Re: [patch 2/7] x86 PAT: Add follow_pfnmp_pte routine to help tracking pfnmap pages - v3

[Nick Piggin <npiggin@suse.de>]

On Thu, Dec 18, 2008 at 11:41:28AM -0800, venkatesh.pallipadi@intel.com wrote:
> Add a generic interface to follow pfn in a pfnmap vma range. This is used by
> one of the subsequent x86 PAT related patch to keep track of memory types
> for vma regions across vma copy and free.
> 
> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>

Can you please reuse follow_phys for this? (preferably use the same API
even if it requires some modification, otherwise if not possible, then
at least can you implement a common core for both APIs).


> 
> ---
>  include/linux/mm.h |    3 +++
>  mm/memory.c        |   43 +++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 46 insertions(+)
> 
> Index: linux-2.6/include/linux/mm.h
> ===================================================================
> --- linux-2.6.orig/include/linux/mm.h	2008-11-25 13:56:46.000000000 -0800
> +++ linux-2.6/include/linux/mm.h	2008-11-25 14:20:23.000000000 -0800
> @@ -1223,6 +1223,9 @@ struct page *follow_page(struct vm_area_
>  #define FOLL_GET	0x04	/* do get_page on page */
>  #define FOLL_ANON	0x08	/* give ZERO_PAGE if no pgtable */
>  
> +int follow_pfnmap_pte(struct vm_area_struct *vma,
> +				unsigned long address, pte_t *ret_ptep);
> +
>  typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
>  			void *data);
>  extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
> Index: linux-2.6/mm/memory.c
> ===================================================================
> --- linux-2.6.orig/mm/memory.c	2008-11-25 14:07:42.000000000 -0800
> +++ linux-2.6/mm/memory.c	2008-11-25 14:18:35.000000000 -0800
> @@ -1111,6 +1111,49 @@ no_page_table:
>  	return page;
>  }
>  
> +int follow_pfnmap_pte(struct vm_area_struct *vma, unsigned long address,
> +			pte_t *ret_ptep)
> +{
> +	pgd_t *pgd;
> +	pud_t *pud;
> +	pmd_t *pmd;
> +	pte_t *ptep, pte;
> +	spinlock_t *ptl;
> +	struct page *page;
> +	struct mm_struct *mm = vma->vm_mm;
> +
> +	if (!is_pfn_mapping(vma))
> +		goto err;
> +
> +	page = NULL;
> +	pgd = pgd_offset(mm, address);
> +	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
> +		goto err;
> +
> +	pud = pud_offset(pgd, address);
> +	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
> +		goto err;
> +
> +	pmd = pmd_offset(pud, address);
> +	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
> +		goto err;
> +
> +	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
> +
> +	pte = *ptep;
> +	if (!pte_present(pte))
> +		goto err_unlock;
> +
> +	*ret_ptep = pte;
> +	pte_unmap_unlock(ptep, ptl);
> +	return 0;
> +
> +err_unlock:
> +	pte_unmap_unlock(ptep, ptl);
> +err:
> +	return -EINVAL;
> +}
> +
>  /* Can we do the FOLL_ANON optimization? */
>  static inline int use_zero_page(struct vm_area_struct *vma)
>  {
> 
> --