Re: [PATCH v3] misc: sgi-gru: fix use-after-free error in gru_set_context_option, gru_fault and gru_handle_user_call_os

From: Zheng Yejian
Date: Tue Oct 18 2022 - 21:56:38 EST


On Wed, 19 Oct 2022 00:52:59 +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>
> ---
> v3:
> - add preempt_enable and use VM_FAULT_NOPAGE as failure code by Yejian

Sorry, maybe I didn't make it clearly enough in
https://lore.kernel.org/lkml/20221009201418.509417-1-zhengyejian1@xxxxxxxxxx/

What I suggested was that return value of gru_fault() should be some VM_FAULT_XXX,
because this return value would be specially handled in pagefault flow like:
__do_fault() {
......
ret = vma->vm_ops->fault(vmf);
......
}

But in other functions that are not in pagefault flow, common error code
like -EINVAL is ok. Meanings of every error code can be found in:
https://man7.org/linux/man-pages/man3/errno.3.html

By the way, these are all personal suggestions. You need Reviewed-by Maintainer :)

-- Zheng Yejian

>
> v2:
> - commit message changes suggested by Greg
>
> v1: https://lore.kernel.org/lkml/CAJedcCzY72jqgF-pCPtx66vXXwdPn-KMagZnqrxcpWw1NxTLaA@xxxxxxxxxxxxxx/
> ---
> drivers/misc/sgi-gru/grufault.c | 14 ++++++++++++--
> drivers/misc/sgi-gru/grumain.c | 18 ++++++++++++++----
> drivers/misc/sgi-gru/grutables.h | 2 +-
> 3 files changed, 27 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
> index d7ef61e602ed..864be8a2cb61 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 VM_FAULT_NOPAGE;
> }
>
> /*
> @@ -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 +895,10 @@ int gru_set_context_option(unsigned long arg)
> ret = -EINVAL;
> }
> gru_unlock_gts(gts);
> + if (ret) {
> + gru_unload_context(gts, 1);
> + ret = VM_FAULT_NOPAGE;
> + }
>
> return ret;
> }
> diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
> index 9afda47efbf2..952803790818 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 = VM_FAULT_NOPAGE;
> } 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 +938,13 @@ 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) {
> + preempt_enable();
> + mutex_unlock(&gts->ts_ctxlock);
> + gru_unload_context(gts, 1);
> + return ret;
> + }
>
> 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 5efc869fe59a..f4a5a787685f 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