On 6/30/26 2:18 PM, Gregory Price wrote:
> There is no way for drivers leveraging dax_kmem to plumb through a
> preferred auto-online policy - the system default policy is forced.
>
> Add 'enum mmop' field to DAX device creation path to allow drivers
> to specify an auto-online policy when using the kmem driver.
>
> Capturing the system default would otherwise break the ABI, because
> the system default can change - but we would be statically assigning
> the value at device creation time.
>
> To resolve this we add DAX_ONLINE_DEFAULT, which defaults devices to
> the current behavior, while providing a clean way to override it.
>
> No behavioural change for existing callers (still the system default).
behavioral
>
> Signed-off-by: Gregory Price <[email protected]>
Reviewed-by: Dave Jiang <[email protected]>
> ---
> drivers/dax/bus.c | 3 +++
> drivers/dax/bus.h | 9 +++++++++
> drivers/dax/cxl.c | 1 +
> drivers/dax/dax-private.h | 4 ++++
> drivers/dax/hmem/hmem.c | 1 +
> drivers/dax/kmem.c | 11 +++++++++--
> drivers/dax/pmem.c | 1 +
> 7 files changed, 28 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index 492573b47f66..4a03b323b003 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -1,6 +1,7 @@
> // SPDX-License-Identifier: GPL-2.0
> /* Copyright(c) 2017-2018 Intel Corporation. All rights reserved. */
> #include <linux/memremap.h>
> +#include <linux/memory_hotplug.h>
> #include <linux/device.h>
> #include <linux/mutex.h>
> #include <linux/list.h>
> @@ -394,6 +395,7 @@ static ssize_t create_store(struct device *dev, struct
> device_attribute *attr,
> .size = 0,
> .id = -1,
> .memmap_on_memory = false,
> + .online_type = DAX_ONLINE_DEFAULT,
> };
> struct dev_dax *dev_dax = __devm_create_dev_dax(&data);
>
> @@ -1527,6 +1529,7 @@ static struct dev_dax *__devm_create_dev_dax(struct
> dev_dax_data *data)
> ida_init(&dev_dax->ida);
>
> dev_dax->memmap_on_memory = data->memmap_on_memory;
> + dev_dax->online_type = data->online_type;
>
> inode = dax_inode(dax_dev);
> dev->devt = inode->i_rdev;
> diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
> index 5909171a4428..3bc76bc0a145 100644
> --- a/drivers/dax/bus.h
> +++ b/drivers/dax/bus.h
> @@ -3,6 +3,7 @@
> #ifndef __DAX_BUS_H__
> #define __DAX_BUS_H__
> #include <linux/device.h>
> +#include <linux/memory_hotplug.h>
> #include <linux/platform_device.h>
> #include <linux/range.h>
> #include <linux/workqueue.h>
> @@ -16,6 +17,13 @@ struct dax_region;
> #define IORESOURCE_DAX_STATIC BIT(0)
> #define IORESOURCE_DAX_KMEM BIT(1)
>
> +/*
> + * online_type sentinel: the device was created without an explicit online
> + * policy, so the system default is resolved when the kmem driver binds,
> + * (not at device-creation time, which would freeze a stale policy).
> + */
> +#define DAX_ONLINE_DEFAULT (-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);
> @@ -26,6 +34,7 @@ struct dev_dax_data {
> resource_size_t size;
> int id;
> bool memmap_on_memory;
> + int online_type; /* enum mmop, or DAX_ONLINE_DEFAULT sentinel */
> };
>
> struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
> diff --git a/drivers/dax/cxl.c b/drivers/dax/cxl.c
> index 3ab39b77843d..1a7ec6212213 100644
> --- a/drivers/dax/cxl.c
> +++ b/drivers/dax/cxl.c
> @@ -27,6 +27,7 @@ static int cxl_dax_region_probe(struct device *dev)
> .id = -1,
> .size = range_len(&cxlr_dax->hpa_range),
> .memmap_on_memory = true,
> + .online_type = DAX_ONLINE_DEFAULT,
> };
>
> return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
> diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
> index 81e4af49e39c..902e922dc4e4 100644
> --- a/drivers/dax/dax-private.h
> +++ b/drivers/dax/dax-private.h
> @@ -8,6 +8,7 @@
> #include <linux/device.h>
> #include <linux/cdev.h>
> #include <linux/idr.h>
> +#include <linux/memory_hotplug.h>
>
> /* private routines between core files */
> struct dax_device;
> @@ -79,6 +80,8 @@ struct dev_dax_range {
> * @dev: device core
> * @pgmap: pgmap for memmap setup / lifetime (driver owned)
> * @memmap_on_memory: allow kmem to put the memmap in the memory
> + * @online_type: MMOP_* online type for memory hotplug, or DAX_ONLINE_DEFAULT
> + * to resolve the system default policy when kmem binds
> * @nr_range: size of @ranges
> * @ranges: range tuples of memory used
> */
> @@ -95,6 +98,7 @@ struct dev_dax {
> struct device dev;
> struct dev_pagemap *pgmap;
> bool memmap_on_memory;
> + int online_type; /* enum mmop, or DAX_ONLINE_DEFAULT sentinel */
> int nr_range;
> struct dev_dax_range *ranges;
> };
> diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
> index af21f66bf872..2de3bc925172 100644
> --- a/drivers/dax/hmem/hmem.c
> +++ b/drivers/dax/hmem/hmem.c
> @@ -37,6 +37,7 @@ static int dax_hmem_probe(struct platform_device *pdev)
> .id = -1,
> .size = region_idle ? 0 : range_len(&mri->range),
> .memmap_on_memory = false,
> + .online_type = DAX_ONLINE_DEFAULT,
> };
>
> return PTR_ERR_OR_ZERO(devm_create_dev_dax(&data));
> diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
> index 592171ec10f4..0a184c0878dd 100644
> --- a/drivers/dax/kmem.c
> +++ b/drivers/dax/kmem.c
> @@ -72,6 +72,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> int i, rc, mapped = 0;
> mhp_t mhp_flags;
> int numa_node;
> + int online_type;
> int adist = MEMTIER_DEFAULT_DAX_ADISTANCE;
>
> /*
> @@ -132,6 +133,11 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> goto err_reg_mgid;
> data->mgid = rc;
>
> + /* Resolve system default at bind time in case it changed */
> + online_type = dev_dax->online_type;
> + if (online_type == DAX_ONLINE_DEFAULT)
> + online_type = mhp_get_default_online_type();
> +
> for (i = 0; i < dev_dax->nr_range; i++) {
> struct resource *res;
> struct range range;
> @@ -172,8 +178,9 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> * 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_flags);
> + rc = __add_memory_driver_managed(data->mgid, range.start,
> + range_len(&range), kmem_name, mhp_flags,
> + online_type);
>
> if (rc) {
> dev_warn(dev, "mapping%d: %#llx-%#llx memory add
> failed\n",
> diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
> index bee93066a849..e7adace69195 100644
> --- a/drivers/dax/pmem.c
> +++ b/drivers/dax/pmem.c
> @@ -63,6 +63,7 @@ static struct dev_dax *__dax_pmem_probe(struct device *dev)
> .pgmap = &pgmap,
> .size = range_len(&range),
> .memmap_on_memory = false,
> + .online_type = DAX_ONLINE_DEFAULT,
> };
>
> return devm_create_dev_dax(&data);
