mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Dan Williams](/assets/img/avatar_default.png)
The default mode for device-dax instances is backwards for RAM-regions as evidenced by the fact that it tends to catch end users by surprise. "Where is my memory?". Recall that platforms are increasingly shipping with performance-differentiated memory pools beyond typical DRAM and NUMA effects. This includes HBM (high-bandwidth-memory) and CXL (dynamic interleave, varied media types, and future fabric attached possibilities). For this reason the EFI_MEMORY_SP (EFI Special Purpose Memory => Linux 'Soft Reserved') attribute is expected to be applied to all memory-pools that are not the general purpose pool. This designation gives an Operating System a chance to defer usage of a memory pool until later in the boot process where its performance properties can be interrogated and administrator policy can be applied. 'Soft Reserved' memory can be anything from too limited and precious to be part of the general purpose pool (HBM), too slow to host hot kernel data structures (some PMEM media), or anything in between. However, in the absence of an explicit policy, the memory should at least be made usable by default. The current device-dax default hides all non-general-purpose memory behind a device interface. The expectation is that the distribution of users that want the memory online by default vs device-dedicated-access by default follows the Pareto principle. A small number of enlightened users may want to do userspace memory management through a device, but general users just want the kernel to make the memory available with an option to get more advanced later. Arrange for all device-dax instances not backed by PMEM to default to attaching to the dax_kmem driver. From there the baseline memory hotplug policy (CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE / memhp_default_state=) gates whether the memory comes online or stays offline. Where, if it stays offline, it can be reliably converted back to device-mode where it can be partitioned, or fronted by a userspace allocator. So, if someone wants device-dax instances for their 'Soft Reserved' memory: 1/ Build a kernel with CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=n or boot with memhp_default_state=offline, or roll the dice and hope that the kernel has not pinned a page in that memory before step 2. 2/ Write a udev rule to convert the target dax device(s) from 'system-ram' mode to 'devdax' mode: daxctl reconfigure-device $dax -m devdax -f Cc: Michal Hocko <mhocko@suse.com> Cc: David Hildenbrand <david@redhat.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Gregory Price <gregory.price@memverge.com> Tested-by: Fan Ni <fan.ni@samsung.com> Reviewed-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/167602003336.1924368.6809503401422267885.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
63 lines
1.7 KiB
C
63 lines
1.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */
|
|
#ifndef __DAX_BUS_H__
|
|
#define __DAX_BUS_H__
|
|
#include <linux/device.h>
|
|
#include <linux/range.h>
|
|
|
|
struct dev_dax;
|
|
struct resource;
|
|
struct dax_device;
|
|
struct dax_region;
|
|
void dax_region_put(struct dax_region *dax_region);
|
|
|
|
/* dax bus specific ioresource flags */
|
|
#define IORESOURCE_DAX_STATIC BIT(0)
|
|
#define IORESOURCE_DAX_KMEM BIT(1)
|
|
|
|
struct dax_region *alloc_dax_region(struct device *parent, int region_id,
|
|
struct range *range, int target_node, unsigned int align,
|
|
unsigned long flags);
|
|
|
|
struct dev_dax_data {
|
|
struct dax_region *dax_region;
|
|
struct dev_pagemap *pgmap;
|
|
resource_size_t size;
|
|
int id;
|
|
};
|
|
|
|
struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
|
|
|
|
enum dax_driver_type {
|
|
DAXDRV_KMEM_TYPE,
|
|
DAXDRV_DEVICE_TYPE,
|
|
};
|
|
|
|
struct dax_device_driver {
|
|
struct device_driver drv;
|
|
struct list_head ids;
|
|
enum dax_driver_type type;
|
|
int (*probe)(struct dev_dax *dev);
|
|
void (*remove)(struct dev_dax *dev);
|
|
};
|
|
|
|
int __dax_driver_register(struct dax_device_driver *dax_drv,
|
|
struct module *module, const char *mod_name);
|
|
#define dax_driver_register(driver) \
|
|
__dax_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)
|
|
void dax_driver_unregister(struct dax_device_driver *dax_drv);
|
|
void kill_dev_dax(struct dev_dax *dev_dax);
|
|
bool static_dev_dax(struct dev_dax *dev_dax);
|
|
|
|
/*
|
|
* While run_dax() is potentially a generic operation that could be
|
|
* defined in include/linux/dax.h we don't want to grow any users
|
|
* outside of drivers/dax/
|
|
*/
|
|
void run_dax(struct dax_device *dax_dev);
|
|
|
|
#define MODULE_ALIAS_DAX_DEVICE(type) \
|
|
MODULE_ALIAS("dax:t" __stringify(type) "*")
|
|
#define DAX_DEVICE_MODALIAS_FMT "dax:t%d"
|
|
|
|
#endif /* __DAX_BUS_H__ */
|