mm/memremap: add ZONE_DEVICE support for compound pages

Add a new @vmemmap_shift property for struct dev_pagemap which specifies
that a devmap is composed of a set of compound pages of order
@vmemmap_shift, instead of base pages.  When a compound page devmap is
requested, all but the first page are initialised as tail pages instead
of order-0 pages.

For certain ZONE_DEVICE users like device-dax which have a fixed page
size, this creates an opportunity to optimize GUP and GUP-fast walkers,
treating it the same way as THP or hugetlb pages.

Additionally, commit 7118fc2906e2 ("hugetlb: address ref count racing in
prep_compound_gigantic_page") removed set_page_count() because the
setting of page ref count to zero was redundant.  devmap pages don't
come from page allocator though and only head page refcount is used for
compound pages, hence initialize tail page count to zero.

Link: https://lkml.kernel.org/r/20211202204422.26777-5-joao.m.martins@oracle.com
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 49 insertions, 7 deletions

diff --git a/mm/memremap.c b/mm/memremap.c
index 5a66a71ab591..a2869d8519a2 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -102,15 +102,22 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
 	return (range->start + range_len(range)) >> PAGE_SHIFT;
 }
 
-static unsigned long pfn_next(unsigned long pfn)
+static unsigned long pfn_next(struct dev_pagemap *pgmap, unsigned long pfn)
 {
-	if (pfn % 1024 == 0)
+	if (pfn % (1024 << pgmap->vmemmap_shift))
 		cond_resched();
-	return pfn + 1;
+	return pfn + pgmap_vmemmap_nr(pgmap);
+}
+
+static unsigned long pfn_len(struct dev_pagemap *pgmap, unsigned long range_id)
+{
+	return (pfn_end(pgmap, range_id) -
+		pfn_first(pgmap, range_id)) >> pgmap->vmemmap_shift;
 }
 
 #define for_each_device_pfn(pfn, map, i) \
-	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn))
+	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); \
+	     pfn = pfn_next(map, pfn))
 
 static void dev_pagemap_kill(struct dev_pagemap *pgmap)
 {
@@ -295,8 +302,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), pgmap);
-	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
-			- pfn_first(pgmap, range_id));
+	percpu_ref_get_many(pgmap->ref, pfn_len(pgmap, range_id));
 	return 0;
 
 err_add_memory:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 23045a2a1339..d59023a676ed 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6612,6 +6612,35 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
 	}
 }
 
+static void __ref memmap_init_compound(struct page *head,
+				       unsigned long head_pfn,
+				       unsigned long zone_idx, int nid,
+				       struct dev_pagemap *pgmap,
+				       unsigned long nr_pages)
+{
+	unsigned long pfn, end_pfn = head_pfn + nr_pages;
+	unsigned int order = pgmap->vmemmap_shift;
+
+	__SetPageHead(head);
+	for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) {
+		struct page *page = pfn_to_page(pfn);
+
+		__init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
+		prep_compound_tail(head, pfn - head_pfn);
+		set_page_count(page, 0);
+
+		/*
+		 * The first tail page stores compound_mapcount_ptr() and
+		 * compound_order() and the second tail page stores
+		 * compound_pincount_ptr(). Call prep_compound_head() after
+		 * the first and second tail pages have been initialized to
+		 * not have the data overwritten.
+		 */
+		if (pfn == head_pfn + 2)
+			prep_compound_head(head, order);
+	}
+}
+
 void __ref memmap_init_zone_device(struct zone *zone,
 				   unsigned long start_pfn,
 				   unsigned long nr_pages,
@@ -6620,6 +6649,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 	unsigned long pfn, end_pfn = start_pfn + nr_pages;
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	struct vmem_altmap *altmap = pgmap_altmap(pgmap);
+	unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap);
 	unsigned long zone_idx = zone_idx(zone);
 	unsigned long start = jiffies;
 	int nid = pgdat->node_id;
@@ -6637,10 +6667,16 @@ void __ref memmap_init_zone_device(struct zone *zone,
 		nr_pages = end_pfn - start_pfn;
 	}
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) {
 		struct page *page = pfn_to_page(pfn);
 
 		__init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
+
+		if (pfns_per_compound == 1)
+			continue;
+
+		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
+				     pfns_per_compound);
 	}
 
 	pr_info("%s initialised %lu pages in %ums\n", __func__,