copied = btrfs_copy_from_user(pos, write_bytes, pages, i);
+ num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ reserve_bytes);
+ dirty_sectors = round_up(copied + sector_offset,
+ root->sectorsize);
+ dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ dirty_sectors);
+
/*
* if we have trouble faulting in the pages, fall
* back to one page at a time
if (copied == 0) {
force_page_uptodate = true;
+ dirty_sectors = 0;
dirty_pages = 0;
} else {
force_page_uptodate = false;
/*
* If we had a short copy we need to release the excess delaloc
* bytes we reserved. We need to increment outstanding_extents
- * because btrfs_delalloc_release_space will decrement it, but
+ * because btrfs_delalloc_release_space and
+ * btrfs_delalloc_release_metadata will decrement it, but
* we still have an outstanding extent for the chunk we actually
* managed to copy.
*/
- num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
- reserve_bytes);
- dirty_sectors = round_up(copied + sector_offset,
- root->sectorsize);
- dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
- dirty_sectors);
-
if (num_sectors > dirty_sectors) {
- release_bytes = (write_bytes - copied)
- & ~((u64)root->sectorsize - 1);
+ /*
+ * we round down because we don't want to count
+ * any partial blocks actually sent through the
+ * IO machines
+ */
+ release_bytes = round_down(release_bytes - copied,
+ root->sectorsize);
if (copied > 0) {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
return num_written ? num_written : ret;
}
-static ssize_t __btrfs_direct_write(struct kiocb *iocb,
- struct iov_iter *from,
- loff_t pos)
+static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
+ loff_t pos = iocb->ki_pos;
ssize_t written;
ssize_t written_buffered;
loff_t endbyte;
int err;
- written = generic_file_direct_write(iocb, from, pos);
+ written = generic_file_direct_write(iocb, from);
if (written < 0 || !iov_iter_count(from))
return written;
atomic_inc(&BTRFS_I(inode)->sync_writers);
if (iocb->ki_flags & IOCB_DIRECT) {
- num_written = __btrfs_direct_write(iocb, from, pos);
+ num_written = __btrfs_direct_write(iocb, from);
} else {
num_written = __btrfs_buffered_write(file, from, pos);
if (num_written > 0)
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->last_sub_trans = root->log_transid;
spin_unlock(&BTRFS_I(inode)->lock);
- if (num_written > 0) {
- err = generic_write_sync(file, pos, num_written);
- if (err < 0)
- num_written = err;
- }
+ if (num_written > 0)
+ num_written = generic_write_sync(iocb, num_written);
if (sync)
atomic_dec(&BTRFS_I(inode)->sync_writers);
BTRFS_I(inode)->last_trans
<= root->fs_info->last_trans_committed)) {
/*
- * We'v had everything committed since the last time we were
+ * We've had everything committed since the last time we were
* modified so clear this flag in case it was set for whatever
* reason, it's no longer relevant.
*/
/* Check the aligned pages after the first unaligned page,
* if offset != orig_start, which means the first unaligned page
- * including serveral following pages are already in holes,
+ * including several following pages are already in holes,
* the extra check can be skipped */
if (offset == orig_start) {
/* after truncate page, check hole again */
/*
* skip compression for a small file range(<=blocksize) that
- * isn't an inline extent, since it dosen't save disk space at all.
+ * isn't an inline extent, since it doesn't save disk space at all.
*/
if (total_compressed <= blocksize &&
(start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
{
WARN_ON((end & (PAGE_SIZE - 1)) == 0);
return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
- cached_state, GFP_NOFS);
+ cached_state);
}
/* see btrfs_writepage_start_hook for details on why this is required */
if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
- clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM,
- GFP_NOFS);
+ clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM);
return 0;
}
* and doesn't have an inode ref with the name "bar" anymore.
*
* Setting last_unlink_trans to last_trans is a pessimistic approach,
- * but it guarantees correctness at the expense of ocassional full
+ * but it guarantees correctness at the expense of occasional full
* transaction commits on fsync if our inode is a directory, or if our
* inode is not a directory, logging its parent unnecessarily.
*/
* be instantly completed which will give us extents that need
* to be truncated. If we fail to get an orphan inode down we
* could have left over extents that were never meant to live,
- * so we need to garuntee from this point on that everything
+ * so we need to guarantee from this point on that everything
* will be consistent.
*/
ret = btrfs_orphan_add(trans, inode);
}
/*
- * We can't just steal from the global reserve, we need tomake
+ * We can't just steal from the global reserve, we need to make
* sure there is room to do it, if not we need to commit and try
* again.
*/
cached_state);
/*
* We're concerned with the entire range that we're going to be
- * doing DIO to, so we need to make sure theres no ordered
+ * doing DIO to, so we need to make sure there's no ordered
* extents in this range.
*/
ordered = btrfs_lookup_ordered_range(inode, lockstart,
if (current->journal_info) {
/*
* Need to pull our outstanding extents and set journal_info to NULL so
- * that anything that needs to check if there's a transction doesn't get
+ * that anything that needs to check if there's a transaction doesn't get
* confused.
*/
dio_data = current->journal_info;
* decompress it, so there will be buffering required no matter what we
* do, so go ahead and fallback to buffered.
*
- * We return -ENOTBLK because thats what makes DIO go ahead and go back
+ * We return -ENOTBLK because that's what makes DIO go ahead and go back
* to buffered IO. Don't blame me, this is the price we pay for using
* the generic code.
*/
return retval;
}
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_dio_data dio_data = { 0 };
+ loff_t offset = iocb->ki_pos;
size_t count = 0;
int flags = 0;
bool wakeup = true;
ret = __blockdev_direct_IO(iocb, inode,
BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iter, offset, btrfs_get_blocks_direct, NULL,
+ iter, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (iov_iter_rw(iter) == WRITE) {
current->journal_info = NULL;
return ret;
/*
- * Yes ladies and gentelment, this is indeed ugly. The fact is we have
+ * Yes ladies and gentlemen, this is indeed ugly. The fact is we have
* 3 things going on here
*
* 1) We need to reserve space for our orphan item and the space to
* space reserved in case it uses space during the truncate (thank you
* very much snapshotting).
*
- * And we need these to all be seperate. The fact is we can use alot of
+ * And we need these to all be separate. The fact is we can use a lot of
* space doing the truncate, and we have no earthly idea how much space
- * we will use, so we need the truncate reservation to be seperate so it
+ * we will use, so we need the truncate reservation to be separate so it
* doesn't end up using space reserved for updating the inode or
* removing the orphan item. We also need to be able to stop the
* transaction and start a new one, which means we need to be able to
* update the inode several times, and we have no idea of knowing how
* many times that will be, so we can't just reserve 1 item for the
- * entirety of the opration, so that has to be done seperately as well.
+ * entirety of the operation, so that has to be done separately as well.
* Then there is the orphan item, which does indeed need to be held on
* to for the whole operation, and we need nobody to touch this reserved
* space except the orphan code.
.symlink = btrfs_symlink,
.setattr = btrfs_setattr,
.mknod = btrfs_mknod,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
static const struct inode_operations btrfs_file_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = btrfs_permission,
.fiemap = btrfs_fiemap,
.get_acl = btrfs_get_acl,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.update_time = btrfs_update_time,
};
}
} else {
/*
- * Revert back under same assuptions as above
+ * Revert back under same assumptions as above
*/
if (S_ISREG(mode)) {
if (inode->i_size == 0)
/*
* Don't create subvolume whose level is not zero. Or qgroup will be
- * screwed up since it assume subvolme qgroup's level to be 0.
+ * screwed up since it assumes subvolume qgroup's level to be 0.
*/
if (btrfs_qgroup_level(objectid)) {
ret = -ENOSPC;
* a. be owner of dir, or
* b. be owner of victim, or
* c. have CAP_FOWNER capability
- * 6. If the victim is append-only or immutable we can't do antyhing with
+ * 6. If the victim is append-only or immutable we can't do anything with
* links pointing to it.
* 7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
* 8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
struct dentry *dentry;
int error;
- error = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- if (error == -EINTR)
- return error;
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ // XXX: should've been
+ // mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+ // if (error == -EINTR)
+ // return error;
dentry = lookup_one_len(name, parent->dentry, namelen);
error = PTR_ERR(dentry);
set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
- &cached_state, GFP_NOFS);
+ &cached_state);
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
page_start, page_end - 1, &cached_state,
goto out;
- err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
- if (err == -EINTR)
- goto out_drop_write;
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ // XXX: should've been
+ // err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+ // if (err == -EINTR)
+ // goto out_drop_write;
dentry = lookup_one_len(vol_args->name, parent, namelen);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
dput(dentry);
out_unlock_dir:
inode_unlock(dir);
-out_drop_write:
+//out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
}
/*
- * mut. excl. ops lock is locked. Three possibilites:
+ * mut. excl. ops lock is locked. Three possibilities:
* (1) some other op is running
* (2) balance is running
* (3) balance is paused -- special case (think resume)
ret = btrfs_sync_fs(file_inode(file)->i_sb, 1);
/*
* The transaction thread may want to do more work,
- * namely it pokes the cleaner ktread that will start
+ * namely it pokes the cleaner kthread that will start
* processing uncleaned subvols.
*/
wake_up_process(root->fs_info->transaction_kthread);
break;
/* for regular files, make sure corresponding
- * orhpan item exist. extents past the new EOF
+ * orphan item exist. extents past the new EOF
* will be truncated later by orphan cleanup.
*/
if (S_ISREG(mode)) {
break;
clear_extent_bits(&log->dirty_log_pages, start, end,
- EXTENT_DIRTY | EXTENT_NEW, GFP_NOFS);
+ EXTENT_DIRTY | EXTENT_NEW);
}
/*
* the actual unlink operation, so if we do this check before a concurrent task
* sets last_unlink_trans it means we've logged a consistent version/state of
* all the inode items, otherwise we are not sure and must do a transaction
- * commit (the concurrent task migth have only updated last_unlink_trans before
+ * commit (the concurrent task might have only updated last_unlink_trans before
* we logged the inode or it might have also done the unlink).
*/
static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
goto out;
if (!S_ISDIR(inode->i_mode)) {
- if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
goto out;
inode = d_inode(parent);
}
while (1) {
/*
* If we are logging a directory then we start with our inode,
- * not our parents inode, so we need to skipp setting the
+ * not our parent's inode, so we need to skip setting the
* logged_trans so that further down in the log code we don't
* think this inode has already been logged.
*/
break;
}
- if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
break;
if (IS_ROOT(parent))
log_dentries = true;
/*
- * On unlink we must make sure all our current and old parent directores
+ * On unlink we must make sure all our current and old parent directory
* inodes are fully logged. This is to prevent leaving dangling
* directory index entries in directories that were our parents but are
* not anymore. Not doing this results in old parent directory being
}
while (1) {
- if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+ if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
break;
inode = d_inode(parent);
#include <linux/slab.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
-#include <linux/random.h>
#include <linux/iocontext.h>
#include <linux/capability.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/semaphore.h>
+#include <linux/uuid.h>
#include <asm/div64.h>
#include "ctree.h"
#include "extent_map.h"
}
/*
- * strore the expected generation for seed devices in device items.
+ * Store the expected generation for seed devices in device items.
*/
static int btrfs_finish_sprout(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
} else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) {
/*
* Same logic as the 'limit' filter; the minimum cannot be
- * determined here because we do not have the global informatoin
+ * determined here because we do not have the global information
* about the count of all chunks that satisfy the filters.
*/
if (bargs->limit_max == 0)
{
atomic_inc(&bbio->error);
if (atomic_dec_and_test(&bbio->stripes_pending)) {
- /* Shoud be the original bio. */
+ /* Should be the original bio. */
WARN_ON(bio != bbio->orig_bio);
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
set_extent_buffer_uptodate(sb);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
/*
- * The sb extent buffer is artifical and just used to read the system array.
+ * The sb extent buffer is artificial and just used to read the system array.
* set_extent_buffer_uptodate() call does not properly mark all it's
* pages up-to-date when the page is larger: extent does not cover the
* whole page and consequently check_page_uptodate does not find all
sb_array_offset += len;
cur_offset += len;
}
- free_extent_buffer(sb);
+ free_extent_buffer_stale(sb);
return ret;
out_short_read:
printk(KERN_ERR "BTRFS: sys_array too short to read %u bytes at offset %u\n",
len, cur_offset);
- free_extent_buffer(sb);
+ free_extent_buffer_stale(sb);
return -EIO;
}