static int ecryptfs_flush(struct file *file, fl_owner_t td)
{
struct file *lower_file = ecryptfs_file_to_lower(file);
if (lower_file->f_op && lower_file->f_op->flush) {
filemap_write_and_wait(file->f_mapping);
return lower_file->f_op->flush(lower_file, td);
}
return 0;
}
int v9fs_dir_release(struct inode *inode, struct file *filp)
{
struct p9_fid *fid;
fid = filp->private_data;
P9_DPRINTK(P9_DEBUG_VFS,
"inode: %p filp: %p fid: %d\n", inode, filp, fid->fid);
filemap_write_and_wait(inode->i_mapping);
p9_client_clunk(fid);
return 0;
}
static int
ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
int rc;
rc = filemap_write_and_wait(file->f_mapping);
if (rc)
return rc;
return vfs_fsync(ecryptfs_file_to_lower(file), datasync);
}
int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
if (!trans || !trans->transaction) {
struct inode *btree_inode;
btree_inode = root->fs_info->btree_inode;
return filemap_write_and_wait(btree_inode->i_mapping);
}
return btrfs_write_and_wait_marked_extents(root,
&trans->transaction->dirty_pages,
EXTENT_DIRTY);
}
int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
{
int retval;
struct v9fs_session_info *v9ses;
struct p9_fid *fid;
struct p9_iattr_dotl p9attr;
P9_DPRINTK(P9_DEBUG_VFS, "\n");
retval = inode_change_ok(dentry->d_inode, iattr);
if (retval)
return retval;
p9attr.valid = iattr->ia_valid;
p9attr.mode = iattr->ia_mode;
p9attr.uid = iattr->ia_uid;
p9attr.gid = iattr->ia_gid;
p9attr.size = iattr->ia_size;
p9attr.atime_sec = iattr->ia_atime.tv_sec;
p9attr.atime_nsec = iattr->ia_atime.tv_nsec;
p9attr.mtime_sec = iattr->ia_mtime.tv_sec;
p9attr.mtime_nsec = iattr->ia_mtime.tv_nsec;
retval = -EPERM;
v9ses = v9fs_dentry2v9ses(dentry);
fid = v9fs_fid_lookup(dentry);
if (IS_ERR(fid))
return PTR_ERR(fid);
/* Write all dirty data */
if (S_ISREG(dentry->d_inode->i_mode))
filemap_write_and_wait(dentry->d_inode->i_mapping);
retval = p9_client_setattr(fid, &p9attr);
if (retval < 0)
return retval;
if ((iattr->ia_valid & ATTR_SIZE) &&
iattr->ia_size != i_size_read(dentry->d_inode))
truncate_setsize(dentry->d_inode, iattr->ia_size);
v9fs_invalidate_inode_attr(dentry->d_inode);
setattr_copy(dentry->d_inode, iattr);
mark_inode_dirty(dentry->d_inode);
if (iattr->ia_valid & ATTR_MODE) {
/* We also want to update ACL when we update mode bits */
retval = v9fs_acl_chmod(dentry);
if (retval < 0)
return retval;
}
return 0;
}
static int
tierfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
int rc;
TRACE_ENTRY();
rc = filemap_write_and_wait(file->f_mapping);
if (rc)
return rc;
TRACE_EXIT();
return vfs_fsync(tierfs_file_to_lower(file), datasync);
}
static int
lofs_fsync(FSYNC_ARGS(struct file *file,
struct dentry *dentry,
loff_t start,
loff_t end,
int datasync))
{
struct file *lower = lofs_file_to_lower(file);
int result = 0;
/* Make sure the LOFS pages are flushed out to the lower filesystem.
* Different kernels have different utility functions to help with
* this; in the worst case (2.6.9) we roll our own.
*/
#if defined(HAVE_OFFSET_IN_FSYNC)
/* This is the 3.2.0+ version. */
result = filemap_write_and_wait_range(file->f_mapping, start, end);
#elif defined(HAVE_FILEMAP_WRITE_AND_WAIT)
/* This is the 2.6.18 - 3.2.0 version. */
result = filemap_write_and_wait(file->f_mapping);
#else
/* This is for versions prior to 2.6.18. This is basically a copy of
* the implementation of filemap_write_and_wait, which unfortunately was
* not added until 2.6.18 or so.
*/
if (file->f_mapping->nrpages) {
result = filemap_fdatawrite(file->f_mapping);
if (result != -EIO) {
int result2 = filemap_fdatawait(file->f_mapping);
if (result == 0) {
result = result2;
}
}
}
#endif
if (result != 0) {
return result;
}
/* Then give the lower filesystem a chance to do its own sync. */
return FSYNC_HELPER(FSYNC_ARGS(lower,
lofs_dentry_to_lower(dentry),
start,
end,
datasync));
}
/*
* set the attributes of an inode
*/
int afs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct afs_fs_cursor fc;
struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
struct key *key;
int ret;
_enter("{%x:%u},{n=%pd},%x",
vnode->fid.vid, vnode->fid.vnode, dentry,
attr->ia_valid);
if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
ATTR_MTIME))) {
_leave(" = 0 [unsupported]");
return 0;
}
/* flush any dirty data outstanding on a regular file */
if (S_ISREG(vnode->vfs_inode.i_mode))
filemap_write_and_wait(vnode->vfs_inode.i_mapping);
if (attr->ia_valid & ATTR_FILE) {
key = afs_file_key(attr->ia_file);
} else {
key = afs_request_key(vnode->volume->cell);
if (IS_ERR(key)) {
ret = PTR_ERR(key);
goto error;
}
}
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, vnode, key)) {
while (afs_select_fileserver(&fc)) {
fc.cb_break = vnode->cb_break + vnode->cb_s_break;
afs_fs_setattr(&fc, attr);
}
afs_check_for_remote_deletion(&fc, fc.vnode);
afs_vnode_commit_status(&fc, vnode, fc.cb_break);
ret = afs_end_vnode_operation(&fc);
}
if (!(attr->ia_valid & ATTR_FILE))
key_put(key);
error:
_leave(" = %d", ret);
return ret;
}
int jfs_umount(struct super_block *sb)
{
struct jfs_sb_info *sbi = JFS_SBI(sb);
struct inode *ipbmap = sbi->ipbmap;
struct inode *ipimap = sbi->ipimap;
struct inode *ipaimap = sbi->ipaimap;
struct inode *ipaimap2 = sbi->ipaimap2;
struct jfs_log *log;
int rc = 0;
jfs_info("UnMount JFS: sb:0x%p", sb);
if ((log = sbi->log))
/*
* Wait for outstanding transactions to be written to log:
*/
jfs_flush_journal(log, 2);
diUnmount(ipimap, 0);
diFreeSpecial(ipimap);
sbi->ipimap = NULL;
ipaimap2 = sbi->ipaimap2;
if (ipaimap2) {
diUnmount(ipaimap2, 0);
diFreeSpecial(ipaimap2);
sbi->ipaimap2 = NULL;
}
ipaimap = sbi->ipaimap;
diUnmount(ipaimap, 0);
diFreeSpecial(ipaimap);
sbi->ipaimap = NULL;
dbUnmount(ipbmap, 0);
diFreeSpecial(ipbmap);
sbi->ipimap = NULL;
filemap_write_and_wait(sbi->direct_inode->i_mapping);
if (log) {
updateSuper(sb, FM_CLEAN);
rc = lmLogClose(sb);
}
jfs_info("UnMount JFS Complete: rc = %d", rc);
return rc;
}
static int
smb_file_release(struct inode *inode, struct file * file)
{
lock_kernel();
if (!--SMB_I(inode)->openers) {
/* We must flush any dirty pages now as we won't be able to
write anything after close. mmap can trigger this.
"openers" should perhaps include mmap'ers ... */
filemap_write_and_wait(inode->i_mapping);
smb_close(inode);
}
unlock_kernel();
return 0;
}
/*
* dbSync()
*/
int dbSync(struct inode *ipbmap)
{
struct dbmap_disk *dbmp_le;
struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap;
struct metapage *mp;
int i;
/*
* write bmap global control page
*/
/* get the buffer for the on-disk bmap descriptor. */
mp = read_metapage(ipbmap,
BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage,
PSIZE, 0);
if (mp == NULL) {
jfs_err("dbSync: read_metapage failed!");
return -EIO;
}
/* copy the in-memory version of the bmap to the on-disk version */
dbmp_le = (struct dbmap_disk *) mp->data;
dbmp_le->dn_mapsize = cpu_to_le64(bmp->db_mapsize);
dbmp_le->dn_nfree = cpu_to_le64(bmp->db_nfree);
dbmp_le->dn_l2nbperpage = cpu_to_le32(bmp->db_l2nbperpage);
dbmp_le->dn_numag = cpu_to_le32(bmp->db_numag);
dbmp_le->dn_maxlevel = cpu_to_le32(bmp->db_maxlevel);
dbmp_le->dn_maxag = cpu_to_le32(bmp->db_maxag);
dbmp_le->dn_agpref = cpu_to_le32(bmp->db_agpref);
dbmp_le->dn_aglevel = cpu_to_le32(bmp->db_aglevel);
dbmp_le->dn_agheight = cpu_to_le32(bmp->db_agheight);
dbmp_le->dn_agwidth = cpu_to_le32(bmp->db_agwidth);
dbmp_le->dn_agstart = cpu_to_le32(bmp->db_agstart);
dbmp_le->dn_agl2size = cpu_to_le32(bmp->db_agl2size);
for (i = 0; i < MAXAG; i++)
dbmp_le->dn_agfree[i] = cpu_to_le64(bmp->db_agfree[i]);
dbmp_le->dn_agsize = cpu_to_le64(bmp->db_agsize);
dbmp_le->dn_maxfreebud = bmp->db_maxfreebud;
/* write the buffer */
write_metapage(mp);
/*
* write out dirty pages of bmap
*/
filemap_write_and_wait(ipbmap->i_mapping);
diWriteSpecial(ipbmap, 0);
return (0);
}
static int tierfs_flush(struct file *file, fl_owner_t td)
{
struct file *lower_file = tierfs_file_to_lower(file);
TRACE_ENTRY();
if (lower_file->f_op) {
if (lower_file->f_op->flush ) {
filemap_write_and_wait(file->f_mapping);
return lower_file->f_op->flush(lower_file, td);
}
}
TRACE_EXIT();
return 0;
}
/*
* Pre-COW all shared blocks within a given byte range of a file and turn off
* the reflink flag if we unshare all of the file's blocks.
*/
int
xfs_reflink_unshare(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t fbno;
xfs_filblks_t end;
xfs_off_t isize;
int error;
if (!xfs_is_reflink_inode(ip))
return 0;
trace_xfs_reflink_unshare(ip, offset, len);
inode_dio_wait(VFS_I(ip));
/* Try to CoW the selected ranges */
xfs_ilock(ip, XFS_ILOCK_EXCL);
fbno = XFS_B_TO_FSBT(mp, offset);
isize = i_size_read(VFS_I(ip));
end = XFS_B_TO_FSB(mp, offset + len);
error = xfs_reflink_dirty_extents(ip, fbno, end, isize);
if (error)
goto out_unlock;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* Wait for the IO to finish */
error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out;
/* Turn off the reflink flag if possible. */
error = xfs_reflink_try_clear_inode_flag(ip);
if (error)
goto out;
return 0;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_unshare_error(ip, error, _RET_IP_);
return error;
}
static int ioctl_fiemap(struct file *filp, unsigned long arg)
{
struct fiemap fiemap;
struct fiemap_extent_info fieinfo = { 0, };
struct inode *inode = filp->f_dentry->d_inode;
struct super_block *sb = inode->i_sb;
u64 len;
int error;
if (!(inode->i_sb->s_type->fs_flags & FS_HAS_FIEMAP))
return -EOPNOTSUPP;
if (!inode->i_op->fiemap)
return -EOPNOTSUPP;
if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
sizeof(struct fiemap)))
return -EFAULT;
if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
return -EINVAL;
error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
&len);
if (error)
return error;
fieinfo.fi_flags = fiemap.fm_flags;
fieinfo.fi_extents_max = fiemap.fm_extent_count;
fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
if (fiemap.fm_extent_count != 0 &&
!access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
return -EFAULT;
if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
filemap_write_and_wait(inode->i_mapping);
error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
fiemap.fm_flags = fieinfo.fi_flags;
fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
error = -EFAULT;
return error;
}
/*
* If we are changing DAX flags, we have to ensure the file is clean and any
* cached objects in the address space are invalidated and removed. This
* requires us to lock out other IO and page faults similar to a truncate
* operation. The locks need to be held until the transaction has been committed
* so that the cache invalidation is atomic with respect to the DAX flag
* manipulation.
*/
static int
xfs_ioctl_setattr_dax_invalidate(
struct xfs_inode *ip,
struct fsxattr *fa,
int *join_flags)
{
struct inode *inode = VFS_I(ip);
int error;
*join_flags = 0;
/*
* It is only valid to set the DAX flag on regular files and
* directories on filesystems where the block size is equal to the page
* size. On directories it serves as an inherit hint.
*/
if (fa->fsx_xflags & FS_XFLAG_DAX) {
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
return -EINVAL;
if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
return -EINVAL;
}
/* If the DAX state is not changing, we have nothing to do here. */
if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode))
return 0;
if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode))
return 0;
/* lock, flush and invalidate mapping in preparation for flag change */
xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
error = filemap_write_and_wait(inode->i_mapping);
if (error)
goto out_unlock;
error = invalidate_inode_pages2(inode->i_mapping);
if (error)
goto out_unlock;
*join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL;
return 0;
out_unlock:
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
return error;
}
static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
{
int res = 0;
struct inode *inode = filp->f_path.dentry->d_inode;
P9_DPRINTK(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
/* No mandatory locks */
if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
return -ENOLCK;
if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
filemap_write_and_wait(inode->i_mapping);
invalidate_mapping_pages(&inode->i_data, 0, -1);
}
return res;
}
int
xfs_flushinval_pages(
xfs_inode_t *ip,
xfs_off_t first,
xfs_off_t last,
int fiopt)
{
struct address_space *mapping = ip->i_vnode->i_mapping;
int ret = 0;
if (mapping->nrpages) {
xfs_iflags_clear(ip, XFS_ITRUNCATED);
ret = filemap_write_and_wait(mapping);
if (!ret)
truncate_inode_pages(mapping, first);
}
return ret;
}
int jfs_umount_rw(struct super_block *sb)
{
struct jfs_sb_info *sbi = JFS_SBI(sb);
struct jfs_log *log = sbi->log;
if (!log)
return 0;
jfs_flush_journal(log, 2);
dbSync(sbi->ipbmap);
diSync(sbi->ipimap);
filemap_write_and_wait(sbi->direct_inode->i_mapping);
updateSuper(sb, FM_CLEAN);
return lmLogClose(sb);
}
/*
* set the attributes of an inode
*/
int afs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
struct key *key;
int ret;
_enter("{%x:%u},{n=%pd},%x",
vnode->fid.vid, vnode->fid.vnode, dentry,
attr->ia_valid);
if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
ATTR_MTIME))) {
_leave(" = 0 [unsupported]");
return 0;
}
/* flush any dirty data outstanding on a regular file */
if (S_ISREG(vnode->vfs_inode.i_mode)) {
filemap_write_and_wait(vnode->vfs_inode.i_mapping);
afs_writeback_all(vnode);
}
if (attr->ia_valid & ATTR_FILE) {
key = attr->ia_file->private_data;
} else {
key = afs_request_key(vnode->volume->cell);
if (IS_ERR(key)) {
ret = PTR_ERR(key);
goto error;
}
}
ret = afs_vnode_setattr(vnode, key, attr);
if (!(attr->ia_valid & ATTR_FILE))
key_put(key);
error:
_leave(" = %d", ret);
return ret;
}
static int exofs_file_fsync(struct file *filp, int datasync)
{
int ret;
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
struct super_block *sb;
ret = filemap_write_and_wait(mapping);
if (ret)
return ret;
/* sync the inode attributes */
ret = write_inode_now(inode, 1);
/* This is a good place to write the sb */
/* TODO: Sechedule an sb-sync on create */
sb = inode->i_sb;
if (sb->s_dirt)
exofs_sync_fs(sb, 1);
return ret;
}
static void xen_update_blkif_status(struct xen_blkif *blkif)
{
int err;
char name[TASK_COMM_LEN];
/* Not ready to connect? */
if (!blkif->irq || !blkif->vbd.bdev)
return;
/* Already connected? */
if (blkif->be->dev->state == XenbusStateConnected)
return;
/* Attempt to connect: exit if we fail to. */
connect(blkif->be);
if (blkif->be->dev->state != XenbusStateConnected)
return;
err = blkback_name(blkif, name);
if (err) {
xenbus_dev_error(blkif->be->dev, err, "get blkback dev name");
return;
}
err = filemap_write_and_wait(blkif->vbd.bdev->bd_inode->i_mapping);
if (err) {
xenbus_dev_error(blkif->be->dev, err, "block flush");
return;
}
invalidate_inode_pages2(blkif->vbd.bdev->bd_inode->i_mapping);
blkif->xenblkd = kthread_run(xen_blkif_schedule, blkif, "%s", name);
if (IS_ERR(blkif->xenblkd)) {
err = PTR_ERR(blkif->xenblkd);
blkif->xenblkd = NULL;
xenbus_dev_error(blkif->be->dev, err, "start xenblkd");
}
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
int alloc_required = 0;
struct gfs2_holder gh;
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
/* Update file times before taking page lock */
file_update_time(vma->vm_file);
ret = get_write_access(inode);
if (ret)
goto out;
ret = gfs2_rs_alloc(ip);
if (ret)
goto out_write_access;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
gfs2_size_hint(inode, pos, PAGE_CACHE_SIZE);
ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
if (ret)
goto out_unlock;
if (!alloc_required) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(page);
}
goto out_unlock;
}
ret = gfs2_rindex_update(sdp);
if (ret)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_unlock;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
ret = gfs2_inplace_reserve(ip, &ap);
if (ret)
goto out_quota_unlock;
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
size = i_size_read(inode);
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
/* Check page index against inode size */
if (size == 0 || (page->index > last_index))
goto out_trans_end;
ret = -EAGAIN;
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping)
goto out_trans_end;
/* Unstuff, if required, and allocate backing blocks for page */
ret = 0;
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
ret = gfs2_allocate_page_backing(page);
out_trans_end:
if (ret)
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
wait_for_stable_page(page);
}
out_write_access:
put_write_access(inode);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
static const struct vm_operations_struct gfs2_vm_ops = {
.fault = filemap_fault,
.page_mkwrite = gfs2_page_mkwrite,
};
/**
* gfs2_mmap -
* @file: The file to map
* @vma: The VMA which described the mapping
*
* There is no need to get a lock here unless we should be updating
* atime. We ignore any locking errors since the only consequence is
* a missed atime update (which will just be deferred until later).
*
* Returns: 0
*/
static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
if (!(file->f_flags & O_NOATIME) &&
!IS_NOATIME(&ip->i_inode)) {
struct gfs2_holder i_gh;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
/* grab lock to update inode */
gfs2_glock_dq_uninit(&i_gh);
file_accessed(file);
}
vma->vm_ops = &gfs2_vm_ops;
vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
/**
* gfs2_open - open a file
* @inode: the inode to open
* @file: the struct file for this opening
*
* Returns: errno
*/
static int gfs2_open(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
struct gfs2_file *fp;
int error;
fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
if (!fp)
return -ENOMEM;
mutex_init(&fp->f_fl_mutex);
gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
file->private_data = fp;
if (S_ISREG(ip->i_inode.i_mode)) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
goto fail;
if (!(file->f_flags & O_LARGEFILE) &&
i_size_read(inode) > MAX_NON_LFS) {
error = -EOVERFLOW;
goto fail_gunlock;
}
gfs2_glock_dq_uninit(&i_gh);
}
return 0;
fail_gunlock:
gfs2_glock_dq_uninit(&i_gh);
fail:
file->private_data = NULL;
kfree(fp);
return error;
}
/**
* gfs2_release - called to close a struct file
* @inode: the inode the struct file belongs to
* @file: the struct file being closed
*
* Returns: errno
*/
static int gfs2_release(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
kfree(file->private_data);
file->private_data = NULL;
if (!(file->f_mode & FMODE_WRITE))
return 0;
gfs2_rs_delete(ip);
return 0;
}
/**
* gfs2_fsync - sync the dirty data for a file (across the cluster)
* @file: the file that points to the dentry
* @start: the start position in the file to sync
* @end: the end position in the file to sync
* @datasync: set if we can ignore timestamp changes
*
* The VFS will flush data for us. We only need to worry
* about metadata here.
*
* Returns: errno
*/
static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
int sync_state = inode->i_state & I_DIRTY;
struct gfs2_inode *ip = GFS2_I(inode);
int ret;
if (!gfs2_is_jdata(ip))
sync_state &= ~I_DIRTY_PAGES;
if (datasync)
sync_state &= ~I_DIRTY_SYNC;
if (sync_state) {
ret = sync_inode_metadata(inode, 1);
if (ret)
return ret;
if (gfs2_is_jdata(ip))
filemap_write_and_wait(inode->i_mapping);
gfs2_ail_flush(ip->i_gl, 1);
}
return 0;
}
/**
* gfs2_file_aio_write - Perform a write to a file
* @iocb: The io context
* @iov: The data to write
* @nr_segs: Number of @iov segments
* @pos: The file position
*
* We have to do a lock/unlock here to refresh the inode size for
* O_APPEND writes, otherwise we can land up writing at the wrong
* offset. There is still a race, but provided the app is using its
* own file locking, this will make O_APPEND work as expected.
*
*/
static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct dentry *dentry = file->f_dentry;
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_sbd *sdp;
int ret;
sdp = GFS2_SB(file->f_mapping->host);
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file->f_dentry->d_inode, pos, writesize);
if (file->f_flags & O_APPEND) {
struct gfs2_holder gh;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
return ret;
gfs2_glock_dq_uninit(&gh);
}
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
int error;
struct inode *inode = out->f_mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
error = gfs2_rs_alloc(ip);
if (error)
return (ssize_t)error;
gfs2_size_hint(inode, *ppos, len);
return generic_file_splice_write(pipe, out, ppos, len, flags);
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
struct gfs2_holder gh;
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
/* Update file times before taking page lock */
file_update_time(vma->vm_file);
ret = get_write_access(inode);
if (ret)
goto out;
ret = gfs2_rs_alloc(ip);
if (ret)
goto out_write_access;
gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(page);
}
goto out_unlock;
}
ret = gfs2_rindex_update(sdp);
if (ret)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_unlock;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
ret = gfs2_inplace_reserve(ip, &ap);
if (ret)
goto out_quota_unlock;
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
size = i_size_read(inode);
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
/* Check page index against inode size */
if (size == 0 || (page->index > last_index))
goto out_trans_end;
ret = -EAGAIN;
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping)
goto out_trans_end;
/* Unstuff, if required, and allocate backing blocks for page */
ret = 0;
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
ret = gfs2_allocate_page_backing(page);
out_trans_end:
if (ret)
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
wait_for_stable_page(page);
}
out_write_access:
put_write_access(inode);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
static const struct vm_operations_struct gfs2_vm_ops = {
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = gfs2_page_mkwrite,
.remap_pages = generic_file_remap_pages,
};
/**
* gfs2_mmap -
* @file: The file to map
* @vma: The VMA which described the mapping
*
* There is no need to get a lock here unless we should be updating
* atime. We ignore any locking errors since the only consequence is
* a missed atime update (which will just be deferred until later).
*
* Returns: 0
*/
static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
if (!(file->f_flags & O_NOATIME) &&
!IS_NOATIME(&ip->i_inode)) {
struct gfs2_holder i_gh;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
/* grab lock to update inode */
gfs2_glock_dq_uninit(&i_gh);
file_accessed(file);
}
vma->vm_ops = &gfs2_vm_ops;
return 0;
}
/**
* gfs2_open_common - This is common to open and atomic_open
* @inode: The inode being opened
* @file: The file being opened
*
* This maybe called under a glock or not depending upon how it has
* been called. We must always be called under a glock for regular
* files, however. For other file types, it does not matter whether
* we hold the glock or not.
*
* Returns: Error code or 0 for success
*/
int gfs2_open_common(struct inode *inode, struct file *file)
{
struct gfs2_file *fp;
int ret;
if (S_ISREG(inode->i_mode)) {
ret = generic_file_open(inode, file);
if (ret)
return ret;
}
fp = kzalloc(sizeof(struct gfs2_file), GFP_NOFS);
if (!fp)
return -ENOMEM;
mutex_init(&fp->f_fl_mutex);
gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
file->private_data = fp;
return 0;
}
/**
* gfs2_open - open a file
* @inode: the inode to open
* @file: the struct file for this opening
*
* After atomic_open, this function is only used for opening files
* which are already cached. We must still get the glock for regular
* files to ensure that we have the file size uptodate for the large
* file check which is in the common code. That is only an issue for
* regular files though.
*
* Returns: errno
*/
static int gfs2_open(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
int error;
bool need_unlock = false;
if (S_ISREG(ip->i_inode.i_mode)) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
need_unlock = true;
}
error = gfs2_open_common(inode, file);
if (need_unlock)
gfs2_glock_dq_uninit(&i_gh);
return error;
}
/**
* gfs2_release - called to close a struct file
* @inode: the inode the struct file belongs to
* @file: the struct file being closed
*
* Returns: errno
*/
static int gfs2_release(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
kfree(file->private_data);
file->private_data = NULL;
if (!(file->f_mode & FMODE_WRITE))
return 0;
gfs2_rs_delete(ip, &inode->i_writecount);
return 0;
}
/**
* gfs2_fsync - sync the dirty data for a file (across the cluster)
* @file: the file that points to the dentry
* @start: the start position in the file to sync
* @end: the end position in the file to sync
* @datasync: set if we can ignore timestamp changes
*
* We split the data flushing here so that we don't wait for the data
* until after we've also sent the metadata to disk. Note that for
* data=ordered, we will write & wait for the data at the log flush
* stage anyway, so this is unlikely to make much of a difference
* except in the data=writeback case.
*
* If the fdatawrite fails due to any reason except -EIO, we will
* continue the remainder of the fsync, although we'll still report
* the error at the end. This is to match filemap_write_and_wait_range()
* behaviour.
*
* Returns: errno
*/
static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
int sync_state = inode->i_state & I_DIRTY;
struct gfs2_inode *ip = GFS2_I(inode);
int ret = 0, ret1 = 0;
if (mapping->nrpages) {
ret1 = filemap_fdatawrite_range(mapping, start, end);
if (ret1 == -EIO)
return ret1;
}
if (!gfs2_is_jdata(ip))
sync_state &= ~I_DIRTY_PAGES;
if (datasync)
sync_state &= ~I_DIRTY_SYNC;
if (sync_state) {
ret = sync_inode_metadata(inode, 1);
if (ret)
return ret;
if (gfs2_is_jdata(ip))
filemap_write_and_wait(mapping);
gfs2_ail_flush(ip->i_gl, 1);
}
if (mapping->nrpages)
ret = filemap_fdatawait_range(mapping, start, end);
return ret ? ret : ret1;
}
/**
* gfs2_file_aio_write - Perform a write to a file
* @iocb: The io context
* @iov: The data to write
* @nr_segs: Number of @iov segments
* @pos: The file position
*
* We have to do a lock/unlock here to refresh the inode size for
* O_APPEND writes, otherwise we can land up writing at the wrong
* offset. There is still a race, but provided the app is using its
* own file locking, this will make O_APPEND work as expected.
*
*/
static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct gfs2_inode *ip = GFS2_I(file_inode(file));
int ret;
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file, pos, writesize);
if (file->f_flags & O_APPEND) {
struct gfs2_holder gh;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
return ret;
gfs2_glock_dq_uninit(&gh);
}
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
int mode)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct buffer_head *dibh;
int error;
loff_t size = len;
unsigned int nr_blks;
sector_t lblock = offset >> inode->i_blkbits;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (unlikely(error))
return error;
gfs2_trans_add_meta(ip->i_gl, dibh);
if (gfs2_is_stuffed(ip)) {
error = gfs2_unstuff_dinode(ip, NULL);
if (unlikely(error))
goto out;
}
while (len) {
struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
bh_map.b_size = len;
set_buffer_zeronew(&bh_map);
error = gfs2_block_map(inode, lblock, &bh_map, 1);
if (unlikely(error))
goto out;
len -= bh_map.b_size;
nr_blks = bh_map.b_size >> inode->i_blkbits;
lblock += nr_blks;
if (!buffer_new(&bh_map))
continue;
if (unlikely(!buffer_zeronew(&bh_map))) {
error = -EIO;
goto out;
}
}
if (offset + size > inode->i_size && !(mode & FALLOC_FL_KEEP_SIZE))
i_size_write(inode, offset + size);
mark_inode_dirty(inode);
out:
brelse(dibh);
return error;
}
static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
unsigned int *data_blocks, unsigned int *ind_blocks)
{
const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
unsigned int max_blocks = ip->i_rgd->rd_free_clone;
unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
for (tmp = max_data; tmp > sdp->sd_diptrs;) {
tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
max_data -= tmp;
}
/* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
so it might end up with fewer data blocks */
if (max_data <= *data_blocks)
return;
*data_blocks = max_data;
*ind_blocks = max_blocks - max_data;
*len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
if (*len > max) {
*len = max;
gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
}
}
static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
struct inode *inode = file_inode(file);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
loff_t bytes, max_bytes;
int error;
const loff_t pos = offset;
const loff_t count = len;
loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1);
loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
loff_t max_chunk_size = UINT_MAX & bsize_mask;
struct gfs2_holder gh;
next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
/* We only support the FALLOC_FL_KEEP_SIZE mode */
if (mode & ~FALLOC_FL_KEEP_SIZE)
return -EOPNOTSUPP;
offset &= bsize_mask;
len = next - offset;
bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
if (!bytes)
bytes = UINT_MAX;
bytes &= bsize_mask;
if (bytes == 0)
bytes = sdp->sd_sb.sb_bsize;
error = gfs2_rs_alloc(ip);
if (error)
return error;
mutex_lock(&inode->i_mutex);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
error = gfs2_glock_nq(&gh);
if (unlikely(error))
goto out_uninit;
gfs2_size_hint(file, offset, len);
while (len > 0) {
if (len < bytes)
bytes = len;
if (!gfs2_write_alloc_required(ip, offset, bytes)) {
len -= bytes;
offset += bytes;
continue;
}
error = gfs2_quota_lock_check(ip);
if (error)
goto out_unlock;
retry:
gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
error = gfs2_inplace_reserve(ip, &ap);
if (error) {
if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
bytes >>= 1;
bytes &= bsize_mask;
if (bytes == 0)
bytes = sdp->sd_sb.sb_bsize;
goto retry;
}
goto out_qunlock;
}
max_bytes = bytes;
calc_max_reserv(ip, (len > max_chunk_size)? max_chunk_size: len,
&max_bytes, &data_blocks, &ind_blocks);
rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
RES_RG_HDR + gfs2_rg_blocks(ip, data_blocks + ind_blocks);
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
error = gfs2_trans_begin(sdp, rblocks,
PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
if (error)
goto out_trans_fail;
error = fallocate_chunk(inode, offset, max_bytes, mode);
gfs2_trans_end(sdp);
if (error)
goto out_trans_fail;
len -= max_bytes;
offset += max_bytes;
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
}
if (error == 0)
error = generic_write_sync(file, pos, count);
goto out_unlock;
out_trans_fail:
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
mutex_unlock(&inode->i_mutex);
return error;
}
#ifdef CONFIG_GFS2_FS_LOCKING_DLM
/**
* gfs2_setlease - acquire/release a file lease
* @file: the file pointer
* @arg: lease type
* @fl: file lock
*
* We don't currently have a way to enforce a lease across the whole
* cluster; until we do, disable leases (by just returning -EINVAL),
* unless the administrator has requested purely local locking.
*
* Locking: called under i_lock
*
* Returns: errno
*/
static int gfs2_setlease(struct file *file, long arg, struct file_lock **fl)
{
return -EINVAL;
}
/**
* gfs2_lock - acquire/release a posix lock on a file
* @file: the file pointer
* @cmd: either modify or retrieve lock state, possibly wait
* @fl: type and range of lock
*
* Returns: errno
*/
static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host);
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
if (!(fl->fl_flags & FL_POSIX))
return -ENOLCK;
if (__mandatory_lock(&ip->i_inode) && fl->fl_type != F_UNLCK)
return -ENOLCK;
if (cmd == F_CANCELLK) {
/* Hack: */
cmd = F_SETLK;
fl->fl_type = F_UNLCK;
}
if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
if (fl->fl_type == F_UNLCK)
posix_lock_file_wait(file, fl);
return -EIO;
}
if (IS_GETLK(cmd))
return dlm_posix_get(ls->ls_dlm, ip->i_no_addr, file, fl);
else if (fl->fl_type == F_UNLCK)
return dlm_posix_unlock(ls->ls_dlm, ip->i_no_addr, file, fl);
else
return dlm_posix_lock(ls->ls_dlm, ip->i_no_addr, file, cmd, fl);
}
static int do_flock(struct file *file, int cmd, struct file_lock *fl)
{
struct gfs2_file *fp = file->private_data;
struct gfs2_holder *fl_gh = &fp->f_fl_gh;
struct gfs2_inode *ip = GFS2_I(file_inode(file));
struct gfs2_glock *gl;
unsigned int state;
int flags;
int error = 0;
state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
mutex_lock(&fp->f_fl_mutex);
gl = fl_gh->gh_gl;
if (gl) {
if (fl_gh->gh_state == state)
goto out;
flock_lock_file_wait(file,
&(struct file_lock){.fl_type = F_UNLCK});
gfs2_glock_dq_wait(fl_gh);
gfs2_holder_reinit(state, flags, fl_gh);
} else {
error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
&gfs2_flock_glops, CREATE, &gl);
if (error)
goto out;
gfs2_holder_init(gl, state, flags, fl_gh);
gfs2_glock_put(gl);
}
error = gfs2_glock_nq(fl_gh);
if (error) {
gfs2_holder_uninit(fl_gh);
if (error == GLR_TRYFAILED)
error = -EAGAIN;
} else {
error = flock_lock_file_wait(file, fl);
gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
}
out:
mutex_unlock(&fp->f_fl_mutex);
return error;
}
static void ecryptfs_vma_close(struct vm_area_struct *vma)
{
filemap_write_and_wait(vma->vm_file->f_mapping);
}
/*
* Initialize a new device for device replace target from a given source dev
* and path.
*
* Return 0 and new device in @device_out, otherwise return < 0
*/
static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
const char *device_path,
struct btrfs_device *srcdev,
struct btrfs_device **device_out)
{
struct btrfs_device *device;
struct block_device *bdev;
struct list_head *devices;
struct rcu_string *name;
u64 devid = BTRFS_DEV_REPLACE_DEVID;
int ret = 0;
*device_out = NULL;
if (fs_info->fs_devices->seeding) {
btrfs_err(fs_info, "the filesystem is a seed filesystem!");
return -EINVAL;
}
bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
fs_info->bdev_holder);
if (IS_ERR(bdev)) {
btrfs_err(fs_info, "target device %s is invalid!", device_path);
return PTR_ERR(bdev);
}
filemap_write_and_wait(bdev->bd_inode->i_mapping);
devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
if (device->bdev == bdev) {
btrfs_err(fs_info,
"target device is in the filesystem!");
ret = -EEXIST;
goto error;
}
}
if (i_size_read(bdev->bd_inode) <
btrfs_device_get_total_bytes(srcdev)) {
btrfs_err(fs_info,
"target device is smaller than source device!");
ret = -EINVAL;
goto error;
}
device = btrfs_alloc_device(NULL, &devid, NULL);
if (IS_ERR(device)) {
ret = PTR_ERR(device);
goto error;
}
name = rcu_string_strdup(device_path, GFP_KERNEL);
if (!name) {
btrfs_free_device(device);
ret = -ENOMEM;
goto error;
}
rcu_assign_pointer(device->name, name);
mutex_lock(&fs_info->fs_devices->device_list_mutex);
set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
device->generation = 0;
device->io_width = fs_info->sectorsize;
device->io_align = fs_info->sectorsize;
device->sector_size = fs_info->sectorsize;
device->total_bytes = btrfs_device_get_total_bytes(srcdev);
device->disk_total_bytes = btrfs_device_get_disk_total_bytes(srcdev);
device->bytes_used = btrfs_device_get_bytes_used(srcdev);
device->commit_total_bytes = srcdev->commit_total_bytes;
device->commit_bytes_used = device->bytes_used;
device->fs_info = fs_info;
device->bdev = bdev;
set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
device->mode = FMODE_EXCL;
device->dev_stats_valid = 1;
set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
device->fs_devices = fs_info->fs_devices;
list_add(&device->dev_list, &fs_info->fs_devices->devices);
fs_info->fs_devices->num_devices++;
fs_info->fs_devices->open_devices++;
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
*device_out = device;
return 0;
error:
blkdev_put(bdev, FMODE_EXCL);
return ret;
}
/*
* Called at inode eviction from icache
*/
void ext3_evict_inode (struct inode *inode)
{
struct ext3_inode_info *ei = EXT3_I(inode);
struct ext3_block_alloc_info *rsv;
handle_t *handle;
int want_delete = 0;
trace_ext3_evict_inode(inode);
if (!inode->i_nlink && !is_bad_inode(inode)) {
dquot_initialize(inode);
want_delete = 1;
}
/*
* When journalling data dirty buffers are tracked only in the journal.
* So although mm thinks everything is clean and ready for reaping the
* inode might still have some pages to write in the running
* transaction or waiting to be checkpointed. Thus calling
* journal_invalidatepage() (via truncate_inode_pages()) to discard
* these buffers can cause data loss. Also even if we did not discard
* these buffers, we would have no way to find them after the inode
* is reaped and thus user could see stale data if he tries to read
* them before the transaction is checkpointed. So be careful and
* force everything to disk here... We use ei->i_datasync_tid to
* store the newest transaction containing inode's data.
*
* Note that directories do not have this problem because they don't
* use page cache.
*
* The s_journal check handles the case when ext3_get_journal() fails
* and puts the journal inode.
*/
if (inode->i_nlink && ext3_should_journal_data(inode) &&
EXT3_SB(inode->i_sb)->s_journal &&
(S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
inode->i_ino != EXT3_JOURNAL_INO) {
tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
log_start_commit(journal, commit_tid);
log_wait_commit(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages(&inode->i_data, 0);
ext3_discard_reservation(inode);
rsv = ei->i_block_alloc_info;
ei->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
if (!want_delete)
goto no_delete;
handle = start_transaction(inode);
if (IS_ERR(handle)) {
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
* cleaned up.
*/
ext3_orphan_del(NULL, inode);
goto no_delete;
}
if (IS_SYNC(inode))
handle->h_sync = 1;
inode->i_size = 0;
if (inode->i_blocks)
ext3_truncate(inode);
/*
* Kill off the orphan record created when the inode lost the last
* link. Note that ext3_orphan_del() has to be able to cope with the
* deletion of a non-existent orphan - ext3_truncate() could
* have removed the record.
*/
ext3_orphan_del(handle, inode);
ei->i_dtime = get_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
if (ext3_mark_inode_dirty(handle, inode)) {
/* If that failed, just dquot_drop() and be done with that */
dquot_drop(inode);
clear_inode(inode);
} else {
ext3_xattr_delete_inode(handle, inode);
dquot_free_inode(inode);
dquot_drop(inode);
clear_inode(inode);
ext3_free_inode(handle, inode);
}
ext3_journal_stop(handle);
return;
no_delete:
clear_inode(inode);
dquot_drop(inode);
}
static int ecryptfs_flush(struct file *file, fl_owner_t td)
{
return file->f_mode & FMODE_WRITE
? filemap_write_and_wait(file->f_mapping) : 0;
}
int
xfs_swap_extents(
xfs_inode_t *ip, /* target inode */
xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp)
{
xfs_mount_t *mp = ip->i_mount;
xfs_trans_t *tp;
xfs_bstat_t *sbp = &sxp->sx_stat;
xfs_ifork_t *tempifp, *ifp, *tifp;
int src_log_flags, target_log_flags;
int error = 0;
int aforkblks = 0;
int taforkblks = 0;
__uint64_t tmp;
tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
if (!tempifp) {
error = XFS_ERROR(ENOMEM);
goto out;
}
/*
* we have to do two separate lock calls here to keep lockdep
* happy. If we try to get all the locks in one call, lock will
* report false positives when we drop the ILOCK and regain them
* below.
*/
xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/* Verify that both files have the same format */
if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify both files are either real-time or non-realtime */
if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
if (error)
goto out_unlock;
truncate_pagecache_range(VFS_I(tip), 0, -1);
/* Verify O_DIRECT for ftmp */
if (VN_CACHED(VFS_I(tip)) != 0) {
error = XFS_ERROR(EINVAL);
goto out_unlock;
}
/* Verify all data are being swapped */
if (sxp->sx_offset != 0 ||
sxp->sx_length != ip->i_d.di_size ||
sxp->sx_length != tip->i_d.di_size) {
error = XFS_ERROR(EFAULT);
goto out_unlock;
}
trace_xfs_swap_extent_before(ip, 0);
trace_xfs_swap_extent_before(tip, 1);
/* check inode formats now that data is flushed */
error = xfs_swap_extents_check_format(ip, tip);
if (error) {
xfs_notice(mp,
"%s: inode 0x%llx format is incompatible for exchanging.",
__func__, ip->i_ino);
goto out_unlock;
}
/*
* Compare the current change & modify times with that
* passed in. If they differ, we abort this swap.
* This is the mechanism used to ensure the calling
* process that the file was not changed out from
* under it.
*/
if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
(sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
(sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
(sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
error = XFS_ERROR(EBUSY);
goto out_unlock;
}
/* We need to fail if the file is memory mapped. Once we have tossed
* all existing pages, the page fault will have no option
* but to go to the filesystem for pages. By making the page fault call
* vop_read (or write in the case of autogrow) they block on the iolock
* until we have switched the extents.
*/
if (VN_MAPPED(VFS_I(ip))) {
error = XFS_ERROR(EBUSY);
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_iunlock(tip, XFS_ILOCK_EXCL);
/*
* There is a race condition here since we gave up the
* ilock. However, the data fork will not change since
* we have the iolock (locked for truncation too) so we
* are safe. We don't really care if non-io related
* fields change.
*/
truncate_pagecache_range(VFS_I(ip), 0, -1);
tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
if (error) {
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
xfs_iunlock(tip, XFS_IOLOCK_EXCL);
xfs_trans_cancel(tp, 0);
goto out;
}
xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/*
* Count the number of extended attribute blocks
*/
if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
if (error)
goto out_trans_cancel;
}
if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
(tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
&taforkblks);
if (error)
goto out_trans_cancel;
}
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
/*
* Before we've swapped the forks, lets set the owners of the forks
* appropriately. We have to do this as we are demand paging the btree
* buffers, and so the validation done on read will expect the owner
* field to be correctly set. Once we change the owners, we can swap the
* inode forks.
*
* Note the trickiness in setting the log flags - we set the owner log
* flag on the opposite inode (i.e. the inode we are setting the new
* owner to be) because once we swap the forks and log that, log
* recovery is going to see the fork as owned by the swapped inode,
* not the pre-swapped inodes.
*/
src_log_flags = XFS_ILOG_CORE;
target_log_flags = XFS_ILOG_CORE;
if (ip->i_d.di_version == 3 &&
ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
target_log_flags |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
tip->i_ino, NULL);
if (error)
goto out_trans_cancel;
}
if (tip->i_d.di_version == 3 &&
tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
src_log_flags |= XFS_ILOG_DOWNER;
error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
ip->i_ino, NULL);
if (error)
goto out_trans_cancel;
}
/*
* Swap the data forks of the inodes
*/
ifp = &ip->i_df;
tifp = &tip->i_df;
*tempifp = *ifp; /* struct copy */
*ifp = *tifp; /* struct copy */
*tifp = *tempifp; /* struct copy */
/*
* Fix the on-disk inode values
*/
tmp = (__uint64_t)ip->i_d.di_nblocks;
ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
tmp = (__uint64_t) ip->i_d.di_nextents;
ip->i_d.di_nextents = tip->i_d.di_nextents;
tip->i_d.di_nextents = tmp;
tmp = (__uint64_t) ip->i_d.di_format;
ip->i_d.di_format = tip->i_d.di_format;
tip->i_d.di_format = tmp;
/*
* The extents in the source inode could still contain speculative
* preallocation beyond EOF (e.g. the file is open but not modified
* while defrag is in progress). In that case, we need to copy over the
* number of delalloc blocks the data fork in the source inode is
* tracking beyond EOF so that when the fork is truncated away when the
* temporary inode is unlinked we don't underrun the i_delayed_blks
* counter on that inode.
*/
ASSERT(tip->i_delayed_blks == 0);
tip->i_delayed_blks = ip->i_delayed_blks;
ip->i_delayed_blks = 0;
switch (ip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
*/
if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
ifp->if_u1.if_extents =
ifp->if_u2.if_inline_ext;
}
src_log_flags |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
ASSERT(ip->i_d.di_version < 3 ||
(src_log_flags & XFS_ILOG_DOWNER));
src_log_flags |= XFS_ILOG_DBROOT;
break;
}
switch (tip->i_d.di_format) {
case XFS_DINODE_FMT_EXTENTS:
/* If the extents fit in the inode, fix the
* pointer. Otherwise it's already NULL or
* pointing to the extent.
*/
if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
tifp->if_u1.if_extents =
tifp->if_u2.if_inline_ext;
}
target_log_flags |= XFS_ILOG_DEXT;
break;
case XFS_DINODE_FMT_BTREE:
target_log_flags |= XFS_ILOG_DBROOT;
ASSERT(tip->i_d.di_version < 3 ||
(target_log_flags & XFS_ILOG_DOWNER));
break;
}
xfs_trans_log_inode(tp, ip, src_log_flags);
xfs_trans_log_inode(tp, tip, target_log_flags);
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
trace_xfs_swap_extent_after(ip, 0);
trace_xfs_swap_extent_after(tip, 1);
out:
kmem_free(tempifp);
return error;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
goto out;
out_trans_cancel:
xfs_trans_cancel(tp, 0);
goto out_unlock;
}
/*
* Get inode's extents as described in bmv, and format for output.
* Calls formatter to fill the user's buffer until all extents
* are mapped, until the passed-in bmv->bmv_count slots have
* been filled, or until the formatter short-circuits the loop,
* if it is tracking filled-in extents on its own.
*/
int /* error code */
xfs_getbmap(
xfs_inode_t *ip,
struct getbmapx *bmv, /* user bmap structure */
xfs_bmap_format_t formatter, /* format to user */
void *arg) /* formatter arg */
{
__int64_t bmvend; /* last block requested */
int error = 0; /* return value */
__int64_t fixlen; /* length for -1 case */
int i; /* extent number */
int lock; /* lock state */
xfs_bmbt_irec_t *map; /* buffer for user's data */
xfs_mount_t *mp; /* file system mount point */
int nex; /* # of user extents can do */
int nexleft; /* # of user extents left */
int subnex; /* # of bmapi's can do */
int nmap; /* number of map entries */
struct getbmapx *out; /* output structure */
int whichfork; /* data or attr fork */
int prealloced; /* this is a file with
* preallocated data space */
int iflags; /* interface flags */
int bmapi_flags; /* flags for xfs_bmapi */
int cur_ext = 0;
mp = ip->i_mount;
iflags = bmv->bmv_iflags;
whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
if (whichfork == XFS_ATTR_FORK) {
if (XFS_IFORK_Q(ip)) {
if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
} else if (unlikely(
ip->i_d.di_aformat != 0 &&
ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
ip->i_mount);
return XFS_ERROR(EFSCORRUPTED);
}
prealloced = 0;
fixlen = 1LL << 32;
} else {
if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
return XFS_ERROR(EINVAL);
if (xfs_get_extsz_hint(ip) ||
ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
prealloced = 1;
fixlen = mp->m_super->s_maxbytes;
} else {
prealloced = 0;
fixlen = XFS_ISIZE(ip);
}
}
if (bmv->bmv_length == -1) {
fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
bmv->bmv_length =
max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
} else if (bmv->bmv_length == 0) {
bmv->bmv_entries = 0;
return 0;
} else if (bmv->bmv_length < 0) {
return XFS_ERROR(EINVAL);
}
nex = bmv->bmv_count - 1;
if (nex <= 0)
return XFS_ERROR(EINVAL);
bmvend = bmv->bmv_offset + bmv->bmv_length;
if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
return XFS_ERROR(ENOMEM);
out = kmem_zalloc_large(bmv->bmv_count * sizeof(struct getbmapx), 0);
if (!out)
return XFS_ERROR(ENOMEM);
xfs_ilock(ip, XFS_IOLOCK_SHARED);
if (whichfork == XFS_DATA_FORK) {
if (!(iflags & BMV_IF_DELALLOC) &&
(ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out_unlock_iolock;
/*
* Even after flushing the inode, there can still be
* delalloc blocks on the inode beyond EOF due to
* speculative preallocation. These are not removed
* until the release function is called or the inode
* is inactivated. Hence we cannot assert here that
* ip->i_delayed_blks == 0.
*/
}
lock = xfs_ilock_data_map_shared(ip);
} else {
lock = xfs_ilock_attr_map_shared(ip);
}
/*
* Don't let nex be bigger than the number of extents
* we can have assuming alternating holes and real extents.
*/
if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
bmapi_flags = xfs_bmapi_aflag(whichfork);
if (!(iflags & BMV_IF_PREALLOC))
bmapi_flags |= XFS_BMAPI_IGSTATE;
/*
* Allocate enough space to handle "subnex" maps at a time.
*/
error = ENOMEM;
subnex = 16;
map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
if (!map)
goto out_unlock_ilock;
bmv->bmv_entries = 0;
if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
(whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
error = 0;
goto out_free_map;
}
nexleft = nex;
do {
nmap = (nexleft > subnex) ? subnex : nexleft;
error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
XFS_BB_TO_FSB(mp, bmv->bmv_length),
map, &nmap, bmapi_flags);
if (error)
goto out_free_map;
ASSERT(nmap <= subnex);
for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
out[cur_ext].bmv_oflags = 0;
if (map[i].br_state == XFS_EXT_UNWRITTEN)
out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
else if (map[i].br_startblock == DELAYSTARTBLOCK)
out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
out[cur_ext].bmv_offset =
XFS_FSB_TO_BB(mp, map[i].br_startoff);
out[cur_ext].bmv_length =
XFS_FSB_TO_BB(mp, map[i].br_blockcount);
out[cur_ext].bmv_unused1 = 0;
out[cur_ext].bmv_unused2 = 0;
/*
* delayed allocation extents that start beyond EOF can
* occur due to speculative EOF allocation when the
* delalloc extent is larger than the largest freespace
* extent at conversion time. These extents cannot be
* converted by data writeback, so can exist here even
* if we are not supposed to be finding delalloc
* extents.
*/
if (map[i].br_startblock == DELAYSTARTBLOCK &&
map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
ASSERT((iflags & BMV_IF_DELALLOC) != 0);
if (map[i].br_startblock == HOLESTARTBLOCK &&
whichfork == XFS_ATTR_FORK) {
/* came to the end of attribute fork */
out[cur_ext].bmv_oflags |= BMV_OF_LAST;
goto out_free_map;
}
if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
prealloced, bmvend,
map[i].br_startblock))
goto out_free_map;
bmv->bmv_offset =
out[cur_ext].bmv_offset +
out[cur_ext].bmv_length;
bmv->bmv_length =
max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
/*
* In case we don't want to return the hole,
* don't increase cur_ext so that we can reuse
* it in the next loop.
*/
if ((iflags & BMV_IF_NO_HOLES) &&
map[i].br_startblock == HOLESTARTBLOCK) {
memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
continue;
}
nexleft--;
bmv->bmv_entries++;
cur_ext++;
}
} while (nmap && nexleft && bmv->bmv_length);
out_free_map:
kmem_free(map);
out_unlock_ilock:
xfs_iunlock(ip, lock);
out_unlock_iolock:
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
for (i = 0; i < cur_ext; i++) {
int full = 0; /* user array is full */
/* format results & advance arg */
error = formatter(&arg, &out[i], &full);
if (error || full)
break;
}
kmem_free(out);
return error;
}
/*
* NAME: jfs_umount(vfsp, flags, crp)
*
* FUNCTION: vfs_umount()
*
* PARAMETERS: vfsp - virtual file system pointer
* flags - unmount for shutdown
* crp - credential
*
* RETURN : EBUSY - device has open files
*/
int jfs_umount(struct super_block *sb)
{
struct jfs_sb_info *sbi = JFS_SBI(sb);
struct inode *ipbmap = sbi->ipbmap;
struct inode *ipimap = sbi->ipimap;
struct inode *ipaimap = sbi->ipaimap;
struct inode *ipaimap2 = sbi->ipaimap2;
struct jfs_log *log;
int rc = 0;
jfs_info("UnMount JFS: sb:0x%p", sb);
/*
* update superblock and close log
*
* if mounted read-write and log based recovery was enabled
*/
if ((log = sbi->log))
/*
* Wait for outstanding transactions to be written to log:
*/
jfs_flush_journal(log, 1);
/*
* close fileset inode allocation map (aka fileset inode)
*/
diUnmount(ipimap, 0);
diFreeSpecial(ipimap);
sbi->ipimap = NULL;
/*
* close secondary aggregate inode allocation map
*/
ipaimap2 = sbi->ipaimap2;
if (ipaimap2) {
diUnmount(ipaimap2, 0);
diFreeSpecial(ipaimap2);
sbi->ipaimap2 = NULL;
}
/*
* close aggregate inode allocation map
*/
ipaimap = sbi->ipaimap;
diUnmount(ipaimap, 0);
diFreeSpecial(ipaimap);
sbi->ipaimap = NULL;
/*
* close aggregate block allocation map
*/
dbUnmount(ipbmap, 0);
diFreeSpecial(ipbmap);
sbi->ipimap = NULL;
/*
* Make sure all metadata makes it to disk before we mark
* the superblock as clean
*/
filemap_write_and_wait(sbi->direct_inode->i_mapping);
/*
* ensure all file system file pages are propagated to their
* home blocks on disk (and their in-memory buffer pages are
* invalidated) BEFORE updating file system superblock state
* (to signify file system is unmounted cleanly, and thus in
* consistent state) and log superblock active file system
* list (to signify skip logredo()).
*/
if (log) { /* log = NULL if read-only mount */
updateSuper(sb, FM_CLEAN);
/*
* close log:
*
* remove file system from log active file system list.
*/
rc = lmLogClose(sb);
}
jfs_info("UnMount JFS Complete: rc = %d", rc);
return rc;
}
