Re: [RFC PATCH 5/8] mm: Take placement mappings gap into account

["Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>]

On Thu, Feb 15, 2024 at 03:13:29PM -0800, Rick Edgecombe wrote:
> When memory is being placed, mmap() will take care to respect the guard
> gaps of certain types of memory (VM_SHADOWSTACK, VM_GROWSUP and
> VM_GROWSDOWN). In order to ensure guard gaps between mappings, mmap()
> needs to consider two things:
>  1. That the new mapping isn’t placed in an any existing mappings guard
>     gaps.
>  2. That the new mapping isn’t placed such that any existing mappings
>     are not in *its* guard gaps.
> 
> The long standing behavior of mmap() is to ensure 1, but not take any care
> around 2. So for example, if there is a PAGE_SIZE free area, and a
> mmap() with a PAGE_SIZE size, and a type that has a guard gap is being
> placed, mmap() may place the shadow stack in the PAGE_SIZE free area. Then
> the mapping that is supposed to have a guard gap will not have a gap to
> the adjacent VMA.
> 
> For MAP_GROWSDOWN/VM_GROWSDOWN and MAP_GROWSUP/VM_GROWSUP this has not
> been a problem in practice because applications place these kinds of
> mappings very early, when there is not many mappings to find a space
> between. But for shadow stacks, they may be placed throughout the lifetime
> of the application.
> 
> So define a VM_UNMAPPED_START_GAP_SET flag to specify that a start_gap
> field has been set, as most vm_unmapped_area_info structs are not zeroed,
> so the added field will often contain garbage. Use
> VM_UNMAPPED_START_GAP_SET in unmapped_area/_topdown() to find a space that
> includes the guard gap for the new mapping. Take care to not interfere
> with the alignment.
> 
> Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
> ---
>  include/linux/mm.h |  2 ++
>  mm/mmap.c          | 21 ++++++++++++++-------
>  2 files changed, 16 insertions(+), 7 deletions(-)
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 9addf16dbf18..160bb6db7a16 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3393,12 +3393,14 @@ extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
>  
>  struct vm_unmapped_area_info {
>  #define VM_UNMAPPED_AREA_TOPDOWN 1
> +#define VM_UNMAPPED_START_GAP_SET 2

The flag seems to be an workaround not to clear the structure. I think
users need to be updated to clear the structure. In most cases rework code
to use C99 struct initializer would do the trick.

>  	unsigned long flags;
>  	unsigned long length;
>  	unsigned long low_limit;
>  	unsigned long high_limit;
>  	unsigned long align_mask;
>  	unsigned long align_offset;
> +	unsigned long start_gap;
>  };
>  
>  extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info);
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 936d728ba1ca..1b6c333656f9 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -1567,14 +1567,17 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags)
>   */
>  static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
>  {
> -	unsigned long length, gap;
> +	unsigned long length, gap, start_gap = 0;
>  	unsigned long low_limit, high_limit;
>  	struct vm_area_struct *tmp;
>  
>  	MA_STATE(mas, &current->mm->mm_mt, 0, 0);
>  
> +	if (info->flags & VM_UNMAPPED_START_GAP_SET)
> +		start_gap = info->start_gap;
> +
>  	/* Adjust search length to account for worst case alignment overhead */
> -	length = info->length + info->align_mask;
> +	length = info->length + info->align_mask + start_gap;
>  	if (length < info->length)
>  		return -ENOMEM;
>  
> @@ -1586,7 +1589,7 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
>  	if (mas_empty_area(&mas, low_limit, high_limit - 1, length))
>  		return -ENOMEM;
>  
> -	gap = mas.index;
> +	gap = mas.index + start_gap;
>  	gap += (info->align_offset - gap) & info->align_mask;

Do we care to check if alignment itself would satisfy start_gap
requirement?

>  	tmp = mas_next(&mas, ULONG_MAX);
>  	if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */
> @@ -1619,13 +1622,17 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
>   */
>  static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
>  {
> -	unsigned long length, gap, gap_end;
> +	unsigned long length, gap, gap_end, start_gap = 0;
>  	unsigned long low_limit, high_limit;
>  	struct vm_area_struct *tmp;
>  
>  	MA_STATE(mas, &current->mm->mm_mt, 0, 0);
> +
> +	if (info->flags & VM_UNMAPPED_START_GAP_SET)
> +		start_gap = info->start_gap;
> +
>  	/* Adjust search length to account for worst case alignment overhead */
> -	length = info->length + info->align_mask;
> +	length = info->length + info->align_mask + start_gap;
>  	if (length < info->length)
>  		return -ENOMEM;
>  
> @@ -1832,7 +1839,7 @@ unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *fi
>  
>  unsigned long
>  __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
> -		unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
> +		    unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)

Unrelated space change.

>  {
>  	unsigned long (*get_area)(struct file *, unsigned long,
>  				  unsigned long, unsigned long, unsigned long)
> @@ -1883,7 +1890,7 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
>  
>  unsigned long
>  get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
> -		unsigned long pgoff, unsigned long flags)
> +		  unsigned long pgoff, unsigned long flags)

Ditto.

>  {
>  	return __get_unmapped_area(file, addr, len, pgoff, flags, 0);
>  }
> -- 
> 2.34.1
> 

-- 
  Kiryl Shutsemau / Kirill A. Shutemov