Re: [PATCH v12 2/8] cxl/mem: Read dynamic capacity configuration from the device

On Fri, Jul 31, 2026 at 01:48:07AM +0800, Anisa Su wrote:
> From: Ira Weiny <[email protected]>
> 
> Devices which optionally support Dynamic Capacity (DC) are configured
> via mailbox commands.  CXL r4.0 section 9.13.3 requires the host to issue
> the Get DC Configuration command in order to properly configure DCDs.
> Without the Get DC Configuration command DCD can't be supported.
> 
> Implement the DC mailbox commands as specified in CXL 4.0 section
> 8.2.10.9.9 (opcodes 48XXh) to read and store the DCD configuration
> information.  Disable DCD if an invalid configuration is found.
> 
> Linux has no support for more than one dynamic capacity partition.  Read
> and validate all the partitions but configure only the first partition
> as 'dynamic ram 1'.  Additional partitions can be added in the future if
> such a device ever materializes.  Additionally it is anticipated that no
> skips will be present from the end of the pmem partition.  Check for and
> disallow this configuration as well.
> 
> Based on an original patch by Navneet Singh.
> 
> Signed-off-by: Ira Weiny <[email protected]>
> Signed-off-by: Anisa Su <[email protected]>
> Tested-by: Wonjae Lee <[email protected]>
> Tested-by: Junhee Park <[email protected]>
> Tested-by: Heesoo Kim <[email protected]>
> 
> ---
> Changes:
> 1. mbox.c: bound the Get DC Config request by the negotiated mailbox
>    payload. Requesting all CXL_MAX_DC_PARTITIONS (8) needs a 328-byte
>    response, which exceeds a spec-minimum 256-byte mailbox and fails
>    -E2BIG, disabling DCD. Cap partition_count per call to what the
>    payload holds and read the rest via the existing start_partition
>    loop.
> ---
>  drivers/cxl/core/hdm.c  |   2 +
>  drivers/cxl/core/mbox.c | 220 ++++++++++++++++++++++++++++++++++++++++
>  drivers/cxl/cxlmem.h    |  55 ++++++++++
>  drivers/cxl/pci.c       |   3 +
>  include/cxl/cxl.h       |   3 +-
>  5 files changed, 282 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
> index 0c80b76a5f9b..0ef076c08ed2 100644
> --- a/drivers/cxl/core/hdm.c
> +++ b/drivers/cxl/core/hdm.c
> @@ -446,6 +446,8 @@ static const char *cxl_mode_name(enum cxl_partition_mode mode)
>  		return "ram";
>  	case CXL_PARTMODE_PMEM:
>  		return "pmem";
> +	case CXL_PARTMODE_DYNAMIC_RAM_1:
> +		return "dynamic_ram_1";
>  	default:
>  		return "";
>  	};
> diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
> index 4790524c32a7..d79019fbd790 100644
> --- a/drivers/cxl/core/mbox.c
> +++ b/drivers/cxl/core/mbox.c
> @@ -1352,6 +1352,197 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd)
>  	return -EBUSY;
>  }
>  
> +static int cxl_dc_check(struct device *dev, struct cxl_dc_partition_info *part_array,
> +			u8 index, struct cxl_dc_partition *dev_part)
> +{
> +	u64 blk_size = le64_to_cpu(dev_part->block_size);
> +	u64 len = le64_to_cpu(dev_part->length);
> +
> +	part_array[index].start = le64_to_cpu(dev_part->base);
> +	part_array[index].size = le64_to_cpu(dev_part->decode_length);
> +	part_array[index].size *= CXL_CAPACITY_MULTIPLIER;
> +
> +	/* Check partitions are in increasing DPA order */
> +	if (index > 0) {
> +		struct cxl_dc_partition_info *prev_part = &part_array[index - 1];
> +
> +		if ((prev_part->start + prev_part->size) >
> +		     part_array[index].start) {
> +			dev_err(dev,
> +				"DPA ordering violation for DC partition %d and %d\n",
> +				index - 1, index);
> +			return -EINVAL;
> +		}
> +	}
> +
> +	if (part_array[index].size == 0 || len == 0 ||
> +	    part_array[index].size < len || !IS_ALIGNED(len, blk_size)) {
> +		dev_err(dev, "DC partition %d invalid length; size %llu len %llu blk size %llu\n",
> +			index, part_array[index].size, len, blk_size);
> +		return -EINVAL;
> +	}
> +

Hi Anisa,

I think here , 0s are legal, according to spec CXL 4.0 8.2.10.9.9.1 "Get Dynamic Capacity Configuration",
Table 8-347 "DC Region Configuration". It says "Report 0 if the region is unavailable for Dynamici Capacity"

Imagine if we have a device ports 8 regions and only region 0 is configured, regions 1~7 come back with 0s.
cxl_dc_check() will check them all, so the first zero region fails and cxl_configure_dcd() ends up disabling
DCD on a device that is perfectly fine.

Maybe we should skip the all-zero regions instead of rejecting them ?

Best regards,
Richard Cheng.

> +	if (blk_size == 0 || blk_size % CXL_DCD_BLOCK_LINE_SIZE ||
> +	    !is_power_of_2(blk_size)) {
> +		dev_err(dev, "DC partition %d invalid block size %llu\n",
> +			index, blk_size);
> +		return -EINVAL;
> +	}
> +
> +	if (!IS_ALIGNED(part_array[index].start, SZ_256M) ||
> +	    !IS_ALIGNED(part_array[index].start, blk_size)) {
> +		dev_err(dev, "DC partition %d invalid start %llu blk size %llu\n",
> +			index, part_array[index].start, blk_size);
> +		return -EINVAL;
> +	}
> +
> +	dev_dbg(dev, "DC partition %d start %llu size %llu blk_size: %llu\n",
> +		index, part_array[index].start, part_array[index].size,
> +		blk_size);
> +
> +	return 0;
> +}
> +
> +/* Returns the number of partitions in dc_resp or -ERRNO */
> +static int cxl_get_dc_config(struct cxl_mailbox *mbox, u8 start_partition,
> +			     u8 partition_count,
> +			     struct cxl_mbox_get_dc_config_out *dc_resp,
> +			     size_t dc_resp_size)
> +{
> +	struct cxl_mbox_get_dc_config_in get_dc = (struct cxl_mbox_get_dc_config_in) {
> +		.partition_count = partition_count,
> +		.start_partition_index = start_partition,
> +	};
> +	struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) {
> +		.opcode = CXL_MBOX_OP_GET_DC_CONFIG,
> +		.payload_in = &get_dc,
> +		.size_in = sizeof(get_dc),
> +		.size_out = dc_resp_size,
> +		.payload_out = dc_resp,
> +		.min_out = 8,
> +	};
> +	size_t expected_sz;
> +	int rc;
> +
> +	rc = cxl_internal_send_cmd(mbox, &mbox_cmd);
> +	if (rc < 0)
> +		return rc;
> +
> +	if (dc_resp->partitions_returned > partition_count) {
> +		dev_err(mbox->host, "Device returned %u partitions, requested %u\n",
> +			dc_resp->partitions_returned, partition_count);
> +		return -EIO;
> +	}
> +
> +	/*
> +	 * The payload carries trailing extent/tag count fields after the
> +	 * partition array (CXL r4.0 Table 8-179) which the driver ignores, so
> +	 * the response is at least, not exactly, expected_sz.
> +	 */
> +	expected_sz = struct_size(dc_resp, partition,
> +				  dc_resp->partitions_returned);
> +
> +	if (mbox_cmd.size_out < expected_sz) {
> +		dev_err(mbox->host,
> +			"Payload size %zu less than expected %zu for %u partitions\n",
> +			mbox_cmd.size_out,
> +			expected_sz,
> +			dc_resp->partitions_returned);
> +		return -EIO;
> +	}
> +
> +	dev_dbg(mbox->host, "Read %d/%d DC partitions\n",
> +		dc_resp->partitions_returned, dc_resp->avail_partition_count);
> +	return dc_resp->partitions_returned;
> +}
> +
> +/**
> + * cxl_dev_dc_identify() - Reads the dynamic capacity information from the
> + *                         device.
> + * @mbox: Mailbox to query
> + * @dc_info: The dynamic partition information to return
> + *
> + * Read Dynamic Capacity information from the device and return the partition
> + * information.
> + *
> + * Return: 0 if identify was executed successfully, -ERRNO on error.
> + *         on error only dc_info is left unchanged.
> + */
> +int cxl_dev_dc_identify(struct cxl_mailbox *mbox,
> +			struct cxl_dc_partition_info *dc_info)
> +{
> +	struct cxl_dc_partition_info partitions[CXL_MAX_DC_PARTITIONS];
> +	struct cxl_mbox_get_dc_config_out *dc_resp __free(kfree) = NULL;
> +	struct device *dev = mbox->host;
> +	u8 start_partition;
> +	u8 num_partitions;
> +	u8 partition_count;
> +	size_t dc_resp_size;
> +
> +	/* Bound requested number of partitions by mailbox payload size */
> +	partition_count = min_t(size_t, CXL_MAX_DC_PARTITIONS,
> +				(mbox->payload_size - sizeof(*dc_resp) -
> +				 sizeof(struct cxl_mbox_get_dc_config_tail)) /
> +				sizeof(struct cxl_dc_partition));
> +	dc_resp_size = struct_size(dc_resp, partition, partition_count) +
> +		       sizeof(struct cxl_mbox_get_dc_config_tail);
> +
> +	dc_resp = kmalloc(dc_resp_size, GFP_KERNEL);
> +	if (!dc_resp)
> +		return -ENOMEM;
> +
> +	/*
> +	 * Read and check all partition information for validity and potential
> +	 * debugging; see debug output in cxl_dc_check()
> +	 */
> +	start_partition = 0;
> +	num_partitions = 0;
> +	do {
> +		int rc, i, j;
> +
> +		rc = cxl_get_dc_config(mbox, start_partition, partition_count,
> +				       dc_resp, dc_resp_size);
> +		if (rc < 0) {
> +			dev_err(dev, "Failed to get DC config: %d\n", rc);
> +			return rc;
> +		}
> +
> +		if (rc == 0) {
> +			dev_err(dev,
> +				"Device reported %u partitions available but returned none at index %u\n",
> +				dc_resp->avail_partition_count, start_partition);
> +			return -EIO;
> +		}
> +
> +		num_partitions += rc;
> +
> +		if (num_partitions < 1 || num_partitions > CXL_MAX_DC_PARTITIONS) {
> +			dev_err(dev, "Invalid num of dynamic capacity partitions %d\n",
> +				num_partitions);
> +			return -EINVAL;
> +		}
> +
> +		for (i = start_partition, j = 0; i < num_partitions; i++, j++) {
> +			rc = cxl_dc_check(dev, partitions, i,
> +					  &dc_resp->partition[j]);
> +			if (rc)
> +				return rc;
> +		}
> +
> +		start_partition = num_partitions;
> +
> +	} while (num_partitions < dc_resp->avail_partition_count);
> +
> +	/* Return 1st partition */
> +	dc_info->start = partitions[0].start;
> +	dc_info->size = partitions[0].size;
> +	dev_dbg(dev, "Returning partition 0 %llu size %llu\n",
> +		dc_info->start, dc_info->size);
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_dev_dc_identify, "CXL");
> +
>  static void add_part(struct cxl_dpa_info *info, u64 start, u64 size, enum cxl_partition_mode mode)
>  {
>  	int i = info->nr_partitions;
> @@ -1422,6 +1613,35 @@ int cxl_get_dirty_count(struct cxl_memdev_state *mds, u32 *count)
>  }
>  EXPORT_SYMBOL_NS_GPL(cxl_get_dirty_count, "CXL");
>  
> +void cxl_configure_dcd(struct cxl_memdev_state *mds, struct cxl_dpa_info *info)
> +{
> +	struct cxl_dc_partition_info dc_info = { 0 };
> +	struct device *dev = mds->cxlds.dev;
> +	int rc;
> +
> +	rc = cxl_dev_dc_identify(&mds->cxlds.cxl_mbox, &dc_info);
> +	if (rc) {
> +		dev_warn(dev,
> +			 "Failed to read Dynamic Capacity config: %d\n", rc);
> +		cxl_disable_dcd(mds);
> +		return;
> +	}
> +
> +	/* Skips between pmem and the dynamic partition are not supported */
> +	if (dc_info.start != info->size) {
> +		dev_warn(dev,
> +			 "Dynamic Capacity skip from pmem not supported\n");
> +		cxl_disable_dcd(mds);
> +		return;
> +	}
> +
> +	info->size += dc_info.size;
> +	dev_dbg(dev, "Adding dynamic ram partition 1; %llu size %llu\n",
> +		dc_info.start, dc_info.size);
> +	add_part(info, dc_info.start, dc_info.size, CXL_PARTMODE_DYNAMIC_RAM_1);
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_configure_dcd, "CXL");
> +
>  int cxl_arm_dirty_shutdown(struct cxl_memdev_state *mds)
>  {
>  	struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox;
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index 616eeaeee5b9..a9782939d82b 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -407,6 +407,8 @@ struct cxl_security_state {
>  	struct kernfs_node *sanitize_node;
>  };
>  
> +#define CXL_MAX_DC_PARTITIONS 8
> +
>  static inline resource_size_t cxl_pmem_size(struct cxl_dev_state *cxlds)
>  {
>  	/*
> @@ -691,6 +693,39 @@ struct cxl_mbox_set_shutdown_state_in {
>  	u8 state;
>  } __packed;
>  
> +/* See CXL r4.0 Table 8-178 get dynamic capacity config Input Payload */
> +struct cxl_mbox_get_dc_config_in {
> +	u8 partition_count;
> +	u8 start_partition_index;
> +} __packed;
> +
> +/* See CXL r4.0 Table 8-179 get dynamic capacity config Output Payload */
> +struct cxl_mbox_get_dc_config_out {
> +	u8 avail_partition_count;
> +	u8 partitions_returned;
> +	u8 rsvd[6];
> +	/* See CXL r4.0 Table 8-180 */
> +	struct cxl_dc_partition {
> +		__le64 base;
> +		__le64 decode_length;
> +		__le64 length;
> +		__le64 block_size;
> +		__le32 dsmad_handle;
> +		u8 flags;
> +		u8 rsvd[3];
> +	} __packed partition[] __counted_by(partitions_returned);
> +	/* Trailing extent/tag count fields unused */
> +} __packed;
> +
> +/* Trailing counts; cannot be a member after the flex array above */
> +struct cxl_mbox_get_dc_config_tail {
> +	__le32 num_extents_supported;
> +	__le32 num_extents_available;
> +	__le32 num_tags_supported;
> +	__le32 num_tags_available;
> +} __packed;
> +#define CXL_DCD_BLOCK_LINE_SIZE 0x40
> +
>  /* Set Timestamp CXL 3.0 Spec 8.2.9.4.2 */
>  struct cxl_mbox_set_timestamp_in {
>  	__le64 timestamp;
> @@ -814,9 +849,18 @@ enum {
>  int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox,
>  			  struct cxl_mbox_cmd *cmd);
>  int cxl_dev_state_identify(struct cxl_memdev_state *mds);
> +
> +struct cxl_dc_partition_info {
> +	u64 start;
> +	u64 size;
> +};
> +
> +int cxl_dev_dc_identify(struct cxl_mailbox *mbox,
> +			struct cxl_dc_partition_info *dc_info);
>  int cxl_await_media_ready(struct cxl_dev_state *cxlds);
>  int cxl_enumerate_cmds(struct cxl_memdev_state *mds);
>  int cxl_mem_dpa_fetch(struct cxl_memdev_state *mds, struct cxl_dpa_info *info);
> +void cxl_configure_dcd(struct cxl_memdev_state *mds, struct cxl_dpa_info *info);
>  struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev, u64 serial,
>  						 u16 dvsec);
>  void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
> @@ -830,6 +874,17 @@ void cxl_event_trace_record(struct cxl_memdev *cxlmd,
>  			    const uuid_t *uuid, union cxl_event *evt);
>  int cxl_get_dirty_count(struct cxl_memdev_state *mds, u32 *count);
>  int cxl_arm_dirty_shutdown(struct cxl_memdev_state *mds);
> +
> +static inline bool cxl_dcd_supported(struct cxl_memdev_state *mds)
> +{
> +	return mds->dcd_supported;
> +}
> +
> +static inline void cxl_disable_dcd(struct cxl_memdev_state *mds)
> +{
> +	mds->dcd_supported = false;
> +}
> +
>  int cxl_set_timestamp(struct cxl_memdev_state *mds);
>  int cxl_poison_state_init(struct cxl_memdev_state *mds);
>  int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
> index 267c679b0b3c..9b320a2b6fe0 100644
> --- a/drivers/cxl/pci.c
> +++ b/drivers/cxl/pci.c
> @@ -870,6 +870,9 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>  	if (rc)
>  		return rc;
>  
> +	if (cxl_dcd_supported(mds))
> +		cxl_configure_dcd(mds, &range_info);
> +
>  	rc = cxl_dpa_setup(cxlds, &range_info);
>  	if (rc)
>  		return rc;
> diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
> index 016c74fb747c..87c2bd73df21 100644
> --- a/include/cxl/cxl.h
> +++ b/include/cxl/cxl.h
> @@ -133,6 +133,7 @@ struct cxl_dpa_perf {
>  enum cxl_partition_mode {
>  	CXL_PARTMODE_RAM,
>  	CXL_PARTMODE_PMEM,
> +	CXL_PARTMODE_DYNAMIC_RAM_1,
>  };
>  
>  /**
> @@ -147,7 +148,7 @@ struct cxl_dpa_partition {
>  	enum cxl_partition_mode mode;
>  };
>  
> -#define CXL_NR_PARTITIONS_MAX 2
> +#define CXL_NR_PARTITIONS_MAX 3
>  
>  /**
>   * struct cxl_dev_state - The driver device state
> -- 
> 2.43.0
> 
>