static void ceph_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct ceph_inode_info *ci = ceph_inode(inode);

	kmem_cache_free(ceph_inode_cachep, ci);
}

/*
 * Dirty a page.  Optimistically adjust accounting, on the assumption
 * that we won't race with invalidate.  If we do, readjust.
 */
static int ceph_set_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode;
	struct ceph_inode_info *ci;
	struct ceph_snap_context *snapc;
	int ret;

	if (unlikely(!mapping))
		return !TestSetPageDirty(page);

	if (PageDirty(page)) {
		dout("%p set_page_dirty %p idx %lu -- already dirty\n",
		     mapping->host, page, page->index);
		BUG_ON(!PagePrivate(page));
		return 0;
	}

	inode = mapping->host;
	ci = ceph_inode(inode);

	/* dirty the head */
	spin_lock(&ci->i_ceph_lock);
	BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference
	if (__ceph_have_pending_cap_snap(ci)) {
		struct ceph_cap_snap *capsnap =
				list_last_entry(&ci->i_cap_snaps,
						struct ceph_cap_snap,
						ci_item);
		snapc = ceph_get_snap_context(capsnap->context);
		capsnap->dirty_pages++;
	} else {

/*
 * Helpers to fill in size, ctime, mtime, and atime.  We have to be
 * careful because either the client or MDS may have more up to date
 * info, depending on which capabilities are held, and whether
 * time_warp_seq or truncate_seq have increased.  (Ordinarily, mtime
 * and size are monotonically increasing, except when utimes() or
 * truncate() increments the corresponding _seq values.)
 */
int ceph_fill_file_size(struct inode *inode, int issued,
			u32 truncate_seq, u64 truncate_size, u64 size)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int queue_trunc = 0;

	if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 ||
	    (truncate_seq == ci->i_truncate_seq && size > inode->i_size)) {
		dout("size %lld -> %llu\n", inode->i_size, size);
		inode->i_size = size;
		inode->i_blocks = (size + (1<<9) - 1) >> 9;
		ci->i_reported_size = size;
		if (truncate_seq != ci->i_truncate_seq) {
			dout("truncate_seq %u -> %u\n",
			     ci->i_truncate_seq, truncate_seq);
			ci->i_truncate_seq = truncate_seq;
			/*
			 * If we hold relevant caps, or in the case where we're
			 * not the only client referencing this file and we
			 * don't hold those caps, then we need to check whether
			 * the file is either opened or mmaped
			 */
			if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_RD|
				       CEPH_CAP_FILE_WR|CEPH_CAP_FILE_BUFFER|
				       CEPH_CAP_FILE_EXCL|
				       CEPH_CAP_FILE_LAZYIO)) ||
			    mapping_mapped(inode->i_mapping) ||
			    __ceph_caps_file_wanted(ci)) {
				ci->i_truncate_pending++;
				queue_trunc = 1;
			}
		}
	}

static int striped_read(struct inode *inode,
			u64 off, u64 len,
			struct page **pages, int num_pages,
			int *checkeof, bool o_direct,
			unsigned long buf_align)
{
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 pos, this_len;
	int io_align, page_align;
	int left, pages_left;
	int read;
	struct page **page_pos;
	int ret;
	bool hit_stripe, was_short;

	pos = off;
	left = len;
	page_pos = pages;
	pages_left = num_pages;
	read = 0;
	io_align = off & ~PAGE_MASK;

more:
	if (o_direct)
		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
	else
		page_align = pos & ~PAGE_MASK;
	this_len = left;
	ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
				  &ci->i_layout, pos, &this_len,
				  ci->i_truncate_seq,
				  ci->i_truncate_size,
				  page_pos, pages_left, page_align);
	if (ret == -ENOENT)
		ret = 0;
	hit_stripe = this_len < left;
	was_short = ret >= 0 && ret < this_len;
	dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");

	if (ret > 0) {
		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_align + read,
						    pos - off - read, pages);
		}
		pos += ret;
		read = pos - off;
		left -= ret;
		page_pos += didpages;
		pages_left -= didpages;

		
		if (left && hit_stripe)
			goto more;
	}

/*
 * Read a range of bytes striped over one or more objects.  Iterate over
 * objects we stripe over.  (That's not atomic, but good enough for now.)
 *
 * If we get a short result from the OSD, check against i_size; we need to
 * only return a short read to the caller if we hit EOF.
 */
static int striped_read(struct inode *inode,
			u64 off, u64 len,
			struct page **pages, int num_pages,
			int *checkeof)
{
	struct ceph_client *client = ceph_inode_to_client(inode);
	struct ceph_inode_info *ci = ceph_inode(inode);
	u64 pos, this_len;
	int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
	int left, pages_left;
	int read;
	struct page **page_pos;
	int ret;
	bool hit_stripe, was_short;

	/*
	 * we may need to do multiple reads.  not atomic, unfortunately.
	 */
	pos = off;
	left = len;
	page_pos = pages;
	pages_left = num_pages;
	read = 0;

more:
	this_len = left;
	ret = ceph_osdc_readpages(&client->osdc, ceph_vino(inode),
				  &ci->i_layout, pos, &this_len,
				  ci->i_truncate_seq,
				  ci->i_truncate_size,
				  page_pos, pages_left);
	hit_stripe = this_len < left;
	was_short = ret >= 0 && ret < this_len;
	if (ret == -ENOENT)
		ret = 0;
	dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
	     ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");

	if (ret > 0) {
		int didpages =
			((pos & ~PAGE_CACHE_MASK) + ret) >> PAGE_CACHE_SHIFT;

		if (read < pos - off) {
			dout(" zero gap %llu to %llu\n", off + read, pos);
			zero_page_vector_range(page_off + read,
					       pos - off - read, pages);
		}
		pos += ret;
		read = pos - off;
		left -= ret;
		page_pos += didpages;
		pages_left -= didpages;

		/* hit stripe? */
		if (left && hit_stripe)
			goto more;
	}

/*
 * Process dirfrag (delegation) info from the mds.  Include leaf
 * fragment in tree ONLY if ndist > 0.  Otherwise, only
 * branches/splits are included in i_fragtree)
 */
static int ceph_fill_dirfrag(struct inode *inode,
			     struct ceph_mds_reply_dirfrag *dirinfo)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_inode_frag *frag;
	u32 id = le32_to_cpu(dirinfo->frag);
	int mds = le32_to_cpu(dirinfo->auth);
	int ndist = le32_to_cpu(dirinfo->ndist);
	int i;
	int err = 0;

	mutex_lock(&ci->i_fragtree_mutex);
	if (ndist == 0) {
		/* no delegation info needed. */
		frag = __ceph_find_frag(ci, id);
		if (!frag)
			goto out;
		if (frag->split_by == 0) {
			/* tree leaf, remove */
			dout("fill_dirfrag removed %llx.%llx frag %x"
			     " (no ref)\n", ceph_vinop(inode), id);
			rb_erase(&frag->node, &ci->i_fragtree);
			kfree(frag);
		} else {
			/* tree branch, keep and clear */
			dout("fill_dirfrag cleared %llx.%llx frag %x"
			     " referral\n", ceph_vinop(inode), id);
			frag->mds = -1;
			frag->ndist = 0;
		}
		goto out;
	}


	/* find/add this frag to store mds delegation info */
	frag = __get_or_create_frag(ci, id);
	if (IS_ERR(frag)) {
		/* this is not the end of the world; we can continue
		   with bad/inaccurate delegation info */
		pr_err("fill_dirfrag ENOMEM on mds ref %llx.%llx fg %x\n",
		       ceph_vinop(inode), le32_to_cpu(dirinfo->frag));
		err = -ENOMEM;
		goto out;
	}

	frag->mds = mds;
	frag->ndist = min_t(u32, ndist, CEPH_MAX_DIRFRAG_REP);
	for (i = 0; i < frag->ndist; i++)
		frag->dist[i] = le32_to_cpu(dirinfo->dist[i]);
	dout("fill_dirfrag %llx.%llx frag %x ndist=%d\n",
	     ceph_vinop(inode), frag->frag, frag->ndist);

out:
	mutex_unlock(&ci->i_fragtree_mutex);
	return err;
}

static inline void ceph_set_cached_acl(struct inode *inode,
					int type, struct posix_acl *acl)
{
	struct ceph_inode_info *ci = ceph_inode(inode);

	spin_lock(&ci->i_ceph_lock);
	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
		set_cached_acl(inode, type, acl);
	spin_unlock(&ci->i_ceph_lock);
}

/*
 * Return object name, size/offset information, and location (OSD
 * number, network address) for a given file offset.
 */
static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
{
	struct ceph_ioctl_dataloc dl;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_osd_client *osdc =
		&ceph_sb_to_client(inode->i_sb)->client->osdc;
	u64 len = 1, olen;
	u64 tmp;
	struct ceph_object_layout ol;
	struct ceph_pg pgid;
	int r;

	/* copy and validate */
	if (copy_from_user(&dl, arg, sizeof(dl)))
		return -EFAULT;

	down_read(&osdc->map_sem);
	r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len,
					  &dl.object_no, &dl.object_offset,
					  &olen);
	if (r < 0)
		return -EIO;
	dl.file_offset -= dl.object_offset;
	dl.object_size = ceph_file_layout_object_size(ci->i_layout);
	dl.block_size = ceph_file_layout_su(ci->i_layout);

	/* block_offset = object_offset % block_size */
	tmp = dl.object_offset;
	dl.block_offset = do_div(tmp, dl.block_size);

	snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
		 ceph_ino(inode), dl.object_no);
	ceph_calc_object_layout(&ol, dl.object_name, &ci->i_layout,
				osdc->osdmap);

	pgid = ol.ol_pgid;
	dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
	if (dl.osd >= 0) {
		struct ceph_entity_addr *a =
			ceph_osd_addr(osdc->osdmap, dl.osd);
		if (a)
			memcpy(&dl.osd_addr, &a->in_addr, sizeof(dl.osd_addr));
	} else {
		memset(&dl.osd_addr, 0, sizeof(dl.osd_addr));
	}
	up_read(&osdc->map_sem);

	/* send result back to user */
	if (copy_to_user(arg, &dl, sizeof(dl)))
		return -EFAULT;

	return 0;
}

/*
 * This function walks through the snaprealm for an inode and returns the
 * ceph_snap_realm for the first snaprealm that has quotas set (either max_files
 * or max_bytes).  If the root is reached, return the root ceph_snap_realm
 * instead.
 *
 * Note that the caller is responsible for calling ceph_put_snap_realm() on the
 * returned realm.
 */
static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc,
					       struct inode *inode)
{
	struct ceph_inode_info *ci = NULL;
	struct ceph_snap_realm *realm, *next;
	struct inode *in;
	bool has_quota;

	if (ceph_snap(inode) != CEPH_NOSNAP)
		return NULL;

	realm = ceph_inode(inode)->i_snap_realm;
	if (realm)
		ceph_get_snap_realm(mdsc, realm);
	else
		pr_err_ratelimited("get_quota_realm: ino (%llx.%llx) "
				   "null i_snap_realm\n", ceph_vinop(inode));
	while (realm) {
		spin_lock(&realm->inodes_with_caps_lock);
		in = realm->inode ? igrab(realm->inode) : NULL;
		spin_unlock(&realm->inodes_with_caps_lock);
		if (!in)
			break;

		ci = ceph_inode(in);
		has_quota = __ceph_has_any_quota(ci);
		iput(in);

		next = realm->parent;
		if (has_quota || !next)
		       return realm;

		ceph_get_snap_realm(mdsc, next);
		ceph_put_snap_realm(mdsc, realm);
		realm = next;
	}
	if (realm)
		ceph_put_snap_realm(mdsc, realm);

	return NULL;
}

static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode,
							int type)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct posix_acl *acl = ACL_NOT_CACHED;

	spin_lock(&ci->i_ceph_lock);
	if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
		acl = get_cached_acl(inode, type);
	spin_unlock(&ci->i_ceph_lock);

	return acl;
}

static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
{
	struct ceph_file_info *cf;
	int ret = 0;

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
	case S_IFDIR:
		dout("init_file %p %p 0%o (regular)\n", inode, file,
		     inode->i_mode);
		cf = kmem_cache_alloc(ceph_file_cachep, GFP_NOFS | __GFP_ZERO);
		if (cf == NULL) {
			ceph_put_fmode(ceph_inode(inode), fmode); 
			return -ENOMEM;
		}
		cf->fmode = fmode;
		cf->next_offset = 2;
		file->private_data = cf;
		BUG_ON(inode->i_fop->release != ceph_release);
		break;

	case S_IFLNK:
		dout("init_file %p %p 0%o (symlink)\n", inode, file,
		     inode->i_mode);
		ceph_put_fmode(ceph_inode(inode), fmode); 
		break;

	default:
		dout("init_file %p %p 0%o (special)\n", inode, file,
		     inode->i_mode);
		ceph_put_fmode(ceph_inode(inode), fmode); 
		BUG_ON(inode->i_fop->release == ceph_release);

		
		ret = inode->i_fop->open(inode, file);
	}
	return ret;
}

int ceph_release(struct inode *inode, struct file *file)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_file_info *cf = file->private_data;

	dout("release inode %p file %p\n", inode, file);
	ceph_put_fmode(ci, cf->fmode);
	if (cf->last_readdir)
		ceph_mdsc_put_request(cf->last_readdir);
	kfree(cf->last_name);
	kfree(cf->dir_info);
	kmem_cache_free(ceph_file_cachep, cf);

	/* wake up anyone waiting for caps on this inode */
	wake_up_all(&ci->i_cap_wq);
	return 0;
}

/*
 * get and set the file layout
 */
static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
{
	struct ceph_inode_info *ci = ceph_inode(file_inode(file));
	struct ceph_ioctl_layout l;
	int err;

	err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
	if (!err) {
		l.stripe_unit = ceph_file_layout_su(ci->i_layout);
		l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
		l.object_size = ceph_file_layout_object_size(ci->i_layout);
		l.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
		l.preferred_osd = (s32)-1;
		if (copy_to_user(arg, &l, sizeof(l)))
			return -EFAULT;
	}

	return err;
}

static int ceph_fill_fragtree(struct inode *inode,
			      struct ceph_frag_tree_head *fragtree,
			      struct ceph_mds_reply_dirfrag *dirinfo)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_inode_frag *frag;
	struct rb_node *rb_node;
	int i;
	u32 id, nsplits;
	bool update = false;

	mutex_lock(&ci->i_fragtree_mutex);
	nsplits = le32_to_cpu(fragtree->nsplits);
	if (nsplits) {
		i = prandom_u32() % nsplits;
		id = le32_to_cpu(fragtree->splits[i].frag);
		if (!__ceph_find_frag(ci, id))
			update = true;
	} else

static void ceph_aio_complete(struct inode *inode,
			      struct ceph_aio_request *aio_req)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int ret;

	if (!atomic_dec_and_test(&aio_req->pending_reqs))
		return;

	ret = aio_req->error;
	if (!ret)
		ret = aio_req->total_len;

	dout("ceph_aio_complete %p rc %d\n", inode, ret);

	if (ret >= 0 && aio_req->write) {
		int dirty;

		loff_t endoff = aio_req->iocb->ki_pos + aio_req->total_len;
		if (endoff > i_size_read(inode)) {
			if (ceph_inode_set_size(inode, endoff))
				ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
		}

		spin_lock(&ci->i_ceph_lock);
		ci->i_inline_version = CEPH_INLINE_NONE;
		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
					       &aio_req->prealloc_cf);
		spin_unlock(&ci->i_ceph_lock);
		if (dirty)
			__mark_inode_dirty(inode, dirty);

	}

	ceph_put_cap_refs(ci, (aio_req->write ? CEPH_CAP_FILE_WR :
						CEPH_CAP_FILE_RD));

	aio_req->iocb->ki_complete(aio_req->iocb, ret, 0);

	ceph_free_cap_flush(aio_req->prealloc_cf);
	kfree(aio_req);
}

void ceph_handle_quota(struct ceph_mds_client *mdsc,
		       struct ceph_mds_session *session,
		       struct ceph_msg *msg)
{
	struct super_block *sb = mdsc->fsc->sb;
	struct ceph_mds_quota *h = msg->front.iov_base;
	struct ceph_vino vino;
	struct inode *inode;
	struct ceph_inode_info *ci;

	if (msg->front.iov_len < sizeof(*h)) {
		pr_err("%s corrupt message mds%d len %d\n", __func__,
		       session->s_mds, (int)msg->front.iov_len);
		ceph_msg_dump(msg);
		return;
	}

	/* increment msg sequence number */
	mutex_lock(&session->s_mutex);
	session->s_seq++;
	mutex_unlock(&session->s_mutex);

	/* lookup inode */
	vino.ino = le64_to_cpu(h->ino);
	vino.snap = CEPH_NOSNAP;
	inode = ceph_find_inode(sb, vino);
	if (!inode) {
		pr_warn("Failed to find inode %llu\n", vino.ino);
		return;
	}
	ci = ceph_inode(inode);

	spin_lock(&ci->i_ceph_lock);
	ci->i_rbytes = le64_to_cpu(h->rbytes);
	ci->i_rfiles = le64_to_cpu(h->rfiles);
	ci->i_rsubdirs = le64_to_cpu(h->rsubdirs);
	__ceph_update_quota(ci, le64_to_cpu(h->max_bytes),
		            le64_to_cpu(h->max_files));
	spin_unlock(&ci->i_ceph_lock);

	iput(inode);
}

static long ceph_ioctl_lazyio(struct file *file)
{
	struct ceph_file_info *fi = file->private_data;
	struct inode *inode = file->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);

	if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
		spin_lock(&inode->i_lock);
		ci->i_nr_by_mode[fi->fmode]--;
		fi->fmode |= CEPH_FILE_MODE_LAZY;
		ci->i_nr_by_mode[fi->fmode]++;
		spin_unlock(&inode->i_lock);
		dout("ioctl_layzio: file %p marked lazy\n", file);

		ceph_check_caps(ci, 0, NULL);
	} else {
		dout("ioctl_layzio: file %p already lazy\n", file);
	}
	return 0;
}

static void ceph_aio_retry_work(struct work_struct *work)
{
	struct ceph_aio_work *aio_work =
		container_of(work, struct ceph_aio_work, work);
	struct ceph_osd_request *orig_req = aio_work->req;
	struct ceph_aio_request *aio_req = orig_req->r_priv;
	struct inode *inode = orig_req->r_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_snap_context *snapc;
	struct ceph_osd_request *req;
	int ret;

	spin_lock(&ci->i_ceph_lock);
	if (__ceph_have_pending_cap_snap(ci)) {
		struct ceph_cap_snap *capsnap =
			list_last_entry(&ci->i_cap_snaps,
					struct ceph_cap_snap,
					ci_item);
		snapc = ceph_get_snap_context(capsnap->context);
	} else {

void ceph_destroy_inode(struct inode *inode)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_inode_frag *frag;
	struct rb_node *n;

	dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));

	ceph_queue_caps_release(inode);

	/*
	 * we may still have a snap_realm reference if there are stray
	 * caps in i_cap_exporting_issued or i_snap_caps.
	 */
	if (ci->i_snap_realm) {
		struct ceph_mds_client *mdsc =
			ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
		struct ceph_snap_realm *realm = ci->i_snap_realm;

		dout(" dropping residual ref to snap realm %p\n", realm);
		spin_lock(&realm->inodes_with_caps_lock);
		list_del_init(&ci->i_snap_realm_item);
		spin_unlock(&realm->inodes_with_caps_lock);
		ceph_put_snap_realm(mdsc, realm);
	}

	kfree(ci->i_symlink);
	while ((n = rb_first(&ci->i_fragtree)) != NULL) {
		frag = rb_entry(n, struct ceph_inode_frag, node);
		rb_erase(n, &ci->i_fragtree);
		kfree(frag);
	}

	__ceph_destroy_xattrs(ci);
	if (ci->i_xattrs.blob)
		ceph_buffer_put(ci->i_xattrs.blob);
	if (ci->i_xattrs.prealloc_blob)
		ceph_buffer_put(ci->i_xattrs.prealloc_blob);

	call_rcu(&inode->i_rcu, ceph_i_callback);
}

/*
 * get/constuct snapdir inode for a given directory
 */
struct inode *ceph_get_snapdir(struct inode *parent)
{
	struct ceph_vino vino = {
		.ino = ceph_ino(parent),
		.snap = CEPH_SNAPDIR,
	};
	struct inode *inode = ceph_get_inode(parent->i_sb, vino);
	struct ceph_inode_info *ci = ceph_inode(inode);

	BUG_ON(!S_ISDIR(parent->i_mode));
	if (IS_ERR(inode))
		return inode;
	inode->i_mode = parent->i_mode;
	inode->i_uid = parent->i_uid;
	inode->i_gid = parent->i_gid;
	inode->i_op = &ceph_dir_iops;
	inode->i_fop = &ceph_dir_fops;
	ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */
	ci->i_rbytes = 0;
	return inode;
}