Re: [PATCH v5 4/9] mm/memory_hotplug: add __add_memory_driver_managed() with online_type arg

["Gupta, Pankaj" <pankaj.gupta@amd.com>]

> Existing callers of add_memory_driver_managed cannot select the
> preferred online type (ZONE_NORMAL vs ZONE_MOVABLE), requiring it to
> hot-add memory as offline blocks, and then follow up by onlining each
> memory block individually.
>
> Most drivers prefer the system default, but the CXL driver wants to
> plumb a preferred policy through the dax kmem driver.
>
> Refactor APIs to add a new interface which allows the dax kmem module
> to select a preferred policy.
>
> Overriding the configured auto-online policy is only safe for known
> in-tree modules, where we know the override reflects a different,
> user-requested policy.  We do not want arbitrary out-of-tree drivers
> silently overriding the system-wide onlining policy, so restrict the
> new interface to the kmem module using EXPORT_SYMBOL_FOR_MODULES()
> rather than a plain EXPORT_SYMBOL_GPL().  Other in-tree modules (e.g.
> cxl_core) can be added to the allowed list as the need arises.
>
> Refactor add_memory_driver_managed, extract __add_memory_driver_managed
> - Add proper kernel-doc for add_memory_driver_managed while refactoring
> - New helper accepts an explicit online_type.
> - New helper validates online_type is between OFFLINE and ONLINE_MOVABLE
>
> Refactor: add_memory_resource, extract __add_memory_resource
> - new helper accepts an explicit online_type
>
> Original APIs now explicitly pass the system-default to new helpers.
>
> No functional change for existing users.
>
> Acked-by: David Hildenbrand (Arm) <david@kernel.org>
> Signed-off-by: Gregory Price <gourry@gourry.net>
> ---
>   include/linux/memory_hotplug.h |  3 ++
>   mm/memory_hotplug.c            | 61 +++++++++++++++++++++++++++++-----
>   2 files changed, 56 insertions(+), 8 deletions(-)
>
> diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
> index f059025f8f8b..d3edeb80aadb 100644
> --- a/include/linux/memory_hotplug.h
> +++ b/include/linux/memory_hotplug.h
> @@ -294,6 +294,9 @@ extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
>   extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
>   extern int add_memory_resource(int nid, struct resource *resource,
>   			       mhp_t mhp_flags);
> +int __add_memory_driver_managed(int nid, u64 start, u64 size,
> +				const char *resource_name, mhp_t mhp_flags,
> +				enum mmop online_type);
>   extern int add_memory_driver_managed(int nid, u64 start, u64 size,
>   				     const char *resource_name,
>   				     mhp_t mhp_flags);
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 494257054095..a66346def504 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -1494,10 +1494,10 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
>    *
>    * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
>    */
> -int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
> +static int __add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags,
> +				 enum mmop online_type)
>   {
>   	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
> -	enum mmop online_type = mhp_get_default_online_type();
>   	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
>   	struct memory_group *group = NULL;
>   	u64 start, size;
> @@ -1585,7 +1585,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>   		merge_system_ram_resource(res);
>   
>   	/* online pages if requested */
> -	if (mhp_get_default_online_type() != MMOP_OFFLINE)
> +	if (online_type != MMOP_OFFLINE)
>   		walk_memory_blocks(start, size, &online_type,
>   				   online_memory_block);
>   
> @@ -1603,7 +1603,13 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>   	return ret;
>   }
>   
> -/* requires device_hotplug_lock, see add_memory_resource() */
> +int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
> +{
> +	return __add_memory_resource(nid, res, mhp_flags,
> +				     mhp_get_default_online_type());
> +}
> +
> +/* requires device_hotplug_lock, see __add_memory_resource() */
>   int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
>   {
>   	struct resource *res;
> @@ -1631,7 +1637,15 @@ int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
>   }
>   EXPORT_SYMBOL_GPL(add_memory);
>   
> -/*
> +/**
> + * __add_memory_driver_managed - add driver-managed memory with explicit online_type
> + * @nid: NUMA node ID where the memory will be added
> + * @start: Start physical address of the memory range
> + * @size: Size of the memory range in bytes
> + * @resource_name: Resource name in format "System RAM ($DRIVER)"
> + * @mhp_flags: Memory hotplug flags
> + * @online_type: Auto-Online behavior (offline, online, kernel, movable)
> + *
>    * Add special, driver-managed memory to the system as system RAM. Such
>    * memory is not exposed via the raw firmware-provided memmap as system
>    * RAM, instead, it is detected and added by a driver - during cold boot,
> @@ -1639,6 +1653,7 @@ EXPORT_SYMBOL_GPL(add_memory);
>    *
>    * Reasons why this memory should not be used for the initial memmap of a
>    * kexec kernel or for placing kexec images:
> + *
>    * - The booting kernel is in charge of determining how this memory will be
>    *   used (e.g., use persistent memory as system RAM)
>    * - Coordination with a hypervisor is required before this memory
> @@ -1651,9 +1666,12 @@ EXPORT_SYMBOL_GPL(add_memory);
>    *
>    * The resource_name (visible via /proc/iomem) has to have the format
>    * "System RAM ($DRIVER)".
> + *
> + * Return: 0 on success, negative error code on failure.
>    */
> -int add_memory_driver_managed(int nid, u64 start, u64 size,
> -			      const char *resource_name, mhp_t mhp_flags)
> +int __add_memory_driver_managed(int nid, u64 start, u64 size,
> +		const char *resource_name, mhp_t mhp_flags,
> +		enum mmop online_type)
>   {
>   	struct resource *res;
>   	int rc;
> @@ -1663,6 +1681,9 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
>   	    resource_name[strlen(resource_name) - 1] != ')')
>   		return -EINVAL;
>   
> +	if (online_type < MMOP_OFFLINE || online_type > MMOP_ONLINE_MOVABLE)
> +		return -EINVAL;
> +
>   	lock_device_hotplug();
>   
>   	res = register_memory_resource(start, size, resource_name);
> @@ -1671,7 +1692,7 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
>   		goto out_unlock;
>   	}
>   
> -	rc = add_memory_resource(nid, res, mhp_flags);
> +	rc = __add_memory_resource(nid, res, mhp_flags, online_type);
>   	if (rc < 0)
>   		release_memory_resource(res);
>   
> @@ -1679,6 +1700,30 @@ int add_memory_driver_managed(int nid, u64 start, u64 size,
>   	unlock_device_hotplug();
>   	return rc;
>   }
> +EXPORT_SYMBOL_FOR_MODULES(__add_memory_driver_managed, "kmem");
> +
> +/**
> + * add_memory_driver_managed - add driver-managed memory
> + * @nid: NUMA node ID where the memory will be added
> + * @start: Start physical address of the memory range
> + * @size: Size of the memory range in bytes
> + * @resource_name: Resource name in format "System RAM ($DRIVER)"
> + * @mhp_flags: Memory hotplug flags
> + *
> + * Add driver-managed memory with the system default online type set by
> + * build config or kernel boot parameter.
> + *
> + * See __add_memory_driver_managed for more details.
> + *
> + * Return: 0 on success, negative error code on failure.
> + */
> +int add_memory_driver_managed(int nid, u64 start, u64 size,
> +			      const char *resource_name, mhp_t mhp_flags)
> +{
> +	return __add_memory_driver_managed(nid, start, size, resource_name,
> +			mhp_flags,
> +			mhp_get_default_online_type());
> +}
>   EXPORT_SYMBOL_GPL(add_memory_driver_managed);
>   
>   /*

Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>