[PATCH 2/4] mm: speed up mremap by 500x on large regions (v2)

Kirill A. Shutemov kirill at shutemov.name
Wed Oct 24 03:12:56 PDT 2018


On Fri, Oct 12, 2018 at 06:31:58PM -0700, Joel Fernandes (Google) wrote:
> diff --git a/mm/mremap.c b/mm/mremap.c
> index 9e68a02a52b1..2fd163cff406 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -191,6 +191,54 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
>  		drop_rmap_locks(vma);
>  }
>  
> +static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
> +		  unsigned long new_addr, unsigned long old_end,
> +		  pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
> +{
> +	spinlock_t *old_ptl, *new_ptl;
> +	struct mm_struct *mm = vma->vm_mm;
> +
> +	if ((old_addr & ~PMD_MASK) || (new_addr & ~PMD_MASK)
> +	    || old_end - old_addr < PMD_SIZE)
> +		return false;
> +
> +	/*
> +	 * The destination pmd shouldn't be established, free_pgtables()
> +	 * should have release it.
> +	 */
> +	if (WARN_ON(!pmd_none(*new_pmd)))
> +		return false;
> +
> +	/*
> +	 * We don't have to worry about the ordering of src and dst
> +	 * ptlocks because exclusive mmap_sem prevents deadlock.
> +	 */
> +	old_ptl = pmd_lock(vma->vm_mm, old_pmd);
> +	if (old_ptl) {

How can it ever be false?

> +		pmd_t pmd;
> +
> +		new_ptl = pmd_lockptr(mm, new_pmd);
> +		if (new_ptl != old_ptl)
> +			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
> +
> +		/* Clear the pmd */
> +		pmd = *old_pmd;
> +		pmd_clear(old_pmd);
> +
> +		VM_BUG_ON(!pmd_none(*new_pmd));
> +
> +		/* Set the new pmd */
> +		set_pmd_at(mm, new_addr, new_pmd, pmd);
> +		if (new_ptl != old_ptl)
> +			spin_unlock(new_ptl);
> +		spin_unlock(old_ptl);
> +
> +		*need_flush = true;
> +		return true;
> +	}
> +	return false;
> +}
> +
-- 
 Kirill A. Shutemov



More information about the linux-riscv mailing list