linux/drivers/dax/kmem.c
David Hildenbrand b611719978 mm/memory_hotplug: prepare passing flags to add_memory() and friends
We soon want to pass flags, e.g., to mark added System RAM resources.
mergeable.  Prepare for that.

This patch is based on a similar patch by Oscar Salvador:

https://lkml.kernel.org/r/20190625075227.15193-3-osalvador@suse.de

Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen related part
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Baoquan He <bhe@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Link: https://lkml.kernel.org/r/20200911103459.10306-5-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-16 11:11:18 -07:00

229 lines
5.7 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;
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;
struct resource *res[];
};
static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
struct dax_kmem_data *data;
int rc = -ENOMEM;
int i, 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;
}
data = kzalloc(sizeof(*data) + sizeof(struct resource *) * dev_dax->nr_range, GFP_KERNEL);
if (!data)
return -ENOMEM;
data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
if (!data->res_name)
goto err_res_name;
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) {
dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
i, range.start, range.end);
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(numa_node, range.start,
range_len(&range), kmem_name, MHP_NONE);
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:
kfree(data->res_name);
err_res_name:
kfree(data);
return rc;
}
#ifdef CONFIG_MEMORY_HOTREMOVE
static int 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(dev_dax->target_node, 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) {
kfree(data->res_name);
kfree(data);
dev_set_drvdata(dev, NULL);
}
return 0;
}
#else
static int 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;
return 0;
}
#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);