1 files changed, 54 insertions, 28 deletions

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 3dd37a998ea9..ab4fc1255aca 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)
@@ -712,6 +713,7 @@ static ssize_t fuse_async_req_send(struct fuse_conn *fc,
 	spin_unlock(&io->lock);
 
 	ia->ap.args.end = fuse_aio_complete_req;
+	ia->ap.args.may_block = io->should_dirty;
 	err = fuse_simple_background(fc, &ia->ap.args, GFP_KERNEL);
 	if (err)
 		fuse_aio_complete_req(fc, &ia->ap.args, err);
@@ -2147,10 +2149,8 @@ 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);
@@ -2759,7 +2759,16 @@ 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;
@@ -3065,11 +3074,10 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	ssize_t ret = 0;
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
-	bool async_dio = ff->fc->async_dio;
 	loff_t pos = 0;
 	struct inode *inode;
 	loff_t i_size;
-	size_t count = iov_iter_count(iter);
+	size_t count = iov_iter_count(iter), shortened = 0;
 	loff_t offset = iocb->ki_pos;
 	struct fuse_io_priv *io;
 
@@ -3077,17 +3085,9 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	inode = file->f_mapping->host;
 	i_size = i_size_read(inode);
 
-	if ((iov_iter_rw(iter) == READ) && (offset > i_size))
+	if ((iov_iter_rw(iter) == READ) && (offset >= i_size))
 		return 0;
 
-	/* optimization for short read */
-	if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) {
-		if (offset >= i_size)
-			return 0;
-		iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset));
-		count = iov_iter_count(iter);
-	}
-
 	io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
 	if (!io)
 		return -ENOMEM;
@@ -3103,15 +3103,22 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	 * By default, we want to optimize all I/Os with async request
 	 * submission to the client filesystem if supported.
 	 */
-	io->async = async_dio;
+	io->async = ff->fc->async_dio;
 	io->iocb = iocb;
 	io->blocking = is_sync_kiocb(iocb);
 
+	/* optimization for short read */
+	if (io->async && !io->write && offset + count > i_size) {
+		iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset));
+		shortened = count - iov_iter_count(iter);
+		count -= shortened;
+	}
+
 	/*
 	 * We cannot asynchronously extend the size of a file.
 	 * In such case the aio will behave exactly like sync io.
 	 */
-	if ((offset + count > i_size) && iov_iter_rw(iter) == WRITE)
+	if ((offset + count > i_size) && io->write)
 		io->blocking = true;
 
 	if (io->async && io->blocking) {
@@ -3129,6 +3136,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	} else {
 		ret = __fuse_direct_read(io, iter, &pos);
 	}
+	iov_iter_reexpand(iter, iov_iter_count(iter) + shortened);
 
 	if (io->async) {
 		bool blocking = io->blocking;
@@ -3279,13 +3287,11 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
 		return -EXDEV;
 
-	if (fc->writeback_cache) {
-		inode_lock(inode_in);
-		err = fuse_writeback_range(inode_in, pos_in, pos_in + len);
-		inode_unlock(inode_in);
-		if (err)
-			return err;
-	}
+	inode_lock(inode_in);
+	err = fuse_writeback_range(inode_in, pos_in, pos_in + len - 1);
+	inode_unlock(inode_in);
+	if (err)
+		return err;
 
 	inode_lock(inode_out);
 
@@ -3293,11 +3299,27 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (err)
 		goto out;
 
-	if (fc->writeback_cache) {
-		err = fuse_writeback_range(inode_out, pos_out, pos_out + len);
-		if (err)
-			goto out;
-	}
+	/*
+	 * Write out dirty pages in the destination file before sending the COPY
+	 * request to userspace.  After the request is completed, truncate off
+	 * pages (including partial ones) from the cache that have been copied,
+	 * since these contain stale data at that point.
+	 *
+	 * This should be mostly correct, but if the COPY writes to partial
+	 * pages (at the start or end) and the parts not covered by the COPY are
+	 * written through a memory map after calling fuse_writeback_range(),
+	 * then these partial page modifications will be lost on truncation.
+	 *
+	 * It is unlikely that someone would rely on such mixed style
+	 * modifications.  Yet this does give less guarantees than if the
+	 * copying was performed with write(2).
+	 *
+	 * To fix this a i_mmap_sem style lock could be used to prevent new
+	 * faults while the copy is ongoing.
+	 */
+	err = fuse_writeback_range(inode_out, pos_out, pos_out + len - 1);
+	if (err)
+		goto out;
 
 	if (is_unstable)
 		set_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state);
@@ -3318,6 +3340,10 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (err)
 		goto out;
 
+	truncate_inode_pages_range(inode_out->i_mapping,
+				   ALIGN_DOWN(pos_out, PAGE_SIZE),
+				   ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1);
+
 	if (fc->writeback_cache) {
 		fuse_write_update_size(inode_out, pos_out + outarg.size);
 		file_update_time(file_out);