[PATCH v4 02/11] mm: add PMD swap entry splitting support

[Usama Arif <usama.arif@linux.dev>]

Add a swap branch in __split_huge_pmd_locked() that splits a PMD swap
entry into 512 PTE swap entries.  Unlike migration splits, no folio
reference is needed because swap entries point to swap slots, not
pages.  Each PTE inherits the correct sub-slot offset and preserves
soft_dirty, uffd_wp, and exclusive flags.

The folio_remove_rmap_pmd() gate at the end must inspect old_pmd rather
than *pmd: for a present THP split, *pmd has already been cleared by
pmdp_invalidate() by the time the gate runs, and the invalidated bit
pattern can decode as a plausible swap entry via softleaf_from_pmd()
(any type_num < MAX_SWAPFILES reads as SWAP).

This branch is reached from the explicit __split_huge_pmd() callers
that hit a non-present PMD: partial-range mprotect / munmap, the
wp_huge_pmd() PMD-COW fallback, and the swap-in / swapoff fallbacks
added in later patches when the cached folio is no longer PMD-sized.
page_vma_mapped_walk() does not iterate PMD swap entries, so
try_to_unmap_one() and try_to_migrate_one() do not reach this branch
and freeze=true cannot occur in this branch today.  page and folio
are therefore left uninitialized in the swap branch; a
VM_WARN_ON_ONCE(freeze) catches any future caller that breaks this
invariant before the freeze path dereferences page_to_pfn(page + i)
or put_page(page).

Signed-off-by: Usama Arif <usama.arif@linux.dev>
---
 mm/huge_memory.c | 27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0dc6d630570f..e602cf2b48db 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3208,6 +3208,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
 						 vma, haddr, rmap_flags);
 		}
+	} else if (pmd_is_swap_entry(*pmd)) {
+		VM_WARN_ON_ONCE(freeze);
+		old_pmd = *pmd;
+		soft_dirty = pmd_swp_soft_dirty(old_pmd);
+		uffd_wp = pmd_swp_uffd_wp(old_pmd);
+		anon_exclusive = pmd_swp_exclusive(old_pmd);
 	} else {
 		/*
 		 * Up to this point the pmd is present and huge and userland has
@@ -3344,6 +3350,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			VM_WARN_ON(!pte_none(ptep_get(pte + i)));
 			set_pte_at(mm, addr, pte + i, entry);
 		}
+	} else if (pmd_is_swap_entry(old_pmd)) {
+		softleaf_t sl_entry = softleaf_from_pmd(old_pmd);
+		pte_t swp_pte;
+		swp_entry_t sub_entry;
+
+		for (i = 0, addr = haddr; i < HPAGE_PMD_NR;
+		     i++, addr += PAGE_SIZE) {
+			sub_entry = swp_entry(swp_type(sl_entry),
+					      swp_offset(sl_entry) + i);
+			swp_pte = swp_entry_to_pte(sub_entry);
+			if (soft_dirty)
+				swp_pte = pte_swp_mksoft_dirty(swp_pte);
+			if (uffd_wp)
+				swp_pte = pte_swp_mkuffd(swp_pte);
+			if (anon_exclusive)
+				swp_pte = pte_swp_mkexclusive(swp_pte);
+			VM_WARN_ON(!pte_none(ptep_get(pte + i)));
+			set_pte_at(mm, addr, pte + i, swp_pte);
+		}
 	} else {
 		pte_t entry;
 
@@ -3371,7 +3396,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	}
 	pte_unmap(pte);
 
-	if (!pmd_is_migration_entry(*pmd))
+	if (!pmd_is_migration_entry(old_pmd) && !pmd_is_swap_entry(old_pmd))
 		folio_remove_rmap_pmd(folio, page, vma);
 	if (freeze)
 		put_page(page);
-- 
2.53.0-Meta