#include <linux/fs.h>
#include <linux/quotaops.h>
+#include <linux/slab.h>
#include "ext4_jbd2.h"
#include "ext4_extents.h"
#include "ext4.h"
mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
struct ext4_extent **extent)
{
+ struct ext4_extent_header *eh;
int ppos, leaf_ppos = path->p_depth;
ppos = leaf_ppos;
if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
/* leaf block */
*extent = ++path[ppos].p_ext;
+ path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
return 0;
}
/* index block */
path[ppos].p_idx++;
- path[ppos].p_block = idx_pblock(path[ppos].p_idx);
+ path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
if (path[ppos+1].p_bh)
brelse(path[ppos+1].p_bh);
path[ppos+1].p_bh =
path[cur_ppos].p_idx =
EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
path[cur_ppos].p_block =
- idx_pblock(path[cur_ppos].p_idx);
+ ext4_idx_pblock(path[cur_ppos].p_idx);
if (path[cur_ppos+1].p_bh)
brelse(path[cur_ppos+1].p_bh);
path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
ext_block_hdr(path[cur_ppos+1].p_bh);
}
+ path[leaf_ppos].p_ext = *extent = NULL;
+
+ eh = path[leaf_ppos].p_hdr;
+ if (le16_to_cpu(eh->eh_entries) == 0)
+ /* empty leaf is found */
+ return -ENODATA;
+
/* leaf block */
path[leaf_ppos].p_ext = *extent =
EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
+ path[leaf_ppos].p_block =
+ ext4_ext_pblock(path[leaf_ppos].p_ext);
return 0;
}
}
*/
static int
mext_check_null_inode(struct inode *inode1, struct inode *inode2,
- const char *function)
+ const char *function, unsigned int line)
{
int ret = 0;
if (inode1 == NULL) {
- ext4_error(inode2->i_sb, function,
+ __ext4_error(inode2->i_sb, function, line,
"Both inodes should not be NULL: "
"inode1 NULL inode2 %lu", inode2->i_ino);
ret = -EIO;
} else if (inode2 == NULL) {
- ext4_error(inode1->i_sb, function,
+ __ext4_error(inode1->i_sb, function, line,
"Both inodes should not be NULL: "
"inode1 %lu inode2 NULL", inode1->i_ino);
ret = -EIO;
}
/**
- * mext_double_down_read - Acquire two inodes' read semaphore
- *
- * @orig_inode: original inode structure
- * @donor_inode: donor inode structure
- * Acquire read semaphore of the two inodes (orig and donor) by i_ino order.
- */
-static void
-mext_double_down_read(struct inode *orig_inode, struct inode *donor_inode)
-{
- struct inode *first = orig_inode, *second = donor_inode;
-
- /*
- * Use the inode number to provide the stable locking order instead
- * of its address, because the C language doesn't guarantee you can
- * compare pointers that don't come from the same array.
- */
- if (donor_inode->i_ino < orig_inode->i_ino) {
- first = donor_inode;
- second = orig_inode;
- }
-
- down_read(&EXT4_I(first)->i_data_sem);
- down_read(&EXT4_I(second)->i_data_sem);
-}
-
-/**
- * mext_double_down_write - Acquire two inodes' write semaphore
+ * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem
*
* @orig_inode: original inode structure
* @donor_inode: donor inode structure
- * Acquire write semaphore of the two inodes (orig and donor) by i_ino order.
+ * Acquire write lock of i_data_sem of the two inodes (orig and donor) by
+ * i_ino order.
*/
static void
-mext_double_down_write(struct inode *orig_inode, struct inode *donor_inode)
+double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
{
struct inode *first = orig_inode, *second = donor_inode;
}
down_write(&EXT4_I(first)->i_data_sem);
- down_write(&EXT4_I(second)->i_data_sem);
-}
-
-/**
- * mext_double_up_read - Release two inodes' read semaphore
- *
- * @orig_inode: original inode structure to be released its lock first
- * @donor_inode: donor inode structure to be released its lock second
- * Release read semaphore of two inodes (orig and donor).
- */
-static void
-mext_double_up_read(struct inode *orig_inode, struct inode *donor_inode)
-{
- up_read(&EXT4_I(orig_inode)->i_data_sem);
- up_read(&EXT4_I(donor_inode)->i_data_sem);
+ down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING);
}
/**
- * mext_double_up_write - Release two inodes' write semaphore
+ * double_up_write_data_sem - Release two inodes' write lock of i_data_sem
*
* @orig_inode: original inode structure to be released its lock first
* @donor_inode: donor inode structure to be released its lock second
- * Release write semaphore of two inodes (orig and donor).
+ * Release write lock of i_data_sem of two inodes (orig and donor).
*/
static void
-mext_double_up_write(struct inode *orig_inode, struct inode *donor_inode)
+double_up_write_data_sem(struct inode *orig_inode, struct inode *donor_inode)
{
up_write(&EXT4_I(orig_inode)->i_data_sem);
up_write(&EXT4_I(donor_inode)->i_data_sem);
*/
o_end->ee_block = end_ext->ee_block;
o_end->ee_len = end_ext->ee_len;
- ext4_ext_store_pblock(o_end, ext_pblock(end_ext));
+ ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
}
o_start->ee_len = start_ext->ee_len;
+ eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (start_ext->ee_len && new_ext->ee_len &&
* orig |------------------------------|
*/
o_start->ee_len = start_ext->ee_len;
+ eblock = le32_to_cpu(start_ext->ee_block);
new_flag = 1;
} else if (!start_ext->ee_len && new_ext->ee_len &&
*/
o_end->ee_block = end_ext->ee_block;
o_end->ee_len = end_ext->ee_len;
- ext4_ext_store_pblock(o_end, ext_pblock(end_ext));
+ ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
/*
* Set 0 to the extent block if new_ext was
/* Insert new entry */
if (new_ext->ee_len) {
o_start[i] = *new_ext;
- ext4_ext_store_pblock(&o_start[i++], ext_pblock(new_ext));
+ ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
}
/* Insert end entry */
struct ext4_extent *oext, *o_start, *o_end, *prev_ext;
struct ext4_extent new_ext, start_ext, end_ext;
ext4_lblk_t new_ext_end;
- ext4_fsblk_t new_phys_end;
int oext_alen, new_ext_alen, end_ext_alen;
int depth = ext_depth(orig_inode);
int ret;
+ start_ext.ee_block = end_ext.ee_block = 0;
o_start = o_end = oext = orig_path[depth].p_ext;
oext_alen = ext4_ext_get_actual_len(oext);
start_ext.ee_len = end_ext.ee_len = 0;
new_ext.ee_block = cpu_to_le32(*from);
- ext4_ext_store_pblock(&new_ext, ext_pblock(dext));
+ ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
new_ext.ee_len = dext->ee_len;
new_ext_alen = ext4_ext_get_actual_len(&new_ext);
new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
- new_phys_end = ext_pblock(&new_ext) + new_ext_alen - 1;
/*
* Case: original extent is first
le32_to_cpu(oext->ee_block) + oext_alen) {
start_ext.ee_len = cpu_to_le16(le32_to_cpu(new_ext.ee_block) -
le32_to_cpu(oext->ee_block));
+ start_ext.ee_block = oext->ee_block;
copy_extent_status(oext, &start_ext);
} else if (oext > EXT_FIRST_EXTENT(orig_path[depth].p_hdr)) {
prev_ext = oext - 1;
start_ext.ee_len = cpu_to_le16(
ext4_ext_get_actual_len(prev_ext) +
new_ext_alen);
+ start_ext.ee_block = oext->ee_block;
copy_extent_status(prev_ext, &start_ext);
new_ext.ee_len = 0;
}
* new_ext |-------|
*/
if (le32_to_cpu(oext->ee_block) + oext_alen - 1 < new_ext_end) {
- ext4_error(orig_inode->i_sb, __func__,
+ EXT4_ERROR_INODE(orig_inode,
"new_ext_end(%u) should be less than or equal to "
"oext->ee_block(%u) + oext_alen(%d) - 1",
new_ext_end, le32_to_cpu(oext->ee_block),
copy_extent_status(oext, &end_ext);
end_ext_alen = ext4_ext_get_actual_len(&end_ext);
ext4_ext_store_pblock(&end_ext,
- (ext_pblock(o_end) + oext_alen - end_ext_alen));
+ (ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
end_ext.ee_block =
cpu_to_le32(le32_to_cpu(o_end->ee_block) +
oext_alen - end_ext_alen);
* @tmp_oext: the extent that will belong to the donor inode
* @orig_off: block offset of original inode
* @donor_off: block offset of donor inode
- * @max_count: the maximun length of extents
+ * @max_count: the maximum length of extents
*
* Return 0 on success, or a negative error value on failure.
*/
/* When tmp_dext is too large, pick up the target range. */
diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
- ext4_ext_store_pblock(tmp_dext, ext_pblock(tmp_dext) + diff);
+ ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
tmp_dext->ee_block =
cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff);
tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff);
tmp_dext->ee_len = cpu_to_le16(max_count);
orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
- ext4_ext_store_pblock(tmp_oext, ext_pblock(tmp_oext) + orig_diff);
+ ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
/* Adjust extent length if donor extent is larger than orig */
if (ext4_ext_get_actual_len(tmp_dext) >
int replaced_count = 0;
int dext_alen;
- mext_double_down_write(orig_inode, donor_inode);
+ /* Protect extent trees against block allocations via delalloc */
+ double_down_write_data_sem(orig_inode, donor_inode);
/* Get the original extent for the block "orig_off" */
*err = get_ext_path(orig_inode, orig_off, &orig_path);
while (1) {
/* The extent for donor must be found. */
if (!dext) {
- ext4_error(donor_inode->i_sb, __func__,
+ EXT4_ERROR_INODE(donor_inode,
"The extent for donor must be found");
*err = -EIO;
goto out;
} else if (donor_off != le32_to_cpu(tmp_dext.ee_block)) {
- ext4_error(donor_inode->i_sb, __func__,
+ EXT4_ERROR_INODE(donor_inode,
"Donor offset(%u) and the first block of donor "
"extent(%u) should be equal",
donor_off,
kfree(donor_path);
}
- mext_double_up_write(orig_inode, donor_inode);
+ ext4_ext_invalidate_cache(orig_inode);
+ ext4_ext_invalidate_cache(donor_inode);
+
+ double_up_write_data_sem(orig_inode, donor_inode);
+
return replaced_count;
}
replaced_count = mext_replace_branches(handle, orig_inode,
donor_inode, orig_blk_offset,
block_len_in_page, err);
-
- /* Clear the inode cache not to refer to the old data */
- ext4_ext_invalidate_cache(orig_inode);
- ext4_ext_invalidate_cache(donor_inode);
goto out2;
}
goto out;
}
- /* Clear the inode cache not to refer to the old data */
- ext4_ext_invalidate_cache(orig_inode);
- ext4_ext_invalidate_cache(donor_inode);
-
if (!page_has_buffers(page))
create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0);
}
/**
- * mext_check_argumants - Check whether move extent can be done
+ * mext_check_arguments - Check whether move extent can be done
*
* @orig_inode: original inode
* @donor_inode: donor inode
* @orig_start: logical start offset in block for orig
* @donor_start: logical start offset in block for donor
* @len: the number of blocks to be moved
- * @moved_len: moved block length
*
* Check the arguments of ext4_move_extents() whether the files can be
* exchanged with each other.
*/
static int
mext_check_arguments(struct inode *orig_inode,
- struct inode *donor_inode, __u64 orig_start,
- __u64 donor_start, __u64 *len, __u64 moved_len)
+ struct inode *donor_inode, __u64 orig_start,
+ __u64 donor_start, __u64 *len)
{
ext4_lblk_t orig_blocks, donor_blocks;
unsigned int blkbits = orig_inode->i_blkbits;
unsigned int blocksize = 1 << blkbits;
- /* Regular file check */
- if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
- ext4_debug("ext4 move extent: The argument files should be "
- "regular file [ino:orig %lu, donor %lu]\n",
- orig_inode->i_ino, donor_inode->i_ino);
+ if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
+ ext4_debug("ext4 move extent: suid or sgid is set"
+ " to donor file [ino:orig %lu, donor %lu]\n",
+ orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
+ if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode))
+ return -EPERM;
+
/* Ext4 move extent does not support swapfile */
if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
ext4_debug("ext4 move extent: The argument files should "
}
/* Ext4 move extent supports only extent based file */
- if (!(EXT4_I(orig_inode)->i_flags & EXT4_EXTENTS_FL)) {
+ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: orig file is not extents "
"based file [ino:orig %lu]\n", orig_inode->i_ino);
return -EOPNOTSUPP;
- } else if (!(EXT4_I(donor_inode)->i_flags & EXT4_EXTENTS_FL)) {
+ } else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: donor file is not extents "
"based file [ino:donor %lu]\n", donor_inode->i_ino);
return -EOPNOTSUPP;
return -EINVAL;
}
- if (moved_len) {
- ext4_debug("ext4 move extent: moved_len should be 0 "
- "[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
- donor_inode->i_ino);
- return -EINVAL;
- }
-
- if ((orig_start > EXT_MAX_BLOCK) ||
- (donor_start > EXT_MAX_BLOCK) ||
- (*len > EXT_MAX_BLOCK) ||
- (orig_start + *len > EXT_MAX_BLOCK)) {
+ if ((orig_start >= EXT_MAX_BLOCKS) ||
+ (donor_start >= EXT_MAX_BLOCKS) ||
+ (*len > EXT_MAX_BLOCKS) ||
+ (orig_start + *len >= EXT_MAX_BLOCKS)) {
ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
- "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCK,
+ "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
}
if (!*len) {
- ext4_debug("ext4 move extent: len shoudld not be 0 "
+ ext4_debug("ext4 move extent: len should not be 0 "
"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
donor_inode->i_ino);
return -EINVAL;
BUG_ON(inode1 == NULL && inode2 == NULL);
- ret = mext_check_null_inode(inode1, inode2, __func__);
+ ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
if (ret < 0)
goto out;
BUG_ON(inode1 == NULL && inode2 == NULL);
- ret = mext_check_null_inode(inode1, inode2, __func__);
+ ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__);
if (ret < 0)
goto out;
return -EINVAL;
}
- /* protect orig and donor against a truncate */
+ /* Regular file check */
+ if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
+ ext4_debug("ext4 move extent: The argument files should be "
+ "regular file [ino:orig %lu, donor %lu]\n",
+ orig_inode->i_ino, donor_inode->i_ino);
+ return -EINVAL;
+ }
+
+ /* Protect orig and donor inodes against a truncate */
ret1 = mext_inode_double_lock(orig_inode, donor_inode);
if (ret1 < 0)
return ret1;
- mext_double_down_read(orig_inode, donor_inode);
+ /* Protect extent tree against block allocations via delalloc */
+ double_down_write_data_sem(orig_inode, donor_inode);
/* Check the filesystem environment whether move_extent can be done */
ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start,
- donor_start, &len, *moved_len);
- mext_double_up_read(orig_inode, donor_inode);
+ donor_start, &len);
if (ret1)
goto out;
seq_start = le32_to_cpu(ext_cur->ee_block);
rest_blocks = seq_blocks;
- /* Discard preallocations of two inodes */
- down_write(&EXT4_I(orig_inode)->i_data_sem);
- ext4_discard_preallocations(orig_inode);
- up_write(&EXT4_I(orig_inode)->i_data_sem);
-
- down_write(&EXT4_I(donor_inode)->i_data_sem);
- ext4_discard_preallocations(donor_inode);
- up_write(&EXT4_I(donor_inode)->i_data_sem);
+ /*
+ * Up semaphore to avoid following problems:
+ * a. transaction deadlock among ext4_journal_start,
+ * ->write_begin via pagefault, and jbd2_journal_commit
+ * b. racing with ->readpage, ->write_begin, and ext4_get_block
+ * in move_extent_per_page
+ */
+ double_up_write_data_sem(orig_inode, donor_inode);
while (orig_page_offset <= seq_end_page) {
/* Count how many blocks we have exchanged */
*moved_len += block_len_in_page;
if (ret1 < 0)
- goto out;
+ break;
if (*moved_len > len) {
- ext4_error(orig_inode->i_sb, __func__,
+ EXT4_ERROR_INODE(orig_inode,
"We replaced blocks too much! "
"sum of replaced: %llu requested: %llu",
*moved_len, len);
ret1 = -EIO;
- goto out;
+ break;
}
orig_page_offset++;
block_len_in_page = rest_blocks;
}
+ double_down_write_data_sem(orig_inode, donor_inode);
+ if (ret1 < 0)
+ break;
+
/* Decrease buffer counter */
if (holecheck_path)
ext4_ext_drop_refs(holecheck_path);
}
out:
+ if (*moved_len) {
+ ext4_discard_preallocations(orig_inode);
+ ext4_discard_preallocations(donor_inode);
+ }
+
if (orig_path) {
ext4_ext_drop_refs(orig_path);
kfree(orig_path);
ext4_ext_drop_refs(holecheck_path);
kfree(holecheck_path);
}
-
+ double_up_write_data_sem(orig_inode, donor_inode);
ret2 = mext_inode_double_unlock(orig_inode, donor_inode);
if (ret1)