Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 9 Nov 2022 16:32:57 -0600
From:   Dimitri Sivanich <sivanich@hpe.com>
To:     Zheng Wang <zyytlz.wz@163.com>
Cc:     gregkh@linuxfoundation.org, zhengyejian1@huawei.com,
        dimitri.sivanich@hpe.com, arnd@arndb.de,
        linux-kernel@vger.kernel.org, hackerzheng666@gmail.com,
        alex000young@gmail.com, security@kernel.org, lkp@intel.com
Subject: Re: [PATCH v9] misc: sgi-gru: fix use-after-free error in
  gru_set_context_option, gru_fault and gru_handle_user_call_os
Message-ID: <20221109223257.GB34247@hpe.com>
References: <20221109141701.237407-1-zyytlz.wz@163.com>
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20221109141701.237407-1-zyytlz.wz@163.com>
MIME-Version: 1.0
Precedence: bulk

On Wed, Nov 09, 2022 at 10:17:01PM +0800, Zheng Wang wrote:
> In some bad situation, the gts may be freed gru_check_chiplet_assignment.
> The call chain can be gru_unload_context->gru_free_gru_context->gts_drop
> and kfree finally. However, the caller didn't know if the gts is freed
> or not and use it afterwards. This will trigger a Use after Free bug.
> 
> 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")
> Signed-off-by: Zheng Wang <zyytlz.wz@163.com>
> Acked-by: Dimitri Sivanich <sivanich@hpe.com>
> ---
> v9:
> - rewrite changelog and add comment in the code to make it more clear
> 
> v8:
> - remove tested-by tag suggested by Greg
> 
> v7:
> - fix some spelling problems suggested by Greg, change kernel test robot from reported-by tag to tested-by tag
> 
> v6:
> - remove unused var checked by kernel test robot
> 
> v5:
> - fix logical issue and remove unnecessary variable suggested by Dimitri Sivanich
> 
> v4:
> - use VM_FAULT_NOPAGE as failure code in gru_fault and -EINVAL in other functions suggested by Yejian
> 
> v3:
> - add preempt_enable and use VM_FAULT_NOPAGE as failure code suggested by Yejian
> 
> v2:
> - commit message changes suggested by Greg
> 
> v1: https://lore.kernel.org/lkml/CAJedcCzY72jqgF-pCPtx66vXXwdPn-KMagZnqrxcpWw1NxTLaA@mail.gmail.com/
> ---
>  drivers/misc/sgi-gru/grufault.c  | 14 ++++++++++++--
>  drivers/misc/sgi-gru/grumain.c   | 22 ++++++++++++++++++----
>  drivers/misc/sgi-gru/grutables.h |  2 +-
>  3 files changed, 31 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
> index d7ef61e602ed..bdd515d33225 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);

Below we do not want to skip over the rest of the logic in either return case.
You will have to do the gru_find_lock_gts again after unloading the gru context,
then check the gts value, then return EINVAL if not set (same as earlier in the
function).

> +	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 +880,11 @@ 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);
> +			if (gru_check_context_placement(gts)) {
> +				gru_unlock_gts(gts);
> +				gru_unload_context(gts, 1);

Looking at this again, I think we should return 0, as we originally would 
have done in this case anyway.

> +				return -EINVAL;
> +			}
>  		}
>  		break;
>  	case sco_gseg_owner:
> diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
> index 6706ef3c5977..816def778078 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
> @@ -726,15 +727,23 @@ void gru_check_context_placement(struct gru_thread_state *gts)
>  	 * references. Pthread apps use non-owner references to the CBRs.
>  	 */
>  	gru = gts->ts_gru;
> +	/*
> +	 * If gru or gts->ts_tgid_owner isn't initialized properly, return
> +	 * success is fine, for it's not a deadly error. The related variable
> +	 * can be reconfigure in other function.The caller is responsible
> +	 * for their inspection, and reinitialization if needed.
> +	 */

How about this instead?
  "If gru or gts->ts_tgid_owner isn't initialized properly, return
   success to indicate that the caller does not need to unload the gru
   context.  The caller is responsible for their inspection and
   reinitialization if needed."

>  	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;
>  }
>  
>  
> @@ -934,7 +943,12 @@ vm_fault_t gru_fault(struct vm_fault *vmf)
>  	mutex_lock(&gts->ts_ctxlock);
>  	preempt_disable();
>  
> -	gru_check_context_placement(gts);
> +	if (gru_check_context_placement(gts)) {
> +		preempt_enable();
> +		mutex_unlock(&gts->ts_ctxlock);
> +		gru_unload_context(gts, 1);
> +		return VM_FAULT_NOPAGE;
> +	}
>  
>  	if (!gts->ts_gru) {
>  		STAT(load_user_context);
> diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h
> index 8c52776db234..640daf1994df 100644
> --- a/drivers/misc/sgi-gru/grutables.h
> +++ b/drivers/misc/sgi-gru/grutables.h
> @@ -632,7 +632,7 @@ extern int gru_user_flush_tlb(unsigned long arg);
>  extern int gru_user_unload_context(unsigned long arg);
>  extern int gru_get_exception_detail(unsigned long arg);
>  extern int gru_set_context_option(unsigned long address);
> -extern void gru_check_context_placement(struct gru_thread_state *gts);
> +extern int gru_check_context_placement(struct gru_thread_state *gts);
>  extern int gru_cpu_fault_map_id(void);
>  extern struct vm_area_struct *gru_find_vma(unsigned long vaddr);
>  extern void gru_flush_all_tlb(struct gru_state *gru);
> -- 
> 2.25.1