xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Browse Source 
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (47 commits)
  ext4: Fix potential fiemap deadlock (mmap_sem vs. i_data_sem)
  ext4: Do not override ext2 or ext3 if built they are built as modules
  jbd2: Export jbd2_log_start_commit to fix ext4 build
  ext4: Fix insufficient checks in EXT4_IOC_MOVE_EXT
  ext4: Wait for proper transaction commit on fsync
  ext4: fix incorrect block reservation on quota transfer.
  ext4: quota macros cleanup
  ext4: ext4_get_reserved_space() must return bytes instead of blocks
  ext4: remove blocks from inode prealloc list on failure
  ext4: wait for log to commit when umounting
  ext4: Avoid data / filesystem corruption when write fails to copy data
  ext4: Use ext4 file system driver for ext2/ext3 file system mounts
  ext4: Return the PTR_ERR of the correct pointer in setup_new_group_blocks()
  jbd2: Add ENOMEM checking in and for jbd2_journal_write_metadata_buffer()
  ext4: remove unused parameter wbc from __ext4_journalled_writepage()
  ext4: remove encountered_congestion trace
  ext4: move_extent_per_page() cleanup
  ext4: initialize moved_len before calling ext4_move_extents()
  ext4: Fix double-free of blocks with EXT4_IOC_MOVE_EXT
  ext4: use ext4_data_block_valid() in ext4_free_blocks()
  ...
This commit is contained in:
Linus Torvalds
2009-12-10 09:33:29 -08:00
parent a5eba3f66f fab3a549e2
commit 4515c3069d
21 changed files with 678 additions and 515 deletions
Download Patch File Download Diff File Expand all files Collapse all files

193
fs/ext4/inode.c
View File

@@ -70,58 +70,6 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
/*
* The ext4 forget function must perform a revoke if we are freeing data
* which has been journaled. Metadata (eg. indirect blocks) must be
* revoked in all cases.
*
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
*
* If the handle isn't valid we're not journaling, but we still need to
* call into ext4_journal_revoke() to put the buffer head.
*/
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr)
{
int err;
might_sleep();
BUFFER_TRACE(bh, "enter");
jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
"data mode %x\n",
bh, is_metadata, inode->i_mode,
test_opt(inode->i_sb, DATA_FLAGS));
/* Never use the revoke function if we are doing full data
* journaling: there is no need to, and a V1 superblock won't
* support it. Otherwise, only skip the revoke on un-journaled
* data blocks. */
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
(!is_metadata && !ext4_should_journal_data(inode))) {
if (bh) {
BUFFER_TRACE(bh, "call jbd2_journal_forget");
return ext4_journal_forget(handle, bh);
}
return 0;
}
/*
* data!=journal && (is_metadata || should_journal_data(inode))
*/
BUFFER_TRACE(bh, "call ext4_journal_revoke");
err = ext4_journal_revoke(handle, blocknr, bh);
if (err)
ext4_abort(inode->i_sb, __func__,
"error %d when attempting revoke", err);
BUFFER_TRACE(bh, "exit");
return err;
}
/*
* Work out how many blocks we need to proceed with the next chunk of a
* truncate transaction.
@@ -721,7 +669,7 @@ allocated:
return ret;
failed_out:
for (i = 0; i < index; i++)
ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
return ret;
}
@@ -817,14 +765,20 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
return err;
failed:
/* Allocation failed, free what we already allocated */
ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
for (i = 1; i <= n ; i++) {
BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
ext4_journal_forget(handle, branch[i].bh);
/*
* branch[i].bh is newly allocated, so there is no
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
*/
ext4_free_blocks(handle, inode, 0, new_blocks[i], 1,
EXT4_FREE_BLOCKS_FORGET);
}
for (i = 0; i < indirect_blks; i++)
ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
for (i = n+1; i < indirect_blks; i++)
ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0);
return err;
}
@@ -903,12 +857,16 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
err_out:
for (i = 1; i <= num; i++) {
BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget");
ext4_journal_forget(handle, where[i].bh);
ext4_free_blocks(handle, inode,
le32_to_cpu(where[i-1].key), 1, 0);
/*
* branch[i].bh is newly allocated, so there is no
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
*/
ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
EXT4_FREE_BLOCKS_FORGET);
}
ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks, 0);
ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key),
blks, 0);
return err;
}
@@ -1021,10 +979,12 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
if (!err)
err = ext4_splice_branch(handle, inode, iblock,
partial, indirect_blks, count);
else
if (err)
goto cleanup;
set_buffer_new(bh_result);
ext4_update_inode_fsync_trans(handle, inode, 1);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
if (count > blocks_to_boundary)
@@ -1052,7 +1012,7 @@ qsize_t ext4_get_reserved_space(struct inode *inode)
EXT4_I(inode)->i_reserved_meta_blocks;
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
return total;
return (total << inode->i_blkbits);
}
/*
* Calculate the number of metadata blocks need to reserve
@@ -1534,6 +1494,16 @@ static int do_journal_get_write_access(handle_t *handle,
return ext4_journal_get_write_access(handle, bh);
}
/*
* Truncate blocks that were not used by write. We have to truncate the
* pagecache as well so that corresponding buffers get properly unmapped.
*/
static void ext4_truncate_failed_write(struct inode *inode)
{
truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
}
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -1599,7 +1569,7 @@ retry:
ext4_journal_stop(handle);
if (pos + len > inode->i_size) {
ext4_truncate(inode);
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
@@ -1709,7 +1679,7 @@ static int ext4_ordered_write_end(struct file *file,
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate(inode);
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
@@ -1751,7 +1721,7 @@ static int ext4_writeback_write_end(struct file *file,
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate(inode);
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
@@ -1814,7 +1784,7 @@ static int ext4_journalled_write_end(struct file *file,
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate(inode);
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
@@ -2600,7 +2570,6 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
}
static int __ext4_journalled_writepage(struct page *page,
struct writeback_control *wbc,
unsigned int len)
{
struct address_space *mapping = page->mapping;
@@ -2758,7 +2727,7 @@ static int ext4_writepage(struct page *page,
* doesn't seem much point in redirtying the page here.
*/
ClearPageChecked(page);
return __ext4_journalled_writepage(page, wbc, len);
return __ext4_journalled_writepage(page, len);
}
if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
@@ -2788,7 +2757,7 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
* number of contiguous block. So we will limit
* number of contiguous block to a sane value
*/
if (!(inode->i_flags & EXT4_EXTENTS_FL) &&
if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) &&
(max_blocks > EXT4_MAX_TRANS_DATA))
max_blocks = EXT4_MAX_TRANS_DATA;
@@ -3091,7 +3060,7 @@ retry:
* i_size_read because we hold i_mutex.
*/
if (pos + len > inode->i_size)
ext4_truncate(inode);
ext4_truncate_failed_write(inode);
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -4120,6 +4089,11 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
__le32 *last)
{
__le32 *p;
int flags = EXT4_FREE_BLOCKS_FORGET;
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
flags |= EXT4_FREE_BLOCKS_METADATA;
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
@@ -4134,27 +4108,10 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
}
}
/*
* Any buffers which are on the journal will be in memory. We
* find them on the hash table so jbd2_journal_revoke() will
* run jbd2_journal_forget() on them. We've already detached
* each block from the file, so bforget() in
* jbd2_journal_forget() should be safe.
*
* AKPM: turn on bforget in jbd2_journal_forget()!!!
*/
for (p = first; p < last; p++) {
u32 nr = le32_to_cpu(*p);
if (nr) {
struct buffer_head *tbh;
for (p = first; p < last; p++)
*p = 0;
*p = 0;
tbh = sb_find_get_block(inode->i_sb, nr);
ext4_forget(handle, 0, inode, tbh, nr);
}
}
ext4_free_blocks(handle, inode, block_to_free, count, 0);
ext4_free_blocks(handle, inode, 0, block_to_free, count, flags);
}
/**
@@ -4342,7 +4299,8 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
blocks_for_truncate(inode));
}
ext4_free_blocks(handle, inode, nr, 1, 1);
ext4_free_blocks(handle, inode, 0, nr, 1,
EXT4_FREE_BLOCKS_METADATA);
if (parent_bh) {
/*
@@ -4781,8 +4739,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
struct buffer_head *bh;
struct inode *inode;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
int block;
@@ -4793,11 +4751,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
return inode;
ei = EXT4_I(inode);
iloc.bh = 0;
ret = __ext4_get_inode_loc(inode, &iloc, 0);
if (ret < 0)
goto bad_inode;
bh = iloc.bh;
raw_inode = ext4_raw_inode(&iloc);
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
@@ -4820,7 +4778,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
if (inode->i_mode == 0 ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
/* this inode is deleted */
brelse(bh);
ret = -ESTALE;
goto bad_inode;
}
@@ -4848,11 +4805,35 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
/*
* Set transaction id's of transactions that have to be committed
* to finish f[data]sync. We set them to currently running transaction
* as we cannot be sure that the inode or some of its metadata isn't
* part of the transaction - the inode could have been reclaimed and
* now it is reread from disk.
*/
if (journal) {
transaction_t *transaction;
tid_t tid;
spin_lock(&journal->j_state_lock);
if (journal->j_running_transaction)
transaction = journal->j_running_transaction;
else
transaction = journal->j_committing_transaction;
if (transaction)
tid = transaction->t_tid;
else
tid = journal->j_commit_sequence;
spin_unlock(&journal->j_state_lock);
ei->i_sync_tid = tid;
ei->i_datasync_tid = tid;
}
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT4_INODE_SIZE(inode->i_sb)) {
brelse(bh);
ret = -EIO;
goto bad_inode;
}
@@ -4884,10 +4865,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ret = 0;
if (ei->i_file_acl &&
((ei->i_file_acl <
(le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
EXT4_SB(sb)->s_gdb_count)) ||
(ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) {
!ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
ext4_error(sb, __func__,
"bad extended attribute block %llu in inode #%lu",
ei->i_file_acl, inode->i_ino);
@@ -4905,10 +4883,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
/* Validate block references which are part of inode */
ret = ext4_check_inode_blockref(inode);
}
if (ret) {
brelse(bh);
if (ret)
goto bad_inode;
}
if (S_ISREG(inode->i_mode)) {
inode->i_op = &ext4_file_inode_operations;
@@ -4936,7 +4912,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
} else {
brelse(bh);
ret = -EIO;
ext4_error(inode->i_sb, __func__,
"bogus i_mode (%o) for inode=%lu",
@@ -4949,6 +4924,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
return inode;
bad_inode:
brelse(iloc.bh);
iget_failed(inode);
return ERR_PTR(ret);
}
@@ -5108,6 +5084,7 @@ static int ext4_do_update_inode(handle_t *handle,
err = rc;
ei->i_state &= ~EXT4_STATE_NEW;
ext4_update_inode_fsync_trans(handle, inode, 0);
out_brelse:
brelse(bh);
ext4_std_error(inode->i_sb, err);
@@ -5227,8 +5204,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+
EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3);
handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;