[RFC v1 1/3] mm/mmu_notifier: Add a new notifier for mapping updates (new pages)

[Alistair Popple]

Vivek Kasireddy <vivek.kasireddy at intel.com> writes:

> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index 64a3239b6407..1f2f0209101a 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -6096,8 +6096,12 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
>  		 * hugetlb_no_page will drop vma lock and hugetlb fault
>  		 * mutex internally, which make us return immediately.
>  		 */
> -		return hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
> +		ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
>  				      entry, flags);
> +		if (!ret)
> +			mmu_notifier_update_mapping(vma->vm_mm, address,
> +						    pte_pfn(*ptep));

The next patch ends up calling pfn_to_page() on the result of
pte_pfn(*ptep). I don't think that's safe because couldn't the PTE have
already changed and/or the new page have been freed?

> +		return ret;
>  
>  	ret = 0;
>  
> @@ -6223,6 +6227,9 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
>  	 */
>  	if (need_wait_lock)
>  		folio_wait_locked(folio);
> +	if (!ret)
> +		mmu_notifier_update_mapping(vma->vm_mm, address,
> +					    pte_pfn(*ptep));
>  	return ret;
>  }
>  
> diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
> index 50c0dde1354f..6421405334b9 100644
> --- a/mm/mmu_notifier.c
> +++ b/mm/mmu_notifier.c
> @@ -441,6 +441,23 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
>  	srcu_read_unlock(&srcu, id);
>  }
>  
> +void __mmu_notifier_update_mapping(struct mm_struct *mm, unsigned long address,
> +				   unsigned long pfn)
> +{
> +	struct mmu_notifier *subscription;
> +	int id;
> +
> +	id = srcu_read_lock(&srcu);
> +	hlist_for_each_entry_rcu(subscription,
> +				 &mm->notifier_subscriptions->list, hlist,
> +				 srcu_read_lock_held(&srcu)) {
> +		if (subscription->ops->update_mapping)
> +			subscription->ops->update_mapping(subscription, mm,
> +							  address, pfn);
> +	}
> +	srcu_read_unlock(&srcu, id);
> +}
> +
>  static int mn_itree_invalidate(struct mmu_notifier_subscriptions *subscriptions,
>  			       const struct mmu_notifier_range *range)
>  {
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 2f2e0e618072..e59eb5fafadb 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -77,6 +77,7 @@ static struct vfsmount *shm_mnt;
>  #include <linux/fcntl.h>
>  #include <uapi/linux/memfd.h>
>  #include <linux/rmap.h>
> +#include <linux/mmu_notifier.h>
>  #include <linux/uuid.h>
>  
>  #include <linux/uaccess.h>
> @@ -2164,8 +2165,12 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf)
>  				  gfp, vma, vmf, &ret);
>  	if (err)
>  		return vmf_error(err);
> -	if (folio)
> +	if (folio) {
>  		vmf->page = folio_file_page(folio, vmf->pgoff);
> +		if (ret == VM_FAULT_LOCKED)
> +			mmu_notifier_update_mapping(vma->vm_mm, vmf->address,
> +						    page_to_pfn(vmf->page));
> +	}
>  	return ret;
>  }