Re: [PATCH 4.4 22/32] net: hso: fix null-ptr-deref during tty device unregistration

From: Greg Kroah-Hartman
Date: Mon Apr 26 2021 - 03:59:54 EST


On Mon, Apr 26, 2021 at 09:36:57AM +0200, Johan Hovold wrote:
> On Mon, Apr 26, 2021 at 09:29:20AM +0200, Greg Kroah-Hartman wrote:
> > From: Anirudh Rayabharam <mail@xxxxxxxxxxxxx>
> >
> > commit 8a12f8836145ffe37e9c8733dce18c22fb668b66 upstream
> >
> > Multiple ttys try to claim the same the minor number causing a double
> > unregistration of the same device. The first unregistration succeeds
> > but the next one results in a null-ptr-deref.
> >
> > The get_free_serial_index() function returns an available minor number
> > but doesn't assign it immediately. The assignment is done by the caller
> > later. But before this assignment, calls to get_free_serial_index()
> > would return the same minor number.
> >
> > Fix this by modifying get_free_serial_index to assign the minor number
> > immediately after one is found to be and rename it to obtain_minor()
> > to better reflect what it does. Similary, rename set_serial_by_index()
> > to release_minor() and modify it to free up the minor number of the
> > given hso_serial. Every obtain_minor() should have corresponding
> > release_minor() call.
> >
> > Fixes: 72dc1c096c705 ("HSO: add option hso driver")
> > Reported-by: syzbot+c49fe6089f295a05e6f8@xxxxxxxxxxxxxxxxxxxxxxxxx
> > Tested-by: syzbot+c49fe6089f295a05e6f8@xxxxxxxxxxxxxxxxxxxxxxxxx
> > Reviewed-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> > Signed-off-by: Anirudh Rayabharam <mail@xxxxxxxxxxxxx>
> > Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
> > [sudip: adjust context]
> > Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@xxxxxxxxx>
> > Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> > ---
> > drivers/net/usb/hso.c | 33 ++++++++++++---------------------
> > 1 file changed, 12 insertions(+), 21 deletions(-)
>
> We just got a regression report against this one. Perhaps better to hold
> off until that has been resolved.
>
> https://lore.kernel.org/r/20210425233509.9ce29da49037e1a421000bdd@xxxxxxxx

Good point, I'll go drop this from everywhere.

greg k-h