Commit 318b067a authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'for-4.20-part1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This is the first batch with fixes and some nice performance
  improvements.

  Preliminary results show eg. more files/sec in fsmark, better perf on
  multi-threaded workloads (filebench, dbench), fewer context switches
  and overall better memory allocation characteristics (multiple
  benchmarks).

  Apart from general performance, there's an improvement for qgroups +
  balance workload that's been troubling our users.

  Note for stable: there are 20+ patches tagged for stable, out of 90.
  Not all of them apply cleanly on all stable versions but the conflicts
  are mostly due to simple cleanups and resolving should be obvious. The
  fixes are otherwise independent.

  Performance improvements:

   - transition between blocking and spinning modes of path is gone,
     which originally resulted to more unnecessary wakeups and updates
     to the path locks, the effects are measurable and improve latency
     and scalability

   - qgroups: first batch of changes that should speedup balancing with
     qgroups on, skip quota accounting on unchanged subtrees, overall
     gain is about 30+% in runtime

   - use rb-tree with cached first node for several structures, small
     improvement to avoid pointer chasing

  Fixes:

   - trim
      - fix: some blockgroups could have been missed if their logical
        address was past the total filesystem size (ie. after a lot of
        balancing)
      - better error reporting, after processing blockgroups and whole
        device
      - fix: continue trimming block groups after an error is
        encountered
      - check for trim support of the device earlier and avoid some
        unnecessary work
      - less interaction with transaction commit that improves latency
        on slower storage (eg. image files over NFS)

   - fsync
      - fix warning when replaying log after fsync of a O_TMPFILE
      - fix wrong dentries after fsync of file that got its parent
        replaced

   - qgroups: fix rescan that might misc some dirty groups

   - don't clean dirty pages during buffered writes, this could lead to
     lost updates in some corner cases

   - some block groups could have been delayed in creation, if the
     allocation triggered another one

   - error handling improvements

  Cleanups:

   - removed unused struct members and variables

   - function return type cleanups

   - delayed refs code refactoring

   - protect against deadlock that could be caused by crafted image that
     tries to allocate from a tree that's locked already"

* tag 'for-4.20-part1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (93 commits)
  btrfs: switch return_bigger to bool in find_ref_head
  btrfs: remove fs_info from btrfs_should_throttle_delayed_refs
  btrfs: remove fs_info from btrfs_check_space_for_delayed_refs
  btrfs: delayed-ref: pass delayed_refs directly to btrfs_delayed_ref_lock
  btrfs: delayed-ref: pass delayed_refs directly to btrfs_select_ref_head
  btrfs: qgroup: move the qgroup->members check out from (!qgroup)'s else branch
  btrfs: relocation: Remove redundant tree level check
  btrfs: relocation: Cleanup while loop using rbtree_postorder_for_each_entry_safe
  btrfs: qgroup: Avoid calling qgroup functions if qgroup is not enabled
  Btrfs: fix wrong dentries after fsync of file that got its parent replaced
  Btrfs: fix warning when replaying log after fsync of a tmpfile
  btrfs: drop min_size from evict_refill_and_join
  btrfs: assert on non-empty delayed iputs
  btrfs: make sure we create all new block groups
  btrfs: reset max_extent_size on clear in a bitmap
  btrfs: protect space cache inode alloc with GFP_NOFS
  btrfs: release metadata before running delayed refs
  Btrfs: kill btrfs_clear_path_blocking
  btrfs: dev-replace: remove pointless assert in write unlock
  btrfs: dev-replace: move replace members out of fs_info
  ...
parents 44adbac8 d9352794
......@@ -112,11 +112,11 @@ static int find_extent_in_eb(const struct extent_buffer *eb,
}
struct preftree {
struct rb_root root;
struct rb_root_cached root;
unsigned int count;
};
#define PREFTREE_INIT { .root = RB_ROOT, .count = 0 }
#define PREFTREE_INIT { .root = RB_ROOT_CACHED, .count = 0 }
struct preftrees {
struct preftree direct; /* BTRFS_SHARED_[DATA|BLOCK]_REF_KEY */
......@@ -225,14 +225,15 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info,
struct prelim_ref *newref,
struct share_check *sc)
{
struct rb_root *root;
struct rb_root_cached *root;
struct rb_node **p;
struct rb_node *parent = NULL;
struct prelim_ref *ref;
int result;
bool leftmost = true;
root = &preftree->root;
p = &root->rb_node;
p = &root->rb_root.rb_node;
while (*p) {
parent = *p;
......@@ -242,6 +243,7 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info,
p = &(*p)->rb_left;
} else if (result > 0) {
p = &(*p)->rb_right;
leftmost = false;
} else {
/* Identical refs, merge them and free @newref */
struct extent_inode_elem *eie = ref->inode_list;
......@@ -272,7 +274,7 @@ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info,
preftree->count++;
trace_btrfs_prelim_ref_insert(fs_info, newref, NULL, preftree->count);
rb_link_node(&newref->rbnode, parent, p);
rb_insert_color(&newref->rbnode, root);
rb_insert_color_cached(&newref->rbnode, root, leftmost);
}
/*
......@@ -283,11 +285,11 @@ static void prelim_release(struct preftree *preftree)
{
struct prelim_ref *ref, *next_ref;
rbtree_postorder_for_each_entry_safe(ref, next_ref, &preftree->root,
rbnode)
rbtree_postorder_for_each_entry_safe(ref, next_ref,
&preftree->root.rb_root, rbnode)
free_pref(ref);
preftree->root = RB_ROOT;
preftree->root = RB_ROOT_CACHED;
preftree->count = 0;
}
......@@ -627,7 +629,7 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info,
* freeing the entire indirect tree when we're done. In some test
* cases, the tree can grow quite large (~200k objects).
*/
while ((rnode = rb_first(&preftrees->indirect.root))) {
while ((rnode = rb_first_cached(&preftrees->indirect.root))) {
struct prelim_ref *ref;
ref = rb_entry(rnode, struct prelim_ref, rbnode);
......@@ -637,7 +639,7 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info,
goto out;
}
rb_erase(&ref->rbnode, &preftrees->indirect.root);
rb_erase_cached(&ref->rbnode, &preftrees->indirect.root);
preftrees->indirect.count--;
if (ref->count == 0) {
......@@ -717,9 +719,9 @@ static int add_missing_keys(struct btrfs_fs_info *fs_info,
struct preftree *tree = &preftrees->indirect_missing_keys;
struct rb_node *node;
while ((node = rb_first(&tree->root))) {
while ((node = rb_first_cached(&tree->root))) {
ref = rb_entry(node, struct prelim_ref, rbnode);
rb_erase(node, &tree->root);
rb_erase_cached(node, &tree->root);
BUG_ON(ref->parent); /* should not be a direct ref */
BUG_ON(ref->key_for_search.type);
......@@ -769,7 +771,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key);
spin_lock(&head->lock);
for (n = rb_first(&head->ref_tree); n; n = rb_next(n)) {
for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) {
node = rb_entry(n, struct btrfs_delayed_ref_node,
ref_node);
if (node->seq > seq)
......@@ -1229,14 +1231,14 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
if (ret)
goto out;
WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root));
WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root.rb_root));
ret = resolve_indirect_refs(fs_info, path, time_seq, &preftrees,
extent_item_pos, total_refs, sc, ignore_offset);
if (ret)
goto out;
WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect.root));
WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect.root.rb_root));
/*
* This walks the tree of merged and resolved refs. Tree blocks are
......@@ -1245,7 +1247,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
*
* We release the entire tree in one go before returning.
*/
node = rb_first(&preftrees.direct.root);
node = rb_first_cached(&preftrees.direct.root);
while (node) {
ref = rb_entry(node, struct prelim_ref, rbnode);
node = rb_next(&ref->rbnode);
......@@ -1468,7 +1470,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr)
struct seq_list elem = SEQ_LIST_INIT(elem);
int ret = 0;
struct share_check shared = {
.root_objectid = root->objectid,
.root_objectid = root->root_key.objectid,
.inum = inum,
.share_count = 0,
};
......@@ -2031,7 +2033,8 @@ static int iterate_inode_refs(u64 inum, struct btrfs_root *fs_root,
/* path must be released before calling iterate()! */
btrfs_debug(fs_root->fs_info,
"following ref at offset %u for inode %llu in tree %llu",
cur, found_key.objectid, fs_root->objectid);
cur, found_key.objectid,
fs_root->root_key.objectid);
ret = iterate(parent, name_len,
(unsigned long)(iref + 1), eb, ctx);
if (ret)
......
......@@ -206,7 +206,7 @@ static inline struct btrfs_inode *BTRFS_I(const struct inode *inode)
static inline unsigned long btrfs_inode_hash(u64 objectid,
const struct btrfs_root *root)
{
u64 h = objectid ^ (root->objectid * GOLDEN_RATIO_PRIME);
u64 h = objectid ^ (root->root_key.objectid * GOLDEN_RATIO_PRIME);
#if BITS_PER_LONG == 32
h = (h >> 32) ^ (h & 0xffffffff);
......@@ -339,15 +339,15 @@ static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
struct btrfs_root *root = inode->root;
/* Output minus objectid, which is more meaningful */
if (root->objectid >= BTRFS_LAST_FREE_OBJECTID)
if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID)
btrfs_warn_rl(root->fs_info,
"csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d",
root->objectid, btrfs_ino(inode),
root->root_key.objectid, btrfs_ino(inode),
logical_start, csum, csum_expected, mirror_num);
else
btrfs_warn_rl(root->fs_info,
"csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d",
root->objectid, btrfs_ino(inode),
root->root_key.objectid, btrfs_ino(inode),
logical_start, csum, csum_expected, mirror_num);
}
......
......@@ -1594,6 +1594,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
{
unsigned int num_pages;
unsigned int i;
size_t size;
u64 dev_bytenr;
int ret;
......@@ -1608,9 +1609,8 @@ static int btrfsic_read_block(struct btrfsic_state *state,
num_pages = (block_ctx->len + (u64)PAGE_SIZE - 1) >>
PAGE_SHIFT;
block_ctx->mem_to_free = kcalloc(sizeof(*block_ctx->datav) +
sizeof(*block_ctx->pagev),
num_pages, GFP_NOFS);
size = sizeof(*block_ctx->datav) + sizeof(*block_ctx->pagev);
block_ctx->mem_to_free = kcalloc(num_pages, size, GFP_NOFS);
if (!block_ctx->mem_to_free)
return -ENOMEM;
block_ctx->datav = block_ctx->mem_to_free;
......
......@@ -528,7 +528,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct extent_io_tree *tree;
struct extent_map_tree *em_tree;
struct compressed_bio *cb;
unsigned long compressed_len;
......@@ -545,7 +544,6 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int faili = 0;
u32 *sums;
tree = &BTRFS_I(inode)->io_tree;
em_tree = &BTRFS_I(inode)->extent_tree;
/* we need the actual starting offset of this extent in the file */
......
......@@ -52,42 +52,6 @@ noinline void btrfs_set_path_blocking(struct btrfs_path *p)
}
}
/*
* reset all the locked nodes in the patch to spinning locks.
*
* held is used to keep lockdep happy, when lockdep is enabled
* we set held to a blocking lock before we go around and
* retake all the spinlocks in the path. You can safely use NULL
* for held
*/
noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
struct extent_buffer *held, int held_rw)
{
int i;
if (held) {
btrfs_set_lock_blocking_rw(held, held_rw);
if (held_rw == BTRFS_WRITE_LOCK)
held_rw = BTRFS_WRITE_LOCK_BLOCKING;
else if (held_rw == BTRFS_READ_LOCK)
held_rw = BTRFS_READ_LOCK_BLOCKING;
}
btrfs_set_path_blocking(p);
for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
if (p->nodes[i] && p->locks[i]) {
btrfs_clear_lock_blocking_rw(p->nodes[i], p->locks[i]);
if (p->locks[i] == BTRFS_WRITE_LOCK_BLOCKING)
p->locks[i] = BTRFS_WRITE_LOCK;
else if (p->locks[i] == BTRFS_READ_LOCK_BLOCKING)
p->locks[i] = BTRFS_READ_LOCK;
}
}
if (held)
btrfs_clear_lock_blocking_rw(held, held_rw);
}
/* this also releases the path */
void btrfs_free_path(struct btrfs_path *p)
{
......@@ -207,7 +171,7 @@ static void add_root_to_dirty_list(struct btrfs_root *root)
spin_lock(&fs_info->trans_lock);
if (!test_and_set_bit(BTRFS_ROOT_DIRTY, &root->state)) {
/* Want the extent tree to be the last on the list */
if (root->objectid == BTRFS_EXTENT_TREE_OBJECTID)
if (root->root_key.objectid == BTRFS_EXTENT_TREE_OBJECTID)
list_move_tail(&root->dirty_list,
&fs_info->dirty_cowonly_roots);
else
......@@ -1306,7 +1270,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
}
}
btrfs_clear_path_blocking(path, NULL, BTRFS_READ_LOCK);
btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
......@@ -1815,8 +1778,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
int orig_slot = path->slots[level];
u64 orig_ptr;
if (level == 0)
return 0;
ASSERT(level > 0);
mid = path->nodes[level];
......@@ -2483,7 +2445,6 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
btrfs_set_path_blocking(p);
reada_for_balance(fs_info, p, level);
sret = split_node(trans, root, p, level);
btrfs_clear_path_blocking(p, NULL, 0);
BUG_ON(sret > 0);
if (sret) {
......@@ -2504,7 +2465,6 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
btrfs_set_path_blocking(p);
reada_for_balance(fs_info, p, level);
sret = balance_level(trans, root, p, level);
btrfs_clear_path_blocking(p, NULL, 0);
if (sret) {
ret = sret;
......@@ -2789,7 +2749,10 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
}
cow_done:
p->nodes[level] = b;
btrfs_clear_path_blocking(p, NULL, 0);
/*
* Leave path with blocking locks to avoid massive
* lock context switch, this is made on purpose.
*/
/*
* we have a lock on b and as long as we aren't changing
......@@ -2871,8 +2834,6 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_lock(b);
btrfs_clear_path_blocking(p, b,
BTRFS_WRITE_LOCK);
}
p->locks[level] = BTRFS_WRITE_LOCK;
} else {
......@@ -2880,8 +2841,6 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
btrfs_clear_path_blocking(p, b,
BTRFS_READ_LOCK);
}
p->locks[level] = BTRFS_READ_LOCK;
}
......@@ -2900,7 +2859,6 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
btrfs_set_path_blocking(p);
err = split_leaf(trans, root, key,
p, ins_len, ret == 0);
btrfs_clear_path_blocking(p, NULL, 0);
BUG_ON(err > 0);
if (err) {
......@@ -2910,7 +2868,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
}
if (!p->search_for_split)
unlock_up(p, level, lowest_unlock,
min_write_lock_level, &write_lock_level);
min_write_lock_level, NULL);
goto done;
}
}
......@@ -2961,13 +2919,16 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
again:
b = get_old_root(root, time_seq);
if (!b) {
ret = -EIO;
goto done;
}
level = btrfs_header_level(b);
p->locks[level] = BTRFS_READ_LOCK;
while (b) {
level = btrfs_header_level(b);
p->nodes[level] = b;
btrfs_clear_path_blocking(p, NULL, 0);
/*
* we have a lock on b and as long as we aren't changing
......@@ -3013,8 +2974,6 @@ int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
btrfs_clear_path_blocking(p, b,
BTRFS_READ_LOCK);
}
b = tree_mod_log_rewind(fs_info, p, b, time_seq);
if (!b) {
......@@ -5198,7 +5157,6 @@ int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
path->locks[level - 1] = BTRFS_READ_LOCK;
path->nodes[level - 1] = cur;
unlock_up(path, level, 1, 0, NULL);
btrfs_clear_path_blocking(path, NULL, 0);
}
out:
path->keep_locks = keep_locks;
......@@ -5783,8 +5741,6 @@ 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_clear_path_blocking(path, next,
BTRFS_READ_LOCK);
}
next_rw_lock = BTRFS_READ_LOCK;
}
......@@ -5820,8 +5776,6 @@ 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_clear_path_blocking(path, next,
BTRFS_READ_LOCK);
}
next_rw_lock = BTRFS_READ_LOCK;
}
......
......@@ -41,12 +41,6 @@ extern struct kmem_cache *btrfs_path_cachep;
extern struct kmem_cache *btrfs_free_space_cachep;
struct btrfs_ordered_sum;
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
#define STATIC noinline
#else
#define STATIC static noinline
#endif
#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
#define BTRFS_MAX_MIRRORS 3
......@@ -367,11 +361,13 @@ struct btrfs_dev_replace {
struct mutex lock_finishing_cancel_unmount;
rwlock_t lock;
atomic_t read_locks;
atomic_t blocking_readers;
wait_queue_head_t read_lock_wq;
struct btrfs_scrub_progress scrub_progress;
struct percpu_counter bio_counter;
wait_queue_head_t replace_wait;
};
/* For raid type sysfs entries */
......@@ -1094,9 +1090,6 @@ struct btrfs_fs_info {
/* device replace state */
struct btrfs_dev_replace dev_replace;
struct percpu_counter bio_counter;
wait_queue_head_t replace_wait;
struct semaphore uuid_tree_rescan_sem;
/* Used to reclaim the metadata space in the background. */
......@@ -1202,18 +1195,12 @@ struct btrfs_root {
int last_log_commit;
pid_t log_start_pid;
u64 objectid;
u64 last_trans;
u32 type;
u64 highest_objectid;
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/* only used with CONFIG_BTRFS_FS_RUN_SANITY_TESTS is enabled */
u64 alloc_bytenr;
#endif
u64 defrag_trans_start;
struct btrfs_key defrag_progress;
struct btrfs_key defrag_max;
......@@ -1286,6 +1273,10 @@ struct btrfs_root {
spinlock_t qgroup_meta_rsv_lock;
u64 qgroup_meta_rsv_pertrans;
u64 qgroup_meta_rsv_prealloc;
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
u64 alloc_bytenr;
#endif
};
struct btrfs_file_private {
......@@ -2607,10 +2598,8 @@ static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
}
int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans);
int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans);
void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
const u64 start);
void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
......@@ -2771,7 +2760,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
enum btrfs_reserve_flush_enum flush);
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv, u64 num_bytes,
int update_size);
bool update_size);
int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *dest, u64 num_bytes,
int min_factor);
......@@ -2877,8 +2866,6 @@ void btrfs_release_path(struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_set_path_blocking(struct btrfs_path *p);
void btrfs_clear_path_blocking(struct btrfs_path *p,
struct extent_buffer *held, int held_rw);
void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
......@@ -3021,8 +3008,7 @@ int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info,
/* dir-item.c */
int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
const char *name, int name_len);
int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root, const char *name,
int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name,
int name_len, struct btrfs_inode *dir,
struct btrfs_key *location, u8 type, u64 index);
struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
......@@ -3180,8 +3166,8 @@ void __cold btrfs_destroy_cachep(void);
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *was_new);
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
struct page *page, size_t pg_offset,
u64 start, u64 end, int create);
struct page *page, size_t pg_offset,
u64 start, u64 end, int create);
int btrfs_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode);
......@@ -3201,9 +3187,6 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
extern const struct dentry_operations btrfs_dentry_operations;
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_inode_set_ops(struct inode *inode);
#endif
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
......@@ -3716,18 +3699,19 @@ 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);
#endif
static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
{
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
if (unlikely(test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO,
&fs_info->fs_state)))
return 1;
#endif
return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
}
#else
static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
{
return 0;
}
#endif
static inline void cond_wake_up(struct wait_queue_head *wq)
{
......
......@@ -42,8 +42,8 @@ static inline void btrfs_init_delayed_node(
delayed_node->root = root;
delayed_node->inode_id = inode_id;
refcount_set(&delayed_node->refs, 0);
delayed_node->ins_root = RB_ROOT;
delayed_node->del_root = RB_ROOT;
delayed_node->ins_root = RB_ROOT_CACHED;
delayed_node->del_root = RB_ROOT_CACHED;
mutex_init(&delayed_node->mutex);
INIT_LIST_HEAD(&delayed_node->n_list);
INIT_LIST_HEAD(&delayed_node->p_list);
......@@ -390,7 +390,7 @@ static struct btrfs_delayed_item *__btrfs_lookup_delayed_insertion_item(
struct btrfs_delayed_node *delayed_node,
struct btrfs_key *key)
{
return __btrfs_lookup_delayed_item(&delayed_node->ins_root, key,
return __btrfs_lookup_delayed_item(&delayed_node->ins_root.rb_root, key,
NULL, NULL);
}
......@@ -400,9 +400,10 @@ static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node,
{
struct rb_node **p, *node;
struct rb_node *parent_node = NULL;
struct rb_root *root;
struct rb_root_cached *root;
struct btrfs_delayed_item *item;
int cmp;
bool leftmost = true;
if (action == BTRFS_DELAYED_INSERTION_ITEM)
root = &delayed_node->ins_root;
......@@ -410,7 +411,7 @@ static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node,
root = &delayed_node->del_root;
else
BUG();
p = &root->rb_node;
p = &root->rb_root.rb_node;
node = &ins->rb_node;
while (*p) {
......@@ -419,16 +420,18 @@ static int __btrfs_add_delayed_item(struct btrfs_delayed_node *delayed_node,
rb_node);
cmp = btrfs_comp_cpu_keys(&item->key, &ins->key);
if (cmp < 0)
if (cmp < 0) {
p = &(*p)->rb_right;
else if (cmp > 0)
leftmost = false;
} else if (cmp > 0) {
p = &(*p)->rb_left;
else
} else {
return -EEXIST;
}
}
rb_link_node(node, parent_node, p);
rb_insert_color(node, root);
rb_insert_color_cached(node, root, leftmost);
ins->delayed_node = delayed_node;
ins->ins_or_del = action;
......@@ -468,7 +471,7 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root)
static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
{
struct rb_root *root;
struct rb_root_cached *root;
struct btrfs_delayed_root *delayed_root;
delayed_root = delayed_item->delayed_node->root->fs_info->delayed_root;
......@@ -482,7 +485,7 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
else
root = &delayed_item->delayed_node->del_root;
rb_erase(&delayed_item->rb_node, root);
rb_erase_cached(&delayed_item->rb_node, root);
delayed_item->delayed_node->count--;
finish_one_item(delayed_root);
......@@ -503,7 +506,7 @@ static struct btrfs_delayed_item *__btrfs_first_delayed_insertion_item(
struct rb_node *p;
struct btrfs_delayed_item *item = NULL;
p = rb_first(&delayed_node->ins_root);
p = rb_first_cached(&delayed_node->ins_root);
if (p)
item = rb_entry(p, struct btrfs_delayed_item, rb_node);
......@@ -516,7 +519,7 @@ static struct btrfs_delayed_item *__btrfs_first_delayed_deletion_item(
struct rb_node *p;
struct btrfs_delayed_item *item = NULL;
p = rb_first(&delayed_node->del_root);
p = rb_first_cached(&delayed_node->del_root);
if (p)
item = rb_entry(p, struct btrfs_delayed_item, rb_node);
......@@ -559,7 +562,7 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
* reserved space when starting a transaction. So no need to reserve
* qgroup space here.
*/
ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, true);
if (!ret) {
trace_btrfs_space_reservation(fs_info, "delayed_item",
item->key.objectid,
......@@ -647,7 +650,7 @@ static int btrfs_delayed_inode_reserve_metadata(
return ret;
}
ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, true);
if (!ret) {
trace_btrfs_space_reservation(fs_info, "delayed_inode",
btrfs_ino(inode), num_bytes, 1);
......@@ -762,9 +765,6 @@ static int btrfs_batch_insert_items(struct btrfs_root *root,
i++;
}
/* reset all the locked nodes in the patch to spinning locks. */
btrfs_clear_path_blocking(path, NULL, 0);
/* insert the keys of the items */
setup_items_for_insert(root, path, keys, data_size,
total_data_size, total_size, nitems);
......@@ -1462,7 +1462,7 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
if (unlikely(ret)) {
btrfs_err(trans->fs_info,
"err add delayed dir index item(name: %.*s) into the insertion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
name_len, name, delayed_node->root->objectid,
name_len, name, delayed_node->root->root_key.objectid,
delayed_node->inode_id, ret);
BUG();
}
......@@ -1533,7 +1533,8 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
if (unlikely(ret)) {
btrfs_err(trans->fs_info,
"err add delayed dir index item(index: %llu) into the deletion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
index, node->root->objectid, node->inode_id, ret);
index, node->root->root_key.objectid,
node->inode_id, ret);
BUG();
}
mutex_unlock(&node->mutex);
......
......@@ -50,8 +50,8 @@ struct btrfs_delayed_node {
* is waiting to be dealt with by the async worker.
*/
struct list_head p_list;
struct rb_root ins_root;
struct rb_root del_root;
struct rb_root_cached ins_root;
struct rb_root_cached del_root;
struct mutex mutex;
struct btrfs_inode_item inode_item;
refcount_t refs;
......
......@@ -101,14 +101,15 @@ static int comp_refs(struct btrfs_delayed_ref_node *ref1,
}
/* insert a new ref to head ref rbtree */
static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
static struct btrfs_delayed_ref_head *htree_insert(struct rb_root_cached *root,
struct rb_node *node)
{
struct rb_node **p = &root->rb_node;
struct rb_node **p = &root->rb_root.rb_node;
struct rb_node *parent_node = NULL;
struct btrfs_delayed_ref_head *entry;
struct btrfs_delayed_ref_head *ins;
u64 bytenr;
bool leftmost = true;
ins = rb_entry(node, struct btrfs_delayed_ref_head, href_node);
bytenr = ins->bytenr;
......@@ -117,26 +118,29 @@ static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
entry = rb_entry(parent_node, struct btrfs_delayed_ref_head,
href_node);
if (bytenr < entry->bytenr)
if (bytenr < entry->bytenr) {
p = &(*p)->rb_left;
else if (bytenr > entry->bytenr)
} else if (bytenr > entry->bytenr) {
p = &(*p)->rb_right;
else
leftmost = false;
} else {
return entry;
}
}
rb_link_node(node, parent_node,</