_num);
int clean_io_failure(struct btrfs_fs_info *fs_info,
struct extent_io_tree *failure_tree,
struct extent_io_tree *io_tree, u64 start,
struct page *page, u64 ino, unsigned int pg_offset);
void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num);
......@@ -535,19 +314,12 @@ struct io_failure_record {
};
void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
u64 end);
int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
struct io_failure_record **failrec_ret);
bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
struct io_failure_record *failrec, int fail_mirror);
struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
struct io_failure_record *failrec,
struct page *page, int pg_offset, int icsum,
bio_end_io_t *endio_func, void *data);
int free_io_failure(struct extent_io_tree *failure_tree,
struct extent_io_tree *io_tree,
struct io_failure_record *rec);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
bool find_lock_delalloc_range(struct inode *inode,
struct page *locked_page, u64 *start,
......@@ -555,5 +327,4 @@ bool find_lock_delalloc_range(struct inode *inode,
#endif
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
#endif
fs/btrfs/extent_map.c
浏览文件 @ 97d0bf96
......@@ -214,9 +214,13 @@ static int mergable_maps(struct extent_map *prev, struct extent_map *next)
ASSERT(next->block_start != EXTENT_MAP_DELALLOC &&
prev->block_start != EXTENT_MAP_DELALLOC);
if (prev->map_lookup || next->map_lookup)
ASSERT(test_bit(EXTENT_FLAG_FS_MAPPING, &prev->flags) &&
test_bit(EXTENT_FLAG_FS_MAPPING, &next->flags));
if (extent_map_end(prev) == next->start &&
prev->flags == next->flags &&
prev->bdev == next->bdev &&
prev->map_lookup == next->map_lookup &&
((next->block_start == EXTENT_MAP_HOLE &&
prev->block_start == EXTENT_MAP_HOLE) ||
(next->block_start == EXTENT_MAP_INLINE &&
......
fs/btrfs/extent_map.h
浏览文件 @ 97d0bf96
......@@ -42,15 +42,8 @@ struct extent_map {
u64 block_len;
u64 generation;
unsigned long flags;
union {
struct block_device *bdev;
/*
* used for chunk mappings
* flags & EXTENT_FLAG_FS_MAPPING must be set
*/
struct map_lookup *map_lookup;
};
/* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */
struct map_lookup *map_lookup;
refcount_t refs;
unsigned int compress_type;
struct list_head list;
......
fs/btrfs/file-item.c
浏览文件 @ 97d0bf96
......@@ -945,7 +945,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
u8 type = btrfs_file_extent_type(leaf, fi);
int compress_type = btrfs_file_extent_compression(leaf, fi);
em->bdev = fs_info->fs_devices->latest_bdev;
btrfs_item_key_to_cpu(leaf, &key, slot);
extent_start = key.offset;
......
fs/btrfs/file.c
浏览文件 @ 97d0bf96
......@@ -296,7 +296,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
key.objectid = defrag->ino;
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
inode = btrfs_iget(fs_info->sb, &key, inode_root);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
goto cleanup;
......@@ -667,7 +667,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
}
split->generation = gen;
split->bdev = em->bdev;
split->flags = flags;
split->compress_type = em->compress_type;
replace_extent_mapping(em_tree, em, split, modified);
......@@ -680,7 +679,6 @@ void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
split->start = start + len;
split->len = em->start + em->len - (start + len);
split->bdev = em->bdev;
split->flags = flags;
split->compress_type = em->compress_type;
split->generation = gen;
......@@ -1636,6 +1634,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
break;
}
only_release_metadata = false;
sector_offset = pos & (fs_info->sectorsize - 1);
reserve_bytes = round_up(write_bytes + sector_offset,
fs_info->sectorsize);
......@@ -1791,7 +1790,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
lockend, EXTENT_NORESERVE, NULL,
NULL, GFP_NOFS);
only_release_metadata = false;
}
btrfs_drop_pages(pages, num_pages);
......@@ -1903,9 +1901,10 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
(iocb->ki_flags & IOCB_NOWAIT))
return -EOPNOTSUPP;
if (!inode_trylock(inode)) {
if (iocb->ki_flags & IOCB_NOWAIT)
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!inode_trylock(inode))
return -EAGAIN;
} else {
inode_lock(inode);
}
......@@ -2359,7 +2358,6 @@ static int fill_holes(struct btrfs_trans_handle *trans,
hole_em->block_start = EXTENT_MAP_HOLE;
hole_em->block_len = 0;
hole_em->orig_block_len = 0;
hole_em->bdev = fs_info->fs_devices->latest_bdev;
hole_em->compress_type = BTRFS_COMPRESS_NONE;
hole_em->generation = trans->transid;
......@@ -3350,29 +3348,30 @@ static long btrfs_fallocate(struct file *file, int mode,
return ret;
}
static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
static loff_t find_desired_extent(struct inode *inode, loff_t offset,
int whence)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
loff_t i_size = inode->i_size;
u64 lockstart;
u64 lockend;
u64 start;
u64 len;
int ret = 0;
if (inode->i_size == 0)
if (i_size == 0 || offset >= i_size)
return -ENXIO;
/*
* *offset can be negative, in this case we start finding DATA/HOLE from
* offset can be negative, in this case we start finding DATA/HOLE from
* the very start of the file.
*/
start = max_t(loff_t, 0, *offset);
start = max_t(loff_t, 0, offset);
lockstart = round_down(start, fs_info->sectorsize);
lockend = round_up(i_size_read(inode),
fs_info->sectorsize);
lockend = round_up(i_size, fs_info->sectorsize);
if (lockend <= lockstart)
lockend = lockstart + fs_info->sectorsize;
lockend--;
......@@ -3381,7 +3380,7 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state);
while (start < inode->i_size) {
while (start < i_size) {
em = btrfs_get_extent_fiemap(BTRFS_I(inode), start, len);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
......@@ -3404,46 +3403,39 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
cond_resched();
}
free_extent_map(em);
if (!ret) {
if (whence == SEEK_DATA && start >= inode->i_size)
ret = -ENXIO;
else
*offset = min_t(loff_t, start, inode->i_size);
}
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state);
return ret;
if (ret) {
offset = ret;
} else {
if (whence == SEEK_DATA && start >= i_size)
offset = -ENXIO;
else
offset = min_t(loff_t, start, i_size);
}
return offset;
}
static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
int ret;
inode_lock(inode);
switch (whence) {
case SEEK_END:
case SEEK_CUR:
offset = generic_file_llseek(file, offset, whence);
goto out;
default:
return generic_file_llseek(file, offset, whence);
case SEEK_DATA:
case SEEK_HOLE:
if (offset >= i_size_read(inode)) {
inode_unlock(inode);
return -ENXIO;
}
ret = find_desired_extent(inode, &offset, whence);
if (ret) {
inode_unlock(inode);
return ret;
}
inode_lock_shared(inode);
offset = find_desired_extent(inode, offset, whence);
inode_unlock_shared(inode);
break;
}
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out:
inode_unlock(inode);
return offset;
if (offset < 0)
return offset;
return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
}
static int btrfs_file_open(struct inode *inode, struct file *filp)
......
fs/btrfs/free-space-cache.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/free-space-cache.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/free-space-tree.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/free-space-tree.h
浏览文件 @ 97d0bf96
......@@ -16,14 +16,14 @@ struct btrfs_caching_control;
#define BTRFS_FREE_SPACE_BITMAP_SIZE 256
#define BTRFS_FREE_SPACE_BITMAP_BITS (BTRFS_FREE_SPACE_BITMAP_SIZE * BITS_PER_BYTE)
void set_free_space_tree_thresholds(struct btrfs_block_group_cache *block_group);
void set_free_space_tree_thresholds(struct btrfs_block_group *block_group);
int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
int add_block_group_free_space(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group);
struct btrfs_block_group *block_group);
int remove_block_group_free_space(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group);
struct btrfs_block_group *block_group);
int add_to_free_space_tree(struct btrfs_trans_handle *trans,
u64 start, u64 size);
int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
......@@ -32,21 +32,21 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans,
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct btrfs_free_space_info *
search_free_space_info(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group,
struct btrfs_block_group *block_group,
struct btrfs_path *path, int cow);
int __add_to_free_space_tree(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group,
struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 start, u64 size);
int __remove_from_free_space_tree(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group,
struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 start, u64 size);
int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group,
struct btrfs_block_group *block_group,
struct btrfs_path *path);
int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *block_group,
struct btrfs_block_group *block_group,
struct btrfs_path *path);
int free_space_test_bit(struct btrfs_block_group_cache *block_group,
int free_space_test_bit(struct btrfs_block_group *block_group,
struct btrfs_path *path, u64 offset);
#endif
......
fs/btrfs/inode.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/ioctl.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/locking.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/locking.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/lzo.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/misc.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/ordered-data.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/ordered-data.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/print-tree.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/props.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/qgroup.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/qgroup.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/raid56.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/reada.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/relocation.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/scrub.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/send.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/space-info.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/space-info.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/super.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/sysfs.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/sysfs.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/tests/btrfs-tests.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/tests/btrfs-tests.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/tests/free-space-tests.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/transaction.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/transaction.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/tree-checker.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/tree-log.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/volumes.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/volumes.h
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/zlib.c
浏览文件 @ 97d0bf96
此差异已折叠。
fs/btrfs/zstd.c
浏览文件 @ 97d0bf96
此差异已折叠。
include/trace/events/btrfs.h
浏览文件 @ 97d0bf96
此差异已折叠。
include/uapi/linux/btrfs.h
浏览文件 @ 97d0bf96
此差异已折叠。
include/uapi/linux/btrfs_tree.h
浏览文件 @ 97d0bf96
此差异已折叠。
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或