linux-kernel - [PATCH 2/2] mm: compaction: skip the memory hole rapidly when isolating free pages

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]

Date:   Fri,  7 Jul 2023 16:51:47 +0800
From:   Baolin Wang <baolin.wang@...ux.alibaba.com>
To:     akpm@...ux-foundation.org
Cc:     mgorman@...hsingularity.net, vbabka@...e.cz, david@...hat.com,
        ying.huang@...el.com, baolin.wang@...ux.alibaba.com,
        linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: [PATCH 2/2] mm: compaction: skip the memory hole rapidly when isolating free pages

On my machine with below memory layout, and I can see it will take more
time to skip the larger memory hole (range: 0x100000000 - 0x1800000000)
when isolating free pages. So adding a new helper to skip the memory
hole rapidly, which can reduce the time consumed from about 70us to less
than 1us.

[    0.000000] Zone ranges:
[    0.000000]   DMA      [mem 0x0000000040000000-0x00000000ffffffff]
[    0.000000]   DMA32    empty
[    0.000000]   Normal   [mem 0x0000000100000000-0x0000001fa7ffffff]
[    0.000000] Movable zone start for each node
[    0.000000] Early memory node ranges
[    0.000000]   node   0: [mem 0x0000000040000000-0x0000000fffffffff]
[    0.000000]   node   0: [mem 0x0000001800000000-0x0000001fa3c7ffff]
[    0.000000]   node   0: [mem 0x0000001fa3c80000-0x0000001fa3ffffff]
[    0.000000]   node   0: [mem 0x0000001fa4000000-0x0000001fa402ffff]
[    0.000000]   node   0: [mem 0x0000001fa4030000-0x0000001fa40effff]
[    0.000000]   node   0: [mem 0x0000001fa40f0000-0x0000001fa73cffff]
[    0.000000]   node   0: [mem 0x0000001fa73d0000-0x0000001fa745ffff]
[    0.000000]   node   0: [mem 0x0000001fa7460000-0x0000001fa746ffff]
[    0.000000]   node   0: [mem 0x0000001fa7470000-0x0000001fa758ffff]
[    0.000000]   node   0: [mem 0x0000001fa7590000-0x0000001fa7ffffff]

Signed-off-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
---
 mm/compaction.c | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 43358efdbdc2..9641e2131901 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -249,11 +249,31 @@ static unsigned long skip_offline_sections(unsigned long start_pfn)
 
 	return 0;
 }
+
+static unsigned long skip_offline_sections_reverse(unsigned long start_pfn)
+{
+	unsigned long start_nr = pfn_to_section_nr(start_pfn);
+
+	if (!start_nr || online_section_nr(start_nr))
+		return 0;
+
+	while (start_nr-- > 0) {
+		if (online_section_nr(start_nr))
+			return section_nr_to_pfn(start_nr) + PAGES_PER_SECTION - 1;
+	}
+
+	return 0;
+}
 #else
 static unsigned long skip_offline_sections(unsigned long start_pfn)
 {
 	return 0;
 }
+
+static unsigned long skip_offline_sections_reverse(unsigned long start_pfn)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -1668,8 +1688,16 @@ static void isolate_freepages(struct compact_control *cc)
 
 		page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn,
 									zone);
-		if (!page)
+		if (!page) {
+			unsigned long next_pfn;
+
+			next_pfn = skip_offline_sections_reverse(block_start_pfn);
+			if (next_pfn)
+				block_start_pfn = max(pageblock_start_pfn(next_pfn),
+						      low_pfn);
+
 			continue;
+		}
 
 		/* Check the block is suitable for migration */
 		if (!suitable_migration_target(cc, page))
-- 
2.39.3