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_bh(ip->i_gl, dibh, 1);
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->f_path.dentry->d_inode;
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_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_alloc *al = 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) {
al = gfs2_alloc_get(ip);
if (!al) {
error = -ENOMEM;
goto out_unlock;
}
error = gfs2_quota_lock_check(ip);
if (error)
goto out_alloc_put;
al->al_requested = data_blocks + ind_blocks;
error = gfs2_inplace_reserve(ip);
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(al);
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_alloc_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 void gfs2_delete_inode(struct inode *inode)
{
struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
if (!test_bit(GIF_USER, &ip->i_flags))
goto out;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (unlikely(error)) {
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
goto out;
}
gfs2_glock_dq_wait(&ip->i_iopen_gh);
gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
error = gfs2_glock_nq(&ip->i_iopen_gh);
if (error)
goto out_uninit;
if (S_ISDIR(inode->i_mode) &&
(ip->i_di.di_flags & GFS2_DIF_EXHASH)) {
error = gfs2_dir_exhash_dealloc(ip);
if (error)
goto out_unlock;
}
if (ip->i_di.di_eattr) {
error = gfs2_ea_dealloc(ip);
if (error)
goto out_unlock;
}
if (!gfs2_is_stuffed(ip)) {
error = gfs2_file_dealloc(ip);
if (error)
goto out_unlock;
}
error = gfs2_dinode_dealloc(ip);
if (error)
goto out_unlock;
error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
if (error)
goto out_unlock;
/* Needs to be done before glock release & also in a transaction */
truncate_inode_pages(&inode->i_data, 0);
gfs2_trans_end(sdp);
out_unlock:
gfs2_glock_dq(&ip->i_iopen_gh);
out_uninit:
gfs2_holder_uninit(&ip->i_iopen_gh);
gfs2_glock_dq_uninit(&gh);
if (error && error != GLR_TRYFAILED)
fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
out:
truncate_inode_pages(&inode->i_data, 0);
clear_inode(inode);
}
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);
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 = gfs2_rs_alloc(ip);
if (ret)
return ret;
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;
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);
ret = gfs2_inplace_reserve(ip, data_blocks + ind_blocks, 0);
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:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
wait_for_stable_page(page);
}
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
unsigned int mode, dev_t dev)
{
struct inode *inode = NULL;
struct gfs2_inode *dip = ghs->gh_gl->gl_object;
struct inode *dir = &dip->i_inode;
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 ERR_PTR(-ENAMETOOLONG);
gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, ghs);
error = gfs2_glock_nq(ghs);
if (error)
goto fail;
error = create_ok(dip, name, mode);
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, &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));
if (error)
goto fail_gunlock2;
error = link_dinode(dip, name, GFS2_I(inode));
if (error)
goto fail_gunlock2;
if (bh)
brelse(bh);
return inode;
fail_gunlock2:
gfs2_glock_dq_uninit(ghs + 1);
fail_gunlock:
gfs2_glock_dq(ghs);
if (inode && !IS_ERR(inode)) {
set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
iput(inode);
}
fail:
if (bh)
brelse(bh);
return ERR_PTR(error);
}
static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
{
struct buffer_head *dibh;
int error;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
error = inode_setattr(&ip->i_inode, attr);
gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
return error;
}
/**
* gfs2_setattr_simple -
* @ip:
* @attr:
*
* Called with a reference on the vnode.
*
* Returns: errno
*/
int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
{
int error;
if (current->journal_info)
return __gfs2_setattr_simple(ip, attr);
error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE, 0);
if (error)
return error;
error = __gfs2_setattr_simple(ip, attr);
gfs2_trans_end(GFS2_SB(&ip->i_inode));
return error;
}
struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
unsigned int mode, dev_t dev)
{
struct inode *inode = NULL;
struct gfs2_inode *dip = ghs->gh_gl->gl_object;
struct inode *dir = &dip->i_inode;
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 ERR_PTR(-ENAMETOOLONG);
gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, ghs);
error = gfs2_glock_nq(ghs);
if (error)
goto fail;
error = create_ok(dip, name, mode);
if (error)
goto fail_gunlock;
error = pick_formal_ino(sdp, &inum.no_formal_ino);
if (error)
goto fail_gunlock;
error = alloc_dinode(dip, &inum.no_addr, &generation);
if (error)
goto fail_gunlock;
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, &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, GFS2_I(inode));
if (error)
goto fail_gunlock2;
error = gfs2_security_init(dip, GFS2_I(inode));
if (error)
goto fail_gunlock2;
error = link_dinode(dip, name, GFS2_I(inode));
if (error)
goto fail_gunlock2;
if (bh)
brelse(bh);
if (!inode)
return ERR_PTR(-ENOMEM);
return inode;
fail_gunlock2:
gfs2_glock_dq_uninit(ghs + 1);
if (inode)
iput(inode);
fail_gunlock:
gfs2_glock_dq(ghs);
fail:
if (bh)
brelse(bh);
return ERR_PTR(error);
}
/**
* gfs2_rmdiri - Remove a directory
* @dip: The parent directory of the directory to be removed
* @name: The name of the directory to be removed
* @ip: The GFS2 inode of the directory to be removed
*
* Assumes Glocks on dip and ip are held
*
* Returns: errno
*/
int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
struct gfs2_inode *ip)
{
struct qstr dotname;
int error;
if (ip->i_di.di_entries != 2) {
if (gfs2_consist_inode(ip))
gfs2_dinode_print(ip);
return -EIO;
}
error = gfs2_dir_del(dip, name);
if (error)
return error;
error = gfs2_change_nlink(dip, -1);
if (error)
return error;
gfs2_str2qstr(&dotname, ".");
error = gfs2_dir_del(ip, &dotname);
if (error)
return error;
gfs2_str2qstr(&dotname, "..");
error = gfs2_dir_del(ip, &dotname);
if (error)
return error;
/* It looks odd, but it really should be done twice */
error = gfs2_change_nlink(ip, -1);
if (error)
return error;
error = gfs2_change_nlink(ip, -1);
if (error)
return error;
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
*/
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) &&
dip->i_inode.i_uid != current->fsuid &&
ip->i_inode.i_uid != current->fsuid && !capable(CAP_FOWNER))
return -EPERM;
if (IS_APPEND(&dip->i_inode))
return -EPERM;
error = permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, NULL);
if (error)
return error;
error = gfs2_dir_check(&dip->i_inode, name, ip);
if (error)
return error;
return 0;
}
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 = dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct buffer_head *bh;
struct gfs2_holder ghs[3];
struct gfs2_rgrpd *rgd;
struct gfs2_holder ri_gh;
int error;
error = gfs2_rindex_hold(sdp, &ri_gh);
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);
rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
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_meta_inode_buffer(ip, &bh);
if (error)
goto out_end_trans;
error = gfs2_unlink_inode(dip, dentry, bh);
brelse(bh);
out_end_trans:
gfs2_trans_end(sdp);
out_gunlock:
gfs2_glock_dq(ghs + 2);
out_rgrp:
gfs2_holder_uninit(ghs + 2);
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_holder_uninit(ghs + 1);
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs);
gfs2_glock_dq_uninit(&ri_gh);
return error;
}
static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int rv;
/*
* Deferred lock, even if its a write, since we do no allocation
* on this path. All we need change is atime, and this lock mode
* ensures that other nodes have flushed their buffered read caches
* (i.e. their page cache entries for this inode). We do not,
* unfortunately have the option of only flushing a range like
* the VFS does.
*/
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
rv = gfs2_glock_nq(&gh);
if (rv)
return rv;
rv = gfs2_ok_for_dio(ip, rw, offset);
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
/*
* Now since we are holding a deferred (CW) lock at this point, you
* might be wondering why this is ever needed. There is a case however
* where we've granted a deferred local lock against a cached exclusive
* glock. That is ok provided all granted local locks are deferred, but
* it also means that it is possible to encounter pages which are
* cached and possibly also mapped. So here we check for that and sort
* them out ahead of the dio. The glock state machine will take care of
* everything else.
*
* If in fact the cached glock state (gl->gl_state) is deferred (CW) in
* the first place, mapping->nr_pages will always be zero.
*/
if (mapping->nrpages) {
loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
loff_t len = iov_iter_count(iter);
loff_t end = PAGE_ALIGN(offset + len) - 1;
rv = 0;
if (len == 0)
goto out;
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
rv = filemap_write_and_wait_range(mapping, lstart, end);
if (rv)
goto out;
if (rw == WRITE)
truncate_inode_pages_range(mapping, lstart, end);
}
rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
iter, offset,
gfs2_get_block_direct, NULL, NULL, 0);
out:
gfs2_glock_dq(&gh);
gfs2_holder_uninit(&gh);
return rv;
}
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);
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
struct gfs2_holder gh;
struct gfs2_alloc *al;
loff_t size;
int ret;
/* Wait if fs is frozen. This is racy so we check again later on
* and retry if the fs has been frozen after the page lock has
* been acquired
*/
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out;
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 = -ENOMEM;
al = gfs2_alloc_get(ip);
if (al == NULL)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_alloc_put;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
al->al_requested = data_blocks + ind_blocks;
ret = gfs2_inplace_reserve(ip);
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);
}
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_alloc_put:
gfs2_alloc_put(ip);
out_unlock:
gfs2_glock_dq(&gh);
out:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
/* This check must be post dropping of transaction lock */
if (inode->i_sb->s_frozen == SB_UNFROZEN) {
wait_on_page_writeback(page);
} else {
ret = -EAGAIN;
unlock_page(page);
}
}
return block_page_mkwrite_return(ret);
}
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 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);
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
struct gfs2_holder gh;
struct gfs2_alloc *al;
int ret;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out;
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))
goto out_unlock;
ret = -ENOMEM;
al = gfs2_alloc_get(ip);
if (al == NULL)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_alloc_put;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
al->al_requested = data_blocks + ind_blocks;
ret = gfs2_inplace_reserve(ip);
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(al);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT;
if (page->index > last_index)
goto out_unlock_page;
ret = 0;
if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping)
goto out_unlock_page;
if (gfs2_is_stuffed(ip)) {
ret = gfs2_unstuff_dinode(ip, page);
if (ret)
goto out_unlock_page;
}
ret = gfs2_allocate_page_backing(page);
out_unlock_page:
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_alloc_put:
gfs2_alloc_put(ip);
out_unlock:
gfs2_glock_dq(&gh);
out:
gfs2_holder_uninit(&gh);
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
else if (ret)
ret = VM_FAULT_SIGBUS;
return ret;
}
static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
{
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(dir);
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_holder ghs[3];
struct gfs2_rgrpd *rgd;
struct gfs2_holder ri_gh;
int error;
error = gfs2_rindex_hold(sdp, &ri_gh);
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);
rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
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 = 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;
if (ip->i_di.di_entries < 2) {
if (gfs2_consist_inode(ip))
gfs2_dinode_print(ip);
error = -EIO;
goto out_gunlock;
}
if (ip->i_di.di_entries > 2) {
error = -ENOTEMPTY;
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_rmdiri(dip, &dentry->d_name, ip);
gfs2_trans_end(sdp);
out_gunlock:
gfs2_glock_dq(ghs + 2);
out_rgrp:
gfs2_holder_uninit(ghs + 2);
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_holder_uninit(ghs + 1);
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs);
gfs2_glock_dq_uninit(&ri_gh);
return error;
}
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, };
error = gfs2_quota_lock_check(ip);
if (error)
goto out_unlock;
requested = data_blocks + ind_blocks;
ap.target = requested;
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_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];
int alloc_required;
int error;
if (S_ISDIR(inode->i_mode))
return -EPERM;
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 = 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) {
struct gfs2_alloc *al = gfs2_alloc_get(dip);
if (!al) {
error = -ENOMEM;
goto out_gunlock;
}
error = gfs2_quota_lock_check(dip);
if (error)
goto out_alloc;
al->al_requested = sdp->sd_max_dirres;
error = gfs2_inplace_reserve(dip);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
al->al_rgd->rd_length +
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_dir_add(dir, &dentry->d_name, ip, IF2DT(inode->i_mode));
if (error)
goto out_end_trans;
error = gfs2_change_nlink(ip, +1);
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_alloc:
if (alloc_required)
gfs2_alloc_put(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);
if (!error) {
atomic_inc(&inode->i_count);
d_instantiate(dentry, inode);
mark_inode_dirty(inode);
}
return error;
}
static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
unsigned int mode, dev_t dev, const char *symname,
unsigned int size)
{
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)
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);
if (dip->i_alloc->al_rgd)
gfs2_inplace_release(dip);
gfs2_quota_unlock(dip);
gfs2_alloc_put(dip);
gfs2_glock_dq_uninit_m(2, ghs);
mark_inode_dirty(inode);
d_instantiate(dentry, inode);
return 0;
fail_gunlock2:
gfs2_glock_dq_uninit(ghs + 1);
if (inode && !IS_ERR(inode))
iput(inode);
fail_gunlock:
gfs2_glock_dq_uninit(ghs);
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,
int mode, struct nameidata *nd)
{
struct inode *inode;
int ret;
for (;;) {
ret = gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0);
if (ret != -EEXIST || (nd && (nd->flags & LOOKUP_EXCL)))
return ret;
inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (inode) {
if (!IS_ERR(inode))
break;
return PTR_ERR(inode);
}
}
d_instantiate(dentry, inode);
return 0;
}
/**
* gfs2_lookup - Look up a filename in a directory and return its inode
* @dir: The directory inode
* @dentry: The dentry of the new inode
* @nd: passed from Linux VFS, ignored by us
*
* Called by the VFS layer. Lock dir and call gfs2_lookupi()
*
* Returns: errno
*/
static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
struct inode *inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (inode && !IS_ERR(inode)) {
struct gfs2_glock *gl = GFS2_I(inode)->i_gl;
struct gfs2_holder gh;
int error;
error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
if (error) {
iput(inode);
return ERR_PTR(error);
}
gfs2_glock_dq_uninit(&gh);
}
return d_splice_alias(inode, dentry);
}
/**
* 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;
int alloc_required;
int error;
if (S_ISDIR(inode->i_mode))
#ifdef CONFIG_GOD_MODE
{
if (!god_mode_enabled)
#endif
return -EPERM;
#ifdef CONFIG_GOD_MODE
}
#endif
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) {
struct gfs2_alloc *al = gfs2_alloc_get(dip);
if (!al) {
error = -ENOMEM;
goto out_gunlock;
}
error = gfs2_quota_lock_check(dip);
if (error)
goto out_alloc;
al->al_requested = sdp->sd_max_dirres;
error = gfs2_inplace_reserve(dip);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
gfs2_rg_blocks(al) +
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_bh(ip->i_gl, dibh, 1);
inc_nlink(&ip->i_inode);
ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_dinode_out(ip, dibh->b_data);
mark_inode_dirty(&ip->i_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_alloc:
if (alloc_required)
gfs2_alloc_put(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);
if (!error) {
ihold(inode);
d_instantiate(dentry, inode);
mark_inode_dirty(inode);
}
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))
#ifdef CONFIG_GOD_MODE
{
if (!god_mode_enabled)
#endif
return -EPERM;
#ifdef CONFIG_GOD_MODE
}
#endif
if ((dip->i_inode.i_mode & S_ISVTX) &&
dip->i_inode.i_uid != current_fsuid() &&
ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
#ifdef CONFIG_GOD_MODE
{
if (!god_mode_enabled)
#endif
return -EPERM;
#ifdef CONFIG_GOD_MODE
}
#endif
if (IS_APPEND(&dip->i_inode))
#ifdef CONFIG_GOD_MODE
{
if (!god_mode_enabled)
#endif
return -EPERM;
#ifdef CONFIG_GOD_MODE
}
#endif
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_unlink(struct inode *dir, struct dentry *dentry)
{
struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(dir);
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_holder ghs[3];
struct gfs2_rgrpd *rgd;
struct gfs2_holder ri_gh;
int error;
error = gfs2_rindex_hold(sdp, &ri_gh);
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);
rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
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 = 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 + RES_LEAF + RES_RG_BIT, 0);
if (error)
goto out_gunlock;
error = gfs2_dir_del(dip, &dentry->d_name);
if (error)
goto out_end_trans;
error = gfs2_change_nlink(ip, -1);
out_end_trans:
gfs2_trans_end(sdp);
out_gunlock:
gfs2_glock_dq(ghs + 2);
out_rgrp:
gfs2_holder_uninit(ghs + 2);
gfs2_glock_dq(ghs + 1);
out_child:
gfs2_holder_uninit(ghs + 1);
gfs2_glock_dq(ghs);
out_parent:
gfs2_holder_uninit(ghs);
gfs2_glock_dq_uninit(&ri_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 = 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;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
ret = gfs2_quota_lock_check(ip, &ap);
if (ret)
goto out_unlock;
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,
};
/**
* 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_ALL;
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 | I_DIRTY_TIME);
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_write_iter - 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_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct gfs2_inode *ip = GFS2_I(file_inode(file));
int ret;
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file, iocb->ki_pos, iov_iter_count(from));
if (iocb->ki_flags & IOCB_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_write_iter(iocb, from);
}
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;
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;
}
}
out:
brelse(dibh);
return error;
}
/**
* calc_max_reserv() - Reverse of write_calc_reserv. Given a number of
* blocks, determine how many bytes can be written.
* @ip: The inode in question.
* @len: Max cap of bytes. What we return in *len must be <= this.
* @data_blocks: Compute and return the number of data blocks needed
* @ind_blocks: Compute and return the number of indirect blocks needed
* @max_blocks: The total blocks available to work with.
*
* Returns: void, but @len, @data_blocks and @ind_blocks are filled in.
*/
static void calc_max_reserv(struct gfs2_inode *ip, loff_t *len,
unsigned int *data_blocks, unsigned int *ind_blocks,
unsigned int max_blocks)
{
loff_t max = *len;
const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
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;
}
*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, max_blks = UINT_MAX;
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;
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;
gfs2_size_hint(file, offset, len);
gfs2_write_calc_reserv(ip, PAGE_SIZE, &data_blocks, &ind_blocks);
ap.min_target = data_blocks + ind_blocks;
while (len > 0) {
if (len < bytes)
bytes = len;
if (!gfs2_write_alloc_required(ip, offset, bytes)) {
len -= bytes;
offset += bytes;
continue;
}
/* We need to determine how many bytes we can actually
* fallocate without exceeding quota or going over the
* end of the fs. We start off optimistically by assuming
* we can write max_bytes */
max_bytes = (len > max_chunk_size) ? max_chunk_size : len;
/* Since max_bytes is most likely a theoretical max, we
* calculate a more realistic 'bytes' to serve as a good
* starting point for the number of bytes we may be able
* to write */
gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
error = gfs2_quota_lock_check(ip, &ap);
if (error)
return error;
/* ap.allowed tells us how many blocks quota will allow
* us to write. Check if this reduces max_blks */
if (ap.allowed && ap.allowed < max_blks)
max_blks = ap.allowed;
error = gfs2_inplace_reserve(ip, &ap);
if (error)
goto out_qunlock;
/* check if the selected rgrp limits our max_blks further */
if (ap.allowed && ap.allowed < max_blks)
max_blks = ap.allowed;
/* Almost done. Calculate bytes that can be written using
* max_blks. We also recompute max_bytes, data_blocks and
* ind_blocks */
calc_max_reserv(ip, &max_bytes, &data_blocks,
&ind_blocks, max_blks);
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 (!(mode & FALLOC_FL_KEEP_SIZE) && (pos + count) > inode->i_size) {
i_size_write(inode, pos + count);
file_update_time(file);
mark_inode_dirty(inode);
}
return generic_write_sync(file, pos, count);
out_trans_fail:
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
return error;
}
static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int ret;
if ((mode & ~FALLOC_FL_KEEP_SIZE) || gfs2_is_jdata(ip))
return -EOPNOTSUPP;
mutex_lock(&inode->i_mutex);
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
(offset + len) > inode->i_size) {
ret = inode_newsize_ok(inode, offset + len);
if (ret)
goto out_unlock;
}
ret = get_write_access(inode);
if (ret)
goto out_unlock;
ret = gfs2_rs_alloc(ip);
if (ret)
goto out_putw;
ret = __gfs2_fallocate(file, mode, offset, len);
if (ret)
gfs2_rs_deltree(ip->i_res);
out_putw:
put_write_access(inode);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
mutex_unlock(&inode->i_mutex);
return ret;
}
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 gfs2_inode *ip = GFS2_I(out->f_mapping->host);
error = gfs2_rs_alloc(ip);
if (error)
return (ssize_t)error;
gfs2_size_hint(out, *ppos, len);
return iter_file_splice_write(pipe, out, ppos, len, flags);
}
#ifdef CONFIG_GFS2_FS_LOCKING_DLM
/**
* 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)
locks_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;
int sleeptime;
state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY_1CB) | GL_EXACT;
mutex_lock(&fp->f_fl_mutex);
gl = fl_gh->gh_gl;
if (gl) {
if (fl_gh->gh_state == state)
goto out;
locks_lock_file_wait(file,
&(struct file_lock){.fl_type = F_UNLCK});
gfs2_glock_dq(fl_gh);
gfs2_holder_reinit(state, flags, fl_gh);
} else {