From d381c54760dcfad23743da40516e7e003d73952a Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Fri, 28 Dec 2018 00:33:56 -0800
Subject: [PATCH] mm: only report isolation failures when offlining memory
Git-commit: d381c54760dcfad23743da40516e7e003d73952a
Patch-mainline: v5.0-rc1
References: generic hotplug debugability
Heiko has complained that his log is swamped by warnings from
has_unmovable_pages
[ 20.536664] page dumped because: has_unmovable_pages
[ 20.536792] page:000003d081ff4080 count:1 mapcount:0 mapping:000000008ff88600 index:0x0 compound_mapcount: 0
[ 20.536794] flags: 0x3fffe0000010200(slab|head)
[ 20.536795] raw: 03fffe0000010200 0000000000000100 0000000000000200 000000008ff88600
[ 20.536796] raw: 0000000000000000 0020004100000000 ffffffff00000001 0000000000000000
[ 20.536797] page dumped because: has_unmovable_pages
[ 20.536814] page:000003d0823b0000 count:1 mapcount:0 mapping:0000000000000000 index:0x0
[ 20.536815] flags: 0x7fffe0000000000()
[ 20.536817] raw: 07fffe0000000000 0000000000000100 0000000000000200 0000000000000000
[ 20.536818] raw: 0000000000000000 0000000000000000 ffffffff00000001 0000000000000000
which are not triggered by the memory hotplug but rather CMA allocator.
The original idea behind dumping the page state for all call paths was
that these messages will be helpful debugging failures. From the above it
seems that this is not the case for the CMA path because we are lacking
much more context. E.g the second reported page might be a CMA allocated
page. It is still interesting to see a slab page in the CMA area but it
is hard to tell whether this is bug from the above output alone.
Address this issue by dumping the page state only on request. Both
start_isolate_page_range and has_unmovable_pages already have an argument
to ignore hwpoison pages so make this argument more generic and turn it
into flags and allow callers to combine non-default modes into a mask.
While we are at it, has_unmovable_pages call from
is_pageblock_removable_nolock (sysfs removable file) is questionable to
report the failure so drop it from there as well.
Link: http://lkml.kernel.org/r/20181218092802.31429-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
include/linux/page-isolation.h | 11 +++++++++--
mm/memory_hotplug.c | 3 ++-
mm/page_alloc.c | 13 ++++++-------
mm/page_isolation.c | 10 ++++------
4 files changed, 21 insertions(+), 16 deletions(-)
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -29,8 +29,11 @@ static inline bool is_migrate_isolate(in
}
#endif
+#define SKIP_HWPOISON 0x1
+#define REPORT_FAILURE 0x2
+
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
- int migratetype, bool skip_hwpoisoned_pages);
+ int migratetype, int flags);
void set_pageblock_migratetype(struct page *page, int migratetype);
int move_freepages_block(struct zone *zone, struct page *page,
int migratetype, int *num_movable);
@@ -43,10 +46,14 @@ int move_freepages_block(struct zone *zo
* For isolating all pages in the range finally, the caller have to
* free all pages in the range. test_page_isolated() can be used for
* test it.
+ *
+ * The following flags are allowed (they can be combined in a bit mask)
+ * SKIP_HWPOISON - ignore hwpoison pages
+ * REPORT_FAILURE - report details about the failure to isolate the range
*/
int
start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
- unsigned migratetype, bool skip_hwpoisoned_pages);
+ unsigned migratetype, int flags);
/*
* Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE.
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1769,7 +1769,8 @@ static int __ref __offline_pages(unsigne
/* set above range as isolated */
ret = start_isolate_page_range(start_pfn, end_pfn,
- MIGRATE_MOVABLE, true);
+ MIGRATE_MOVABLE,
+ SKIP_HWPOISON | REPORT_FAILURE);
if (ret) {
reason = "failure to isolate range";
goto failed_removal;
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7383,8 +7383,7 @@ void *__init alloc_large_system_hash(con
* race condition. So you can't expect this function should be exact.
*/
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
- int migratetype,
- bool skip_hwpoisoned_pages)
+ int migratetype, int flags)
{
unsigned long pfn, iter, found;
@@ -7446,7 +7445,7 @@ bool has_unmovable_pages(struct zone *zo
* The HWPoisoned page may be not in buddy system, and
* page_count() is not 0.
*/
- if (skip_hwpoisoned_pages && PageHWPoison(page))
+ if ((flags & SKIP_HWPOISON) && PageHWPoison(page))
continue;
if (__PageMovable(page))
@@ -7472,7 +7471,8 @@ bool has_unmovable_pages(struct zone *zo
}
return false;
unmovable:
- dump_page(pfn_to_page(pfn+iter), "unmovable page");
+ if (flags & REPORT_FAILURE)
+ dump_page(pfn_to_page(pfn+iter), "unmovable page");
return true;
}
@@ -7496,7 +7496,7 @@ bool is_pageblock_removable_nolock(struc
if (!zone_spans_pfn(zone, pfn))
return false;
- return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, true);
+ return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, SKIP_HWPOISON);
}
#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
@@ -7621,8 +7621,7 @@ int alloc_contig_range(unsigned long sta
*/
ret = start_isolate_page_range(pfn_max_align_down(start),
- pfn_max_align_up(end), migratetype,
- false);
+ pfn_max_align_up(end), migratetype, 0);
if (ret)
return ret;
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -14,8 +14,7 @@
#define CREATE_TRACE_POINTS
#include <trace/events/page_isolation.h>
-static int set_migratetype_isolate(struct page *page, int migratetype,
- bool skip_hwpoisoned_pages)
+static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
{
struct zone *zone;
unsigned long flags, pfn;
@@ -51,8 +50,7 @@ static int set_migratetype_isolate(struc
* FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
* We just check MOVABLE pages.
*/
- if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype,
- skip_hwpoisoned_pages))
+ if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype, flags))
ret = 0;
/*
@@ -168,7 +166,7 @@ __first_valid_page(unsigned long pfn, un
* Returns 0 on success and -EBUSY if any part of range cannot be isolated.
*/
int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
- unsigned migratetype, bool skip_hwpoisoned_pages)
+ unsigned migratetype, int flags)
{
unsigned long pfn;
unsigned long undo_pfn;
@@ -182,7 +180,7 @@ int start_isolate_page_range(unsigned lo
pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
if (page &&
- set_migratetype_isolate(page, migratetype, skip_hwpoisoned_pages)) {
+ set_migratetype_isolate(page, migratetype, flags)) {
undo_pfn = pfn;
goto undo;
}