On Mon, Sep 09, 2024 at 04:41:00PM +0800, Junxian Huang wrote:
> On 2024/9/7 20:12, Jason Gunthorpe wrote:
> > On Thu, Sep 05, 2024 at 09:11:54PM +0800, Junxian Huang wrote:
> >
> >> @@ -698,11 +700,20 @@ static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma)
> >> ucontext = ib_uverbs_get_ucontext_file(file);
> >> if (IS_ERR(ucontext)) {
> >> ret = PTR_ERR(ucontext);
> >> - goto out;
> >> + goto out_srcu;
> >> }
> >> +
> >> + mutex_lock(&file->disassociation_lock);
> >> + if (file->disassociated) {
> >> + ret = -EPERM;
> >> + goto out_mutex;
> >> + }
> >
> > What sets disassociated back to false once the driver reset is
> > completed?
> >
> > I think you should probably drop this and instead add a lock and test
> > inside the driver within its mmap op. While reset is ongoing fail all
> > new mmaps.
> >
>
> disassociated won't be set back to false. This is to stop new mmaps on
> this ucontext even after reset is completed, because during hns reset,
> all resources will be destroyed, and the ucontexts will become unavailable.
That isn't really the model we are going for, the ucontext should be
recoverable even if the objects are not.
If you want to really fully destroy and fence things then you have to
unregister the whole ib_device
> > I think this doesn't need the hw_destroy_rwsem anymore since you are
> > using this new disassociation_lock instead. It doesn't make alot of
> > sense to hold the hw_destroy_rwsem for read here, it was ment to be
> > held for write.
>
> Then it seems we should remove the lockdep_assert_held() here?
Yes
Jason
