[PATCH v2 03/14] mm: Teach memmap_init_zone() to initialize ZONE_DEVICE pages

[Dan Williams <dan.j.williams@xxxxxxxxx>]

Rather than run a loop over the freshly initialized pages in
devm_memremap_pages() *after* arch_add_memory() returns, teach
memmap_init_zone() to return the pages fully initialized. This is in
preparation for multi-threading page initialization work, but it also
has some straight line performance benefits to not incur another loop of
cache misses across a large (100s of GBs to TBs) address range.

Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Cc: "Jérôme Glisse" <jglisse@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
 kernel/memremap.c |   16 +---------------
 mm/page_alloc.c   |   19 +++++++++++++++++++
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/kernel/memremap.c b/kernel/memremap.c
index b861fe909932..85e4a7c576b2 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -173,8 +173,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap,
 	struct vmem_altmap *altmap = pgmap->altmap_valid ?
 			&pgmap->altmap : NULL;
 	struct resource *res = &pgmap->res;
-	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
+	unsigned long pgoff, order;
 	int error, nid, is_ram;
 
 	if (!pgmap->ref || !kill)
@@ -251,20 +251,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap,
 	if (error)
 		goto err_add_memory;
 
-	for_each_device_pfn(pfn, pgmap) {
-		struct page *page = pfn_to_page(pfn);
-
-		/*
-		 * ZONE_DEVICE pages union ->lru with a ->pgmap back
-		 * pointer.  It is a bug if a ZONE_DEVICE page is ever
-		 * freed or placed on a driver-private list.  Seed the
-		 * storage with LIST_POISON* values.
-		 */
-		list_del(&page->lru);
-		page->pgmap = pgmap;
-		percpu_ref_get(pgmap->ref);
-	}
-
 	pgmap->kill = kill;
 	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
 			pgmap);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f83682ef006e..fb45cfeb4a50 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5548,6 +5548,25 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 			cond_resched();
 		}
+
+		if (is_zone_device_page(page)) {
+			if (WARN_ON_ONCE(!pgmap))
+				continue;
+
+			/* skip invalid device pages */
+			if (altmap && (pfn < (altmap->base_pfn
+						+ vmem_altmap_offset(altmap))))
+				continue;
+			/*
+			 * ZONE_DEVICE pages union ->lru with a ->pgmap back
+			 * pointer.  It is a bug if a ZONE_DEVICE page is ever
+			 * freed or placed on a driver-private list.  Seed the
+			 * storage with poison.
+			 */
+			page->lru.prev = LIST_POISON2;
+			page->pgmap = pgmap;
+			percpu_ref_get(pgmap->ref);
+		}
 	}
 }