diff mbox series

[RESEND,v10,11/12] mm, migrate: apply luf mechanism to unmapping during migration

Message ID 20240520021734.21527-12-byungchul@sk.com (mailing list archive)
State New
Headers show
Series LUF(Lazy Unmap Flush) reducing tlb numbers over 90% | expand

Commit Message

Byungchul Park May 20, 2024, 2:17 a.m. UTC
A new mechanism, LUF(Lazy Unmap Flush), defers tlb flush until folios
that have been unmapped and freed, eventually get allocated again.  It's
safe for folios that had been mapped read only and were unmapped, since
the contents of the folios don't change while staying in pcp or buddy
so we can still read the data through the stale tlb entries.

Applied the mechanism to unmapping during migration.

Signed-off-by: Byungchul Park <byungchul@sk.com>
---
 include/linux/rmap.h |  2 +-
 mm/migrate.c         | 56 ++++++++++++++++++++++++++++++++------------
 mm/rmap.c            |  9 ++++---
 3 files changed, 48 insertions(+), 19 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 0f906dc6d280..1898a2c1c087 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -657,7 +657,7 @@  static inline int folio_try_share_anon_rmap_pmd(struct folio *folio,
 int folio_referenced(struct folio *, int is_locked,
 			struct mem_cgroup *memcg, unsigned long *vm_flags);
 
-void try_to_migrate(struct folio *folio, enum ttu_flags flags);
+bool try_to_migrate(struct folio *folio, enum ttu_flags flags);
 void try_to_unmap(struct folio *, enum ttu_flags flags);
 
 int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
diff --git a/mm/migrate.c b/mm/migrate.c
index f9ed7a2b8720..c8b0e5203e9a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1090,7 +1090,8 @@  static void migrate_folio_undo_dst(struct folio *dst, bool locked,
 
 /* Cleanup src folio upon migration success */
 static void migrate_folio_done(struct folio *src,
-			       enum migrate_reason reason)
+			       enum migrate_reason reason,
+			       unsigned short int ugen)
 {
 	/*
 	 * Compaction can migrate also non-LRU pages which are
@@ -1101,8 +1102,12 @@  static void migrate_folio_done(struct folio *src,
 		mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON +
 				    folio_is_file_lru(src), -folio_nr_pages(src));
 
-	if (reason != MR_MEMORY_FAILURE)
-		/* We release the page in page_handle_poison. */
+	/* We release the page in page_handle_poison. */
+	if (reason == MR_MEMORY_FAILURE)
+		check_luf_flush(ugen);
+	else if (ugen)
+		folio_put_ugen(src, ugen);
+	else
 		folio_put(src);
 }
 
@@ -1110,7 +1115,8 @@  static void migrate_folio_done(struct folio *src,
 static int migrate_folio_unmap(new_folio_t get_new_folio,
 		free_folio_t put_new_folio, unsigned long private,
 		struct folio *src, struct folio **dstp, enum migrate_mode mode,
-		enum migrate_reason reason, struct list_head *ret)
+		enum migrate_reason reason, struct list_head *ret,
+		bool *can_luf)
 {
 	struct folio *dst;
 	int rc = -EAGAIN;
@@ -1126,7 +1132,7 @@  static int migrate_folio_unmap(new_folio_t get_new_folio,
 		folio_clear_unevictable(src);
 		/* free_pages_prepare() will clear PG_isolated. */
 		list_del(&src->lru);
-		migrate_folio_done(src, reason);
+		migrate_folio_done(src, reason, 0);
 		return MIGRATEPAGE_SUCCESS;
 	}
 
@@ -1244,7 +1250,7 @@  static int migrate_folio_unmap(new_folio_t get_new_folio,
 		/* Establish migration ptes */
 		VM_BUG_ON_FOLIO(folio_test_anon(src) &&
 			       !folio_test_ksm(src) && !anon_vma, src);
-		try_to_migrate(src, mode == MIGRATE_ASYNC ? TTU_BATCH_FLUSH : 0);
+		*can_luf = try_to_migrate(src, mode == MIGRATE_ASYNC ? TTU_BATCH_FLUSH : 0);
 		old_page_state |= PAGE_WAS_MAPPED;
 	}
 
@@ -1272,7 +1278,7 @@  static int migrate_folio_unmap(new_folio_t get_new_folio,
 static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
 			      struct folio *src, struct folio *dst,
 			      enum migrate_mode mode, enum migrate_reason reason,
-			      struct list_head *ret)
+			      struct list_head *ret, unsigned short int ugen)
 {
 	int rc;
 	int old_page_state = 0;
@@ -1326,7 +1332,7 @@  static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
 	if (anon_vma)
 		put_anon_vma(anon_vma);
 	folio_unlock(src);
-	migrate_folio_done(src, reason);
+	migrate_folio_done(src, reason, ugen);
 
 	return rc;
 out:
@@ -1616,7 +1622,7 @@  static void migrate_folios_move(struct list_head *src_folios,
 		struct list_head *ret_folios,
 		struct migrate_pages_stats *stats,
 		int *retry, int *thp_retry, int *nr_failed,
-		int *nr_retry_pages)
+		int *nr_retry_pages, unsigned short int ugen)
 {
 	struct folio *folio, *folio2, *dst, *dst2;
 	bool is_thp;
@@ -1633,7 +1639,7 @@  static void migrate_folios_move(struct list_head *src_folios,
 
 		rc = migrate_folio_move(put_new_folio, private,
 				folio, dst, mode,
-				reason, ret_folios);
+				reason, ret_folios, ugen);
 		/*
 		 * The rules are:
 		 *	Success: folio will be freed
@@ -1710,7 +1716,11 @@  static int migrate_pages_batch(struct list_head *from,
 	int rc, rc_saved = 0, nr_pages;
 	LIST_HEAD(unmap_folios);
 	LIST_HEAD(dst_folios);
+	LIST_HEAD(unmap_folios_luf);
+	LIST_HEAD(dst_folios_luf);
 	bool nosplit = (reason == MR_NUMA_MISPLACED);
+	unsigned short int ugen;
+	bool can_luf;
 
 	VM_WARN_ON_ONCE(mode != MIGRATE_ASYNC &&
 			!list_empty(from) && !list_is_singular(from));
@@ -1773,9 +1783,11 @@  static int migrate_pages_batch(struct list_head *from,
 				continue;
 			}
 
+			can_luf = false;
 			rc = migrate_folio_unmap(get_new_folio, put_new_folio,
 					private, folio, &dst, mode, reason,
-					ret_folios);
+					ret_folios, &can_luf);
+
 			/*
 			 * The rules are:
 			 *	Success: folio will be freed
@@ -1821,7 +1833,8 @@  static int migrate_pages_batch(struct list_head *from,
 				/* nr_failed isn't updated for not used */
 				stats->nr_thp_failed += thp_retry;
 				rc_saved = rc;
-				if (list_empty(&unmap_folios))
+				if (list_empty(&unmap_folios) &&
+				    list_empty(&unmap_folios_luf))
 					goto out;
 				else
 					goto move;
@@ -1835,8 +1848,13 @@  static int migrate_pages_batch(struct list_head *from,
 				stats->nr_thp_succeeded += is_thp;
 				break;
 			case MIGRATEPAGE_UNMAP:
-				list_move_tail(&folio->lru, &unmap_folios);
-				list_add_tail(&dst->lru, &dst_folios);
+				if (can_luf) {
+					list_move_tail(&folio->lru, &unmap_folios_luf);
+					list_add_tail(&dst->lru, &dst_folios_luf);
+				} else {
+					list_move_tail(&folio->lru, &unmap_folios);
+					list_add_tail(&dst->lru, &dst_folios);
+				}
 				break;
 			default:
 				/*
@@ -1856,6 +1874,8 @@  static int migrate_pages_batch(struct list_head *from,
 	stats->nr_thp_failed += thp_retry;
 	stats->nr_failed_pages += nr_retry_pages;
 move:
+	/* Should be before try_to_unmap_flush() */
+	ugen = try_to_unmap_luf();
 	/* Flush TLBs for all unmapped folios */
 	try_to_unmap_flush();
 
@@ -1869,7 +1889,11 @@  static int migrate_pages_batch(struct list_head *from,
 		migrate_folios_move(&unmap_folios, &dst_folios,
 				put_new_folio, private, mode, reason,
 				ret_folios, stats, &retry, &thp_retry,
-				&nr_failed, &nr_retry_pages);
+				&nr_failed, &nr_retry_pages, 0);
+		migrate_folios_move(&unmap_folios_luf, &dst_folios_luf,
+				put_new_folio, private, mode, reason,
+				ret_folios, stats, &retry, &thp_retry,
+				&nr_failed, &nr_retry_pages, ugen);
 	}
 	nr_failed += retry;
 	stats->nr_thp_failed += thp_retry;
@@ -1880,6 +1904,8 @@  static int migrate_pages_batch(struct list_head *from,
 	/* Cleanup remaining folios */
 	migrate_folios_undo(&unmap_folios, &dst_folios,
 			put_new_folio, private, ret_folios);
+	migrate_folios_undo(&unmap_folios_luf, &dst_folios_luf,
+			put_new_folio, private, ret_folios);
 
 	return rc;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index e42783c02114..d25ae20a47b5 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2600,8 +2600,9 @@  static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
  *
  * Tries to remove all the page table entries which are mapping this folio and
  * replace them with special swap entries. Caller must hold the folio lock.
+ * Return true if all the mappings are read-only, otherwise false.
  */
-void try_to_migrate(struct folio *folio, enum ttu_flags flags)
+bool try_to_migrate(struct folio *folio, enum ttu_flags flags)
 {
 	struct rmap_walk_control rwc = {
 		.rmap_one = try_to_migrate_one,
@@ -2620,11 +2621,11 @@  void try_to_migrate(struct folio *folio, enum ttu_flags flags)
 	 */
 	if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
 					TTU_SYNC | TTU_BATCH_FLUSH)))
-		return;
+		return false;
 
 	if (folio_is_zone_device(folio) &&
 	    (!folio_is_device_private(folio) && !folio_is_device_coherent(folio)))
-		return;
+		return false;
 
 	/*
 	 * During exec, a temporary VMA is setup and later moved.
@@ -2649,6 +2650,8 @@  void try_to_migrate(struct folio *folio, enum ttu_flags flags)
 		fold_ubc(tlb_ubc_luf, tlb_ubc_ro);
 	else
 		fold_ubc(tlb_ubc, tlb_ubc_ro);
+
+	return can_luf;
 }
 
 #ifdef CONFIG_DEVICE_PRIVATE