Reading a sysfs "memoryN/valid_zones" file leads to the following oops
when the first page of a range is not backed by struct page.
show_valid_zones() assumes that 'start_pfn' is always valid for
page_zone().
BUG: unable to handle kernel paging request at ffffea017a000000
IP: show_valid_zones+0x6f/0x160
This issue may happen on x86-64 systems with 64GiB or more memory since
their memory block size is bumped up to 2GiB. [1] An example of such
systems is desribed below. 0x3240000000 is only aligned by 1GiB and
this memory block starts from 0x3200000000, which is not backed by
struct page.
BIOS-e820: [mem 0x0000003240000000-0x000000603fffffff] usable
Since test_pages_in_a_zone() already checks holes, fix this issue by
extending this function to return 'valid_start' and 'valid_end' for a
given range. show_valid_zones() then proceeds with the valid range.
[1] 'Commit bdee237c0343 ("x86: mm: Use 2GB memory block size on
large-memory x86-64 systems")'
Link: http://lkml.kernel.org/r/20170127222149.30893-3-toshi.kani@xxxxxxx
Signed-off-by: Toshi Kani <toshi.kani@xxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Zhang Zhen <zhenzhang.zhang@xxxxxxxxxx>
Cc: Reza Arbab <arbab@xxxxxxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [4.4+]
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
---
This patch backports commit a96dfddbcc to 4.4. This is 2/2 of patch-set.
The 1/2 patch is commit deb88a2a19e that applies/has applied cleanly to 4.4.
Link: http://www.spinics.net/lists/stable/msg158242.html
---
drivers/base/memory.c | 11 +++++------
include/linux/memory_hotplug.h | 3 ++-
mm/memory_hotplug.c | 20 +++++++++++++++-----
3 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 213456c..3805279 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -388,30 +388,29 @@ static ssize_t show_valid_zones(struct device *dev,
{
struct memory_block *mem = to_memory_block(dev);
unsigned long start_pfn, end_pfn;
+ unsigned long valid_start, valid_end;
unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
- struct page *first_page;
struct zone *zone;
start_pfn = section_nr_to_pfn(mem->start_section_nr);
end_pfn = start_pfn + nr_pages;
- first_page = pfn_to_page(start_pfn);
/* The block contains more than one zone can not be offlined. */
- if (!test_pages_in_a_zone(start_pfn, end_pfn))
+ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
return sprintf(buf, "none\n");
- zone = page_zone(first_page);
+ zone = page_zone(pfn_to_page(valid_start));
if (zone_idx(zone) == ZONE_MOVABLE - 1) {
/*The mem block is the last memoryblock of this zone.*/
- if (end_pfn == zone_end_pfn(zone))
+ if (valid_end == zone_end_pfn(zone))
return sprintf(buf, "%s %s\n",
zone->name, (zone + 1)->name);
}
if (zone_idx(zone) == ZONE_MOVABLE) {
/*The mem block is the first memoryblock of ZONE_MOVABLE.*/
- if (start_pfn == zone->zone_start_pfn)
+ if (valid_start == zone->zone_start_pfn)
return sprintf(buf, "%s %s\n",
zone->name, (zone - 1)->name);
}
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 4340599..04f5b7a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -85,7 +85,8 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
/* VM interface that may be used by firmware interface */
extern int online_pages(unsigned long, unsigned long, int);
-extern int test_pages_in_a_zone(unsigned long, unsigned long);
+extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long *valid_start, unsigned long *valid_end);
extern void __offline_isolated_pages(unsigned long, unsigned long);
typedef void (*online_page_callback_t)(struct page *page);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index fb9fed4..dd74825 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1402,10 +1402,13 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
/*
* Confirm all pages in a range [start, end) belong to the same zone.
+ * When true, return its valid [start, end).
*/
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long *valid_start, unsigned long *valid_end)
{
unsigned long pfn, sec_end_pfn;
+ unsigned long start, end;
struct zone *zone = NULL;
struct page *page;
int i;
@@ -1427,14 +1430,20 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
page = pfn_to_page(pfn + i);
if (zone && page_zone(page) != zone)
return 0;
+ if (!zone)
+ start = pfn + i;
zone = page_zone(page);
+ end = pfn + MAX_ORDER_NR_PAGES;
}
}
- if (zone)
+ if (zone) {
+ *valid_start = start;
+ *valid_end = end;
return 1;
- else
+ } else {
return 0;
+ }
}
/*
@@ -1752,6 +1761,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
long offlined_pages;
int ret, drain, retry_max, node;
unsigned long flags;
+ unsigned long valid_start, valid_end;
struct zone *zone;
struct memory_notify arg;
@@ -1762,10 +1772,10 @@ static int __ref __offline_pages(unsigned long start_pfn,
return -EINVAL;
/* This makes hotplug much easier...and readable.
we assume this for now. .*/
- if (!test_pages_in_a_zone(start_pfn, end_pfn))
+ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
return -EINVAL;
- zone = page_zone(pfn_to_page(start_pfn));
+ zone = page_zone(pfn_to_page(valid_start));
node = zone_to_nid(zone);
nr_pages = end_pfn - start_pfn;
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html