[PATCH 5.4 170/261] mm: initialize deferred pages with interrupts enabled

From: Greg Kroah-Hartman
Date: Fri Jun 19 2020 - 11:12:15 EST


From: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>

commit 3d060856adfc59afb9d029c233141334cfaba418 upstream.

Initializing struct pages is a long task and keeping interrupts disabled
for the duration of this operation introduces a number of problems.

1. jiffies are not updated for long period of time, and thus incorrect time
is reported. See proposed solution and discussion here:
lkml/20200311123848.118638-1-shile.zhang@xxxxxxxxxxxxxxxxx
2. It prevents farther improving deferred page initialization by allowing
intra-node multi-threading.

We are keeping interrupts disabled to solve a rather theoretical problem
that was never observed in real world (See 3a2d7fa8a3d5).

Let's keep interrupts enabled. In case we ever encounter a scenario where
an interrupt thread wants to allocate large amount of memory this early in
boot we can deal with that by growing zone (see deferred_grow_zone()) by
the needed amount before starting deferred_init_memmap() threads.

Before:
[ 1.232459] node 0 initialised, 12058412 pages in 1ms

After:
[ 1.632580] node 0 initialised, 12051227 pages in 436ms

Fixes: 3a2d7fa8a3d5 ("mm: disable interrupts while initializing deferred pages")
Reported-by: Shile Zhang <shile.zhang@xxxxxxxxxxxxxxxxx>
Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: James Morris <jmorris@xxxxxxxxx>
Cc: Kirill Tkhai <ktkhai@xxxxxxxxxxxxx>
Cc: Sasha Levin <sashal@xxxxxxxxxx>
Cc: Yiqian Wei <yiwei@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [4.17+]
Link: http://lkml.kernel.org/r/20200403140952.17177-3-pasha.tatashin@xxxxxxxxxx
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
include/linux/mmzone.h | 2 ++
mm/page_alloc.c | 20 +++++++-------------
2 files changed, 9 insertions(+), 13 deletions(-)

--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -709,6 +709,8 @@ typedef struct pglist_data {
/*
* Must be held any time you expect node_start_pfn,
* node_present_pages, node_spanned_pages or nr_zones to stay constant.
+ * Also synchronizes pgdat->first_deferred_pfn during deferred page
+ * init.
*
* pgdat_resize_lock() and pgdat_resize_unlock() are provided to
* manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1793,6 +1793,13 @@ static int __init deferred_init_memmap(v
BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
pgdat->first_deferred_pfn = ULONG_MAX;

+ /*
+ * Once we unlock here, the zone cannot be grown anymore, thus if an
+ * interrupt thread must allocate this early in boot, zone must be
+ * pre-grown prior to start of deferred page initialization.
+ */
+ pgdat_resize_unlock(pgdat, &flags);
+
/* Only the highest zone is deferred so find it */
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
zone = pgdat->node_zones + zid;
@@ -1813,8 +1820,6 @@ static int __init deferred_init_memmap(v
while (spfn < epfn)
nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
zone_empty:
- pgdat_resize_unlock(pgdat, &flags);
-
/* Sanity check that the next zone really is unpopulated */
WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));

@@ -1857,17 +1862,6 @@ deferred_grow_zone(struct zone *zone, un
pgdat_resize_lock(pgdat, &flags);

/*
- * If deferred pages have been initialized while we were waiting for
- * the lock, return true, as the zone was grown. The caller will retry
- * this zone. We won't return to this function since the caller also
- * has this static branch.
- */
- if (!static_branch_unlikely(&deferred_pages)) {
- pgdat_resize_unlock(pgdat, &flags);
- return true;
- }
-
- /*
* If someone grew this zone while we were waiting for spinlock, return
* true, as there might be enough pages already.
*/