Commit 98b211d6415f ("madvise: convert madvise_free_pte_range() to use a
folio") replaced the page_mapcount() with folio_mapcount() to check
whether the folio is shared by other mapping.
It's not correct for large folios. folio_mapcount() returns the total
mapcount of large folio which is not suitable to detect whether the folio
is shared.
Use folio_estimated_sharers() which returns a estimated number of shares.
That means it's not 100% correct. It should be OK for madvise case here.
User-visible effects is that the THP is skipped when user call madvise.
But the correct behavior is THP should be split and processed then.
NOTE: this change is a temporary fix to reduce the user-visible effects
before the long term fix from David is ready.
Link: https://lkml.kernel.org/r/20230808020917.2230692-4-fengwei.yin@xxxxxxxxx
Fixes: 98b211d6415f ("madvise: convert madvise_free_pte_range() to use a folio")
Signed-off-by: Yin Fengwei <fengwei.yin@xxxxxxxxx>
Reviewed-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Reviewed-by: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Vishal Moola (Oracle) <vishal.moola@xxxxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
(cherry picked from commit 0e0e9bd5f7b9d40fd03b70092367247d52da1db0)
---
include/linux/mm.h | 19 +++++++++++++++++++
mm/madvise.c | 4 ++--
2 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b8ed44f401b5..983ae8b31e31 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1727,6 +1727,25 @@ static inline size_t folio_size(struct folio *folio)
return PAGE_SIZE << folio_order(folio);
}
+/**
+ * folio_estimated_sharers - Estimate the number of sharers of a folio.
+ * @folio: The folio.
+ *
+ * folio_estimated_sharers() aims to serve as a function to efficiently
+ * estimate the number of processes sharing a folio. This is done by
+ * looking at the precise mapcount of the first subpage in the folio, and
+ * assuming the other subpages are the same. This may not be true for large
+ * folios. If you want exact mapcounts for exact calculations, look at
+ * page_mapcount() or folio_total_mapcount().
+ *
+ * Return: The estimated number of processes sharing a folio.
+ */
+static inline int folio_estimated_sharers(struct folio *folio)
+{
+ return page_mapcount(folio_page(folio, 0));
+}
+
+
#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
static inline int arch_make_page_accessible(struct page *page)
{
diff --git a/mm/madvise.c b/mm/madvise.c
index d03e149ffe6e..5973399b2f9b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -654,8 +654,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
* deactivate all pages.
*/
if (folio_test_large(folio)) {
- if (folio_mapcount(folio) != 1)
- goto out;
+ if (folio_estimated_sharers(folio) != 1)
+ break;
folio_get(folio);
if (!folio_trylock(folio)) {
folio_put(folio);
--
2.39.2
