static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock)
{
struct gfs2_inode *ip = GFS2_I(mapping->host);
struct gfs2_holder i_gh;
sector_t dblock = 0;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
if (error)
return 0;
if (!gfs2_is_stuffed(ip))
dblock = generic_block_bmap(mapping, lblock, gfs2_block_map);
gfs2_glock_dq_uninit(&i_gh);
return dblock;
}
static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
struct gfs2_holder i_gh;
loff_t error;
if (origin == 2) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (!error) {
error = generic_file_llseek_unlocked(file, offset, origin);
gfs2_glock_dq_uninit(&i_gh);
}
} else
error = generic_file_llseek_unlocked(file, offset, origin);
return error;
}
int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
struct gfs2_glock *j_gl = ip->i_gl;
struct gfs2_holder t_gh;
struct gfs2_log_header_host head;
int error;
error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &t_gh);
if (error)
return error;
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
error = gfs2_find_jhead(sdp->sd_jdesc, &head);
if (error)
goto fail;
if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
gfs2_consist(sdp);
error = -EIO;
goto fail;
}
/* Initialize some head of the log stuff */
sdp->sd_log_sequence = head.lh_sequence + 1;
gfs2_log_pointers_init(sdp, head.lh_blkno);
error = gfs2_quota_init(sdp);
if (error)
goto fail;
set_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
gfs2_glock_dq_uninit(&t_gh);
return 0;
fail:
t_gh.gh_flags |= GL_NOCACHE;
gfs2_glock_dq_uninit(&t_gh);
return error;
}
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;
if (file->f_flags & O_APPEND) {
struct dentry *dentry = file->f_dentry;
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_holder gh;
int ret;
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);
}
struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
int is_root)
{
struct super_block *sb = dir->i_sb;
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_holder d_gh;
int error = 0;
struct inode *inode = NULL;
int unlock = 0;
if (!name->len || name->len > GFS2_FNAMESIZE)
return ERR_PTR(-ENAMETOOLONG);
if ((name->len == 1 && memcmp(name->name, ".", 1) == 0) ||
(name->len == 2 && memcmp(name->name, "..", 2) == 0 &&
dir == sb->s_root->d_inode)) {
igrab(dir);
return dir;
}
if (gfs2_glock_is_locked_by_me(dip->i_gl) == NULL) {
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
if (error)
return ERR_PTR(error);
unlock = 1;
}
if (!is_root) {
error = gfs2_permission(dir, MAY_EXEC);
if (error)
goto out;
}
inode = gfs2_dir_search(dir, name);
if (IS_ERR(inode))
error = PTR_ERR(inode);
out:
if (unlock)
gfs2_glock_dq_uninit(&d_gh);
if (error == -ENOENT)
return NULL;
return inode ? inode : ERR_PTR(error);
}
static int gfs2_permission(struct inode *inode, int mask, struct nameidata *nd)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
int error;
int unlock = 0;
if (gfs2_glock_is_locked_by_me(ip->i_gl) == 0) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
if (error)
return error;
unlock = 1;
}
error = generic_permission(inode, mask, gfs2_check_acl);
if (unlock)
gfs2_glock_dq_uninit(&i_gh);
return error;
}
static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int ret;
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
if (ret)
return ret;
mutex_lock(&inode->i_mutex);
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
goto out;
if (gfs2_is_stuffed(ip)) {
u64 phys = ip->i_no_addr << inode->i_blkbits;
u64 size = i_size_read(inode);
u32 flags = FIEMAP_EXTENT_LAST|FIEMAP_EXTENT_NOT_ALIGNED|
FIEMAP_EXTENT_DATA_INLINE;
phys += sizeof(struct gfs2_dinode);
phys += start;
if (start + len > size)
len = size - start;
if (start < size)
ret = fiemap_fill_next_extent(fieinfo, start, phys,
len, flags);
if (ret == 1)
ret = 0;
} else {
ret = __generic_block_fiemap(inode, fieinfo, start, len,
gfs2_block_map);
}
gfs2_glock_dq_uninit(&gh);
out:
mutex_unlock(&inode->i_mutex);
return ret;
}
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;
}
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;
}
static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
int unlock = 0;
if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
if (error)
return error;
unlock = 1;
}
generic_fillattr(inode, stat);
if (unlock)
gfs2_glock_dq_uninit(&gh);
return 0;
}
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;
}
static int gfs2_write_inode(struct inode *inode, int sync)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_holder gh;
struct buffer_head *bh;
struct timespec atime;
struct gfs2_dinode *di;
int ret = 0;
/* Check this is a "normal" inode, etc */
if (!test_bit(GIF_USER, &ip->i_flags) ||
(current->flags & PF_MEMALLOC))
return 0;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (ret)
goto do_flush;
ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
if (ret)
goto do_unlock;
ret = gfs2_meta_inode_buffer(ip, &bh);
if (ret == 0) {
di = (struct gfs2_dinode *)bh->b_data;
atime.tv_sec = be64_to_cpu(di->di_atime);
atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
if (timespec_compare(&inode->i_atime, &atime) > 0) {
gfs2_trans_add_bh(ip->i_gl, bh, 1);
gfs2_dinode_out(ip, bh->b_data);
}
brelse(bh);
}
gfs2_trans_end(sdp);
do_unlock:
gfs2_glock_dq_uninit(&gh);
do_flush:
if (sync != 0)
gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
return ret;
}
static int gfs2_get_name(struct dentry *parent, char *name,
struct dentry *child)
{
struct inode *dir = parent->d_inode;
struct inode *inode = child->d_inode;
struct gfs2_inode *dip, *ip;
struct get_name_filldir gnfd;
struct gfs2_holder gh;
u64 offset = 0;
int error;
if (!dir)
return -EINVAL;
if (!S_ISDIR(dir->i_mode) || !inode)
return -EINVAL;
dip = GFS2_I(dir);
ip = GFS2_I(inode);
*name = 0;
gnfd.inum.no_addr = ip->i_no_addr;
gnfd.inum.no_formal_ino = ip->i_no_formal_ino;
gnfd.name = name;
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh);
if (error)
return error;
error = gfs2_dir_read(dir, &offset, &gnfd, get_name_filldir);
gfs2_glock_dq_uninit(&gh);
if (!error && !*name)
error = -ENOENT;
return error;
}
static loff_t gfs2_llseek(struct file *file, loff_t offset, int whence)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
struct gfs2_holder i_gh;
loff_t error;
switch (whence) {
case SEEK_END:
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (!error) {
error = generic_file_llseek(file, offset, whence);
gfs2_glock_dq_uninit(&i_gh);
}
break;
case SEEK_DATA:
error = gfs2_seek_data(file, offset);
break;
case SEEK_HOLE:
error = gfs2_seek_hole(file, offset);
break;
case SEEK_CUR:
case SEEK_SET:
/*
* These don't reference inode->i_size and don't depend on the
* block mapping, so we don't need the glock.
*/
error = generic_file_llseek(file, offset, whence);
break;
default:
error = -EINVAL;
}
return error;
}
static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
struct file *file, int *opened)
{
struct inode *inode;
struct dentry *d;
struct gfs2_holder gh;
struct gfs2_glock *gl;
int error;
inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (!inode)
return NULL;
if (IS_ERR(inode))
return ERR_CAST(inode);
gl = GFS2_I(inode)->i_gl;
error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
if (error) {
iput(inode);
return ERR_PTR(error);
}
d = d_splice_alias(inode, dentry);
if (IS_ERR(d)) {
iput(inode);
gfs2_glock_dq_uninit(&gh);
return d;
}
if (file && S_ISREG(inode->i_mode))
error = finish_open(file, dentry, gfs2_open_common, opened);
gfs2_glock_dq_uninit(&gh);
if (error) {
dput(d);
return ERR_PTR(error);
}
return d;
}
int gfs2_permission(struct inode *inode, int mask)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
int error;
int unlock = 0;
if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
if (error)
return error;
unlock = 1;
}
if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
error = -EACCES;
else
error = generic_permission(inode, mask, gfs2_check_acl);
if (unlock)
gfs2_glock_dq_uninit(&i_gh);
return error;
}
static struct dentry *gfs2_get_dentry(struct super_block *sb,
struct gfs2_inum_host *inum)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_fh_obj *fh_obj = (struct gfs2_fh_obj *)inum_obj;
struct gfs2_holder i_gh, ri_gh, rgd_gh;
struct gfs2_rgrpd *rgd;
struct inode *inode;
struct dentry *dentry;
int error;
/* System files? */
inode = gfs2_ilookup(sb, inum);
if (inode) {
if (GFS2_I(inode)->i_num.no_formal_ino != inum->no_formal_ino) {
iput(inode);
return ERR_PTR(-ESTALE);
}
goto out_inode;
}
error = gfs2_glock_nq_num(sdp, inum->no_addr, &gfs2_inode_glops,
LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
if (error)
return ERR_PTR(error);
error = gfs2_rindex_hold(sdp, &ri_gh);
if (error)
goto fail;
error = -EINVAL;
rgd = gfs2_blk2rgrpd(sdp, inum->no_addr);
if (!rgd)
goto fail_rindex;
error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
if (error)
goto fail_rindex;
error = -ESTALE;
if (gfs2_get_block_type(rgd, inum->no_addr) != GFS2_BLKST_DINODE)
goto fail_rgd;
gfs2_glock_dq_uninit(&rgd_gh);
gfs2_glock_dq_uninit(&ri_gh);
inode = gfs2_inode_lookup(sb, inum, fh_obj->imode);
if (!inode)
goto fail;
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
goto fail;
}
error = gfs2_inode_refresh(GFS2_I(inode));
if (error) {
iput(inode);
goto fail;
}
error = -EIO;
if (GFS2_I(inode)->i_di.di_flags & GFS2_DIF_SYSTEM) {
iput(inode);
goto fail;
}
gfs2_glock_dq_uninit(&i_gh);
out_inode:
dentry = d_alloc_anon(inode);
if (!dentry) {
iput(inode);
return ERR_PTR(-ENOMEM);
}
dentry->d_op = &gfs2_dops;
return dentry;
fail_rgd:
gfs2_glock_dq_uninit(&rgd_gh);
fail_rindex:
gfs2_glock_dq_uninit(&ri_gh);
fail:
gfs2_glock_dq_uninit(&i_gh);
return ERR_PTR(error);
}
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 int gfs2_rename(struct inode *odir, struct dentry *odentry,
struct inode *ndir, struct dentry *ndentry)
{
struct gfs2_inode *odip = GFS2_I(odir);
struct gfs2_inode *ndip = GFS2_I(ndir);
struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
struct gfs2_inode *nip = NULL;
struct gfs2_sbd *sdp = GFS2_SB(odir);
struct gfs2_holder ghs[5], r_gh;
struct gfs2_rgrpd *nrgd;
unsigned int num_gh;
int dir_rename = 0;
int alloc_required;
unsigned int x;
int error;
if (ndentry->d_inode) {
nip = GFS2_I(ndentry->d_inode);
if (ip == nip)
return 0;
}
/* Make sure we aren't trying to move a dirctory into it's subdir */
if (S_ISDIR(ip->i_inode.i_mode) && odip != ndip) {
dir_rename = 1;
error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE, 0,
&r_gh);
if (error)
goto out;
error = gfs2_ok_to_move(ip, ndip);
if (error)
goto out_gunlock_r;
}
num_gh = 1;
gfs2_holder_init(odip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (odip != ndip) {
gfs2_holder_init(ndip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
num_gh++;
}
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
num_gh++;
if (nip) {
gfs2_holder_init(nip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
num_gh++;
/* grab the resource lock for unlink flag twiddling
* this is the case of the target file already existing
* so we unlink before doing the rename
*/
nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
if (nrgd)
gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
}
error = gfs2_glock_nq_m(num_gh, ghs);
if (error)
goto out_uninit;
/* Check out the old directory */
error = gfs2_unlink_ok(odip, &odentry->d_name, ip);
if (error)
goto out_gunlock;
/* Check out the new directory */
if (nip) {
error = gfs2_unlink_ok(ndip, &ndentry->d_name, nip);
if (error)
goto out_gunlock;
if (S_ISDIR(nip->i_inode.i_mode)) {
if (nip->i_di.di_entries < 2) {
if (gfs2_consist_inode(nip))
gfs2_dinode_print(nip);
error = -EIO;
goto out_gunlock;
}
if (nip->i_di.di_entries > 2) {
error = -ENOTEMPTY;
goto out_gunlock;
}
}
} else {
error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
error = gfs2_dir_check(ndir, &ndentry->d_name, NULL);
switch (error) {
case -ENOENT:
error = 0;
break;
case 0:
error = -EEXIST;
default:
goto out_gunlock;
};
if (odip != ndip) {
if (!ndip->i_inode.i_nlink) {
error = -EINVAL;
goto out_gunlock;
}
if (ndip->i_di.di_entries == (u32)-1) {
error = -EFBIG;
goto out_gunlock;
}
if (S_ISDIR(ip->i_inode.i_mode) &&
ndip->i_inode.i_nlink == (u32)-1) {
error = -EMLINK;
goto out_gunlock;
}
}
}
/* Check out the dir to be renamed */
if (dir_rename) {
error = gfs2_permission(odentry->d_inode, MAY_WRITE);
if (error)
goto out_gunlock;
}
alloc_required = error = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
if (error < 0)
goto out_gunlock;
error = 0;
if (alloc_required) {
struct gfs2_alloc *al = gfs2_alloc_get(ndip);
if (!al) {
error = -ENOMEM;
goto out_gunlock;
}
error = gfs2_quota_lock_check(ndip);
if (error)
goto out_alloc;
al->al_requested = sdp->sd_max_dirres;
error = gfs2_inplace_reserve(ndip);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
al->al_rgd->rd_length +
4 * RES_DINODE + 4 * RES_LEAF +
RES_STATFS + RES_QUOTA + 4, 0);
if (error)
goto out_ipreserv;
} else {
error = gfs2_trans_begin(sdp, 4 * RES_DINODE +
5 * RES_LEAF + 4, 0);
if (error)
goto out_gunlock;
}
/* Remove the target file, if it exists */
if (nip) {
if (S_ISDIR(nip->i_inode.i_mode))
error = gfs2_rmdiri(ndip, &ndentry->d_name, nip);
else {
error = gfs2_dir_del(ndip, &ndentry->d_name);
if (error)
goto out_end_trans;
error = gfs2_change_nlink(nip, -1);
}
if (error)
goto out_end_trans;
}
if (dir_rename) {
struct qstr name;
gfs2_str2qstr(&name, "..");
error = gfs2_change_nlink(ndip, +1);
if (error)
goto out_end_trans;
error = gfs2_change_nlink(odip, -1);
if (error)
goto out_end_trans;
error = gfs2_dir_mvino(ip, &name, ndip, DT_DIR);
if (error)
goto out_end_trans;
} else {
struct buffer_head *dibh;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out_end_trans;
ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
error = gfs2_dir_del(odip, &odentry->d_name);
if (error)
goto out_end_trans;
error = gfs2_dir_add(ndir, &ndentry->d_name, ip, IF2DT(ip->i_inode.i_mode));
if (error)
goto out_end_trans;
out_end_trans:
gfs2_trans_end(sdp);
out_ipreserv:
if (alloc_required)
gfs2_inplace_release(ndip);
out_gunlock_q:
if (alloc_required)
gfs2_quota_unlock(ndip);
out_alloc:
if (alloc_required)
gfs2_alloc_put(ndip);
out_gunlock:
gfs2_glock_dq_m(num_gh, ghs);
out_uninit:
for (x = 0; x < num_gh; x++)
gfs2_holder_uninit(ghs + x);
out_gunlock_r:
if (dir_rename)
gfs2_glock_dq_uninit(&r_gh);
out:
return error;
}
struct inode *gfs2_inode_lookup(struct super_block *sb,
unsigned int type,
u64 no_addr,
u64 no_formal_ino)
{
struct inode *inode;
struct gfs2_inode *ip;
struct gfs2_glock *io_gl = NULL;
int error;
inode = gfs2_iget(sb, no_addr);
ip = GFS2_I(inode);
if (!inode)
return ERR_PTR(-ENOBUFS);
if (inode->i_state & I_NEW) {
struct gfs2_sbd *sdp = GFS2_SB(inode);
ip->i_no_formal_ino = no_formal_ino;
error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (unlikely(error))
goto fail;
ip->i_gl->gl_object = ip;
error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (unlikely(error))
goto fail_put;
set_bit(GIF_INVALID, &ip->i_flags);
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail_iopen;
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
io_gl = NULL;
if ((type == DT_UNKNOWN) && (no_formal_ino == 0))
goto gfs2_nfsbypass;
inode->i_mode = DT2IF(type);
/*
* We must read the inode in order to work out its type in
* this case. Note that this doesn't happen often as we normally
* know the type beforehand. This code path only occurs during
* unlinked inode recovery (where it is safe to do this glock,
* which is not true in the general case).
*/
if (type == DT_UNKNOWN) {
struct gfs2_holder gh;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (unlikely(error))
goto fail_glock;
/* Inode is now uptodate */
gfs2_glock_dq_uninit(&gh);
}
gfs2_set_iop(inode);
}
gfs2_nfsbypass:
return inode;
fail_glock:
gfs2_glock_dq(&ip->i_iopen_gh);
fail_iopen:
if (io_gl)
gfs2_glock_put(io_gl);
fail_put:
if (inode->i_state & I_NEW)
ip->i_gl->gl_object = NULL;
gfs2_glock_put(ip->i_gl);
fail:
if (inode->i_state & I_NEW)
iget_failed(inode);
else
iput(inode);
return ERR_PTR(error);
}
static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
{
struct dentry *parent = dget_parent(dentry);
struct gfs2_sbd *sdp = GFS2_SB(parent->d_inode);
struct gfs2_inode *dip = GFS2_I(parent->d_inode);
struct inode *inode = dentry->d_inode;
struct gfs2_holder d_gh;
struct gfs2_inode *ip;
struct gfs2_inum_host inum;
unsigned int type;
int error;
int had_lock=0;
if (inode && is_bad_inode(inode))
goto invalid;
if (sdp->sd_args.ar_localcaching)
goto valid;
had_lock = gfs2_glock_is_locked_by_me(dip->i_gl);
if (!had_lock) {
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
if (error)
goto fail;
}
error = gfs2_dir_search(parent->d_inode, &dentry->d_name, &inum, &type);
switch (error) {
case 0:
if (!inode)
goto invalid_gunlock;
break;
case -ENOENT:
if (!inode)
goto valid_gunlock;
goto invalid_gunlock;
default:
goto fail_gunlock;
}
ip = GFS2_I(inode);
if (!gfs2_inum_equal(&ip->i_num, &inum))
goto invalid_gunlock;
if (IF2DT(ip->i_inode.i_mode) != type) {
gfs2_consist_inode(dip);
goto fail_gunlock;
}
valid_gunlock:
if (!had_lock)
gfs2_glock_dq_uninit(&d_gh);
valid:
dput(parent);
return 1;
invalid_gunlock:
if (!had_lock)
gfs2_glock_dq_uninit(&d_gh);
invalid:
if (inode && S_ISDIR(inode->i_mode)) {
if (have_submounts(dentry))
goto valid;
shrink_dcache_parent(dentry);
}
d_drop(dentry);
dput(parent);
return 0;
fail_gunlock:
gfs2_glock_dq_uninit(&d_gh);
fail:
dput(parent);
return 0;
}
static int gfs2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct gfs2_inode *ip = GFS2_I(mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
unsigned requested = 0;
int alloc_required;
int error = 0;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
struct page *page;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
error = gfs2_glock_nq(&ip->i_gh);
if (unlikely(error))
goto out_uninit;
if (&ip->i_inode == sdp->sd_rindex) {
error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
GL_NOCACHE, &m_ip->i_gh);
if (unlikely(error)) {
gfs2_glock_dq(&ip->i_gh);
goto out_uninit;
}
}
alloc_required = gfs2_write_alloc_required(ip, pos, len);
if (alloc_required || gfs2_is_jdata(ip))
gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
if (alloc_required) {
struct gfs2_alloc_parms ap = { .aflags = 0, };
requested = data_blocks + ind_blocks;
ap.target = requested;
error = gfs2_quota_lock_check(ip, &ap);
if (error)
goto out_unlock;
error = gfs2_inplace_reserve(ip, &ap);
if (error)
goto out_qunlock;
}
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;
if (&ip->i_inode == sdp->sd_rindex)
rblocks += 2 * RES_STATFS;
if (alloc_required)
rblocks += gfs2_rg_blocks(ip, requested);
error = gfs2_trans_begin(sdp, rblocks,
PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
if (error)
goto out_trans_fail;
error = -ENOMEM;
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, index, flags);
*pagep = page;
if (unlikely(!page))
goto out_endtrans;
if (gfs2_is_stuffed(ip)) {
error = 0;
if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
error = gfs2_unstuff_dinode(ip, page);
if (error == 0)
goto prepare_write;
} else if (!PageUptodate(page)) {
error = stuffed_readpage(ip, page);
}
goto out;
}
prepare_write:
error = __block_write_begin(page, from, len, gfs2_block_map);
out:
if (error == 0)
return 0;
unlock_page(page);
page_cache_release(page);
gfs2_trans_end(sdp);
if (pos + len > ip->i_inode.i_size)
gfs2_trim_blocks(&ip->i_inode);
goto out_trans_fail;
out_endtrans:
gfs2_trans_end(sdp);
out_trans_fail:
if (alloc_required) {
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
}
out_unlock:
if (&ip->i_inode == sdp->sd_rindex) {
gfs2_glock_dq(&m_ip->i_gh);
gfs2_holder_uninit(&m_ip->i_gh);
}
gfs2_glock_dq(&ip->i_gh);
out_uninit:
gfs2_holder_uninit(&ip->i_gh);
return error;
}
/**
* adjust_fs_space - Adjusts the free space available due to gfs2_grow
* @inode: the rindex inode
*/
static void adjust_fs_space(struct inode *inode)
{
struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct buffer_head *m_bh, *l_bh;
u64 fs_total, new_free;
/* Total up the file system space, according to the latest rindex. */
fs_total = gfs2_ri_total(sdp);
if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0)
return;
spin_lock(&sdp->sd_statfs_spin);
gfs2_statfs_change_in(m_sc, m_bh->b_data +
sizeof(struct gfs2_dinode));
if (fs_total > (m_sc->sc_total + l_sc->sc_total))
new_free = fs_total - (m_sc->sc_total + l_sc->sc_total);
else
new_free = 0;
spin_unlock(&sdp->sd_statfs_spin);
fs_warn(sdp, "File system extended by %llu blocks.\n",
(unsigned long long)new_free);
gfs2_statfs_change(sdp, new_free, new_free, 0);
if (gfs2_meta_inode_buffer(l_ip, &l_bh) != 0)
goto out;
update_statfs(sdp, m_bh, l_bh);
brelse(l_bh);
out:
brelse(m_bh);
}
/**
* gfs2_stuffed_write_end - Write end for stuffed files
* @inode: The inode
* @dibh: The buffer_head containing the on-disk inode
* @pos: The file position
* @len: The length of the write
* @copied: How much was actually copied by the VFS
* @page: The page
*
* This copies the data from the page into the inode block after
* the inode data structure itself.
*
* Returns: errno
*/
static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
loff_t pos, unsigned len, unsigned copied,
struct page *page)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
u64 to = pos + copied;
void *kaddr;
unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
kaddr = kmap_atomic(page);
memcpy(buf + pos, kaddr + pos, copied);
memset(kaddr + pos + copied, 0, len - copied);
flush_dcache_page(page);
kunmap_atomic(kaddr);
if (!PageUptodate(page))
SetPageUptodate(page);
unlock_page(page);
page_cache_release(page);
if (copied) {
if (inode->i_size < to)
i_size_write(inode, to);
mark_inode_dirty(inode);
}
if (inode == sdp->sd_rindex) {
adjust_fs_space(inode);
sdp->sd_rindex_uptodate = 0;
}
brelse(dibh);
gfs2_trans_end(sdp);
if (inode == sdp->sd_rindex) {
gfs2_glock_dq(&m_ip->i_gh);
gfs2_holder_uninit(&m_ip->i_gh);
}
gfs2_glock_dq(&ip->i_gh);
gfs2_holder_uninit(&ip->i_gh);
return copied;
}
/**
* gfs2_write_end
* @file: The file to write to
* @mapping: The address space to write to
* @pos: The file position
* @len: The length of the data
* @copied:
* @page: The page that has been written
* @fsdata: The fsdata (unused in GFS2)
*
* The main write_end function for GFS2. We have a separate one for
* stuffed files as they are slightly different, otherwise we just
* put our locking around the VFS provided functions.
*
* Returns: errno
*/
static int gfs2_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
struct buffer_head *dibh;
unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
unsigned int to = from + len;
int ret;
struct gfs2_trans *tr = current->journal_info;
BUG_ON(!tr);
BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
ret = gfs2_meta_inode_buffer(ip, &dibh);
if (unlikely(ret)) {
unlock_page(page);
page_cache_release(page);
goto failed;
}
if (gfs2_is_stuffed(ip))
return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
if (!gfs2_is_writeback(ip))
gfs2_page_add_databufs(ip, page, from, to);
ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
if (tr->tr_num_buf_new)
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
else
gfs2_trans_add_meta(ip->i_gl, dibh);
if (inode == sdp->sd_rindex) {
adjust_fs_space(inode);
sdp->sd_rindex_uptodate = 0;
}
brelse(dibh);
failed:
gfs2_trans_end(sdp);
gfs2_inplace_release(ip);
if (ip->i_res->rs_qa_qd_num)
gfs2_quota_unlock(ip);
if (inode == sdp->sd_rindex) {
gfs2_glock_dq(&m_ip->i_gh);
gfs2_holder_uninit(&m_ip->i_gh);
}
gfs2_glock_dq(&ip->i_gh);
gfs2_holder_uninit(&ip->i_gh);
return ret;
}
/**
* gfs2_set_page_dirty - Page dirtying function
* @page: The page to dirty
*
* Returns: 1 if it dirtyed the page, or 0 otherwise
*/
static int gfs2_set_page_dirty(struct page *page)
{
SetPageChecked(page);
return __set_page_dirty_buffers(page);
}
static int gfs2_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct gfs2_inode *ip = GFS2_I(mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
int alloc_required;
int error = 0;
struct gfs2_qadata *qa = NULL;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
struct page *page;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
error = gfs2_glock_nq(&ip->i_gh);
if (unlikely(error))
goto out_uninit;
if (&ip->i_inode == sdp->sd_rindex) {
error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
GL_NOCACHE, &m_ip->i_gh);
if (unlikely(error)) {
gfs2_glock_dq(&ip->i_gh);
goto out_uninit;
}
}
alloc_required = gfs2_write_alloc_required(ip, pos, len);
if (alloc_required || gfs2_is_jdata(ip))
gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
if (alloc_required) {
qa = gfs2_qadata_get(ip);
if (!qa) {
error = -ENOMEM;
goto out_unlock;
}
error = gfs2_quota_lock_check(ip);
if (error)
goto out_alloc_put;
error = gfs2_inplace_reserve(ip, data_blocks + ind_blocks);
if (error)
goto out_qunlock;
}
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;
if (&ip->i_inode == sdp->sd_rindex)
rblocks += 2 * RES_STATFS;
if (alloc_required)
rblocks += gfs2_rg_blocks(ip);
error = gfs2_trans_begin(sdp, rblocks,
PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
if (error)
goto out_trans_fail;
error = -ENOMEM;
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, index, flags);
*pagep = page;
if (unlikely(!page))
goto out_endtrans;
if (gfs2_is_stuffed(ip)) {
error = 0;
if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
error = gfs2_unstuff_dinode(ip, page);
if (error == 0)
goto prepare_write;
} else if (!PageUptodate(page)) {
error = stuffed_readpage(ip, page);
}
goto out;
}
prepare_write:
error = __block_write_begin(page, from, len, gfs2_block_map);
out:
if (error == 0)
return 0;
unlock_page(page);
page_cache_release(page);
gfs2_trans_end(sdp);
if (pos + len > ip->i_inode.i_size)
gfs2_trim_blocks(&ip->i_inode);
goto out_trans_fail;
out_endtrans:
gfs2_trans_end(sdp);
out_trans_fail:
if (alloc_required) {
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
out_alloc_put:
gfs2_qadata_put(ip);
}
out_unlock:
if (&ip->i_inode == sdp->sd_rindex) {
gfs2_glock_dq(&m_ip->i_gh);
gfs2_holder_uninit(&m_ip->i_gh);
}
gfs2_glock_dq(&ip->i_gh);
out_uninit:
gfs2_holder_uninit(&ip->i_gh);
return error;
}
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);
}
void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr)
{
struct gfs2_sbd *sdp;
struct gfs2_inode *ip;
struct gfs2_glock *io_gl = NULL;
int error;
struct gfs2_holder gh;
struct inode *inode;
inode = gfs2_iget_skip(sb, no_addr);
if (!inode)
return;
/* If it's not a new inode, someone's using it, so leave it alone. */
if (!(inode->i_state & I_NEW)) {
iput(inode);
return;
}
ip = GFS2_I(inode);
sdp = GFS2_SB(inode);
ip->i_no_formal_ino = -1;
error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (unlikely(error))
goto fail;
ip->i_gl->gl_object = ip;
error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (unlikely(error))
goto fail_put;
set_bit(GIF_INVALID, &ip->i_flags);
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, LM_FLAG_TRY | GL_EXACT,
&ip->i_iopen_gh);
if (unlikely(error))
goto fail_iopen;
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
io_gl = NULL;
inode->i_mode = DT2IF(DT_UNKNOWN);
/*
* We must read the inode in order to work out its type in
* this case. Note that this doesn't happen often as we normally
* know the type beforehand. This code path only occurs during
* unlinked inode recovery (where it is safe to do this glock,
* which is not true in the general case).
*/
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, LM_FLAG_TRY,
&gh);
if (unlikely(error))
goto fail_glock;
/* Inode is now uptodate */
gfs2_glock_dq_uninit(&gh);
gfs2_set_iop(inode);
/* The iput will cause it to be deleted. */
iput(inode);
return;
fail_glock:
gfs2_glock_dq(&ip->i_iopen_gh);
fail_iopen:
if (io_gl)
gfs2_glock_put(io_gl);
fail_put:
ip->i_gl->gl_object = NULL;
gfs2_glock_put(ip->i_gl);
fail:
iget_failed(inode);
return;
}
/**
* gfs2_set_flags - set flags on an inode
* @inode: The inode
* @flags: The flags to set
* @mask: Indicates which flags are valid
*
*/
static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *bh;
struct gfs2_holder gh;
int error;
u32 new_flags, flags;
error = mnt_want_write(filp->f_path.mnt);
if (error)
return error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (error)
goto out_drop_write;
error = -EACCES;
if (!is_owner_or_cap(inode))
goto out;
error = 0;
flags = ip->i_diskflags;
new_flags = (flags & ~mask) | (reqflags & mask);
if ((new_flags ^ flags) == 0)
goto out;
error = -EINVAL;
if ((new_flags ^ flags) & ~GFS2_FLAGS_USER_SET)
goto out;
error = -EPERM;
if (IS_IMMUTABLE(inode) && (new_flags & GFS2_DIF_IMMUTABLE))
goto out;
if (IS_APPEND(inode) && (new_flags & GFS2_DIF_APPENDONLY))
goto out;
if (((new_flags ^ flags) & GFS2_DIF_IMMUTABLE) &&
!capable(CAP_LINUX_IMMUTABLE))
goto out;
if (!IS_IMMUTABLE(inode)) {
error = gfs2_permission(inode, MAY_WRITE);
if (error)
goto out;
}
if ((flags ^ new_flags) & GFS2_DIF_JDATA) {
if (flags & GFS2_DIF_JDATA)
gfs2_log_flush(sdp, ip->i_gl);
error = filemap_fdatawrite(inode->i_mapping);
if (error)
goto out;
error = filemap_fdatawait(inode->i_mapping);
if (error)
goto out;
}
error = gfs2_trans_begin(sdp, RES_DINODE, 0);
if (error)
goto out;
error = gfs2_meta_inode_buffer(ip, &bh);
if (error)
goto out_trans_end;
gfs2_trans_add_meta(ip->i_gl, bh);
ip->i_diskflags = new_flags;
gfs2_dinode_out(ip, bh->b_data);
brelse(bh);
gfs2_set_inode_flags(inode);
gfs2_set_aops(inode);
out_trans_end:
gfs2_trans_end(sdp);
out:
gfs2_glock_dq_uninit(&gh);
out_drop_write:
mnt_drop_write(filp->f_path.mnt);
return error;
}
static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
struct gfs2_inode *ip, struct gfs2_diradd *da)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_alloc_parms ap = { .target = da->nr_blocks, };
int error;
if (da->nr_blocks) {
error = gfs2_quota_lock_check(dip);
if (error)
goto fail_quota_locks;
error = gfs2_inplace_reserve(dip, &ap);
if (error)
goto fail_quota_locks;
error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, da, 2), 0);
if (error)
goto fail_ipreserv;
} else {
error = gfs2_trans_begin(sdp, RES_LEAF + 2 * RES_DINODE, 0);
if (error)
goto fail_quota_locks;
}
error = gfs2_dir_add(&dip->i_inode, name, ip, da);
if (error)
goto fail_end_trans;
fail_end_trans:
gfs2_trans_end(sdp);
fail_ipreserv:
gfs2_inplace_release(dip);
fail_quota_locks:
gfs2_quota_unlock(dip);
return error;
}
static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
void *fs_info)
{
const struct xattr *xattr;
int err = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
err = __gfs2_xattr_set(inode, xattr->name, xattr->value,
xattr->value_len, 0,
GFS2_EATYPE_SECURITY);
if (err < 0)
break;
}
return err;
}
static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
const struct qstr *qstr)
{
return security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr,
&gfs2_initxattrs, NULL);
}
/**
* gfs2_create_inode - Create a new inode
* @dir: The parent directory
* @dentry: The new dentry
* @file: If non-NULL, the file which is being opened
* @mode: The permissions on the new inode
* @dev: For device nodes, this is the device number
* @symname: For symlinks, this is the link destination
* @size: The initial size of the inode (ignored for directories)
*
* Returns: 0 on success, or error code
*/
static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
struct file *file,
umode_t mode, dev_t dev, const char *symname,
unsigned int size, int excl, int *opened)
{
const struct qstr *name = &dentry->d_name;
struct posix_acl *default_acl, *acl;
struct gfs2_holder ghs[2];
struct inode *inode = NULL;
struct gfs2_inode *dip = GFS2_I(dir), *ip;
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_glock *io_gl;
struct dentry *d;
int error;
u32 aflags = 0;
struct gfs2_diradd da = { .bh = NULL, };
if (!name->len || name->len > GFS2_FNAMESIZE)
return -ENAMETOOLONG;
error = gfs2_rs_alloc(dip);
if (error)
return error;
error = gfs2_rindex_update(sdp);
if (error)
return error;
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (error)
goto fail;
error = create_ok(dip, name, mode);
if (error)
goto fail_gunlock;
inode = gfs2_dir_search(dir, &dentry->d_name, !S_ISREG(mode) || excl);
error = PTR_ERR(inode);
if (!IS_ERR(inode)) {
d = d_splice_alias(inode, dentry);
error = PTR_ERR(d);
if (IS_ERR(d)) {
inode = ERR_CAST(d);
goto fail_gunlock;
}
error = 0;
if (file) {
if (S_ISREG(inode->i_mode)) {
WARN_ON(d != NULL);
error = finish_open(file, dentry, gfs2_open_common, opened);
} else {
error = finish_no_open(file, d);
}
} else {
dput(d);
}
gfs2_glock_dq_uninit(ghs);
return error;
} else if (error != -ENOENT) {
goto fail_gunlock;
}
error = gfs2_diradd_alloc_required(dir, name, &da);
if (error < 0)
goto fail_gunlock;
inode = new_inode(sdp->sd_vfs);
error = -ENOMEM;
if (!inode)
goto fail_gunlock;
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
goto fail_free_vfs_inode;
ip = GFS2_I(inode);
error = gfs2_rs_alloc(ip);
if (error)
goto fail_free_acls;
inode->i_mode = mode;
set_nlink(inode, S_ISDIR(mode) ? 2 : 1);
inode->i_rdev = dev;
inode->i_size = size;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
gfs2_set_inode_blocks(inode, 1);
munge_mode_uid_gid(dip, inode);
ip->i_goal = dip->i_goal;
ip->i_diskflags = 0;
ip->i_eattr = 0;
ip->i_height = 0;
ip->i_depth = 0;
ip->i_entries = 0;
switch(mode & S_IFMT) {
case S_IFREG:
if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
gfs2_tune_get(sdp, gt_new_files_jdata))
ip->i_diskflags |= GFS2_DIF_JDATA;
gfs2_set_aops(inode);
break;
case S_IFDIR:
ip->i_diskflags |= (dip->i_diskflags & GFS2_DIF_INHERIT_JDATA);
ip->i_diskflags |= GFS2_DIF_JDATA;
ip->i_entries = 2;
break;
}
gfs2_set_inode_flags(inode);
if ((GFS2_I(sdp->sd_root_dir->d_inode) == dip) ||
(dip->i_diskflags & GFS2_DIF_TOPDIR))
aflags |= GFS2_AF_ORLOV;
error = alloc_dinode(ip, aflags);
if (error)
goto fail_free_inode;
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (error)
goto fail_free_inode;
ip->i_gl->gl_object = ip;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
if (error)
goto fail_free_inode;
error = gfs2_trans_begin(sdp, RES_DINODE, 0);
if (error)
goto fail_gunlock2;
init_dinode(dip, ip, symname);
gfs2_trans_end(sdp);
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (error)
goto fail_gunlock2;
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (error)
goto fail_gunlock2;
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
gfs2_set_iop(inode);
insert_inode_hash(inode);
if (default_acl) {
error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
posix_acl_release(default_acl);
}
if (acl) {
if (!error)
error = gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS);
posix_acl_release(acl);
}
if (error)
goto fail_gunlock3;
error = gfs2_security_init(dip, ip, name);
if (error)
goto fail_gunlock3;
error = link_dinode(dip, name, ip, &da);
if (error)
goto fail_gunlock3;
mark_inode_dirty(inode);
d_instantiate(dentry, inode);
if (file) {
*opened |= FILE_CREATED;
error = finish_open(file, dentry, gfs2_open_common, opened);
}
gfs2_glock_dq_uninit(ghs);
gfs2_glock_dq_uninit(ghs + 1);
return error;
fail_gunlock3:
gfs2_glock_dq_uninit(ghs + 1);
if (ip->i_gl)
gfs2_glock_put(ip->i_gl);
goto fail_gunlock;
fail_gunlock2:
gfs2_glock_dq_uninit(ghs + 1);
fail_free_inode:
if (ip->i_gl)
gfs2_glock_put(ip->i_gl);
gfs2_rs_delete(ip, NULL);
fail_free_acls:
if (default_acl)
posix_acl_release(default_acl);
if (acl)
posix_acl_release(acl);
fail_free_vfs_inode:
free_inode_nonrcu(inode);
inode = NULL;
fail_gunlock:
gfs2_dir_no_add(&da);
gfs2_glock_dq_uninit(ghs);
if (inode && !IS_ERR(inode)) {
clear_nlink(inode);
mark_inode_dirty(inode);
set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
iput(inode);
}
fail:
return error;
}
/**
* gfs2_create - Create a file
* @dir: The directory in which to create the file
* @dentry: The dentry of the new file
* @mode: The mode of the new file
*
* Returns: errno
*/
static int gfs2_create(struct inode *dir, struct dentry *dentry,
umode_t mode, bool excl)
{
return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl, NULL);
}
/**
* __gfs2_lookup - Look up a filename in a directory and return its inode
* @dir: The directory inode
* @dentry: The dentry of the new inode
* @file: File to be opened
* @opened: atomic_open flags
*
*
* Returns: errno
*/
static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
struct file *file, int *opened)
{
struct inode *inode;
struct dentry *d;
struct gfs2_holder gh;
struct gfs2_glock *gl;
int error;
inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (!inode)
return NULL;
if (IS_ERR(inode))
return ERR_CAST(inode);
gl = GFS2_I(inode)->i_gl;
error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
if (error) {
iput(inode);
return ERR_PTR(error);
}
d = d_splice_alias(inode, dentry);
if (IS_ERR(d)) {
gfs2_glock_dq_uninit(&gh);
return d;
}
if (file && S_ISREG(inode->i_mode))
error = finish_open(file, dentry, gfs2_open_common, opened);
gfs2_glock_dq_uninit(&gh);
if (error) {
dput(d);
return ERR_PTR(error);
}
return d;
}
static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
unsigned flags)
{
return __gfs2_lookup(dir, dentry, NULL, NULL);
}
/**
* gfs2_link - Link to a file
* @old_dentry: The inode to link
* @dir: Add link to this directory
* @dentry: The name of the link
*
* Link the inode in "old_dentry" into the directory "dir" with the
* name in "dentry".
*
* Returns: errno
*/
static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(dir);
struct inode *inode = old_dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder ghs[2];
struct buffer_head *dibh;
struct gfs2_diradd da = { .bh = NULL, };
int error;
if (S_ISDIR(inode->i_mode))
return -EPERM;
error = gfs2_rs_alloc(dip);
if (error)
return error;
gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
error = gfs2_glock_nq(ghs); /* parent */
if (error)
goto out_parent;
error = gfs2_glock_nq(ghs + 1); /* child */
if (error)
goto out_child;
error = -ENOENT;
if (inode->i_nlink == 0)
goto out_gunlock;
error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
error = gfs2_dir_check(dir, &dentry->d_name, NULL);
switch (error) {
case -ENOENT:
break;
case 0:
error = -EEXIST;
default:
goto out_gunlock;
}
error = -EINVAL;
if (!dip->i_inode.i_nlink)
goto out_gunlock;
error = -EFBIG;
if (dip->i_entries == (u32)-1)
goto out_gunlock;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out_gunlock;
error = -EINVAL;
if (!ip->i_inode.i_nlink)
goto out_gunlock;
error = -EMLINK;
if (ip->i_inode.i_nlink == (u32)-1)
goto out_gunlock;
error = gfs2_diradd_alloc_required(dir, &dentry->d_name, &da);
if (error < 0)
goto out_gunlock;
if (da.nr_blocks) {
struct gfs2_alloc_parms ap = { .target = da.nr_blocks, };
error = gfs2_quota_lock_check(dip);
if (error)
goto out_gunlock;
error = gfs2_inplace_reserve(dip, &ap);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, gfs2_trans_da_blks(dip, &da, 2), 0);
if (error)
goto out_ipres;
} else {
error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
if (error)
goto out_ipres;
}
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out_end_trans;
error = gfs2_dir_add(dir, &dentry->d_name, ip, &da);
if (error)
goto out_brelse;
gfs2_trans_add_meta(ip->i_gl, dibh);
inc_nlink(&ip->i_inode);
ip->i_inode.i_ctime = CURRENT_TIME;
ihold(inode);
d_instantiate(dentry, inode);
mark_inode_dirty(inode);
out_brelse:
brelse(dibh);
out_end_trans:
gfs2_trans_end(sdp);
out_ipres:
if (da.nr_blocks)
gfs2_inplace_release(dip);
out_gunlock_q:
if (da.nr_blocks)
gfs2_quota_unlock(dip);
out_gunlock:
gfs2_dir_no_add(&da);
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs);
gfs2_holder_uninit(ghs + 1);
return error;
}
/*
* gfs2_unlink_ok - check to see that a inode is still in a directory
* @dip: the directory
* @name: the name of the file
* @ip: the inode
*
* Assumes that the lock on (at least) @dip is held.
*
* Returns: 0 if the parent/child relationship is correct, errno if it isn't
*/
static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
const struct gfs2_inode *ip)
{
int error;
if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
return -EPERM;
if ((dip->i_inode.i_mode & S_ISVTX) &&
!uid_eq(dip->i_inode.i_uid, current_fsuid()) &&
!uid_eq(ip->i_inode.i_uid, current_fsuid()) && !capable(CAP_FOWNER))
return -EPERM;
if (IS_APPEND(&dip->i_inode))
return -EPERM;
error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
error = gfs2_dir_check(&dip->i_inode, name, ip);
if (error)
return error;
return 0;
}
struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
u64 no_addr, u64 no_formal_ino, int non_block)
{
struct inode *inode;
struct gfs2_inode *ip;
struct gfs2_glock *io_gl = NULL;
int error;
inode = gfs2_iget(sb, no_addr, non_block);
ip = GFS2_I(inode);
if (!inode)
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
struct gfs2_sbd *sdp = GFS2_SB(inode);
ip->i_no_formal_ino = no_formal_ino;
error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (unlikely(error))
goto fail;
ip->i_gl->gl_object = ip;
error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (unlikely(error))
goto fail_put;
set_bit(GIF_INVALID, &ip->i_flags);
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
goto fail_iopen;
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
io_gl = NULL;
if (type == DT_UNKNOWN) {
/* Inode glock must be locked already */
error = gfs2_inode_refresh(GFS2_I(inode));
if (error)
goto fail_refresh;
} else {
inode->i_mode = DT2IF(type);
}
gfs2_set_iop(inode);
unlock_new_inode(inode);
}
return inode;
fail_refresh:
ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
ip->i_iopen_gh.gh_gl->gl_object = NULL;
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
fail_iopen:
if (io_gl)
gfs2_glock_put(io_gl);
fail_put:
ip->i_gl->gl_object = NULL;
gfs2_glock_put(ip->i_gl);
fail:
iget_failed(inode);
return ERR_PTR(error);
}
static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
umode_t mode, dev_t dev, const char *symname,
unsigned int size, int excl)
{
const struct qstr *name = &dentry->d_name;
struct gfs2_holder ghs[2];
struct inode *inode = NULL;
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
int error;
u64 generation;
struct buffer_head *bh = NULL;
if (!name->len || name->len > GFS2_FNAMESIZE)
return -ENAMETOOLONG;
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (error)
goto fail;
error = create_ok(dip, name, mode);
if ((error == -EEXIST) && S_ISREG(mode) && !excl) {
inode = gfs2_lookupi(dir, &dentry->d_name, 0);
gfs2_glock_dq_uninit(ghs);
d_instantiate(dentry, inode);
return IS_ERR(inode) ? PTR_ERR(inode) : 0;
}
if (error)
goto fail_gunlock;
error = alloc_dinode(dip, &inum.no_addr, &generation);
if (error)
goto fail_gunlock;
inum.no_formal_ino = generation;
error = gfs2_glock_nq_num(sdp, inum.no_addr, &gfs2_inode_glops,
LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
if (error)
goto fail_gunlock;
error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, symname, size, &bh);
if (error)
goto fail_gunlock2;
inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr,
inum.no_formal_ino, 0);
if (IS_ERR(inode))
goto fail_gunlock2;
error = gfs2_inode_refresh(GFS2_I(inode));
if (error)
goto fail_gunlock2;
error = gfs2_acl_create(dip, inode);
if (error)
goto fail_gunlock2;
error = gfs2_security_init(dip, GFS2_I(inode), name);
if (error)
goto fail_gunlock2;
error = link_dinode(dip, name, GFS2_I(inode));
if (error)
goto fail_gunlock2;
if (bh)
brelse(bh);
gfs2_trans_end(sdp);
/* Check if we reserved space in the rgrp. Function link_dinode may
not, depending on whether alloc is required. */
if (dip->i_res)
gfs2_inplace_release(dip);
gfs2_quota_unlock(dip);
gfs2_qadata_put(dip);
mark_inode_dirty(inode);
gfs2_glock_dq_uninit_m(2, ghs);
d_instantiate(dentry, inode);
return 0;
fail_gunlock2:
gfs2_glock_dq_uninit(ghs + 1);
fail_gunlock:
gfs2_glock_dq_uninit(ghs);
if (inode && !IS_ERR(inode)) {
set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
iput(inode);
}
fail:
if (bh)
brelse(bh);
return error;
}
/**
* gfs2_create - Create a file
* @dir: The directory in which to create the file
* @dentry: The dentry of the new file
* @mode: The mode of the new file
*
* Returns: errno
*/
static int gfs2_create(struct inode *dir, struct dentry *dentry,
umode_t mode, struct nameidata *nd)
{
int excl = 0;
if (nd && (nd->flags & LOOKUP_EXCL))
excl = 1;
return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl);
}
static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
{
struct dentry *parent;
struct gfs2_sbd *sdp;
struct gfs2_inode *dip;
struct inode *inode;
struct gfs2_holder d_gh;
struct gfs2_inode *ip = NULL;
int error;
int had_lock = 0;
if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
sdp = GFS2_SB(parent->d_inode);
dip = GFS2_I(parent->d_inode);
inode = dentry->d_inode;
if (inode) {
if (is_bad_inode(inode))
goto invalid;
ip = GFS2_I(inode);
}
if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
goto valid;
had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
if (!had_lock) {
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
if (error)
goto fail;
}
error = gfs2_dir_check(parent->d_inode, &dentry->d_name, ip);
switch (error) {
case 0:
if (!inode)
goto invalid_gunlock;
break;
case -ENOENT:
if (!inode)
goto valid_gunlock;
goto invalid_gunlock;
default:
goto fail_gunlock;
}
valid_gunlock:
if (!had_lock)
gfs2_glock_dq_uninit(&d_gh);
valid:
dput(parent);
return 1;
invalid_gunlock:
if (!had_lock)
gfs2_glock_dq_uninit(&d_gh);
invalid:
if (inode && S_ISDIR(inode->i_mode)) {
if (have_submounts(dentry))
goto valid;
shrink_dcache_parent(dentry);
}
d_drop(dentry);
dput(parent);
return 0;
fail_gunlock:
gfs2_glock_dq_uninit(&d_gh);
fail:
dput(parent);
return 0;
}