Linux: Fix ZFS_ENTER/ZFS_EXIT/ZFS_VERFY_ZP usage

The ZFS_ENTER/ZFS_EXIT/ZFS_VERFY_ZP macros should not be used
in the Linux zpl_*.c source files.  They return a positive error
value which is correct for the common code, but not for the Linux
specific kernel code which expects a negative return value.  The
ZPL_ENTER/ZPL_EXIT/ZPL_VERFY_ZP macros should be used instead.

Furthermore, the ZPL_EXIT macro has been updated to not call the
zfs_exit_fs() function.  This prevents a possible deadlock which
can occur when a snapshot is automatically unmounted because the
zpl_show_devname() must never wait on in progress automatic
snapshot unmounts.

Reviewed-by: Adam Moss <c@yotes.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11169 
Closes #11201

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

@@ -90,7 +90,11 @@ do {								\
 	zfs_exit_fs(zfsvfs);					\
 	rrm_exit(&(zfsvfs)->z_teardown_lock, FTAG);		\
 } while (0)
-#define	ZPL_EXIT(zfsvfs)	ZFS_EXIT(zfsvfs)
+
+#define	ZPL_EXIT(zfsvfs)					\
+do {								\
+	rrm_exit(&(zfsvfs)->z_teardown_lock, FTAG);		\
+} while (0)
 
 /* Verifies the znode is valid. */
 #define	ZFS_VERIFY_ZP_ERROR(zp, error)				\