linux-kernel - Re: Performance regressions in "boot

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: <20201013131735.GL25604@MiWiFi-R3L-srv>
Date:   Tue, 13 Oct 2020 21:17:35 +0800
From:   "bhe@...hat.com" <bhe@...hat.com>
To:     Rahul Gopakumar <gopakumarr@...are.com>
Cc:     "linux-mm@...ck.org" <linux-mm@...ck.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        "akpm@...ux-foundation.org" <akpm@...ux-foundation.org>,
        "natechancellor@...il.com" <natechancellor@...il.com>,
        "ndesaulniers@...gle.com" <ndesaulniers@...gle.com>,
        "clang-built-linux@...glegroups.com" 
        <clang-built-linux@...glegroups.com>,
        "rostedt@...dmis.org" <rostedt@...dmis.org>,
        Rajender M <manir@...are.com>,
        Yiu Cho Lau <lauyiuch@...are.com>,
        Peter Jonasson <pjonasson@...are.com>,
        Venkatesh Rajaram <rajaramv@...are.com>
Subject: Re: Performance regressions in "boot_time" tests in Linux 5.8 Kernel

Hi Rahul,

On 10/12/20 at 05:21pm, Rahul Gopakumar wrote:
> Hi Baoquan,
> 
> Attached collected dmesg logs for with and without
> commit after adding memblock=debug to kernel cmdline.

Can you test below draft patch and see if it works for you? 

>From a2ea6caef3c73ad9efb2dd2b48039065fe430bb2 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@...hat.com>
Date: Tue, 13 Oct 2020 20:05:30 +0800
Subject: [PATCH] mm: make memmap defer init only take effect per zone

Deferred struct page init is designed to work per zone. However since
commit 73a6e474cb376 ("mm: memmap_init: iterate over memblock regions
rather that check each PFN"), the handling is mistakenly done in all memory
ranges inside one zone. Especially in those unmovable zones of multiple nodes,
memblock reservation split them into many memory ranges. This makes
initialized struct page more than expected in early stage, then increases
much boot time.

Let's fix it to make the memmap defer init handled in zone wide, but not in
memory range of one zone.

Signed-off-by: Baoquan He <bhe@...hat.com>
---
 arch/ia64/mm/init.c | 4 ++--
 include/linux/mm.h  | 5 +++--
 mm/memory_hotplug.c | 2 +-
 mm/page_alloc.c     | 6 +++---
 4 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index ef12e097f318..27ca549ff47e 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -536,7 +536,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg)
 
 	if (map_start < map_end)
 		memmap_init_zone((unsigned long)(map_end - map_start),
-				 args->nid, args->zone, page_to_pfn(map_start),
+				 args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end),
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	return 0;
 }
@@ -546,7 +546,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone,
 	     unsigned long start_pfn)
 {
 	if (!vmem_map) {
-		memmap_init_zone(size, nid, zone, start_pfn,
+		memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size,
 				 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 	} else {
 		struct page *start;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef360fe70aaf..5f9fc61d5be2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2439,8 +2439,9 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
-		enum meminit_context, struct vmem_altmap *, int migratetype);
+extern void memmap_init_zone(unsigned long, int, unsigned long,
+		unsigned long, unsigned long, enum meminit_context,
+		struct vmem_altmap *, int migratetype);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b44d4c7ba73b..f9a37e6abc1c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -732,7 +732,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * expects the zone spans the pfn range. All the pages in the range
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
-	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn,
+	memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, 0,
 			 MEMINIT_HOTPLUG, altmap, migratetype);
 
 	set_zone_contiguous(zone);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2ebf9ddafa3a..e8b19fdd18ec 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6044,7 +6044,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
  * zone stats (e.g., nr_isolate_pageblock) are touched.
  */
 void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
-		unsigned long start_pfn,
+		unsigned long start_pfn, unsigned long zone_end_pfn,
 		enum meminit_context context,
 		struct vmem_altmap *altmap, int migratetype)
 {
@@ -6080,7 +6080,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		if (context == MEMINIT_EARLY) {
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
-			if (defer_init(nid, pfn, end_pfn))
+			if (defer_init(nid, pfn, zone_end_pfn))
 				break;
 		}
 
@@ -6194,7 +6194,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid,
 
 		if (end_pfn > start_pfn) {
 			size = end_pfn - start_pfn;
-			memmap_init_zone(size, nid, zone, start_pfn,
+			memmap_init_zone(size, nid, zone, start_pfn, range_end_pfn,
 					 MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
 		}
 	}
-- 
2.17.2