Re: [PATCH 1/2] mm: vmalloc: streamline vmalloc memory accounting

[Uladzislau Rezki]

On Fri, Feb 20, 2026 at 02:10:34PM -0500, Johannes Weiner wrote:
> Use a vmstat counter instead of a custom, open-coded atomic. This has
> the added benefit of making the data available per-node, and prepares
> for cleaning up the memcg accounting as well.
> 
> Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> ---
>  fs/proc/meminfo.c       |  3 ++-
>  include/linux/mmzone.h  |  1 +
>  include/linux/vmalloc.h |  3 ---
>  mm/vmalloc.c            | 19 ++++++++++---------
>  mm/vmstat.c             |  1 +
>  5 files changed, 14 insertions(+), 13 deletions(-)
> 
> diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
> index a458f1e112fd..549793f44726 100644
> --- a/fs/proc/meminfo.c
> +++ b/fs/proc/meminfo.c
> @@ -126,7 +126,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
>  	show_val_kb(m, "Committed_AS:   ", committed);
>  	seq_printf(m, "VmallocTotal:   %8lu kB\n",
>  		   (unsigned long)VMALLOC_TOTAL >> 10);
> -	show_val_kb(m, "VmallocUsed:    ", vmalloc_nr_pages());
> +	show_val_kb(m, "VmallocUsed:    ",
> +		    global_node_page_state(NR_VMALLOC));
>  	show_val_kb(m, "VmallocChunk:   ", 0ul);
>  	show_val_kb(m, "Percpu:         ", pcpu_nr_pages());
>  
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index fc5d6c88d2f0..64df797d45c6 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -220,6 +220,7 @@ enum node_stat_item {
>  	NR_KERNEL_MISC_RECLAIMABLE,	/* reclaimable non-slab kernel pages */
>  	NR_FOLL_PIN_ACQUIRED,	/* via: pin_user_page(), gup flag: FOLL_PIN */
>  	NR_FOLL_PIN_RELEASED,	/* pages returned via unpin_user_page() */
> +	NR_VMALLOC,
>  	NR_KERNEL_STACK_KB,	/* measured in KiB */
>  #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
>  	NR_KERNEL_SCS_KB,	/* measured in KiB */
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index e8e94f90d686..3b02c0c6b371 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -286,8 +286,6 @@ int unregister_vmap_purge_notifier(struct notifier_block *nb);
>  #ifdef CONFIG_MMU
>  #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
>  
> -unsigned long vmalloc_nr_pages(void);
> -
>  int vm_area_map_pages(struct vm_struct *area, unsigned long start,
>  		      unsigned long end, struct page **pages);
>  void vm_area_unmap_pages(struct vm_struct *area, unsigned long start,
> @@ -304,7 +302,6 @@ static inline void set_vm_flush_reset_perms(void *addr)
>  #else  /* !CONFIG_MMU */
>  #define VMALLOC_TOTAL 0UL
>  
> -static inline unsigned long vmalloc_nr_pages(void) { return 0; }
>  static inline void set_vm_flush_reset_perms(void *addr) {}
>  #endif /* CONFIG_MMU */
>  
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index e286c2d2068c..a49a46de9c4f 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -1063,14 +1063,8 @@ static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
>  static void drain_vmap_area_work(struct work_struct *work);
>  static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work);
>  
> -static __cacheline_aligned_in_smp atomic_long_t nr_vmalloc_pages;
>  static __cacheline_aligned_in_smp atomic_long_t vmap_lazy_nr;
>  
> -unsigned long vmalloc_nr_pages(void)
> -{
> -	return atomic_long_read(&nr_vmalloc_pages);
> -}
> -
>  static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
>  {
>  	struct rb_node *n = root->rb_node;
> @@ -3463,11 +3457,11 @@ void vfree(const void *addr)
>  		 * High-order allocs for huge vmallocs are split, so
>  		 * can be freed as an array of order-0 allocations
>  		 */
> +		if (!(vm->flags & VM_MAP_PUT_PAGES))
> +			dec_node_page_state(page, NR_VMALLOC);
>  		__free_page(page);
>  		cond_resched();
>  	}
> -	if (!(vm->flags & VM_MAP_PUT_PAGES))
> -		atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
>  	kvfree(vm->pages);
>  	kfree(vm);
>  }
> @@ -3655,6 +3649,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>  			continue;
>  		}
>  
> +		mod_node_page_state(page, NR_VMALLOC, 1 << large_order);
> +
>  		split_page(page, large_order);
>  		for (i = 0; i < (1U << large_order); i++)
>  			pages[nr_allocated + i] = page + i;
> @@ -3675,6 +3671,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>  	if (!order) {
>  		while (nr_allocated < nr_pages) {
>  			unsigned int nr, nr_pages_request;
> +			int i;
>  
>  			/*
>  			 * A maximum allowed request is hard-coded and is 100
> @@ -3698,6 +3695,9 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>  							nr_pages_request,
>  							pages + nr_allocated);
>  
> +			for (i = nr_allocated; i < nr_allocated + nr; i++)
> +				inc_node_page_state(pages[i], NR_VMALLOC);
> +
>  			nr_allocated += nr;
>  
>  			/*
> @@ -3722,6 +3722,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>  		if (unlikely(!page))
>  			break;
>  
> +		mod_node_page_state(page, NR_VMALLOC, 1 << order);
> +
>  		/*
Can we move *_node_page_stat() to the end of the vm_area_alloc_pages()?

Or mod_node_page_state in first place should be invoked on high-order
page before split(to avoid of looping over small pages afterword)?

I mean it would be good to place to the one solid place. If it is possible
of course.

--
Uladzislau Rezk