[v1 resend 07/12] mm/memremap: add folio_split support

[Balbir Singh <balbirs@nvidia.com>]

When a zone device page is split (via huge pmd folio split). The
driver callback for folio_split is invoked to let the device driver
know that the folio size has been split into a smaller order.

The HMM test driver has been updated to handle the split, since the
test driver uses backing pages, it requires a mechanism of reorganizing
the backing pages (backing pages are used to create a mirror device)
again into the right sized order pages. This is supported by exporting
prep_compound_page().

Cc: Karol Herbst <kherbst@redhat.com>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Donet Tom <donettom@linux.ibm.com>

Signed-off-by: Balbir Singh <balbirs@nvidia.com>
---
 include/linux/memremap.h |  7 +++++++
 include/linux/mm.h       |  1 +
 lib/test_hmm.c           | 42 ++++++++++++++++++++++++++++++++++++++++
 mm/huge_memory.c         | 14 ++++++++++++++
 mm/page_alloc.c          |  1 +
 5 files changed, 65 insertions(+)

diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 11d586dd8ef1..2091b754f1da 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -100,6 +100,13 @@ struct dev_pagemap_ops {
 	 */
 	int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn,
 			      unsigned long nr_pages, int mf_flags);
+
+	/*
+	 * Used for private (un-addressable) device memory only.
+	 * This callback is used when a folio is split into
+	 * a smaller folio
+	 */
+	void (*folio_split)(struct folio *head, struct folio *tail);
 };
 
 #define PGMAP_ALTMAP_VALID	(1 << 0)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef40f68c1183..f7bda8b1e46c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1183,6 +1183,7 @@ static inline struct folio *virt_to_folio(const void *x)
 void __folio_put(struct folio *folio);
 
 void split_page(struct page *page, unsigned int order);
+void prep_compound_page(struct page *page, unsigned int order);
 void folio_copy(struct folio *dst, struct folio *src);
 int folio_mc_copy(struct folio *dst, struct folio *src);
 
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 95b4276a17fd..e20021fb7c69 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -1646,9 +1646,51 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+static void dmirror_devmem_folio_split(struct folio *head, struct folio *tail)
+{
+	struct page *rpage = BACKING_PAGE(folio_page(head, 0));
+	struct page *rpage_tail;
+	struct folio *rfolio;
+	unsigned long offset = 0;
+	unsigned int tail_order;
+	unsigned int head_order = folio_order(head);
+
+	if (!rpage) {
+		tail->page.zone_device_data = NULL;
+		return;
+	}
+
+	rfolio = page_folio(rpage);
+
+	if (tail == NULL) {
+		folio_reset_order(rfolio);
+		rfolio->mapping = NULL;
+		if (head_order)
+			prep_compound_page(rpage, head_order);
+		folio_set_count(rfolio, 1 << head_order);
+		return;
+	}
+
+	offset = folio_pfn(tail) - folio_pfn(head);
+
+	rpage_tail = folio_page(rfolio, offset);
+	tail->page.zone_device_data = rpage_tail;
+	clear_compound_head(rpage_tail);
+	rpage_tail->mapping = NULL;
+
+	tail_order = folio_order(tail);
+	if (tail_order)
+		prep_compound_page(rpage_tail, tail_order);
+
+	folio_page(tail, 0)->mapping = folio_page(head, 0)->mapping;
+	tail->pgmap = head->pgmap;
+	folio_set_count(page_folio(rpage_tail), 1 << tail_order);
+}
+
 static const struct dev_pagemap_ops dmirror_devmem_ops = {
 	.page_free	= dmirror_devmem_free,
 	.migrate_to_ram	= dmirror_devmem_fault,
+	.folio_split	= dmirror_devmem_folio_split,
 };
 
 static int dmirror_device_init(struct dmirror_device *mdevice, int id)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f29add796931..d55e36ae0c39 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3630,6 +3630,11 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 			if (release == origin_folio)
 				continue;
 
+			if (folio_is_device_private(origin_folio) &&
+					origin_folio->pgmap->ops->folio_split)
+				origin_folio->pgmap->ops->folio_split(
+					origin_folio, release);
+
 			folio_ref_unfreeze(release, 1 +
 					((mapping || swap_cache) ?
 						folio_nr_pages(release) : 0));
@@ -3661,6 +3666,15 @@ static int __split_unmapped_folio(struct folio *folio, int new_order,
 		}
 	}
 
+	/*
+	 * Mark the end of the split, so that the driver can setup origin_folio's
+	 * order and other metadata
+	 */
+	if (folio_is_device_private(origin_folio) &&
+			origin_folio->pgmap->ops->folio_split)
+		origin_folio->pgmap->ops->folio_split(
+			origin_folio, NULL);
+
 	/*
 	 * Unfreeze origin_folio only after all page cache entries, which used
 	 * to point to it, have been updated with new folios. Otherwise,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4f55f8ed65c7..0a538e9c24bd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -722,6 +722,7 @@ void prep_compound_page(struct page *page, unsigned int order)
 
 	prep_compound_head(page, order);
 }
+EXPORT_SYMBOL_GPL(prep_compound_page);
 
 static inline void set_buddy_order(struct page *page, unsigned int order)
 {
-- 
2.49.0