The patch titled
Subject: mm/vmalloc: make show_numa_info() aware of hugepage mappings
has been removed from the -mm tree. Its filename was
mm-vmalloc-make-show_numa_info-aware-of-hugepage-mappings.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Eric Dumazet <edumazet@xxxxxxxxxx>
Subject: mm/vmalloc: make show_numa_info() aware of hugepage mappings
show_numa_info() can be slightly faster, by skipping over hugepages
directly.
Link: https://lkml.kernel.org/r/20211001172725.105824-1-eric.dumazet@xxxxxxxxx
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Cc: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/vmalloc.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
--- a/mm/vmalloc.c~mm-vmalloc-make-show_numa_info-aware-of-hugepage-mappings
+++ a/mm/vmalloc.c
@@ -3864,6 +3864,7 @@ static void show_numa_info(struct seq_fi
{
if (IS_ENABLED(CONFIG_NUMA)) {
unsigned int nr, *counters = m->private;
+ unsigned int step = 1U << vm_area_page_order(v);
if (!counters)
return;
@@ -3875,9 +3876,8 @@ static void show_numa_info(struct seq_fi
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
- for (nr = 0; nr < v->nr_pages; nr++)
- counters[page_to_nid(v->pages[nr])]++;
-
+ for (nr = 0; nr < v->nr_pages; nr += step)
+ counters[page_to_nid(v->pages[nr])] += step;
for_each_node_state(nr, N_HIGH_MEMORY)
if (counters[nr])
seq_printf(m, " N%u=%u", nr, counters[nr]);
_
Patches currently in -mm which might be from edumazet@xxxxxxxxxx are
