[PATCH] sys_sync_file_range()

Remove the recently-added LINUX_FADV_ASYNC_WRITE and LINUX_FADV_WRITE_WAIT
fadvise() additions, do it in a new sys_sync_file_range() syscall instead.
Reasons:

- It's more flexible. Things which would require two or three syscalls with
fadvise() can be done in a single syscall.

- Using fadvise() in this manner is something not covered by POSIX.

The patch wires up the syscall for x86.

The sycall is implemented in the new fs/sync.c. The intention is that we can
move sys_fsync(), sys_fdatasync() and perhaps sys_sync() into there later.

Documentation for the syscall is in fs/sync.c.

A test app (sync_file_range.c) is in
http://www.zip.com.au/~akpm/linux/patches/stuff/ext3-tools.tar.gz.

The available-to-GPL-modules do_sync_file_range() is for knfsd: "A COMMIT can
say NFS_DATA_SYNC or NFS_FILE_SYNC. I can skip the ->fsync call for
NFS_DATA_SYNC which is hopefully the more common."

Note: the `async' writeout mode SYNC_FILE_RANGE_WRITE will turn synchronous if
the queue is congested. This is trivial to fix: add a new flag bit, set
wbc->nonblocking. But I'm not sure that we want to expose implementation
details down to that level.

Note: it's notable that we can sync an fd which wasn't opened for writing.
Same with fsync() and fdatasync()).

Note: the code takes some care to handle attempts to sync file contents
outside the 16TB offset on 32-bit machines. It makes such attempts appear to
succeed, for best 32-bit/64-bit compatibility. Perhaps it should make such
requests fail...

Cc: Nick Piggin <[e-mail]>
Cc: Michael Kerrisk <[e-mail]>
Cc: Ulrich Drepper <[e-mail]>
Cc: Neil Brown <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

arch/i386/kernel/syscall_table.S

···
 	.long sys_set_robust_list
 	.long sys_get_robust_list
 	.long sys_splice
+	.long sys_sync_file_range

fs/Makefile

···
 		ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \
-		ioprio.o pnode.o drop_caches.o splice.o
+		ioprio.o pnode.o drop_caches.o splice.o sync.o
 
 obj-$(CONFIG_INOTIFY)		+= inotify.o
 obj-$(CONFIG_EPOLL)		+= eventpoll.o

fs/sync.c

···
+/*
+ * High-level sync()-related operations
+ */
+
+#include <linux/kernel.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/writeback.h>
+#include <linux/syscalls.h>
+#include <linux/linkage.h>
+#include <linux/pagemap.h>
+
+#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
+			SYNC_FILE_RANGE_WAIT_AFTER)
+
+/*
+ * sys_sync_file_range() permits finely controlled syncing over a segment of
+ * a file in the range offset .. (offset+nbytes-1) inclusive.  If nbytes is
+ * zero then sys_sync_file_range() will operate from offset out to EOF.
+ *
+ * The flag bits are:
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
+ * before performing the write.
+ *
+ * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
+ * range which are not presently under writeback.
+ *
+ * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
+ * after performing the write.
+ *
+ * Useful combinations of the flag bits are:
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
+ * in the range which were dirty on entry to sys_sync_file_range() are placed
+ * under writeout.  This is a start-write-for-data-integrity operation.
+ *
+ * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
+ * are not presently under writeout.  This is an asynchronous flush-to-disk
+ * operation.  Not suitable for data integrity operations.
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
+ * completion of writeout of all pages in the range.  This will be used after an
+ * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
+ * for that operation to complete and to return the result.
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
+ * a traditional sync() operation.  This is a write-for-data-integrity operation
+ * which will ensure that all pages in the range which were dirty on entry to
+ * sys_sync_file_range() are committed to disk.
+ *
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
+ * I/O errors or ENOSPC conditions and will return those to the caller, after
+ * clearing the EIO and ENOSPC flags in the address_space.
+ *
+ * It should be noted that none of these operations write out the file's
+ * metadata.  So unless the application is strictly performing overwrites of
+ * already-instantiated disk blocks, there are no guarantees here that the data
+ * will be available after a crash.
+ */
+asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
+					int flags)
+{
+	int ret;
+	struct file *file;
+	loff_t endbyte;			/* inclusive */
+	int fput_needed;
+	umode_t i_mode;
+
+	ret = -EINVAL;
+	if (flags & ~VALID_FLAGS)
+		goto out;
+
+	endbyte = offset + nbytes;
+
+	if ((s64)offset < 0)
+		goto out;
+	if ((s64)endbyte < 0)
+		goto out;
+	if (endbyte < offset)
+		goto out;
+
+	if (sizeof(pgoff_t) == 4) {
+		if (offset >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
+			/*
+			 * The range starts outside a 32 bit machine's
+			 * pagecache addressing capabilities.  Let it "succeed"
+			 */
+			ret = 0;
+			goto out;
+		}
+		if (endbyte >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
+			/*
+			 * Out to EOF
+			 */
+			nbytes = 0;
+		}
+	}
+
+	if (nbytes == 0)
+		endbyte = -1;
+	else
+		endbyte--;		/* inclusive */
+
+	ret = -EBADF;
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		goto out;
+
+	i_mode = file->f_dentry->d_inode->i_mode;
+	ret = -ESPIPE;
+	if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
+			!S_ISLNK(i_mode))
+		goto out_put;
+
+	ret = do_sync_file_range(file, offset, endbyte, flags);
+out_put:
+	fput_light(file, fput_needed);
+out:
+	return ret;
+}
+
+/*
+ * `endbyte' is inclusive
+ */
+int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte,
+			int flags)
+{
+	int ret;
+	struct address_space *mapping;
+
+	mapping = file->f_mapping;
+	if (!mapping) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = 0;
+	if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
+		ret = wait_on_page_writeback_range(mapping,
+					offset >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+		if (ret < 0)
+			goto out;
+	}
+
+	if (flags & SYNC_FILE_RANGE_WRITE) {
+		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
+						WB_SYNC_NONE);
+		if (ret < 0)
+			goto out;
+	}
+
+	if (flags & SYNC_FILE_RANGE_WAIT_AFTER) {
+		ret = wait_on_page_writeback_range(mapping,
+					offset >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+	}
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(do_sync_file_range);

include/asm-i386/unistd.h

···
 #define __NR_set_robust_list	311
 #define __NR_get_robust_list	312
 #define __NR_sys_splice		313
+#define __NR_sys_sync_file_range 314
 
-#define NR_syscalls 314
+#define NR_syscalls 315
 
 /*
  * user-visible error numbers are in the range -1 - -128: see

include/linux/fadvise.h

···
 #define POSIX_FADV_NOREUSE	5 /* Data will be accessed once.  */
 #endif
 
-/*
- * Linux-specific fadvise() extensions:
- */
-#define LINUX_FADV_ASYNC_WRITE	32	/* Start writeout on range */
-#define LINUX_FADV_WRITE_WAIT	33	/* Wait upon writeout to range */
-
 #endif	/* FADVISE_H_INCLUDED */

include/linux/fs.h

···
 extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
 extern int fcntl_getlease(struct file *filp);
 
+/* fs/sync.c */
+#define SYNC_FILE_RANGE_WAIT_BEFORE	1
+#define SYNC_FILE_RANGE_WRITE		2
+#define SYNC_FILE_RANGE_WAIT_AFTER	4
+extern int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte,
+			int flags);
+
 /* fs/locks.c */
 extern void locks_init_lock(struct file_lock *);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);

include/linux/syscalls.h

···
 asmlinkage long sys_unshare(unsigned long unshare_flags);
 asmlinkage long sys_splice(int fdin, int fdout, size_t len,
 				unsigned int flags);
+asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
+					int flags);
 
 #endif

mm/fadvise.c

···
  *
  * LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk.
  *
- * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently
- * dirty pages at the disk.
- *
- * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push
- * all of the currently dirty pages at the disk, wait until they have been
- * written.
- *
- * It should be noted that none of these operations write out the file's
- * metadata.  So unless the application is strictly performing overwrites of
- * already-instantiated disk blocks, there are no guarantees here that the data
- * will be available after a crash.
  */
 asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 {
···
 		if (end_index >= start_index)
 			invalidate_mapping_pages(mapping, start_index,
 						end_index);
-		break;
-	case LINUX_FADV_ASYNC_WRITE:
-		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
-						WB_SYNC_NONE);
-		break;
-	case LINUX_FADV_WRITE_WAIT:
-		ret = wait_on_page_writeback_range(mapping,
-					offset >> PAGE_CACHE_SHIFT,
-					endbyte >> PAGE_CACHE_SHIFT);
 		break;
 	default:
 		ret = -EINVAL;