[PATCH v2 1/2] mm: vmalloc: streamline vmalloc memory accounting

[Johannes Weiner]

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.

Acked-by: Shakeel Butt <shakeel.butt@xxxxxxxxx>
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(-)

V2:
- Fix mod_node_page_state() pgdat argument (Shakeel)

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..a5fc7795aafd 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_pgdat(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_pgdat(page), NR_VMALLOC, 1 << order);
+
 		/*
 		 * High-order allocations must be able to be treated as
 		 * independent small pages by callers (as they can with
@@ -3864,7 +3866,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 			vmalloc_gfp_adjust(gfp_mask, page_order), node,
 			page_order, nr_small_pages, area->pages);
 
-	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 	/* All pages of vm should be charged to same memcg, so use first one. */
 	if (gfp_mask & __GFP_ACCOUNT && area->nr_pages)
 		mod_memcg_page_state(area->pages[0], MEMCG_VMALLOC,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index d6e814c82952..bc199c7cd07b 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1270,6 +1270,7 @@ const char * const vmstat_text[] = {
 	[I(NR_KERNEL_MISC_RECLAIMABLE)]		= "nr_kernel_misc_reclaimable",
 	[I(NR_FOLL_PIN_ACQUIRED)]		= "nr_foll_pin_acquired",
 	[I(NR_FOLL_PIN_RELEASED)]		= "nr_foll_pin_released",
+	[I(NR_VMALLOC)]				= "nr_vmalloc",
 	[I(NR_KERNEL_STACK_KB)]			= "nr_kernel_stack",
 #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
 	[I(NR_KERNEL_SCS_KB)]			= "nr_shadow_call_stack",
-- 
2.53.0