[v7 04/16] mm/rmap: extend rmap and migration support device-private entries

[Balbir Singh <balbirs@nvidia.com>]

Add device-private THP support to reverse mapping infrastructure, enabling
proper handling during migration and walk operations.

The key changes are:
- add_migration_pmd()/remove_migration_pmd(): Handle device-private
  entries during folio migration and splitting
- page_vma_mapped_walk(): Recognize device-private THP entries during
  VMA traversal operations

This change supports folio splitting and migration operations on
device-private entries.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: Ying Huang <ying.huang@linux.alibaba.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Barry Song <baohua@kernel.org>
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: Ralph Campbell <rcampbell@nvidia.com>
Cc: Mika Penttilä <mpenttil@redhat.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: Balbir Singh <balbirs@nvidia.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
---
 mm/damon/ops-common.c | 20 +++++++++++++++++---
 mm/huge_memory.c      | 16 +++++++++++++++-
 mm/page_idle.c        |  7 +++++--
 mm/page_vma_mapped.c  |  7 +++++++
 mm/rmap.c             | 24 ++++++++++++++++++++----
 5 files changed, 64 insertions(+), 10 deletions(-)

diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
index 998c5180a603..ac54bf5b2623 100644
--- a/mm/damon/ops-common.c
+++ b/mm/damon/ops-common.c
@@ -75,12 +75,24 @@ void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr
 void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	struct folio *folio = damon_get_folio(pmd_pfn(pmdp_get(pmd)));
+	pmd_t pmdval = pmdp_get(pmd);
+	struct folio *folio;
+	bool young = false;
+	unsigned long pfn;
+
+	if (likely(pmd_present(pmdval)))
+		pfn = pmd_pfn(pmdval);
+	else
+		pfn = swp_offset_pfn(pmd_to_swp_entry(pmdval));
 
+	folio = damon_get_folio(pfn);
 	if (!folio)
 		return;
 
-	if (pmdp_clear_young_notify(vma, addr, pmd))
+	if (likely(pmd_present(pmdval)))
+		young |= pmdp_clear_young_notify(vma, addr, pmd);
+	young |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + HPAGE_PMD_SIZE);
+	if (young)
 		folio_set_young(folio);
 
 	folio_set_idle(folio);
@@ -203,7 +215,9 @@ static bool damon_folio_young_one(struct folio *folio,
 				mmu_notifier_test_young(vma->vm_mm, addr);
 		} else {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			*accessed = pmd_young(pmdp_get(pvmw.pmd)) ||
+			pmd_t pmd = pmdp_get(pvmw.pmd);
+
+			*accessed = (pmd_present(pmd) && pmd_young(pmd)) ||
 				!folio_test_idle(folio) ||
 				mmu_notifier_test_young(vma->vm_mm, addr);
 #else
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8e0a1747762d..483b8341ce22 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -4628,7 +4628,10 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		return 0;
 
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
-	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
+	if (unlikely(!pmd_present(*pvmw->pmd)))
+		pmdval = pmdp_huge_get_and_clear(vma->vm_mm, address, pvmw->pmd);
+	else
+		pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
 
 	/* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */
 	anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page);
@@ -4678,6 +4681,17 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	entry = pmd_to_swp_entry(*pvmw->pmd);
 	folio_get(folio);
 	pmde = folio_mk_pmd(folio, READ_ONCE(vma->vm_page_prot));
+
+	if (folio_is_device_private(folio)) {
+		if (pmd_write(pmde))
+			entry = make_writable_device_private_entry(
+							page_to_pfn(new));
+		else
+			entry = make_readable_device_private_entry(
+							page_to_pfn(new));
+		pmde = swp_entry_to_pmd(entry);
+	}
+
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
 	if (is_writable_migration_entry(entry))
diff --git a/mm/page_idle.c b/mm/page_idle.c
index a82b340dc204..d4299de81031 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -71,8 +71,11 @@ static bool page_idle_clear_pte_refs_one(struct folio *folio,
 				referenced |= ptep_test_and_clear_young(vma, addr, pvmw.pte);
 			referenced |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE);
 		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
-			if (pmdp_clear_young_notify(vma, addr, pvmw.pmd))
-				referenced = true;
+			pmd_t pmdval = pmdp_get(pvmw.pmd);
+
+			if (likely(pmd_present(pmdval)))
+				referenced |= pmdp_clear_young_notify(vma, addr, pvmw.pmd);
+			referenced |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + PMD_SIZE);
 		} else {
 			/* unexpected pmd-mapped page? */
 			WARN_ON_ONCE(1);
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index c498a91b6706..137ce27ff68c 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -277,6 +277,13 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 			 * cannot return prematurely, while zap_huge_pmd() has
 			 * cleared *pmd but not decremented compound_mapcount().
 			 */
+			swp_entry_t entry = pmd_to_swp_entry(pmde);
+
+			if (is_device_private_entry(entry)) {
+				pvmw->ptl = pmd_lock(mm, pvmw->pmd);
+				return true;
+			}
+
 			if ((pvmw->flags & PVMW_SYNC) &&
 			    thp_vma_suitable_order(vma, pvmw->address,
 						   PMD_ORDER) &&
diff --git a/mm/rmap.c b/mm/rmap.c
index 9bab13429975..c3fc30cf3636 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1046,9 +1046,16 @@ static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw)
 		} else {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 			pmd_t *pmd = pvmw->pmd;
-			pmd_t entry;
+			pmd_t entry = pmdp_get(pmd);
 
-			if (!pmd_dirty(*pmd) && !pmd_write(*pmd))
+			/*
+			 * Please see the comment above (!pte_present).
+			 * A non present PMD is not writable from a CPU
+			 * perspective.
+			 */
+			if (!pmd_present(entry))
+				continue;
+			if (!pmd_dirty(entry) && !pmd_write(entry))
 				continue;
 
 			flush_cache_range(vma, address,
@@ -2343,6 +2350,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 	while (page_vma_mapped_walk(&pvmw)) {
 		/* PMD-mapped THP migration entry */
 		if (!pvmw.pte) {
+			__maybe_unused unsigned long pfn;
+			__maybe_unused pmd_t pmdval;
+
 			if (flags & TTU_SPLIT_HUGE_PMD) {
 				split_huge_pmd_locked(vma, pvmw.address,
 						      pvmw.pmd, true);
@@ -2351,8 +2361,14 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				break;
 			}
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
-			subpage = folio_page(folio,
-				pmd_pfn(*pvmw.pmd) - folio_pfn(folio));
+			pmdval = pmdp_get(pvmw.pmd);
+			if (likely(pmd_present(pmdval)))
+				pfn = pmd_pfn(pmdval);
+			else
+				pfn = swp_offset_pfn(pmd_to_swp_entry(pmdval));
+
+			subpage = folio_page(folio, pfn - folio_pfn(folio));
+
 			VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) ||
 					!folio_test_pmd_mappable(folio), folio);
 
-- 
2.51.0