1 files changed, 78 insertions, 54 deletions

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e573b0cd2737..83d917f7e542 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -18,6 +18,7 @@
 #include <linux/swap.h>
 #include <linux/falloc.h>
 #include <linux/uio.h>
+#include <linux/fs.h>
 
 static struct page **fuse_pages_alloc(unsigned int npages, gfp_t flags,
 				      struct fuse_page_desc **desc)
@@ -1586,7 +1587,6 @@ static void fuse_writepage_finish(struct fuse_conn *fc,
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
 	int i;
 
-	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	for (i = 0; i < ap->num_pages; i++) {
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		dec_node_page_state(ap->pages[i], NR_WRITEBACK_TEMP);
@@ -1637,6 +1637,7 @@ __acquires(fi->lock)
 
  out_free:
 	fi->writectr--;
+	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	fuse_writepage_finish(fc, wpa);
 	spin_unlock(&fi->lock);
 
@@ -1674,7 +1675,8 @@ __acquires(fi->lock)
 	}
 }
 
-static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
+static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root,
+						struct fuse_writepage_args *wpa)
 {
 	pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT;
 	pgoff_t idx_to = idx_from + wpa->ia.ap.num_pages - 1;
@@ -1697,11 +1699,17 @@ static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
 		else if (idx_to < curr_index)
 			p = &(*p)->rb_left;
 		else
-			return (void) WARN_ON(true);
+			return curr;
 	}
 
 	rb_link_node(&wpa->writepages_entry, parent, p);
 	rb_insert_color(&wpa->writepages_entry, root);
+	return NULL;
+}
+
+static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
+{
+	WARN_ON(fuse_insert_writeback(root, wpa));
 }
 
 static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_args *args,
@@ -1714,6 +1722,7 @@ static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_args *args,
 
 	mapping_set_error(inode->i_mapping, error);
 	spin_lock(&fi->lock);
+	rb_erase(&wpa->writepages_entry, &fi->writepages);
 	while (wpa->next) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
 		struct fuse_write_in *inarg = &wpa->ia.write.in;
@@ -1952,14 +1961,14 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
 }
 
 /*
- * First recheck under fi->lock if the offending offset is still under
- * writeback.  If yes, then iterate auxiliary write requests, to see if there's
+ * Check under fi->lock if the page is under writeback, and insert it onto the
+ * rb_tree if not. Otherwise iterate auxiliary write requests, to see if there's
  * one already added for a page at this offset.  If there's none, then insert
  * this new request onto the auxiliary list, otherwise reuse the existing one by
- * copying the new page contents over to the old temporary page.
+ * swapping the new temp page with the old one.
  */
-static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
-				     struct page *page)
+static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
+			       struct page *page)
 {
 	struct fuse_inode *fi = get_fuse_inode(new_wpa->inode);
 	struct fuse_writepage_args *tmp;
@@ -1967,17 +1976,15 @@ static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
 	struct fuse_args_pages *new_ap = &new_wpa->ia.ap;
 
 	WARN_ON(new_ap->num_pages != 0);
+	new_ap->num_pages = 1;
 
 	spin_lock(&fi->lock);
-	rb_erase(&new_wpa->writepages_entry, &fi->writepages);
-	old_wpa = fuse_find_writeback(fi, page->index, page->index);
+	old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa);
 	if (!old_wpa) {
-		tree_insert(&fi->writepages, new_wpa);
 		spin_unlock(&fi->lock);
-		return false;
+		return true;
 	}
 
-	new_ap->num_pages = 1;
 	for (tmp = old_wpa->next; tmp; tmp = tmp->next) {
 		pgoff_t curr_index;
 
@@ -2006,7 +2013,41 @@ static bool fuse_writepage_in_flight(struct fuse_writepage_args *new_wpa,
 		fuse_writepage_free(new_wpa);
 	}
 
-	return true;
+	return false;
+}
+
+static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page,
+				     struct fuse_args_pages *ap,
+				     struct fuse_fill_wb_data *data)
+{
+	WARN_ON(!ap->num_pages);
+
+	/*
+	 * Being under writeback is unlikely but possible.  For example direct
+	 * read to an mmaped fuse file will set the page dirty twice; once when
+	 * the pages are faulted with get_user_pages(), and then after the read
+	 * completed.
+	 */
+	if (fuse_page_is_writeback(data->inode, page->index))
+		return true;
+
+	/* Reached max pages */
+	if (ap->num_pages == fc->max_pages)
+		return true;
+
+	/* Reached max write bytes */
+	if ((ap->num_pages + 1) * PAGE_SIZE > fc->max_write)
+		return true;
+
+	/* Discontinuity */
+	if (data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)
+		return true;
+
+	/* Need to grow the pages array?  If so, did the expansion fail? */
+	if (ap->num_pages == data->max_pages && !fuse_pages_realloc(data))
+		return true;
+
+	return false;
 }
 
 static int fuse_writepages_fill(struct page *page,
@@ -2019,7 +2060,6 @@ static int fuse_writepages_fill(struct page *page,
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct page *tmp_page;
-	bool is_writeback;
 	int err;
 
 	if (!data->ff) {
@@ -2029,25 +2069,9 @@ static int fuse_writepages_fill(struct page *page,
 			goto out_unlock;
 	}
 
-	/*
-	 * Being under writeback is unlikely but possible.  For example direct
-	 * read to an mmaped fuse file will set the page dirty twice; once when
-	 * the pages are faulted with get_user_pages(), and then after the read
-	 * completed.
-	 */
-	is_writeback = fuse_page_is_writeback(inode, page->index);
-
-	if (wpa && ap->num_pages &&
-	    (is_writeback || ap->num_pages == fc->max_pages ||
-	     (ap->num_pages + 1) * PAGE_SIZE > fc->max_write ||
-	     data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)) {
+	if (wpa && fuse_writepage_need_send(fc, page, ap, data)) {
 		fuse_writepages_send(data);
 		data->wpa = NULL;
-	} else if (wpa && ap->num_pages == data->max_pages) {
-		if (!fuse_pages_realloc(data)) {
-			fuse_writepages_send(data);
-			data->wpa = NULL;
-		}
 	}
 
 	err = -ENOMEM;
@@ -2085,12 +2109,6 @@ static int fuse_writepages_fill(struct page *page,
 		ap->args.end = fuse_writepage_end;
 		ap->num_pages = 0;
 		wpa->inode = inode;
-
-		spin_lock(&fi->lock);
-		tree_insert(&fi->writepages, wpa);
-		spin_unlock(&fi->lock);
-
-		data->wpa = wpa;
 	}
 	set_page_writeback(page);
 
@@ -2098,26 +2116,25 @@ static int fuse_writepages_fill(struct page *page,
 	ap->pages[ap->num_pages] = tmp_page;
 	ap->descs[ap->num_pages].offset = 0;
 	ap->descs[ap->num_pages].length = PAGE_SIZE;
+	data->orig_pages[ap->num_pages] = page;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
-	if (is_writeback && fuse_writepage_in_flight(wpa, page)) {
+	if (data->wpa) {
+		/*
+		 * Protected by fi->lock against concurrent access by
+		 * fuse_page_is_writeback().
+		 */
+		spin_lock(&fi->lock);
+		ap->num_pages++;
+		spin_unlock(&fi->lock);
+	} else if (fuse_writepage_add(wpa, page)) {
+		data->wpa = wpa;
+	} else {
 		end_page_writeback(page);
-		data->wpa = NULL;
-		goto out_unlock;
 	}
-	data->orig_pages[ap->num_pages] = page;
-
-	/*
-	 * Protected by fi->lock against concurrent access by
-	 * fuse_page_is_writeback().
-	 */
-	spin_lock(&fi->lock);
-	ap->num_pages++;
-	spin_unlock(&fi->lock);
-
 out_unlock:
 	unlock_page(page);
 
@@ -2149,10 +2166,8 @@ static int fuse_writepages(struct address_space *mapping,
 
 	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
 	if (data.wpa) {
-		/* Ignore errors if we can write at least one page */
 		WARN_ON(!data.wpa->ia.ap.num_pages);
 		fuse_writepages_send(&data);
-		err = 0;
 	}
 	if (data.ff)
 		fuse_file_put(data.ff, false, false);
@@ -2761,7 +2776,16 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		struct iovec *iov = iov_page;
 
 		iov->iov_base = (void __user *)arg;
-		iov->iov_len = _IOC_SIZE(cmd);
+
+		switch (cmd) {
+		case FS_IOC_GETFLAGS:
+		case FS_IOC_SETFLAGS:
+			iov->iov_len = sizeof(int);
+			break;
+		default:
+			iov->iov_len = _IOC_SIZE(cmd);
+			break;
+		}
 
 		if (_IOC_DIR(cmd) & _IOC_WRITE) {
 			in_iov = iov;