summaryrefslogtreecommitdiff
path: root/fs/btrfs/file.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/file.c')
-rw-r--r--fs/btrfs/file.c91
1 files changed, 54 insertions, 37 deletions
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 53bf2d764bb..9aa01ec2138 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -65,6 +65,21 @@ struct inode_defrag {
int cycled;
};
+static int __compare_inode_defrag(struct inode_defrag *defrag1,
+ struct inode_defrag *defrag2)
+{
+ if (defrag1->root > defrag2->root)
+ return 1;
+ else if (defrag1->root < defrag2->root)
+ return -1;
+ else if (defrag1->ino > defrag2->ino)
+ return 1;
+ else if (defrag1->ino < defrag2->ino)
+ return -1;
+ else
+ return 0;
+}
+
/* pop a record for an inode into the defrag tree. The lock
* must be held already
*
@@ -81,15 +96,17 @@ static void __btrfs_add_inode_defrag(struct inode *inode,
struct inode_defrag *entry;
struct rb_node **p;
struct rb_node *parent = NULL;
+ int ret;
p = &root->fs_info->defrag_inodes.rb_node;
while (*p) {
parent = *p;
entry = rb_entry(parent, struct inode_defrag, rb_node);
- if (defrag->ino < entry->ino)
+ ret = __compare_inode_defrag(defrag, entry);
+ if (ret < 0)
p = &parent->rb_left;
- else if (defrag->ino > entry->ino)
+ else if (ret > 0)
p = &parent->rb_right;
else {
/* if we're reinserting an entry for
@@ -103,7 +120,7 @@ static void __btrfs_add_inode_defrag(struct inode *inode,
goto exists;
}
}
- BTRFS_I(inode)->in_defrag = 1;
+ set_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
rb_link_node(&defrag->rb_node, parent, p);
rb_insert_color(&defrag->rb_node, &root->fs_info->defrag_inodes);
return;
@@ -131,7 +148,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
if (btrfs_fs_closing(root->fs_info))
return 0;
- if (BTRFS_I(inode)->in_defrag)
+ if (test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags))
return 0;
if (trans)
@@ -148,7 +165,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
defrag->root = root->root_key.objectid;
spin_lock(&root->fs_info->defrag_inodes_lock);
- if (!BTRFS_I(inode)->in_defrag)
+ if (!test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags))
__btrfs_add_inode_defrag(inode, defrag);
else
kfree(defrag);
@@ -159,28 +176,35 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
/*
* must be called with the defrag_inodes lock held
*/
-struct inode_defrag *btrfs_find_defrag_inode(struct btrfs_fs_info *info, u64 ino,
+struct inode_defrag *btrfs_find_defrag_inode(struct btrfs_fs_info *info,
+ u64 root, u64 ino,
struct rb_node **next)
{
struct inode_defrag *entry = NULL;
+ struct inode_defrag tmp;
struct rb_node *p;
struct rb_node *parent = NULL;
+ int ret;
+
+ tmp.ino = ino;
+ tmp.root = root;
p = info->defrag_inodes.rb_node;
while (p) {
parent = p;
entry = rb_entry(parent, struct inode_defrag, rb_node);
- if (ino < entry->ino)
+ ret = __compare_inode_defrag(&tmp, entry);
+ if (ret < 0)
p = parent->rb_left;
- else if (ino > entry->ino)
+ else if (ret > 0)
p = parent->rb_right;
else
return entry;
}
if (next) {
- while (parent && ino > entry->ino) {
+ while (parent && __compare_inode_defrag(&tmp, entry) > 0) {
parent = rb_next(parent);
entry = rb_entry(parent, struct inode_defrag, rb_node);
}
@@ -202,6 +226,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
struct btrfs_key key;
struct btrfs_ioctl_defrag_range_args range;
u64 first_ino = 0;
+ u64 root_objectid = 0;
int num_defrag;
int defrag_batch = 1024;
@@ -214,11 +239,14 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
n = NULL;
/* find an inode to defrag */
- defrag = btrfs_find_defrag_inode(fs_info, first_ino, &n);
+ defrag = btrfs_find_defrag_inode(fs_info, root_objectid,
+ first_ino, &n);
if (!defrag) {
- if (n)
- defrag = rb_entry(n, struct inode_defrag, rb_node);
- else if (first_ino) {
+ if (n) {
+ defrag = rb_entry(n, struct inode_defrag,
+ rb_node);
+ } else if (root_objectid || first_ino) {
+ root_objectid = 0;
first_ino = 0;
continue;
} else {
@@ -228,6 +256,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
/* remove it from the rbtree */
first_ino = defrag->ino + 1;
+ root_objectid = defrag->root;
rb_erase(&defrag->rb_node, &fs_info->defrag_inodes);
if (btrfs_fs_closing(fs_info))
@@ -252,7 +281,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
goto next;
/* do a chunk of defrag */
- BTRFS_I(inode)->in_defrag = 0;
+ clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
range.start = defrag->last_offset;
num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
defrag_batch);
@@ -1305,7 +1334,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
loff_t *ppos, size_t count, size_t ocount)
{
struct file *file = iocb->ki_filp;
- struct inode *inode = fdentry(file)->d_inode;
struct iov_iter i;
ssize_t written;
ssize_t written_buffered;
@@ -1315,18 +1343,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos,
count, ocount);
- /*
- * the generic O_DIRECT will update in-memory i_size after the
- * DIOs are done. But our endio handlers that update the on
- * disk i_size never update past the in memory i_size. So we
- * need one more update here to catch any additions to the
- * file
- */
- if (inode->i_size != BTRFS_I(inode)->disk_i_size) {
- btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
- mark_inode_dirty(inode);
- }
-
if (written < 0 || written == count)
return written;
@@ -1404,12 +1420,11 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
goto out;
}
- err = btrfs_update_time(file);
+ err = file_update_time(file);
if (err) {
mutex_unlock(&inode->i_mutex);
goto out;
}
- BTRFS_I(inode)->sequence++;
start_pos = round_down(pos, root->sectorsize);
if (start_pos > i_size_read(inode)) {
@@ -1466,8 +1481,8 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
* flush down new bytes that may have been written if the
* application were using truncate to replace a file in place.
*/
- if (BTRFS_I(inode)->ordered_data_close) {
- BTRFS_I(inode)->ordered_data_close = 0;
+ if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
+ &BTRFS_I(inode)->runtime_flags)) {
btrfs_add_ordered_operation(NULL, BTRFS_I(inode)->root, inode);
if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
filemap_flush(inode->i_mapping);
@@ -1498,14 +1513,15 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
trace_btrfs_sync_file(file, datasync);
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- if (ret)
- return ret;
mutex_lock(&inode->i_mutex);
- /* we wait first, since the writeback may change the inode */
+ /*
+ * we wait first, since the writeback may change the inode, also wait
+ * ordered range does a filemape_write_and_wait_range which is why we
+ * don't do it above like other file systems.
+ */
root->log_batch++;
- btrfs_wait_ordered_range(inode, 0, (u64)-1);
+ btrfs_wait_ordered_range(inode, start, end);
root->log_batch++;
/*
@@ -1523,7 +1539,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* syncing
*/
smp_mb();
- if (BTRFS_I(inode)->last_trans <=
+ if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
+ BTRFS_I(inode)->last_trans <=
root->fs_info->last_trans_committed) {
BTRFS_I(inode)->last_trans = 0;
mutex_unlock(&inode->i_mutex);
generated by cgit v1.2.3-70-g09d2 (git 2.51.2) at 2025-11-04 15:55:19 +0000