int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
atomic_add(nr_dirty, &nilfs->ns_ndirtyblks);
if (test_and_set_bit(NILFS_I_DIRTY, &ii->i_state))
return 0;
spin_lock(&nilfs->ns_inode_lock);
if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
!test_bit(NILFS_I_BUSY, &ii->i_state)) {
/* Because this routine may race with nilfs_dispose_list(),
we have to check NILFS_I_QUEUED here, too. */
if (list_empty(&ii->i_dirty) && igrab(inode) == NULL) {
/* This will happen when somebody is freeing
this inode. */
nilfs_warning(inode->i_sb, __func__,
"cannot get inode (ino=%lu)\n",
inode->i_ino);
spin_unlock(&nilfs->ns_inode_lock);
return -EINVAL; /* NILFS_I_DIRTY may remain for
freeing inode */
}
list_move_tail(&ii->i_dirty, &nilfs->ns_dirty_files);
set_bit(NILFS_I_QUEUED, &ii->i_state);
}
spin_unlock(&nilfs->ns_inode_lock);
return 0;
}
static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
unsigned long from)
{
unsigned long b;
int ret;
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
repeat:
ret = nilfs_bmap_last_key(ii->i_bmap, &b);
if (ret == -ENOENT)
return;
else if (ret < 0)
goto failed;
if (b < from)
return;
b -= min_t(unsigned long, NILFS_MAX_TRUNCATE_BLOCKS, b - from);
ret = nilfs_bmap_truncate(ii->i_bmap, b);
nilfs_relax_pressure_in_lock(ii->vfs_inode.i_sb);
if (!ret || (ret == -ENOMEM &&
nilfs_bmap_truncate(ii->i_bmap, b) == 0))
goto repeat;
failed:
if (ret == -EINVAL)
nilfs_error(ii->vfs_inode.i_sb, __func__,
"bmap is broken (ino=%lu)", ii->vfs_inode.i_ino);
else
nilfs_warning(ii->vfs_inode.i_sb, __func__,
"failed to truncate bmap (ino=%lu, err=%d)",
ii->vfs_inode.i_ino, ret);
}
static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode;
struct nilfs_dir_entry *de;
struct page *page;
int err;
err = -ENOENT;
de = nilfs_find_entry(dir, &dentry->d_name, &page);
if (!de)
goto out;
inode = dentry->d_inode;
err = -EIO;
if (le64_to_cpu(de->inode) != inode->i_ino)
goto out;
if (!inode->i_nlink) {
nilfs_warning(inode->i_sb, __func__,
"deleting nonexistent file (%lu), %d\n",
inode->i_ino, inode->i_nlink);
set_nlink(inode, 1);
}
err = nilfs_delete_entry(de, page);
if (err)
goto out;
inode->i_ctime = dir->i_ctime;
drop_nlink(inode);
err = 0;
out:
return err;
}
int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
atomic_add(nr_dirty, &nilfs->ns_ndirtyblks);
if (test_and_set_bit(NILFS_I_DIRTY, &ii->i_state))
return 0;
spin_lock(&nilfs->ns_inode_lock);
if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
!test_bit(NILFS_I_BUSY, &ii->i_state)) {
if (list_empty(&ii->i_dirty) && igrab(inode) == NULL) {
nilfs_warning(inode->i_sb, __func__,
"cannot get inode (ino=%lu)\n",
inode->i_ino);
spin_unlock(&nilfs->ns_inode_lock);
return -EINVAL;
}
list_move_tail(&ii->i_dirty, &nilfs->ns_dirty_files);
set_bit(NILFS_I_QUEUED, &ii->i_state);
}
spin_unlock(&nilfs->ns_inode_lock);
return 0;
}
static int nilfs_sync_super(struct nilfs_sb_info *sbi, int dupsb)
{
struct the_nilfs *nilfs = sbi->s_nilfs;
int err;
int barrier_done = 0;
if (nilfs_test_opt(sbi, BARRIER)) {
set_buffer_ordered(nilfs->ns_sbh[0]);
barrier_done = 1;
}
retry:
set_buffer_dirty(nilfs->ns_sbh[0]);
err = sync_dirty_buffer(nilfs->ns_sbh[0]);
if (err == -EOPNOTSUPP && barrier_done) {
nilfs_warning(sbi->s_super, __func__,
"barrier-based sync failed. "
"disabling barriers\n");
nilfs_clear_opt(sbi, BARRIER);
barrier_done = 0;
clear_buffer_ordered(nilfs->ns_sbh[0]);
goto retry;
}
if (unlikely(err)) {
printk(KERN_ERR
"NILFS: unable to write superblock (err=%d)\n", err);
if (err == -EIO && nilfs->ns_sbh[1]) {
nilfs_fall_back_super_block(nilfs);
goto retry;
}
} else {
struct nilfs_super_block *sbp = nilfs->ns_sbp[0];
/*
* The latest segment becomes trailable from the position
* written in superblock.
*/
clear_nilfs_discontinued(nilfs);
/* update GC protection for recent segments */
if (nilfs->ns_sbh[1]) {
sbp = NULL;
if (dupsb) {
set_buffer_dirty(nilfs->ns_sbh[1]);
if (!sync_dirty_buffer(nilfs->ns_sbh[1]))
sbp = nilfs->ns_sbp[1];
}
}
if (sbp) {
spin_lock(&nilfs->ns_last_segment_lock);
nilfs->ns_prot_seq = le64_to_cpu(sbp->s_last_seq);
spin_unlock(&nilfs->ns_last_segment_lock);
}
}
return err;
}
/**
* nilfs_clear_dirty_page - discard dirty page
* @page: dirty page that will be discarded
* @silent: suppress [true] or print [false] warning messages
*/
void nilfs_clear_dirty_page(struct page *page, bool silent)
{
struct inode *inode = page->mapping->host;
struct super_block *sb = inode->i_sb;
BUG_ON(!PageLocked(page));
if (!silent) {
nilfs_warning(sb, __func__,
"discard page: offset %lld, ino %lu",
page_offset(page), inode->i_ino);
}
ClearPageUptodate(page);
ClearPageMappedToDisk(page);
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
bh = head = page_buffers(page);
do {
lock_buffer(bh);
if (!silent) {
nilfs_warning(sb, __func__,
"discard block %llu, size %zu",
(u64)bh->b_blocknr, bh->b_size);
}
clear_buffer_async_write(bh);
clear_buffer_dirty(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_nilfs_checked(bh);
clear_buffer_nilfs_redirected(bh);
clear_buffer_uptodate(bh);
clear_buffer_mapped(bh);
unlock_buffer(bh);
} while (bh = bh->b_this_page, bh != head);
}
__nilfs_clear_page_dirty(page);
}
/**
* nilfs_clear_dirty_page - discard dirty page
* @page: dirty page that will be discarded
* @silent: suppress [true] or print [false] warning messages
*/
void nilfs_clear_dirty_page(struct page *page, bool silent)
{
struct inode *inode = page->mapping->host;
struct super_block *sb = inode->i_sb;
BUG_ON(!PageLocked(page));
if (!silent) {
nilfs_warning(sb, __func__,
"discard page: offset %lld, ino %lu",
page_offset(page), inode->i_ino);
}
ClearPageUptodate(page);
ClearPageMappedToDisk(page);
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
const unsigned long clear_bits =
(1 << BH_Uptodate | 1 << BH_Dirty | 1 << BH_Mapped |
1 << BH_Async_Write | 1 << BH_NILFS_Volatile |
1 << BH_NILFS_Checked | 1 << BH_NILFS_Redirected);
bh = head = page_buffers(page);
do {
lock_buffer(bh);
if (!silent) {
nilfs_warning(sb, __func__,
"discard block %llu, size %zu",
(u64)bh->b_blocknr, bh->b_size);
}
set_mask_bits(&bh->b_state, clear_bits, 0);
unlock_buffer(bh);
} while (bh = bh->b_this_page, bh != head);
}
__nilfs_clear_page_dirty(page);
}
/**
* nilfs_dirty_inode - reflect changes on given inode to an inode block.
* @inode: inode of the file to be registered.
*
* nilfs_dirty_inode() loads a inode block containing the specified
* @inode and copies data from a nilfs_inode to a corresponding inode
* entry in the inode block. This operation is excluded from the segment
* construction. This function can be called both as a single operation
* and as a part of indivisible file operations.
*/
void nilfs_dirty_inode(struct inode *inode)
{
struct nilfs_transaction_info ti;
if (is_bad_inode(inode)) {
nilfs_warning(inode->i_sb, __func__,
"tried to mark bad_inode dirty. ignored.\n");
dump_stack();
return;
}
nilfs_transaction_begin(inode->i_sb, &ti, 0);
nilfs_mark_inode_dirty(inode);
nilfs_transaction_commit(inode->i_sb); /* never fails */
}
int nilfs_mark_inode_dirty(struct inode *inode)
{
struct buffer_head *ibh;
int err;
err = nilfs_load_inode_block(inode, &ibh);
if (unlikely(err)) {
nilfs_warning(inode->i_sb, __func__,
"failed to reget inode block.\n");
return err;
}
nilfs_update_inode(inode, ibh);
mark_buffer_dirty(ibh);
nilfs_mdt_mark_dirty(NILFS_I(inode)->i_root->ifile);
brelse(ibh);
return 0;
}
int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino,
struct buffer_head **out_bh)
{
struct super_block *sb = ifile->i_sb;
int err;
if (unlikely(!NILFS_VALID_INODE(sb, ino))) {
nilfs_error(sb, __func__, "bad inode number: %lu",
(unsigned long) ino);
return -EINVAL;
}
err = nilfs_palloc_get_entry_block(ifile, ino, 0, out_bh);
if (unlikely(err))
nilfs_warning(sb, __func__, "unable to read inode: %lu",
(unsigned long) ino);
return err;
}
static int nilfs_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode;
struct nilfs_dir_entry *de;
struct page *page;
struct nilfs_transaction_info ti;
int err;
err = nilfs_transaction_begin(dir->i_sb, &ti, 0);
if (err)
return err;
err = -ENOENT;
de = nilfs_find_entry(dir, dentry, &page);
if (!de)
goto out;
inode = dentry->d_inode;
err = -EIO;
if (le64_to_cpu(de->inode) != inode->i_ino)
goto out;
if (!inode->i_nlink) {
nilfs_warning(inode->i_sb, __func__,
"deleting nonexistent file (%lu), %d\n",
inode->i_ino, inode->i_nlink);
inode->i_nlink = 1;
}
err = nilfs_delete_entry(de, page);
if (err)
goto out;
inode->i_ctime = dir->i_ctime;
inode_dec_link_count(inode);
err = 0;
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
else
nilfs_transaction_abort(dir->i_sb);
return err;
}
/**
* nilfs_dirty_inode - reflect changes on given inode to an inode block.
* @inode: inode of the file to be registered.
*
* nilfs_dirty_inode() loads a inode block containing the specified
* @inode and copies data from a nilfs_inode to a corresponding inode
* entry in the inode block. This operation is excluded from the segment
* construction. This function can be called both as a single operation
* and as a part of indivisible file operations.
*/
void nilfs_dirty_inode(struct inode *inode, int flags)
{
struct nilfs_transaction_info ti;
struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
if (is_bad_inode(inode)) {
nilfs_warning(inode->i_sb, __func__,
"tried to mark bad_inode dirty. ignored.\n");
dump_stack();
return;
}
if (mdi) {
nilfs_mdt_mark_dirty(inode);
return;
}
nilfs_transaction_begin(inode->i_sb, &ti, 0);
__nilfs_mark_inode_dirty(inode, flags);
nilfs_transaction_commit(inode->i_sb); /* never fails */
}
int nilfs_mark_inode_dirty(struct inode *inode)
{
struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
struct buffer_head *ibh;
int err;
err = nilfs_load_inode_block(sbi, inode, &ibh);
if (unlikely(err)) {
nilfs_warning(inode->i_sb, __func__,
"failed to reget inode block.\n");
return err;
}
lock_buffer(ibh);
nilfs_update_inode(inode, ibh);
unlock_buffer(ibh);
nilfs_mdt_mark_buffer_dirty(ibh);
nilfs_mdt_mark_dirty(sbi->s_ifile);
brelse(ibh);
return 0;
}
struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
.ino = ino, .root = root, .cno = 0, .for_gc = 0
};
return ilookup5(sb, ino, nilfs_iget_test, &args);
}
struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
.ino = ino, .root = root, .cno = 0, .for_gc = 0
};
return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
}
struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct inode *inode;
int err;
inode = nilfs_iget_locked(sb, root, ino);
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
err = __nilfs_read_inode(sb, root, ino, inode);
if (unlikely(err)) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
return inode;
}
struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
__u64 cno)
{
struct nilfs_iget_args args = {
.ino = ino, .root = NULL, .cno = cno, .for_gc = 1
};
struct inode *inode;
int err;
inode = iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
err = nilfs_init_gcinode(inode);
if (unlikely(err)) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
return inode;
}
void nilfs_write_inode_common(struct inode *inode,
struct nilfs_inode *raw_inode, int has_bmap)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
raw_inode->i_uid = cpu_to_le32(inode->i_uid);
raw_inode->i_gid = cpu_to_le32(inode->i_gid);
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le64(inode->i_size);
raw_inode->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
raw_inode->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
raw_inode->i_blocks = cpu_to_le64(inode->i_blocks);
raw_inode->i_flags = cpu_to_le32(ii->i_flags);
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (NILFS_ROOT_METADATA_FILE(inode->i_ino)) {
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
/* zero-fill unused portion in the case of super root block */
raw_inode->i_xattr = 0;
raw_inode->i_pad = 0;
memset((void *)raw_inode + sizeof(*raw_inode), 0,
nilfs->ns_inode_size - sizeof(*raw_inode));
}
if (has_bmap)
nilfs_bmap_write(ii->i_bmap, raw_inode);
else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
raw_inode->i_device_code =
cpu_to_le64(huge_encode_dev(inode->i_rdev));
/* When extending inode, nilfs->ns_inode_size should be checked
for substitutions of appended fields */
}
void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
{
ino_t ino = inode->i_ino;
struct nilfs_inode_info *ii = NILFS_I(inode);
struct inode *ifile = ii->i_root->ifile;
struct nilfs_inode *raw_inode;
raw_inode = nilfs_ifile_map_inode(ifile, ino, ibh);
if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state))
memset(raw_inode, 0, NILFS_MDT(ifile)->mi_entry_size);
set_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
nilfs_write_inode_common(inode, raw_inode, 0);
/* XXX: call with has_bmap = 0 is a workaround to avoid
deadlock of bmap. This delays update of i_bmap to just
before writing */
nilfs_ifile_unmap_inode(ifile, ino, ibh);
}
#define NILFS_MAX_TRUNCATE_BLOCKS 16384 /* 64MB for 4KB block */
static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
unsigned long from)
{
unsigned long b;
int ret;
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
repeat:
ret = nilfs_bmap_last_key(ii->i_bmap, &b);
if (ret == -ENOENT)
return;
else if (ret < 0)
goto failed;
if (b < from)
return;
b -= min_t(unsigned long, NILFS_MAX_TRUNCATE_BLOCKS, b - from);
ret = nilfs_bmap_truncate(ii->i_bmap, b);
nilfs_relax_pressure_in_lock(ii->vfs_inode.i_sb);
if (!ret || (ret == -ENOMEM &&
nilfs_bmap_truncate(ii->i_bmap, b) == 0))
goto repeat;
failed:
nilfs_warning(ii->vfs_inode.i_sb, __func__,
"failed to truncate bmap (ino=%lu, err=%d)",
ii->vfs_inode.i_ino, ret);
}
void nilfs_truncate(struct inode *inode)
{
unsigned long blkoff;
unsigned int blocksize;
struct nilfs_transaction_info ti;
struct super_block *sb = inode->i_sb;
struct nilfs_inode_info *ii = NILFS_I(inode);
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return;
blocksize = sb->s_blocksize;
blkoff = (inode->i_size + blocksize - 1) >> sb->s_blocksize_bits;
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
block_truncate_page(inode->i_mapping, inode->i_size, nilfs_get_block);
nilfs_truncate_bmap(ii, blkoff);
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_mark_inode_dirty(inode);
nilfs_set_file_dirty(inode, 0);
nilfs_transaction_commit(sb);
/* May construct a logical segment and may fail in sync mode.
But truncate has no return value. */
}
static int nilfs_sync_super(struct super_block *sb, int flag)
{
struct the_nilfs *nilfs = sb->s_fs_info;
int err;
#if HAVE_BH_ORDERED
int barrier_done = 0;
if (nilfs_sb_barrier(nilfs)) {
set_buffer_ordered(nilfs->ns_sbh[0]);
barrier_done = 1;
}
retry:
set_buffer_dirty(nilfs->ns_sbh[0]);
err = sync_dirty_buffer(nilfs->ns_sbh[0]);
if (err == -EOPNOTSUPP && barrier_done) {
nilfs_warning(sb, __func__, "barrier-based sync failed. "
"disabling barriers for superblock\n");
clear_nilfs_sb_barrier(nilfs);
barrier_done = 0;
clear_buffer_ordered(nilfs->ns_sbh[0]);
goto retry;
}
#else
retry:
set_buffer_dirty(nilfs->ns_sbh[0]);
if (nilfs_sb_barrier(nilfs)) {
#if HAVE_BIO_BARRIER
err = __sync_dirty_buffer(nilfs->ns_sbh[0],
WRITE_SYNC | WRITE_BARRIER);
if (err == -EOPNOTSUPP) {
nilfs_warning(sb, __func__,
"barrier-based sync failed. "
"disabling barriers for superblock\n");
clear_nilfs_sb_barrier(nilfs);
goto retry;
}
#else
err = __sync_dirty_buffer(nilfs->ns_sbh[0],
WRITE_SYNC | WRITE_FLUSH_FUA);
#endif /* HAVE_BIO_BARRIER */
} else {
err = sync_dirty_buffer(nilfs->ns_sbh[0]);
}
#endif /* HAVE_BH_ORDERED */
if (unlikely(err)) {
printk(KERN_ERR
"NILFS: unable to write superblock (err=%d)\n", err);
if (err == -EIO && nilfs->ns_sbh[1]) {
/*
* sbp[0] points to newer log than sbp[1],
* so copy sbp[0] to sbp[1] to take over sbp[0].
*/
memcpy(nilfs->ns_sbp[1], nilfs->ns_sbp[0],
nilfs->ns_sbsize);
nilfs_fall_back_super_block(nilfs);
goto retry;
}
} else {
struct nilfs_super_block *sbp = nilfs->ns_sbp[0];
nilfs->ns_sbwcount++;
/*
* The latest segment becomes trailable from the position
* written in superblock.
*/
clear_nilfs_discontinued(nilfs);
/* update GC protection for recent segments */
if (nilfs->ns_sbh[1]) {
if (flag == NILFS_SB_COMMIT_ALL) {
set_buffer_dirty(nilfs->ns_sbh[1]);
if (sync_dirty_buffer(nilfs->ns_sbh[1]) < 0)
goto out;
}
if (le64_to_cpu(nilfs->ns_sbp[1]->s_last_cno) <
le64_to_cpu(nilfs->ns_sbp[0]->s_last_cno))
sbp = nilfs->ns_sbp[1];
}
spin_lock(&nilfs->ns_last_segment_lock);
nilfs->ns_prot_seq = le64_to_cpu(sbp->s_last_seq);
spin_unlock(&nilfs->ns_last_segment_lock);
}
out:
return err;
}
