Re: [PATCH v11 11/23] cxl: define a driver interface for HPA free space enumeration

[Ben Cheatham <benjamin.cheatham@amd.com>]

On 3/10/25 4:03 PM, alejandro.lucero-palau@amd.com wrote:
> From: Alejandro Lucero <alucerop@amd.com>
> 
> CXL region creation involves allocating capacity from device DPA
> (device-physical-address space) and assigning it to decode a given HPA
> (host-physical-address space). Before determining how much DPA to
> allocate the amount of available HPA must be determined. Also, not all
> HPA is created equal, some specifically targets RAM, some target PMEM,
> some is prepared for device-memory flows like HDM-D and HDM-DB, and some
> is host-only (HDM-H).
> 
> Wrap all of those concerns into an API that retrieves a root decoder
> (platform CXL window) that fits the specified constraints and the
> capacity available for a new region.
> 
> Add a complementary function for releasing the reference to such root
> decoder.
> 
> Based on https://lore.kernel.org/linux-cxl/168592159290.1948938.13522227102445462976.stgit@dwillia2-xfh.jf.intel.com/
> 
> Signed-off-by: Alejandro Lucero <alucerop@amd.com>
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> ---
>  drivers/cxl/core/region.c | 160 ++++++++++++++++++++++++++++++++++++++
>  drivers/cxl/cxl.h         |   3 +
>  drivers/cxl/mem.c         |  26 +++++--
>  include/cxl/cxl.h         |  11 +++
>  4 files changed, 194 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
> index 8537b6a9ca18..ad809721a3e4 100644
> --- a/drivers/cxl/core/region.c
> +++ b/drivers/cxl/core/region.c
> @@ -695,6 +695,166 @@ static int free_hpa(struct cxl_region *cxlr)
>  	return 0;
>  }
>  
> +struct cxlrd_max_context {
> +	struct device * const *host_bridges;
> +	int interleave_ways;
> +	unsigned long flags;
> +	resource_size_t max_hpa;
> +	struct cxl_root_decoder *cxlrd;
> +};
> +
> +static int find_max_hpa(struct device *dev, void *data)
> +{
> +	struct cxlrd_max_context *ctx = data;
> +	struct cxl_switch_decoder *cxlsd;
> +	struct cxl_root_decoder *cxlrd;
> +	struct resource *res, *prev;
> +	struct cxl_decoder *cxld;
> +	resource_size_t max;
> +	int found = 0;
> +
> +	if (!is_root_decoder(dev))
> +		return 0;
> +
> +	cxlrd = to_cxl_root_decoder(dev);
> +	cxlsd = &cxlrd->cxlsd;
> +	cxld = &cxlsd->cxld;
> +	if ((cxld->flags & ctx->flags) != ctx->flags) {
> +		dev_dbg(dev, "flags not matching: %08lx vs %08lx\n",
> +			cxld->flags, ctx->flags);
> +		return 0;
> +	}
> +
> +	for (int i = 0; i < ctx->interleave_ways; i++)
> +		for (int j = 0; j < ctx->interleave_ways; j++)
> +			if (ctx->host_bridges[i] == cxlsd->target[j]->dport_dev) {
> +				found++;
> +				break;
> +			}

I think kernel coding style requires braces on the above for statements, but I may be wrong here.

> +
> +	if (found != ctx->interleave_ways) {
> +		dev_dbg(dev, "Not enough host bridges found(%d) for interleave ways requested (%d)\n",
> +			found, ctx->interleave_ways);
> +		return 0;
> +	}
> +
> +	/*
> +	 * Walk the root decoder resource range relying on cxl_region_rwsem to
> +	 * preclude sibling arrival/departure and find the largest free space
> +	 * gap.
> +	 */
> +	lockdep_assert_held_read(&cxl_region_rwsem);
> +	max = 0;
> +	res = cxlrd->res->child;
> +
> +	/* With no resource child the whole parent resource is available */
> +	if (!res)
> +		max = resource_size(cxlrd->res);
> +	else
> +		max = 0;
> +
> +	for (prev = NULL; res; prev = res, res = res->sibling) {
> +		struct resource *next = res->sibling;
> +		resource_size_t free = 0;
> +
> +		/*
> +		 * Sanity check for preventing arithmetic problems below as a
> +		 * resource with size 0 could imply using the end field below
> +		 * when set to unsigned zero - 1 or all f in hex.
> +		 */
> +		if (prev && !resource_size(prev))
> +			continue;
> +
> +		if (!prev && res->start > cxlrd->res->start) {
> +			free = res->start - cxlrd->res->start;
> +			max = max(free, max);
> +		}
> +		if (prev && res->start > prev->end + 1) {
> +			free = res->start - prev->end + 1;
> +			max = max(free, max);
> +		}
> +		if (next && res->end + 1 < next->start) {
> +			free = next->start - res->end + 1;
> +			max = max(free, max);
> +		}
> +		if (!next && res->end + 1 < cxlrd->res->end + 1) {
> +			free = cxlrd->res->end + 1 - res->end + 1;
> +			max = max(free, max);
> +		}
> +	}
> +
> +	dev_dbg(CXLRD_DEV(cxlrd), "found %pa bytes of free space\n", &max);
> +	if (max > ctx->max_hpa) {
> +		if (ctx->cxlrd)
> +			put_device(CXLRD_DEV(ctx->cxlrd));
> +		get_device(CXLRD_DEV(cxlrd));
> +		ctx->cxlrd = cxlrd;
> +		ctx->max_hpa = max;
> +		dev_dbg(CXLRD_DEV(cxlrd), "found %pa bytes of free space\n",
> +			&max);
Duplicate debug prints here

> +	}
> +	return 0;
> +}
> +
> +/**
> + * cxl_get_hpa_freespace - find a root decoder with free capacity per constraints
> + * @cxlmd: the CXL memory device with an endpoint that is mapped by the returned
> + *	    decoder
> + * @interleave_ways: number of entries in @host_bridges
> + * @flags: CXL_DECODER_F flags for selecting RAM vs PMEM, and HDM-H vs HDM-D[B]

Looking below, the HDM-H vs HDM-D[B] flag is called CXL_DECODER_F_TYPE2, so I think
it would be good to reference that either here or in include/cxl/cxl.h.

> + * @max_avail_contig: output parameter of max contiguous bytes available in the
> + *		      returned decoder
> + *
> + * The return tuple of a 'struct cxl_root_decoder' and 'bytes available given
> + * in (@max_avail_contig))' is a point in time snapshot. If by the time the
> + * caller goes to use this root decoder's capacity the capacity is reduced then
> + * caller needs to loop and retry.
> + *
> + * The returned root decoder has an elevated reference count that needs to be
> + * put with put_device(CXLRD_DEV(cxlrd)).

s/put_device(CXLRD_DEV(cxlrd))/cxl_put_root_decoder(cxlrd)/

Using put_device() isn't possible in accelerator drivers due to not struct cxl_root_decoder
not being exported.

> + */
> +struct cxl_root_decoder *cxl_get_hpa_freespace(struct cxl_memdev *cxlmd,
> +					       int interleave_ways,
> +					       unsigned long flags,
> +					       resource_size_t *max_avail_contig)
> +{
> +	struct cxl_port *endpoint = cxlmd->endpoint;
> +	struct cxlrd_max_context ctx = {
> +		.host_bridges = &endpoint->host_bridge,
> +		.flags = flags,
> +	};
> +	struct cxl_port *root_port;
> +	struct cxl_root *root __free(put_cxl_root) = find_cxl_root(endpoint);
> +
> +	if (!is_cxl_endpoint(endpoint)) {
> +		dev_dbg(&endpoint->dev, "hpa requestor is not an endpoint\n");
> +		return ERR_PTR(-EINVAL);
> +	}
> +
> +	if (!root) {
> +		dev_dbg(&endpoint->dev, "endpoint can not be related to a root port\n");
> +		return ERR_PTR(-ENXIO);
> +	}
> +
> +	root_port = &root->port;
> +	down_read(&cxl_region_rwsem);
> +	device_for_each_child(&root_port->dev, &ctx, find_max_hpa);
> +	up_read(&cxl_region_rwsem);
> +
> +	if (!ctx.cxlrd)
> +		return ERR_PTR(-ENOMEM);
> +
> +	*max_avail_contig = ctx.max_hpa;
> +	return ctx.cxlrd;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_get_hpa_freespace, "CXL");
> +
> +void cxl_put_root_decoder(struct cxl_root_decoder *cxlrd)
> +{
> +	put_device(CXLRD_DEV(cxlrd));
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_put_root_decoder, "CXL");
> +
>  static ssize_t size_store(struct device *dev, struct device_attribute *attr,
>  			  const char *buf, size_t len)
>  {
> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
> index 4523864eebd2..c35620c24c8f 100644
> --- a/drivers/cxl/cxl.h
> +++ b/drivers/cxl/cxl.h
> @@ -672,6 +672,9 @@ struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev);
>  struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
>  struct cxl_endpoint_decoder *to_cxl_endpoint_decoder(struct device *dev);
>  bool is_root_decoder(struct device *dev);
> +
> +#define CXLRD_DEV(cxlrd) (&(cxlrd)->cxlsd.cxld.dev)
> +
>  bool is_switch_decoder(struct device *dev);
>  bool is_endpoint_decoder(struct device *dev);
>  struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
> diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
> index 9675243bd05b..ac152f58df98 100644
> --- a/drivers/cxl/mem.c
> +++ b/drivers/cxl/mem.c
> @@ -130,12 +130,19 @@ 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 +226,13 @@ 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;
> +

Are these changes to cxl/mem.c supposed to be in patch 09/23? They aren't related to this one
as far as I can tell...

>  	if (a == &dev_attr_trigger_poison_list.attr)
>  		if (!test_bit(CXL_POISON_ENABLED_LIST,
>  			      mds->poison.enabled_cmds))
> diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
> index 340503d7c33c..6ca6230d1fe5 100644
> --- a/include/cxl/cxl.h
> +++ b/include/cxl/cxl.h
> @@ -25,6 +25,9 @@ enum cxl_devtype {
>  
>  struct device;
>  
> +#define CXL_DECODER_F_RAM   BIT(0)
> +#define CXL_DECODER_F_PMEM  BIT(1)
> +#define CXL_DECODER_F_TYPE2 BIT(2)
>  
>  /* Capabilities as defined for:
>   *
> @@ -244,4 +247,12 @@ void cxl_mem_dpa_init(struct cxl_dpa_info *info, u64 volatile_bytes,
>  int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info);
>  struct cxl_memdev *devm_cxl_add_memdev(struct device *host,
>  				       struct cxl_dev_state *cxlmds);
> +struct cxl_memdev *devm_cxl_add_memdev(struct device *host,
> +				       struct cxl_dev_state *cxlds);

This declaration is duplicated

> +struct cxl_port;
> +struct cxl_root_decoder *cxl_get_hpa_freespace(struct cxl_memdev *cxlmd,
> +					       int interleave_ways,
> +					       unsigned long flags,
> +					       resource_size_t *max);
> +void cxl_put_root_decoder(struct cxl_root_decoder *cxlrd);
>  #endif