Re: [PATCH v2] misc: sgi-gru: fix use-after-free error in gru_set_context_option, gru_fault and gru_handle_user_call_os

[Zheng Hacker]

Zheng Yejian <zhengyejian1@xxxxxxxxxx> 于2022年10月9日周日 19:28写道：
>
> On Thu,  6 Oct 2022 23:26:43 +0800
> Zheng Wang <zyytlz.wz@xxxxxxx> wrote:
> > Gts may be freed in gru_check_chiplet_assignment.
> > The caller still use it after that, UAF happens.
> >
> > Fix it by introducing a return value to see if it's in error path or not.
> > Free the gts in caller if gru_check_chiplet_assignment check failed.
> >
> > Fixes: 55484c45dbec ("gru: allow users to specify gru chiplet 2")
> > Reported-by: Zheng Wang <hackerzheng666@xxxxxxxxx>
> > Signed-off-by: Zheng Wang <zyytlz.wz@xxxxxxx>
> > ---
> > v2:
> > - commit message changes suggested by Greg
> >
> > v1: https://lore.kernel.org/lkml/CAJedcCzY72jqgF-pCPtx66vXXwdPn-KMagZnqrxcpWw1NxTLaA@xxxxxxxxxxxxxx/
> > ---
> >  drivers/misc/sgi-gru/grufault.c  | 15 ++++++++++++---
> >  drivers/misc/sgi-gru/grumain.c   | 17 +++++++++++++----
> >  drivers/misc/sgi-gru/grutables.h |  2 +-
> >  3 files changed, 26 insertions(+), 8 deletions(-)
> >
> > diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
> > index d7ef61e602ed..f1e5b96fef4b 100644
> > --- a/drivers/misc/sgi-gru/grufault.c
> > +++ b/drivers/misc/sgi-gru/grufault.c
> > @@ -656,7 +656,9 @@ int gru_handle_user_call_os(unsigned long cb)
> >       if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE)
> >               goto exit;
> >
> > -     gru_check_context_placement(gts);
> > +     ret = gru_check_context_placement(gts);
> > +     if (ret)
> > +             goto err;
> >
> >       /*
> >        * CCH may contain stale data if ts_force_cch_reload is set.
> > @@ -677,6 +679,10 @@ int gru_handle_user_call_os(unsigned long cb)
> >  exit:
> >       gru_unlock_gts(gts);
> >       return ret;
> > +err:
> > +     gru_unlock_gts(gts);
> > +     gru_unload_context(gts, 1);
> > +     return -EINVAL;
> >  }
> >
> >  /*
> > @@ -874,7 +880,7 @@ int gru_set_context_option(unsigned long arg)
> >               } else {
> >                       gts->ts_user_blade_id = req.val1;
> >                       gts->ts_user_chiplet_id = req.val0;
> > -                     gru_check_context_placement(gts);
> > +                     ret = gru_check_context_placement(gts);
> >               }
> >               break;
> >       case sco_gseg_owner:
> > @@ -889,6 +895,9 @@ int gru_set_context_option(unsigned long arg)
> >               ret = -EINVAL;
> >       }
> >       gru_unlock_gts(gts);
> > -
> > +     if (ret) {
> > +             gru_unload_context(gts, 1);
> > +             ret = -EINVAL;
> > +     }
> >       return ret;
> >  }
> > diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
> > index 9afda47efbf2..79903cf7e706 100644
> > --- a/drivers/misc/sgi-gru/grumain.c
> > +++ b/drivers/misc/sgi-gru/grumain.c
> > @@ -716,9 +716,10 @@ static int gru_check_chiplet_assignment(struct gru_state *gru,
> >   * chiplet. Misassignment can occur if the process migrates to a different
> >   * blade or if the user changes the selected blade/chiplet.
> >   */
> > -void gru_check_context_placement(struct gru_thread_state *gts)
> > +int gru_check_context_placement(struct gru_thread_state *gts)
> >  {
> >       struct gru_state *gru;
> > +     int ret = 0;
> >
> >       /*
> >        * If the current task is the context owner, verify that the
> > @@ -727,14 +728,16 @@ void gru_check_context_placement(struct gru_thread_state *gts)
> >        */
> >       gru = gts->ts_gru;
> >       if (!gru || gts->ts_tgid_owner != current->tgid)
> > -             return;
> > +             return ret;
> >
> >       if (!gru_check_chiplet_assignment(gru, gts)) {
> >               STAT(check_context_unload);
> > -             gru_unload_context(gts, 1);
> > +             ret = -EINVAL;
> >       } else if (gru_retarget_intr(gts)) {
> >               STAT(check_context_retarget_intr);
> >       }
> > +
> > +     return ret;
> >  }
> >
> >
> > @@ -919,6 +922,7 @@ vm_fault_t gru_fault(struct vm_fault *vmf)
> >       struct gru_thread_state *gts;
> >       unsigned long paddr, vaddr;
> >       unsigned long expires;
> > +     int ret;
> >
> >       vaddr = vmf->address;
> >       gru_dbg(grudev, "vma %p, vaddr 0x%lx (0x%lx)\n",
> > @@ -934,7 +938,12 @@ vm_fault_t gru_fault(struct vm_fault *vmf)
> >       mutex_lock(&gts->ts_ctxlock);
> >       preempt_disable();
> >
> > -     gru_check_context_placement(gts);
> > +     ret = gru_check_context_placement(gts);
> > +     if (ret) {
> > +             mutex_unlock(&gts->ts_ctxlock);
> > +             gru_unload_context(gts, 1);
>
> preempt_disable() is called before, is a preempt_enable() required here?
>

Oh yes, thanks for your suggestion Yejian. I will add that in the next patch :).

Best regards,
Zheng Wang