vmscan: add a vmscan event for reclaim_pages

reclaim_folio_list uses a dummy reclaim_stat and is not being used.  To
know the memory stat, add a new trace event.  This is useful how how many
pages are not reclaimed or why.

This is an example:

mm_vmscan_reclaim_pages: nid=0 nr_scanned=112 nr_reclaimed=112 nr_dirty=0 nr_writeback=0 nr_congested=0 nr_immediate=0 nr_activate_anon=0 nr_activate_file=0 nr_ref_keep=0 nr_unmap_fail=0

Currently reclaim_folio_list is only called by reclaim_pages, and
reclaim_pages is used by damon and madvise.  In the latest Android,
reclaim_pages is also used by shmem to reclaim all pages in a
address_space.

Link: https://lkml.kernel.org/r/20241011124928.1224813-1-jaewon31.kim@samsung.com
Signed-off-by: Jaewon Kim <jaewon31.kim@samsung.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Jaewon Kim <jaewon31.kim@samsung.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 1a488c30afa5343cb47d41d9d0f43d5a6e62d424..490958fa10deed4f62df64e485fa515fc20f07b8 100644 (file)
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -346,6 +346,51 @@ TRACE_EVENT(mm_vmscan_write_folio,
                show_reclaim_flags(__entry->reclaim_flags))
 );
 
+TRACE_EVENT(mm_vmscan_reclaim_pages,
+
+       TP_PROTO(int nid,
+               unsigned long nr_scanned, unsigned long nr_reclaimed,
+               struct reclaim_stat *stat),
+
+       TP_ARGS(nid, nr_scanned, nr_reclaimed, stat),
+
+       TP_STRUCT__entry(
+               __field(int, nid)
+               __field(unsigned long, nr_scanned)
+               __field(unsigned long, nr_reclaimed)
+               __field(unsigned long, nr_dirty)
+               __field(unsigned long, nr_writeback)
+               __field(unsigned long, nr_congested)
+               __field(unsigned long, nr_immediate)
+               __field(unsigned int, nr_activate0)
+               __field(unsigned int, nr_activate1)
+               __field(unsigned long, nr_ref_keep)
+               __field(unsigned long, nr_unmap_fail)
+       ),
+
+       TP_fast_assign(
+               __entry->nid = nid;
+               __entry->nr_scanned = nr_scanned;
+               __entry->nr_reclaimed = nr_reclaimed;
+               __entry->nr_dirty = stat->nr_dirty;
+               __entry->nr_writeback = stat->nr_writeback;
+               __entry->nr_congested = stat->nr_congested;
+               __entry->nr_immediate = stat->nr_immediate;
+               __entry->nr_activate0 = stat->nr_activate[0];
+               __entry->nr_activate1 = stat->nr_activate[1];
+               __entry->nr_ref_keep = stat->nr_ref_keep;
+               __entry->nr_unmap_fail = stat->nr_unmap_fail;
+       ),
+
+       TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld",
+               __entry->nid,
+               __entry->nr_scanned, __entry->nr_reclaimed,
+               __entry->nr_dirty, __entry->nr_writeback,
+               __entry->nr_congested, __entry->nr_immediate,
+               __entry->nr_activate0, __entry->nr_activate1,
+               __entry->nr_ref_keep, __entry->nr_unmap_fail)
+);
+
 TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 
        TP_PROTO(int nid,

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6a3c498383fa102388489d28bb988d922f7d6d9b..6d0739cb1873308e43cea4c7ac5e38aa5a4840a6 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2127,9 +2127,10 @@ static void shrink_active_list(unsigned long nr_to_scan,
 }
 
 static unsigned int reclaim_folio_list(struct list_head *folio_list,
+                                     unsigned int nr_scanned,
                                      struct pglist_data *pgdat)
 {
-       struct reclaim_stat dummy_stat;
+       struct reclaim_stat stat;
        unsigned int nr_reclaimed;
        struct folio *folio;
        struct scan_control sc = {
@@ -2140,12 +2141,13 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
                .no_demotion = 1,
        };
 
-       nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, true);
+       nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &stat, true);
        while (!list_empty(folio_list)) {
                folio = lru_to_folio(folio_list);
                list_del(&folio->lru);
                folio_putback_lru(folio);
        }
+       trace_mm_vmscan_reclaim_pages(pgdat->node_id, nr_scanned, nr_reclaimed, &stat);
 
        return nr_reclaimed;
 }
@@ -2153,6 +2155,7 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list,
 unsigned long reclaim_pages(struct list_head *folio_list)
 {
        int nid;
+       unsigned int nr_scanned = 0;
        unsigned int nr_reclaimed = 0;
        LIST_HEAD(node_folio_list);
        unsigned int noreclaim_flag;
@@ -2169,15 +2172,18 @@ unsigned long reclaim_pages(struct list_head *folio_list)
                if (nid == folio_nid(folio)) {
                        folio_clear_active(folio);
                        list_move(&folio->lru, &node_folio_list);
+                       nr_scanned += folio_nr_pages(folio);
                        continue;
                }
 
-               nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
+               nr_reclaimed += reclaim_folio_list(&node_folio_list, nr_scanned,
+                                                  NODE_DATA(nid));
+               nr_scanned = 0;
                nid = folio_nid(lru_to_folio(folio_list));
        } while (!list_empty(folio_list));
 
-       nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid));
-
+       nr_reclaimed += reclaim_folio_list(&node_folio_list, nr_scanned,
+                                          NODE_DATA(nid));
        memalloc_noreclaim_restore(noreclaim_flag);
 
        return nr_reclaimed;