The patch titled
Subject: mm, page_owner: make init_pages_in_zone() faster
has been added to the -mm tree. Its filename is
mm-page_owner-make-init_pages_in_zone-faster.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-page_owner-make-init_pages_in_zone-faster.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-page_owner-make-init_pages_in_zone-faster.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/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Vlastimil Babka <vbabka@xxxxxxx>
Subject: mm, page_owner: make init_pages_in_zone() faster
In init_pages_in_zone() we currently use the generic set_page_owner()
function to initialize page_owner info for early allocated pages. This
means we needlessly do lookup_page_ext() twice for each page, and more
importantly save_stack(), which has to unwind the stack and find the
corresponding stack depot handle. Because the stack is always the same
for the initialization, unwind it once in init_pages_in_zone() and reuse
the handle. Also avoid the repeated lookup_page_ext().
This can significantly reduce boot times with page_owner=on on large
machines, especially for kernels built without frame pointer, where the
stack unwinding is noticeably slower.
Link: http://lkml.kernel.org/r/20170720134029.25268-2-vbabka@xxxxxxx
Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Yang Shi <yang.shi@xxxxxxxxxx>
Cc: Laura Abbott <labbott@xxxxxxxxxx>
Cc: Vinayak Menon <vinmenon@xxxxxxxxxxxxxx>
Cc: zhong jiang <zhongjiang@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/page_owner.c | 19 ++++++++++++++++++-
1 file changed, 18 insertions(+), 1 deletion(-)
diff -puN mm/page_owner.c~mm-page_owner-make-init_pages_in_zone-faster mm/page_owner.c
--- a/mm/page_owner.c~mm-page_owner-make-init_pages_in_zone-faster
+++ a/mm/page_owner.c
@@ -183,6 +183,20 @@ noinline void __set_page_owner(struct pa
__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
}
+static void __set_page_owner_init(struct page_ext *page_ext,
+ depot_stack_handle_t handle)
+{
+ struct page_owner *page_owner;
+
+ page_owner = get_page_owner(page_ext);
+ page_owner->handle = handle;
+ page_owner->order = 0;
+ page_owner->gfp_mask = 0;
+ page_owner->last_migrate_reason = -1;
+
+ __set_bit(PAGE_EXT_OWNER, &page_ext->flags);
+}
+
void __set_page_owner_migrate_reason(struct page *page, int reason)
{
struct page_ext *page_ext = lookup_page_ext(page);
@@ -520,10 +534,13 @@ static void init_pages_in_zone(pg_data_t
unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
unsigned long end_pfn = pfn + zone->spanned_pages;
unsigned long count = 0;
+ depot_stack_handle_t init_handle;
/* Scan block by block. First and last block may be incomplete */
pfn = zone->zone_start_pfn;
+ init_handle = save_stack(0);
+
/*
* Walk the zone in pageblock_nr_pages steps. If a page block spans
* a zone boundary, it will be double counted between zones. This does
@@ -570,7 +587,7 @@ static void init_pages_in_zone(pg_data_t
continue;
/* Found early allocated page */
- set_page_owner(page, 0, 0);
+ __set_page_owner_init(page_ext, init_handle);
count++;
}
}
_
Patches currently in -mm which might be from vbabka@xxxxxxx are
mm-page_owner-make-init_pages_in_zone-faster.patch
mm-page_ext-periodically-reschedule-during-page_ext_init.patch
mm-page_owner-dont-grab-zone-lock-for-init_pages_in_zone.patch
mm-page_ext-move-page_ext_init-after-page_alloc_init_late.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
