[RFC PATCH 3/3] mm/compaction: respect compact_unevictable_allowed in alloc_contig path

[Wandun Chen]

From: Wandun Chen <chenwandun@xxxxxxxxxxx>

vm.compact_unevictable_allowed=0 is used to prevent compacting
unevictable pages. However, isolate_migratepages_range() passes
ISOLATE_UNEVICTABLE regardless of this sysctl, so the setting
has no effect in the alloc_contig path.

Fix it by:
  - Keep ISOLATE_UNEVICTABLE for CMA allocation, discussed in [1].
  - Honour sysctl_compact_unevictable_allowed for non-CMA allocation.

Suggested-by: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Wandun Chen <chenwandun@xxxxxxxxxxx>
Link: https://lore.kernel.org/all/25ba0d77-eb61-4efc-b2fc-73878cbd85c1@xxxxxxx/ [1]
---
 include/linux/compaction.h | 6 ++++++
 mm/compaction.c            | 9 +++++++--
 mm/internal.h              | 1 +
 mm/page_alloc.c            | 2 ++
 4 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index f29ef0653546..04e60f65b976 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -106,6 +106,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 extern void __meminit kcompactd_run(int nid);
 extern void __meminit kcompactd_stop(int nid);
 extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx);
+extern bool compaction_allow_unevictable(void);
 
 #else
 static inline void reset_isolation_suitable(pg_data_t *pgdat)
@@ -131,6 +132,11 @@ static inline void wakeup_kcompactd(pg_data_t *pgdat,
 {
 }
 
+static inline bool compaction_allow_unevictable(void)
+{
+	return true;
+}
+
 #endif /* CONFIG_COMPACTION */
 
 struct node;
diff --git a/mm/compaction.c b/mm/compaction.c
index 007d5e00a8ae..a10acb273454 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1341,6 +1341,7 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 							unsigned long end_pfn)
 {
 	unsigned long pfn, block_start_pfn, block_end_pfn;
+	isolate_mode_t mode = cc->allow_unevictable ? ISOLATE_UNEVICTABLE : 0;
 	int ret = 0;
 
 	/* Scan block by block. First and last block may be incomplete */
@@ -1360,8 +1361,7 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
 					block_end_pfn, cc->zone))
 			continue;
 
-		ret = isolate_migratepages_block(cc, pfn, block_end_pfn,
-						 ISOLATE_UNEVICTABLE);
+		ret = isolate_migratepages_block(cc, pfn, block_end_pfn, mode);
 
 		if (ret)
 			break;
@@ -1902,6 +1902,11 @@ typedef enum {
  * compactable pages.
  */
 static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT;
+
+bool compaction_allow_unevictable(void)
+{
+	return sysctl_compact_unevictable_allowed;
+}
 /*
  * Tunable for proactive compaction. It determines how
  * aggressively the kernel should compact memory in the
diff --git a/mm/internal.h b/mm/internal.h
index 181e79f1d6a2..163f9d6b37f3 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1052,6 +1052,7 @@ struct compact_control {
 					 * ensure forward progress.
 					 */
 	bool alloc_contig;		/* alloc_contig_range allocation */
+	bool allow_unevictable;		/* Allow isolation of unevictable folios */
 };
 
 /*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 81a9d4d1e6c0..1cf9d4a3b14c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7118,6 +7118,8 @@ int alloc_contig_frozen_range_noprof(unsigned long start, unsigned long end,
 		.ignore_skip_hint = true,
 		.no_set_skip_hint = true,
 		.alloc_contig = true,
+		.allow_unevictable = !!(alloc_flags & ACR_FLAGS_CMA) ||
+					     compaction_allow_unevictable(),
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
 	enum pb_isolate_mode mode = (alloc_flags & ACR_FLAGS_CMA) ?
-- 
2.43.0