1 files changed, 51 insertions, 35 deletions

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 4adcf09d4b01..f1ef77a0be05 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -356,8 +356,14 @@ void fuse_file_release(struct inode *inode, struct fuse_file *ff,
 	 * Make the release synchronous if this is a fuseblk mount,
 	 * synchronous RELEASE is allowed (and desirable) in this case
 	 * because the server can be trusted not to screw up.
+	 *
+	 * Always use the asynchronous file put because the current thread
+	 * might be the fuse server.  This can happen if a process starts some
+	 * aio and closes the fd before the aio completes.  Since aio takes its
+	 * own ref to the file, the IO completion has to drop the ref, which is
+	 * how the fuse server can end up closing its clients' files.
 	 */
-	fuse_file_put(ff, ff->fm->fc->destroy);
+	fuse_file_put(ff, false);
 }
 
 void fuse_release_common(struct file *file, bool isdir)
@@ -865,22 +871,20 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 	struct fuse_args_pages *ap = &ia->ap;
 	size_t count = ia->read.in.size;
 	size_t num_read = args->out_args[0].size;
-	struct address_space *mapping = NULL;
-
-	for (i = 0; mapping == NULL && i < ap->num_folios; i++)
-		mapping = ap->folios[i]->mapping;
+	struct address_space *mapping;
+	struct inode *inode;
 
-	if (mapping) {
-		struct inode *inode = mapping->host;
+	WARN_ON_ONCE(!ap->num_folios);
+	mapping = ap->folios[0]->mapping;
+	inode = mapping->host;
 
-		/*
-		 * Short read means EOF. If file size is larger, truncate it
-		 */
-		if (!err && num_read < count)
-			fuse_short_read(inode, ia->read.attr_ver, num_read, ap);
+	/*
+	 * Short read means EOF. If file size is larger, truncate it
+	 */
+	if (!err && num_read < count)
+		fuse_short_read(inode, ia->read.attr_ver, num_read, ap);
 
-		fuse_invalidate_atime(inode);
-	}
+	fuse_invalidate_atime(inode);
 
 	for (i = 0; i < ap->num_folios; i++) {
 		folio_end_read(ap->folios[i], !err);
@@ -1175,7 +1179,6 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 	num = min(iov_iter_count(ii), fc->max_write);
 
 	ap->args.in_pages = true;
-	ap->descs[0].offset = offset;
 
 	while (num && ap->num_folios < max_folios) {
 		size_t tmp;
@@ -1823,19 +1826,15 @@ static void fuse_writepage_finish(struct fuse_writepage_args *wpa)
 	struct fuse_args_pages *ap = &wpa->ia.ap;
 	struct inode *inode = wpa->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	struct backing_dev_info *bdi = inode_to_bdi(inode);
 	int i;
 
-	for (i = 0; i < ap->num_folios; i++) {
+	for (i = 0; i < ap->num_folios; i++)
 		/*
 		 * Benchmarks showed that ending writeback within the
 		 * scope of the fi->lock alleviates xarray lock
 		 * contention and noticeably improves performance.
 		 */
 		iomap_finish_folio_write(inode, ap->folios[i], 1);
-		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
-		wb_writeout_inc(&bdi->wb);
-	}
 
 	wake_up(&fi->page_waitq);
 }
@@ -2010,14 +2009,11 @@ static void fuse_writepage_add_to_bucket(struct fuse_conn *fc,
 static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struct folio *folio,
 					  uint32_t folio_index, loff_t offset, unsigned len)
 {
-	struct inode *inode = folio->mapping->host;
 	struct fuse_args_pages *ap = &wpa->ia.ap;
 
 	ap->folios[folio_index] = folio;
 	ap->descs[folio_index].offset = offset;
 	ap->descs[folio_index].length = len;
-
-	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 }
 
 static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio,
@@ -2960,10 +2956,12 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 		.nodeid_out = ff_out->nodeid,
 		.fh_out = ff_out->fh,
 		.off_out = pos_out,
-		.len = min_t(size_t, len, UINT_MAX & PAGE_MASK),
+		.len = len,
 		.flags = flags
 	};
 	struct fuse_write_out outarg;
+	struct fuse_copy_file_range_out outarg_64;
+	u64 bytes_copied;
 	ssize_t err;
 	/* mark unstable when write-back is not used, and file_out gets
 	 * extended */
@@ -3013,33 +3011,51 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (is_unstable)
 		set_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state);
 
-	args.opcode = FUSE_COPY_FILE_RANGE;
+	args.opcode = FUSE_COPY_FILE_RANGE_64;
 	args.nodeid = ff_in->nodeid;
 	args.in_numargs = 1;
 	args.in_args[0].size = sizeof(inarg);
 	args.in_args[0].value = &inarg;
 	args.out_numargs = 1;
-	args.out_args[0].size = sizeof(outarg);
-	args.out_args[0].value = &outarg;
+	args.out_args[0].size = sizeof(outarg_64);
+	args.out_args[0].value = &outarg_64;
+	if (fc->no_copy_file_range_64) {
+fallback:
+		/* Fall back to old op that can't handle large copy length */
+		args.opcode = FUSE_COPY_FILE_RANGE;
+		args.out_args[0].size = sizeof(outarg);
+		args.out_args[0].value = &outarg;
+		inarg.len = len = min_t(size_t, len, UINT_MAX & PAGE_MASK);
+	}
 	err = fuse_simple_request(fm, &args);
 	if (err == -ENOSYS) {
-		fc->no_copy_file_range = 1;
-		err = -EOPNOTSUPP;
+		if (fc->no_copy_file_range_64) {
+			fc->no_copy_file_range = 1;
+			err = -EOPNOTSUPP;
+		} else {
+			fc->no_copy_file_range_64 = 1;
+			goto fallback;
+		}
 	}
-	if (!err && outarg.size > len)
-		err = -EIO;
-
 	if (err)
 		goto out;
 
+	bytes_copied = fc->no_copy_file_range_64 ?
+		outarg.size : outarg_64.bytes_copied;
+
+	if (bytes_copied > len) {
+		err = -EIO;
+		goto out;
+	}
+
 	truncate_inode_pages_range(inode_out->i_mapping,
 				   ALIGN_DOWN(pos_out, PAGE_SIZE),
-				   ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1);
+				   ALIGN(pos_out + bytes_copied, PAGE_SIZE) - 1);
 
 	file_update_time(file_out);
-	fuse_write_update_attr(inode_out, pos_out + outarg.size, outarg.size);
+	fuse_write_update_attr(inode_out, pos_out + bytes_copied, bytes_copied);
 
-	err = outarg.size;
+	err = bytes_copied;
 out:
 	if (is_unstable)
 		clear_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state);