Re: zfs questions

hi,

On Mon, Mar 2, 2026 at 8:19 PM J. Hannken-Illjes <[email protected]> wrote:
>
> > On 1. Mar 2026, at 15:13, Takashi YAMAMOTO <[email protected]> wrote:
> >
> > On Fri, Feb 20, 2026 at 5:09 PM Takashi YAMAMOTO <[email protected]> wrote:
> >>
> >> hi,
> >>
> >> recently i have used netbsd zfs and have a few questions.
> >>
> >> * what's the purpose of zfs_zget_cleaner/VN_RELE_CLEANER?
> >>  i have read the explanation in
> >> https://gnats.netbsd.org/cgi-bin/query-pr-single.pl?number=59885 .
> >>  but i don't understand why we want to avoid the normal zfs_zget in
> >> the first place.
> >>  for me, it seems working w/o these special versions of functions:
> >>  https://github.com/yamt/netbsd-src/commit/438ec29437465e0b7e2b831d4452159f83cad0cf
> >>  (i will attach the same patch to this mail for those who don't like github.)
> >
> > this version had a few deadlock issues.
> >
> > i will attach a fixed version i'm currently testing.
> >
> >>
> >> * is anyone using zfs in netbsd seriously? :-)
> >>
> >> * does anyone have a plan to update the codebase to recent openzfs?
> > <a.diff>
>
> This patch makes the situation better but it fires assertions during unmount.
>
> Running some stress tests on a 16-core amd64 vm with DEBUG+LOCKDEBUG and
> kern.maxvnodes=1105 unmount crashes as it tries to load a vnode during unmount:
>
>
> panic: kernel diagnostic assertion "mp == NULL || (mp->mnt_iflag & IMNT_UNMOUNT) == 0 || vp->v_tag == VT_VFS" failed: file "src/sys/kern/vfs_mount.c", line 545
>
> #12  vfs_insmntque (vp=0xffffb751d4324a80, mp=0xffffb751cf2e2000) at src/sys/kern/vfs_mount.c:545
> #13  vcache_get (mp=0xffffb751cf2e2000, key=key@entry=0xffffc3070a334bc8, key_len=key_len@entry=8, vpp=vpp@entry=0xffffc3070a334bd8) at src/sys/kern/vfs_vnode.c:1666
> #14  zfs_zget (zfsvfs=zfsvfs@entry=0xffffc3002f7ba000, obj_num=<optimized out>, obj_num@entry=24865, zpp=zpp@entry=0xffffc3070a334c20) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zfs_znode.c:1287
> #15  zfs_get_data (arg=0xffffc3002f7ba000, lr=0xffffc30048cd41d8, buf=0xffffc30048cd4298 "", zio=0xffffb751e587e840) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vnops.c:1500
> #16  zil_lwb_commit (zilog=<optimized out>, itx=0xffffb7517fb6f5c0, lwb=0xffffb751bffa25f8) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zil.c:1144
> #17 zil_commit_writer (zilog=0xffffb751e664d540) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zil.c:1556
> #18 zil_commit (zilog=0xffffb751e664d540, foid=<optimized out>) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zil.c:1638
> #19  zil_commit (zilog=0xffffb751e664d540, foid=0) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zil.c:1620
> #20 zil_close (zilog=0xffffb751e664d540) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zil.c:1856
> #21  zfsvfs_teardown (zfsvfs=zfsvfs@entry=0xffffc3002f7ba000, unmounting=unmounting@entry=1) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c:2288
> #22  zfs_umount (vfsp=0xffffb751cf2e2000, fflag=524288) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c:2445
> #23  VFS_UNMOUNT (mp=mp@entry=0xffffb751cf2e2000, a=a@entry=524288) at src/sys/kern/vfs_subr.c:1526
> #24  dounmount (mp=mp@entry=0xffffb751cf2e2000, flags=524288, l=l@entry=0xffffb751e855d800) at src/sys/kern/vfs_mount.c:980
> #25  sys_unmount (l=0xffffb751e855d800, uap=0xffffc3070a335000, retval=<optimized out>) at src/sys/kern/vfs_syscalls.c:728
> #26  sy_call (sy=0xffffffff8210a050 <sysent+528>, l=0xffffb751e855d800, uap=0xffffc3070a335000, rval=0xffffc3070a334fb0) at src/sys/sys/syscallvar.h:65
> #27 sy_invoke (sy=0xffffffff8210a050 <sysent+528>, l=0xffffb751e855d800, uap=0xffffc3070a335000, rval=0xffffc3070a334fb0, code=22) at src/sys/sys/syscallvar.h:94
> #28  syscall (frame=0xffffc3070a335000) at src/sys/arch/x86/x86/syscall.c:137
> #29  handle_syscall ()
>
> Here we have mp != NULL and mp->mnt_iflag == 0x122 (IMNT_MPSAFE | IMNT_NCLOOKUP | IMNT_UNMOUNT)

it's an interesting crash. thank you.
i tried to reproduce it by myself. but no luck.
the attached patch (b.diff) would fix it.

well, honestly speaking, i don't understand why zil_close commits the
zil in the first place.
my impression is that it should not be necessary because we are
syncing txg for unmount anyway.
what do you think?

>
>
> Disabling this assertion zfs unmount fails to destroy a list as it is not empty:
>
>
> panic: solaris assert: list->list_head.list_next == node, file: src/sys/../external/cddl/osnet/dist/uts/common/os/list.c, line: 86
>
> #12  list_destroy (list=list@entry=0xffff940059153040) at src/sys/../external/cddl/osnet/dist/uts/common/os/list.c:86
> #13  zfsvfs_free (zfsvfs=0xffff940059152000) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c:1439
> #14  zfs_freevfs (vfsp=0xffff859a2e81d000) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c:2782
> #15 zfs_umount (vfsp=0xffff859a2e81d000, fflag=<optimized out>) at src/sys/../external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c:2471
> #16  VFS_UNMOUNT (mp=mp@entry=0xffff859a2e81d000, a=a@entry=524288) at src/sys/kern/vfs_subr.c:1526
> #17  dounmount (mp=mp@entry=0xffff859a2e81d000, flags=524288, l=l@entry=0xffff859a6a698400) at src/sys/kern/vfs_mount.c:980
> #18  sys_unmount (l=0xffff859a6a698400, uap=0xffff94070afdc000, retval=<optimized out>) at src/sys/kern/vfs_syscalls.c:728
> #19  sy_call (sy=0xffffffff8210a050 <sysent+528>, l=0xffff859a6a698400, uap=0xffff94070afdc000, rval=0xffff94070afdbfb0) at src/sys/sys/syscallvar.h:65
> #20  sy_invoke (sy=0xffffffff8210a050 <sysent+528>, l=0xffff859a6a698400, uap=0xffff94070afdc000, rval=0xffff94070afdbfb0, code=22) at src/sys/sys/syscallvar.h:94
> #21 syscall (frame=0xffff94070afdc000) at src/sys/arch/x86/x86/syscall.c:137
> #22  handle_syscall ()
>
> where *list is (list_t *) 0xffff940059153040:
>
> {
>   list_size = 240,
>   list_offset = 200,
>   list_head = {
>     list_next = 0xffff859a07007ab8,
>     list_prev = 0xffff8599c322bea8
>   }
> }
>
> --
> J. Hannken-Illjes - [email protected]

diff --git a/external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c b/external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c
index 464bf0019009..aef2cb29fb7e 100644
--- a/external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c
+++ b/external/cddl/osnet/dist/uts/common/fs/zfs/zfs_vfsops.c
@@ -2428,12 +2428,26 @@ zfs_umount(vfs_t *vfsp, int fflag)
 	 */
 #ifdef __FreeBSD_kernel__
 	ret = vflush(vfsp, 0, (fflag & MS_FORCE) ? FORCECLOSE : 0, td);
+	if (ret != 0)
+		return (ret);
 #endif
 #ifdef __NetBSD__
-	ret = vflush(vfsp, NULL, (fflag & MS_FORCE) ? FORCECLOSE : 0);
+	/*
+	 * we loop here because zil_commit can bring some vnodes
+	 * back to mnt_vnodelist via zfs_get_data.
+	 */
+	mutex_enter(vfsp->mnt_vnodelock);
+	while (!TAILQ_EMPTY(&vfsp->mnt_vnodelist)) {
+		mutex_exit(vfsp->mnt_vnodelock);
+		ret = vflush(vfsp, NULL, (fflag & MS_FORCE) ? FORCECLOSE : 0);
+		if (ret != 0)
+			return (ret);
+		if (zfsvfs->z_log)
+			zil_commit(zfsvfs->z_log, 0);
+		mutex_enter(vfsp->mnt_vnodelock);
+	}
+	mutex_exit(vfsp->mnt_vnodelock);
 #endif
-	if (ret != 0)
-		return (ret);
 
 #ifdef illumos
 	if (!(fflag & MS_FORCE)) {
diff --git a/sys/kern/vfs_mount.c b/sys/kern/vfs_mount.c
index 7a69b58632c9..9e9d358f0c09 100644
--- a/sys/kern/vfs_mount.c
+++ b/sys/kern/vfs_mount.c
@@ -542,7 +542,7 @@ vfs_insmntque(vnode_t *vp, struct mount *mp)
 	struct mount *omp;
 	kmutex_t *lock;
 
-	KASSERT(mp == NULL || (mp->mnt_iflag & IMNT_UNMOUNT) == 0 ||
+	KASSERT(mp == NULL || (mp->mnt_iflag & IMNT_GONE) == 0 ||
 	    vp->v_tag == VT_VFS);
 
 	/*
@@ -1003,6 +1003,7 @@ dounmount(struct mount *mp, int flags, struct lwp *l)
 	 * vfs_busy() from succeeding.
 	 */
 	mp->mnt_iflag |= IMNT_GONE;
+	KASSERT(TAILQ_EMPTY(&mp->mnt_vnodelist));
 	if ((coveredvp = mp->mnt_vnodecovered) != NULLVP) {
 		coveredvp->v_mountedhere = NULL;
 	}