Re: [PATCH 4/6] dax/hmem: Defer Soft Reserved overlap handling until CXL region assembly completes

["Zhijian Li (Fujitsu)" <lizhijian@fujitsu.com>]

On 22/08/2025 11:42, Smita Koralahalli wrote:
> Previously, dax_hmem deferred to CXL only when an immediate resource
> intersection with a CXL window was detected. This left a gap: if cxl_acpi
> or cxl_pci probing or region assembly had not yet started, hmem could
> prematurely claim ranges.
> 
> Fix this by introducing a dax_cxl_mode state machine and a deferred
> work mechanism.
> 
> The new workqueue delays consideration of Soft Reserved overlaps until
> the CXL subsystem has had a chance to complete its discovery and region
> assembly. This avoids premature iomem claims, eliminates race conditions
> with async cxl_pci probe, and provides a cleaner handoff between hmem and
> CXL resource management.
> 
> Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
>   drivers/dax/hmem/hmem.c | 72 +++++++++++++++++++++++++++++++++++++++--
>   1 file changed, 70 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
> index 7ada820cb177..90978518e5f4 100644
> --- a/drivers/dax/hmem/hmem.c
> +++ b/drivers/dax/hmem/hmem.c
> @@ -58,9 +58,45 @@ static void release_hmem(void *pdev)
>   	platform_device_unregister(pdev);
>   }
>   
> +static enum dax_cxl_mode {
> +	DAX_CXL_MODE_DEFER,
> +	DAX_CXL_MODE_REGISTER,


The patch looks good overall, but I have one question for the community:
Should we retain the `DAX_CXL_MODE_REGISTER` enum value which for the feature
we have not ever supported.


The idea of having a 'register' mode as the last resort for 'Soft Reserved'
memory might seem appealing, but it is not easy to implement. Instead, to
avoid increasing driver complexity, I would prefer that when we encounter
quirk/misconfiguration cases, we allow the user to reprogram/recorrect it. However, this
is beyond the scope of the current patchset


Thanks
Zhijian

> +	DAX_CXL_MODE_DROP,
> +} dax_cxl_mode;
> +
> +static int handle_deferred_cxl(struct device *host, int target_nid,
> +				const struct resource *res)
> +{
> +	if (region_intersects(res->start, resource_size(res), IORESOURCE_MEM,
> +			      IORES_DESC_CXL) != REGION_DISJOINT) {
> +		if (dax_cxl_mode == DAX_CXL_MODE_DROP)
> +			dev_dbg(host, "dropping CXL range: %pr\n", res);
> +	}
> +	return 0;
> +}
> +
> +struct dax_defer_work {
> +	struct platform_device *pdev;
> +	struct work_struct work;
> +};
> +
> +static void process_defer_work(struct work_struct *_work)
> +{
> +	struct dax_defer_work *work = container_of(_work, typeof(*work), work);
> +	struct platform_device *pdev = work->pdev;
> +
> +	/* relies on cxl_acpi and cxl_pci having had a chance to load */
> +	wait_for_device_probe();
> +
> +	dax_cxl_mode = DAX_CXL_MODE_DROP;
> +
> +	walk_hmem_resources(&pdev->dev, handle_deferred_cxl);
> +}
> +
>   static int hmem_register_device(struct device *host, int target_nid,
>   				const struct resource *res)
>   {
> +	struct dax_defer_work *work = dev_get_drvdata(host);
>   	struct platform_device *pdev;
>   	struct memregion_info info;
>   	long id;
> @@ -69,8 +105,18 @@ static int hmem_register_device(struct device *host, int target_nid,
>   	if (IS_ENABLED(CONFIG_DEV_DAX_CXL) &&
>   	    region_intersects(res->start, resource_size(res), IORESOURCE_MEM,
>   			      IORES_DESC_CXL) != REGION_DISJOINT) {
> -		dev_dbg(host, "deferring range to CXL: %pr\n", res);
> -		return 0;
> +		switch (dax_cxl_mode) {
> +		case DAX_CXL_MODE_DEFER:
> +			dev_dbg(host, "deferring range to CXL: %pr\n", res);
> +			schedule_work(&work->work);
> +			return 0;
> +		case DAX_CXL_MODE_REGISTER:
> +			dev_dbg(host, "registering CXL range: %pr\n", res);
> +			break;
> +		case DAX_CXL_MODE_DROP:
> +			dev_dbg(host, "dropping CXL range: %pr\n", res);
> +			return 0;
> +		}
>   	}
>   
>   #ifdef CONFIG_EFI_SOFT_RESERVE
> @@ -130,8 +176,30 @@ static int hmem_register_device(struct device *host, int target_nid,
>   	return rc;
>   }
>   
> +static void kill_defer_work(void *_work)
> +{
> +	struct dax_defer_work *work = container_of(_work, typeof(*work), work);
> +
> +	cancel_work_sync(&work->work);
> +	kfree(work);
> +}
> +
>   static int dax_hmem_platform_probe(struct platform_device *pdev)
>   {
> +	struct dax_defer_work *work = kzalloc(sizeof(*work), GFP_KERNEL);
> +	int rc;
> +
> +	if (!work)
> +		return -ENOMEM;
> +
> +	work->pdev = pdev;
> +	INIT_WORK(&work->work, process_defer_work);
> +
> +	rc = devm_add_action_or_reset(&pdev->dev, kill_defer_work, work);
> +	if (rc)
> +		return rc;
> +
> +	platform_set_drvdata(pdev, work);
>   	return walk_hmem_resources(&pdev->dev, hmem_register_device);
>   }
>