static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
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, GL_ATIME, &gh);
rv = gfs2_glock_nq_atime(&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 */
rv = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev,
iov, offset, nr_segs,
gfs2_get_block_direct, NULL);
out:
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
return rv;
}
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_m(3, ghs);
if (error)
goto out;
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_m(3, ghs);
out:
gfs2_holder_uninit(ghs);
gfs2_holder_uninit(ghs + 1);
gfs2_holder_uninit(ghs + 2);
gfs2_glock_dq_uninit(&ri_gh);
return error;
}
static int gfs2_readpage(struct file *file, struct page *page)
{
struct gfs2_inode *ip = GFS2_I(page->mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
struct gfs2_file *gf = NULL;
struct gfs2_holder gh;
int error;
int do_unlock = 0;
if (likely(file != &gfs2_internal_file_sentinel)) {
if (file) {
gf = file->private_data;
if (test_bit(GFF_EXLOCK, &gf->f_flags))
/* gfs2_sharewrite_nopage has grabbed the ip->i_gl already */
goto skip_lock;
}
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);
do_unlock = 1;
error = gfs2_glock_nq_atime(&gh);
if (unlikely(error))
goto out_unlock;
}
skip_lock:
if (gfs2_is_stuffed(ip)) {
error = stuffed_readpage(ip, page);
unlock_page(page);
} else
error = mpage_readpage(page, gfs2_get_block);
if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
error = -EIO;
if (do_unlock) {
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
}
out:
return error;
out_unlock:
unlock_page(page);
if (error == GLR_TRYFAILED) {
error = AOP_TRUNCATED_PAGE;
yield();
}
if (do_unlock)
gfs2_holder_uninit(&gh);
goto out;
}
/**
* gfs2_readpages - Read a bunch of pages at once
*
* Some notes:
* 1. This is only for readahead, so we can simply ignore any things
* which are slightly inconvenient (such as locking conflicts between
* the page lock and the glock) and return having done no I/O. Its
* obviously not something we'd want to do on too regular a basis.
* Any I/O we ignore at this time will be done via readpage later.
* 2. We don't handle stuffed files here we let readpage do the honours.
* 3. mpage_readpages() does most of the heavy lifting in the common case.
* 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places.
* 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as
* well as read-ahead.
*/
static int gfs2_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct inode *inode = mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_holder gh;
int ret = 0;
int do_unlock = 0;
if (likely(file != &gfs2_internal_file_sentinel)) {
if (file) {
struct gfs2_file *gf = file->private_data;
if (test_bit(GFF_EXLOCK, &gf->f_flags))
goto skip_lock;
}
gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
LM_FLAG_TRY_1CB|GL_ATIME, &gh);
do_unlock = 1;
ret = gfs2_glock_nq_atime(&gh);
if (ret == GLR_TRYFAILED)
goto out_noerror;
if (unlikely(ret))
goto out_unlock;
}
skip_lock:
if (!gfs2_is_stuffed(ip))
ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block);
if (do_unlock) {
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
}
out:
if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
ret = -EIO;
return ret;
out_noerror:
ret = 0;
out_unlock:
if (do_unlock)
gfs2_holder_uninit(&gh);
goto out;
}
static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
u32 fsflags;
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
error = gfs2_glock_nq_atime(&gh);
if (error)
return error;
fsflags = fsflags_cvt(gfs2_to_fsflags, ip->i_di.di_flags);
if (put_user(fsflags, ptr))
error = -EFAULT;
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
return error;
}
static int gfs2_rename(struct inode *odir, struct dentry *odentry,
struct inode *ndir, struct dentry *ndentry)
{
struct gfs2_inode *odip = GFS2_I(odir);
struct gfs2_inode *ndip = GFS2_I(ndir);
struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
struct gfs2_inode *nip = NULL;
struct gfs2_sbd *sdp = GFS2_SB(odir);
struct gfs2_holder ghs[5], r_gh;
struct gfs2_rgrpd *nrgd;
unsigned int num_gh;
int dir_rename = 0;
int alloc_required;
unsigned int x;
int error;
if (ndentry->d_inode) {
nip = GFS2_I(ndentry->d_inode);
if (ip == nip)
return 0;
}
/* Make sure we aren't trying to move a dirctory into it's subdir */
if (S_ISDIR(ip->i_inode.i_mode) && odip != ndip) {
dir_rename = 1;
error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE, 0,
&r_gh);
if (error)
goto out;
error = gfs2_ok_to_move(ip, ndip);
if (error)
goto out_gunlock_r;
}
num_gh = 1;
gfs2_holder_init(odip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (odip != ndip) {
gfs2_holder_init(ndip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
num_gh++;
}
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
num_gh++;
if (nip) {
gfs2_holder_init(nip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
num_gh++;
/* grab the resource lock for unlink flag twiddling
* this is the case of the target file already existing
* so we unlink before doing the rename
*/
nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
if (nrgd)
gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
}
error = gfs2_glock_nq_m(num_gh, ghs);
if (error)
goto out_uninit;
/* Check out the old directory */
error = gfs2_unlink_ok(odip, &odentry->d_name, ip);
if (error)
goto out_gunlock;
/* Check out the new directory */
if (nip) {
error = gfs2_unlink_ok(ndip, &ndentry->d_name, nip);
if (error)
goto out_gunlock;
if (S_ISDIR(nip->i_inode.i_mode)) {
if (nip->i_di.di_entries < 2) {
if (gfs2_consist_inode(nip))
gfs2_dinode_print(nip);
error = -EIO;
goto out_gunlock;
}
if (nip->i_di.di_entries > 2) {
error = -ENOTEMPTY;
goto out_gunlock;
}
}
} else {
error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC);
if (error)
goto out_gunlock;
error = gfs2_dir_check(ndir, &ndentry->d_name, NULL);
switch (error) {
case -ENOENT:
error = 0;
break;
case 0:
error = -EEXIST;
default:
goto out_gunlock;
};
if (odip != ndip) {
if (!ndip->i_inode.i_nlink) {
error = -EINVAL;
goto out_gunlock;
}
if (ndip->i_di.di_entries == (u32)-1) {
error = -EFBIG;
goto out_gunlock;
}
if (S_ISDIR(ip->i_inode.i_mode) &&
ndip->i_inode.i_nlink == (u32)-1) {
error = -EMLINK;
goto out_gunlock;
}
}
}
/* Check out the dir to be renamed */
if (dir_rename) {
error = gfs2_permission(odentry->d_inode, MAY_WRITE);
if (error)
goto out_gunlock;
}
alloc_required = error = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
if (error < 0)
goto out_gunlock;
error = 0;
if (alloc_required) {
struct gfs2_alloc *al = gfs2_alloc_get(ndip);
if (!al) {
error = -ENOMEM;
goto out_gunlock;
}
error = gfs2_quota_lock_check(ndip);
if (error)
goto out_alloc;
al->al_requested = sdp->sd_max_dirres;
error = gfs2_inplace_reserve(ndip);
if (error)
goto out_gunlock_q;
error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
al->al_rgd->rd_length +
4 * RES_DINODE + 4 * RES_LEAF +
RES_STATFS + RES_QUOTA + 4, 0);
if (error)
goto out_ipreserv;
} else {
error = gfs2_trans_begin(sdp, 4 * RES_DINODE +
5 * RES_LEAF + 4, 0);
if (error)
goto out_gunlock;
}
/* Remove the target file, if it exists */
if (nip) {
if (S_ISDIR(nip->i_inode.i_mode))
error = gfs2_rmdiri(ndip, &ndentry->d_name, nip);
else {
error = gfs2_dir_del(ndip, &ndentry->d_name);
if (error)
goto out_end_trans;
error = gfs2_change_nlink(nip, -1);
}
if (error)
goto out_end_trans;
}
if (dir_rename) {
struct qstr name;
gfs2_str2qstr(&name, "..");
error = gfs2_change_nlink(ndip, +1);
if (error)
goto out_end_trans;
error = gfs2_change_nlink(odip, -1);
if (error)
goto out_end_trans;
error = gfs2_dir_mvino(ip, &name, ndip, DT_DIR);
if (error)
goto out_end_trans;
} else {
struct buffer_head *dibh;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto out_end_trans;
ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
error = gfs2_dir_del(odip, &odentry->d_name);
if (error)
goto out_end_trans;
error = gfs2_dir_add(ndir, &ndentry->d_name, ip, IF2DT(ip->i_inode.i_mode));
if (error)
goto out_end_trans;
out_end_trans:
gfs2_trans_end(sdp);
out_ipreserv:
if (alloc_required)
gfs2_inplace_release(ndip);
out_gunlock_q:
if (alloc_required)
gfs2_quota_unlock(ndip);
out_alloc:
if (alloc_required)
gfs2_alloc_put(ndip);
out_gunlock:
gfs2_glock_dq_m(num_gh, ghs);
out_uninit:
for (x = 0; x < num_gh; x++)
gfs2_holder_uninit(ghs + x);
out_gunlock_r:
if (dir_rename)
gfs2_glock_dq_uninit(&r_gh);
out:
return error;
}
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_m(2, ghs);
if (error)
goto out;
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_di.di_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_m(2, ghs);
out:
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_commit_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
int error = -EOPNOTSUPP;
struct buffer_head *dibh;
struct gfs2_alloc *al = &ip->i_alloc;
struct gfs2_dinode *di;
if (gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)))
goto fail_nounlock;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto fail_endtrans;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
di = (struct gfs2_dinode *)dibh->b_data;
if (gfs2_is_stuffed(ip)) {
u64 file_size;
void *kaddr;
file_size = ((u64)page->index << PAGE_CACHE_SHIFT) + to;
kaddr = kmap_atomic(page, KM_USER0);
memcpy(dibh->b_data + sizeof(struct gfs2_dinode) + from,
kaddr + from, to - from);
kunmap_atomic(kaddr, KM_USER0);
SetPageUptodate(page);
if (inode->i_size < file_size) {
i_size_write(inode, file_size);
mark_inode_dirty(inode);
}
} else {
if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED ||
gfs2_is_jdata(ip))
gfs2_page_add_databufs(ip, page, from, to);
error = generic_commit_write(file, page, from, to);
if (error)
goto fail;
}
if (ip->i_di.di_size < inode->i_size) {
ip->i_di.di_size = inode->i_size;
di->di_size = cpu_to_be64(inode->i_size);
}
brelse(dibh);
gfs2_trans_end(sdp);
if (al->al_requested) {
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
gfs2_glock_dq_m(1, &ip->i_gh);
gfs2_holder_uninit(&ip->i_gh);
return 0;
fail:
brelse(dibh);
fail_endtrans:
gfs2_trans_end(sdp);
if (al->al_requested) {
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
gfs2_glock_dq_m(1, &ip->i_gh);
gfs2_holder_uninit(&ip->i_gh);
fail_nounlock:
ClearPageUptodate(page);
return error;
}
static int gfs2_prepare_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct gfs2_inode *ip = GFS2_I(page->mapping->host);
struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
unsigned int data_blocks, ind_blocks, rblocks;
int alloc_required;
int error = 0;
loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + from;
loff_t end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
struct gfs2_alloc *al;
unsigned int write_len = to - from;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME|LM_FLAG_TRY_1CB, &ip->i_gh);
error = gfs2_glock_nq_atime(&ip->i_gh);
if (unlikely(error)) {
if (error == GLR_TRYFAILED) {
unlock_page(page);
error = AOP_TRUNCATED_PAGE;
yield();
}
goto out_uninit;
}
gfs2_write_calc_reserv(ip, write_len, &data_blocks, &ind_blocks);
error = gfs2_write_alloc_required(ip, pos, write_len, &alloc_required);
if (error)
goto out_unlock;
ip->i_alloc.al_requested = 0;
if (alloc_required) {
al = gfs2_alloc_get(ip);
error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
if (error)
goto out_alloc_put;
error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
if (error)
goto out_qunlock;
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;
error = gfs2_trans_begin(sdp, rblocks, 0);
if (error)
goto out;
if (gfs2_is_stuffed(ip)) {
if (end > 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_prepare_write(page, from, to, gfs2_get_block);
out:
if (error) {
gfs2_trans_end(sdp);
if (alloc_required) {
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
out_alloc_put:
gfs2_alloc_put(ip);
}
out_unlock:
gfs2_glock_dq_m(1, &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);
unsigned int data_blocks, ind_blocks, rblocks;
int alloc_required;
int error = 0;
struct gfs2_alloc *al;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
unsigned to = from + len;
struct page *page;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &ip->i_gh);
error = gfs2_glock_nq_atime(&ip->i_gh);
if (unlikely(error))
goto out_uninit;
error = -ENOMEM;
page = grab_cache_page_write_begin(mapping, index, flags);
*pagep = page;
if (!page)
goto out_unlock;
gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
if (error)
goto out_putpage;
ip->i_alloc.al_requested = 0;
if (alloc_required) {
al = gfs2_alloc_get(ip);
error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
if (error)
goto out_alloc_put;
error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
if (error)
goto out_qunlock;
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;
error = gfs2_trans_begin(sdp, rblocks, 0);
if (error)
goto out;
if (gfs2_is_stuffed(ip)) {
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_prepare_write(page, from, to, gfs2_get_block);
out:
if (error) {
gfs2_trans_end(sdp);
if (alloc_required) {
gfs2_inplace_release(ip);
out_qunlock:
gfs2_quota_unlock(ip);
out_alloc_put:
gfs2_alloc_put(ip);
}
out_putpage:
page_cache_release(page);
if (pos + len > ip->i_inode.i_size)
vmtruncate(&ip->i_inode, ip->i_inode.i_size);
out_unlock:
gfs2_glock_dq_m(1, &ip->i_gh);
out_uninit:
gfs2_holder_uninit(&ip->i_gh);
}
return error;
}
static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
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_length(iov, nr_segs);
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)
return rv;
truncate_inode_pages_range(mapping, lstart, end);
}
rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs, gfs2_get_block_direct,
NULL, NULL, 0);
out:
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
return rv;
}
