The memmap_init_zone_device() function only initializes the migratetype
of the first pageblock of a compound page. If the compound page size
exceeds pageblock_nr_pages (e.g., 1GB hugepages with 2MB pageblocks),
subsequent pageblocks in the compound page remain uninitialized.
Move the migratetype initialization out of __init_zone_device_page()
and into a separate pageblock_migratetype_init_range() function. This
iterates over the entire PFN range of the memory, ensuring that all
pageblocks are correctly initialized.
Also remove the stale confusing comment about MEMINIT_HOTPLUG above
the migratetype setting since it is an obsolete relic from commit
966cf44f637e ("mm: defer ZONE_DEVICE page initialization to the point
where we init pgmap") and no longer makes sense here.
Fixes: c4386bd8ee3a ("mm/memremap: add ZONE_DEVICE support for compound pages")
Signed-off-by: Muchun Song <[email protected]>
Reviewed-by: Mike Rapoport (Microsoft) <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
---
mm/mm_init.c | 34 +++++++++++++++++++---------------
1 file changed, 19 insertions(+), 15 deletions(-)
diff --git a/mm/mm_init.c b/mm/mm_init.c
index f9f8e1af921c..cfc76953e249 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -674,6 +674,20 @@ static inline void fixup_hashdist(void)
static inline void fixup_hashdist(void) {}
#endif /* CONFIG_NUMA */
+#ifdef CONFIG_ZONE_DEVICE
+static __meminit void pageblock_migratetype_init_range(unsigned long pfn,
+ unsigned long nr_pages, int migratetype)
+{
+ const unsigned long end = pfn + nr_pages;
+
+ for (pfn = pageblock_align(pfn); pfn < end; pfn += pageblock_nr_pages) {
+ init_pageblock_migratetype(pfn_to_page(pfn), migratetype,
false);
+ if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
+ cond_resched();
+ }
+}
+#endif
+
/*
* Initialize a reserved page unconditionally, finding its zone first.
*/
@@ -1011,21 +1025,6 @@ static void __ref __init_zone_device_page(struct page
*page, unsigned long pfn,
page_folio(page)->pgmap = pgmap;
page->zone_device_data = NULL;
- /*
- * Mark the block movable so that blocks are reserved for
- * movable at startup. This will force kernel allocations
- * to reserve their blocks rather than leaking throughout
- * the address space during boot when many long-lived
- * kernel allocations are made.
- *
- * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
- * because this is done early in section_activate()
- */
- if (pageblock_aligned(pfn)) {
- init_pageblock_migratetype(page, MIGRATE_MOVABLE, false);
- cond_resched();
- }
-
/*
* ZONE_DEVICE pages other than MEMORY_TYPE_GENERIC are released
* directly to the driver page allocator which will set the page count
@@ -1122,6 +1121,9 @@ void __ref memmap_init_zone_device(struct zone *zone,
__init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
+ if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
+ cond_resched();
+
if (pfns_per_compound == 1)
continue;
@@ -1129,6 +1131,8 @@ void __ref memmap_init_zone_device(struct zone *zone,
compound_nr_pages(altmap, pgmap));
}
+ pageblock_migratetype_init_range(start_pfn, nr_pages, MIGRATE_MOVABLE);
+
pr_debug("%s initialised %lu pages in %ums\n", __func__,
nr_pages, jiffies_to_msecs(jiffies - start));
}
--
2.20.1
