The patch titled
Subject: mm/page_alloc: reuse tail struct pages for compound devmaps
has been added to the -mm tree. Its filename is
mm-page_alloc-reuse-tail-struct-pages-for-compound-devmaps.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-page_alloc-reuse-tail-struct-pages-for-compound-devmaps.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-page_alloc-reuse-tail-struct-pages-for-compound-devmaps.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: Joao Martins <joao.m.martins@xxxxxxxxxx>
Subject: mm/page_alloc: reuse tail struct pages for compound devmaps
Currently memmap_init_zone_device() ends up initializing 32768 pages when
it only needs to initialize 128 given tail page reuse. That number is
worse with 1GB compound pages, 262144 instead of 128. Update
memmap_init_zone_device() to skip redundant initialization, detailed
below.
When a pgmap @vmemmap_shift is set, all pages are mapped at a given huge
page alignment and use compound pages to describe them as opposed to a
struct per 4K.
With @vmemmap_shift > 0 and when struct pages are stored in ram (!altmap)
most tail pages are reused. Consequently, the amount of unique struct
pages is a lot smaller that the total amount of struct pages being mapped.
The altmap path is left alone since it does not support memory savings
based on compound pages devmap.
Link: https://lkml.kernel.org/r/20220223194807.12070-6-joao.m.martins@xxxxxxxxxx
Signed-off-by: Joao Martins <joao.m.martins@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Jane Chu <jane.chu@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/page_alloc.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
--- a/mm/page_alloc.c~mm-page_alloc-reuse-tail-struct-pages-for-compound-devmaps
+++ a/mm/page_alloc.c
@@ -6622,6 +6622,20 @@ static void __ref __init_zone_device_pag
}
}
+/*
+ * With compound page geometry and when struct pages are stored in ram most
+ * tail pages are reused. Consequently, the amount of unique struct pages to
+ * initialize is a lot smaller that the total amount of struct pages being
+ * mapped. This is a paired / mild layering violation with explicit knowledge
+ * of how the sparse_vmemmap internals handle compound pages in the lack
+ * of an altmap. See vmemmap_populate_compound_pages().
+ */
+static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
+ unsigned long nr_pages)
+{
+ return !altmap ? 2 * (PAGE_SIZE/sizeof(struct page)) : nr_pages;
+}
+
static void __ref memmap_init_compound(struct page *head,
unsigned long head_pfn,
unsigned long zone_idx, int nid,
@@ -6686,7 +6700,7 @@ void __ref memmap_init_zone_device(struc
continue;
memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
- pfns_per_compound);
+ compound_nr_pages(altmap, pfns_per_compound));
}
pr_info("%s initialised %lu pages in %ums\n", __func__,
_
Patches currently in -mm which might be from joao.m.martins@xxxxxxxxxx are
mm-sparse-vmemmap-add-a-pgmap-argument-to-section-activation.patch
mm-sparse-vmemmap-refactor-core-of-vmemmap_populate_basepages-to-helper.patch
mm-hugetlb_vmemmap-move-comment-block-to-documentation-vm.patch
mm-sparse-vmemmap-improve-memory-savings-for-compound-devmaps.patch
mm-page_alloc-reuse-tail-struct-pages-for-compound-devmaps.patch
