Assume we have a crashkernel area of 256MB reserved:
root@vm0:~# cat /proc/iomem
00000000-6fffffff : System RAM
0f258000-0fcfffff : Kernel code
0fd00000-101d10e3 : Kernel data
105b3000-1068dfff : Kernel bss
70000000-7fffffff : Crash kernel
This exactly corresponds to memory block 7 (memory block size is 256MB).
Trying to offline that memory block results in:
root@vm0:~# echo "offline" > /sys/devices/system/memory/memory7/state
-bash: echo: write error: Device or resource busy
[ 128.458762] page:000003d081c00000 refcount:1 mapcount:0 mapping:00000000d01cecd4 index:0x0
[ 128.458773] flags: 0x1ffff00000001000(reserved)
[ 128.458781] raw: 1ffff00000001000 000003d081c00008 000003d081c00008 0000000000000000
[ 128.458781] raw: 0000000000000000 0000000000000000 ffffffff00000001 0000000000000000
[ 128.458783] page dumped because: unmovable page
The craskernel area is marked reserved in the bootmem allocator. This
results in the memmap getting initialized (refcount=1, PG_reserved), but
the pages are never freed to the page allocator.
So these pages look like allocated pages that are unmovable (esp.
PG_reserved), and therefore, memory offlining fails early, when trying to
isolate the page range.
We don't need a special memory notifier and can drop it. Repeating the
above test with this patch results in the same behavior.
Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx>
Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: Philipp Rudo <prudo@xxxxxxxxxxxxx>
Cc: Gerald Schaefer <gerald.schaefer@xxxxxxxxxx>
Cc: Eric W. Biederman <ebiederm@xxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
arch/s390/kernel/setup.c | 33 ---------------------------------
1 file changed, 33 deletions(-)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 0f0b140b5558..95d4fba0d811 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -39,7 +39,6 @@
#include <linux/kernel_stat.h>
#include <linux/dma-contiguous.h>
#include <linux/device.h>
-#include <linux/notifier.h>
#include <linux/pfn.h>
#include <linux/ctype.h>
#include <linux/reboot.h>
@@ -591,35 +590,6 @@ static void __init setup_memory_end(void)
pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
}
-#ifdef CONFIG_CRASH_DUMP
-
-/*
- * When kdump is enabled, we have to ensure that no memory from
- * the area [0 - crashkernel memory size] and
- * [crashk_res.start - crashk_res.end] is set offline.
- */
-static int kdump_mem_notifier(struct notifier_block *nb,
- unsigned long action, void *data)
-{
- struct memory_notify *arg = data;
-
- if (action != MEM_GOING_OFFLINE)
- return NOTIFY_OK;
- if (arg->start_pfn < PFN_DOWN(resource_size(&crashk_res)))
- return NOTIFY_BAD;
- if (arg->start_pfn > PFN_DOWN(crashk_res.end))
- return NOTIFY_OK;
- if (arg->start_pfn + arg->nr_pages - 1 < PFN_DOWN(crashk_res.start))
- return NOTIFY_OK;
- return NOTIFY_BAD;
-}
-
-static struct notifier_block kdump_mem_nb = {
- .notifier_call = kdump_mem_notifier,
-};
-
-#endif
-
/*
* Make sure that the area behind memory_end is protected
*/
@@ -703,9 +673,6 @@ static void __init reserve_crashkernel(void)
return;
}
- if (register_memory_notifier(&kdump_mem_nb))
- return;
-
if (!OLDMEM_BASE && MACHINE_IS_VM)
diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
crashk_res.start = crash_base;
--
2.25.3
