Re: confusion about root partition causes panic during startup

On 7/20/23, Mike Karels <mike@karels.net> wrote:
> I installed an additional NVME drive on a system, and then booted.  It
> turns
> out that the new drive became nda0, renumbering the other drives.  The
> loader
> found the correct partition to boot (the only choice), and loaded the
> kernel
> correctly.  However, /etc/fstab still had the old name (nvd1p2), which is
> now drive 2.  I expected it to drop into single user, but instead the
> system
> panicked in vfs_mountroot_shuffle trying to switch root devices (see
> below).
> It doesn't seem that having the wrong root device in /etc/fstab should
> cause
> a panic; it makes it harder to patch the system.  I was unable to get the
> system to boot using boot-to-single-user or setting currdev, but I managed
> to remember doing "boot -a" from a loader prompt to get the system to ask
> the root device before mounting it.  I can easily reproduce this to test.
> Probably the NDFREE_PNBUF() shouldn't happen if namei() returned an error.
>

ye, this should do it (untested):

diff --git a/sys/kern/vfs_mountroot.c b/sys/kern/vfs_mountroot.c
index 956d29e3f084..85398ff781e4 100644
--- a/sys/kern/vfs_mountroot.c
+++ b/sys/kern/vfs_mountroot.c
@@ -352,13 +352,13 @@ vfs_mountroot_shuffle(struct thread *td, struct
mount *mpdevfs)
                NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE, fspath);
                error = namei(&nd);
                if (error) {
-                       NDFREE_PNBUF(&nd);
                        fspath = "/mnt";
                        NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE,
                            fspath);
                        error = namei(&nd);
                }
                if (!error) {
+                       NDFREE_PNBUF(&nd);
                        vp = nd.ni_vp;
                        error = (vp->v_type == VDIR) ? 0 : ENOTDIR;
                        if (!error)
@@ -376,7 +376,6 @@ vfs_mountroot_shuffle(struct thread *td, struct
mount *mpdevfs)
                        } else
                                vput(vp);
                }
-               NDFREE_PNBUF(&nd);

                if (error)
                        printf("mountroot: unable to remount previous root "
@@ -387,6 +386,7 @@ vfs_mountroot_shuffle(struct thread *td, struct
mount *mpdevfs)
        NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE, "/dev");
        error = namei(&nd);
        if (!error) {
+               NDFREE_PNBUF(&nd);
                vp = nd.ni_vp;
                error = (vp->v_type == VDIR) ? 0 : ENOTDIR;
                if (!error)



> 		Mike
>
> Trying to mount root from ufs:/dev/nvd1p2 [rw]...
> WARNING: WITNESS option enabled, expect reduced performance.
> mountroot: unable to remount devfs under /dev (error 2)
> panic: Assertion _ndp->ni_cnd.cn_pnbuf != NULL failed at
> ../../../kern/vfs_mountroot.c:416
> cpuid = 19
> time = 11
> KDB: stack backtrace:
> db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame
> 0xfffffe006d3bac40
> vpanic() at vpanic+0x149/frame 0xfffffe006d3bac90
> panic() at panic+0x43/frame 0xfffffe006d3bacf0
> vfs_mountroot() at vfs_mountroot+0x1bf7/frame 0xfffffe006d3bae60
> start_init() at start_init+0x23/frame 0xfffffe006d3baef0
> fork_exit() at fork_exit+0x82/frame 0xfffffe006d3baf30
> fork_trampoline() at fork_trampoline+0xe/frame 0xfffffe006d3baf30
> --- trap 0x5c035c02, rip = 0x680c680c680c680c, rsp = 0x1b6b1f6b1b6b1b6b, rbp
> = 0x4eb54eb54eb54eb5 ---
> KDB: enter: panic
> [ thread pid 1 tid 100002 ]
> Stopped at      kdb_enter+0x32: movq    $0,0xde7643(%rip)
>
>


-- 
Mateusz Guzik <mjguzik gmail.com>