Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
提交 11e3235b 编写于 作者: L Linus Torvalds
浏览文件
操作

Merge tag 'for-5.10-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux 

Pull btrfs updates from David Sterba:
 "Mostly core updates with a few user visible bits and fixes.

  Hilights:

   - fsync performance improvements
      - less contention of log mutex (throughput +4%, latency -14%,
        dbench with 32 clients)
      - skip unnecessary commits for link and rename (throughput +6%,
        latency -30%, rename latency -75%, dbench with 16 clients)
      - make fast fsync wait only for writeback (throughput +10..40%,
        runtime -1..-20%, dbench with 1 to 64 clients on various
        file/block sizes)

   - direct io is now implemented using the iomap infrastructure, that's
     the main part, we still have a workaround that requires an iomap
     API update, coming in 5.10

   - new sysfs exports:
      - information about the exclusive filesystem operation status
        (balance, device add/remove/replace, ...)
      - supported send stream version

  Core:

   - use ticket space reservations for data, fair policy using the same
     infrastructure as metadata

   - preparatory work to switch locking from our custom tree locks to
     standard rwsem, now the locking context is propagated to all
     callers, actual switch is expected to happen in the next dev cycle

   - seed device structures are now using list API

   - extent tracepoints print proper tree id

   - unified range checks for extent buffer helpers

   - send: avoid using temporary buffer for copying data

   - remove unnecessary RCU protection from space infos

   - remove unused readpage callback for metadata, enabling several
     cleanups

   - replace indirect function calls for end io hooks and remove
     extent_io_ops completely

  Fixes:

   - more lockdep warning fixes

   - fix qgroup reservation for delayed inode and an occasional
     reservation leak for preallocated files

   - fix device replace of a seed device

   - fix metadata reservation for fallocate that leads to transaction
     aborts

   - reschedule if necessary when logging directory items or when
     cloning lots of extents

   - tree-checker: fix false alert caused by legacy btrfs root item

   - send: fix rename/link conflicts for orphanized inodes

   - properly initialize device stats for seed devices

   - skip devices without magic signature when mounting

  Other:

   - error handling improvements, BUG_ONs replaced by proper handling,
     fuzz fixes

   - various function parameter cleanups

   - various W=1 cleanups

   - error/info messages improved

  Mishaps:

   - commit 62cf5391 ("btrfs: move btrfs_rm_dev_replace_free_srcdev
     outside of all locks") is a rebase leftover after the patch got
     merged to 5.9-rc8 as a466c85e ("btrfs: move
     btrfs_rm_dev_replace_free_srcdev outside of all locks"), the
     remaining part is trivial and the patch is in the middle of the
     series so I'm keeping it there instead of rebasing"

* tag 'for-5.10-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (161 commits)
  btrfs: rename BTRFS_INODE_ORDERED_DATA_CLOSE flag
  btrfs: annotate device name rcu_string with __rcu
  btrfs: skip devices without magic signature when mounting
  btrfs: cleanup cow block on error
  btrfs: remove BTRFS_INODE_READDIO_NEED_LOCK
  fs: remove no longer used dio_end_io()
  btrfs: return error if we're unable to read device stats
  btrfs: init device stats for seed devices
  btrfs: remove struct extent_io_ops
  btrfs: call submit_bio_hook directly for metadata pages
  btrfs: stop calling submit_bio_hook for data inodes
  btrfs: don't opencode is_data_inode in end_bio_extent_readpage
  btrfs: call submit_bio_hook directly in submit_one_bio
  btrfs: remove extent_io_ops::readpage_end_io_hook
  btrfs: replace readpage_end_io_hook with direct calls
  btrfs: send, recompute reference path after orphanization of a directory
  btrfs: send, orphanize first all conflicting inodes when processing references
  btrfs: tree-checker: fix false alert caused by legacy btrfs root item
  btrfs: use unaligned helpers for stack and header set/get helpers
  btrfs: free-space-cache: use unaligned helpers to access data
  ...
上级 c024a811 1fd4033d
展开全部 隐藏空白更改
内联 并排
Showing with 2719 addition and 1993 deletion
fs/btrfs/Kconfig
浏览文件 @ 11e3235b
......@@ -14,6 +14,7 @@ config BTRFS_FS
select LZO_DECOMPRESS
select ZSTD_COMPRESS
select ZSTD_DECOMPRESS
select FS_IOMAP
select RAID6_PQ
select XOR_BLOCKS
select SRCU
......
fs/btrfs/backref.c
浏览文件 @ 11e3235b
......@@ -2997,7 +2997,6 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache,
while (!list_empty(&pending_edge)) {
struct btrfs_backref_node *upper;
struct btrfs_backref_node *lower;
struct rb_node *rb_node;
edge = list_first_entry(&pending_edge,
struct btrfs_backref_edge, list[UPPER]);
......
fs/btrfs/block-group.c
浏览文件 @ 11e3235b
......@@ -1766,16 +1766,10 @@ static void link_block_group(struct btrfs_block_group *cache)
{
struct btrfs_space_info *space_info = cache->space_info;
int index = btrfs_bg_flags_to_raid_index(cache->flags);
bool first = false;
down_write(&space_info->groups_sem);
if (list_empty(&space_info->block_groups[index]))
first = true;
list_add_tail(&cache->list, &space_info->block_groups[index]);
up_write(&space_info->groups_sem);
if (first)
btrfs_sysfs_add_block_group_type(cache);
}
static struct btrfs_block_group *btrfs_create_block_group_cache(
......@@ -1873,7 +1867,7 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
return ret;
}
static int read_block_group_item(struct btrfs_block_group *cache,
static void read_block_group_item(struct btrfs_block_group *cache,
struct btrfs_path *path,
const struct btrfs_key *key)
{
......@@ -1887,8 +1881,6 @@ static int read_block_group_item(struct btrfs_block_group *cache,
sizeof(bgi));
cache->used = btrfs_stack_block_group_used(&bgi);
cache->flags = btrfs_stack_block_group_flags(&bgi);
return 0;
}
static int read_one_block_group(struct btrfs_fs_info *info,
......@@ -1907,9 +1899,7 @@ static int read_one_block_group(struct btrfs_fs_info *info,
if (!cache)
return -ENOMEM;
ret = read_block_group_item(cache, path, key);
if (ret < 0)
goto error;
read_block_group_item(cache, path, key);
set_free_space_tree_thresholds(cache);
......@@ -2035,8 +2025,18 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
btrfs_release_path(path);
}
rcu_read_lock();
list_for_each_entry_rcu(space_info, &info->space_info, list) {
list_for_each_entry(space_info, &info->space_info, list) {
int i;
for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
if (list_empty(&space_info->block_groups[i]))
continue;
cache = list_first_entry(&space_info->block_groups[i],
struct btrfs_block_group,
list);
btrfs_sysfs_add_block_group_type(cache);
}
if (!(btrfs_get_alloc_profile(info, space_info->flags) &
(BTRFS_BLOCK_GROUP_RAID10 |
BTRFS_BLOCK_GROUP_RAID1_MASK |
......@@ -2056,7 +2056,6 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
list)
inc_block_group_ro(cache, 1);
}
rcu_read_unlock();
btrfs_init_global_block_rsv(info);
ret = check_chunk_block_group_mappings(info);
......@@ -2097,12 +2096,16 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
return;
while (!list_empty(&trans->new_bgs)) {
int index;
block_group = list_first_entry(&trans->new_bgs,
struct btrfs_block_group,
bg_list);
if (ret)
goto next;
index = btrfs_bg_flags_to_raid_index(block_group->flags);
ret = insert_block_group_item(trans, block_group);
if (ret)
btrfs_abort_transaction(trans, ret);
......@@ -2111,6 +2114,16 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
if (ret)
btrfs_abort_transaction(trans, ret);
add_block_group_free_space(trans, block_group);
/*
* If we restriped during balance, we may have added a new raid
* type, so now add the sysfs entries when it is safe to do so.
* We don't have to worry about locking here as it's handled in
* btrfs_sysfs_add_block_group_type.
*/
if (block_group->space_info->block_group_kobjs[index] == NULL)
btrfs_sysfs_add_block_group_type(block_group);
/* Already aborted the transaction if it failed. */
next:
btrfs_delayed_refs_rsv_release(fs_info, 1);
......@@ -2785,7 +2798,7 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
* finished yet (no block group item in the extent tree
* yet, etc). If this is the case, wait for all free
* space endio workers to finish and retry. This is a
* a very rare case so no need for a more efficient and
* very rare case so no need for a more efficient and
* complex approach.
*/
if (ret == -ENOENT) {
......@@ -2961,6 +2974,13 @@ int btrfs_add_reserved_bytes(struct btrfs_block_group *cache,
space_info, -ram_bytes);
if (delalloc)
cache->delalloc_bytes += num_bytes;
/*
* Compression can use less space than we reserved, so wake
* tickets if that happens
*/
if (num_bytes < ram_bytes)
btrfs_try_granting_tickets(cache->fs_info, space_info);
}
spin_unlock(&cache->lock);
spin_unlock(&space_info->lock);
......@@ -2994,6 +3014,8 @@ void btrfs_free_reserved_bytes(struct btrfs_block_group *cache,
if (delalloc)
cache->delalloc_bytes -= num_bytes;
spin_unlock(&cache->lock);
btrfs_try_granting_tickets(cache->fs_info, space_info);
spin_unlock(&space_info->lock);
}
......@@ -3002,12 +3024,10 @@ static void force_metadata_allocation(struct btrfs_fs_info *info)
struct list_head *head = &info->space_info;
struct btrfs_space_info *found;
rcu_read_lock();
list_for_each_entry_rcu(found, head, list) {
list_for_each_entry(found, head, list) {
if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
found->force_alloc = CHUNK_ALLOC_FORCE;
}
rcu_read_unlock();
}
static int should_alloc_chunk(struct btrfs_fs_info *fs_info,
......@@ -3338,14 +3358,6 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
}
spin_unlock(&info->block_group_cache_lock);
/*
* Now that all the block groups are freed, go through and free all the
* space_info structs. This is only called during the final stages of
* unmount, and so we know nobody is using them. We call
* synchronize_rcu() once before we start, just to be on the safe side.
*/
synchronize_rcu();
btrfs_release_global_block_rsv(info);
while (!list_empty(&info->space_info)) {
......
fs/btrfs/btrfs_inode.h
浏览文件 @ 11e3235b
......@@ -21,14 +21,18 @@
* new data the application may have written before commit.
*/
enum {
BTRFS_INODE_ORDERED_DATA_CLOSE,
BTRFS_INODE_FLUSH_ON_CLOSE,
BTRFS_INODE_DUMMY,
BTRFS_INODE_IN_DEFRAG,
BTRFS_INODE_HAS_ASYNC_EXTENT,
/*
* Always set under the VFS' inode lock, otherwise it can cause races
* during fsync (we start as a fast fsync and then end up in a full
* fsync racing with ordered extent completion).
*/
BTRFS_INODE_NEEDS_FULL_SYNC,
BTRFS_INODE_COPY_EVERYTHING,
BTRFS_INODE_IN_DELALLOC_LIST,
BTRFS_INODE_READDIO_NEED_LOCK,
BTRFS_INODE_HAS_PROPS,
BTRFS_INODE_SNAPSHOT_FLUSH,
};
......@@ -212,6 +216,11 @@ struct btrfs_inode {
struct inode vfs_inode;
};
static inline u32 btrfs_inode_sectorsize(const struct btrfs_inode *inode)
{
return inode->root->fs_info->sectorsize;
}
static inline struct btrfs_inode *BTRFS_I(const struct inode *inode)
{
return container_of(inode, struct btrfs_inode, vfs_inode);
......@@ -324,23 +333,6 @@ struct btrfs_dio_private {
u8 csums[];
};
/*
* Disable DIO read nolock optimization, so new dio readers will be forced
* to grab i_mutex. It is used to avoid the endless truncate due to
* nonlocked dio read.
*/
static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode)
{
set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
smp_mb();
}
static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode)
{
smp_mb__before_atomic();
clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
}
/* Array of bytes with variable length, hexadecimal format 0x1234 */
#define CSUM_FMT "0x%*phN"
#define CSUM_FMT_VALUE(size, bytes) size, bytes
......
fs/btrfs/compression.c
浏览文件 @ 11e3235b
......@@ -29,41 +29,6 @@
#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)
......
fs/btrfs/compression.h
浏览文件 @ 11e3235b
......@@ -144,4 +144,39 @@ bool btrfs_compress_is_valid_type(const char *str, size_t len);
int btrfs_compress_heuristic(struct inode *inode, u64 start, u64 end);
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);
#endif
fs/btrfs/ctree.c
浏览文件 @ 11e3235b
......@@ -198,7 +198,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
btrfs_node_key(buf, &disk_key, 0);
cow = btrfs_alloc_tree_block(trans, root, 0, new_root_objectid,
&disk_key, level, buf->start, 0);
&disk_key, level, buf->start, 0,
BTRFS_NESTING_NEW_ROOT);
if (IS_ERR(cow))
return PTR_ERR(cow);
......@@ -957,7 +958,8 @@ static struct extent_buffer *alloc_tree_block_no_bg_flush(
const struct btrfs_disk_key *disk_key,
int level,
u64 hint,
u64 empty_size)
u64 empty_size,
enum btrfs_lock_nesting nest)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_buffer *ret;
......@@ -986,7 +988,7 @@ static struct extent_buffer *alloc_tree_block_no_bg_flush(
ret = btrfs_alloc_tree_block(trans, root, parent_start,
root->root_key.objectid, disk_key, level,
hint, empty_size);
hint, empty_size, nest);
trans->can_flush_pending_bgs = true;
return ret;
......@@ -1009,7 +1011,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
struct extent_buffer *buf,
struct extent_buffer *parent, int parent_slot,
struct extent_buffer **cow_ret,
u64 search_start, u64 empty_size)
u64 search_start, u64 empty_size,
enum btrfs_lock_nesting nest)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_disk_key disk_key;
......@@ -1040,7 +1043,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
parent_start = parent->start;
cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
level, search_start, empty_size);
level, search_start, empty_size, nest);
if (IS_ERR(cow))
return PTR_ERR(cow);
......@@ -1061,6 +1064,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
ret = update_ref_for_cow(trans, root, buf, cow, &last_ref);
if (ret) {
btrfs_tree_unlock(cow);
free_extent_buffer(cow);
btrfs_abort_transaction(trans, ret);
return ret;
}
......@@ -1068,6 +1073,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) {
ret = btrfs_reloc_cow_block(trans, root, buf, cow);
if (ret) {
btrfs_tree_unlock(cow);
free_extent_buffer(cow);
btrfs_abort_transaction(trans, ret);
return ret;
}
......@@ -1100,6 +1107,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
if (last_ref) {
ret = tree_mod_log_free_eb(buf);
if (ret) {
btrfs_tree_unlock(cow);
free_extent_buffer(cow);
btrfs_abort_transaction(trans, ret);
return ret;
}
......@@ -1446,7 +1455,8 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *buf,
struct extent_buffer *parent, int parent_slot,
struct extent_buffer **cow_ret)
struct extent_buffer **cow_ret,
enum btrfs_lock_nesting nest)
{
struct btrfs_fs_info *fs_info = root->fs_info;
u64 search_start;
......@@ -1485,7 +1495,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
*/
btrfs_qgroup_trace_subtree_after_cow(trans, root, buf);
ret = __btrfs_cow_block(trans, root, buf, parent,
parent_slot, cow_ret, search_start, 0);
parent_slot, cow_ret, search_start, 0, nest);
trace_btrfs_cow_block(root, buf, *cow_ret);
......@@ -1657,7 +1667,8 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
err = __btrfs_cow_block(trans, root, cur, parent, i,
&cur, search_start,
min(16 * blocksize,
(end_slot - i) * blocksize));
(end_slot - i) * blocksize),
BTRFS_NESTING_COW);
if (err) {
btrfs_tree_unlock(cur);
free_extent_buffer(cur);
......@@ -1855,7 +1866,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
btrfs_tree_lock(child);
btrfs_set_lock_blocking_write(child);
ret = btrfs_cow_block(trans, root, child, mid, 0, &child);
ret = btrfs_cow_block(trans, root, child, mid, 0, &child,
BTRFS_NESTING_COW);
if (ret) {
btrfs_tree_unlock(child);
free_extent_buffer(child);
......@@ -1891,10 +1903,11 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
left = NULL;
if (left) {
btrfs_tree_lock(left);
__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
btrfs_set_lock_blocking_write(left);
wret = btrfs_cow_block(trans, root, left,
parent, pslot - 1, &left);
parent, pslot - 1, &left,
BTRFS_NESTING_LEFT_COW);
if (wret) {
ret = wret;
goto enospc;
......@@ -1906,10 +1919,11 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
right = NULL;
if (right) {
btrfs_tree_lock(right);
__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
btrfs_set_lock_blocking_write(right);
wret = btrfs_cow_block(trans, root, right,
parent, pslot + 1, &right);
parent, pslot + 1, &right,
BTRFS_NESTING_RIGHT_COW);
if (wret) {
ret = wret;
goto enospc;
......@@ -2069,7 +2083,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
if (left) {
u32 left_nr;
btrfs_tree_lock(left);
__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
btrfs_set_lock_blocking_write(left);
left_nr = btrfs_header_nritems(left);
......@@ -2077,7 +2091,8 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
wret = 1;
} else {
ret = btrfs_cow_block(trans, root, left, parent,
pslot - 1, &left);
pslot - 1, &left,
BTRFS_NESTING_LEFT_COW);
if (ret)
wret = 1;
else {
......@@ -2123,7 +2138,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
if (right) {
u32 right_nr;
btrfs_tree_lock(right);
__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
btrfs_set_lock_blocking_write(right);
right_nr = btrfs_header_nritems(right);
......@@ -2132,7 +2147,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
} else {
ret = btrfs_cow_block(trans, root, right,
parent, pslot + 1,
&right);
&right, BTRFS_NESTING_RIGHT_COW);
if (ret)
wret = 1;
else {
......@@ -2601,7 +2616,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
* We don't know the level of the root node until we actually
* have it read locked
*/
b = btrfs_read_lock_root_node(root);
b = __btrfs_read_lock_root_node(root, p->recurse);
level = btrfs_header_level(b);
if (level > write_lock_level)
goto out;
......@@ -2740,11 +2755,13 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
btrfs_set_path_blocking(p);
if (last_level)
err = btrfs_cow_block(trans, root, b, NULL, 0,
&b);
&b,
BTRFS_NESTING_COW);
else
err = btrfs_cow_block(trans, root, b,
p->nodes[level + 1],
p->slots[level + 1], &b);
p->slots[level + 1], &b,
BTRFS_NESTING_COW);
if (err) {
ret = err;
goto done;
......@@ -2875,7 +2892,8 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
} else {
if (!btrfs_tree_read_lock_atomic(b)) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
__btrfs_tree_read_lock(b, BTRFS_NESTING_NORMAL,
p->recurse);
}
p->locks[level] = BTRFS_READ_LOCK;
}
......@@ -3163,6 +3181,58 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
fixup_low_keys(path, &disk_key, 1);
}
/*
* Check key order of two sibling extent buffers.
*
* Return true if something is wrong.
* Return false if everything is fine.
*
* Tree-checker only works inside one tree block, thus the following
* corruption can not be detected by tree-checker:
*
* Leaf @left | Leaf @right
* --------------------------------------------------------------
* | 1 | 2 | 3 | 4 | 5 | f6 | | 7 | 8 |
*
* Key f6 in leaf @left itself is valid, but not valid when the next
* key in leaf @right is 7.
* This can only be checked at tree block merge time.
* And since tree checker has ensured all key order in each tree block
* is correct, we only need to bother the last key of @left and the first
* key of @right.
*/
static bool check_sibling_keys(struct extent_buffer *left,
struct extent_buffer *right)
{
struct btrfs_key left_last;
struct btrfs_key right_first;
int level = btrfs_header_level(left);
int nr_left = btrfs_header_nritems(left);
int nr_right = btrfs_header_nritems(right);
/* No key to check in one of the tree blocks */
if (!nr_left || !nr_right)
return false;
if (level) {
btrfs_node_key_to_cpu(left, &left_last, nr_left - 1);
btrfs_node_key_to_cpu(right, &right_first, 0);
} else {
btrfs_item_key_to_cpu(left, &left_last, nr_left - 1);
btrfs_item_key_to_cpu(right, &right_first, 0);
}
if (btrfs_comp_cpu_keys(&left_last, &right_first) >= 0) {
btrfs_crit(left->fs_info,
"bad key order, sibling blocks, left last (%llu %u %llu) right first (%llu %u %llu)",
left_last.objectid, left_last.type,
left_last.offset, right_first.objectid,
right_first.type, right_first.offset);
return true;
}
return false;
}
/*
* try to push data from one node into the next node left in the
* tree.
......@@ -3207,6 +3277,12 @@ static int push_node_left(struct btrfs_trans_handle *trans,
} else
push_items = min(src_nritems - 8, push_items);
/* dst is the left eb, src is the middle eb */
if (check_sibling_keys(dst, src)) {
ret = -EUCLEAN;
btrfs_abort_transaction(trans, ret);
return ret;
}
ret = tree_mod_log_eb_copy(dst, src, dst_nritems, 0, push_items);
if (ret) {
btrfs_abort_transaction(trans, ret);
......@@ -3275,6 +3351,12 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
if (max_push < push_items)
push_items = max_push;
/* dst is the right eb, src is the middle eb */
if (check_sibling_keys(src, dst)) {
ret = -EUCLEAN;
btrfs_abort_transaction(trans, ret);
return ret;
}
ret = tree_mod_log_insert_move(dst, push_items, 0, dst_nritems);
BUG_ON(ret < 0);
memmove_extent_buffer(dst, btrfs_node_key_ptr_offset(push_items),
......@@ -3331,7 +3413,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
btrfs_node_key(lower, &lower_key, 0);
c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
root->node->start, 0);
root->node->start, 0,
BTRFS_NESTING_NEW_ROOT);
if (IS_ERR(c))
return PTR_ERR(c);
......@@ -3461,7 +3544,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
btrfs_node_key(c, &disk_key, mid);
split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
c->start, 0);
c->start, 0, BTRFS_NESTING_SPLIT);
if (IS_ERR(split))
return PTR_ERR(split);
......@@ -3730,7 +3813,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
if (IS_ERR(right))
return 1;
btrfs_tree_lock(right);
__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
btrfs_set_lock_blocking_write(right);
free_space = btrfs_leaf_free_space(right);
......@@ -3739,7 +3822,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
/* cow and double check */
ret = btrfs_cow_block(trans, root, right, upper,
slot + 1, &right);
slot + 1, &right, BTRFS_NESTING_RIGHT_COW);
if (ret)
goto out_unlock;
......@@ -3751,6 +3834,12 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
if (left_nritems == 0)
goto out_unlock;
if (check_sibling_keys(left, right)) {
ret = -EUCLEAN;
btrfs_tree_unlock(right);
free_extent_buffer(right);
return ret;
}
if (path->slots[0] == left_nritems && !empty) {
/* Key greater than all keys in the leaf, right neighbor has
* enough room for it and we're not emptying our leaf to delete
......@@ -3963,7 +4052,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
if (IS_ERR(left))
return 1;
btrfs_tree_lock(left);
__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
btrfs_set_lock_blocking_write(left);
free_space = btrfs_leaf_free_space(left);
......@@ -3974,7 +4063,8 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
/* cow and double check */
ret = btrfs_cow_block(trans, root, left,
path->nodes[1], slot - 1, &left);
path->nodes[1], slot - 1, &left,
BTRFS_NESTING_LEFT_COW);
if (ret) {
/* we hit -ENOSPC, but it isn't fatal here */
if (ret == -ENOSPC)
......@@ -3988,6 +4078,10 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
goto out;
}
if (check_sibling_keys(left, right)) {
ret = -EUCLEAN;
goto out;
}
return __push_leaf_left(path, min_data_size,
empty, left, free_space, right_nritems,
max_slot);
......@@ -4236,8 +4330,18 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
else
btrfs_item_key(l, &disk_key, mid);
/*
* We have to about BTRFS_NESTING_NEW_ROOT here if we've done a double
* split, because we're only allowed to have MAX_LOCKDEP_SUBCLASSES
* subclasses, which is 8 at the time of this patch, and we've maxed it
* out. In the future we could add a
* BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just
* use BTRFS_NESTING_NEW_ROOT.
*/
right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
l->start, 0);
l->start, 0, num_doubles ?
BTRFS_NESTING_NEW_ROOT :
BTRFS_NESTING_SPLIT);
if (IS_ERR(right))
return PTR_ERR(right);
......@@ -4482,9 +4586,7 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
return ret;
path->slots[0]++;
setup_items_for_insert(root, path, new_key, &item_size,
item_size, item_size +
sizeof(struct btrfs_item), 1);
setup_items_for_insert(root, path, new_key, &item_size, 1);
leaf = path->nodes[0];
memcpy_extent_buffer(leaf,
btrfs_item_ptr_offset(leaf, path->slots[0]),
......@@ -4657,14 +4759,20 @@ void btrfs_extend_item(struct btrfs_path *path, u32 data_size)
}
}
/*
* this is a helper for btrfs_insert_empty_items, the main goal here is
* to save stack depth by doing the bulk of the work in a function
* that doesn't call btrfs_search_slot
/**
* setup_items_for_insert - Helper called before inserting one or more items
* to a leaf. Main purpose is to save stack depth by doing the bulk of the work
* in a function that doesn't call btrfs_search_slot
*
* @root: root we are inserting items to
* @path: points to the leaf/slot where we are going to insert new items
* @cpu_key: array of keys for items to be inserted
* @data_size: size of the body of each item we are going to insert
* @nr: size of @cpu_key/@data_size arrays
*/
void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
const struct btrfs_key *cpu_key, u32 *data_size,
u32 total_data, u32 total_size, int nr)
int nr)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_item *item;
......@@ -4675,6 +4783,12 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
struct extent_buffer *leaf;
int slot;
struct btrfs_map_token token;
u32 total_size;
u32 total_data = 0;
for (i = 0; i < nr; i++)
total_data += data_size[i];
total_size = total_data + (nr * sizeof(struct btrfs_item));
if (path->slots[0] == 0) {
btrfs_cpu_key_to_disk(&disk_key, cpu_key);
......@@ -4701,7 +4815,8 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
if (old_data < data_end) {
btrfs_print_leaf(leaf);
btrfs_crit(fs_info, "slot %d old_data %d data_end %d",
btrfs_crit(fs_info,
"item at slot %d with data offset %u beyond data end of leaf %u",
slot, old_data, data_end);
BUG();
}
......@@ -4734,8 +4849,8 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
btrfs_cpu_key_to_disk(&disk_key, cpu_key + i);
btrfs_set_item_key(leaf, &disk_key, slot + i);
item = btrfs_item_nr(slot + i);
btrfs_set_token_item_offset(&token, item, data_end - data_size[i]);
data_end -= data_size[i];
btrfs_set_token_item_offset(&token, item, data_end);
btrfs_set_token_item_size(&token, item, data_size[i]);
}
......@@ -4777,8 +4892,7 @@ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
slot = path->slots[0];
BUG_ON(slot < 0);
setup_items_for_insert(root, path, cpu_key, data_size,
total_data, total_size, nr);
setup_items_for_insert(root, path, cpu_key, data_size, nr);
return 0;
}
......@@ -5115,7 +5229,7 @@ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
slot--;
/*
* check this node pointer against the min_trans parameters.
* If it is too old, old, skip to the next one.
* If it is too old, skip to the next one.
*/
while (slot < nritems) {
u64 gen;
......@@ -5379,7 +5493,9 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
}
if (!ret) {
btrfs_set_path_blocking(path);
btrfs_tree_read_lock(next);
__btrfs_tree_read_lock(next,
BTRFS_NESTING_RIGHT,
path->recurse);
}
next_rw_lock = BTRFS_READ_LOCK;
}
......@@ -5414,7 +5530,9 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
ret = btrfs_try_tree_read_lock(next);
if (!ret) {
btrfs_set_path_blocking(path);
btrfs_tree_read_lock(next);
__btrfs_tree_read_lock(next,
BTRFS_NESTING_RIGHT,
path->recurse);
}
next_rw_lock = BTRFS_READ_LOCK;
}
......
fs/btrfs/ctree.h
浏览文件 @ 11e3235b
......@@ -374,6 +374,7 @@ struct btrfs_path {
unsigned int search_commit_root:1;
unsigned int need_commit_sem:1;
unsigned int skip_release_on_error:1;
unsigned int recurse:1;
};
#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
sizeof(struct btrfs_item))
......@@ -494,7 +495,7 @@ enum btrfs_orphan_cleanup_state {
ORPHAN_CLEANUP_DONE = 2,
};
void btrfs_init_async_reclaim_work(struct work_struct *work);
void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info);
/* fs_info */
struct reloc_control;
......@@ -540,11 +541,6 @@ enum {
BTRFS_FS_QUOTA_OVERRIDE,
/* Used to record internally whether fs has been frozen */
BTRFS_FS_FROZEN,
/*
* Indicate that a whole-filesystem exclusive operation is running
* (device replace, resize, device add/delete, balance)
*/
BTRFS_FS_EXCL_OP,
/*
* Indicate that balance has been set up from the ioctl and is in the
* main phase. The fs_info::balance_ctl is initialized.
......@@ -565,6 +561,19 @@ enum {
BTRFS_FS_DISCARD_RUNNING,
};
/*
* Exclusive operations (device replace, resize, device add/remove, balance)
*/
enum btrfs_exclusive_operation {
BTRFS_EXCLOP_NONE,
BTRFS_EXCLOP_BALANCE,
BTRFS_EXCLOP_DEV_ADD,
BTRFS_EXCLOP_DEV_REMOVE,
BTRFS_EXCLOP_DEV_REPLACE,
BTRFS_EXCLOP_RESIZE,
BTRFS_EXCLOP_SWAP_ACTIVATE,
};
struct btrfs_fs_info {
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
unsigned long flags;
......@@ -912,6 +921,7 @@ struct btrfs_fs_info {
/* Used to reclaim the metadata space in the background. */
struct work_struct async_reclaim_work;
struct work_struct async_data_reclaim_work;
spinlock_t unused_bgs_lock;
struct list_head unused_bgs;
......@@ -935,6 +945,9 @@ struct btrfs_fs_info {
*/
int send_in_progress;
/* Type of exclusive operation running */
unsigned long exclusive_operation;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
struct rb_root block_tree;
......@@ -1181,24 +1194,40 @@ struct btrfs_root {
#endif
};
struct btrfs_clone_extent_info {
/*
* Structure that conveys information about an extent that is going to replace
* all the extents in a file range.
*/
struct btrfs_replace_extent_info {
u64 disk_offset;
u64 disk_len;
u64 data_offset;
u64 data_len;
u64 file_offset;
/* Pointer to a file extent item of type regular or prealloc. */
char *extent_buf;
u32 item_size;
/*
* Set to true when attempting to replace a file range with a new extent
* described by this structure, set to false when attempting to clone an
* existing extent into a file range.
*/
bool is_new_extent;
/* Meaningful only if is_new_extent is true. */
int qgroup_reserved;
/*
* Meaningful only if is_new_extent is true.
* Used to track how many extent items we have already inserted in a
* subvolume tree that refer to the extent described by this structure,
* so that we know when to create a new delayed ref or update an existing
* one.
*/
int insertions;
};
struct btrfs_file_private {
void *filldir_buf;
};
static inline u32 btrfs_inode_sectorsize(const struct inode *inode)
{
return btrfs_sb(inode->i_sb)->sectorsize;
}
static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
{
......@@ -1391,6 +1420,16 @@ static inline void btrfs_init_map_token(struct btrfs_map_token *token,
#define cpu_to_le8(v) (v)
#define __le8 u8
static inline u8 get_unaligned_le8(const void *p)
{
return *(u8 *)p;
}
static inline void put_unaligned_le8(u8 val, void *p)
{
*(u8 *)p = val;
}
#define read_eb_member(eb, ptr, type, member, result) (\
read_extent_buffer(eb, (char *)(result), \
((unsigned long)(ptr)) + \
......@@ -1449,27 +1488,25 @@ static inline void btrfs_set_token_##name(struct btrfs_map_token *token,\
static inline u##bits btrfs_##name(const struct extent_buffer *eb) \
{ \
const type *p = page_address(eb->pages[0]); \
u##bits res = le##bits##_to_cpu(p->member); \
return res; \
return get_unaligned_le##bits(&p->member); \
} \
static inline void btrfs_set_##name(const struct extent_buffer *eb, \
u##bits val) \
{ \
type *p = page_address(eb->pages[0]); \
p->member = cpu_to_le##bits(val); \
put_unaligned_le##bits(val, &p->member); \
}
#define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(const type *s) \
{ \
return le##bits##_to_cpu(s->member); \
return get_unaligned_le##bits(&s->member); \
} \
static inline void btrfs_set_##name(type *s, u##bits val) \
{ \
s->member = cpu_to_le##bits(val); \
put_unaligned_le##bits(val, &s->member); \
}
static inline u64 btrfs_device_total_bytes(const struct extent_buffer *eb,
struct btrfs_dev_item *s)
{
......@@ -2524,7 +2561,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
u64 parent, u64 root_objectid,
const struct btrfs_disk_key *key,
int level, u64 hint,
u64 empty_size);
u64 empty_size,
enum btrfs_lock_nesting nest);
void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
......@@ -2592,6 +2630,8 @@ enum btrfs_reserve_flush_enum {
*
* Can be interruped by fatal signal.
*/
BTRFS_RESERVE_FLUSH_DATA,
BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE,
BTRFS_RESERVE_FLUSH_ALL,
/*
......@@ -2619,7 +2659,7 @@ enum btrfs_flush_state {
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
void btrfs_subvolume_release_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv);
void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
......@@ -2651,8 +2691,6 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
struct btrfs_path *path,
const struct btrfs_key *new_key);
struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *key, int lowest_level,
u64 min_trans);
......@@ -2665,7 +2703,8 @@ struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent,
int btrfs_cow_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *buf,
struct extent_buffer *parent, int parent_slot,
struct extent_buffer **cow_ret);
struct extent_buffer **cow_ret,
enum btrfs_lock_nesting nest);
int btrfs_copy_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
......@@ -2713,7 +2752,7 @@ static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
const struct btrfs_key *cpu_key, u32 *data_size,
u32 total_data, u32 total_size, int nr);
int nr);
int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
const struct btrfs_key *key, void *data, u32 data_size);
int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
......@@ -2930,6 +2969,10 @@ void btrfs_inode_safe_disk_i_size_write(struct inode *inode, u64 new_i_size);
u64 btrfs_file_extent_end(const struct btrfs_path *path);
/* inode.c */
blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u64 phy_offset,
struct page *page, u64 start, u64 end, int mirror);
struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
u64 start, u64 len);
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
......@@ -2956,7 +2999,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
u32 min_type);
int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr);
int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
unsigned int extra_bits,
struct extent_state **cached_state);
......@@ -3017,6 +3060,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
u64 end, int uptodate);
extern const struct dentry_operations btrfs_dentry_operations;
ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
......@@ -3031,6 +3075,9 @@ void btrfs_get_block_group_info(struct list_head *groups_list,
struct btrfs_ioctl_space_info *space);
void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_balance_args *bargs);
bool btrfs_exclop_start(struct btrfs_fs_info *fs_info,
enum btrfs_exclusive_operation type);
void btrfs_exclop_finish(struct btrfs_fs_info *fs_info);
/* file.c */
int __init btrfs_auto_defrag_init(void);
......@@ -3053,9 +3100,9 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode, u64 start,
u64 end, int drop_cache);
int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path,
int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
const u64 start, const u64 end,
struct btrfs_clone_extent_info *clone_info,
struct btrfs_replace_extent_info *extent_info,
struct btrfs_trans_handle **trans_out);
int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode, u64 start, u64 end);
......@@ -3536,9 +3583,7 @@ static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_inode_set_ops(struct inode *inode);
void btrfs_test_destroy_inode(struct inode *inode);
static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
{
return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
......
fs/btrfs/delalloc-space.c
浏览文件 @ 11e3235b
......@@ -115,126 +115,15 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
{
struct btrfs_root *root = inode->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_space_info *data_sinfo = fs_info->data_sinfo;
u64 used;
int ret = 0;
int need_commit = 2;
int have_pinned_space;
enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_DATA;
/* Make sure bytes are sectorsize aligned */
bytes = ALIGN(bytes, fs_info->sectorsize);
if (btrfs_is_free_space_inode(inode)) {
need_commit = 0;
ASSERT(current->journal_info);
}
again:
/* Make sure we have enough space to handle the data first */
spin_lock(&data_sinfo->lock);
used = btrfs_space_info_used(data_sinfo, true);
if (used + bytes > data_sinfo->total_bytes) {
struct btrfs_trans_handle *trans;
/*
* If we don't have enough free bytes in this space then we need
* to alloc a new chunk.
*/
if (!data_sinfo->full) {
u64 alloc_target;
data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
spin_unlock(&data_sinfo->lock);
alloc_target = btrfs_data_alloc_profile(fs_info);
/*
* It is ugly that we don't call nolock join
* transaction for the free space inode case here.
* But it is safe because we only do the data space
* reservation for the free space cache in the
* transaction context, the common join transaction
* just increase the counter of the current transaction
* handler, doesn't try to acquire the trans_lock of
* the fs.
*/
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
return PTR_ERR(trans);
ret = btrfs_chunk_alloc(trans, alloc_target,
CHUNK_ALLOC_NO_FORCE);
btrfs_end_transaction(trans);
if (ret < 0) {
if (ret != -ENOSPC)
return ret;
else {
have_pinned_space = 1;
goto commit_trans;
}
}
goto again;
}
/*
* If we don't have enough pinned space to deal with this
* allocation, and no removed chunk in current transaction,
* don't bother committing the transaction.
*/
have_pinned_space = __percpu_counter_compare(
&data_sinfo->total_bytes_pinned,
used + bytes - data_sinfo->total_bytes,
BTRFS_TOTAL_BYTES_PINNED_BATCH);
spin_unlock(&data_sinfo->lock);
/* Commit the current transaction and try again */
commit_trans:
if (need_commit) {
need_commit--;
if (need_commit > 0) {
btrfs_start_delalloc_roots(fs_info, -1);
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0,
(u64)-1);
}
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
return PTR_ERR(trans);
if (have_pinned_space >= 0 ||
test_bit(BTRFS_TRANS_HAVE_FREE_BGS,
&trans->transaction->flags) ||
need_commit > 0) {
ret = btrfs_commit_transaction(trans);
if (ret)
return ret;
/*
* The cleaner kthread might still be doing iput
* operations. Wait for it to finish so that
* more space is released. We don't need to
* explicitly run the delayed iputs here because
* the commit_transaction would have woken up
* the cleaner.
*/
ret = btrfs_wait_on_delayed_iputs(fs_info);
if (ret)
return ret;
goto again;
} else {
btrfs_end_transaction(trans);
}
}
trace_btrfs_space_reservation(fs_info,
"space_info:enospc",
data_sinfo->flags, bytes, 1);
return -ENOSPC;
}
btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, bytes);
spin_unlock(&data_sinfo->lock);
if (btrfs_is_free_space_inode(inode))
flush = BTRFS_RESERVE_FLUSH_FREE_SPACE_INODE;
return 0;
return btrfs_reserve_data_bytes(fs_info, bytes, flush);
}
int btrfs_check_data_free_space(struct btrfs_inode *inode,
......@@ -277,9 +166,7 @@ void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info,
ASSERT(IS_ALIGNED(len, fs_info->sectorsize));
data_sinfo = fs_info->data_sinfo;
spin_lock(&data_sinfo->lock);
btrfs_space_info_update_bytes_may_use(fs_info, data_sinfo, -len);
spin_unlock(&data_sinfo->lock);
btrfs_space_info_free_bytes_may_use(fs_info, data_sinfo, len);
}
/*
......
fs/btrfs/delayed-inode.c
浏览文件 @ 11e3235b
......@@ -627,8 +627,7 @@ static int btrfs_delayed_inode_reserve_metadata(
*/
if (!src_rsv || (!trans->bytes_reserved &&
src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
ret = btrfs_qgroup_reserve_meta_prealloc(root,
fs_info->nodesize, true);
ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
if (ret < 0)
return ret;
ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
......@@ -769,8 +768,7 @@ static int btrfs_batch_insert_items(struct btrfs_root *root,
}
/* insert the keys of the items */
setup_items_for_insert(root, path, keys, data_size,
total_data_size, total_size, nitems);
setup_items_for_insert(root, path, keys, data_size, nitems);
/* insert the dir index items */
slot = path->slots[0];
......
fs/btrfs/dev-replace.c
浏览文件 @ 11e3235b
......@@ -64,10 +64,6 @@
static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
int scrub_ret);
static void btrfs_dev_replace_update_device_in_mapping_tree(
struct btrfs_fs_info *fs_info,
struct btrfs_device *srcdev,
struct btrfs_device *tgtdev);
static int btrfs_dev_replace_kthread(void *data);
int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
......@@ -224,13 +220,12 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
{
struct btrfs_device *device;
struct block_device *bdev;
struct list_head *devices;
struct rcu_string *name;
u64 devid = BTRFS_DEV_REPLACE_DEVID;
int ret = 0;
*device_out = NULL;
if (fs_info->fs_devices->seeding) {
if (srcdev->fs_devices->seeding) {
btrfs_err(fs_info, "the filesystem is a seed filesystem!");
return -EINVAL;
}
......@@ -244,8 +239,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
sync_blockdev(bdev);
devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
if (device->bdev == bdev) {
btrfs_err(fs_info,
"target device is in the filesystem!");
......@@ -512,7 +506,7 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
up_write(&dev_replace->rwsem);
ret = btrfs_sysfs_add_devices_dir(tgt_device->fs_devices, tgt_device);
ret = btrfs_sysfs_add_device(tgt_device);
if (ret)
btrfs_err(fs_info, "kobj add dev failed %d", ret);
......@@ -630,6 +624,32 @@ static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev,
return ret;
}
static void btrfs_dev_replace_update_device_in_mapping_tree(
struct btrfs_fs_info *fs_info,
struct btrfs_device *srcdev,
struct btrfs_device *tgtdev)
{
struct extent_map_tree *em_tree = &fs_info->mapping_tree;
struct extent_map *em;
struct map_lookup *map;
u64 start = 0;
int i;
write_lock(&em_tree->lock);
do {
em = lookup_extent_mapping(em_tree, start, (u64)-1);
if (!em)
break;
map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++)
if (srcdev == map->stripes[i].dev)
map->stripes[i].dev = tgtdev;
start = em->start + em->len;
free_extent_map(em);
} while (start);
write_unlock(&em_tree->lock);
}
static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
int scrub_ret)
{
......@@ -661,7 +681,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
* flush all outstanding I/O and inode extent mappings before the
* copy operation is declared as being finished
*/
ret = btrfs_start_delalloc_roots(fs_info, -1);
ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
if (ret) {
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return ret;
......@@ -781,7 +801,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
/* replace the sysfs entry */
btrfs_sysfs_remove_devices_dir(fs_info->fs_devices, src_device);
btrfs_sysfs_remove_device(src_device);
btrfs_sysfs_update_devid(tgt_device);
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state))
btrfs_scratch_superblocks(fs_info, src_device->bdev,
......@@ -799,32 +819,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
return 0;
}
static void btrfs_dev_replace_update_device_in_mapping_tree(
struct btrfs_fs_info *fs_info,
struct btrfs_device *srcdev,
struct btrfs_device *tgtdev)
{
struct extent_map_tree *em_tree = &fs_info->mapping_tree;
struct extent_map *em;
struct map_lookup *map;
u64 start = 0;
int i;
write_lock(&em_tree->lock);
do {
em = lookup_extent_mapping(em_tree, start, (u64)-1);
if (!em)
break;
map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++)
if (srcdev == map->stripes[i].dev)
map->stripes[i].dev = tgtdev;
start = em->start + em->len;
free_extent_map(em);
} while (start);
write_unlock(&em_tree->lock);
}
/*
* Read progress of device replace status according to the state and last
* stored position. The value format is the same as for
......@@ -1025,7 +1019,7 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
* should never allow both to start and pause. We don't want to allow
* dev-replace to start anyway.
*/
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_REPLACE)) {
down_write(&dev_replace->rwsem);
dev_replace->replace_state =
BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
......@@ -1062,7 +1056,7 @@ static int btrfs_dev_replace_kthread(void *data)
ret = btrfs_dev_replace_finishing(fs_info, ret);
WARN_ON(ret && ret != -ECANCELED);
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
btrfs_exclop_finish(fs_info);
return 0;
}
......
fs/btrfs/disk-io.c
浏览文件 @ 11e3235b
......@@ -50,7 +50,6 @@
BTRFS_SUPER_FLAG_METADUMP |\
BTRFS_SUPER_FLAG_METADUMP_V2)
static const struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
......@@ -204,53 +203,6 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
#endif
/*
* extents on the btree inode are pretty simple, there's one extent
* that covers the entire device
*/
struct extent_map *btree_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 len)
{
struct extent_map_tree *em_tree = &inode->extent_tree;
struct extent_map *em;
int ret;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
if (em) {
read_unlock(&em_tree->lock);
goto out;
}
read_unlock(&em_tree->lock);
em = alloc_extent_map();
if (!em) {
em = ERR_PTR(-ENOMEM);
goto out;
}
em->start = 0;
em->len = (u64)-1;
em->block_len = (u64)-1;
em->block_start = 0;
write_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em, 0);
if (ret == -EEXIST) {
free_extent_map(em);
em = lookup_extent_mapping(em_tree, start, len);
if (!em)
em = ERR_PTR(-EIO);
} else if (ret) {
free_extent_map(em);
em = ERR_PTR(ret);
}
write_unlock(&em_tree->lock);
out:
return em;
}
/*
* Compute the csum of a btree block and store the result to provided buffer.
*/
......@@ -545,38 +497,35 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
static int check_tree_block_fsid(struct extent_buffer *eb)
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs;
u8 fsid[BTRFS_FSID_SIZE];
int ret = 1;
u8 *metadata_uuid;
read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid),
BTRFS_FSID_SIZE);
while (fs_devices) {
u8 *metadata_uuid;
/*
* Checking the incompat flag is only valid for the current fs. For
* seed devices it's forbidden to have their uuid changed so reading
* ->fsid in this case is fine
*/
if (btrfs_fs_incompat(fs_info, METADATA_UUID))
metadata_uuid = fs_devices->metadata_uuid;
else
metadata_uuid = fs_devices->fsid;
/*
* Checking the incompat flag is only valid for the current
* fs. For seed devices it's forbidden to have their uuid
* changed so reading ->fsid in this case is fine
*/
if (fs_devices == fs_info->fs_devices &&
btrfs_fs_incompat(fs_info, METADATA_UUID))
metadata_uuid = fs_devices->metadata_uuid;
else
metadata_uuid = fs_devices->fsid;
if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE))
return 0;
if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) {
ret = 0;
break;
}
fs_devices = fs_devices->seed;
}
return ret;
list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list)
if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE))
return 0;
return 1;
}
static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset,
struct page *page, u64 start, u64 end,
int mirror)
{
u64 found_start;
int found_level;
......@@ -864,9 +813,8 @@ static int check_async_write(struct btrfs_fs_info *fs_info,
return 1;
}
static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio,
int mirror_num,
unsigned long bio_flags)
blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
int async = check_async_write(fs_info, BTRFS_I(inode));
......@@ -951,11 +899,6 @@ static int btree_writepages(struct address_space *mapping,
return btree_write_cache_pages(mapping, wbc);
}
static int btree_readpage(struct file *file, struct page *page)
{
return extent_read_full_page(page, btree_get_extent, 0);
}
static int btree_releasepage(struct page *page, gfp_t gfp_flags)
{
if (PageWriteback(page) || PageDirty(page))
......@@ -995,7 +938,6 @@ static int btree_set_page_dirty(struct page *page)
}
static const struct address_space_operations btree_aops = {
.readpage = btree_readpage,
.writepages = btree_writepages,
.releasepage = btree_releasepage,
.invalidatepage = btree_invalidatepage,
......@@ -1208,7 +1150,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
root->root_key.type = BTRFS_ROOT_ITEM_KEY;
root->root_key.offset = 0;
leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
BTRFS_NESTING_NORMAL);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
leaf = NULL;
......@@ -1280,7 +1223,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
*/
leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
NULL, 0, 0, 0);
NULL, 0, 0, 0, BTRFS_NESTING_NORMAL);
if (IS_ERR(leaf)) {
btrfs_put_root(root);
return ERR_CAST(leaf);
......@@ -1505,10 +1448,12 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
struct btrfs_root *root;
while (!list_empty(&fs_info->allocated_roots)) {
char buf[BTRFS_ROOT_NAME_BUF_LEN];
root = list_first_entry(&fs_info->allocated_roots,
struct btrfs_root, leak_list);
btrfs_err(fs_info, "leaked root %llu-%llu refcount %d",
root->root_key.objectid, root->root_key.offset,
btrfs_err(fs_info, "leaked root %s refcount %d",
btrfs_root_name(root->root_key.objectid, buf),
refcount_read(&root->refs));
while (refcount_read(&root->refs) > 1)
btrfs_put_root(root);
......@@ -2115,12 +2060,10 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree,
IO_TREE_INODE_IO, inode);
IO_TREE_BTREE_INODE_IO, inode);
BTRFS_I(inode)->io_tree.track_uptodate = false;
extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops;
BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root);
memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key));
set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
......@@ -2626,18 +2569,17 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
level = btrfs_super_root_level(sb);
tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb),
generation, level, NULL);
if (IS_ERR(tree_root->node) ||
!extent_buffer_uptodate(tree_root->node)) {
if (IS_ERR(tree_root->node)) {
handle_error = true;
ret = PTR_ERR(tree_root->node);
tree_root->node = NULL;
btrfs_warn(fs_info, "couldn't read tree root");
continue;
if (IS_ERR(tree_root->node)) {
ret = PTR_ERR(tree_root->node);
tree_root->node = NULL;
} else if (!extent_buffer_uptodate(tree_root->node)) {
ret = -EUCLEAN;
}
btrfs_warn(fs_info, "failed to read tree root");
} else if (!extent_buffer_uptodate(tree_root->node)) {
handle_error = true;
ret = -EIO;
btrfs_warn(fs_info, "error while reading tree root");
continue;
}
......@@ -2753,7 +2695,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
fs_info->check_integrity_print_mask = 0;
#endif
btrfs_init_balance(fs_info);
btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
btrfs_init_async_reclaim_work(fs_info);
spin_lock_init(&fs_info->block_group_cache_lock);
fs_info->block_group_cache_tree = RB_ROOT;
......@@ -2928,7 +2870,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
}
/*
* Verify the type first, if that or the the checksum value are
* Verify the type first, if that or the checksum value are
* corrupted, we'll find out
*/
csum_type = btrfs_super_csum_type(disk_super);
......@@ -3482,8 +3424,12 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
return ERR_CAST(page);
super = page_address(page);
if (btrfs_super_bytenr(super) != bytenr ||
btrfs_super_magic(super) != BTRFS_MAGIC) {
if (btrfs_super_magic(super) != BTRFS_MAGIC) {
btrfs_release_disk_super(super);
return ERR_PTR(-ENODATA);
}
if (btrfs_super_bytenr(super) != bytenr) {
btrfs_release_disk_super(super);
return ERR_PTR(-EINVAL);
}
......@@ -4056,6 +4002,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
btrfs_cleanup_defrag_inodes(fs_info);
cancel_work_sync(&fs_info->async_reclaim_work);
cancel_work_sync(&fs_info->async_data_reclaim_work);
/* Cancel or finish ongoing discard work */
btrfs_discard_cleanup(fs_info);
......@@ -4687,9 +4634,3 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
return 0;
}
static const struct extent_io_ops btree_extent_io_ops = {
/* mandatory callbacks */
.submit_bio_hook = btree_submit_bio_hook,
.readpage_end_io_hook = btree_readpage_end_io_hook,
};
fs/btrfs/disk-io.h
浏览文件 @ 11e3235b
......@@ -76,7 +76,11 @@ void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info);
void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info);
void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset,
struct page *page, u64 start, u64 end,
int mirror);
blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info);
#endif
......@@ -123,9 +127,6 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
u64 objectid);
int btree_lock_page_hook(struct page *page, void *data,
void (*flush_fn)(void *));
struct extent_map *btree_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 len);
int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
int __init btrfs_end_io_wq_init(void);
void __cold btrfs_end_io_wq_exit(void);
......
fs/btrfs/extent-io-tree.h
浏览文件 @ 11e3235b
......@@ -40,6 +40,7 @@ struct io_failure_record;
enum {
IO_TREE_FS_PINNED_EXTENTS,
IO_TREE_FS_EXCLUDED_EXTENTS,
IO_TREE_BTREE_INODE_IO,
IO_TREE_INODE_IO,
IO_TREE_INODE_IO_FAILURE,
IO_TREE_RELOC_BLOCKS,
......@@ -48,6 +49,7 @@ enum {
IO_TREE_INODE_FILE_EXTENT,
IO_TREE_LOG_CSUM_RANGE,
IO_TREE_SELFTEST,
IO_TREE_DEVICE_ALLOC_STATE,
};
struct extent_io_tree {
......@@ -61,7 +63,6 @@ struct extent_io_tree {
u8 owner;
spinlock_t lock;
const struct extent_io_ops *ops;
};
struct extent_state {
......
fs/btrfs/extent-tree.c
浏览文件 @ 11e3235b
......@@ -1177,7 +1177,22 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
num_bytes, parent, root_objectid,
owner, offset, 1);
if (ret == 0) {
BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
/*
* We're adding refs to a tree block we already own, this
* should not happen at all.
*/
if (owner < BTRFS_FIRST_FREE_OBJECTID) {
btrfs_crit(trans->fs_info,
"adding refs to an existing tree ref, bytenr %llu num_bytes %llu root_objectid %llu",
bytenr, num_bytes, root_objectid);
if (IS_ENABLED(CONFIG_BTRFS_DEBUG)) {
WARN_ON(1);
btrfs_crit(trans->fs_info,
"path->slots[0]=%d path->nodes[0]:", path->slots[0]);
btrfs_print_leaf(path->nodes[0]);
}
return -EUCLEAN;
}
update_inline_extent_backref(path, iref, refs_to_add,
extent_op, NULL);
} else if (ret == -ENOENT) {
......@@ -1397,6 +1412,9 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
/*
* __btrfs_inc_extent_ref - insert backreference for a given extent
*
* The counterpart is in __btrfs_free_extent(), with examples and more details
* how it works.
*
* @trans: Handle of transaction
*
* @node: The delayed ref node used to get the bytenr/length for
......@@ -2849,11 +2867,10 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
len -= to_add;
}
spin_unlock(&global_rsv->lock);
/* Add to any tickets we may have */
if (len)
btrfs_try_granting_tickets(fs_info,
space_info);
}
/* Add to any tickets we may have */
if (!readonly && return_free_space && len)
btrfs_try_granting_tickets(fs_info, space_info);
spin_unlock(&space_info->lock);
}
......@@ -2935,6 +2952,65 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
return 0;
}
/*
* Drop one or more refs of @node.
*
* 1. Locate the extent refs.
* It's either inline in EXTENT/METADATA_ITEM or in keyed SHARED_* item.
* Locate it, then reduce the refs number or remove the ref line completely.
*
* 2. Update the refs count in EXTENT/METADATA_ITEM
*
* Inline backref case:
*
* in extent tree we have:
*
* item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 16201 itemsize 82
* refs 2 gen 6 flags DATA
* extent data backref root FS_TREE objectid 258 offset 0 count 1
* extent data backref root FS_TREE objectid 257 offset 0 count 1
*
* This function gets called with:
*
* node->bytenr = 13631488
* node->num_bytes = 1048576
* root_objectid = FS_TREE
* owner_objectid = 257
* owner_offset = 0
* refs_to_drop = 1
*
* Then we should get some like:
*
* item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 16201 itemsize 82
* refs 1 gen 6 flags DATA
* extent data backref root FS_TREE objectid 258 offset 0 count 1
*
* Keyed backref case:
*
* in extent tree we have:
*
* item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 3971 itemsize 24
* refs 754 gen 6 flags DATA
* [...]
* item 2 key (13631488 EXTENT_DATA_REF <HASH>) itemoff 3915 itemsize 28
* extent data backref root FS_TREE objectid 866 offset 0 count 1
*
* This function get called with:
*
* node->bytenr = 13631488
* node->num_bytes = 1048576
* root_objectid = FS_TREE
* owner_objectid = 866
* owner_offset = 0
* refs_to_drop = 1
*
* Then we should get some like:
*
* item 0 key (13631488 EXTENT_ITEM 1048576) itemoff 3971 itemsize 24
* refs 753 gen 6 flags DATA
*
* And that (13631488 EXTENT_DATA_REF <HASH>) gets removed.
*/
static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_node *node, u64 parent,
u64 root_objectid, u64 owner_objectid,
......@@ -2967,7 +3043,15 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
path->leave_spinning = 1;
is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID;
BUG_ON(!is_data && refs_to_drop != 1);
if (!is_data && refs_to_drop != 1) {
btrfs_crit(info,
"invalid refs_to_drop, dropping more than 1 refs for tree block %llu refs_to_drop %u",
node->bytenr, refs_to_drop);
ret = -EINVAL;
btrfs_abort_transaction(trans, ret);
goto out;
}
if (is_data)
skinny_metadata = false;
......@@ -2976,6 +3060,13 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
parent, root_objectid, owner_objectid,
owner_offset);
if (ret == 0) {
/*
* Either the inline backref or the SHARED_DATA_REF/
* SHARED_BLOCK_REF is found
*
* Here is a quick path to locate EXTENT/METADATA_ITEM.
* It's possible the EXTENT/METADATA_ITEM is near current slot.
*/
extent_slot = path->slots[0];
while (extent_slot >= 0) {
btrfs_item_key_to_cpu(path->nodes[0], &key,
......@@ -2992,13 +3083,21 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
found_extent = 1;
break;
}
/* Quick path didn't find the EXTEMT/METADATA_ITEM */
if (path->slots[0] - extent_slot > 5)
break;
extent_slot--;
}
if (!found_extent) {
BUG_ON(iref);
if (iref) {
btrfs_crit(info,
"invalid iref, no EXTENT/METADATA_ITEM found but has inline extent ref");
btrfs_abort_transaction(trans, -EUCLEAN);
goto err_dump;
}
/* Must be SHARED_* item, remove the backref first */
ret = remove_extent_backref(trans, path, NULL,
refs_to_drop,
is_data, &last_ref);
......@@ -3009,6 +3108,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
path->leave_spinning = 1;
/* Slow path to locate EXTENT/METADATA_ITEM */
key.objectid = bytenr;
key.type = BTRFS_EXTENT_ITEM_KEY;
key.offset = num_bytes;
......@@ -3083,19 +3183,26 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID &&
key.type == BTRFS_EXTENT_ITEM_KEY) {
struct btrfs_tree_block_info *bi;
BUG_ON(item_size < sizeof(*ei) + sizeof(*bi));
if (item_size < sizeof(*ei) + sizeof(*bi)) {
btrfs_crit(info,
"invalid extent item size for key (%llu, %u, %llu) owner %llu, has %u expect >= %lu",
key.objectid, key.type, key.offset,
owner_objectid, item_size,
sizeof(*ei) + sizeof(*bi));
btrfs_abort_transaction(trans, -EUCLEAN);
goto err_dump;
}
bi = (struct btrfs_tree_block_info *)(ei + 1);
WARN_ON(owner_objectid != btrfs_tree_block_level(leaf, bi));
}
refs = btrfs_extent_refs(leaf, ei);
if (refs < refs_to_drop) {
btrfs_err(info,
"trying to drop %d refs but we only have %Lu for bytenr %Lu",
btrfs_crit(info,
"trying to drop %d refs but we only have %llu for bytenr %llu",
refs_to_drop, refs, bytenr);
ret = -EINVAL;
btrfs_abort_transaction(trans, ret);
goto out;
btrfs_abort_transaction(trans, -EUCLEAN);
goto err_dump;
}
refs -= refs_to_drop;
......@@ -3107,7 +3214,12 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
* be updated by remove_extent_backref
*/
if (iref) {
BUG_ON(!found_extent);
if (!found_extent) {
btrfs_crit(info,
"invalid iref, got inlined extent ref but no EXTENT/METADATA_ITEM found");
btrfs_abort_transaction(trans, -EUCLEAN);
goto err_dump;
}
} else {
btrfs_set_extent_refs(leaf, ei, refs);
btrfs_mark_buffer_dirty(leaf);
......@@ -3122,13 +3234,39 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
}
}
} else {
/* In this branch refs == 1 */
if (found_extent) {
BUG_ON(is_data && refs_to_drop !=
extent_data_ref_count(path, iref));
if (is_data && refs_to_drop !=
extent_data_ref_count(path, iref)) {
btrfs_crit(info,
"invalid refs_to_drop, current refs %u refs_to_drop %u",
extent_data_ref_count(path, iref),
refs_to_drop);
btrfs_abort_transaction(trans, -EUCLEAN);
goto err_dump;
}
if (iref) {
BUG_ON(path->slots[0] != extent_slot);
if (path->slots[0] != extent_slot) {
btrfs_crit(info,
"invalid iref, extent item key (%llu %u %llu) doesn't have wanted iref",
key.objectid, key.type,
key.offset);
btrfs_abort_transaction(trans, -EUCLEAN);
goto err_dump;
}
} else {
BUG_ON(path->slots[0] != extent_slot + 1);
/*
* No inline ref, we must be at SHARED_* item,
* And it's single ref, it must be:
* | extent_slot ||extent_slot + 1|
* [ EXTENT/METADATA_ITEM ][ SHARED_* ITEM ]
*/
if (path->slots[0] != extent_slot + 1) {
btrfs_crit(info,
"invalid SHARED_* item, previous item is not EXTENT/METADATA_ITEM");
btrfs_abort_transaction(trans, -EUCLEAN);
goto err_dump;
}
path->slots[0] = extent_slot;
num_to_del = 2;
}
......@@ -3169,6 +3307,19 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
out:
btrfs_free_path(path);
return ret;
err_dump:
/*
* Leaf dump can take up a lot of log buffer, so we only do full leaf
* dump for debug build.
*/
if (IS_ENABLED(CONFIG_BTRFS_DEBUG)) {
btrfs_crit(info, "path->slots[0]=%d extent_slot=%d",
path->slots[0], extent_slot);
btrfs_print_leaf(path->nodes[0]);
}
btrfs_free_path(path);
return -EUCLEAN;
}
/*
......@@ -3918,11 +4069,12 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
* |- Push harder to find free extents
* |- If not found, re-iterate all block groups
*/
static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
static noinline int find_free_extent(struct btrfs_root *root,
u64 ram_bytes, u64 num_bytes, u64 empty_size,
u64 hint_byte_orig, struct btrfs_key *ins,
u64 flags, int delalloc)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret = 0;
int cache_block_group_error = 0;
struct btrfs_block_group *block_group = NULL;
......@@ -3954,7 +4106,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
ins->objectid = 0;
ins->offset = 0;
trace_find_free_extent(fs_info, num_bytes, empty_size, flags);
trace_find_free_extent(root, num_bytes, empty_size, flags);
space_info = btrfs_find_space_info(fs_info, flags);
if (!space_info) {
......@@ -4203,7 +4355,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
flags = get_alloc_profile_by_root(root, is_data);
again:
WARN_ON(num_bytes < fs_info->sectorsize);
ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size,
ret = find_free_extent(root, ram_bytes, num_bytes, empty_size,
hint_byte, ins, flags, delalloc);
if (!ret && !is_data) {
btrfs_dec_block_group_reservations(fs_info, ins->objectid);
......@@ -4504,7 +4656,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
static struct extent_buffer *
btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
u64 bytenr, int level, u64 owner)
u64 bytenr, int level, u64 owner,
enum btrfs_lock_nesting nest)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_buffer *buf;
......@@ -4527,7 +4680,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
}
btrfs_set_buffer_lockdep_class(owner, buf, level);
btrfs_tree_lock(buf);
__btrfs_tree_lock(buf, nest);
btrfs_clean_tree_block(buf);
clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
......@@ -4573,7 +4726,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
u64 parent, u64 root_objectid,
const struct btrfs_disk_key *key,
int level, u64 hint,
u64 empty_size)
u64 empty_size,
enum btrfs_lock_nesting nest)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_key ins;
......@@ -4589,7 +4743,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
if (btrfs_is_testing(fs_info)) {
buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
level, root_objectid);
level, root_objectid, nest);
if (!IS_ERR(buf))
root->alloc_bytenr += blocksize;
return buf;
......@@ -4606,7 +4760,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
goto out_unuse;
buf = btrfs_init_new_buffer(trans, root, ins.objectid, level,
root_objectid);
root_objectid, nest);
if (IS_ERR(buf)) {
ret = PTR_ERR(buf);
goto out_free_reserved;
......
fs/btrfs/extent_io.c
浏览文件 @ 11e3235b
......@@ -160,19 +160,20 @@ static int add_extent_changeset(struct extent_state *state, unsigned bits,
return ret;
}
static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
unsigned long bio_flags)
int __must_check submit_one_bio(struct bio *bio, int mirror_num,
unsigned long bio_flags)
{
blk_status_t ret = 0;
struct extent_io_tree *tree = bio->bi_private;
bio->bi_private = NULL;
if (tree->ops)
ret = tree->ops->submit_bio_hook(tree->private_data, bio,
mirror_num, bio_flags);
if (is_data_inode(tree->private_data))
ret = btrfs_submit_data_bio(tree->private_data, bio, mirror_num,
bio_flags);
else
btrfsic_submit_bio(bio);
ret = btrfs_submit_metadata_bio(tree->private_data, bio,
mirror_num, bio_flags);
return blk_status_to_errno(ret);
}
......@@ -280,7 +281,6 @@ void extent_io_tree_init(struct btrfs_fs_info *fs_info,
{
tree->fs_info = fs_info;
tree->state = RB_ROOT;
tree->ops = NULL;
tree->dirty_bytes = 0;
spin_lock_init(&tree->lock);
tree->private_data = private_data;
......@@ -2819,8 +2819,6 @@ static void end_bio_extent_readpage(struct bio *bio)
struct page *page = bvec->bv_page;
struct inode *inode = page->mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
bool data_inode = btrfs_ino(BTRFS_I(inode))
!= BTRFS_BTREE_INODE_OBJECTID;
btrfs_debug(fs_info,
"end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u",
......@@ -2851,9 +2849,12 @@ static void end_bio_extent_readpage(struct bio *bio)
mirror = io_bio->mirror_num;
if (likely(uptodate)) {
ret = tree->ops->readpage_end_io_hook(io_bio, offset,
page, start, end,
mirror);
if (is_data_inode(inode))
ret = btrfs_verify_data_csum(io_bio, offset, page,
start, end, mirror);
else
ret = btrfs_validate_metadata_buffer(io_bio,
offset, page, start, end, mirror);
if (ret)
uptodate = 0;
else
......@@ -2866,7 +2867,7 @@ static void end_bio_extent_readpage(struct bio *bio)
if (likely(uptodate))
goto readpage_ok;
if (data_inode) {
if (is_data_inode(inode)) {
/*
* The generic bio_readpage_error handles errors the
......@@ -2881,7 +2882,7 @@ static void end_bio_extent_readpage(struct bio *bio)
if (!btrfs_submit_read_repair(inode, bio, offset, page,
start - page_offset(page),
start, end, mirror,
tree->ops->submit_bio_hook)) {
btrfs_submit_data_bio)) {
uptodate = !bio->bi_status;
offset += len;
continue;
......@@ -3053,7 +3054,6 @@ static int submit_extent_page(unsigned int opf,
else
contig = bio_end_sector(bio) == sector;
ASSERT(tree->ops);
if (btrfs_bio_fits_in_stripe(page, page_size, bio, bio_flags))
can_merge = false;
......@@ -3110,8 +3110,7 @@ void set_page_extent_mapped(struct page *page)
static struct extent_map *
__get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
u64 start, u64 len, get_extent_t *get_extent,
struct extent_map **em_cached)
u64 start, u64 len, struct extent_map **em_cached)
{
struct extent_map *em;
......@@ -3127,7 +3126,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
*em_cached = NULL;
}
em = get_extent(BTRFS_I(inode), page, pg_offset, start, len);
em = btrfs_get_extent(BTRFS_I(inode), page, pg_offset, start, len);
if (em_cached && !IS_ERR_OR_NULL(em)) {
BUG_ON(*em_cached);
refcount_inc(&em->refs);
......@@ -3142,12 +3141,9 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
* XXX JDM: This needs looking at to ensure proper page locking
* return 0 on success, otherwise return error
*/
static int __do_readpage(struct page *page,
get_extent_t *get_extent,
struct extent_map **em_cached,
struct bio **bio, int mirror_num,
unsigned long *bio_flags, unsigned int read_flags,
u64 *prev_em_start)
int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
struct bio **bio, unsigned long *bio_flags,
unsigned int read_flags, u64 *prev_em_start)
{
struct inode *inode = page->mapping->host;
u64 start = page_offset(page);
......@@ -3209,7 +3205,7 @@ static int __do_readpage(struct page *page,
break;
}
em = __get_extent_map(inode, page, pg_offset, cur,
end - cur + 1, get_extent, em_cached);
end - cur + 1, em_cached);
if (IS_ERR_OR_NULL(em)) {
SetPageError(page);
unlock_extent(tree, cur, end);
......@@ -3241,7 +3237,7 @@ static int __do_readpage(struct page *page,
/*
* If we have a file range that points to a compressed extent
* and it's followed by a consecutive file range that points to
* and it's followed by a consecutive file range that points
* to the same compressed extent (possibly with a different
* offset and/or length, so it either points to the whole extent
* or only part of it), we must make sure we do not submit a
......@@ -3325,7 +3321,7 @@ static int __do_readpage(struct page *page,
ret = submit_extent_page(REQ_OP_READ | read_flags, NULL,
page, offset, disk_io_size,
pg_offset, bio,
end_bio_extent_readpage, mirror_num,
end_bio_extent_readpage, 0,
*bio_flags,
this_bio_flag,
force_bio_submit);
......@@ -3362,44 +3358,12 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages,
btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
for (index = 0; index < nr_pages; index++) {
__do_readpage(pages[index], btrfs_get_extent, em_cached,
bio, 0, bio_flags, REQ_RAHEAD, prev_em_start);
btrfs_do_readpage(pages[index], em_cached, bio, bio_flags,
REQ_RAHEAD, prev_em_start);
put_page(pages[index]);
}
}
static int __extent_read_full_page(struct page *page,
get_extent_t *get_extent,
struct bio **bio, int mirror_num,
unsigned long *bio_flags,
unsigned int read_flags)
{
struct btrfs_inode *inode = BTRFS_I(page->mapping->host);
u64 start = page_offset(page);
u64 end = start + PAGE_SIZE - 1;
int ret;
btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);
ret = __do_readpage(page, get_extent, NULL, bio, mirror_num,
bio_flags, read_flags, NULL);
return ret;
}
int extent_read_full_page(struct page *page, get_extent_t *get_extent,
int mirror_num)
{
struct bio *bio = NULL;
unsigned long bio_flags = 0;
int ret;
ret = __extent_read_full_page(page, get_extent, &bio, mirror_num,
&bio_flags, 0);
if (bio)
ret = submit_one_bio(bio, mirror_num, bio_flags);
return ret;
}
static void update_nr_written(struct writeback_control *wbc,
unsigned long nr_written)
{
......@@ -4552,7 +4516,7 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
* helper function for fiemap, which doesn't want to see any holes.
* This maps until we find something past 'last'
*/
static struct extent_map *get_extent_skip_holes(struct inode *inode,
static struct extent_map *get_extent_skip_holes(struct btrfs_inode *inode,
u64 offset, u64 last)
{
u64 sectorsize = btrfs_inode_sectorsize(inode);
......@@ -4567,7 +4531,7 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
if (len == 0)
break;
len = ALIGN(len, sectorsize);
em = btrfs_get_extent_fiemap(BTRFS_I(inode), offset, len);
em = btrfs_get_extent_fiemap(inode, offset, len);
if (IS_ERR_OR_NULL(em))
return em;
......@@ -4696,7 +4660,7 @@ static int emit_last_fiemap_cache(struct fiemap_extent_info *fieinfo,
return ret;
}
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
int ret = 0;
......@@ -4707,12 +4671,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 last;
u64 last_for_get_extent = 0;
u64 disko = 0;
u64 isize = i_size_read(inode);
u64 isize = i_size_read(&inode->vfs_inode);
struct btrfs_key found_key;
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
struct btrfs_path *path;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_root *root = inode->root;
struct fiemap_cache cache = { 0 };
struct ulist *roots;
struct ulist *tmp_ulist;
......@@ -4743,8 +4707,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
* lookup the last file extent. We're not using i_size here
* because there might be preallocation past i_size
*/
ret = btrfs_lookup_file_extent(NULL, root, path,
btrfs_ino(BTRFS_I(inode)), -1, 0);
ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode), -1,
0);
if (ret < 0) {
goto out_free_ulist;
} else {
......@@ -4758,7 +4722,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
found_type = found_key.type;
/* No extents, but there might be delalloc bits */
if (found_key.objectid != btrfs_ino(BTRFS_I(inode)) ||
if (found_key.objectid != btrfs_ino(inode) ||
found_type != BTRFS_EXTENT_DATA_KEY) {
/* have to trust i_size as the end */
last = (u64)-1;
......@@ -4784,7 +4748,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
last_for_get_extent = isize;
}
lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len - 1,
lock_extent_bits(&inode->io_tree, start, start + len - 1,
&cached_state);
em = get_extent_skip_holes(inode, start, last_for_get_extent);
......@@ -4853,8 +4817,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
* then we're just getting a count and we can skip the
* lookup stuff.
*/
ret = btrfs_check_shared(root,
btrfs_ino(BTRFS_I(inode)),
ret = btrfs_check_shared(root, btrfs_ino(inode),
bytenr, roots, tmp_ulist);
if (ret < 0)
goto out_free;
......@@ -4898,7 +4861,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
ret = emit_last_fiemap_cache(fieinfo, &cache);
free_extent_map(em);
out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, start, start + len - 1,
unlock_extent_cached(&inode->io_tree, start, start + len - 1,
&cached_state);
out_free_ulist:
......@@ -4990,7 +4953,7 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
rwlock_init(&eb->lock);
atomic_set(&eb->blocking_readers, 0);
eb->blocking_writers = 0;
eb->lock_nested = false;
eb->lock_recursed = false;
init_waitqueue_head(&eb->write_lock_wq);
init_waitqueue_head(&eb->read_lock_wq);
......@@ -5574,20 +5537,19 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
}
ClearPageError(page);
err = __extent_read_full_page(page,
btree_get_extent, &bio,
mirror_num, &bio_flags,
REQ_META);
err = submit_extent_page(REQ_OP_READ | REQ_META, NULL,
page, page_offset(page), PAGE_SIZE, 0,
&bio, end_bio_extent_readpage,
mirror_num, 0, 0, false);
if (err) {
ret = err;
/*
* We use &bio in above __extent_read_full_page,
* so we ensure that if it returns error, the
* current page fails to add itself to bio and
* it's been unlocked.
*
* We must dec io_pages by ourselves.
* We failed to submit the bio so it's the
* caller's responsibility to perform cleanup
* i.e unlock page/set error bit.
*/
ret = err;
SetPageError(page);
unlock_page(page);
atomic_dec(&eb->io_pages);
}
} else {
......@@ -5622,6 +5584,36 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
return ret;
}
static bool report_eb_range(const struct extent_buffer *eb, unsigned long start,
unsigned long len)
{
btrfs_warn(eb->fs_info,
"access to eb bytenr %llu len %lu out of range start %lu len %lu",
eb->start, eb->len, start, len);
WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
return true;
}
/*
* Check if the [start, start + len) range is valid before reading/writing
* the eb.
* NOTE: @start and @len are offset inside the eb, not logical address.
*
* Caller should not touch the dst/src memory if this function returns error.
*/
static inline int check_eb_range(const struct extent_buffer *eb,
unsigned long start, unsigned long len)
{
unsigned long offset;
/* start, start + len should not go beyond eb->len nor overflow */
if (unlikely(check_add_overflow(start, len, &offset) || offset > eb->len))
return report_eb_range(eb, start, len);
return false;
}
void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
unsigned long start, unsigned long len)
{
......@@ -5632,12 +5624,8 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv,
char *dst = (char *)dstv;
unsigned long i = start >> PAGE_SHIFT;
if (start + len > eb->len) {
WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
eb->start, eb->len, start, len);
memset(dst, 0, len);
if (check_eb_range(eb, start, len))
return;
}
offset = offset_in_page(start);
......@@ -5702,8 +5690,8 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
unsigned long i = start >> PAGE_SHIFT;
int ret = 0;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
if (check_eb_range(eb, start, len))
return -EINVAL;
offset = offset_in_page(start);
......@@ -5756,8 +5744,8 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
char *src = (char *)srcv;
unsigned long i = start >> PAGE_SHIFT;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
if (check_eb_range(eb, start, len))
return;
offset = offset_in_page(start);
......@@ -5785,8 +5773,8 @@ void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
char *kaddr;
unsigned long i = start >> PAGE_SHIFT;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
if (check_eb_range(eb, start, len))
return;
offset = offset_in_page(start);
......@@ -5830,6 +5818,10 @@ void copy_extent_buffer(const struct extent_buffer *dst,
char *kaddr;
unsigned long i = dst_offset >> PAGE_SHIFT;
if (check_eb_range(dst, dst_offset, len) ||
check_eb_range(src, src_offset, len))
return;
WARN_ON(src->len != dst_len);
offset = offset_in_page(dst_offset);
......@@ -6019,25 +6011,15 @@ void memcpy_extent_buffer(const struct extent_buffer *dst,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len)
{
struct btrfs_fs_info *fs_info = dst->fs_info;
size_t cur;
size_t dst_off_in_page;
size_t src_off_in_page;
unsigned long dst_i;
unsigned long src_i;
if (src_offset + len > dst->len) {
btrfs_err(fs_info,
"memmove bogus src_offset %lu move len %lu dst len %lu",
src_offset, len, dst->len);
BUG();
}
if (dst_offset + len > dst->len) {
btrfs_err(fs_info,
"memmove bogus dst_offset %lu move len %lu dst len %lu",
dst_offset, len, dst->len);
BUG();
}
if (check_eb_range(dst, dst_offset, len) ||
check_eb_range(dst, src_offset, len))
return;
while (len > 0) {
dst_off_in_page = offset_in_page(dst_offset);
......@@ -6064,7 +6046,6 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
unsigned long dst_offset, unsigned long src_offset,
unsigned long len)
{
struct btrfs_fs_info *fs_info = dst->fs_info;
size_t cur;
size_t dst_off_in_page;
size_t src_off_in_page;
......@@ -6073,18 +6054,9 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
unsigned long dst_i;
unsigned long src_i;
if (src_offset + len > dst->len) {
btrfs_err(fs_info,
"memmove bogus src_offset %lu move len %lu len %lu",
src_offset, len, dst->len);
BUG();
}
if (dst_offset + len > dst->len) {
btrfs_err(fs_info,
"memmove bogus dst_offset %lu move len %lu len %lu",
dst_offset, len, dst->len);
BUG();
}
if (check_eb_range(dst, dst_offset, len) ||
check_eb_range(dst, src_offset, len))
return;
if (dst_offset < src_offset) {
memcpy_extent_buffer(dst, dst_offset, src_offset, len);
return;
......
fs/btrfs/extent_io.h
浏览文件 @ 11e3235b
......@@ -74,18 +74,6 @@ typedef blk_status_t (submit_bio_hook_t)(struct inode *inode, struct bio *bio,
typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
struct bio *bio, u64 bio_offset);
struct extent_io_ops {
/*
* The following callbacks must be always defined, the function
* pointer will be called unconditionally.
*/
submit_bio_hook_t *submit_bio_hook;
int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
struct page *page, u64 start, u64 end,
int mirror);
};
#define INLINE_EXTENT_BUFFER_PAGES 16
#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
struct extent_buffer {
......@@ -102,7 +90,7 @@ struct extent_buffer {
int blocking_writers;
atomic_t blocking_readers;
bool lock_nested;
bool lock_recursed;
/* >= 0 if eb belongs to a log tree, -1 otherwise */
short log_index;
......@@ -193,8 +181,11 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
int try_release_extent_mapping(struct page *page, gfp_t mask);
int try_release_extent_buffer(struct page *page);
int extent_read_full_page(struct page *page, get_extent_t *get_extent,
int mirror_num);
int __must_check submit_one_bio(struct bio *bio, int mirror_num,
unsigned long bio_flags);
int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
struct bio **bio, unsigned long *bio_flags,
unsigned int read_flags, u64 *prev_em_start);
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);
......@@ -203,7 +194,7 @@ int extent_writepages(struct address_space *mapping,
int btree_write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc);
void extent_readahead(struct readahead_control *rac);
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
void set_page_extent_mapped(struct page *page);
......
fs/btrfs/file-item.c
浏览文件 @ 11e3235b
......@@ -318,8 +318,8 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
if (page_offsets)
offset = page_offset(bvec.bv_page) + bvec.bv_offset;
count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
csum, nblocks);
count = btrfs_find_ordered_sum(BTRFS_I(inode), offset,
disk_bytenr, csum, nblocks);
if (count)
goto found;
......
fs/btrfs/file.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/free-space-cache.c
浏览文件 @ 11e3235b
......@@ -413,8 +413,6 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate)
static void io_ctl_set_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
{
__le64 *val;
io_ctl_map_page(io_ctl, 1);
/*
......@@ -429,14 +427,13 @@ static void io_ctl_set_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
io_ctl->size -= sizeof(u64) * 2;
}
val = io_ctl->cur;
*val = cpu_to_le64(generation);
put_unaligned_le64(generation, io_ctl->cur);
io_ctl->cur += sizeof(u64);
}
static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
{
__le64 *gen;
u64 cache_gen;
/*
* Skip the crc area. If we don't check crcs then we just have a 64bit
......@@ -451,11 +448,11 @@ static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
io_ctl->size -= sizeof(u64) * 2;
}
gen = io_ctl->cur;
if (le64_to_cpu(*gen) != generation) {
cache_gen = get_unaligned_le64(io_ctl->cur);
if (cache_gen != generation) {
btrfs_err_rl(io_ctl->fs_info,
"space cache generation (%llu) does not match inode (%llu)",
*gen, generation);
cache_gen, generation);
io_ctl_unmap_page(io_ctl);
return -EIO;
}
......@@ -525,8 +522,8 @@ static int io_ctl_add_entry(struct btrfs_io_ctl *io_ctl, u64 offset, u64 bytes,
return -ENOSPC;
entry = io_ctl->cur;
entry->offset = cpu_to_le64(offset);
entry->bytes = cpu_to_le64(bytes);
put_unaligned_le64(offset, &entry->offset);
put_unaligned_le64(bytes, &entry->bytes);
entry->type = (bitmap) ? BTRFS_FREE_SPACE_BITMAP :
BTRFS_FREE_SPACE_EXTENT;
io_ctl->cur += sizeof(struct btrfs_free_space_entry);
......@@ -599,8 +596,8 @@ static int io_ctl_read_entry(struct btrfs_io_ctl *io_ctl,
}
e = io_ctl->cur;
entry->offset = le64_to_cpu(e->offset);
entry->bytes = le64_to_cpu(e->bytes);
entry->offset = get_unaligned_le64(&e->offset);
entry->bytes = get_unaligned_le64(&e->bytes);
*type = e->type;
io_ctl->cur += sizeof(struct btrfs_free_space_entry);
io_ctl->size -= sizeof(struct btrfs_free_space_entry);
......@@ -1353,7 +1350,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
/*
* at this point the pages are under IO and we're happy,
* The caller is responsible for waiting on them and updating the
* The caller is responsible for waiting on them and updating
* the cache and the inode
*/
io_ctl->entries = entries;
......
fs/btrfs/inode.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/ioctl.c
浏览文件 @ 11e3235b
......@@ -378,6 +378,18 @@ static int check_xflags(unsigned int flags)
return 0;
}
bool btrfs_exclop_start(struct btrfs_fs_info *fs_info,
enum btrfs_exclusive_operation type)
{
return !cmpxchg(&fs_info->exclusive_operation, BTRFS_EXCLOP_NONE, type);
}
void btrfs_exclop_finish(struct btrfs_fs_info *fs_info)
{
WRITE_ONCE(fs_info->exclusive_operation, BTRFS_EXCLOP_NONE);
sysfs_notify(&fs_info->fs_devices->fsid_kobj, NULL, "exclusive_operation");
}
/*
* Set the xflags from the internal inode flags. The remaining items of fsxattr
* are zeroed.
......@@ -618,7 +630,7 @@ static noinline int create_subvol(struct inode *dir,
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_subvolume_release_metadata(fs_info, &block_rsv);
btrfs_subvolume_release_metadata(root, &block_rsv);
goto fail_free;
}
trans->block_rsv = &block_rsv;
......@@ -628,7 +640,8 @@ static noinline int create_subvol(struct inode *dir,
if (ret)
goto fail;
leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
BTRFS_NESTING_NORMAL);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
goto fail;
......@@ -742,7 +755,7 @@ static noinline int create_subvol(struct inode *dir,
kfree(root_item);
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
btrfs_subvolume_release_metadata(fs_info, &block_rsv);
btrfs_subvolume_release_metadata(root, &block_rsv);
err = btrfs_commit_transaction(trans);
if (err && !ret)
......@@ -856,7 +869,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
if (ret && pending_snapshot->snap)
pending_snapshot->snap->anon_dev = 0;
btrfs_put_root(pending_snapshot->snap);
btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv);
free_pending:
if (pending_snapshot->anon_dev)
free_anon_bdev(pending_snapshot->anon_dev);
......@@ -1306,7 +1319,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
break;
unlock_page(page);
btrfs_start_ordered_extent(inode, ordered, 1);
btrfs_start_ordered_extent(ordered, 1);
btrfs_put_ordered_extent(ordered);
lock_page(page);
/*
......@@ -1638,7 +1651,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
if (ret)
return ret;
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_RESIZE)) {
mnt_drop_write_file(file);
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
......@@ -1752,7 +1765,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
out_free:
kfree(vol_args);
out:
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
btrfs_exclop_finish(fs_info);
mnt_drop_write_file(file);
return ret;
}
......@@ -3126,7 +3139,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_ADD))
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
vol_args = memdup_user(arg, sizeof(*vol_args));
......@@ -3143,7 +3156,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
kfree(vol_args);
out:
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
btrfs_exclop_finish(fs_info);
return ret;
}
......@@ -3172,7 +3185,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
goto out;
}
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_REMOVE)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
goto out;
}
......@@ -3183,7 +3196,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
ret = btrfs_rm_device(fs_info, vol_args->name, 0);
}
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
btrfs_exclop_finish(fs_info);
if (!ret) {
if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
......@@ -3214,7 +3227,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
if (ret)
return ret;
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_REMOVE)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
goto out_drop_write;
}
......@@ -3232,7 +3245,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
btrfs_info(fs_info, "disk deleted %s", vol_args->name);
kfree(vol_args);
out:
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
btrfs_exclop_finish(fs_info);
out_drop_write:
mnt_drop_write_file(file);
......@@ -3462,15 +3475,12 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *tmp;
info = NULL;
rcu_read_lock();
list_for_each_entry_rcu(tmp, &fs_info->space_info,
list) {
list_for_each_entry(tmp, &fs_info->space_info, list) {
if (tmp->flags == types[i]) {
info = tmp;
break;
}
}
rcu_read_unlock();
if (!info)
continue;
......@@ -3518,15 +3528,12 @@ static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info,
break;
info = NULL;
rcu_read_lock();
list_for_each_entry_rcu(tmp, &fs_info->space_info,
list) {
list_for_each_entry(tmp, &fs_info->space_info, list) {
if (tmp->flags == types[i]) {
info = tmp;
break;
}
}
rcu_read_unlock();
if (!info)
continue;
......@@ -3736,11 +3743,11 @@ static long btrfs_ioctl_dev_replace(struct btrfs_fs_info *fs_info,
ret = -EROFS;
goto out;
}
if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_REPLACE)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
} else {
ret = btrfs_dev_replace_by_ioctl(fs_info, p);
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
btrfs_exclop_finish(fs_info);
}
break;
case BTRFS_IOCTL_DEV_REPLACE_CMD_STATUS:
......@@ -3951,7 +3958,7 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
return ret;
again:
if (!test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
if (btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE)) {
mutex_lock(&fs_info->balance_mutex);
need_unlock = true;
goto locked;
......@@ -3997,7 +4004,6 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
}
locked:
BUG_ON(!test_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
if (arg) {
bargs = memdup_user(arg, sizeof(*bargs));
......@@ -4052,10 +4058,10 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
do_balance:
/*
* Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP goes to
* btrfs_balance. bctl is freed in reset_balance_state, or, if
* restriper was paused all the way until unmount, in free_fs_info.
* The flag should be cleared after reset_balance_state.
* Ownership of bctl and exclusive operation goes to btrfs_balance.
* bctl is freed in reset_balance_state, or, if restriper was paused
* all the way until unmount, in free_fs_info. The flag should be
* cleared after reset_balance_state.
*/
need_unlock = false;
......@@ -4074,7 +4080,7 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
out_unlock:
mutex_unlock(&fs_info->balance_mutex);
if (need_unlock)
clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
btrfs_exclop_finish(fs_info);
out:
mnt_drop_write_file(file);
return ret;
......@@ -4897,7 +4903,7 @@ long btrfs_ioctl(struct file *file, unsigned int
case BTRFS_IOC_SYNC: {
int ret;
ret = btrfs_start_delalloc_roots(fs_info, -1);
ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
if (ret)
return ret;
ret = btrfs_sync_fs(inode->i_sb, 1);
......
fs/btrfs/locking.c
浏览文件 @ 11e3235b
......@@ -57,8 +57,8 @@
* performance reasons.
*
*
* Lock nesting
* ------------
* Lock recursion
* --------------
*
* A write operation on a tree might indirectly start a look up on the same
* tree. This can happen when btrfs_cow_block locks the tree and needs to
......@@ -201,7 +201,7 @@ void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
* lock, but it won't change to or away from us. If we have the write
* lock, we are the owner and it'll never change.
*/
if (eb->lock_nested && current->pid == eb->lock_owner)
if (eb->lock_recursed && current->pid == eb->lock_owner)
return;
btrfs_assert_tree_read_locked(eb);
atomic_inc(&eb->blocking_readers);
......@@ -225,7 +225,7 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
* lock, but it won't change to or away from us. If we have the write
* lock, we are the owner and it'll never change.
*/
if (eb->lock_nested && current->pid == eb->lock_owner)
if (eb->lock_recursed && current->pid == eb->lock_owner)
return;
if (eb->blocking_writers == 0) {
btrfs_assert_spinning_writers_put(eb);
......@@ -244,7 +244,8 @@ void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
*
* The rwlock is held upon exit.
*/
void btrfs_tree_read_lock(struct extent_buffer *eb)
void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest,
bool recurse)
{
u64 start_ns = 0;
......@@ -263,8 +264,9 @@ void btrfs_tree_read_lock(struct extent_buffer *eb)
* depends on this as it may be called on a partly
* (write-)locked tree.
*/
BUG_ON(eb->lock_nested);
eb->lock_nested = true;
WARN_ON(!recurse);
BUG_ON(eb->lock_recursed);
eb->lock_recursed = true;
read_unlock(&eb->lock);
trace_btrfs_tree_read_lock(eb, start_ns);
return;
......@@ -279,6 +281,11 @@ void btrfs_tree_read_lock(struct extent_buffer *eb)
trace_btrfs_tree_read_lock(eb, start_ns);
}
void btrfs_tree_read_lock(struct extent_buffer *eb)
{
__btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL, false);
}
/*
* Lock extent buffer for read, optimistically expecting that there are no
* contending blocking writers. If there are, don't wait.
......@@ -362,11 +369,11 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
/*
* if we're nested, we have the write lock. No new locking
* is needed as long as we are the lock owner.
* The write unlock will do a barrier for us, and the lock_nested
* The write unlock will do a barrier for us, and the lock_recursed
* field only matters to the lock owner.
*/
if (eb->lock_nested && current->pid == eb->lock_owner) {
eb->lock_nested = false;
if (eb->lock_recursed && current->pid == eb->lock_owner) {
eb->lock_recursed = false;
return;
}
btrfs_assert_tree_read_locked(eb);
......@@ -388,11 +395,11 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
/*
* if we're nested, we have the write lock. No new locking
* is needed as long as we are the lock owner.
* The write unlock will do a barrier for us, and the lock_nested
* The write unlock will do a barrier for us, and the lock_recursed
* field only matters to the lock owner.
*/
if (eb->lock_nested && current->pid == eb->lock_owner) {
eb->lock_nested = false;
if (eb->lock_recursed && current->pid == eb->lock_owner) {
eb->lock_recursed = false;
return;
}
btrfs_assert_tree_read_locked(eb);
......@@ -409,7 +416,7 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
*
* The rwlock is held for write upon exit.
*/
void btrfs_tree_lock(struct extent_buffer *eb)
void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
__acquires(&eb->lock)
{
u64 start_ns = 0;
......@@ -434,6 +441,11 @@ void btrfs_tree_lock(struct extent_buffer *eb)
trace_btrfs_tree_lock(eb, start_ns);
}
void btrfs_tree_lock(struct extent_buffer *eb)
{
__btrfs_tree_lock(eb, BTRFS_NESTING_NORMAL);
}
/*
* Release the write lock, either blocking or spinning (ie. there's no need
* for an explicit blocking unlock, like btrfs_tree_read_unlock_blocking).
......@@ -552,13 +564,14 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
*
* Return: root extent buffer with read lock held
*/
struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
struct extent_buffer *__btrfs_read_lock_root_node(struct btrfs_root *root,
bool recurse)
{
struct extent_buffer *eb;
while (1) {
eb = btrfs_root_node(root);
btrfs_tree_read_lock(eb);
__btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL, recurse);
if (eb == root->node)
break;
btrfs_tree_read_unlock(eb);
......
fs/btrfs/locking.h
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/ordered-data.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/ordered-data.h
浏览文件 @ 11e3235b
......@@ -56,6 +56,12 @@ enum {
BTRFS_ORDERED_TRUNCATED,
/* Regular IO for COW */
BTRFS_ORDERED_REGULAR,
/* Used during fsync to track already logged extents */
BTRFS_ORDERED_LOGGED,
/* We have already logged all the csums of the ordered extent */
BTRFS_ORDERED_LOGGED_CSUM,
/* We wait for this extent to complete in the current transaction */
BTRFS_ORDERED_PENDING,
};
struct btrfs_ordered_extent {
......@@ -104,6 +110,9 @@ struct btrfs_ordered_extent {
/* list of checksums for insertion when the extent io is done */
struct list_head list;
/* used for fast fsyncs */
struct list_head log_list;
/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
wait_queue_head_t wait;
......@@ -142,9 +151,9 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t)
}
void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
void btrfs_remove_ordered_extent(struct inode *inode,
void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
struct btrfs_ordered_extent *entry);
int btrfs_dec_test_ordered_pending(struct inode *inode,
int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
struct btrfs_ordered_extent **cached,
u64 file_offset, u64 io_size, int uptodate);
int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
......@@ -165,17 +174,18 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
struct btrfs_ordered_sum *sum);
struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,
u64 file_offset);
void btrfs_start_ordered_extent(struct inode *inode,
struct btrfs_ordered_extent *entry, int wait);
void btrfs_start_ordered_extent(struct btrfs_ordered_extent *entry, int wait);
int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
struct btrfs_ordered_extent *
btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset);
btrfs_lookup_first_ordered_extent(struct btrfs_inode *inode, u64 file_offset);
struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
struct btrfs_inode *inode,
u64 file_offset,
u64 len);
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
u8 *sum, int len);
void btrfs_get_ordered_extents_for_logging(struct btrfs_inode *inode,
struct list_head *list);
int btrfs_find_ordered_sum(struct btrfs_inode *inode, u64 offset,
u64 disk_bytenr, u8 *sum, int len);
u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
const u64 range_start, const u64 range_len);
void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
......
fs/btrfs/print-tree.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/print-tree.h
浏览文件 @ 11e3235b
......@@ -6,7 +6,11 @@
#ifndef BTRFS_PRINT_TREE_H
#define BTRFS_PRINT_TREE_H
/* Buffer size to contain tree name and possibly additional data (offset) */
#define BTRFS_ROOT_NAME_BUF_LEN 48
void btrfs_print_leaf(struct extent_buffer *l);
void btrfs_print_tree(struct extent_buffer *c, bool follow);
const char *btrfs_root_name(u64 objectid, char *buf);
#endif
fs/btrfs/qgroup.c
浏览文件 @ 11e3235b
......@@ -2315,7 +2315,7 @@ static int qgroup_update_refcnt(struct btrfs_fs_info *fs_info,
* Update qgroup rfer/excl counters.
* Rfer update is easy, codes can explain themselves.
*
* Excl update is tricky, the update is split into 2 part.
* Excl update is tricky, the update is split into 2 parts.
* Part 1: Possible exclusive <-> sharing detect:
* | A | !A |
* -------------------------------------
......
fs/btrfs/reada.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/reflink.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/relocation.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/root-tree.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/scrub.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/send.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/send.h
浏览文件 @ 11e3235b
......@@ -13,7 +13,6 @@
#define BTRFS_SEND_STREAM_VERSION 1
#define BTRFS_SEND_BUF_SIZE SZ_64K
#define BTRFS_SEND_READ_SIZE (48 * SZ_1K)
enum btrfs_tlv_type {
BTRFS_TLV_U8,
......
fs/btrfs/space-info.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/space-info.h
浏览文件 @ 11e3235b
......@@ -149,5 +149,7 @@ static inline void btrfs_space_info_free_bytes_may_use(
btrfs_try_granting_tickets(fs_info, space_info);
spin_unlock(&space_info->lock);
}
int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes,
enum btrfs_reserve_flush_enum flush);
#endif /* BTRFS_SPACE_INFO_H */
fs/btrfs/struct-funcs.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/super.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/sysfs.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/sysfs.h
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/tests/inode-tests.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/transaction.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/transaction.h
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/tree-checker.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/tree-log.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/tree-log.h
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/volumes.c
浏览文件 @ 11e3235b
此差异已折叠。
fs/btrfs/volumes.h
浏览文件 @ 11e3235b
此差异已折叠。
fs/direct-io.c
浏览文件 @ 11e3235b
此差异已折叠。
include/linux/fs.h
浏览文件 @ 11e3235b
此差异已折叠。
include/trace/events/btrfs.h
浏览文件 @ 11e3235b
此差异已折叠。
include/uapi/linux/btrfs_tree.h
浏览文件 @ 11e3235b
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