In preparation for supporting try_to_unmap_one() to unmap PMD-mapped
folios, start the pagewalk first, then call split_huge_pmd_address() to
split the folio.
Since TTU_SPLIT_HUGE_PMD will no longer perform immediately, we might
encounter a PMD-mapped THP missing the mlock in the VM_LOCKED range during
the page walk. It’s probably necessary to mlock this THP to prevent it from
being picked up during page reclaim.
Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
Suggested-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Signed-off-by: Lance Yang <ioworker0@xxxxxxxxx>
---
include/linux/huge_mm.h | 6 ++++++
mm/huge_memory.c | 42 +++++++++++++++++++++--------------------
mm/rmap.c | 26 ++++++++++++++++++-------
3 files changed, 47 insertions(+), 27 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c8d3ec116e29..9fcb0b0b6ed1 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -409,6 +409,9 @@ static inline bool thp_migration_supported(void)
return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
}
+void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, bool freeze, struct folio *folio);
+
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline bool folio_test_pmd_mappable(struct folio *folio)
@@ -471,6 +474,9 @@ static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, bool freeze, struct folio *folio) {}
static inline void split_huge_pmd_address(struct vm_area_struct *vma,
unsigned long address, bool freeze, struct folio *folio) {}
+static inline void split_huge_pmd_locked(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmd,
+ bool freeze, struct folio *folio) {}
#define split_huge_pud(__vma, __pmd, __address) \
do { } while (0)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 317de2afd371..425272c6c50b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2581,6 +2581,27 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
pmd_populate(mm, pmd, pgtable);
}
+void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmd, bool freeze, struct folio *folio)
+{
+ VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio));
+ VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
+ VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
+ VM_BUG_ON(freeze && !folio);
+
+ /*
+ * When the caller requests to set up a migration entry, we
+ * require a folio to check the PMD against. Otherwise, there
+ * is a risk of replacing the wrong folio.
+ */
+ if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
+ is_pmd_migration_entry(*pmd)) {
+ if (folio && folio != pmd_folio(*pmd))
+ return;
+ __split_huge_pmd_locked(vma, pmd, address, freeze);
+ }
+}
+
void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, bool freeze, struct folio *folio)
{
@@ -2592,26 +2613,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
(address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE);
mmu_notifier_invalidate_range_start(&range);
ptl = pmd_lock(vma->vm_mm, pmd);
-
- /*
- * If caller asks to setup a migration entry, we need a folio to check
- * pmd against. Otherwise we can end up replacing wrong folio.
- */
- VM_BUG_ON(freeze && !folio);
- VM_WARN_ON_ONCE(folio && !folio_test_locked(folio));
-
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
- is_pmd_migration_entry(*pmd)) {
- /*
- * It's safe to call pmd_page when folio is set because it's
- * guaranteed that pmd is present.
- */
- if (folio && folio != pmd_folio(*pmd))
- goto out;
- __split_huge_pmd_locked(vma, pmd, range.start, freeze);
- }
-
-out:
+ split_huge_pmd_locked(vma, range.start, pmd, freeze, folio);
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(&range);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index ddffa30c79fb..08a93347f283 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1640,9 +1640,6 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
if (flags & TTU_SYNC)
pvmw.flags = PVMW_SYNC;
- if (flags & TTU_SPLIT_HUGE_PMD)
- split_huge_pmd_address(vma, address, false, folio);
-
/*
* For THP, we have to assume the worse case ie pmd for invalidation.
* For hugetlb, it could be much worse if we need to do pud
@@ -1668,20 +1665,35 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
mmu_notifier_invalidate_range_start(&range);
while (page_vma_mapped_walk(&pvmw)) {
- /* Unexpected PMD-mapped THP? */
- VM_BUG_ON_FOLIO(!pvmw.pte, folio);
-
/*
* If the folio is in an mlock()d vma, we must not swap it out.
*/
if (!(flags & TTU_IGNORE_MLOCK) &&
(vma->vm_flags & VM_LOCKED)) {
/* Restore the mlock which got missed */
- if (!folio_test_large(folio))
+ if (!folio_test_large(folio) ||
+ (!pvmw.pte && (flags & TTU_SPLIT_HUGE_PMD)))
mlock_vma_folio(folio, vma);
goto walk_done_err;
}
+ if (!pvmw.pte && (flags & TTU_SPLIT_HUGE_PMD)) {
+ /*
+ * We temporarily have to drop the PTL and start once
+ * again from that now-PTE-mapped page table.
+ */
+ split_huge_pmd_locked(vma, range.start, pvmw.pmd, false,
+ folio);
+ pvmw.pmd = NULL;
+ spin_unlock(pvmw.ptl);
+ pvmw.ptl = NULL;
+ flags &= ~TTU_SPLIT_HUGE_PMD;
+ continue;
+ }
+
+ /* Unexpected PMD-mapped THP? */
+ VM_BUG_ON_FOLIO(!pvmw.pte, folio);
+
pfn = pte_pfn(ptep_get(pvmw.pte));
subpage = folio_page(folio, pfn - folio_pfn(folio));
address = pvmw.address;
--
2.33.1
