Re: [patch 3/7] x86 PAT: hooks in generic vm code to help archs to track pfnmap regions - v3

[Nick Piggin <npiggin@suse.de>]

On Thu, Dec 18, 2008 at 11:41:29AM -0800, venkatesh.pallipadi@intel.com wrote:
> Introduce generic hooks in remap_pfn_range and vm_insert_pfn and
> corresponding copy and free routines with reserve and free tracking.

These should be inline so that they can be folded out (I'm sure gcc
with -Os and "optimize" inlining will do something stupid here).
Also, the normal way to add such arch hooks is to put the default
into asm-generic and have other archs include it... that would be
nicer than sticking it into mm/memory.c wouldn't it?

Sigh, fork/exit paths slow down yet again. But oh well. Maybe can
you add some branch hints?

 
> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
> 
> ---
>  include/linux/mm.h |    6 ++++
>  mm/memory.c        |   76 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 81 insertions(+), 1 deletion(-)
> 
> Index: linux-2.6/mm/memory.c
> ===================================================================
> --- linux-2.6.orig/mm/memory.c	2008-12-18 10:10:50.000000000 -0800
> +++ linux-2.6/mm/memory.c	2008-12-18 10:11:23.000000000 -0800
> @@ -99,6 +99,50 @@ int randomize_va_space __read_mostly =
>  					2;
>  #endif
>  
> +#ifndef track_pfn_vma_new
> +/*
> + * Interface that can be used by architecture code to keep track of
> + * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
> + *
> + * track_pfn_vma_new is called when a _new_ pfn mapping is being established
> + * for physical range indicated by pfn and size.
> + */
> +int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
> +			unsigned long pfn, unsigned long size)
> +{
> +	return 0;
> +}
> +#endif
> +
> +#ifndef track_pfn_vma_copy
> +/*
> + * Interface that can be used by architecture code to keep track of
> + * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
> + *
> + * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
> + * copied through copy_page_range().
> + */
> +int track_pfn_vma_copy(struct vm_area_struct *vma)
> +{
> +	return 0;
> +}
> +#endif
> +
> +#ifndef untrack_pfn_vma
> +/*
> + * Interface that can be used by architecture code to keep track of
> + * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
> + *
> + * untrack_pfn_vma is called while unmapping a pfnmap for a region.
> + * untrack can be called for a specific region indicated by pfn and size or
> + * can be for the entire vma (in which case size can be zero).
> + */
> +void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
> +			unsigned long size)
> +{
> +}
> +#endif
> +
>  static int __init disable_randmaps(char *s)
>  {
>  	randomize_va_space = 0;
> @@ -669,6 +713,16 @@ int copy_page_range(struct mm_struct *ds
>  	if (is_vm_hugetlb_page(vma))
>  		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
>  
> +	if (is_pfn_mapping(vma)) {
> +		/*
> +		 * We do not free on error cases below as remove_vma
> +		 * gets called on error from higher level routine
> +		 */
> +		ret = track_pfn_vma_copy(vma);
> +		if (ret)
> +			return ret;
> +	}
> +
>  	/*
>  	 * We need to invalidate the secondary MMU mappings only when
>  	 * there could be a permission downgrade on the ptes of the
> @@ -915,6 +969,9 @@ unsigned long unmap_vmas(struct mmu_gath
>  		if (vma->vm_flags & VM_ACCOUNT)
>  			*nr_accounted += (end - start) >> PAGE_SHIFT;
>  
> +		if (is_pfn_mapping(vma))
> +			untrack_pfn_vma(vma, 0, 0);
> +
>  		while (start != end) {
>  			if (!tlb_start_valid) {
>  				tlb_start = start;
> @@ -1473,6 +1530,7 @@ out:
>  int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
>  			unsigned long pfn)
>  {
> +	int ret;
>  	/*
>  	 * Technically, architectures with pte_special can avoid all these
>  	 * restrictions (same for remap_pfn_range).  However we would like
> @@ -1487,7 +1545,15 @@ int vm_insert_pfn(struct vm_area_struct 
>  
>  	if (addr < vma->vm_start || addr >= vma->vm_end)
>  		return -EFAULT;
> -	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
> +	if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
> +		return -EINVAL;
> +
> +  	ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
> +
> +	if (ret)
> +		untrack_pfn_vma(vma, pfn, PAGE_SIZE);
> +
> +	return ret;
>  }
>  EXPORT_SYMBOL(vm_insert_pfn);
>  
> @@ -1625,6 +1691,10 @@ int remap_pfn_range(struct vm_area_struc
>  
>  	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
>  
> +	err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
> +	if (err)
> +		return -EINVAL;
> +
>  	BUG_ON(addr >= end);
>  	pfn -= addr >> PAGE_SHIFT;
>  	pgd = pgd_offset(mm, addr);
> @@ -1636,6 +1706,10 @@ int remap_pfn_range(struct vm_area_struc
>  		if (err)
>  			break;
>  	} while (pgd++, addr = next, addr != end);
> +
> +	if (err)
> +		untrack_pfn_vma(vma, pfn, PAGE_ALIGN(size));
> +
>  	return err;
>  }
>  EXPORT_SYMBOL(remap_pfn_range);
> Index: linux-2.6/include/linux/mm.h
> ===================================================================
> --- linux-2.6.orig/include/linux/mm.h	2008-12-18 10:10:50.000000000 -0800
> +++ linux-2.6/include/linux/mm.h	2008-12-18 10:11:23.000000000 -0800
> @@ -155,6 +155,12 @@ static inline int is_pfn_mapping(struct 
>  	return (vma->vm_flags & VM_PFNMAP);
>  }
>  
> +extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
> +				unsigned long pfn, unsigned long size);
> +extern int track_pfn_vma_copy(struct vm_area_struct *vma);
> +extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
> +				unsigned long size);
> +
>  /*
>   * vm_fault is filled by the the pagefault handler and passed to the vma's
>   * ->fault function. The vma's ->fault is responsible for returning a bitmask
> 
> --