linux_dsm_epyc7002/drivers/acpi/acpi_memhotplug.c

391 lines
10 KiB
C
Raw Normal View History

/*
* Copyright (C) 2004, 2013 Intel Corporation
* Author: Naveen B S <naveen.b.s@intel.com>
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
*
* All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or (at
* your option) any later version.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
* ACPI based HotPlug driver that supports Memory Hotplug
* This driver fields notifications from firmware for memory add
* and remove operations and alerts the VM of the affected memory
* ranges.
*/
#include <linux/acpi.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include "internal.h"
#define ACPI_MEMORY_DEVICE_CLASS "memory"
#define ACPI_MEMORY_DEVICE_HID "PNP0C80"
#define ACPI_MEMORY_DEVICE_NAME "Hotplug Mem Device"
#define _COMPONENT ACPI_MEMORY_DEVICE_COMPONENT
#undef PREFIX
#define PREFIX "ACPI:memory_hp:"
ACPI_MODULE_NAME("acpi_memhotplug");
static const struct acpi_device_id memory_device_ids[] = {
{ACPI_MEMORY_DEVICE_HID, 0},
{"", 0},
};
#ifdef CONFIG_ACPI_HOTPLUG_MEMORY
/* Memory Device States */
#define MEMORY_INVALID_STATE 0
#define MEMORY_POWER_ON_STATE 1
#define MEMORY_POWER_OFF_STATE 2
static int acpi_memory_device_add(struct acpi_device *device,
const struct acpi_device_id *not_used);
static void acpi_memory_device_remove(struct acpi_device *device);
static struct acpi_scan_handler memory_device_handler = {
.ids = memory_device_ids,
.attach = acpi_memory_device_add,
.detach = acpi_memory_device_remove,
.hotplug = {
.enabled = true,
},
};
struct acpi_memory_info {
struct list_head list;
u64 start_addr; /* Memory Range start physical addr */
u64 length; /* Memory Range length */
unsigned short caching; /* memory cache attribute */
unsigned short write_protect; /* memory read/write attribute */
unsigned int enabled:1;
};
struct acpi_memory_device {
struct acpi_device * device;
unsigned int state; /* State of the memory device */
struct list_head res_list;
};
static acpi_status
acpi_memory_get_resource(struct acpi_resource *resource, void *context)
{
struct acpi_memory_device *mem_device = context;
struct acpi_resource_address64 address64;
struct acpi_memory_info *info, *new;
acpi_status status;
status = acpi_resource_to_address64(resource, &address64);
if (ACPI_FAILURE(status) ||
(address64.resource_type != ACPI_MEMORY_RANGE))
return AE_OK;
list_for_each_entry(info, &mem_device->res_list, list) {
/* Can we combine the resource range information? */
if ((info->caching == address64.info.mem.caching) &&
(info->write_protect == address64.info.mem.write_protect) &&
(info->start_addr + info->length == address64.address.minimum)) {
info->length += address64.address.address_length;
return AE_OK;
}
}
new = kzalloc(sizeof(struct acpi_memory_info), GFP_KERNEL);
if (!new)
return AE_ERROR;
INIT_LIST_HEAD(&new->list);
new->caching = address64.info.mem.caching;
new->write_protect = address64.info.mem.write_protect;
new->start_addr = address64.address.minimum;
new->length = address64.address.address_length;
list_add_tail(&new->list, &mem_device->res_list);
return AE_OK;
}
static void
acpi_memory_free_device_resources(struct acpi_memory_device *mem_device)
{
struct acpi_memory_info *info, *n;
list_for_each_entry_safe(info, n, &mem_device->res_list, list)
kfree(info);
INIT_LIST_HEAD(&mem_device->res_list);
}
static int
acpi_memory_get_device_resources(struct acpi_memory_device *mem_device)
{
acpi_status status;
if (!list_empty(&mem_device->res_list))
return 0;
status = acpi_walk_resources(mem_device->device->handle, METHOD_NAME__CRS,
acpi_memory_get_resource, mem_device);
if (ACPI_FAILURE(status)) {
acpi_memory_free_device_resources(mem_device);
return -EINVAL;
}
return 0;
}
static int acpi_memory_check_device(struct acpi_memory_device *mem_device)
{
unsigned long long current_status;
/* Get device present/absent information from the _STA */
if (ACPI_FAILURE(acpi_evaluate_integer(mem_device->device->handle,
METHOD_NAME__STA, NULL,
&current_status)))
return -ENODEV;
/*
* Check for device status. Device should be
* present/enabled/functioning.
*/
if (!((current_status & ACPI_STA_DEVICE_PRESENT)
&& (current_status & ACPI_STA_DEVICE_ENABLED)
&& (current_status & ACPI_STA_DEVICE_FUNCTIONING)))
return -ENODEV;
return 0;
}
static unsigned long acpi_meminfo_start_pfn(struct acpi_memory_info *info)
{
return PFN_DOWN(info->start_addr);
}
static unsigned long acpi_meminfo_end_pfn(struct acpi_memory_info *info)
{
return PFN_UP(info->start_addr + info->length-1);
}
static int acpi_bind_memblk(struct memory_block *mem, void *arg)
{
return acpi_bind_one(&mem->dev, arg);
}
static int acpi_bind_memory_blocks(struct acpi_memory_info *info,
struct acpi_device *adev)
{
return walk_memory_range(acpi_meminfo_start_pfn(info),
acpi_meminfo_end_pfn(info), adev,
acpi_bind_memblk);
}
static int acpi_unbind_memblk(struct memory_block *mem, void *arg)
{
acpi_unbind_one(&mem->dev);
return 0;
}
static void acpi_unbind_memory_blocks(struct acpi_memory_info *info)
{
walk_memory_range(acpi_meminfo_start_pfn(info),
acpi_meminfo_end_pfn(info), NULL, acpi_unbind_memblk);
}
static int acpi_memory_enable_device(struct acpi_memory_device *mem_device)
{
acpi_handle handle = mem_device->device->handle;
int result, num_enabled = 0;
struct acpi_memory_info *info;
int node;
node = acpi_get_node(handle);
/*
* Tell the VM there is more memory here...
* Note: Assume that this function returns zero on success
* We don't have memory-hot-add rollback function,now.
* (i.e. memory-hot-remove function)
*/
list_for_each_entry(info, &mem_device->res_list, list) {
if (info->enabled) { /* just sanity check...*/
num_enabled++;
continue;
}
/*
* If the memory block size is zero, please ignore it.
* Don't try to do the following memory hotplug flowchart.
*/
if (!info->length)
continue;
if (node < 0)
node = memory_add_physaddr_to_nid(info->start_addr);
mm/memory_hotplug: make add_memory() take the device_hotplug_lock add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Len Brown <lenb@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com> Cc: John Allen <jallen@linux.vnet.ibm.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Mathieu Malaterre <malat@debian.org> Cc: Pavel Tatashin <pavel.tatashin@microsoft.com> Cc: YASUAKI ISHIMATSU <yasu.isimatu@gmail.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Michael Neuling <mikey@neuling.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 05:10:24 +07:00
result = __add_memory(node, info->start_addr, info->length);
/*
* If the memory block has been used by the kernel, add_memory()
* returns -EEXIST. If add_memory() returns the other error, it
* means that this memory block is not used by the kernel.
*/
if (result && result != -EEXIST)
continue;
result = acpi_bind_memory_blocks(info, mem_device->device);
if (result) {
acpi_unbind_memory_blocks(info);
return -ENODEV;
}
info->enabled = 1;
/*
* Add num_enable even if add_memory() returns -EEXIST, so the
* device is bound to this driver.
*/
num_enabled++;
}
if (!num_enabled) {
dev_err(&mem_device->device->dev, "add_memory failed\n");
mem_device->state = MEMORY_INVALID_STATE;
return -EINVAL;
}
/*
* Sometimes the memory device will contain several memory blocks.
* When one memory block is hot-added to the system memory, it will
* be regarded as a success.
* Otherwise if the last memory block can't be hot-added to the system
* memory, it will be failure and the memory device can't be bound with
* driver.
*/
return 0;
}
static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device)
{
acpi_handle handle = mem_device->device->handle;
struct acpi_memory_info *info, *n;
int nid = acpi_get_node(handle);
list_for_each_entry_safe(info, n, &mem_device->res_list, list) {
if (!info->enabled)
continue;
if (nid == NUMA_NO_NODE)
nid = memory_add_physaddr_to_nid(info->start_addr);
acpi_unbind_memory_blocks(info);
mm/memory_hotplug: make remove_memory() take the device_hotplug_lock Patch series "mm: online/offline_pages called w.o. mem_hotplug_lock", v3. Reading through the code and studying how mem_hotplug_lock is to be used, I noticed that there are two places where we can end up calling device_online()/device_offline() - online_pages()/offline_pages() without the mem_hotplug_lock. And there are other places where we call device_online()/device_offline() without the device_hotplug_lock. While e.g. echo "online" > /sys/devices/system/memory/memory9/state is fine, e.g. echo 1 > /sys/devices/system/memory/memory9/online Will not take the mem_hotplug_lock. However the device_lock() and device_hotplug_lock. E.g. via memory_probe_store(), we can end up calling add_memory()->online_pages() without the device_hotplug_lock. So we can have concurrent callers in online_pages(). We e.g. touch in online_pages() basically unprotected zone->present_pages then. Looks like there is a longer history to that (see Patch #2 for details), and fixing it to work the way it was intended is not really possible. We would e.g. have to take the mem_hotplug_lock in device/base/core.c, which sounds wrong. Summary: We had a lock inversion on mem_hotplug_lock and device_lock(). More details can be found in patch 3 and patch 6. I propose the general rules (documentation added in patch 6): 1. add_memory/add_memory_resource() must only be called with device_hotplug_lock. 2. remove_memory() must only be called with device_hotplug_lock. This is already documented and holds for all callers. 3. device_online()/device_offline() must only be called with device_hotplug_lock. This is already documented and true for now in core code. Other callers (related to memory hotplug) have to be fixed up. 4. mem_hotplug_lock is taken inside of add_memory/remove_memory/ online_pages/offline_pages. To me, this looks way cleaner than what we have right now (and easier to verify). And looking at the documentation of remove_memory, using lock_device_hotplug also for add_memory() feels natural. This patch (of 6): remove_memory() is exported right now but requires the device_hotplug_lock, which is not exported. So let's provide a variant that takes the lock and only export that one. The lock is already held in arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c arch/powerpc/platforms/powernv/memtrace.c Apart from that, there are not other users in the tree. Link: http://lkml.kernel.org/r/20180925091457.28651-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Pavel Tatashin <pavel.tatashin@microsoft.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Len Brown <lenb@kernel.org> Cc: Rashmica Gupta <rashmica.g@gmail.com> Cc: Michael Neuling <mikey@neuling.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com> Cc: John Allen <jallen@linux.vnet.ibm.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: YASUAKI ISHIMATSU <yasu.isimatu@gmail.com> Cc: Mathieu Malaterre <malat@debian.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Juergen Gross <jgross@suse.com> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: "K. Y. Srinivasan" <kys@microsoft.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Stephen Hemminger <sthemmin@microsoft.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 05:10:18 +07:00
__remove_memory(nid, info->start_addr, info->length);
list_del(&info->list);
kfree(info);
}
}
static void acpi_memory_device_free(struct acpi_memory_device *mem_device)
{
if (!mem_device)
return;
acpi_memory_free_device_resources(mem_device);
mem_device->device->driver_data = NULL;
kfree(mem_device);
}
static int acpi_memory_device_add(struct acpi_device *device,
const struct acpi_device_id *not_used)
{
struct acpi_memory_device *mem_device;
int result;
if (!device)
return -EINVAL;
mem_device = kzalloc(sizeof(struct acpi_memory_device), GFP_KERNEL);
if (!mem_device)
return -ENOMEM;
INIT_LIST_HEAD(&mem_device->res_list);
mem_device->device = device;
sprintf(acpi_device_name(device), "%s", ACPI_MEMORY_DEVICE_NAME);
sprintf(acpi_device_class(device), "%s", ACPI_MEMORY_DEVICE_CLASS);
device->driver_data = mem_device;
/* Get the range from the _CRS */
result = acpi_memory_get_device_resources(mem_device);
if (result) {
device->driver_data = NULL;
kfree(mem_device);
return result;
}
/* Set the device state */
mem_device->state = MEMORY_POWER_ON_STATE;
result = acpi_memory_check_device(mem_device);
if (result) {
acpi_memory_device_free(mem_device);
return 0;
}
result = acpi_memory_enable_device(mem_device);
if (result) {
dev_err(&device->dev, "acpi_memory_enable_device() error\n");
acpi_memory_device_free(mem_device);
return result;
}
dev_dbg(&device->dev, "Memory device configured by ACPI\n");
return 1;
}
static void acpi_memory_device_remove(struct acpi_device *device)
{
struct acpi_memory_device *mem_device;
if (!device || !acpi_driver_data(device))
return;
mem_device = acpi_driver_data(device);
acpi_memory_remove_memory(mem_device);
acpi_memory_device_free(mem_device);
}
ACPI / memhotplug: add parameter to disable memory hotplug When booting a kexec/kdump kernel on a system that has specific memory hotplug regions the boot will fail with warnings like: swapper/0: page allocation failure: order:9, mode:0x84d0 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.10.0-65.el7.x86_64 #1 Hardware name: QCI QSSC-S4R/QSSC-S4R, BIOS QSSC-S4R.QCI.01.00.S013.032920111005 03/29/2011 0000000000000000 ffff8800341bd8c8 ffffffff815bcc67 ffff8800341bd950 ffffffff8113b1a0 ffff880036339b00 0000000000000009 00000000000084d0 ffff8800341bd950 ffffffff815b87ee 0000000000000000 0000000000000200 Call Trace: [<ffffffff815bcc67>] dump_stack+0x19/0x1b [<ffffffff8113b1a0>] warn_alloc_failed+0xf0/0x160 [<ffffffff815b87ee>] ? __alloc_pages_direct_compact+0xac/0x196 [<ffffffff8113f14f>] __alloc_pages_nodemask+0x7ff/0xa00 [<ffffffff815b417c>] vmemmap_alloc_block+0x62/0xba [<ffffffff815b41e9>] vmemmap_alloc_block_buf+0x15/0x3b [<ffffffff815b1ff6>] vmemmap_populate+0xb4/0x21b [<ffffffff815b461d>] sparse_mem_map_populate+0x27/0x35 [<ffffffff815b400f>] sparse_add_one_section+0x7a/0x185 [<ffffffff815a1e9f>] __add_pages+0xaf/0x240 [<ffffffff81047359>] arch_add_memory+0x59/0xd0 [<ffffffff815a21d9>] add_memory+0xb9/0x1b0 [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5 [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160 [<ffffffff81a1ffb5>] acpi_init+0x25d/0x2a6 [<ffffffff81a1fd58>] ? acpi_sleep_proc_init+0x2a/0x2a [<ffffffff810020e2>] do_one_initcall+0xe2/0x190 [<ffffffff819e20c4>] kernel_init_freeable+0x17c/0x207 [<ffffffff819e18d0>] ? do_early_param+0x88/0x88 [<ffffffff8159fea0>] ? rest_init+0x80/0x80 [<ffffffff8159feae>] kernel_init+0xe/0x180 [<ffffffff815cca2c>] ret_from_fork+0x7c/0xb0 [<ffffffff8159fea0>] ? rest_init+0x80/0x80 Mem-Info: Node 0 DMA per-cpu: CPU 0: hi: 0, btch: 1 usd: 0 Node 0 DMA32 per-cpu: CPU 0: hi: 42, btch: 7 usd: 0 active_anon:0 inactive_anon:0 isolated_anon:0 active_file:0 inactive_file:0 isolated_file:0 unevictable:0 dirty:0 writeback:0 unstable:0 free:872 slab_reclaimable:13 slab_unreclaimable:1880 mapped:0 shmem:0 pagetables:0 bounce:0 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) [<ffffffff815a1e9f>] __add_pages+0xaf/0x240 [<ffffffff81047359>] arch_add_memory+0x59/0xd0 [<ffffffff815a21d9>] add_memory+0xb9/0x1b0 [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5 [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160 [<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 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. Signed-off-by: Prarit Bhargava <prarit@redhat.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-01-15 02:21:13 +07:00
static bool __initdata acpi_no_memhotplug;
void __init acpi_memory_hotplug_init(void)
{
if (acpi_no_memhotplug) {
memory_device_handler.attach = NULL;
acpi_scan_add_handler(&memory_device_handler);
ACPI / memhotplug: add parameter to disable memory hotplug When booting a kexec/kdump kernel on a system that has specific memory hotplug regions the boot will fail with warnings like: swapper/0: page allocation failure: order:9, mode:0x84d0 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.10.0-65.el7.x86_64 #1 Hardware name: QCI QSSC-S4R/QSSC-S4R, BIOS QSSC-S4R.QCI.01.00.S013.032920111005 03/29/2011 0000000000000000 ffff8800341bd8c8 ffffffff815bcc67 ffff8800341bd950 ffffffff8113b1a0 ffff880036339b00 0000000000000009 00000000000084d0 ffff8800341bd950 ffffffff815b87ee 0000000000000000 0000000000000200 Call Trace: [<ffffffff815bcc67>] dump_stack+0x19/0x1b [<ffffffff8113b1a0>] warn_alloc_failed+0xf0/0x160 [<ffffffff815b87ee>] ? __alloc_pages_direct_compact+0xac/0x196 [<ffffffff8113f14f>] __alloc_pages_nodemask+0x7ff/0xa00 [<ffffffff815b417c>] vmemmap_alloc_block+0x62/0xba [<ffffffff815b41e9>] vmemmap_alloc_block_buf+0x15/0x3b [<ffffffff815b1ff6>] vmemmap_populate+0xb4/0x21b [<ffffffff815b461d>] sparse_mem_map_populate+0x27/0x35 [<ffffffff815b400f>] sparse_add_one_section+0x7a/0x185 [<ffffffff815a1e9f>] __add_pages+0xaf/0x240 [<ffffffff81047359>] arch_add_memory+0x59/0xd0 [<ffffffff815a21d9>] add_memory+0xb9/0x1b0 [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5 [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160 [<ffffffff81a1ffb5>] acpi_init+0x25d/0x2a6 [<ffffffff81a1fd58>] ? acpi_sleep_proc_init+0x2a/0x2a [<ffffffff810020e2>] do_one_initcall+0xe2/0x190 [<ffffffff819e20c4>] kernel_init_freeable+0x17c/0x207 [<ffffffff819e18d0>] ? do_early_param+0x88/0x88 [<ffffffff8159fea0>] ? rest_init+0x80/0x80 [<ffffffff8159feae>] kernel_init+0xe/0x180 [<ffffffff815cca2c>] ret_from_fork+0x7c/0xb0 [<ffffffff8159fea0>] ? rest_init+0x80/0x80 Mem-Info: Node 0 DMA per-cpu: CPU 0: hi: 0, btch: 1 usd: 0 Node 0 DMA32 per-cpu: CPU 0: hi: 42, btch: 7 usd: 0 active_anon:0 inactive_anon:0 isolated_anon:0 active_file:0 inactive_file:0 isolated_file:0 unevictable:0 dirty:0 writeback:0 unstable:0 free:872 slab_reclaimable:13 slab_unreclaimable:1880 mapped:0 shmem:0 pagetables:0 bounce:0 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) [<ffffffff815a1e9f>] __add_pages+0xaf/0x240 [<ffffffff81047359>] arch_add_memory+0x59/0xd0 [<ffffffff815a21d9>] add_memory+0xb9/0x1b0 [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5 [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160 [<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 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. Signed-off-by: Prarit Bhargava <prarit@redhat.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-01-15 02:21:13 +07:00
return;
}
acpi_scan_add_handler_with_hotplug(&memory_device_handler, "memory");
}
ACPI / memhotplug: add parameter to disable memory hotplug When booting a kexec/kdump kernel on a system that has specific memory hotplug regions the boot will fail with warnings like: swapper/0: page allocation failure: order:9, mode:0x84d0 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.10.0-65.el7.x86_64 #1 Hardware name: QCI QSSC-S4R/QSSC-S4R, BIOS QSSC-S4R.QCI.01.00.S013.032920111005 03/29/2011 0000000000000000 ffff8800341bd8c8 ffffffff815bcc67 ffff8800341bd950 ffffffff8113b1a0 ffff880036339b00 0000000000000009 00000000000084d0 ffff8800341bd950 ffffffff815b87ee 0000000000000000 0000000000000200 Call Trace: [<ffffffff815bcc67>] dump_stack+0x19/0x1b [<ffffffff8113b1a0>] warn_alloc_failed+0xf0/0x160 [<ffffffff815b87ee>] ? __alloc_pages_direct_compact+0xac/0x196 [<ffffffff8113f14f>] __alloc_pages_nodemask+0x7ff/0xa00 [<ffffffff815b417c>] vmemmap_alloc_block+0x62/0xba [<ffffffff815b41e9>] vmemmap_alloc_block_buf+0x15/0x3b [<ffffffff815b1ff6>] vmemmap_populate+0xb4/0x21b [<ffffffff815b461d>] sparse_mem_map_populate+0x27/0x35 [<ffffffff815b400f>] sparse_add_one_section+0x7a/0x185 [<ffffffff815a1e9f>] __add_pages+0xaf/0x240 [<ffffffff81047359>] arch_add_memory+0x59/0xd0 [<ffffffff815a21d9>] add_memory+0xb9/0x1b0 [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5 [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160 [<ffffffff81a1ffb5>] acpi_init+0x25d/0x2a6 [<ffffffff81a1fd58>] ? acpi_sleep_proc_init+0x2a/0x2a [<ffffffff810020e2>] do_one_initcall+0xe2/0x190 [<ffffffff819e20c4>] kernel_init_freeable+0x17c/0x207 [<ffffffff819e18d0>] ? do_early_param+0x88/0x88 [<ffffffff8159fea0>] ? rest_init+0x80/0x80 [<ffffffff8159feae>] kernel_init+0xe/0x180 [<ffffffff815cca2c>] ret_from_fork+0x7c/0xb0 [<ffffffff8159fea0>] ? rest_init+0x80/0x80 Mem-Info: Node 0 DMA per-cpu: CPU 0: hi: 0, btch: 1 usd: 0 Node 0 DMA32 per-cpu: CPU 0: hi: 42, btch: 7 usd: 0 active_anon:0 inactive_anon:0 isolated_anon:0 active_file:0 inactive_file:0 isolated_file:0 unevictable:0 dirty:0 writeback:0 unstable:0 free:872 slab_reclaimable:13 slab_unreclaimable:1880 mapped:0 shmem:0 pagetables:0 bounce:0 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) [<ffffffff815a1e9f>] __add_pages+0xaf/0x240 [<ffffffff81047359>] arch_add_memory+0x59/0xd0 [<ffffffff815a21d9>] add_memory+0xb9/0x1b0 [<ffffffff81333b9c>] acpi_memory_device_add+0x18d/0x26d [<ffffffff81309a01>] acpi_bus_device_attach+0x7d/0xcd [<ffffffff8132379d>] acpi_ns_walk_namespace+0xc8/0x17f [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81309984>] ? acpi_bus_type_and_status+0x90/0x90 [<ffffffff81323c8c>] acpi_walk_namespace+0x95/0xc5 [<ffffffff8130a6d6>] acpi_bus_scan+0x8b/0x9d [<ffffffff81a2019a>] acpi_scan_init+0x63/0x160 [<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 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. Signed-off-by: Prarit Bhargava <prarit@redhat.com> Acked-by: Vivek Goyal <vgoyal@redhat.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2014-01-15 02:21:13 +07:00
static int __init disable_acpi_memory_hotplug(char *str)
{
acpi_no_memhotplug = true;
return 1;
}
__setup("acpi_no_memhotplug", disable_acpi_memory_hotplug);
#else
static struct acpi_scan_handler memory_device_handler = {
.ids = memory_device_ids,
};
void __init acpi_memory_hotplug_init(void)
{
acpi_scan_add_handler(&memory_device_handler);
}
#endif /* CONFIG_ACPI_HOTPLUG_MEMORY */