Re: [PATCH v15 3/8] cxl/cdat: Gather DSMAS data for DCD partitions

[Dave Jiang <dave.jiang@intel.com>]

On 10/7/26 1:16 PM, Anisa Su wrote:
> From: Ira Weiny <iweiny@kernel.org>
> 
> Additional DCD partition (AKA region) information is contained in the
> DSMAS CDAT tables, including performance, shareable and read-only
> attributes.
> 
> Match DCD partitions with DSMAS tables and store the meta data. A DCD
> shall describe its DC partition in a DSMAS entry (CXL r4.0 9.13.3), so
> if the CDAT is absent, fails to parse, or has no entry matching the DC
> partition, disable DCD rather than run with unknown attributes.
> 
> DSLBIS is optional, but cxl_cdat_endpoint_process() treated zero DSLBIS
> entries as a parse failure, which would now disable DCD on a device with
> a valid DSMAS. Accept an empty DSLBIS, and skip DSMAS entries with no
> DSLBIS coordinates.
> 
> Signed-off-by: Ira Weiny <iweiny@kernel.org>
> Co-developed-by: Anisa Su <anisa.su@samsung.com>
> Signed-off-by: Anisa Su <anisa.su@samsung.com>
> 
> ---
> Changes:
> 1. cdat.c: disable DCD when the DC partition has no valid DSMAS entry:
>    no CDAT, CDAT parse failure, or no entry matching the partition.
>    [Richard, Dave]
> 2. cdat.c: DSLBIS is optional. An empty DSLBIS no longer fails the
>    CDAT parse, and cxl_port_perf_data_calculate() skips entries that
>    have no DSLBIS coordinates.
>    [Richard, Dave]
> 3. cdat.c: cxl_memdev_apply_dsmas() takes an enum cxl_dsmas_apply
>    instead of a bool so the call sites say what is applied.
>    [Dave]
> 4. Also record the DSMAS read-only flag (CDAT 1.04, Flags bit 6) on
>    the partition, alongside shareable.
>    [Jonathan]
> ---
>  drivers/cxl/core/cdat.c   | 97 ++++++++++++++++++++++++++++++++++-----
>  drivers/cxl/core/hdm.c    |  1 +
>  drivers/cxl/core/mbox.c   |  9 ++++
>  drivers/cxl/core/memdev.c | 17 ++++---
>  drivers/cxl/cxlmem.h      |  2 +
>  include/cxl/cxl.h         |  6 +++
>  6 files changed, 113 insertions(+), 19 deletions(-)
> 
> diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
> index 5c9f07262513..07aedff657d9 100644
> --- a/drivers/cxl/core/cdat.c
> +++ b/drivers/cxl/core/cdat.c
> @@ -17,6 +17,8 @@ struct dsmas_entry {
>  	struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX];
>  	int entries;
>  	int qos_class;
> +	bool shareable;
> +	bool read_only;
>  };
>  
>  static u32 cdat_normalize(u16 entry, u64 base, u8 type)
> @@ -74,6 +76,10 @@ static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
>  		return -ENOMEM;
>  
>  	dent->handle = dsmas->dsmad_handle;
> +	/* Shareable is CDAT 1.03 and later, DSMAS Flags bit 3 */
> +	dent->shareable = dsmas->flags & ACPI_CDAT_DSMAS_SHAREABLE;
> +	/* Read Only is CDAT 1.04 and later, DSMAS Flags bit 6 */
> +	dent->read_only = dsmas->flags & ACPI_CDAT_DSMAS_READ_ONLY;
>  	dent->dpa_range.start = le64_to_cpu((__force __le64)dsmas->dpa_base_address);
>  	dent->dpa_range.end = le64_to_cpu((__force __le64)dsmas->dpa_base_address) +
>  			      le64_to_cpu((__force __le64)dsmas->dpa_length) - 1;
> @@ -188,9 +194,10 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port,
>  	if (rc)
>  		return rc;
>  
> +	/* DSLBIS is optional; zero entries is not an error */
>  	rc = cdat_table_parse(ACPI_CDAT_TYPE_DSLBIS, cdat_dslbis_handler,
>  			      dsmas_xa, port->cdat.table, port->cdat.length);
> -	return cdat_table_parse_output(rc);
> +	return rc < 0 ? rc : 0;
>  }
>  
>  static int cxl_port_perf_data_calculate(struct cxl_port *port,
> @@ -219,6 +226,13 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port,
>  	xa_for_each(dsmas_xa, index, dent) {
>  		int qos_class;
>  
> +		/* No DSLBIS for this DSMAS; nothing to hand the QTG _DSM */
> +		if (!dent->cdat_coord[ACCESS_COORDINATE_CPU].read_bandwidth &&
> +		    !dent->cdat_coord[ACCESS_COORDINATE_CPU].write_bandwidth &&
> +		    !dent->cdat_coord[ACCESS_COORDINATE_CPU].read_latency &&
> +		    !dent->cdat_coord[ACCESS_COORDINATE_CPU].write_latency)
> +			continue;
> +
>  		cxl_coordinates_combine(dent->coord, dent->cdat_coord, ep_c);
>  		dent->entries = 1;
>  		rc = cxl_root->ops.qos_class(cxl_root,
> @@ -255,35 +269,90 @@ static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
>  		dent->coord[ACCESS_COORDINATE_CPU].write_latency);
>  }
>  
> -static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
> -				     struct xarray *dsmas_xa)
> +/*
> + * A DCD shall describe its DC partition in a DSMAS entry (CXL r4.0 9.13.3).
> + * Without one the partition's attributes are unknown, so disable DCD.
> + */
> +static void cxl_dcd_dsmas_missing(struct cxl_dev_state *cxlds, const char *why)
> +{
> +	struct cxl_memdev_state *mds;
> +
> +	if (cxlds->type != CXL_DEVTYPE_CLASSMEM)
> +		return;
> +
> +	mds = to_cxl_memdev_state(cxlds);
> +	if (!cxl_dcd_supported(mds) ||
> +	    !cxl_part_size(cxlds, CXL_PARTMODE_DYNAMIC_RAM))
> +		return;
> +
> +	dev_warn(cxlds->dev, "DC partition has no valid DSMAS entry (%s), disabling DCD\n",
> +		 why);
> +	cxl_disable_dcd(mds);
> +}
> +
> +enum cxl_dsmas_apply {
> +	CXL_DSMAS_APPLY_FLAGS,		/* shareable etc.; no QTG data */
> +	CXL_DSMAS_APPLY_FLAGS_PERF,	/* perf coordinates and qos_class */
> +};
> +
> +/*
> + * DSMAS flags such as shareable are properties of the CDAT entry and are
> + * applied regardless; perf data is applied only if the QTG lookup produced
> + * recommendations.
> + */
> +static void cxl_memdev_apply_dsmas(struct cxl_dev_state *cxlds,
> +				   struct xarray *dsmas_xa,
> +				   enum cxl_dsmas_apply attrs)
>  {
>  	struct device *dev = cxlds->dev;
>  	struct dsmas_entry *dent;
> +	bool dc_matched = false;
>  	unsigned long index;
>  
>  	xa_for_each(dsmas_xa, index, dent) {
>  		bool found = false;
>  
>  		for (int i = 0; i < cxlds->nr_partitions; i++) {
> -			struct resource *res = &cxlds->part[i].res;
> +			struct cxl_dpa_partition *part = &cxlds->part[i];
>  			struct range range = {
> -				.start = res->start,
> -				.end = res->end,
> +				.start = part->res.start,
> +				.end = part->res.end,
>  			};
>  
> -			if (range_contains(&range, &dent->dpa_range)) {
> -				update_perf_entry(dev, dent,
> -						  &cxlds->part[i].perf);
> -				found = true;
> +			if (!range_contains(&range, &dent->dpa_range))
> +				continue;
> +
> +			found = true;
> +			/*
> +			 * part->handle is from Get DC Config, dent->handle
> +			 * from the CDAT DSMAS entry.
> +			 */
> +			if (part->mode == CXL_PARTMODE_DYNAMIC_RAM &&
> +			    dent->handle != part->handle) {
> +				dev_warn(dev,
> +					 "DSMAD handle mismatch: %pra has %u, DSMAS %pra has %u\n",
> +					 &range, part->handle,
> +					 &dent->dpa_range, dent->handle);
>  				break;
>  			}
> +
> +			if (attrs == CXL_DSMAS_APPLY_FLAGS_PERF)
> +				update_perf_entry(dev, dent, &part->perf);
> +			if (part->mode == CXL_PARTMODE_DYNAMIC_RAM) {
> +				part->shareable = dent->shareable;
> +				part->read_only = dent->read_only;
> +				dc_matched = true;

Should be able to just return here and avoid the dc_matched flag right?


> +			}
> +			break;
>  		}
>  
>  		if (!found)
>  			dev_dbg(dev, "no partition for dsmas dpa: %pra\n",
>  				&dent->dpa_range);
>  	}
> +
> +	if (!dc_matched)
> +		cxl_dcd_dsmas_missing(cxlds, "no matching entry");
>  }
>  
>  static int match_cxlrd_qos_class(struct device *dev, void *data)
> @@ -409,22 +478,26 @@ void cxl_endpoint_parse_cdat(struct cxl_port *port)
>  	int rc;
>  
>  	xa_init(&__dsmas_xa);
> -	if (!port->cdat.table)
> +	if (!port->cdat.table) {
> +		cxl_dcd_dsmas_missing(cxlds, "no CDAT");
>  		return;
> +	}
>  
>  	rc = cxl_cdat_endpoint_process(port, dsmas_xa);
>  	if (rc < 0) {
>  		dev_dbg(&port->dev, "Failed to parse CDAT: %d\n", rc);
> +		cxl_dcd_dsmas_missing(cxlds, "CDAT parse failed");
>  		return;
>  	}
>  
>  	rc = cxl_port_perf_data_calculate(port, dsmas_xa);
>  	if (rc) {
>  		dev_dbg(&port->dev, "Failed to do perf coord calculations.\n");
> +		cxl_memdev_apply_dsmas(cxlds, dsmas_xa, CXL_DSMAS_APPLY_FLAGS);
>  		return;
>  	}
>  
> -	cxl_memdev_set_qos_class(cxlds, dsmas_xa);
> +	cxl_memdev_apply_dsmas(cxlds, dsmas_xa, CXL_DSMAS_APPLY_FLAGS_PERF);
>  	cxl_qos_class_verify(cxlmd);
>  	cxl_memdev_update_perf(cxlmd);
>  }
> diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
> index 5fa2177cefcc..379540246333 100644
> --- a/drivers/cxl/core/hdm.c
> +++ b/drivers/cxl/core/hdm.c
> @@ -486,6 +486,7 @@ int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info)
>  
>  		cxlds->part[i].perf.qos_class = CXL_QOS_CLASS_INVALID;
>  		cxlds->part[i].mode = part->mode;
> +		cxlds->part[i].handle = part->handle;
>  
>  		/* Require ordered + contiguous partitions */
>  		if (i) {
> diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
> index 72af23ba288e..12598d329e95 100644
> --- a/drivers/cxl/core/mbox.c
> +++ b/drivers/cxl/core/mbox.c
> @@ -1366,6 +1366,7 @@ static int cxl_dc_check(struct device *dev, struct cxl_dc_partition_info *part,
>  	u64 decode_len = le64_to_cpu(dev_part->decode_length);
>  	u64 blk_size = le64_to_cpu(dev_part->block_size);
>  	u64 len = le64_to_cpu(dev_part->length);
> +	u32 handle = le32_to_cpu(dev_part->dsmad_handle);
>  	u64 size;
>  
>  	/*
> @@ -1378,6 +1379,13 @@ static int cxl_dc_check(struct device *dev, struct cxl_dc_partition_info *part,
>  		return 0;
>  	}
>  
> +	/* The CDAT DSMAD handle this refers to is 8 bits */
> +	if (handle & ~0xFF) {

Define a mask?

DJ

> +		dev_warn(dev, "DSMAD handle 0x%x exceeds the 8 bit CDAT DSMAD handle\n",
> +			 handle);
> +		return -EINVAL;
> +	}
> +
>  	/*
>  	 * Decode length is a count of 256M units, so a device reporting 2^36
>  	 * or more wraps.
> @@ -1391,6 +1399,7 @@ static int cxl_dc_check(struct device *dev, struct cxl_dc_partition_info *part,
>  	*part = (struct cxl_dc_partition_info) {
>  		.start = le64_to_cpu(dev_part->base),
>  		.size = size,
> +		.handle = handle,
>  	};
>  
>  	/*
> diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
> index def26c490dfe..7aa79a1a53e4 100644
> --- a/drivers/cxl/core/memdev.c
> +++ b/drivers/cxl/core/memdev.c
> @@ -594,7 +594,8 @@ bool is_cxl_memdev(const struct device *dev)
>  }
>  EXPORT_SYMBOL_NS_GPL(is_cxl_memdev, "CXL");
>  
> -static void add_part(struct cxl_dpa_info *info, u64 start, u64 size, enum cxl_partition_mode mode)
> +static void add_part(struct cxl_dpa_info *info, u64 start, u64 size,
> +		     enum cxl_partition_mode mode, u8 handle)
>  {
>  	int i = info->nr_partitions;
>  
> @@ -606,6 +607,7 @@ static void add_part(struct cxl_dpa_info *info, u64 start, u64 size, enum cxl_pa
>  		.end = start + size - 1,
>  	};
>  	info->part[i].mode = mode;
> +	info->part[i].handle = handle;
>  	info->nr_partitions++;
>  }
>  
> @@ -623,9 +625,9 @@ int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
>  	info->size = mds->total_bytes;
>  
>  	if (mds->partition_align_bytes == 0) {
> -		add_part(info, 0, mds->volatile_only_bytes, CXL_PARTMODE_RAM);
> +		add_part(info, 0, mds->volatile_only_bytes, CXL_PARTMODE_RAM, 0);
>  		add_part(info, mds->volatile_only_bytes,
> -			 mds->persistent_only_bytes, CXL_PARTMODE_PMEM);
> +			 mds->persistent_only_bytes, CXL_PARTMODE_PMEM, 0);
>  		return 0;
>  	}
>  
> @@ -635,9 +637,9 @@ int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
>  		return rc;
>  	}
>  
> -	add_part(info, 0, mds->active_volatile_bytes, CXL_PARTMODE_RAM);
> +	add_part(info, 0, mds->active_volatile_bytes, CXL_PARTMODE_RAM, 0);
>  	add_part(info, mds->active_volatile_bytes, mds->active_persistent_bytes,
> -		 CXL_PARTMODE_PMEM);
> +		 CXL_PARTMODE_PMEM, 0);
>  
>  	return 0;
>  }
> @@ -685,7 +687,8 @@ int cxl_configure_dcd(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
>  	info->size = total;
>  	dev_dbg(dev, "Adding dynamic ram partition; %#llx size %#llx\n",
>  		dc_info.start, dc_info.size);
> -	add_part(info, dc_info.start, dc_info.size, CXL_PARTMODE_DYNAMIC_RAM);
> +	add_part(info, dc_info.start, dc_info.size, CXL_PARTMODE_DYNAMIC_RAM,
> +		 dc_info.handle);
>  
>  	return 0;
>  }
> @@ -703,7 +706,7 @@ int cxl_set_capacity(struct cxl_dev_state *cxlds, u64 capacity)
>  		.size = capacity,
>  	};
>  
> -	add_part(&range_info, 0, capacity, CXL_PARTMODE_RAM);
> +	add_part(&range_info, 0, capacity, CXL_PARTMODE_RAM, 0);
>  	return cxl_dpa_setup(cxlds, &range_info);
>  }
>  EXPORT_SYMBOL_NS_GPL(cxl_set_capacity, "CXL");
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index 4fac65dbb808..9fd5af2e41d4 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -140,6 +140,7 @@ struct cxl_dpa_info {
>  	struct cxl_dpa_part_info {
>  		struct range range;
>  		enum cxl_partition_mode mode;
> +		u8 handle;
>  	} part[CXL_NR_PARTITIONS_MAX];
>  	int nr_partitions;
>  };
> @@ -851,6 +852,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds);
>  struct cxl_dc_partition_info {
>  	u64 start;
>  	u64 size;
> +	u8 handle;
>  };
>  
>  int cxl_dev_dc_identify(struct cxl_mailbox *mbox,
> diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
> index e07360849344..728decda57fd 100644
> --- a/include/cxl/cxl.h
> +++ b/include/cxl/cxl.h
> @@ -141,11 +141,17 @@ enum cxl_partition_mode {
>   * @res: shortcut to the partition in the DPA resource tree (cxlds->dpa_res)
>   * @perf: performance attributes of the partition from CDAT
>   * @mode: operation mode for the DPA capacity, e.g. ram, pmem, dynamic...
> + * @handle: DSMAS handle that represents this partition
> + * @shareable: Is the partition shareable (from its CDAT DSMAS entry)
> + * @read_only: Is the partition read-only (from its CDAT DSMAS entry)
>   */
>  struct cxl_dpa_partition {
>  	struct resource res;
>  	struct cxl_dpa_perf perf;
>  	enum cxl_partition_mode mode;
> +	u8 handle;
> +	bool shareable;
> +	bool read_only;
>  };
>  
>  #define CXL_NR_PARTITIONS_MAX 3