Re: [RFC PATCH] mm/mempolicy: Fix memory leak in set_mempolicy_home_node system call

[Aneesh Kumar K.V]

Michal Hocko <mhocko@xxxxxxxx> writes:

> On Wed 14-12-22 17:21:10, Mathieu Desnoyers wrote:
>> When encountering any vma in the range with policy other than MPOL_BIND
>> or MPOL_PREFERRED_MANY, an error is returned without issuing a mpol_put
>> on the policy just allocated with mpol_dup().
>> 
>> This allows arbitrary users to leak kernel memory.
>> 
>> Fixes: c6018b4b2549 ("mm/mempolicy: add set_mempolicy_home_node syscall")
>> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
>> Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
>> Cc: Ben Widawsky <ben.widawsky@xxxxxxxxx>
>> Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
>> Cc: Feng Tang <feng.tang@xxxxxxxxx>
>> Cc: Michal Hocko <mhocko@xxxxxxxxxx>
>> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
>> Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
>> Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
>> Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
>> Cc: Vlastimil Babka <vbabka@xxxxxxx>
>> Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
>> Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
>> Cc: Huang Ying <ying.huang@xxxxxxxxx>
>> Cc: <linux-api@xxxxxxxxxxxxxxx>
>> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
>> Cc: stable@xxxxxxxxxxxxxxx # 5.17+
>
> Acked-by: Michal Hocko <mhocko@xxxxxxxx>
> Thanks for catching this!
>
> Btw. looking at the code again it seems rather pointless to duplicate
> the policy just to throw it away anyway. A slightly bigger diff but this
> looks more reasonable to me. What do you think? I can also send it as a
> clean up on top of your fix.
> ---
> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
> index 61aa9aedb728..918cdc8a7f0c 100644
> --- a/mm/mempolicy.c
> +++ b/mm/mempolicy.c
> @@ -1489,7 +1489,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
>  {
>  	struct mm_struct *mm = current->mm;
>  	struct vm_area_struct *vma;
> -	struct mempolicy *new;
> +	struct mempolicy *new. *old;
>  	unsigned long vmstart;
>  	unsigned long vmend;
>  	unsigned long end;
> @@ -1521,30 +1521,28 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
>  		return 0;
>  	mmap_write_lock(mm);
>  	for_each_vma_range(vmi, vma, end) {
> -		vmstart = max(start, vma->vm_start);
> -		vmend   = min(end, vma->vm_end);
> -		new = mpol_dup(vma_policy(vma));
> -		if (IS_ERR(new)) {
> -			err = PTR_ERR(new);
> -			break;
> -		}
> -		/*
> -		 * Only update home node if there is an existing vma policy
> -		 */
> -		if (!new)
> -			continue;
> -
>  		/*
>  		 * If any vma in the range got policy other than MPOL_BIND
>  		 * or MPOL_PREFERRED_MANY we return error. We don't reset
>  		 * the home node for vmas we already updated before.
>  		 */
> -		if (new->mode != MPOL_BIND && new->mode != MPOL_PREFERRED_MANY) {
> +		old = vma_policy(vma);
> +		if (!old)
> +			continue;
> +		if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) {
>  			err = -EOPNOTSUPP;
>  			break;
>  		}
>  
> +		new = mpol_dup(vma_policy(vma));

		new = mpol_dup(old);

> +		if (IS_ERR(new)) {
> +			err = PTR_ERR(new);
> +			break;
> +		}
> +
>  		new->home_node = home_node;
> +		vmstart = max(start, vma->vm_start);
> +		vmend   = min(end, vma->vm_end);
>  		err = mbind_range(mm, vmstart, vmend, new);
>  		mpol_put(new);
>  		if (err)
> -- 
> Michal Hocko
> SUSE Labs