mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation

Commit ffb29b1c255a ("mm/vmalloc: fix numa spreading for large hash
tables") can cause significant performance regressions in some
situations as Andrew mentioned in [1].  The main situation is vmalloc,
vmalloc will allocate pages with NUMA_NO_NODE by default, that will
result in alloc page one by one;

In order to solve this, __alloc_pages_bulk and mempolicy should be
considered at the same time.

1) If node is specified in memory allocation request, it will alloc all
   pages by __alloc_pages_bulk.

2) If interleaving allocate memory, it will cauculate how many pages
   should be allocated in each node, and use __alloc_pages_bulk to alloc
   pages in each node.

[1]: https://lore.kernel.org/lkml/CALvZod4G3SzP3kWxQYn0fj+VgG-G3yWXz=gz17+3N57ru1iajw@mail.gmail.com/t/#m750c8e3231206134293b089feaa090590afa0f60

[akpm@linux-foundation.org: coding style fixes]
[akpm@linux-foundation.org: make two functions static]
[akpm@linux-foundation.org: fix CONFIG_NUMA=n build]

Link: https://lkml.kernel.org/r/20211021080744.874701-3-chenwandun@huawei.com
Signed-off-by: Chen Wandun <chenwandun@huawei.com>
Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 98 insertions, 4 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d12e0608fced..ce722333d9f6 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2196,6 +2196,88 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
 }
 EXPORT_SYMBOL(alloc_pages);
 
+static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
+		struct mempolicy *pol, unsigned long nr_pages,
+		struct page **page_array)
+{
+	int nodes;
+	unsigned long nr_pages_per_node;
+	int delta;
+	int i;
+	unsigned long nr_allocated;
+	unsigned long total_allocated = 0;
+
+	nodes = nodes_weight(pol->nodes);
+	nr_pages_per_node = nr_pages / nodes;
+	delta = nr_pages - nodes * nr_pages_per_node;
+
+	for (i = 0; i < nodes; i++) {
+		if (delta) {
+			nr_allocated = __alloc_pages_bulk(gfp,
+					interleave_nodes(pol), NULL,
+					nr_pages_per_node + 1, NULL,
+					page_array);
+			delta--;
+		} else {
+			nr_allocated = __alloc_pages_bulk(gfp,
+					interleave_nodes(pol), NULL,
+					nr_pages_per_node, NULL, page_array);
+		}
+
+		page_array += nr_allocated;
+		total_allocated += nr_allocated;
+	}
+
+	return total_allocated;
+}
+
+static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
+		struct mempolicy *pol, unsigned long nr_pages,
+		struct page **page_array)
+{
+	gfp_t preferred_gfp;
+	unsigned long nr_allocated = 0;
+
+	preferred_gfp = gfp | __GFP_NOWARN;
+	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
+
+	nr_allocated  = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes,
+					   nr_pages, NULL, page_array);
+
+	if (nr_allocated < nr_pages)
+		nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL,
+				nr_pages - nr_allocated, NULL,
+				page_array + nr_allocated);
+	return nr_allocated;
+}
+
+/* alloc pages bulk and mempolicy should be considered at the
+ * same time in some situation such as vmalloc.
+ *
+ * It can accelerate memory allocation especially interleaving
+ * allocate memory.
+ */
+unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
+		unsigned long nr_pages, struct page **page_array)
+{
+	struct mempolicy *pol = &default_policy;
+
+	if (!in_interrupt() && !(gfp & __GFP_THISNODE))
+		pol = get_task_policy(current);
+
+	if (pol->mode == MPOL_INTERLEAVE)
+		return alloc_pages_bulk_array_interleave(gfp, pol,
+							 nr_pages, page_array);
+
+	if (pol->mode == MPOL_PREFERRED_MANY)
+		return alloc_pages_bulk_array_preferred_many(gfp,
+				numa_node_id(), pol, nr_pages, page_array);
+
+	return __alloc_pages_bulk(gfp, policy_node(gfp, pol, numa_node_id()),
+				  policy_nodemask(gfp, pol), nr_pages, NULL,
+				  page_array);
+}
+
 int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
 {
 	struct mempolicy *pol = mpol_dup(vma_policy(src));
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c56720136c45..d2a00ad4e1dd 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2843,7 +2843,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * to fails, fallback to a single page allocator that is
 	 * more permissive.
 	 */
-	if (!order && nid != NUMA_NO_NODE) {
+	if (!order) {
 		while (nr_allocated < nr_pages) {
 			unsigned int nr, nr_pages_request;
 
@@ -2855,8 +2855,20 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			 */
 			nr_pages_request = min(100U, nr_pages - nr_allocated);
 
-			nr = alloc_pages_bulk_array_node(gfp, nid,
-				nr_pages_request, pages + nr_allocated);
+			/* memory allocation should consider mempolicy, we can't
+			 * wrongly use nearest node when nid == NUMA_NO_NODE,
+			 * otherwise memory may be allocated in only one node,
+			 * but mempolcy want to alloc memory by interleaving.
+			 */
+			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
+				nr = alloc_pages_bulk_array_mempolicy(gfp,
+							nr_pages_request,
+							pages + nr_allocated);
+
+			else
+				nr = alloc_pages_bulk_array_node(gfp, nid,
+							nr_pages_request,
+							pages + nr_allocated);
 
 			nr_allocated += nr;
 			cond_resched();
@@ -2868,7 +2880,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			if (nr != nr_pages_request)
 				break;
 		}
-	} else if (order)
+	} else
 		/*
 		 * Compound pages required for remap_vmalloc_page if
 		 * high-order pages.