zfs_rename: support RENAME_* flags

Implement support for Linux's RENAME_* flags (for renameat2). Aside from
being quite useful for userspace (providing race-free ways to exchange
paths and implement mv --no-clobber), they are used by overlayfs and are
thus required in order to use overlayfs-on-ZFS.

In order for us to represent the new renameat2(2) flags in the ZIL, we
create two new transaction types for the two flags which need
transactional-level support (RENAME_EXCHANGE and RENAME_WHITEOUT).
RENAME_NOREPLACE does not need any ZIL support because we know that if
the operation succeeded before creating the ZIL entry, there was no file
to be clobbered and thus it can be treated as a regular TX_RENAME.

Reviewed-by: Ryan Moeller <[email protected]>
Reviewed-by: Alexander Motin <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Pavel Snajdr <[email protected]>
Signed-off-by: Aleksa Sarai <[email protected]>
Closes #12209
Closes #14070

1 files changed, 16 insertions, 1 deletions

diff --git a/include/sys/zil.h b/include/sys/zil.h
index cec04f120..9591fb4f6 100644
--- a/include/sys/zil.h
+++ b/include/sys/zil.h
@@ -164,7 +164,9 @@ typedef enum zil_create {
 #define	TX_MKDIR_ACL_ATTR	19	/* mkdir with ACL + attrs */
 #define	TX_WRITE2		20	/* dmu_sync EALREADY write */
 #define	TX_SETSAXATTR		21	/* Set sa xattrs on file */
-#define	TX_MAX_TYPE		22	/* Max transaction type */
+#define	TX_RENAME_EXCHANGE	22	/* Atomic swap via renameat2 */
+#define	TX_RENAME_WHITEOUT	23	/* Atomic whiteout via renameat2 */
+#define	TX_MAX_TYPE		24	/* Max transaction type */
 
 /*
  * The transactions for mkdir, symlink, remove, rmdir, link, and rename
@@ -318,6 +320,19 @@ typedef struct {
 } lr_rename_t;
 
 typedef struct {
+	lr_rename_t	lr_rename;	/* common rename portion */
+	/* members related to the whiteout file (based on lr_create_t) */
+	uint64_t	lr_wfoid;	/* obj id of the new whiteout file */
+	uint64_t	lr_wmode;	/* mode of object */
+	uint64_t	lr_wuid;	/* uid of whiteout */
+	uint64_t	lr_wgid;	/* gid of whiteout */
+	uint64_t	lr_wgen;	/* generation (txg of creation) */
+	uint64_t	lr_wcrtime[2];	/* creation time */
+	uint64_t	lr_wrdev;	/* always makedev(0, 0) */
+	/* 2 strings: names of source and destination follow this */
+} lr_rename_whiteout_t;
+
+typedef struct {
 	lr_t		lr_common;	/* common portion of log record */
 	uint64_t	lr_foid;	/* file object to write */
 	uint64_t	lr_offset;	/* offset to write to */