mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-11-01 00:48:50 +00:00
eedf634aac
Although dax/kmem users often disable auto-onlining and instead online memory manually (usually to ZONE_MOVABLE), there is still value in having auto-onlining be aware of the relationship of memory blocks. Let's treat one probed unit as a single static memory device, similar to a single ACPI memory device. Link: https://lkml.kernel.org/r/20210806124715.17090-7-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Hui Zhu <teawater@gmail.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Marek Kedzierski <mkedzier@redhat.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
248 lines
6.2 KiB
C
248 lines
6.2 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;
|
|
|
|
static int dax_kmem_range(struct dev_dax *dev_dax, int i, struct range *r)
|
|
{
|
|
struct dev_dax_range *dax_range = &dev_dax->ranges[i];
|
|
struct range *range = &dax_range->range;
|
|
|
|
/* memory-block align the hotplug range */
|
|
r->start = ALIGN(range->start, memory_block_size_bytes());
|
|
r->end = ALIGN_DOWN(range->end + 1, memory_block_size_bytes()) - 1;
|
|
if (r->start >= r->end) {
|
|
r->start = range->start;
|
|
r->end = range->end;
|
|
return -ENOSPC;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
struct dax_kmem_data {
|
|
const char *res_name;
|
|
int mgid;
|
|
struct resource *res[];
|
|
};
|
|
|
|
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
|
|
{
|
|
struct device *dev = &dev_dax->dev;
|
|
unsigned long total_len = 0;
|
|
struct dax_kmem_data *data;
|
|
int i, rc, mapped = 0;
|
|
int numa_node;
|
|
|
|
/*
|
|
* 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 with invalid node: %d\n",
|
|
numa_node);
|
|
return -EINVAL;
|
|
}
|
|
|
|
for (i = 0; i < dev_dax->nr_range; i++) {
|
|
struct range range;
|
|
|
|
rc = dax_kmem_range(dev_dax, i, &range);
|
|
if (rc) {
|
|
dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
|
|
i, range.start, range.end);
|
|
continue;
|
|
}
|
|
total_len += range_len(&range);
|
|
}
|
|
|
|
if (!total_len) {
|
|
dev_warn(dev, "rejecting DAX region without any memory after alignment\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
|
|
if (!data)
|
|
return -ENOMEM;
|
|
|
|
rc = -ENOMEM;
|
|
data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
|
|
if (!data->res_name)
|
|
goto err_res_name;
|
|
|
|
rc = memory_group_register_static(numa_node, total_len);
|
|
if (rc < 0)
|
|
goto err_reg_mgid;
|
|
data->mgid = rc;
|
|
|
|
for (i = 0; i < dev_dax->nr_range; i++) {
|
|
struct resource *res;
|
|
struct range range;
|
|
|
|
rc = dax_kmem_range(dev_dax, i, &range);
|
|
if (rc)
|
|
continue;
|
|
|
|
/* Region is permanently reserved if hotremove fails. */
|
|
res = request_mem_region(range.start, range_len(&range), data->res_name);
|
|
if (!res) {
|
|
dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve region\n",
|
|
i, range.start, range.end);
|
|
/*
|
|
* Once some memory has been onlined we can't
|
|
* assume that it can be un-onlined safely.
|
|
*/
|
|
if (mapped)
|
|
continue;
|
|
rc = -EBUSY;
|
|
goto err_request_mem;
|
|
}
|
|
data->res[i] = res;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
res->flags = IORESOURCE_SYSTEM_RAM;
|
|
|
|
/*
|
|
* Ensure that future kexec'd kernels will not treat
|
|
* this as RAM automatically.
|
|
*/
|
|
rc = add_memory_driver_managed(data->mgid, range.start,
|
|
range_len(&range), kmem_name, MHP_NID_IS_MGID);
|
|
|
|
if (rc) {
|
|
dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
|
|
i, range.start, range.end);
|
|
release_resource(res);
|
|
kfree(res);
|
|
data->res[i] = NULL;
|
|
if (mapped)
|
|
continue;
|
|
goto err_request_mem;
|
|
}
|
|
mapped++;
|
|
}
|
|
|
|
dev_set_drvdata(dev, data);
|
|
|
|
return 0;
|
|
|
|
err_request_mem:
|
|
memory_group_unregister(data->mgid);
|
|
err_reg_mgid:
|
|
kfree(data->res_name);
|
|
err_res_name:
|
|
kfree(data);
|
|
return rc;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
|
|
{
|
|
int i, success = 0;
|
|
struct device *dev = &dev_dax->dev;
|
|
struct dax_kmem_data *data = dev_get_drvdata(dev);
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
for (i = 0; i < dev_dax->nr_range; i++) {
|
|
struct range range;
|
|
int rc;
|
|
|
|
rc = dax_kmem_range(dev_dax, i, &range);
|
|
if (rc)
|
|
continue;
|
|
|
|
rc = remove_memory(range.start, range_len(&range));
|
|
if (rc == 0) {
|
|
release_resource(data->res[i]);
|
|
kfree(data->res[i]);
|
|
data->res[i] = NULL;
|
|
success++;
|
|
continue;
|
|
}
|
|
any_hotremove_failed = true;
|
|
dev_err(dev,
|
|
"mapping%d: %#llx-%#llx cannot be hotremoved until the next reboot\n",
|
|
i, range.start, range.end);
|
|
}
|
|
|
|
if (success >= dev_dax->nr_range) {
|
|
memory_group_unregister(data->mgid);
|
|
kfree(data->res_name);
|
|
kfree(data);
|
|
dev_set_drvdata(dev, NULL);
|
|
}
|
|
}
|
|
#else
|
|
static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
|
|
{
|
|
/*
|
|
* 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;
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
static struct dax_device_driver device_dax_kmem_driver = {
|
|
.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);
|