]> www.infradead.org Git - users/hch/dma-mapping.git/commit
mm: khugepaged: fix the incorrect statistics when collapsing large file folios
authorBaolin Wang <baolin.wang@linux.alibaba.com>
Mon, 14 Oct 2024 10:24:44 +0000 (18:24 +0800)
committerAndrew Morton <akpm@linux-foundation.org>
Thu, 17 Oct 2024 07:28:10 +0000 (00:28 -0700)
commitd60fcaf00d752c52fdf566d4184e6d04d9d08879
tree96fb13f785b37347d6f27f61b6e0527f0ca8fcd5
parent22ff9b0ff11a762852cd620972f265b3129e3fe7
mm: khugepaged: fix the incorrect statistics when collapsing large file folios

Khugepaged already supports collapsing file large folios (including shmem
mTHP) by commit 7de856ffd007 ("mm: khugepaged: support shmem mTHP
collapse"), and the control parameters in khugepaged:
'khugepaged_max_ptes_swap' and 'khugepaged_max_ptes_none', still compare
based on PTE granularity to determine whether a file collapse is needed.
However, the statistics for 'present' and 'swap' in
hpage_collapse_scan_file() do not take into account the large folios,
which may lead to incorrect judgments regarding the
khugepaged_max_ptes_swap/none parameters, resulting in unnecessary file
collapses.

To fix this issue, take into account the large folios' statistics for
'present' and 'swap' variables in the hpage_collapse_scan_file().

Link: https://lkml.kernel.org/r/c76305d96d12d030a1a346b50503d148364246d2.1728901391.git.baolin.wang@linux.alibaba.com
Fixes: 7de856ffd007 ("mm: khugepaged: support shmem mTHP collapse")
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
mm/khugepaged.c