mm: remember young/dirty bit for page migrations

When page migration happens, we always ignore the young/dirty bit settings
in the old pgtable, and marking the page as old in the new page table
using either pte_mkold() or pmd_mkold(), and keeping the pte clean.

That's fine from functional-wise, but that's not friendly to page reclaim
because the moving page can be actively accessed within the procedure. 
Not to mention hardware setting the young bit can bring quite some
overhead on some systems, e.g.  x86_64 needs a few hundreds nanoseconds to
set the bit.  The same slowdown problem to dirty bits when the memory is
first written after page migration happened.

Actually we can easily remember the A/D bit configuration and recover the
information after the page is migrated.  To achieve it, define a new set
of bits in the migration swap offset field to cache the A/D bits for old
pte.  Then when removing/recovering the migration entry, we can recover
the A/D bits even if the page changed.

One thing to mention is that here we used max_swapfile_size() to detect
how many swp offset bits we have, and we'll only enable this feature if we
know the swp offset is big enough to store both the PFN value and the A/D
bits.  Otherwise the A/D bits are dropped like before.

Link: https://lkml.kernel.org/r/20220811161331.37055-6-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andi Kleen <andi.kleen@intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 130 insertions, 4 deletions

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 578212fbf2be..11b874f212a2 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -8,6 +8,10 @@
 
 #ifdef CONFIG_MMU
 
+#ifdef CONFIG_SWAP
+#include <linux/swapfile.h>
+#endif	/* CONFIG_SWAP */
+
 /*
  * swapcache pages are stored in the swapper_space radix tree.  We want to
  * get good packing density in that tree, so the index should be dense in
@@ -35,6 +39,31 @@
 #endif	/* MAX_PHYSMEM_BITS */
 #define SWP_PFN_MASK			(BIT(SWP_PFN_BITS) - 1)
 
+/**
+ * Migration swap entry specific bitfield definitions.  Layout:
+ *
+ *   |----------+--------------------|
+ *   | swp_type | swp_offset         |
+ *   |----------+--------+-+-+-------|
+ *   |          | resv   |D|A|  PFN  |
+ *   |----------+--------+-+-+-------|
+ *
+ * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A)
+ * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D)
+ *
+ * Note: A/D bits will be stored in migration entries iff there're enough
+ * free bits in arch specific swp offset.  By default we'll ignore A/D bits
+ * when migrating a page.  Please refer to migration_entry_supports_ad()
+ * for more information.  If there're more bits besides PFN and A/D bits,
+ * they should be reserved and always be zeros.
+ */
+#define SWP_MIG_YOUNG_BIT		(SWP_PFN_BITS)
+#define SWP_MIG_DIRTY_BIT		(SWP_PFN_BITS + 1)
+#define SWP_MIG_TOTAL_BITS		(SWP_PFN_BITS + 2)
+
+#define SWP_MIG_YOUNG			BIT(SWP_MIG_YOUNG_BIT)
+#define SWP_MIG_DIRTY			BIT(SWP_MIG_DIRTY_BIT)
+
 static inline bool is_pfn_swap_entry(swp_entry_t entry);
 
 /* Clear all flags but only keep swp_entry_t related information */
@@ -265,6 +294,57 @@ static inline swp_entry_t make_writable_migration_entry(pgoff_t offset)
 	return swp_entry(SWP_MIGRATION_WRITE, offset);
 }
 
+/*
+ * Returns whether the host has large enough swap offset field to support
+ * carrying over pgtable A/D bits for page migrations.  The result is
+ * pretty much arch specific.
+ */
+static inline bool migration_entry_supports_ad(void)
+{
+	/*
+	 * max_swapfile_size() returns the max supported swp-offset plus 1.
+	 * We can support the migration A/D bits iff the pfn swap entry has
+	 * the offset large enough to cover all of them (PFN, A & D bits).
+	 */
+#ifdef CONFIG_SWAP
+	return max_swapfile_size() >= (1UL << SWP_MIG_TOTAL_BITS);
+#else  /* CONFIG_SWAP */
+	return false;
+#endif	/* CONFIG_SWAP */
+}
+
+static inline swp_entry_t make_migration_entry_young(swp_entry_t entry)
+{
+	if (migration_entry_supports_ad())
+		return swp_entry(swp_type(entry),
+				 swp_offset(entry) | SWP_MIG_YOUNG);
+	return entry;
+}
+
+static inline bool is_migration_entry_young(swp_entry_t entry)
+{
+	if (migration_entry_supports_ad())
+		return swp_offset(entry) & SWP_MIG_YOUNG;
+	/* Keep the old behavior of aging page after migration */
+	return false;
+}
+
+static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry)
+{
+	if (migration_entry_supports_ad())
+		return swp_entry(swp_type(entry),
+				 swp_offset(entry) | SWP_MIG_DIRTY);
+	return entry;
+}
+
+static inline bool is_migration_entry_dirty(swp_entry_t entry)
+{
+	if (migration_entry_supports_ad())
+		return swp_offset(entry) & SWP_MIG_DIRTY;
+	/* Keep the old behavior of clean page after migration */
+	return false;
+}
+
 extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 					spinlock_t *ptl);
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
@@ -311,6 +391,25 @@ static inline int is_readable_migration_entry(swp_entry_t entry)
 	return 0;
 }
 
+static inline swp_entry_t make_migration_entry_young(swp_entry_t entry)
+{
+	return entry;
+}
+
+static inline bool is_migration_entry_young(swp_entry_t entry)
+{
+	return false;
+}
+
+static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry)
+{
+	return entry;
+}
+
+static inline bool is_migration_entry_dirty(swp_entry_t entry)
+{
+	return false;
+}
 #endif	/* CONFIG_MIGRATION */
 
 typedef unsigned long pte_marker;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b4666774abf0..f4a656b279b1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2121,7 +2121,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		write = is_writable_migration_entry(entry);
 		if (PageAnon(page))
 			anon_exclusive = is_readable_exclusive_migration_entry(entry);
-		young = false;
+		young = is_migration_entry_young(entry);
+		dirty = is_migration_entry_dirty(entry);
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);
 		uffd_wp = pmd_swp_uffd_wp(old_pmd);
 	} else {
@@ -2183,6 +2184,10 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			else
 				swp_entry = make_readable_migration_entry(
 							page_to_pfn(page + i));
+			if (young)
+				swp_entry = make_migration_entry_young(swp_entry);
+			if (dirty)
+				swp_entry = make_migration_entry_dirty(swp_entry);
 			entry = swp_entry_to_pte(swp_entry);
 			if (soft_dirty)
 				entry = pte_swp_mksoft_dirty(entry);
@@ -3201,6 +3206,10 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		entry = make_readable_exclusive_migration_entry(page_to_pfn(page));
 	else
 		entry = make_readable_migration_entry(page_to_pfn(page));
+	if (pmd_young(pmdval))
+		entry = make_migration_entry_young(entry);
+	if (pmd_dirty(pmdval))
+		entry = make_migration_entry_dirty(entry);
 	pmdswp = swp_entry_to_pmd(entry);
 	if (pmd_soft_dirty(pmdval))
 		pmdswp = pmd_swp_mksoft_dirty(pmdswp);
@@ -3226,13 +3235,18 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 
 	entry = pmd_to_swp_entry(*pvmw->pmd);
 	get_page(new);
-	pmde = pmd_mkold(mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)));
+	pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot));
 	if (pmd_swp_soft_dirty(*pvmw->pmd))
 		pmde = pmd_mksoft_dirty(pmde);
 	if (is_writable_migration_entry(entry))
 		pmde = maybe_pmd_mkwrite(pmde, vma);
 	if (pmd_swp_uffd_wp(*pvmw->pmd))
 		pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));
+	if (!is_migration_entry_young(entry))
+		pmde = pmd_mkold(pmde);
+	/* NOTE: this may contain setting soft-dirty on some archs */
+	if (PageDirty(new) && is_migration_entry_dirty(entry))
+		pmde = pmd_mkdirty(pmde);
 
 	if (PageAnon(new)) {
 		rmap_t rmap_flags = RMAP_COMPOUND;
diff --git a/mm/migrate.c b/mm/migrate.c
index ce6a58f3b21f..a35eba462e61 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -198,7 +198,7 @@ static bool remove_migration_pte(struct folio *folio,
 #endif
 
 		folio_get(folio);
-		pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot)));
+		pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
 		if (pte_swp_soft_dirty(*pvmw.pte))
 			pte = pte_mksoft_dirty(pte);
 
@@ -206,6 +206,10 @@ static bool remove_migration_pte(struct folio *folio,
 		 * Recheck VMA as permissions can change since migration started
 		 */
 		entry = pte_to_swp_entry(*pvmw.pte);
+		if (!is_migration_entry_young(entry))
+			pte = pte_mkold(pte);
+		if (folio_test_dirty(folio) && is_migration_entry_dirty(entry))
+			pte = pte_mkdirty(pte);
 		if (is_writable_migration_entry(entry))
 			pte = maybe_mkwrite(pte, vma);
 		else if (pte_swp_uffd_wp(*pvmw.pte))
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index d8efd5a0eb40..5ab6ab9d2ed8 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -233,6 +233,12 @@ again:
 			else
 				entry = make_readable_migration_entry(
 							page_to_pfn(page));
+			if (pte_present(pte)) {
+				if (pte_young(pte))
+					entry = make_migration_entry_young(entry);
+				if (pte_dirty(pte))
+					entry = make_migration_entry_dirty(entry);
+			}
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_present(pte)) {
 				if (pte_soft_dirty(pte))
diff --git a/mm/rmap.c b/mm/rmap.c
index 6781f693df50..131def40e4f0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2066,7 +2066,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			else
 				entry = make_readable_migration_entry(
 							page_to_pfn(subpage));
-
+			if (pte_young(pteval))
+				entry = make_migration_entry_young(entry);
+			if (pte_dirty(pteval))
+				entry = make_migration_entry_dirty(entry);
 			swp_pte = swp_entry_to_pte(entry);
 			if (pte_soft_dirty(pteval))
 				swp_pte = pte_swp_mksoft_dirty(swp_pte);