diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b645686ef9b6..45e0dc0e09f8 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -365,6 +365,13 @@ static LIST_HEAD(free_vmap_area_list);
  */
 static struct rb_root free_vmap_area_root = RB_ROOT;
 
+/*
+ * Preload a CPU with one object for "no edge" split case. The
+ * aim is to get rid of allocations from the atomic context, thus
+ * to use more permissive allocation masks.
+ */
+static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node);
+
 static __always_inline unsigned long
 va_size(struct vmap_area *va)
 {
@@ -951,9 +958,24 @@ adjust_va_to_fit_type(struct vmap_area *va,
 		 *   L V  NVA  V R
 		 * |---|-------|---|
 		 */
-		lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
-		if (unlikely(!lva))
-			return -1;
+		lva = __this_cpu_xchg(ne_fit_preload_node, NULL);
+		if (unlikely(!lva)) {
+			/*
+			 * For percpu allocator we do not do any pre-allocation
+			 * and leave it as it is. The reason is it most likely
+			 * never ends up with NE_FIT_TYPE splitting. In case of
+			 * percpu allocations offsets and sizes are aligned to
+			 * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE
+			 * are its main fitting cases.
+			 *
+			 * There are a few exceptions though, as an example it is
+			 * a first allocation (early boot up) when we have "one"
+			 * big free space that has to be split.
+			 */
+			lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
+			if (!lva)
+				return -1;
+		}
 
 		/*
 		 * Build the remainder.
@@ -1032,7 +1054,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 				unsigned long vstart, unsigned long vend,
 				int node, gfp_t gfp_mask)
 {
-	struct vmap_area *va;
+	struct vmap_area *va, *pva;
 	unsigned long addr;
 	int purged = 0;
 
@@ -1057,7 +1079,32 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK);
 
 retry:
+	/*
+	 * Preload this CPU with one extra vmap_area object to ensure
+	 * that we have it available when fit type of free area is
+	 * NE_FIT_TYPE.
+	 *
+	 * The preload is done in non-atomic context, thus it allows us
+	 * to use more permissive allocation masks to be more stable under
+	 * low memory condition and high memory pressure.
+	 *
+	 * Even if it fails we do not really care about that. Just proceed
+	 * as it is. "overflow" path will refill the cache we allocate from.
+	 */
+	preempt_disable();
+	if (!__this_cpu_read(ne_fit_preload_node)) {
+		preempt_enable();
+		pva = kmem_cache_alloc_node(vmap_area_cachep, GFP_KERNEL, node);
+		preempt_disable();
+
+		if (__this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) {
+			if (pva)
+				kmem_cache_free(vmap_area_cachep, pva);
+		}
+	}
+
 	spin_lock(&vmap_area_lock);
+	preempt_enable();
 
 	/*
 	 * If an allocation fails, the "vend" address is