mm/vmstat: add events for THP migration without split

Add following new vmstat events which will help in validating THP
migration without split.  Statistics reported through these new VM events
will help in performance debugging.

1. THP_MIGRATION_SUCCESS
2. THP_MIGRATION_FAILURE
3. THP_MIGRATION_SPLIT

In addition, these new events also update normal page migration statistics
appropriately via PGMIGRATE_SUCCESS and PGMIGRATE_FAILURE.  While here,
this updates current trace event 'mm_migrate_pages' to accommodate now
available THP statistics.

[[email protected]: s/hpage_nr_pages/thp_nr_pages/]
[[email protected]: v2]
  Link: http://lkml.kernel.org/r/[email protected]
[[email protected]: s/thp_nr_pages/hpage_nr_pages/]
  Link: http://lkml.kernel.org/r/[email protected]

Signed-off-by: Anshuman Khandual <[email protected]>
Signed-off-by: Zi Yan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Reviewed-by: Daniel Jordan <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: John Hubbard <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/vm/page_migration.rst

@@ -253,5 +253,32 @@ which are function pointers of struct address_space_operations.
      PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag
      for own purpose.
 
+Monitoring Migration
+=====================
+
+The following events (counters) can be used to monitor page migration.
+
+1. PGMIGRATE_SUCCESS: Normal page migration success. Each count means that a
+   page was migrated. If the page was a non-THP page, then this counter is
+   increased by one. If the page was a THP, then this counter is increased by
+   the number of THP subpages. For example, migration of a single 2MB THP that
+   has 4KB-size base pages (subpages) will cause this counter to increase by
+   512.
+
+2. PGMIGRATE_FAIL: Normal page migration failure. Same counting rules as for
+   _SUCCESS, above: this will be increased by the number of subpages, if it was
+   a THP.
+
+3. THP_MIGRATION_SUCCESS: A THP was migrated without being split.
+
+4. THP_MIGRATION_FAIL: A THP could not be migrated nor it could be split.
+
+5. THP_MIGRATION_SPLIT: A THP was migrated, but not as such: first, the THP had
+   to be split. After splitting, a migration retry was used for it's sub-pages.
+
+THP_MIGRATION_* events also update the appropriate PGMIGRATE_SUCCESS or
+PGMIGRATE_FAIL events. For example, a THP migration failure will cause both
+THP_MIGRATION_FAIL and PGMIGRATE_FAIL to increase.
+
 Christoph Lameter, May 8, 2006.
 Minchan Kim, Mar 28, 2016.

include/linux/vm_event_item.h

@@ -56,6 +56,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
+		THP_MIGRATION_SUCCESS,
+		THP_MIGRATION_FAIL,
+		THP_MIGRATION_SPLIT,
 #endif
 #ifdef CONFIG_COMPACTION
 		COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,

include/trace/events/migrate.h

@@ -46,27 +46,38 @@ MIGRATE_REASON
 TRACE_EVENT(mm_migrate_pages,
 
 	TP_PROTO(unsigned long succeeded, unsigned long failed,
-		 enum migrate_mode mode, int reason),
+		 unsigned long thp_succeeded, unsigned long thp_failed,
+		 unsigned long thp_split, enum migrate_mode mode, int reason),
 
-	TP_ARGS(succeeded, failed, mode, reason),
+	TP_ARGS(succeeded, failed, thp_succeeded, thp_failed,
+		thp_split, mode, reason),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,		succeeded)
 		__field(	unsigned long,		failed)
+		__field(	unsigned long,		thp_succeeded)
+		__field(	unsigned long,		thp_failed)
+		__field(	unsigned long,		thp_split)
 		__field(	enum migrate_mode,	mode)
 		__field(	int,			reason)
 	),
 
 	TP_fast_assign(
 		__entry->succeeded	= succeeded;
 		__entry->failed		= failed;
+		__entry->thp_succeeded	= thp_succeeded;
+		__entry->thp_failed	= thp_failed;
+		__entry->thp_split	= thp_split;
 		__entry->mode		= mode;
 		__entry->reason		= reason;
 	),
 
-	TP_printk("nr_succeeded=%lu nr_failed=%lu mode=%s reason=%s",
+	TP_printk("nr_succeeded=%lu nr_failed=%lu nr_thp_succeeded=%lu nr_thp_failed=%lu nr_thp_split=%lu mode=%s reason=%s",
 		__entry->succeeded,
 		__entry->failed,
+		__entry->thp_succeeded,
+		__entry->thp_failed,
+		__entry->thp_split,
 		__print_symbolic(__entry->mode, MIGRATE_MODE),
 		__print_symbolic(__entry->reason, MIGRATE_REASON))
 );

mm/migrate.c

@@ -1418,22 +1418,35 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 		enum migrate_mode mode, int reason)
 {
 	int retry = 1;
+	int thp_retry = 1;
 	int nr_failed = 0;
 	int nr_succeeded = 0;
+	int nr_thp_succeeded = 0;
+	int nr_thp_failed = 0;
+	int nr_thp_split = 0;
 	int pass = 0;
+	bool is_thp = false;
 	struct page *page;
 	struct page *page2;
 	int swapwrite = current->flags & PF_SWAPWRITE;
-	int rc;
+	int rc, nr_subpages;
 
 	if (!swapwrite)
 		current->flags |= PF_SWAPWRITE;
 
-	for(pass = 0; pass < 10 && retry; pass++) {
+	for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
 		retry = 0;
+		thp_retry = 0;
 
 		list_for_each_entry_safe(page, page2, from, lru) {
 retry:
+			/*
+			 * THP statistics is based on the source huge page.
+			 * Capture required information that might get lost
+			 * during migration.
+			 */
+			is_thp = PageTransHuge(page);
+			nr_subpages = hpage_nr_pages(page);
 			cond_resched();
 
 			if (PageHuge(page))
@@ -1464,15 +1477,30 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 					unlock_page(page);
 					if (!rc) {
 						list_safe_reset_next(page, page2, lru);
+						nr_thp_split++;
 						goto retry;
 					}
 				}
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					goto out;
+				}
 				nr_failed++;
 				goto out;
 			case -EAGAIN:
+				if (is_thp) {
+					thp_retry++;
+					break;
+				}
 				retry++;
 				break;
 			case MIGRATEPAGE_SUCCESS:
+				if (is_thp) {
+					nr_thp_succeeded++;
+					nr_succeeded += nr_subpages;
+					break;
+				}
 				nr_succeeded++;
 				break;
 			default:
@@ -1482,19 +1510,27 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 				 * removed from migration page list and not
 				 * retried in the next outer loop.
 				 */
+				if (is_thp) {
+					nr_thp_failed++;
+					nr_failed += nr_subpages;
+					break;
+				}
 				nr_failed++;
 				break;
 			}
 		}
 	}
-	nr_failed += retry;
+	nr_failed += retry + thp_retry;
+	nr_thp_failed += thp_retry;
 	rc = nr_failed;
 out:
-	if (nr_succeeded)
-		count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
-	if (nr_failed)
-		count_vm_events(PGMIGRATE_FAIL, nr_failed);
-	trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason);
+	count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
+	count_vm_events(PGMIGRATE_FAIL, nr_failed);
+	count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
+	count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed);
+	count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split);
+	trace_mm_migrate_pages(nr_succeeded, nr_failed, nr_thp_succeeded,
+			       nr_thp_failed, nr_thp_split, mode, reason);
 
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;

mm/vmstat.c

@@ -1277,6 +1277,9 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",
 	"pgmigrate_fail",
+	"thp_migration_success",
+	"thp_migration_fail",
+	"thp_migration_split",
 #endif
 #ifdef CONFIG_COMPACTION
 	"compact_migrate_scanned",