Re: [PATCH 4.9] s390/mm: do not trigger write fault when vma does not allow VM_WRITE

[Greg KH <gregkh@linuxfoundation.org>]

On Mon, Aug 29, 2022 at 05:52:38PM +0200, Gerald Schaefer wrote:
> commit 41ac42f137080bc230b5882e3c88c392ab7f2d32 upstream.
> 
> For non-protection pXd_none() page faults in do_dat_exception(), we
> call do_exception() with access == (VM_READ | VM_WRITE | VM_EXEC).
> In do_exception(), vma->vm_flags is checked against that before
> calling handle_mm_fault().
> 
> Since commit 92f842eac7ee3 ("[S390] store indication fault optimization"),
> we call handle_mm_fault() with FAULT_FLAG_WRITE, when recognizing that
> it was a write access. However, the vma flags check is still only
> checking against (VM_READ | VM_WRITE | VM_EXEC), and therefore also
> calling handle_mm_fault() with FAULT_FLAG_WRITE in cases where the vma
> does not allow VM_WRITE.
> 
> Fix this by changing access check in do_exception() to VM_WRITE only,
> when recognizing write access.
> 
> Link: https://lkml.kernel.org/r/20220811103435.188481-3-david@redhat.com
> Fixes: 92f842eac7ee3 ("[S390] store indication fault optimization")
> Cc: <stable@vger.kernel.org>
> Reported-by: David Hildenbrand <david@redhat.com>
> Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
> Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
> ---
>  arch/s390/mm/fault.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
> index ba2f21873cbd..6fa4220e34b5 100644
> --- a/arch/s390/mm/fault.c
> +++ b/arch/s390/mm/fault.c
> @@ -409,7 +409,9 @@ static inline int do_exception(struct pt_regs *regs, int access)
>  	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
>  	if (user_mode(regs))
>  		flags |= FAULT_FLAG_USER;
> -	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
> +	if ((trans_exc_code & store_indication) == 0x400)
> +		access = VM_WRITE;
> +	if (access == VM_WRITE)
>  		flags |= FAULT_FLAG_WRITE;
>  	down_read(&mm->mmap_sem);
>  
> -- 
> 2.34.1
> 

all now queued up, thanks.

greg k-h