Re: [PATCH v9 13/27] cxl: prepare memdev creation for type2

[Dan Williams <dan.j.williams@intel.com>]

alejandro.lucero-palau@ wrote:
> From: Alejandro Lucero <alucerop@amd.com>
> 
> Current cxl core is relying on a CXL_DEVTYPE_CLASSMEM type device when
> creating a memdev leading to problems when obtaining cxl_memdev_state
> references from a CXL_DEVTYPE_DEVMEM type. This last device type is
> managed by a specific vendor driver and does not need same sysfs files
> since not userspace intervention is expected.
> 
> Create a new cxl_mem device type with no attributes for Type2.
> 
> Avoid debugfs files relying on existence of cxl_memdev_state.
> 
> Make devm_cxl_add_memdev accesible from a accel driver.
> 
> Signed-off-by: Alejandro Lucero <alucerop@amd.com>
> ---
>  drivers/cxl/core/cdat.c   |  3 +++
>  drivers/cxl/core/memdev.c | 14 ++++++++++++--
>  drivers/cxl/core/region.c |  3 ++-
>  drivers/cxl/cxlmem.h      |  2 --
>  drivers/cxl/mem.c         | 25 +++++++++++++++++++------
>  include/cxl/cxl.h         |  2 ++
>  6 files changed, 38 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
> index 8153f8d83a16..c57bc83e79ee 100644
> --- a/drivers/cxl/core/cdat.c
> +++ b/drivers/cxl/core/cdat.c
> @@ -577,6 +577,9 @@ static struct cxl_dpa_perf *cxled_get_dpa_perf(struct cxl_endpoint_decoder *cxle
>  	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
>  	struct cxl_dpa_perf *perf;
>  
> +	if (!mds)
> +		return ERR_PTR(-EINVAL);
> +

The references to @mds in cxled_get_dpa_perf() are gone
after the DPA partition changes.

If an accelerator has a CDAT it will get qos_class information for free.
If it does not have a CDAT then I wonder how it is telling the BIOS the
memory type for its CXL.mem?

>  	switch (mode) {
>  	case CXL_DECODER_RAM:
>  		perf = &mds->ram_perf;
> diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
> index 836db4a462b3..f91feca586dd 100644
> --- a/drivers/cxl/core/memdev.c
> +++ b/drivers/cxl/core/memdev.c
> @@ -547,9 +547,16 @@ static const struct device_type cxl_memdev_type = {
>  	.groups = cxl_memdev_attribute_groups,
>  };
>  
> +static const struct device_type cxl_accel_memdev_type = {
> +	.name = "cxl_accel_memdev",
> +	.release = cxl_memdev_release,
> +	.devnode = cxl_memdev_devnode,
> +};
> +
>  bool is_cxl_memdev(const struct device *dev)
>  {
> -	return dev->type == &cxl_memdev_type;
> +	return (dev->type == &cxl_memdev_type ||
> +		dev->type == &cxl_accel_memdev_type);

At this point the game is over in terms of future code that trips over
the assumption that all "is_cxl_memdev() == true" devices are created
equal.

>  }
>  EXPORT_SYMBOL_NS_GPL(is_cxl_memdev, "CXL");
>  
> @@ -660,7 +667,10 @@ static struct cxl_memdev *cxl_memdev_alloc(struct cxl_dev_state *cxlds,
>  	dev->parent = cxlds->dev;
>  	dev->bus = &cxl_bus_type;
>  	dev->devt = MKDEV(cxl_mem_major, cxlmd->id);
> -	dev->type = &cxl_memdev_type;
> +	if (cxlds->type == CXL_DEVTYPE_DEVMEM)
> +		dev->type = &cxl_accel_memdev_type;
> +	else
> +		dev->type = &cxl_memdev_type;
>  	device_set_pm_not_required(dev);
>  	INIT_WORK(&cxlmd->detach_work, detach_memdev);
>  
> diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
> index d77899650798..967132b49832 100644
> --- a/drivers/cxl/core/region.c
> +++ b/drivers/cxl/core/region.c
> @@ -1948,7 +1948,8 @@ static int cxl_region_attach(struct cxl_region *cxlr,
>  		return -EINVAL;
>  	}
>  
> -	cxl_region_perf_data_calculate(cxlr, cxled);
> +	if (cxlr->type == CXL_DECODER_HOSTONLYMEM)
> +		cxl_region_perf_data_calculate(cxlr, cxled);

Per-above no need to worry about @mds reference in this path.

>  	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
>  		int i;
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index 4c1c53c29544..360d3728f492 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -87,8 +87,6 @@ static inline bool is_cxl_endpoint(struct cxl_port *port)
>  	return is_cxl_memdev(port->uport_dev);
>  }
>  
> -struct cxl_memdev *devm_cxl_add_memdev(struct device *host,
> -				       struct cxl_dev_state *cxlds);
>  int devm_cxl_sanitize_setup_notifier(struct device *host,
>  				     struct cxl_memdev *cxlmd);
>  struct cxl_memdev_state;
> diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
> index 2f03a4d5606e..93106a43990b 100644
> --- a/drivers/cxl/mem.c
> +++ b/drivers/cxl/mem.c
> @@ -130,12 +130,18 @@ static int cxl_mem_probe(struct device *dev)
>  	dentry = cxl_debugfs_create_dir(dev_name(dev));
>  	debugfs_create_devm_seqfile(dev, "dpamem", dentry, cxl_mem_dpa_show);
>  
> -	if (test_bit(CXL_POISON_ENABLED_INJECT, mds->poison.enabled_cmds))
> -		debugfs_create_file("inject_poison", 0200, dentry, cxlmd,
> -				    &cxl_poison_inject_fops);
> -	if (test_bit(CXL_POISON_ENABLED_CLEAR, mds->poison.enabled_cmds))
> -		debugfs_create_file("clear_poison", 0200, dentry, cxlmd,
> -				    &cxl_poison_clear_fops);
> +	/*
> +	 * Avoid poison debugfs files for Type2 devices as they rely on
> +	 * cxl_memdev_state.
> +	 */
> +	if (mds) {
> +		if (test_bit(CXL_POISON_ENABLED_INJECT, mds->poison.enabled_cmds))
> +			debugfs_create_file("inject_poison", 0200, dentry, cxlmd,
> +					    &cxl_poison_inject_fops);
> +		if (test_bit(CXL_POISON_ENABLED_CLEAR, mds->poison.enabled_cmds))
> +			debugfs_create_file("clear_poison", 0200, dentry, cxlmd,
> +					    &cxl_poison_clear_fops);
> +	}
>  
>  	rc = devm_add_action_or_reset(dev, remove_debugfs, dentry);
>  	if (rc)
> @@ -219,6 +225,13 @@ static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n)
>  	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
>  	struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
>  
> +	/*
> +	 * Avoid poison sysfs files for Type2 devices as they rely on
> +	 * cxl_memdev_state.
> +	 */
> +	if (!mds)
> +		return 0;

It turns out that nothing in the poison handling path requires 'struct
cxl_memdev_state'. So rather than key this rejection off of @mds ==
NULL, I would prefer to find a way to make this optional relative to
data read from 'struct cxl_mailbox', or 'struct cxl_dev_state'.
Conceptually there is nothing stopping a CXL accelertor from supporting
poison management commands on its mailbox, it's just unlikely.