#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
+#include <linux/quotaops.h>
#define MLOG_MASK_PREFIX ML_NAMEI
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "alloc.h"
+#include "blockcheck.h"
#include "dir.h"
#include "dlmglue.h"
#include "extent_map.h"
struct buffer_head **new_bh);
/*
+ * These are distinct checks because future versions of the file system will
+ * want to have a trailing dirent structure independent of indexing.
+ */
+static int ocfs2_dir_has_trailer(struct inode *dir)
+{
+ if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ return 0;
+
+ return ocfs2_meta_ecc(OCFS2_SB(dir->i_sb));
+}
+
+static int ocfs2_supports_dir_trailer(struct ocfs2_super *osb)
+{
+ return ocfs2_meta_ecc(osb);
+}
+
+static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb)
+{
+ return sb->s_blocksize - sizeof(struct ocfs2_dir_block_trailer);
+}
+
+#define ocfs2_trailer_from_bh(_bh, _sb) ((struct ocfs2_dir_block_trailer *) ((_bh)->b_data + ocfs2_dir_trailer_blk_off((_sb))))
+
+/* XXX ocfs2_block_dqtrailer() is similar but not quite - can we make
+ * them more consistent? */
+struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize,
+ void *data)
+{
+ char *p = data;
+
+ p += blocksize - sizeof(struct ocfs2_dir_block_trailer);
+ return (struct ocfs2_dir_block_trailer *)p;
+}
+
+/*
+ * XXX: This is executed once on every dirent. We should consider optimizing
+ * it.
+ */
+static int ocfs2_skip_dir_trailer(struct inode *dir,
+ struct ocfs2_dir_entry *de,
+ unsigned long offset,
+ unsigned long blklen)
+{
+ unsigned long toff = blklen - sizeof(struct ocfs2_dir_block_trailer);
+
+ if (!ocfs2_dir_has_trailer(dir))
+ return 0;
+
+ if (offset != toff)
+ return 0;
+
+ return 1;
+}
+
+static void ocfs2_init_dir_trailer(struct inode *inode,
+ struct buffer_head *bh)
+{
+ struct ocfs2_dir_block_trailer *trailer;
+
+ trailer = ocfs2_trailer_from_bh(bh, inode->i_sb);
+ strcpy(trailer->db_signature, OCFS2_DIR_TRAILER_SIGNATURE);
+ trailer->db_compat_rec_len =
+ cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer));
+ trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno);
+ trailer->db_blkno = cpu_to_le64(bh->b_blocknr);
+}
+
+/*
* bh passed here can be an inode block or a dir data block, depending
* on the inode inline data flag.
*/
struct ocfs2_dinode *di;
struct ocfs2_inline_data *data;
- ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
- &di_bh, OCFS2_BH_CACHED, dir);
+ ret = ocfs2_read_inode_block(dir, &di_bh);
if (ret) {
mlog_errno(ret);
goto out;
return NULL;
}
-struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen,
- struct inode *dir,
- struct ocfs2_dir_entry **res_dir)
+static int ocfs2_validate_dir_block(struct super_block *sb,
+ struct buffer_head *bh)
+{
+ int rc;
+ struct ocfs2_dir_block_trailer *trailer =
+ ocfs2_trailer_from_bh(bh, sb);
+
+
+ /*
+ * We don't validate dirents here, that's handled
+ * in-place when the code walks them.
+ */
+ mlog(0, "Validating dirblock %llu\n",
+ (unsigned long long)bh->b_blocknr);
+
+ BUG_ON(!buffer_uptodate(bh));
+
+ /*
+ * If the ecc fails, we return the error but otherwise
+ * leave the filesystem running. We know any error is
+ * local to this block.
+ *
+ * Note that we are safe to call this even if the directory
+ * doesn't have a trailer. Filesystems without metaecc will do
+ * nothing, and filesystems with it will have one.
+ */
+ rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &trailer->db_check);
+ if (rc)
+ mlog(ML_ERROR, "Checksum failed for dinode %llu\n",
+ (unsigned long long)bh->b_blocknr);
+
+ return rc;
+}
+
+/*
+ * This function forces all errors to -EIO for consistency with its
+ * predecessor, ocfs2_bread(). We haven't audited what returning the
+ * real error codes would do to callers. We log the real codes with
+ * mlog_errno() before we squash them.
+ */
+static int ocfs2_read_dir_block(struct inode *inode, u64 v_block,
+ struct buffer_head **bh, int flags)
+{
+ int rc = 0;
+ struct buffer_head *tmp = *bh;
+ struct ocfs2_dir_block_trailer *trailer;
+
+ rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, flags,
+ ocfs2_validate_dir_block);
+ if (rc) {
+ mlog_errno(rc);
+ goto out;
+ }
+
+ /*
+ * We check the trailer here rather than in
+ * ocfs2_validate_dir_block() because that function doesn't have
+ * the inode to test.
+ */
+ if (!(flags & OCFS2_BH_READAHEAD) &&
+ ocfs2_dir_has_trailer(inode)) {
+ trailer = ocfs2_trailer_from_bh(tmp, inode->i_sb);
+ if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) {
+ rc = -EINVAL;
+ ocfs2_error(inode->i_sb,
+ "Invalid dirblock #%llu: "
+ "signature = %.*s\n",
+ (unsigned long long)tmp->b_blocknr, 7,
+ trailer->db_signature);
+ goto out;
+ }
+ if (le64_to_cpu(trailer->db_blkno) != tmp->b_blocknr) {
+ rc = -EINVAL;
+ ocfs2_error(inode->i_sb,
+ "Directory block #%llu has an invalid "
+ "db_blkno of %llu",
+ (unsigned long long)tmp->b_blocknr,
+ (unsigned long long)le64_to_cpu(trailer->db_blkno));
+ goto out;
+ }
+ if (le64_to_cpu(trailer->db_parent_dinode) !=
+ OCFS2_I(inode)->ip_blkno) {
+ rc = -EINVAL;
+ ocfs2_error(inode->i_sb,
+ "Directory block #%llu on dinode "
+ "#%llu has an invalid parent_dinode "
+ "of %llu",
+ (unsigned long long)tmp->b_blocknr,
+ (unsigned long long)OCFS2_I(inode)->ip_blkno,
+ (unsigned long long)le64_to_cpu(trailer->db_blkno));
+ goto out;
+ }
+ }
+
+ /* If ocfs2_read_virt_blocks() got us a new bh, pass it up. */
+ if (!*bh)
+ *bh = tmp;
+
+out:
+ return rc ? -EIO : 0;
+}
+
+static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen,
+ struct inode *dir,
+ struct ocfs2_dir_entry **res_dir)
{
struct super_block *sb;
struct buffer_head *bh_use[NAMEI_RA_SIZE];
}
num++;
- bh = ocfs2_bread(dir, b++, &err, 1);
+ bh = NULL;
+ err = ocfs2_read_dir_block(dir, b++, &bh,
+ OCFS2_BH_READAHEAD);
bh_use[ra_max] = bh;
}
}
if ((bh = bh_use[ra_ptr++]) == NULL)
goto next;
- wait_on_buffer(bh);
- if (!buffer_uptodate(bh)) {
- /* read error, skip block & hope for the best */
+ if (ocfs2_read_dir_block(dir, block, &bh, 0)) {
+ /* read error, skip block & hope for the best.
+ * ocfs2_read_dir_block() has released the bh. */
ocfs2_error(dir->i_sb, "reading directory %llu, "
"offset %lu\n",
(unsigned long long)OCFS2_I(dir)->ip_blkno,
block);
- brelse(bh);
goto next;
}
i = ocfs2_search_dirblock(bh, dir, name, namelen,
struct inode *new_entry_inode)
{
int ret;
+ ocfs2_journal_access_func access = ocfs2_journal_access_db;
/*
* The same code works fine for both inline-data and extent
- * based directories, so no need to split this up.
+ * based directories, so no need to split this up. The only
+ * difference is the journal_access function.
*/
- ret = ocfs2_journal_access(handle, dir, de_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ access = ocfs2_journal_access_di;
+
+ ret = access(handle, dir, de_bh, OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
{
struct ocfs2_dir_entry *de, *pde;
int i, status = -ENOENT;
+ ocfs2_journal_access_func access = ocfs2_journal_access_db;
mlog_entry("(0x%p, 0x%p, 0x%p, 0x%p)\n", handle, dir, de_del, bh);
+ if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ access = ocfs2_journal_access_di;
+
i = 0;
pde = NULL;
de = (struct ocfs2_dir_entry *) first_de;
goto bail;
}
if (de == de_del) {
- status = ocfs2_journal_access(handle, dir, bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ status = access(handle, dir, bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
status = -EIO;
mlog_errno(status);
goto bail;
}
if (pde)
- pde->rec_len =
- cpu_to_le16(le16_to_cpu(pde->rec_len) +
- le16_to_cpu(de->rec_len));
+ le16_add_cpu(&pde->rec_len,
+ le16_to_cpu(de->rec_len));
else
de->inode = 0;
dir->i_version++;
struct ocfs2_dinode *di;
struct ocfs2_inline_data *data;
- ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
- &di_bh, OCFS2_BH_CACHED, dir);
+ ret = ocfs2_read_inode_block(dir, &di_bh);
if (ret) {
mlog_errno(ret);
goto out;
goto bail;
}
+ /* We're guaranteed that we should have space, so we
+ * can't possibly have hit the trailer...right? */
+ mlog_bug_on_msg(ocfs2_skip_dir_trailer(dir, de, offset, size),
+ "Hit dir trailer trying to insert %.*s "
+ "(namelen %d) into directory %llu. "
+ "offset is %lu, trailer offset is %d\n",
+ namelen, name, namelen,
+ (unsigned long long)parent_fe_bh->b_blocknr,
+ offset, ocfs2_dir_trailer_blk_off(dir->i_sb));
+
if (ocfs2_dirent_would_fit(de, rec_len)) {
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
retval = ocfs2_mark_inode_dirty(handle, dir, parent_fe_bh);
goto bail;
}
- status = ocfs2_journal_access(handle, dir, insert_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ if (insert_bh == parent_fe_bh)
+ status = ocfs2_journal_access_di(handle, dir,
+ insert_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ else
+ status = ocfs2_journal_access_db(handle, dir,
+ insert_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
/* By now the buffer is marked for journaling */
offset += le16_to_cpu(de->rec_len);
if (le64_to_cpu(de->inode)) {
retval = 0;
goto bail;
}
+
offset += le16_to_cpu(de->rec_len);
de = (struct ocfs2_dir_entry *) ((char *) de + le16_to_cpu(de->rec_len));
}
}
static int ocfs2_dir_foreach_blk_id(struct inode *inode,
- unsigned long *f_version,
+ u64 *f_version,
loff_t *f_pos, void *priv,
filldir_t filldir, int *filldir_err)
{
struct ocfs2_inline_data *data;
struct ocfs2_dir_entry *de;
- ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
- &di_bh, OCFS2_BH_CACHED, inode);
+ ret = ocfs2_read_inode_block(inode, &di_bh);
if (ret) {
mlog(ML_ERROR, "Unable to read inode block for dir %llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
* not the directory has been modified
* during the copy operation.
*/
- unsigned long version = *f_version;
+ u64 version = *f_version;
unsigned char d_type = DT_UNKNOWN;
if (de->file_type < OCFS2_FT_MAX)
}
static int ocfs2_dir_foreach_blk_el(struct inode *inode,
- unsigned long *f_version,
+ u64 *f_version,
loff_t *f_pos, void *priv,
filldir_t filldir, int *filldir_err)
{
int i, stored;
struct buffer_head * bh, * tmp;
struct ocfs2_dir_entry * de;
- int err;
struct super_block * sb = inode->i_sb;
unsigned int ra_sectors = 16;
while (!error && !stored && *f_pos < i_size_read(inode)) {
blk = (*f_pos) >> sb->s_blocksize_bits;
- bh = ocfs2_bread(inode, blk, &err, 0);
- if (!bh) {
- mlog(ML_ERROR,
- "directory #%llu contains a hole at offset %lld\n",
- (unsigned long long)OCFS2_I(inode)->ip_blkno,
- *f_pos);
+ if (ocfs2_read_dir_block(inode, blk, &bh, 0)) {
+ /* Skip the corrupt dirblock and keep trying */
*f_pos += sb->s_blocksize - offset;
continue;
}
|| (((last_ra_blk - blk) << 9) <= (ra_sectors / 2))) {
for (i = ra_sectors >> (sb->s_blocksize_bits - 9);
i > 0; i--) {
- tmp = ocfs2_bread(inode, ++blk, &err, 1);
- if (tmp)
+ tmp = NULL;
+ if (!ocfs2_read_dir_block(inode, ++blk, &tmp,
+ OCFS2_BH_READAHEAD))
brelse(tmp);
}
last_ra_blk = blk;
}
offset = 0;
brelse(bh);
+ bh = NULL;
}
stored = 0;
return stored;
}
-static int ocfs2_dir_foreach_blk(struct inode *inode, unsigned long *f_version,
+static int ocfs2_dir_foreach_blk(struct inode *inode, u64 *f_version,
loff_t *f_pos, void *priv, filldir_t filldir,
int *filldir_err)
{
filldir_t filldir)
{
int ret = 0, filldir_err = 0;
- unsigned long version = inode->i_version;
+ u64 version = inode->i_version;
while (*f_pos < i_size_read(inode)) {
ret = ocfs2_dir_foreach_blk(inode, &version, f_pos, priv,
mlog_entry("dirino=%llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
- error = ocfs2_meta_lock_atime(inode, filp->f_vfsmnt, &lock_level);
+ error = ocfs2_inode_lock_atime(inode, filp->f_vfsmnt, &lock_level);
if (lock_level && error >= 0) {
/* We release EX lock which used to update atime
* and get PR lock again to reduce contention
* on commonly accessed directories. */
- ocfs2_meta_unlock(inode, 1);
+ ocfs2_inode_unlock(inode, 1);
lock_level = 0;
- error = ocfs2_meta_lock(inode, NULL, 0);
+ error = ocfs2_inode_lock(inode, NULL, 0);
}
if (error < 0) {
if (error != -ENOENT)
error = ocfs2_dir_foreach_blk(inode, &filp->f_version, &filp->f_pos,
dirent, filldir, NULL);
- ocfs2_meta_unlock(inode, lock_level);
+ ocfs2_inode_unlock(inode, lock_level);
bail_nolock:
mlog_exit(error);
leave:
if (status < 0) {
*dirent = NULL;
- if (*dirent_bh) {
- brelse(*dirent_bh);
- *dirent_bh = NULL;
- }
+ brelse(*dirent_bh);
+ *dirent_bh = NULL;
}
mlog_exit(status);
ret = 0;
bail:
- if (dirent_bh)
- brelse(dirent_bh);
+ brelse(dirent_bh);
mlog_exit(ret);
return ret;
return !priv.seen_other;
}
-static void ocfs2_fill_initial_dirents(struct inode *inode,
- struct inode *parent,
- char *start, unsigned int size)
+/*
+ * Fills "." and ".." dirents in a new directory block. Returns dirent for
+ * "..", which might be used during creation of a directory with a trailing
+ * header. It is otherwise safe to ignore the return code.
+ */
+static struct ocfs2_dir_entry *ocfs2_fill_initial_dirents(struct inode *inode,
+ struct inode *parent,
+ char *start,
+ unsigned int size)
{
struct ocfs2_dir_entry *de = (struct ocfs2_dir_entry *)start;
de->name_len = 2;
strcpy(de->name, "..");
ocfs2_set_de_type(de, S_IFDIR);
+
+ return de;
}
/*
struct ocfs2_inline_data *data = &di->id2.i_data;
unsigned int size = le16_to_cpu(data->id_count);
- ret = ocfs2_journal_access(handle, inode, di_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ ret = ocfs2_journal_access_di(handle, inode, di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out;
struct ocfs2_alloc_context *data_ac)
{
int status;
+ unsigned int size = osb->sb->s_blocksize;
struct buffer_head *new_bh = NULL;
+ struct ocfs2_dir_entry *de;
mlog_entry_void();
+ if (ocfs2_supports_dir_trailer(osb))
+ size = ocfs2_dir_trailer_blk_off(parent->i_sb);
+
status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh,
data_ac, NULL, &new_bh);
if (status < 0) {
ocfs2_set_new_buffer_uptodate(inode, new_bh);
- status = ocfs2_journal_access(handle, inode, new_bh,
- OCFS2_JOURNAL_ACCESS_CREATE);
+ status = ocfs2_journal_access_db(handle, inode, new_bh,
+ OCFS2_JOURNAL_ACCESS_CREATE);
if (status < 0) {
mlog_errno(status);
goto bail;
}
memset(new_bh->b_data, 0, osb->sb->s_blocksize);
- ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data,
- osb->sb->s_blocksize);
+ de = ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, size);
+ if (ocfs2_supports_dir_trailer(osb))
+ ocfs2_init_dir_trailer(inode, new_bh);
status = ocfs2_journal_dirty(handle, new_bh);
if (status < 0) {
status = 0;
bail:
- if (new_bh)
- brelse(new_bh);
+ brelse(new_bh);
mlog_exit(status);
return status;
data_ac);
}
+/*
+ * Expand rec_len of the rightmost dirent in a directory block so that it
+ * contains the end of our valid space for dirents. We do this during
+ * expansion from an inline directory to one with extents. The first dir block
+ * in that case is taken from the inline data portion of the inode block.
+ *
+ * We add the dir trailer if this filesystem wants it.
+ */
static void ocfs2_expand_last_dirent(char *start, unsigned int old_size,
- unsigned int new_size)
+ struct super_block *sb)
{
struct ocfs2_dir_entry *de;
struct ocfs2_dir_entry *prev_de;
char *de_buf, *limit;
- unsigned int bytes = new_size - old_size;
+ unsigned int new_size = sb->s_blocksize;
+ unsigned int bytes;
+
+ if (ocfs2_supports_dir_trailer(OCFS2_SB(sb)))
+ new_size = ocfs2_dir_trailer_blk_off(sb);
+
+ bytes = new_size - old_size;
limit = start + old_size;
de_buf = start;
unsigned int blocks_wanted,
struct buffer_head **first_block_bh)
{
- int ret, credits = OCFS2_INLINE_TO_EXTENTS_CREDITS;
u32 alloc, bit_off, len;
struct super_block *sb = dir->i_sb;
+ int ret, credits = ocfs2_inline_to_extents_credits(sb);
u64 blkno, bytes = blocks_wanted << sb->s_blocksize_bits;
struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
struct ocfs2_inode_info *oi = OCFS2_I(dir);
struct buffer_head *dirdata_bh = NULL;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
handle_t *handle;
+ struct ocfs2_extent_tree et;
+ int did_quota = 0;
+
+ ocfs2_init_dinode_extent_tree(&et, dir, di_bh);
alloc = ocfs2_clusters_for_bytes(sb, bytes);
down_write(&oi->ip_alloc_sem);
/*
- * Prepare for worst case allocation scenario of two seperate
+ * Prepare for worst case allocation scenario of two separate
* extents.
*/
if (alloc == 2)
goto out_sem;
}
+ if (vfs_dq_alloc_space_nodirty(dir,
+ ocfs2_clusters_to_bytes(osb->sb, alloc))) {
+ ret = -EDQUOT;
+ goto out_commit;
+ }
+ did_quota = 1;
/*
* Try to claim as many clusters as the bitmap can give though
* if we only get one now, that's enough to continue. The rest
ocfs2_set_new_buffer_uptodate(dir, dirdata_bh);
- ret = ocfs2_journal_access(handle, dir, dirdata_bh,
- OCFS2_JOURNAL_ACCESS_CREATE);
+ ret = ocfs2_journal_access_db(handle, dir, dirdata_bh,
+ OCFS2_JOURNAL_ACCESS_CREATE);
if (ret) {
mlog_errno(ret);
goto out_commit;
memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir));
memset(dirdata_bh->b_data + i_size_read(dir), 0,
sb->s_blocksize - i_size_read(dir));
- ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir),
- sb->s_blocksize);
+ ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), sb);
+ if (ocfs2_supports_dir_trailer(osb))
+ ocfs2_init_dir_trailer(dir, dirdata_bh);
ret = ocfs2_journal_dirty(handle, dirdata_bh);
if (ret) {
* We let the later dirent insert modify c/mtime - to the user
* the data hasn't changed.
*/
- ret = ocfs2_journal_access(handle, dir, di_bh,
- OCFS2_JOURNAL_ACCESS_CREATE);
+ ret = ocfs2_journal_access_di(handle, dir, di_bh,
+ OCFS2_JOURNAL_ACCESS_CREATE);
if (ret) {
mlog_errno(ret);
goto out_commit;
di->i_size = cpu_to_le64(sb->s_blocksize);
di->i_ctime = di->i_mtime = cpu_to_le64(dir->i_ctime.tv_sec);
di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(dir->i_ctime.tv_nsec);
- dir->i_blocks = ocfs2_inode_sector_count(dir);
/*
* This should never fail as our extent list is empty and all
* related blocks have been journaled already.
*/
- ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 0, blkno, len, 0,
- NULL);
+ ret = ocfs2_insert_extent(osb, handle, dir, &et, 0, blkno, len,
+ 0, NULL);
if (ret) {
mlog_errno(ret);
- goto out;
+ goto out_commit;
}
+ /*
+ * Set i_blocks after the extent insert for the most up to
+ * date ip_clusters value.
+ */
+ dir->i_blocks = ocfs2_inode_sector_count(dir);
+
ret = ocfs2_journal_dirty(handle, di_bh);
if (ret) {
mlog_errno(ret);
}
blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off);
- ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 1, blkno,
- len, 0, NULL);
+ ret = ocfs2_insert_extent(osb, handle, dir, &et, 1,
+ blkno, len, 0, NULL);
if (ret) {
mlog_errno(ret);
- goto out;
+ goto out_commit;
}
}
dirdata_bh = NULL;
out_commit:
+ if (ret < 0 && did_quota)
+ vfs_dq_free_space_nodirty(dir,
+ ocfs2_clusters_to_bytes(osb->sb, 2));
ocfs2_commit_trans(osb, handle);
out_sem:
struct buffer_head **new_bh)
{
int status;
- int extend;
+ int extend, did_quota = 0;
u64 p_blkno, v_blkno;
spin_lock(&OCFS2_I(dir)->ip_lock);
if (extend) {
u32 offset = OCFS2_I(dir)->ip_clusters;
- status = ocfs2_do_extend_allocation(OCFS2_SB(sb), dir, &offset,
- 1, 0, parent_fe_bh, handle,
- data_ac, meta_ac, NULL);
+ if (vfs_dq_alloc_space_nodirty(dir,
+ ocfs2_clusters_to_bytes(sb, 1))) {
+ status = -EDQUOT;
+ goto bail;
+ }
+ did_quota = 1;
+
+ status = ocfs2_add_inode_data(OCFS2_SB(sb), dir, &offset,
+ 1, 0, parent_fe_bh, handle,
+ data_ac, meta_ac, NULL);
BUG_ON(status == -EAGAIN);
if (status < 0) {
mlog_errno(status);
}
status = 0;
bail:
+ if (did_quota && status < 0)
+ vfs_dq_free_space_nodirty(dir, ocfs2_clusters_to_bytes(sb, 1));
mlog_exit(status);
return status;
}
int credits, num_free_extents, drop_alloc_sem = 0;
loff_t dir_i_size;
struct ocfs2_dinode *fe = (struct ocfs2_dinode *) parent_fe_bh->b_data;
+ struct ocfs2_extent_list *el = &fe->id2.i_list;
struct ocfs2_alloc_context *data_ac = NULL;
struct ocfs2_alloc_context *meta_ac = NULL;
handle_t *handle = NULL;
struct buffer_head *new_bh = NULL;
struct ocfs2_dir_entry * de;
struct super_block *sb = osb->sb;
+ struct ocfs2_extent_tree et;
mlog_entry_void();
spin_lock(&OCFS2_I(dir)->ip_lock);
if (dir_i_size == ocfs2_clusters_to_bytes(sb, OCFS2_I(dir)->ip_clusters)) {
spin_unlock(&OCFS2_I(dir)->ip_lock);
- num_free_extents = ocfs2_num_free_extents(osb, dir, fe);
+ ocfs2_init_dinode_extent_tree(&et, dir, parent_fe_bh);
+ num_free_extents = ocfs2_num_free_extents(osb, dir, &et);
if (num_free_extents < 0) {
status = num_free_extents;
mlog_errno(status);
}
if (!num_free_extents) {
- status = ocfs2_reserve_new_metadata(osb, fe, &meta_ac);
+ status = ocfs2_reserve_new_metadata(osb, el, &meta_ac);
if (status < 0) {
if (status != -ENOSPC)
mlog_errno(status);
goto bail;
}
- credits = ocfs2_calc_extend_credits(sb, fe, 1);
+ credits = ocfs2_calc_extend_credits(sb, el, 1);
} else {
spin_unlock(&OCFS2_I(dir)->ip_lock);
credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS;
ocfs2_set_new_buffer_uptodate(dir, new_bh);
- status = ocfs2_journal_access(handle, dir, new_bh,
- OCFS2_JOURNAL_ACCESS_CREATE);
+ status = ocfs2_journal_access_db(handle, dir, new_bh,
+ OCFS2_JOURNAL_ACCESS_CREATE);
if (status < 0) {
mlog_errno(status);
goto bail;
}
memset(new_bh->b_data, 0, sb->s_blocksize);
+
de = (struct ocfs2_dir_entry *) new_bh->b_data;
de->inode = 0;
- de->rec_len = cpu_to_le16(sb->s_blocksize);
+ if (ocfs2_dir_has_trailer(dir)) {
+ de->rec_len = cpu_to_le16(ocfs2_dir_trailer_blk_off(sb));
+ ocfs2_init_dir_trailer(dir, new_bh);
+ } else {
+ de->rec_len = cpu_to_le16(sb->s_blocksize);
+ }
status = ocfs2_journal_dirty(handle, new_bh);
if (status < 0) {
mlog_errno(status);
if (meta_ac)
ocfs2_free_alloc_context(meta_ac);
- if (new_bh)
- brelse(new_bh);
+ brelse(new_bh);
mlog_exit(status);
return status;
unsigned int *blocks_wanted)
{
int ret;
+ struct super_block *sb = dir->i_sb;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
struct ocfs2_dir_entry *de, *last_de = NULL;
char *de_buf, *limit;
unsigned long offset = 0;
- unsigned int rec_len, new_rec_len;
+ unsigned int rec_len, new_rec_len, free_space = dir->i_sb->s_blocksize;
+
+ /*
+ * This calculates how many free bytes we'd have in block zero, should
+ * this function force expansion to an extent tree.
+ */
+ if (ocfs2_supports_dir_trailer(OCFS2_SB(sb)))
+ free_space = ocfs2_dir_trailer_blk_off(sb) - i_size_read(dir);
+ else
+ free_space = dir->i_sb->s_blocksize - i_size_read(dir);
de_buf = di->id2.i_data.id_data;
limit = de_buf + i_size_read(dir);
ret = -EEXIST;
goto out;
}
+ /*
+ * No need to check for a trailing dirent record here as
+ * they're not used for inline dirs.
+ */
+
if (ocfs2_dirent_would_fit(de, rec_len)) {
/* Ok, we found a spot. Return this bh and let
* the caller actually fill it in. */
* dirent can be found.
*/
*blocks_wanted = 1;
- new_rec_len = le16_to_cpu(last_de->rec_len) + (dir->i_sb->s_blocksize - i_size_read(dir));
+ new_rec_len = le16_to_cpu(last_de->rec_len) + free_space;
if (new_rec_len < (rec_len + OCFS2_DIR_REC_LEN(last_de->name_len)))
*blocks_wanted = 2;
struct ocfs2_dir_entry *de;
struct super_block *sb = dir->i_sb;
int status;
+ int blocksize = dir->i_sb->s_blocksize;
- bh = ocfs2_bread(dir, 0, &status, 0);
- if (!bh) {
+ status = ocfs2_read_dir_block(dir, 0, &bh, 0);
+ if (status) {
mlog_errno(status);
goto bail;
}
status = -ENOSPC;
goto bail;
}
- bh = ocfs2_bread(dir,
- offset >> sb->s_blocksize_bits,
- &status,
- 0);
- if (!bh) {
+ status = ocfs2_read_dir_block(dir,
+ offset >> sb->s_blocksize_bits,
+ &bh, 0);
+ if (status) {
mlog_errno(status);
goto bail;
}
status = -EEXIST;
goto bail;
}
+
+ if (ocfs2_skip_dir_trailer(dir, de, offset % blocksize,
+ blocksize))
+ goto next;
+
if (ocfs2_dirent_would_fit(de, rec_len)) {
/* Ok, we found a spot. Return this bh and let
* the caller actually fill it in. */
status = 0;
goto bail;
}
+next:
offset += le16_to_cpu(de->rec_len);
de = (struct ocfs2_dir_entry *)((char *) de + le16_to_cpu(de->rec_len));
}
status = 0;
bail:
- if (bh)
- brelse(bh);
+ brelse(bh);
mlog_exit(status);
return status;
*ret_de_bh = bh;
bh = NULL;
out:
- if (bh)
- brelse(bh);
+ brelse(bh);
return ret;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff