linux-kernel - [PATCH] mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20211014092952.1500982-1-chenwandun@huawei.com>
Date:   Thu, 14 Oct 2021 17:29:52 +0800
From:   Chen Wandun <chenwandun@...wei.com>
To:     <akpm@...ux-foundation.org>, <shakeelb@...gle.com>,
        <npiggin@...il.com>, <linux-mm@...ck.org>,
        <linux-kernel@...r.kernel.org>, <edumazet@...gle.com>,
        <wangkefeng.wang@...wei.com>, <guohanjun@...wei.com>
CC:     <chenwandun@...wei.com>
Subject: [PATCH] mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation

It will 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

Signed-off-by: Chen Wandun <chenwandun@...wei.com>
----------------
based on "[PATCH] mm/vmalloc: fix numa spreading for large hash tables"
---
 include/linux/gfp.h |  4 +++
 mm/mempolicy.c      | 76 +++++++++++++++++++++++++++++++++++++++++++++
 mm/vmalloc.c        | 19 +++---------
 3 files changed, 85 insertions(+), 14 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 558299cb2970..b976c4177299 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -531,6 +531,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
 				struct list_head *page_list,
 				struct page **page_array);
 
+unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
+				unsigned long nr_pages,
+				struct page **page_array);
+
 /* Bulk allocate order-0 pages */
 static inline unsigned long
 alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9f8cd1457829..f456c5eb8d10 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2196,6 +2196,82 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
 }
 EXPORT_SYMBOL(alloc_pages);
 
+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;
+}
+
+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;
+}
+
+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);
+}
+
 struct folio *folio_alloc(gfp_t gfp, unsigned order)
 {
 	struct page *page = alloc_pages(gfp | __GFP_COMP, order);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b7ac4a8fe2b3..49adba793f3c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2856,23 +2856,14 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			 */
 			nr_pages_request = min(100U, nr_pages - nr_allocated);
 
-			if (nid == NUMA_NO_NODE) {
-				for (i = 0; i < nr_pages_request; i++) {
-					page = alloc_page(gfp);
-					if (page)
-						pages[nr_allocated + i] = page;
-					else {
-						nr = i;
-						break;
-					}
-				}
-				if (i >= nr_pages_request)
-					nr = nr_pages_request;
-			} else {
+			if (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();
 
-- 
2.25.1