Re: [PATCH v2 3/7] mm: introduce vma_count_remaining()

[Lorenzo Stoakes <lorenzo.stoakes@oracle.com>]

On Mon, Sep 15, 2025 at 09:36:34AM -0700, Kalesh Singh wrote:
> The checks against sysctl_max_map_count are open-coded in multiple
> places. While simple checks are manageable, the logic in places like
> mremap.c involves arithmetic with magic numbers that can be difficult
> to reason about. e.g. ... >= sysctl_max_map_count - 3
>
> To improve readability and centralize the logic, introduce a new helper,
> vma_count_remaining(). This function returns the VMA count headroom
> available for a givine process.
>
> The most common case of checking for a single new VMA can be done with
> the convenience helper has_vma_count_remaining():
>
>     if (!vma_count_remaining(mm))
>
> And the complex checks in mremap.c become clearer by expressing the
> required capacity directly:
>
>     if (vma_count_remaining(mm) <  4)

Double space after 4.

>
> While a capacity-based function could be misused (e.g., with an
> incorrect '<' vs '<=' comparison), the improved readability at the call
> sites makes such errors less likely than with the previous open-coded
> arithmetic.
>
> As part of this change, sysctl_max_map_count is made static to
> mm/mmap.c to improve encapsulation.
>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> Cc: Mike Rapoport <rppt@kernel.org>
> Cc: Minchan Kim <minchan@kernel.org>
> Cc: Pedro Falcato <pfalcato@suse.de>
> Signed-off-by: Kalesh Singh <kaleshsingh@google.com>

Generally logic looks ok, with various stuff fixed below + in commit msg we
should be good to go :)

> ---
>
> Changes in v2:
>   - Fix documentation comment for vma_count_remaining(), per Mike
>   - Remove extern in header, per Mike and Pedro
>   - Move declaration to mm/internal.h, per Mike
>   - Replace exceeds_max_map_count() with capacity-based vma_count_remaining(),
>        per Lorenzo.
>   - Fix tools/testing/vma, per Lorenzo.
>
>  include/linux/mm.h               |  2 --
>  mm/internal.h                    |  2 ++
>  mm/mmap.c                        | 21 ++++++++++++++++++++-
>  mm/mremap.c                      |  7 ++++---
>  mm/nommu.c                       |  2 +-
>  mm/util.c                        |  1 -
>  mm/vma.c                         | 10 +++++-----
>  tools/testing/vma/vma_internal.h |  9 +++++++++
>  8 files changed, 41 insertions(+), 13 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 1ae97a0b8ec7..138bab2988f8 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -192,8 +192,6 @@ static inline void __mm_zero_struct_page(struct page *page)
>  #define MAPCOUNT_ELF_CORE_MARGIN	(5)
>  #define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
>
> -extern int sysctl_max_map_count;
> -

Nice to get rid of this as a global! :)

>  extern unsigned long sysctl_user_reserve_kbytes;
>  extern unsigned long sysctl_admin_reserve_kbytes;
>
> diff --git a/mm/internal.h b/mm/internal.h
> index 45b725c3dc03..39f1c9535ae5 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -1661,4 +1661,6 @@ static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
>  void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm);
>  int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm);
>
> +int vma_count_remaining(const struct mm_struct *mm);
> +
>  #endif	/* __MM_INTERNAL_H */
> diff --git a/mm/mmap.c b/mm/mmap.c
> index e5370e7fcd8f..af88ce1fbb5f 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -374,7 +374,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
>  		return -EOVERFLOW;
>
>  	/* Too many mappings? */
> -	if (mm->map_count >= sysctl_max_map_count)
> +	if (!vma_count_remaining(mm))
>  		return -ENOMEM;
>
>  	/*
> @@ -1504,6 +1504,25 @@ struct vm_area_struct *_install_special_mapping(
>  int sysctl_legacy_va_layout;
>  #endif
>
> +static int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
> +
> +/**
> + * vma_count_remaining - Determine available VMA slots
> + * @mm: The memory descriptor for the process.
> + *
> + * Check how many more VMAs can be created for the given @mm
> + * before hitting the sysctl_max_map_count limit.
> + *
> + * Return: The number of new VMAs the process can accommodate.
> + */
> +int vma_count_remaining(const struct mm_struct *mm)
> +{
> +	const int map_count = mm->map_count;
> +	const int max_count = sysctl_max_map_count;

David already commented on the READ_ONCE() here, seems wise.

> +
> +	return (max_count > map_count) ? (max_count - map_count) : 0;

Not a big deal but would prefer:

	if (map_count >= map_count)
		return 0;

	return max_count - map_count;

As the ternary here is a bit less clear, and it puts the 'failure' case first
and the 'success' case afterwards.

> +}
> +

As discussed in reply to the kernel bot, you've accidentally placed this in a
CONFIG_SYSCTL block, so need to move it :>)

>  static const struct ctl_table mmap_table[] = {
>  		{
>  				.procname       = "max_map_count",
> diff --git a/mm/mremap.c b/mm/mremap.c
> index 35de0a7b910e..14d35d87e89b 100644
> --- a/mm/mremap.c
> +++ b/mm/mremap.c
> @@ -1040,7 +1040,7 @@ static unsigned long prep_move_vma(struct vma_remap_struct *vrm)
>  	 * We'd prefer to avoid failure later on in do_munmap:
>  	 * which may split one vma into three before unmapping.
>  	 */
> -	if (current->mm->map_count >= sysctl_max_map_count - 3)
> +	if (vma_count_remaining(current->mm) < 4)
>  		return -ENOMEM;

This is much clearer.

>
>  	if (vma->vm_ops && vma->vm_ops->may_split) {
> @@ -1814,9 +1814,10 @@ static unsigned long check_mremap_params(struct vma_remap_struct *vrm)
>  	 * split in 3 before unmapping it.
>  	 * That means 2 more maps (1 for each) to the ones we already hold.
>  	 * Check whether current map count plus 2 still leads us to 4 maps below
> -	 * the threshold, otherwise return -ENOMEM here to be more safe.
> +	 * the threshold. In other words, is the current map count + 6 at or
> +	 * below the threshold? Otherwise return -ENOMEM here to be more safe.
>  	 */
> -	if ((current->mm->map_count + 2) >= sysctl_max_map_count - 3)
> +	if (vma_count_remaining(current->mm) < 6)
>  		return -ENOMEM;

I hate that we do this silly check here, but the time to revisit it is another
series...

>
>  	return 0;
> diff --git a/mm/nommu.c b/mm/nommu.c
> index 8b819fafd57b..dd75f2334812 100644
> --- a/mm/nommu.c
> +++ b/mm/nommu.c
> @@ -1316,7 +1316,7 @@ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
>  		return -ENOMEM;
>
>  	mm = vma->vm_mm;
> -	if (mm->map_count >= sysctl_max_map_count)
> +	if (!vma_count_remaining(mm))
>  		return -ENOMEM;
>
>  	region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL);
> diff --git a/mm/util.c b/mm/util.c
> index f814e6a59ab1..b6e83922cafe 100644
> --- a/mm/util.c
> +++ b/mm/util.c
> @@ -751,7 +751,6 @@ EXPORT_SYMBOL(folio_mc_copy);
>  int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
>  static int sysctl_overcommit_ratio __read_mostly = 50;
>  static unsigned long sysctl_overcommit_kbytes __read_mostly;
> -int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
>  unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
>  unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
>
> diff --git a/mm/vma.c b/mm/vma.c
> index 033a388bc4b1..df0e8409f63d 100644
> --- a/mm/vma.c
> +++ b/mm/vma.c
> @@ -491,8 +491,8 @@ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma,
>  }
>
>  /*
> - * __split_vma() bypasses sysctl_max_map_count checking.  We use this where it
> - * has already been checked or doesn't make sense to fail.
> + * __split_vma() bypasses vma_count_remaining() checks. We use this where
> + * it has already been checked or doesn't make sense to fail.
>   * VMA Iterator will point to the original VMA.
>   */
>  static __must_check int
> @@ -592,7 +592,7 @@ __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
>  static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
>  		     unsigned long addr, int new_below)
>  {
> -	if (vma->vm_mm->map_count >= sysctl_max_map_count)
> +	if (!vma_count_remaining(vma->vm_mm))
>  		return -ENOMEM;
>
>  	return __split_vma(vmi, vma, addr, new_below);
> @@ -1345,7 +1345,7 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms,
>  		 * its limit temporarily, to help free resources as expected.
>  		 */
>  		if (vms->end < vms->vma->vm_end &&
> -		    vms->vma->vm_mm->map_count >= sysctl_max_map_count) {
> +		    !vma_count_remaining(vms->vma->vm_mm)) {
>  			error = -ENOMEM;
>  			goto map_count_exceeded;
>  		}
> @@ -2772,7 +2772,7 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
>  	if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT))
>  		return -ENOMEM;
>
> -	if (mm->map_count >= sysctl_max_map_count)
> +	if (!vma_count_remaining(mm))
>  		return -ENOMEM;
>
>  	if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT))
> diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
> index 3639aa8dd2b0..52cd7ddc73f4 100644
> --- a/tools/testing/vma/vma_internal.h
> +++ b/tools/testing/vma/vma_internal.h
> @@ -1517,4 +1517,13 @@ static inline vm_flags_t ksm_vma_flags(const struct mm_struct *, const struct fi
>  	return vm_flags;
>  }
>
> +/* Helper to get VMA count capacity */
> +static int vma_count_remaining(const struct mm_struct *mm)
> +{
> +	const int map_count = mm->map_count;
> +	const int max_count = sysctl_max_map_count;
> +
> +	return (max_count > map_count) ? (max_count - map_count) : 0;
> +}
> +
>  #endif	/* __MM_VMA_INTERNAL_H */
> --
> 2.51.0.384.g4c02a37b29-goog
>