Re: [usb-storage] Re: [PATCH] usb-storage: alauda: track media_initialized per port
From: Alan Stern
Date: Sun Nov 22 2026 - 09:53:33 EST
On Sun, Nov 22, 2026 at 01:05:51PM +0500, Arbab Haider wrote:
> On Sat, Nov 21, 2026 at 03:54:57PM -0500, Alan Stern wrote:
> > Has this patch been tested?
>
> Yes, tested in QEMU (x86_64, v7.4-rc3 with KASAN, UBSAN, dummy_hcd,
> raw_gadget, and usb-storage alauda enabled). I do not have physical
> Alauda hardware, so testing was done via dummy_hcd + raw_gadget:
>
> - Before the patch: running the syzbot C reproducer reproduced the
> UBSAN division-overflow / divide error in alauda_read_data()
> (drivers/usb/storage/alauda.c:986) on LUN 1.
>
> - After the patch: the syzbot reproducer passes with no UBSAN, KASAN,
> or divide errors. I also verified additional raw_gadget scenarios:
> * READ_CAPACITY and READ_10 on both LUN 0 and LUN 1
> * Media removal (status 0x80) followed by re-insertion without the
> 0x08 media-change bit and READ_10
> * Media change with a failing alauda_init_media() (unrecognized media
> signature) followed by READ_10 and WRITE_10
> * Recovery back to a valid media signature with TEST_UNIT_READY,
> READ_CAPACITY, and READ_10
I asked because when syzbot tests a patch successfully, it provides a
Tested-by: tag and asks to have the tag included in the final patch
submission -- but you didn't do this. Did you run the reproducer
locally, without using the bot?
Alan Stern