* [PATCH] memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE
@ 2024-10-17 6:44 suhua
2024-10-19 1:57 ` Wei Yang
2024-10-20 7:11 ` Mike Rapoport
0 siblings, 2 replies; 4+ messages in thread
From: suhua @ 2024-10-17 6:44 UTC (permalink / raw)
To: rppt, akpm; +Cc: linux-mm, linux-kernel, suhua.tanke, suhua
Currently when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the reserved
pages are initialized to MIGRATE_MOVABLE by default in memmap_init.
Reserved memory mainly stores the metadata of struct page. When
HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=Y and hugepages are allocated,
the memory occupied by the struct page metadata will be freed.
Before this patch:
when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the freed memory was
placed on the Movable list;
When CONFIG_DEFERRED_STRUCT_PAGE_INIT=Y, the freed memory was placed on
the Unmovable list.
After this patch, the freed memory is placed on the Movable list
regardless of whether CONFIG_DEFERRED_STRUCT_PAGE_INIT is set.
Eg:
echo 500000 > /proc/sys/vm/nr_hugepages
cat /proc/pagetypeinfo
before：
Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
…
Node 0, zone Normal, type Unmovable 51 2 1 28 53 35 35 43 40 69 3852
Node 0, zone Normal, type Movable 6485 4610 666 202 200 185 208 87 54 2 240
Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
Unmovable ≈ 15GB
after：
Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
…
Node 0, zone Normal, type Unmovable 0 1 1 0 0 0 0 1 1 1 0
Node 0, zone Normal, type Movable 1563 4107 1119 189 256 368 286 132 109 4 3841
Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
Signed-off-by: suhua <suhua1@kingsoft.com>
---
mm/mm_init.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 4ba5607aaf19..6dbf2df23eee 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -722,6 +722,10 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
if (zone_spans_pfn(zone, pfn))
break;
}
+
+ if (pageblock_aligned(pfn))
+ set_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE);
+
__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
}
#else
--
2.34.1
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE
2024-10-17 6:44 [PATCH] memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE suhua
@ 2024-10-19 1:57 ` Wei Yang
2024-10-20 7:11 ` Mike Rapoport
1 sibling, 0 replies; 4+ messages in thread
From: Wei Yang @ 2024-10-19 1:57 UTC (permalink / raw)
To: suhua; +Cc: rppt, akpm, linux-mm, linux-kernel, suhua
On Thu, Oct 17, 2024 at 02:44:49PM +0800, suhua wrote:
>Currently when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the reserved
>pages are initialized to MIGRATE_MOVABLE by default in memmap_init.
>
>Reserved memory mainly stores the metadata of struct page. When
>HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=Y and hugepages are allocated,
>the memory occupied by the struct page metadata will be freed.
>
>Before this patch:
>when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the freed memory was
>placed on the Movable list;
>When CONFIG_DEFERRED_STRUCT_PAGE_INIT=Y, the freed memory was placed on
>the Unmovable list.
>
>After this patch, the freed memory is placed on the Movable list
>regardless of whether CONFIG_DEFERRED_STRUCT_PAGE_INIT is set.
>
>Eg:
>echo 500000 > /proc/sys/vm/nr_hugepages
>cat /proc/pagetypeinfo
>
>before：
>Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
>…
>Node 0, zone Normal, type Unmovable 51 2 1 28 53 35 35 43 40 69 3852
>Node 0, zone Normal, type Movable 6485 4610 666 202 200 185 208 87 54 2 240
>Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
>Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
>Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
>Unmovable ≈ 15GB
>
>after：
>Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
>…
>Node 0, zone Normal, type Unmovable 0 1 1 0 0 0 0 1 1 1 0
>Node 0, zone Normal, type Movable 1563 4107 1119 189 256 368 286 132 109 4 3841
>Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
>Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
>Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
>
>Signed-off-by: suhua <suhua1@kingsoft.com>
Looks good to me.
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
>---
> mm/mm_init.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
>diff --git a/mm/mm_init.c b/mm/mm_init.c
>index 4ba5607aaf19..6dbf2df23eee 100644
>--- a/mm/mm_init.c
>+++ b/mm/mm_init.c
>@@ -722,6 +722,10 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
> if (zone_spans_pfn(zone, pfn))
> break;
> }
>+
>+ if (pageblock_aligned(pfn))
>+ set_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE);
>+
> __init_single_page(pfn_to_page(pfn), pfn, zid, nid);
> }
> #else
>--
>2.34.1
>
--
Wei Yang
Help you, Help me
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE
2024-10-17 6:44 [PATCH] memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE suhua
2024-10-19 1:57 ` Wei Yang
@ 2024-10-20 7:11 ` Mike Rapoport
2024-10-21 4:54 ` Su Hua
1 sibling, 1 reply; 4+ messages in thread
From: Mike Rapoport @ 2024-10-20 7:11 UTC (permalink / raw)
To: suhua; +Cc: akpm, linux-mm, linux-kernel, suhua
On Thu, Oct 17, 2024 at 02:44:49PM +0800, suhua wrote:
> Subject: memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE
I'd suggest:
memblock: uniformly initialize all reserved pages to MIGRATE_MOVABLE
> Currently when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the reserved
> pages are initialized to MIGRATE_MOVABLE by default in memmap_init.
>
> Reserved memory mainly stores the metadata of struct page. When
> HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=Y and hugepages are allocated,
> the memory occupied by the struct page metadata will be freed.
The struct page metadata is not freed with HVO, it is rather pages used for
vmemmap.
> Before this patch:
> when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the freed memory was
> placed on the Movable list;
> When CONFIG_DEFERRED_STRUCT_PAGE_INIT=Y, the freed memory was placed on
> the Unmovable list.
>
> After this patch, the freed memory is placed on the Movable list
> regardless of whether CONFIG_DEFERRED_STRUCT_PAGE_INIT is set.
>
> Eg:
Please add back the description of the hardware used for this test and how
much huge pages were allocated at boot.
> echo 500000 > /proc/sys/vm/nr_hugepages
> cat /proc/pagetypeinfo
>
> before：
> Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
> …
> Node 0, zone Normal, type Unmovable 51 2 1 28 53 35 35 43 40 69 3852
> Node 0, zone Normal, type Movable 6485 4610 666 202 200 185 208 87 54 2 240
> Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
> Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
> Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
> Unmovable ≈ 15GB
>
> after：
> Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
> …
> Node 0, zone Normal, type Unmovable 0 1 1 0 0 0 0 1 1 1 0
> Node 0, zone Normal, type Movable 1563 4107 1119 189 256 368 286 132 109 4 3841
> Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
> Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
> Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
>
> Signed-off-by: suhua <suhua1@kingsoft.com>
checkpatch.pl gives this warning:
WARNING: From:/Signed-off-by: email address mismatch: 'From: suhua <suhua.tanke@gmail.com>' != 'Signed-off-by: suhua <suhua1@kingsoft.com>'
Please update the commit authorship or signed-off to match.
Also, Signed-off-by should use a known identity, i.e. Name Lastname.
> ---
> mm/mm_init.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index 4ba5607aaf19..6dbf2df23eee 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -722,6 +722,10 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
> if (zone_spans_pfn(zone, pfn))
> break;
> }
> +
> + if (pageblock_aligned(pfn))
> + set_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE);
> +
> __init_single_page(pfn_to_page(pfn), pfn, zid, nid);
> }
> #else
> --
> 2.34.1
>
--
Sincerely yours,
Mike.
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE
2024-10-20 7:11 ` Mike Rapoport
@ 2024-10-21 4:54 ` Su Hua
0 siblings, 0 replies; 4+ messages in thread
From: Su Hua @ 2024-10-21 4:54 UTC (permalink / raw)
To: Mike Rapoport; +Cc: akpm, linux-mm, linux-kernel, suhua
> On Thu, Oct 17, 2024 at 02:44:49PM +0800, suhua wrote:
> > Subject: memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE
>
> I'd suggest:
>
> memblock: uniformly initialize all reserved pages to MIGRATE_MOVABLE
Thanks for the correction.
> > Currently when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the reserved
> > pages are initialized to MIGRATE_MOVABLE by default in memmap_init.
> >
> > Reserved memory mainly stores the metadata of struct page. When
> > HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=Y and hugepages are allocated,
> > the memory occupied by the struct page metadata will be freed.
>
> The struct page metadata is not freed with HVO, it is rather pages used for
> vmemmap.
Yes, I will update the description.
> > Before this patch:
> > when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the freed memory was
> > placed on the Movable list;
> > When CONFIG_DEFERRED_STRUCT_PAGE_INIT=Y, the freed memory was placed on
> > the Unmovable list.
> >
> > After this patch, the freed memory is placed on the Movable list
> > regardless of whether CONFIG_DEFERRED_STRUCT_PAGE_INIT is set.
> >
> > Eg:
>
> Please add back the description of the hardware used for this test and how
> much huge pages were allocated at boot.
Well, the new patch will add this information.
> > echo 500000 > /proc/sys/vm/nr_hugepages
> > cat /proc/pagetypeinfo
> >
> > before：
> > Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
> > …
> > Node 0, zone Normal, type Unmovable 51 2 1 28 53 35 35 43 40 69 3852
> > Node 0, zone Normal, type Movable 6485 4610 666 202 200 185 208 87 54 2 240
> > Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
> > Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
> > Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
> > Unmovable ≈ 15GB
> >
> > after：
> > Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
> > …
> > Node 0, zone Normal, type Unmovable 0 1 1 0 0 0 0 1 1 1 0
> > Node 0, zone Normal, type Movable 1563 4107 1119 189 256 368 286 132 109 4 3841
> > Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
> > Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
> > Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
> >
> > Signed-off-by: suhua <suhua1@kingsoft.com>
>
> checkpatch.pl gives this warning:
>
> WARNING: From:/Signed-off-by: email address mismatch: 'From: suhua <suhua.tanke@gmail.com>' != 'Signed-off-by: suhua <suhua1@kingsoft.com>'
> Please update the commit authorship or signed-off to match.
>
> Also, Signed-off-by should use a known identity, i.e. Name Lastname.
Oh, this is my oversight.
> > ---
> > mm/mm_init.c | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/mm/mm_init.c b/mm/mm_init.c
> > index 4ba5607aaf19..6dbf2df23eee 100644
> > --- a/mm/mm_init.c
> > +++ b/mm/mm_init.c
> > @@ -722,6 +722,10 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
> > if (zone_spans_pfn(zone, pfn))
> > break;
> > }
> > +
> > + if (pageblock_aligned(pfn))
> > + set_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE);
> > +
> > __init_single_page(pfn_to_page(pfn), pfn, zid, nid);
> > }
> > #else
> > --
> > 2.34.1
> >
Sincerely yours,
Su
Mike Rapoport <rppt@kernel.org> 于2024年10月20日周日 15:15写道：
>
> On Thu, Oct 17, 2024 at 02:44:49PM +0800, suhua wrote:
> > Subject: memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE
>
> I'd suggest:
>
> memblock: uniformly initialize all reserved pages to MIGRATE_MOVABLE
>
> > Currently when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the reserved
> > pages are initialized to MIGRATE_MOVABLE by default in memmap_init.
> >
> > Reserved memory mainly stores the metadata of struct page. When
> > HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=Y and hugepages are allocated,
> > the memory occupied by the struct page metadata will be freed.
>
> The struct page metadata is not freed with HVO, it is rather pages used for
> vmemmap.
>
> > Before this patch:
> > when CONFIG_DEFERRED_STRUCT_PAGE_INIT is not set, the freed memory was
> > placed on the Movable list;
> > When CONFIG_DEFERRED_STRUCT_PAGE_INIT=Y, the freed memory was placed on
> > the Unmovable list.
> >
> > After this patch, the freed memory is placed on the Movable list
> > regardless of whether CONFIG_DEFERRED_STRUCT_PAGE_INIT is set.
> >
> > Eg:
>
> Please add back the description of the hardware used for this test and how
> much huge pages were allocated at boot.
>
> > echo 500000 > /proc/sys/vm/nr_hugepages
> > cat /proc/pagetypeinfo
> >
> > before：
> > Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
> > …
> > Node 0, zone Normal, type Unmovable 51 2 1 28 53 35 35 43 40 69 3852
> > Node 0, zone Normal, type Movable 6485 4610 666 202 200 185 208 87 54 2 240
> > Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
> > Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
> > Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
> > Unmovable ≈ 15GB
> >
> > after：
> > Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
> > …
> > Node 0, zone Normal, type Unmovable 0 1 1 0 0 0 0 1 1 1 0
> > Node 0, zone Normal, type Movable 1563 4107 1119 189 256 368 286 132 109 4 3841
> > Node 0, zone Normal, type Reclaimable 2 2 1 23 13 1 2 1 0 1 0
> > Node 0, zone Normal, type HighAtomic 0 0 0 0 0 0 0 0 0 0 0
> > Node 0, zone Normal, type Isolate 0 0 0 0 0 0 0 0 0 0 0
> >
> > Signed-off-by: suhua <suhua1@kingsoft.com>
>
> checkpatch.pl gives this warning:
>
> WARNING: From:/Signed-off-by: email address mismatch: 'From: suhua <suhua.tanke@gmail.com>' != 'Signed-off-by: suhua <suhua1@kingsoft.com>'
> Please update the commit authorship or signed-off to match.
>
> Also, Signed-off-by should use a known identity, i.e. Name Lastname.
>
> > ---
> > mm/mm_init.c | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/mm/mm_init.c b/mm/mm_init.c
> > index 4ba5607aaf19..6dbf2df23eee 100644
> > --- a/mm/mm_init.c
> > +++ b/mm/mm_init.c
> > @@ -722,6 +722,10 @@ static void __meminit init_reserved_page(unsigned long pfn, int nid)
> > if (zone_spans_pfn(zone, pfn))
> > break;
> > }
> > +
> > + if (pageblock_aligned(pfn))
> > + set_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE);
> > +
> > __init_single_page(pfn_to_page(pfn), pfn, zid, nid);
> > }
> > #else
> > --
> > 2.34.1
> >
>
> --
> Sincerely yours,
> Mike.
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2024-10-21 4:55 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2024-10-17 6:44 [PATCH] memblock: Uniform initialization all reserved pages to MIGRATE_MOVABLE suhua
2024-10-19 1:57 ` Wei Yang
2024-10-20 7:11 ` Mike Rapoport
2024-10-21 4:54 ` Su Hua
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox