mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-25 00:51:28 +07:00
8a725e4694
Currently, when adding memory, we create entries in /sys/firmware/memmap/ as "System RAM". This will lead to kexec-tools to add that memory to the fixed-up initial memmap for a kexec kernel (loaded via kexec_load()). The memory will be considered initial System RAM by the kexec'd kernel and can no longer be reconfigured. This is not what happens during a real reboot. Let's add our memory via add_memory_driver_managed() now, so we won't create entries in /sys/firmware/memmap/ and indicate the memory as "System RAM (kmem)" in /proc/iomem. This allows everybody (especially kexec-tools) to identify that this memory is special and has to be treated differently than ordinary (hotplugged) System RAM. Before configuring the namespace: [root@localhost ~]# cat /proc/iomem ... 140000000-33fffffff : Persistent Memory 140000000-33fffffff : namespace0.0 3280000000-32ffffffff : PCI Bus 0000:00 After configuring the namespace: [root@localhost ~]# cat /proc/iomem ... 140000000-33fffffff : Persistent Memory 140000000-1481fffff : namespace0.0 148200000-33fffffff : dax0.0 3280000000-32ffffffff : PCI Bus 0000:00 After loading kmem before this change: [root@localhost ~]# cat /proc/iomem ... 140000000-33fffffff : Persistent Memory 140000000-1481fffff : namespace0.0 150000000-33fffffff : dax0.0 150000000-33fffffff : System RAM 3280000000-32ffffffff : PCI Bus 0000:00 After loading kmem after this change: [root@localhost ~]# cat /proc/iomem ... 140000000-33fffffff : Persistent Memory 140000000-1481fffff : namespace0.0 150000000-33fffffff : dax0.0 150000000-33fffffff : System RAM (kmem) 3280000000-32ffffffff : PCI Bus 0000:00 After a proper reboot: [root@localhost ~]# cat /proc/iomem ... 140000000-33fffffff : Persistent Memory 140000000-1481fffff : namespace0.0 148200000-33fffffff : dax0.0 3280000000-32ffffffff : PCI Bus 0000:00 Within the kexec kernel before this change: [root@localhost ~]# cat /proc/iomem ... 140000000-33fffffff : Persistent Memory 140000000-1481fffff : namespace0.0 150000000-33fffffff : System RAM 3280000000-32ffffffff : PCI Bus 0000:00 Within the kexec kernel after this change: [root@localhost ~]# cat /proc/iomem ... 140000000-33fffffff : Persistent Memory 140000000-1481fffff : namespace0.0 148200000-33fffffff : dax0.0 3280000000-32ffffffff : PCI Bus 0000:00 /sys/firmware/memmap/ before this change: 0000000000000000-000000000009fc00 (System RAM) 000000000009fc00-00000000000a0000 (Reserved) 00000000000f0000-0000000000100000 (Reserved) 0000000000100000-00000000bffdf000 (System RAM) 00000000bffdf000-00000000c0000000 (Reserved) 00000000feffc000-00000000ff000000 (Reserved) 00000000fffc0000-0000000100000000 (Reserved) 0000000100000000-0000000140000000 (System RAM) 0000000150000000-0000000340000000 (System RAM) /sys/firmware/memmap/ after a proper reboot: 0000000000000000-000000000009fc00 (System RAM) 000000000009fc00-00000000000a0000 (Reserved) 00000000000f0000-0000000000100000 (Reserved) 0000000000100000-00000000bffdf000 (System RAM) 00000000bffdf000-00000000c0000000 (Reserved) 00000000feffc000-00000000ff000000 (Reserved) 00000000fffc0000-0000000100000000 (Reserved) 0000000100000000-0000000140000000 (System RAM) /sys/firmware/memmap/ after this change: 0000000000000000-000000000009fc00 (System RAM) 000000000009fc00-00000000000a0000 (Reserved) 00000000000f0000-0000000000100000 (Reserved) 0000000000100000-00000000bffdf000 (System RAM) 00000000bffdf000-00000000c0000000 (Reserved) 00000000feffc000-00000000ff000000 (Reserved) 00000000fffc0000-0000000100000000 (Reserved) 0000000100000000-0000000140000000 (System RAM) kexec-tools already seem to basically ignore any System RAM that's not on top level when searching for areas to place kexec images - but also for determining crash areas to dump via kdump. Changing the resource name won't have an impact. Handle unloading of the driver after memory hotremove failed properly, by duplicating the string if necessary. Signed-off-by: David Hildenbrand <david@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Baoquan He <bhe@redhat.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Dan Williams <dan.j.williams@intel.com> Link: http://lkml.kernel.org/r/20200508084217.9160-5-david@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
177 lines
4.7 KiB
C
177 lines
4.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* Copyright(c) 2016-2019 Intel Corporation. All rights reserved. */
|
|
#include <linux/memremap.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/memory.h>
|
|
#include <linux/module.h>
|
|
#include <linux/device.h>
|
|
#include <linux/pfn_t.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/dax.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mman.h>
|
|
#include "dax-private.h"
|
|
#include "bus.h"
|
|
|
|
/* Memory resource name used for add_memory_driver_managed(). */
|
|
static const char *kmem_name;
|
|
/* Set if any memory will remain added when the driver will be unloaded. */
|
|
static bool any_hotremove_failed;
|
|
|
|
int dev_dax_kmem_probe(struct device *dev)
|
|
{
|
|
struct dev_dax *dev_dax = to_dev_dax(dev);
|
|
struct resource *res = &dev_dax->region->res;
|
|
resource_size_t kmem_start;
|
|
resource_size_t kmem_size;
|
|
resource_size_t kmem_end;
|
|
struct resource *new_res;
|
|
const char *new_res_name;
|
|
int numa_node;
|
|
int rc;
|
|
|
|
/*
|
|
* Ensure good NUMA information for the persistent memory.
|
|
* Without this check, there is a risk that slow memory
|
|
* could be mixed in a node with faster memory, causing
|
|
* unavoidable performance issues.
|
|
*/
|
|
numa_node = dev_dax->target_node;
|
|
if (numa_node < 0) {
|
|
dev_warn(dev, "rejecting DAX region %pR with invalid node: %d\n",
|
|
res, numa_node);
|
|
return -EINVAL;
|
|
}
|
|
|
|
/* Hotplug starting at the beginning of the next block: */
|
|
kmem_start = ALIGN(res->start, memory_block_size_bytes());
|
|
|
|
kmem_size = resource_size(res);
|
|
/* Adjust the size down to compensate for moving up kmem_start: */
|
|
kmem_size -= kmem_start - res->start;
|
|
/* Align the size down to cover only complete blocks: */
|
|
kmem_size &= ~(memory_block_size_bytes() - 1);
|
|
kmem_end = kmem_start + kmem_size;
|
|
|
|
new_res_name = kstrdup(dev_name(dev), GFP_KERNEL);
|
|
if (!new_res_name)
|
|
return -ENOMEM;
|
|
|
|
/* Region is permanently reserved if hotremove fails. */
|
|
new_res = request_mem_region(kmem_start, kmem_size, new_res_name);
|
|
if (!new_res) {
|
|
dev_warn(dev, "could not reserve region [%pa-%pa]\n",
|
|
&kmem_start, &kmem_end);
|
|
kfree(new_res_name);
|
|
return -EBUSY;
|
|
}
|
|
|
|
/*
|
|
* Set flags appropriate for System RAM. Leave ..._BUSY clear
|
|
* so that add_memory() can add a child resource. Do not
|
|
* inherit flags from the parent since it may set new flags
|
|
* unknown to us that will break add_memory() below.
|
|
*/
|
|
new_res->flags = IORESOURCE_SYSTEM_RAM;
|
|
|
|
/*
|
|
* Ensure that future kexec'd kernels will not treat this as RAM
|
|
* automatically.
|
|
*/
|
|
rc = add_memory_driver_managed(numa_node, new_res->start,
|
|
resource_size(new_res), kmem_name);
|
|
if (rc) {
|
|
release_resource(new_res);
|
|
kfree(new_res);
|
|
kfree(new_res_name);
|
|
return rc;
|
|
}
|
|
dev_dax->dax_kmem_res = new_res;
|
|
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
static int dev_dax_kmem_remove(struct device *dev)
|
|
{
|
|
struct dev_dax *dev_dax = to_dev_dax(dev);
|
|
struct resource *res = dev_dax->dax_kmem_res;
|
|
resource_size_t kmem_start = res->start;
|
|
resource_size_t kmem_size = resource_size(res);
|
|
const char *res_name = res->name;
|
|
int rc;
|
|
|
|
/*
|
|
* We have one shot for removing memory, if some memory blocks were not
|
|
* offline prior to calling this function remove_memory() will fail, and
|
|
* there is no way to hotremove this memory until reboot because device
|
|
* unbind will succeed even if we return failure.
|
|
*/
|
|
rc = remove_memory(dev_dax->target_node, kmem_start, kmem_size);
|
|
if (rc) {
|
|
any_hotremove_failed = true;
|
|
dev_err(dev,
|
|
"DAX region %pR cannot be hotremoved until the next reboot\n",
|
|
res);
|
|
return rc;
|
|
}
|
|
|
|
/* Release and free dax resources */
|
|
release_resource(res);
|
|
kfree(res);
|
|
kfree(res_name);
|
|
dev_dax->dax_kmem_res = NULL;
|
|
|
|
return 0;
|
|
}
|
|
#else
|
|
static int dev_dax_kmem_remove(struct device *dev)
|
|
{
|
|
/*
|
|
* Without hotremove purposely leak the request_mem_region() for the
|
|
* device-dax range and return '0' to ->remove() attempts. The removal
|
|
* of the device from the driver always succeeds, but the region is
|
|
* permanently pinned as reserved by the unreleased
|
|
* request_mem_region().
|
|
*/
|
|
any_hotremove_failed = true;
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
static struct dax_device_driver device_dax_kmem_driver = {
|
|
.drv = {
|
|
.probe = dev_dax_kmem_probe,
|
|
.remove = dev_dax_kmem_remove,
|
|
},
|
|
};
|
|
|
|
static int __init dax_kmem_init(void)
|
|
{
|
|
int rc;
|
|
|
|
/* Resource name is permanently allocated if any hotremove fails. */
|
|
kmem_name = kstrdup_const("System RAM (kmem)", GFP_KERNEL);
|
|
if (!kmem_name)
|
|
return -ENOMEM;
|
|
|
|
rc = dax_driver_register(&device_dax_kmem_driver);
|
|
if (rc)
|
|
kfree_const(kmem_name);
|
|
return rc;
|
|
}
|
|
|
|
static void __exit dax_kmem_exit(void)
|
|
{
|
|
dax_driver_unregister(&device_dax_kmem_driver);
|
|
if (!any_hotremove_failed)
|
|
kfree_const(kmem_name);
|
|
}
|
|
|
|
MODULE_AUTHOR("Intel Corporation");
|
|
MODULE_LICENSE("GPL v2");
|
|
module_init(dax_kmem_init);
|
|
module_exit(dax_kmem_exit);
|
|
MODULE_ALIAS_DAX_DEVICE(0);
|