When booting a kexec/kdump kernel on a system that has specific memory hotplug
regions the boot will fail with warnings like:
[ 2.939467] swapper/0: page allocation failure: order:9, mode:0x84d0
[ 2.946564] CPU: 0 PID: 1 Comm: swapper/0 Not tainted
3.10.0-65.el7.x86_64 #1
[ 2.954532] Hardware name: QCI QSSC-S4R/QSSC-S4R, BIOS
QSSC-S4R.QCI.01.00.S013.032920111005 03/29/2011
[ 2.964926] 0000000000000000 ffff8800341bd8c8 ffffffff815bcc67
ffff8800341bd950
[ 2.973224] ffffffff8113b1a0 ffff880036339b00 0000000000000009
00000000000084d0
[ 2.981523] ffff8800341bd950 ffffffff815b87ee 0000000000000000
0000000000000200
[ 2.989821] Call Trace:
[ 2.992560] [<ffffffff815bcc67>] dump_stack+0x19/0x1b
[ 2.998300] [<ffffffff8113b1a0>] warn_alloc_failed+0xf0/0x160
[ 3.004817] [<ffffffff815b87ee>] ?
__alloc_pages_direct_compact+0xac/0x196
[ 3.012594] [<ffffffff8113f14f>] __alloc_pages_nodemask+0x7ff/0xa00
[ 3.019692] [<ffffffff815b417c>] vmemmap_alloc_block+0x62/0xba
[ 3.026303] [<ffffffff815b41e9>] vmemmap_alloc_block_buf+0x15/0x3b
[ 3.033302] [<ffffffff815b1ff6>] vmemmap_populate+0xb4/0x21b
[ 3.039718] [<ffffffff815b461d>] sparse_mem_map_populate+0x27/0x35
[ 3.046717] [<ffffffff815b400f>] sparse_add_one_section+0x7a/0x185
[ 3.053720] [<ffffffff815a1e9f>] __add_pages+0xaf/0x240
[ 3.059656] [<ffffffff81047359>] arch_add_memory+0x59/0xd0
[ 3.065877] [<ffffffff815a21d9>] add_memory+0xb9/0x1b0
[ 3.071713] [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d
[ 3.078813] [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd
[ 3.085719] [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f
[ 3.092716] [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90
[ 3.100004] [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90
[ 3.107293] [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5
[ 3.113904] [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d
[ 3.119933] [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160
[ 3.126153] [<ffffffff81a1ffb5>] acpi_init+0x25d/0x2a6
[ 3.131987] [<ffffffff81a1fd58>] ? acpi_sleep_proc_init+0x2a/0x2a
[ 3.138889] [<ffffffff810020e2>] do_one_initcall+0xe2/0x190
[ 3.145210] [<ffffffff819e20c4>] kernel_init_freeable+0x17c/0x207
[ 3.152111] [<ffffffff819e18d0>] ? do_early_param+0x88/0x88
[ 3.158430] [<ffffffff8159fea0>] ? rest_init+0x80/0x80
[ 3.164264] [<ffffffff8159feae>] kernel_init+0xe/0x180
[ 3.170097] [<ffffffff815cca2c>] ret_from_fork+0x7c/0xb0
[ 3.176123] [<ffffffff8159fea0>] ? rest_init+0x80/0x80
[ 3.181956] Mem-Info:
[ 3.184490] Node 0 DMA per-cpu:
[ 3.188007] CPU 0: hi: 0, btch: 1 usd: 0
[ 3.193353] Node 0 DMA32 per-cpu:
[ 3.197060] CPU 0: hi: 42, btch: 7 usd: 0
[ 3.202410] active_anon:0 inactive_anon:0 isolated_anon:0
[ 3.202410] active_file:0 inactive_file:0 isolated_file:0
[ 3.202410] unevictable:0 dirty:0 writeback:0 unstable:0
[ 3.202410] free:872 slab_reclaimable:13 slab_unreclaimable:1880
[ 3.202410] mapped:0 shmem:0 pagetables:0 bounce:0
[ 3.202410] free_cma:0
because the system has run out of memory at boot time. This occurs
because of the following sequence in the boot:
Main kernel boots and sets E820 map. The second kernel is booted with a
map generated by the kdump service using memmap= and memmap=exactmap.
These parameters are added to the kernel parameters of the kexec/kdump
kernel. The kexec/kdump kernel has limited memory resources so as not
to severely impact the main kernel.
The system then panics and the kdump/kexec kernel boots (which is a
completely new kernel boot). During this boot ACPI is initialized and the
kernel (as can be seen above) traverses the ACPI namespace and finds an
entry for a memory device to be hotadded.
ie)
[ 3.053720] [<ffffffff815a1e9f>] __add_pages+0xaf/0x240
[ 3.059656] [<ffffffff81047359>] arch_add_memory+0x59/0xd0
[ 3.065877] [<ffffffff815a21d9>] add_memory+0xb9/0x1b0
[ 3.071713] [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d
[ 3.078813] [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd
[ 3.085719] [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f
[ 3.092716] [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90
[ 3.100004] [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90
[ 3.107293] [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5
[ 3.113904] [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d
[ 3.119933] [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160
[ 3.126153] [<ffffffff81a1ffb5>] acpi_init+0x25d/0x2a6
At this point the kernel adds page table information and the the kexec/kdump
kernel runs out of memory.
This can also be reproduced with a "regular" kernel by using the
memmap=exactmap and mem=X parameters on the main kernel and booting.
This patchset resolves the problem by adding a kernel parameter,
acpi_no_memhotplug, to disable ACPI memory hotplug. ACPI memory hotplug
should also be disabled by default when a user specified a memory mapping with
"memmap=exactmap" or "mem=X".
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: Len Brown <lenb@xxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rjw@xxxxxxxxxxxxx>
Cc: Linn Crosetto <linn@xxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: Yinghai Lu <yinghai@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Toshi Kani <toshi.kani@xxxxxx>
Cc: Tang Chen <tangchen@xxxxxxxxxxxxxx>
Cc: Wen Congyang <wency@xxxxxxxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Cc: kosaki.motohiro@xxxxxxxxx
Cc: dyoung@xxxxxxxxxx
Cc: Toshi Kani <toshi.kani@xxxxxx>
Cc: linux-acpi@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
---
Documentation/kernel-parameters.txt | 3 +++
arch/x86/kernel/e820.c | 4 ++++
drivers/acpi/acpi_memhotplug.c | 18 ++++++++++++++++++
include/linux/memory_hotplug.h | 9 +++++++++
4 files changed, 34 insertions(+)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b9e9bd8..ea93f75 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -343,6 +343,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
no: ACPI OperationRegions are not marked as reserved,
no further checks are performed.
+ acpi_no_memhotplug [ACPI] Disable memory hotplug. Useful for kexec
+ and kdump kernels.
+
add_efi_memmap [EFI; X86] Include EFI memory map in
kernel's map of available physical RAM.
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 174da5f..3c431fe 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -20,6 +20,7 @@
#include <linux/firmware-map.h>
#include <linux/memblock.h>
#include <linux/sort.h>
+#include <linux/memory_hotplug.h>
#include <asm/e820.h>
#include <asm/proto.h>
@@ -834,6 +835,8 @@ static int __init parse_memopt(char *p)
return -EINVAL;
e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+ set_acpi_no_memhotplug();
+
return 0;
}
early_param("mem", parse_memopt);
@@ -857,6 +860,7 @@ static int __init parse_memmap_one(char *p)
#endif
e820.nr_map = 0;
userdef = 1;
+ set_acpi_no_memhotplug();
return 0;
}
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 551dad7..d104a7d 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -361,7 +361,25 @@ static void acpi_memory_device_remove(struct acpi_device *device)
acpi_memory_device_free(mem_device);
}
+static bool acpi_no_memhotplug;
+
+void set_acpi_no_memhotplug(void)
+{
+ acpi_no_memhotplug = true;
+ pr_info_once("ACPI: Memory Hotplug Disabled\n");
+}
+
void __init acpi_memory_hotplug_init(void)
{
+ if (acpi_no_memhotplug)
+ return;
+
acpi_scan_add_handler_with_hotplug(&memory_device_handler, "memory");
}
+
+static int __init disable_acpi_memory_hotplug(char *str)
+{
+ set_acpi_no_memhotplug();
+ return 1;
+}
+__setup("acpi_no_memhotplug", disable_acpi_memory_hotplug);
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 4ca3d95..3cdb6e0 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -12,6 +12,15 @@ struct pglist_data;
struct mem_section;
struct memory_block;
+#ifdef CONFIG_ACPI_HOTPLUG_MEMORY
+/* set flag to disable ACPI memory hotplug */
+extern void set_acpi_no_memhotplug(void);
+#else
+static inline void set_acpi_no_memhotplug(void)
+{
+}
+#endif
+
#ifdef CONFIG_MEMORY_HOTPLUG
/*
--
1.7.9.3
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
