[PATCH v5 7/9] mm/mremap: Move TLB flush outside page table lock

[Aneesh Kumar K.V]

On 4/22/21 11:13 AM, Aneesh Kumar K.V wrote:
> Move TLB flush outside page table lock so that kernel does
> less with page table lock held. Releasing the ptl with old
> TLB contents still valid will behave such that such access
> happened before the level3 or level2 entry update.
> 


Ok this break the page lifetime rule

commit: eb66ae030829 ("mremap: properly flush TLB before releasing the 
page")

I will respin dropping this change and add a comment around explaining 
why we need to do tlb flush before dropping ptl.

> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.ibm.com>
> ---
>   mm/mremap.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/mm/mremap.c b/mm/mremap.c
> index 109560977944..9effca76bf17 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -258,7 +258,7 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
>   	 * We don't have to worry about the ordering of src and dst
>   	 * ptlocks because exclusive mmap_lock prevents deadlock.
>   	 */
> -	old_ptl = pmd_lock(vma->vm_mm, old_pmd);
> +	old_ptl = pmd_lock(mm, old_pmd);
>   	new_ptl = pmd_lockptr(mm, new_pmd);
>   	if (new_ptl != old_ptl)
>   		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
> @@ -270,11 +270,11 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
>   	VM_BUG_ON(!pmd_none(*new_pmd));
>   	pmd_populate(mm, new_pmd, (pgtable_t)pmd_page_vaddr(pmd));
>   
> -	flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PMD_SIZE);
>   	if (new_ptl != old_ptl)
>   		spin_unlock(new_ptl);
>   	spin_unlock(old_ptl);
>   
> +	flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PMD_SIZE);
>   	return true;
>   }
>   #else
> @@ -305,7 +305,7 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
>   	 * We don't have to worry about the ordering of src and dst
>   	 * ptlocks because exclusive mmap_lock prevents deadlock.
>   	 */
> -	old_ptl = pud_lock(vma->vm_mm, old_pud);
> +	old_ptl = pud_lock(mm, old_pud);
>   	new_ptl = pud_lockptr(mm, new_pud);
>   	if (new_ptl != old_ptl)
>   		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
> @@ -317,11 +317,11 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
>   	VM_BUG_ON(!pud_none(*new_pud));
>   
>   	pud_populate(mm, new_pud, (pmd_t *)pud_page_vaddr(pud));
> -	flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PUD_SIZE);
>   	if (new_ptl != old_ptl)
>   		spin_unlock(new_ptl);
>   	spin_unlock(old_ptl);
>   
> +	flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PUD_SIZE);
>   	return true;
>   }
>   #else
>