Linux 4.11 compat: statx support

Linux 4.11 added a new statx system call that allows us to expose crtime
as btime. We do this by caching crtime in the znode to match how atime,
ctime and mtime are cached in the inode.

statx also introduced a new way of reporting whether the immutable,
append and nodump bits have been set. It adds support for reporting
compression and encryption, but the semantics on other filesystems is
not just to report compression/encryption, but to allow it to be turned
on/off at the file level. We do not support that.

We could implement semantics where we refuse to allow user modification
of the bit, but we would need to do a dnode_hold() in zfs_znode_alloc()
to find out encryption/compression information. That would introduce
locking that will have a minor (although unmeasured) performance cost.
It also would be inferior to zdb, which reports far more detailed
information. We therefore omit reporting of encryption/compression
through statx in favor of recommending that users interested in such
information use zdb.

Reviewed-by: Tony Nguyen <[email protected]>
Reviewed-by: Allan Jude <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Alexander Motin <[email protected]>
Reviewed-by: Ryan Moeller <[email protected]>
Signed-off-by: Richard Yao <[email protected]>
Closes openzfs#8507

Author: ryao

include/os/linux/zfs/sys/zfs_znode_impl.h

@@ -36,21 +36,21 @@
 #include <sys/list.h>
 #include <sys/dmu.h>
 #include <sys/sa.h>
+#include <sys/time.h>
 #include <sys/zfs_vfsops.h>
 #include <sys/rrwlock.h>
 #include <sys/zfs_sa.h>
 #include <sys/zfs_stat.h>
 #include <sys/zfs_rlock.h>
 
-
 #ifdef	__cplusplus
 extern "C" {
 #endif
 
 #define	ZNODE_OS_FIELDS			\
+	inode_timespec_t z_btime; /* creation/birth time (cached) */ \
 	struct inode	z_inode;
 
-
 /*
  * Convert between znode pointers and inode pointers
  */

module/os/linux/zfs/zfs_znode.c

@@ -525,9 +525,9 @@ zfs_znode_alloc(zfsvfs_t *zfsvfs, dmu_buf_t *db, int blksz,
 	uint64_t tmp_gen;
 	uint64_t links;
 	uint64_t z_uid, z_gid;
-	uint64_t atime[2], mtime[2], ctime[2];
+	uint64_t atime[2], mtime[2], ctime[2], btime[2];
 	uint64_t projid = ZFS_DEFAULT_PROJID;
-	sa_bulk_attr_t bulk[11];
+	sa_bulk_attr_t bulk[12];
 	int count = 0;
 
 	ASSERT(zfsvfs != NULL);
@@ -569,6 +569,7 @@ zfs_znode_alloc(zfsvfs_t *zfsvfs, dmu_buf_t *db, int blksz,
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zfsvfs), NULL, &atime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, &mtime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, 16);
+	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CRTIME(zfsvfs), NULL, &btime, 16);
 
 	if (sa_bulk_lookup(zp->z_sa_hdl, bulk, count) != 0 || tmp_gen == 0 ||
 	    (dmu_objset_projectquota_enabled(zfsvfs->z_os) &&
@@ -596,6 +597,7 @@ zfs_znode_alloc(zfsvfs_t *zfsvfs, dmu_buf_t *db, int blksz,
 	ZFS_TIME_DECODE(&ip->i_atime, atime);
 	ZFS_TIME_DECODE(&ip->i_mtime, mtime);
 	ZFS_TIME_DECODE(&ip->i_ctime, ctime);
+	ZFS_TIME_DECODE(&zp->z_btime, btime);
 
 	ip->i_ino = zp->z_id;
 	zfs_znode_update_vfs(zp);
@@ -1169,12 +1171,12 @@ zfs_rezget(znode_t *zp)
 	uint64_t obj_num = zp->z_id;
 	uint64_t mode;
 	uint64_t links;
-	sa_bulk_attr_t bulk[10];
+	sa_bulk_attr_t bulk[11];
 	int err;
 	int count = 0;
 	uint64_t gen;
 	uint64_t z_uid, z_gid;
-	uint64_t atime[2], mtime[2], ctime[2];
+	uint64_t atime[2], mtime[2], ctime[2], btime[2];
 	uint64_t projid = ZFS_DEFAULT_PROJID;
 	znode_hold_t *zh;
 
@@ -1244,6 +1246,7 @@ zfs_rezget(znode_t *zp)
 	    &mtime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL,
 	    &ctime, 16);
+	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CRTIME(zfsvfs), NULL, &btime, 16);
 
 	if (sa_bulk_lookup(zp->z_sa_hdl, bulk, count)) {
 		zfs_znode_dmu_fini(zp);
@@ -1269,6 +1272,7 @@ zfs_rezget(znode_t *zp)
 	ZFS_TIME_DECODE(&ZTOI(zp)->i_atime, atime);
 	ZFS_TIME_DECODE(&ZTOI(zp)->i_mtime, mtime);
 	ZFS_TIME_DECODE(&ZTOI(zp)->i_ctime, ctime);
+	ZFS_TIME_DECODE(&zp->z_btime, btime);
 
 	if ((uint32_t)gen != ZTOI(zp)->i_generation) {
 		zfs_znode_dmu_fini(zp);

module/os/linux/zfs/zpl_inode.c

@@ -378,18 +378,46 @@ zpl_getattr_impl(const struct path *path, struct kstat *stat, u32 request_mask,
 {
 	int error;
 	fstrans_cookie_t cookie;
+	struct inode *ip = path->dentry->d_inode;
+	znode_t *zp __maybe_unused = ITOZ(ip);
 
 	cookie = spl_fstrans_mark();
 
 	/*
-	 * XXX request_mask and query_flags currently ignored.
+	 * XXX query_flags currently ignored.
 	 */
 
 #ifdef HAVE_USERNS_IOPS_GETATTR
-	error = -zfs_getattr_fast(user_ns, path->dentry->d_inode, stat);
+	error = -zfs_getattr_fast(user_ns, ip, stat);
 #else
-	error = -zfs_getattr_fast(kcred->user_ns, path->dentry->d_inode, stat);
+	error = -zfs_getattr_fast(kcred->user_ns, ip, stat);
 #endif
+
+#ifdef STATX_BTIME
+	if (request_mask & STATX_BTIME) {
+		stat->btime = zp->z_btime;
+		stat->result_mask |= STATX_BTIME;
+	}
+#endif
+
+#ifdef STATX_ATTR_IMMUTABLE
+	if (zp->z_pflags & ZFS_IMMUTABLE)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	stat->attributes_mask |= STATX_ATTR_IMMUTABLE;
+#endif
+
+#ifdef STATX_ATTR_APPEND
+	if (zp->z_pflags & ZFS_APPENDONLY)
+		stat->attributes |= STATX_ATTR_APPEND;
+	stat->attributes_mask |= STATX_ATTR_APPEND;
+#endif
+
+#ifdef STATX_ATTR_NODUMP
+	if (zp->z_pflags & ZFS_NODUMP)
+		stat->attributes |= STATX_ATTR_NODUMP;
+	stat->attributes_mask |= STATX_ATTR_NODUMP;
+#endif
+
 	spl_fstrans_unmark(cookie);
 	ASSERT3S(error, <=, 0);