struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_file_info *cf = file->private_data;
- struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
+ struct inode *parent_inode = NULL;
int err;
int flags, fmode, wanted;
req->r_inode = inode;
ihold(inode);
req->r_num_caps = 1;
+ if (flags & (O_CREAT|O_TRUNC))
+ parent_inode = ceph_get_dentry_parent_inode(file->f_dentry);
err = ceph_mdsc_do_request(mdsc, parent_inode, req);
+ iput(parent_inode);
if (!err)
err = ceph_init_file(inode, file, req->r_fmode);
ceph_mdsc_put_request(req);
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
- struct file *file = nd->intent.open.file;
- struct inode *parent_inode = get_dentry_parent_inode(file->f_dentry);
+ struct file *file;
struct ceph_mds_request *req;
+ struct dentry *ret;
int err;
int flags = nd->intent.open.flags - 1; /* silly vfs! */
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
}
req->r_locked_dir = dir; /* caller holds dir->i_mutex */
- err = ceph_mdsc_do_request(mdsc, parent_inode, req);
- dentry = ceph_finish_lookup(req, dentry, err);
- if (!err && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
+ err = ceph_mdsc_do_request(mdsc,
+ (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
+ req);
+ err = ceph_handle_snapdir(req, dentry, err);
+ if (err)
+ goto out;
+ if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
- if (!err)
- err = ceph_init_file(req->r_dentry->d_inode, file,
- req->r_fmode);
+ if (err)
+ goto out;
+ file = lookup_instantiate_filp(nd, req->r_dentry, ceph_open);
+ if (IS_ERR(file))
+ err = PTR_ERR(file);
+out:
+ ret = ceph_finish_lookup(req, dentry, err);
ceph_mdsc_put_request(req);
- dout("ceph_lookup_open result=%p\n", dentry);
- return dentry;
+ dout("ceph_lookup_open result=%p\n", ret);
+ return ret;
}
int ceph_release(struct inode *inode, struct file *file)
struct ceph_inode_info *ci = ceph_inode(inode);
u64 pos, this_len;
int io_align, page_align;
- int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
int left, pages_left;
int read;
struct page **page_pos;
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
if (ret > 0) {
- int didpages =
- ((pos & ~PAGE_CACHE_MASK) + ret) >> PAGE_CACHE_SHIFT;
+ int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
if (read < pos - off) {
dout(" zero gap %llu to %llu\n", off + read, pos);
- ceph_zero_page_vector_range(page_off + read,
+ ceph_zero_page_vector_range(page_align + read,
pos - off - read, pages);
}
pos += ret;
left = inode->i_size - pos;
dout("zero tail %d\n", left);
- ceph_zero_page_vector_range(page_off + read, left,
+ ceph_zero_page_vector_range(page_align + read, left,
pages);
read += left;
}
else
pos = *offset;
- io_align = pos & ~PAGE_MASK;
- buf_align = (unsigned long)data & ~PAGE_MASK;
-
ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
if (ret < 0)
return ret;
* boundary. this isn't atomic, unfortunately. :(
*/
more:
+ io_align = pos & ~PAGE_MASK;
+ buf_align = (unsigned long)data & ~PAGE_MASK;
len = left;
if (file->f_flags & O_DIRECT) {
/* write from beginning of first page, regardless of
pos += len;
written += len;
left -= len;
+ data += written;
if (left)
goto more;
if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(iocb->ki_filp->f_flags & O_DIRECT) ||
- (inode->i_sb->s_flags & MS_SYNCHRONOUS))
+ (inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
+ (fi->flags & CEPH_F_SYNC))
/* hmm, this isn't really async... */
ret = ceph_sync_read(filp, base, len, ppos, &checkeof);
else
want = CEPH_CAP_FILE_BUFFER;
ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, &got, endoff);
if (ret < 0)
- goto out;
+ goto out_put;
dout("aio_write %p %llx.%llx %llu~%u got cap refs on %s\n",
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
(iocb->ki_filp->f_flags & O_DIRECT) ||
- (inode->i_sb->s_flags & MS_SYNCHRONOUS)) {
+ (inode->i_sb->s_flags & MS_SYNCHRONOUS) ||
+ (fi->flags & CEPH_F_SYNC)) {
ret = ceph_sync_write(file, iov->iov_base, iov->iov_len,
&iocb->ki_pos);
} else {
- ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+ /*
+ * buffered write; drop Fw early to avoid slow
+ * revocation if we get stuck on balance_dirty_pages
+ */
+ int dirty;
+ spin_lock(&inode->i_lock);
+ dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
+ spin_unlock(&inode->i_lock);
+ ceph_put_cap_refs(ci, got);
+
+ ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
if ((ret >= 0 || ret == -EIOCBQUEUED) &&
((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host)
|| ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
if (err < 0)
ret = err;
}
+
+ if (dirty)
+ __mark_inode_dirty(inode, dirty);
+ goto out;
}
+
if (ret >= 0) {
int dirty;
spin_lock(&inode->i_lock);
__mark_inode_dirty(inode, dirty);
}
-out:
+out_put:
dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n",
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
ceph_cap_string(got));
ceph_put_cap_refs(ci, got);
+out:
if (ret == -EOLDSNAPC) {
dout("aio_write %p %llx.%llx %llu~%u got EOLDSNAPC, retrying\n",
inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len);
projects / deliverable / linux.git / blobdiff