static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
const char *symname)
{
struct gfs2_dinode *di;
struct buffer_head *dibh;
dibh = gfs2_meta_new(ip->i_gl, ip->i_no_addr);
gfs2_trans_add_meta(ip->i_gl, dibh);
di = (struct gfs2_dinode *)dibh->b_data;
gfs2_dinode_out(ip, di);
di->di_major = cpu_to_be32(MAJOR(ip->i_inode.i_rdev));
di->di_minor = cpu_to_be32(MINOR(ip->i_inode.i_rdev));
di->__pad1 = 0;
di->__pad2 = 0;
di->__pad3 = 0;
memset(&di->__pad4, 0, sizeof(di->__pad4));
memset(&di->di_reserved, 0, sizeof(di->di_reserved));
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
switch(ip->i_inode.i_mode & S_IFMT) {
case S_IFDIR:
gfs2_init_dir(dibh, dip);
break;
case S_IFLNK:
memcpy(dibh->b_data + sizeof(struct gfs2_dinode), symname, ip->i_inode.i_size);
break;
}
set_buffer_uptodate(dibh);
brelse(dibh);
}
void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
s64 dinodes)
{
struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct buffer_head *l_bh;
s64 x, y;
int need_sync = 0;
int error;
error = gfs2_meta_inode_buffer(l_ip, &l_bh);
if (error)
return;
gfs2_trans_add_meta(l_ip->i_gl, l_bh);
spin_lock(&sdp->sd_statfs_spin);
l_sc->sc_total += total;
l_sc->sc_free += free;
l_sc->sc_dinodes += dinodes;
gfs2_statfs_change_out(l_sc, l_bh->b_data + sizeof(struct gfs2_dinode));
if (sdp->sd_args.ar_statfs_percent) {
x = 100 * l_sc->sc_free;
y = m_sc->sc_free * sdp->sd_args.ar_statfs_percent;
if (x >= y || x <= -y)
need_sync = 1;
}
spin_unlock(&sdp->sd_statfs_spin);
brelse(l_bh);
if (need_sync)
gfs2_wake_up_statfs(sdp);
}
int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
{
struct buffer_head *bh, *dibh;
struct gfs2_dinode *di;
u64 block = 0;
int isdir = gfs2_is_dir(ip);
int error;
down_write(&ip->i_rw_mutex);
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out;
if (i_size_read(&ip->i_inode)) {
/* Get a free block, fill it with the stuffed data,
and write it out to disk */
unsigned int n = 1;
error = gfs2_alloc_blocks(ip, &block, &n, 0, NULL);
if (error)
goto out_brelse;
if (isdir) {
gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1);
error = gfs2_dir_get_new_buffer(ip, block, &bh);
if (error)
goto out_brelse;
gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_meta_header),
dibh, sizeof(struct gfs2_dinode));
brelse(bh);
} else {
error = gfs2_unstuffer_page(ip, dibh, block, page);
if (error)
goto out_brelse;
}
}
/* Set up the pointer to the new block */
gfs2_trans_add_meta(ip->i_gl, dibh);
di = (struct gfs2_dinode *)dibh->b_data;
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
if (i_size_read(&ip->i_inode)) {
*(__be64 *)(di + 1) = cpu_to_be64(block);
gfs2_add_inode_blocks(&ip->i_inode, 1);
di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
}
ip->i_height = 1;
di->di_height = cpu_to_be16(1);
out_brelse:
brelse(dibh);
out:
up_write(&ip->i_rw_mutex);
return error;
}
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;
}
void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
struct buffer_head *l_bh)
{
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;
gfs2_trans_add_meta(l_ip->i_gl, l_bh);
gfs2_trans_add_meta(m_ip->i_gl, m_bh);
spin_lock(&sdp->sd_statfs_spin);
m_sc->sc_total += l_sc->sc_total;
m_sc->sc_free += l_sc->sc_free;
m_sc->sc_dinodes += l_sc->sc_dinodes;
memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
memset(l_bh->b_data + sizeof(struct gfs2_dinode),
0, sizeof(struct gfs2_statfs_change));
gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
spin_unlock(&sdp->sd_statfs_spin);
}
static inline __be64 *gfs2_indirect_init(struct metapath *mp,
struct gfs2_glock *gl, unsigned int i,
unsigned offset, u64 bn)
{
__be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data +
((i > 1) ? sizeof(struct gfs2_meta_header) :
sizeof(struct gfs2_dinode)));
BUG_ON(i < 1);
BUG_ON(mp->mp_bh[i] != NULL);
mp->mp_bh[i] = gfs2_meta_new(gl, bn);
gfs2_trans_add_meta(gl, mp->mp_bh[i]);
gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN);
gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header));
ptr += offset;
*ptr = cpu_to_be64(bn);
return ptr;
}
static void gfs2_init_xattr(struct gfs2_inode *ip)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct buffer_head *bh;
struct gfs2_ea_header *ea;
bh = gfs2_meta_new(ip->i_gl, ip->i_eattr);
gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_metatype_set(bh, GFS2_METATYPE_EA, GFS2_FORMAT_EA);
gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
ea = GFS2_EA_BH2FIRST(bh);
ea->ea_rec_len = cpu_to_be32(sdp->sd_jbsize);
ea->ea_type = GFS2_EATYPE_UNUSED;
ea->ea_flags = GFS2_EAFLAG_LAST;
brelse(bh);
}
static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
struct gfs2_inode *ip)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
int alloc_required;
struct buffer_head *dibh;
int error;
error = gfs2_rindex_update(sdp);
if (error)
return error;
error = gfs2_quota_lock(dip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
if (error)
goto fail;
error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name);
if (alloc_required < 0)
goto fail_quota_locks;
if (alloc_required) {
error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid);
if (error)
goto fail_quota_locks;
error = gfs2_inplace_reserve(dip, sdp->sd_max_dirres, 0);
if (error)
goto fail_quota_locks;
error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
dip->i_rgd->rd_length +
2 * RES_DINODE +
RES_STATFS + RES_QUOTA, 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);
if (error)
goto fail_end_trans;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto fail_end_trans;
set_nlink(&ip->i_inode, S_ISDIR(ip->i_inode.i_mode) ? 2 : 1);
gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
return 0;
fail_end_trans:
gfs2_trans_end(sdp);
fail_ipreserv:
if (alloc_required)
gfs2_inplace_release(dip);
fail_quota_locks:
gfs2_quota_unlock(dip);
fail:
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, &ap);
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);
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;
}
/**
* 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)
{
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 = NULL;
int error, free_vfs_inode = 1;
u32 aflags = 0;
unsigned blocks = 1;
struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
if (!name->len || name->len > GFS2_FNAMESIZE)
return -ENAMETOOLONG;
error = gfs2_rsqa_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;
gfs2_holder_mark_uninitialized(ghs + 1);
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)) {
if (S_ISDIR(inode->i_mode)) {
iput(inode);
inode = ERR_PTR(-EISDIR);
goto fail_gunlock;
}
d_instantiate(dentry, inode);
error = 0;
if (file) {
if (S_ISREG(inode->i_mode))
error = finish_open(file, dentry, gfs2_open_common);
else
error = finish_no_open(file, NULL);
}
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_gunlock;
ip = GFS2_I(inode);
error = gfs2_rsqa_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(inode);
gfs2_set_inode_blocks(inode, 1);
munge_mode_uid_gid(dip, inode);
check_and_update_goal(dip);
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;
ip->i_no_addr = 0; /* Temporarily zero until real addr is assigned */
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;
}
/* Force SYSTEM flag on all files and subdirs of a SYSTEM directory */
if (dip->i_diskflags & GFS2_DIF_SYSTEM)
ip->i_diskflags |= GFS2_DIF_SYSTEM;
gfs2_set_inode_flags(inode);
if ((GFS2_I(d_inode(sdp->sd_root_dir)) == dip) ||
(dip->i_diskflags & GFS2_DIF_TOPDIR))
aflags |= GFS2_AF_ORLOV;
if (default_acl || acl)
blocks++;
error = alloc_dinode(ip, aflags, &blocks);
if (error)
goto fail_free_inode;
gfs2_set_inode_blocks(inode, blocks);
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (error)
goto fail_free_inode;
flush_delayed_work(&ip->i_gl->gl_work);
glock_set_object(ip->i_gl, 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, blocks, 0);
if (error)
goto fail_gunlock2;
if (blocks > 1) {
ip->i_eattr = ip->i_no_addr + 1;
gfs2_init_xattr(ip);
}
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;
BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (error)
goto fail_gunlock2;
glock_set_object(ip->i_iopen_gh.gh_gl, ip);
gfs2_glock_put(io_gl);
gfs2_set_iop(inode);
insert_inode_hash(inode);
free_vfs_inode = 0; /* After this point, the inode is no longer
considered free. Any failures need to undo
the gfs2 structures. */
if (default_acl) {
error = __gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
if (error)
goto fail_gunlock3;
posix_acl_release(default_acl);
default_acl = NULL;
}
if (acl) {
error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS);
if (error)
goto fail_gunlock3;
posix_acl_release(acl);
acl = NULL;
}
error = security_inode_init_security(&ip->i_inode, &dip->i_inode, name,
&gfs2_initxattrs, NULL);
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) {
file->f_mode |= FMODE_CREATED;
error = finish_open(file, dentry, gfs2_open_common);
}
gfs2_glock_dq_uninit(ghs);
gfs2_glock_dq_uninit(ghs + 1);
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
return error;
fail_gunlock3:
glock_clear_object(io_gl, ip);
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
gfs2_glock_put(io_gl);
fail_gunlock2:
if (io_gl)
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
fail_free_inode:
if (ip->i_gl) {
glock_clear_object(ip->i_gl, ip);
gfs2_glock_put(ip->i_gl);
}
gfs2_rsqa_delete(ip, NULL);
fail_free_acls:
posix_acl_release(default_acl);
posix_acl_release(acl);
fail_gunlock:
gfs2_dir_no_add(&da);
gfs2_glock_dq_uninit(ghs);
if (inode && !IS_ERR(inode)) {
clear_nlink(inode);
if (!free_vfs_inode)
mark_inode_dirty(inode);
set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED,
&GFS2_I(inode)->i_flags);
iput(inode);
}
if (gfs2_holder_initialized(ghs + 1))
gfs2_glock_dq_uninit(ghs + 1);
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);
}
/**
* __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
*
*
* Returns: errno
*/
static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
struct file *file)
{
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 == NULL) {
d_add(dentry, NULL);
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);
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);
}
/**
* 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 = d_inode(old_dentry);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder ghs[2];
struct buffer_head *dibh;
struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
int error;
if (S_ISDIR(inode->i_mode))
return -EPERM;
error = gfs2_rsqa_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, &ap);
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(&ip->i_inode);
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;
return gfs2_dir_check(&dip->i_inode, name, ip);
}
/**
* gfs2_unlink_inode - Removes an inode from its parent dir and unlinks it
* @dip: The parent directory
* @name: The name of the entry in the parent directory
* @inode: The inode to be removed
*
* Called with all the locks and in a transaction. This will only be
* called for a directory after it has been checked to ensure it is empty.
*
* Returns: 0 on success, or an error
*/
static int gfs2_unlink_inode(struct gfs2_inode *dip,
const struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
int error;
error = gfs2_dir_del(dip, dentry);
if (error)
return error;
ip->i_entries = 0;
inode->i_ctime = current_time(inode);
if (S_ISDIR(inode->i_mode))
clear_nlink(inode);
else
drop_nlink(inode);
mark_inode_dirty(inode);
if (inode->i_nlink == 0)
gfs2_unlink_di(inode);
return 0;
}
/**
* gfs2_unlink - Unlink an inode (this does rmdir as well)
* @dir: The inode of the directory containing the inode to unlink
* @dentry: The file itself
*
* This routine uses the type of the inode as a flag to figure out
* whether this is an unlink or an rmdir.
*
* Returns: errno
*/
static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
{
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(dir);
struct inode *inode = d_inode(dentry);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder ghs[3];
struct gfs2_rgrpd *rgd;
int error;
error = gfs2_rindex_update(sdp);
if (error)
return error;
error = -EROFS;
gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
if (!rgd)
goto out_inodes;
gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
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_rgrp;
if (S_ISDIR(inode->i_mode)) {
error = -ENOTEMPTY;
if (ip->i_entries > 2 || inode->i_nlink > 2)
goto out_rgrp;
}
error = gfs2_glock_nq(ghs + 2); /* rgrp */
if (error)
goto out_rgrp;
error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
if (error)
goto out_gunlock;
error = gfs2_trans_begin(sdp, 2*RES_DINODE + 3*RES_LEAF + RES_RG_BIT, 0);
if (error)
goto out_gunlock;
error = gfs2_unlink_inode(dip, dentry);
gfs2_trans_end(sdp);
out_gunlock:
gfs2_glock_dq(ghs + 2);
out_rgrp:
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs + 2);
out_inodes:
gfs2_holder_uninit(ghs + 1);
gfs2_holder_uninit(ghs);
return error;
}
/**
* gfs2_symlink - Create a symlink
* @dir: The directory to create the symlink in
* @dentry: The dentry to put the symlink in
* @symname: The thing which the link points to
*
* Returns: errno
*/
static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
unsigned int size;
size = strlen(symname);
if (size >= gfs2_max_stuffed_size(GFS2_I(dir)))
return -ENAMETOOLONG;
return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
}
/**
* gfs2_mkdir - Make a directory
* @dir: The parent directory of the new one
* @dentry: The dentry of the new directory
* @mode: The mode of the new directory
*
* Returns: errno
*/
static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 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);
}
/**
* 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;
}
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_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;
int alloc_required;
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;
alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name);
if (error < 0)
goto out_gunlock;
error = 0;
if (alloc_required) {
error = gfs2_quota_lock_check(dip);
if (error)
goto out_gunlock;
error = gfs2_inplace_reserve(dip, sdp->sd_max_dirres, 0);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
gfs2_rg_blocks(dip, sdp->sd_max_dirres) +
2 * RES_DINODE + RES_STATFS +
RES_QUOTA, 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);
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 (alloc_required)
gfs2_inplace_release(dip);
out_gunlock_q:
if (alloc_required)
gfs2_quota_unlock(dip);
out_gunlock:
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs);
gfs2_holder_uninit(ghs + 1);
return error;
}
static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
const char *symname, struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_dinode *di;
struct buffer_head *dibh;
struct timespec tv = CURRENT_TIME;
dibh = gfs2_meta_new(ip->i_gl, ip->i_no_addr);
gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI);
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
di = (struct gfs2_dinode *)dibh->b_data;
di->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
di->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
di->di_mode = cpu_to_be32(ip->i_inode.i_mode);
di->di_uid = cpu_to_be32(ip->i_inode.i_uid);
di->di_gid = cpu_to_be32(ip->i_inode.i_gid);
di->di_nlink = 0;
di->di_size = cpu_to_be64(ip->i_inode.i_size);
di->di_blocks = cpu_to_be64(1);
di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec);
di->di_major = cpu_to_be32(MAJOR(ip->i_inode.i_rdev));
di->di_minor = cpu_to_be32(MINOR(ip->i_inode.i_rdev));
di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_no_addr);
di->di_generation = cpu_to_be64(ip->i_generation);
di->di_flags = 0;
di->__pad1 = 0;
di->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) ? GFS2_FORMAT_DE : 0);
di->di_height = 0;
di->__pad2 = 0;
di->__pad3 = 0;
di->di_depth = 0;
di->di_entries = 0;
memset(&di->__pad4, 0, sizeof(di->__pad4));
di->di_eattr = 0;
di->di_atime_nsec = cpu_to_be32(tv.tv_nsec);
di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
memset(&di->di_reserved, 0, sizeof(di->di_reserved));
switch(ip->i_inode.i_mode & S_IFMT) {
case S_IFREG:
if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
gfs2_tune_get(sdp, gt_new_files_jdata))
di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
break;
case S_IFDIR:
di->di_flags |= cpu_to_be32(dip->i_diskflags &
GFS2_DIF_INHERIT_JDATA);
di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
di->di_size = cpu_to_be64(sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
di->di_entries = cpu_to_be32(2);
gfs2_init_dir(dibh, dip);
break;
case S_IFLNK:
memcpy(dibh->b_data + sizeof(struct gfs2_dinode), symname, ip->i_inode.i_size);
break;
}
set_buffer_uptodate(dibh);
*bhp = dibh;
}
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);
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;
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;
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;
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);
error = gfs2_inplace_reserve(ip, data_blocks + ind_blocks, 0);
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(&ip->i_gh);
out_uninit:
gfs2_holder_uninit(&ip->i_gh);
return error;
}
static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
struct buffer_head *bh_map, struct metapath *mp,
const unsigned int sheight,
const unsigned int height,
const size_t maxlen)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct super_block *sb = sdp->sd_vfs;
struct buffer_head *dibh = mp->mp_bh[0];
u64 bn, dblock = 0;
unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
unsigned dblks = 0;
unsigned ptrs_per_blk;
const unsigned end_of_metadata = height - 1;
int ret;
int eob = 0;
enum alloc_state state;
__be64 *ptr;
__be64 zero_bn = 0;
BUG_ON(sheight < 1);
BUG_ON(dibh == NULL);
gfs2_trans_add_meta(ip->i_gl, dibh);
if (height == sheight) {
struct buffer_head *bh;
/* Bottom indirect block exists, find unalloced extent size */
ptr = metapointer(end_of_metadata, mp);
bh = mp->mp_bh[end_of_metadata];
dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen,
&eob);
BUG_ON(dblks < 1);
state = ALLOC_DATA;
} else {
/* Need to allocate indirect blocks */
ptrs_per_blk = height > 1 ? sdp->sd_inptrs : sdp->sd_diptrs;
dblks = min(maxlen, (size_t)(ptrs_per_blk -
mp->mp_list[end_of_metadata]));
if (height == ip->i_height) {
/* Writing into existing tree, extend tree down */
iblks = height - sheight;
state = ALLOC_GROW_DEPTH;
} else {
/* Building up tree height */
state = ALLOC_GROW_HEIGHT;
iblks = height - ip->i_height;
branch_start = metapath_branch_start(mp);
iblks += (height - branch_start);
}
}
/* start of the second part of the function (state machine) */
blks = dblks + iblks;
i = sheight;
do {
int error;
n = blks - alloced;
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
if (error)
return error;
alloced += n;
if (state != ALLOC_DATA || gfs2_is_jdata(ip))
gfs2_trans_add_unrevoke(sdp, bn, n);
switch (state) {
/* Growing height of tree */
case ALLOC_GROW_HEIGHT:
if (i == 1) {
ptr = (__be64 *)(dibh->b_data +
sizeof(struct gfs2_dinode));
zero_bn = *ptr;
}
for (; i - 1 < height - ip->i_height && n > 0; i++, n--)
gfs2_indirect_init(mp, ip->i_gl, i, 0, bn++);
if (i - 1 == height - ip->i_height) {
i--;
gfs2_buffer_copy_tail(mp->mp_bh[i],
sizeof(struct gfs2_meta_header),
dibh, sizeof(struct gfs2_dinode));
gfs2_buffer_clear_tail(dibh,
sizeof(struct gfs2_dinode) +
sizeof(__be64));
ptr = (__be64 *)(mp->mp_bh[i]->b_data +
sizeof(struct gfs2_meta_header));
*ptr = zero_bn;
state = ALLOC_GROW_DEPTH;
for(i = branch_start; i < height; i++) {
if (mp->mp_bh[i] == NULL)
break;
brelse(mp->mp_bh[i]);
mp->mp_bh[i] = NULL;
}
i = branch_start;
}
if (n == 0)
break;
/* Branching from existing tree */
case ALLOC_GROW_DEPTH:
if (i > 1 && i < height)
gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
for (; i < height && n > 0; i++, n--)
gfs2_indirect_init(mp, ip->i_gl, i,
mp->mp_list[i-1], bn++);
if (i == height)
state = ALLOC_DATA;
if (n == 0)
break;
/* Tree complete, adding data blocks */
case ALLOC_DATA:
BUG_ON(n > dblks);
BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]);
dblks = n;
ptr = metapointer(end_of_metadata, mp);
dblock = bn;
while (n-- > 0)
*ptr++ = cpu_to_be64(bn++);
if (buffer_zeronew(bh_map)) {
ret = sb_issue_zeroout(sb, dblock, dblks,
GFP_NOFS);
if (ret) {
fs_err(sdp,
"Failed to zero data buffers\n");
clear_buffer_zeronew(bh_map);
}
}
break;
}
} while ((state != ALLOC_DATA) || !dblock);
ip->i_height = height;
gfs2_add_inode_blocks(&ip->i_inode, alloced);
gfs2_dinode_out(ip, mp->mp_bh[0]->b_data);
map_bh(bh_map, inode->i_sb, dblock);
bh_map->b_size = dblks << inode->i_blkbits;
set_buffer_new(bh_map);
return 0;
}
