The patch titled Subject: mm/rmap.c: reuse mergeable anon_vma as parent when forking has been added to the -mm tree. Its filename is mm-rmapc-reuse-mergeable-anon_vma-as-parent-when-fork.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/mm-rmapc-reuse-mergeable-anon_vma-as-parent-when-fork.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/mm-rmapc-reuse-mergeable-anon_vma-as-parent-when-fork.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Wei Yang <richardw.yang@xxxxxxxxxxxxxxx> Subject: mm/rmap.c: reuse mergeable anon_vma as parent when forking In function __anon_vma_prepare(), we will try to find anon_vma if it is possible to reuse it. While on fork, the logic is different. Since commit 5beb49305251 ("mm: change anon_vma linking to fix multi-process server scalability issue"), function anon_vma_clone() tries to allocate new anon_vma for child process. But the logic here will allocate a new anon_vma for each vma, even in parent this vma is mergeable and share the same anon_vma with its sibling. This may do better for scalability issue, while it is not necessary to do so especially after interval tree is used. Commit 7a3ef208e662 ("mm: prevent endless growth of anon_vma hierarchy") tries to reuse some anon_vma by counting child anon_vma and attached vmas. While for those mergeable anon_vmas, we can just reuse it and not necessary to go through the logic. After this change, kernel build test reduces 20% anon_vma allocation. Do the same kernel build test and record time: Original real 2m50.467s user 17m52.002s sys 1m51.953s real 2m48.662s user 17m55.464s sys 1m50.553s real 2m51.143s user 17m59.687s sys 1m53.600s Patched real 2m43.733s user 17m25.705s sys 1m41.791s real 2m47.146s user 17m47.451s sys 1m43.474s real 2m45.763s user 17m38.230s sys 1m42.102s System time is reduced by 8.5%. Link: http://lkml.kernel.org/r/20191004160632.30251-1-richardw.yang@xxxxxxxxxxxxxxx Signed-off-by: Wei Yang <richardw.yang@xxxxxxxxxxxxxxx> Acked-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx> Acked-by: Rik van Riel <riel@xxxxxxxxxxx> Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/rmap.c | 11 +++++++++++ 1 file changed, 11 insertions(+) --- a/mm/rmap.c~mm-rmapc-reuse-mergeable-anon_vma-as-parent-when-fork +++ a/mm/rmap.c @@ -262,6 +262,17 @@ int anon_vma_clone(struct vm_area_struct { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; + struct vm_area_struct *prev = dst->vm_prev, *pprev = src->vm_prev; + + /* + * If parent share anon_vma with its vm_prev, keep this sharing in in + * child. + * + * 1. Parent has vm_prev, which implies we have vm_prev. + * 2. Parent and its vm_prev have the same anon_vma. + */ + if (pprev && pprev->anon_vma == src->anon_vma) + dst->anon_vma = prev->anon_vma; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; _ Patches currently in -mm which might be from richardw.yang@xxxxxxxxxxxxxxx are mm-fix-typo-in-the-comment-when-calling-function-__setpageuptodate.patch mm-mmapc-remove-a-never-trigger-warning-in-__vma_adjust.patch mm-rmapc-reuse-mergeable-anon_vma-as-parent-when-fork.patch hugetlb-remove-unused-hstate-in-hugetlb_fault_mutex_hash.patch userfaultfd-use-vma_pagesize-for-all-huge-page-size-calculation.patch userfaultfd-remove-unnecessary-warn_on-in-__mcopy_atomic_hugetlb.patch userfaultfd-wrap-the-common-dst_vma-check-into-an-inlined-function.patch