1 files changed, 45 insertions, 16 deletions

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 0d0eae05598f..ce549d31eeb7 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -122,7 +122,7 @@ int ceph_open(struct inode *inode, struct file *file)
         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;
 
@@ -194,7 +194,10 @@ int ceph_open(struct inode *inode, struct file *file)
         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);
@@ -222,9 +225,9 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
 {
         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;
 
@@ -242,16 +245,24 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
                 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)
@@ -643,7 +654,8 @@ again:
 
         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
@@ -712,7 +724,7 @@ retry_snap:
                 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,
@@ -720,12 +732,23 @@ retry_snap:
 
         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))) {
@@ -733,7 +756,12 @@ retry_snap:
                         if (err < 0)
                                 ret = err;
                 }
+
+                if (dirty)
+                        __mark_inode_dirty(inode, dirty);
+                goto out;
         }
+
         if (ret >= 0) {
                 int dirty;
                 spin_lock(&inode->i_lock);
@@ -743,12 +771,13 @@ retry_snap:
                         __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);