Re: [PATCH 03/26] cxl/mem: Read dynamic capacity configuration from the device

[Jonathan Cameron <Jonathan.Cameron@Huawei.com>]

On Sun, 24 Mar 2024 16:18:06 -0700
ira.weiny@intel.com wrote:

> From: Navneet Singh <navneet.singh@intel.com>
> 
> Devices can optionally support Dynamic Capacity (DC).  These devices are
> known as Dynamic Capacity Devices (DCD).
> 
> Implement the DC mailbox commands as specified in CXL 3.1 section
> 8.2.9.9.9 (opcodes 48XXh).  Read the DC configuration and store the DC
> region information in the device state.
> 
> Signed-off-by: Navneet Singh <navneet.singh@intel.com>
> Co-developed-by: Ira Weiny <ira.weiny@intel.com>
> Signed-off-by: Ira Weiny <ira.weiny@intel.com>

A few minor things inline,

Jonathan

> 
> ---
> Changes for v1
> [Jørgen: ensure CXL 2.0 device support by removing dc_event_log_size]
> [iweiny/Jørgen: use get DC config command to signal DCD support]
> [djiang: fix subject]
> [Fan: add additional region configuration checks]
> [Jonathan/djiang: split out region mode changes]
> [Jonathan: fix up comments/kdoc]
> [Jonathan: s/cxl_get_dc_id/cxl_get_dc_config/]
> [Jonathan: use __free() in identify call]
> [Jonathan: remove unneeded formatting changes]
> [Jonathan: s/cxl_mbox_dynamic_capacity/cxl_mbox_get_dc_config_out/]
> [Jonathan: s/cxl_mbox_get_dc_config/cxl_mbox_get_dc_config_in/]
> [iweiny: remove type2 work dependancy/rebase on master]
> [iweiny: fix 0day build issues]
> ---
>  drivers/cxl/core/mbox.c | 184 +++++++++++++++++++++++++++++++++++++++++++++++-
>  drivers/cxl/cxlmem.h    |  49 +++++++++++++
>  drivers/cxl/pci.c       |   4 ++
>  3 files changed, 236 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
> index ed4131c6f50b..14e8a7528a8b 100644
> --- a/drivers/cxl/core/mbox.c
> +++ b/drivers/cxl/core/mbox.c
> @@ -1123,7 +1123,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds)
>  	if (rc < 0)
>  		return rc;
>  
> -	mds->total_bytes =
> +	mds->static_cap =
>  		le64_to_cpu(id.total_capacity) * CXL_CAPACITY_MULTIPLIER;
>  	mds->volatile_only_bytes =
>  		le64_to_cpu(id.volatile_capacity) * CXL_CAPACITY_MULTIPLIER;
> @@ -1230,6 +1230,175 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd)
>  	return rc;
>  }
>  
> +static int cxl_dc_save_region_info(struct cxl_memdev_state *mds, u8 index,
> +				   struct cxl_dc_region_config *region_config)
> +{
> +	struct cxl_dc_region_info *dcr = &mds->dc_region[index];
> +	struct device *dev = mds->cxlds.dev;
> +
> +	dcr->base = le64_to_cpu(region_config->region_base);
> +	dcr->decode_len = le64_to_cpu(region_config->region_decode_length);
> +	dcr->decode_len *= CXL_CAPACITY_MULTIPLIER;
> +	dcr->len = le64_to_cpu(region_config->region_length);
> +	dcr->blk_size = le64_to_cpu(region_config->region_block_size);
> +	dcr->dsmad_handle = le32_to_cpu(region_config->region_dsmad_handle);
> +	dcr->flags = region_config->flags;
> +	snprintf(dcr->name, CXL_DC_REGION_STRLEN, "dc%d", index);
> +
> +	/* Check regions are in increasing DPA order */
> +	if (index > 0) {
> +		struct cxl_dc_region_info *prev_dcr = &mds->dc_region[index - 1];
> +
> +		if ((prev_dcr->base + prev_dcr->decode_len) > dcr->base) {
> +			dev_err(dev,
> +				"DPA ordering violation for DC region %d and %d\n",
> +				index - 1, index);
> +			return -EINVAL;
> +		}
> +	}
> +
> +	if (!IS_ALIGNED(dcr->base, SZ_256M) ||
> +	    !IS_ALIGNED(dcr->base, dcr->blk_size)) {
> +		dev_err(dev, "DC region %d invalid base %#llx blk size %#llx\n", index,

Odd choice of line wrap.  I'd drag index onto the line below.

> +			dcr->base, dcr->blk_size);
> +		return -EINVAL;
> +	}
> +
> +	if (dcr->decode_len == 0 || dcr->len == 0 || dcr->decode_len < dcr->len ||
> +	    !IS_ALIGNED(dcr->len, dcr->blk_size)) {
> +		dev_err(dev, "DC region %d invalid length; decode %#llx len %#llx blk size %#llx\n",
> +			index, dcr->decode_len, dcr->len, dcr->blk_size);
> +		return -EINVAL;
> +	}
> +
> +	if (dcr->blk_size == 0 || dcr->blk_size % 0x40 ||

Hmm. I thought we had a define for CXL 'cacheline' size, but can't find it now.
If not we should add one (and find a better name than that).

> +	    !is_power_of_2(dcr->blk_size)) {
> +		dev_err(dev, "DC region %d invalid block size; %#llx\n",
> +			index, dcr->blk_size);
> +		return -EINVAL;
> +	}
> +
> +	dev_dbg(dev,
> +		"DC region %s DPA: %#llx LEN: %#llx BLKSZ: %#llx\n",
> +		dcr->name, dcr->base, dcr->decode_len, dcr->blk_size);
> +
> +	return 0;
> +}
> +
> +/* Returns the number of regions in dc_resp or -ERRNO */
> +static int cxl_get_dc_config(struct cxl_memdev_state *mds, u8 start_region,
> +			     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) {
> +		.region_count = CXL_MAX_DC_REGION,
> +		.start_region_index = start_region,
> +	};
> +	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 = 1,
> +	};
> +	struct device *dev = mds->cxlds.dev;
> +	int rc;
> +
> +	rc = cxl_internal_send_cmd(mds, &mbox_cmd);
> +	if (rc < 0)
> +		return rc;
> +
> +	rc = dc_resp->avail_region_count - start_region;
> +
> +	/*
> +	 * The number of regions in the payload may have been truncated due to
> +	 * payload_size limits; if so adjust the returned count to match.
> +	 */
> +	if (mbox_cmd.size_out < sizeof(*dc_resp))
> +		rc = CXL_REGIONS_RETURNED(mbox_cmd.size_out);

Why not always return this?  If there was space, doesn't it equal
the value set above anyway?

> +
> +	dev_dbg(dev, "Read %d/%d DC regions\n", rc, dc_resp->avail_region_count);
> +
> +	return rc;
> +}

> +/**
> + * cxl_dev_dynamic_capacity_identify() - Reads the dynamic capacity
> + *					 information from the device.
> + * @mds: The memory device state
> + *
> + * Read Dynamic Capacity information from the device and populate the state
> + * structures for later use.
> + *
> + * Return: 0 if identify was executed successfully, -ERRNO on error.
> + */
> +int cxl_dev_dynamic_capacity_identify(struct cxl_memdev_state *mds)
> +{
> +	size_t dc_resp_size = mds->payload_size;
> +	struct device *dev = mds->cxlds.dev;
> +	u8 start_region, i;
> +	int rc = 0;

Is this used before being set?

> +
> +	for (i = 0; i < CXL_MAX_DC_REGION; i++)
> +		snprintf(mds->dc_region[i].name, CXL_DC_REGION_STRLEN, "<nil>");
> +
> +	/* Check GET_DC_CONFIG is supported by device */
> +	if (!cxl_dcd_supported(mds)) {
> +		dev_dbg(dev, "DCD not supported\n");
> +		return 0;
> +	}
> +
> +	struct cxl_mbox_get_dc_config_out *dc_resp __free(kfree) =
> +					kvmalloc(dc_resp_size, GFP_KERNEL);
> +	if (!dc_resp)
> +		return -ENOMEM;
> +
> +	start_region = 0;
> +	do {
> +		int j;
> +
> +		rc = cxl_get_dc_config(mds, start_region, dc_resp, dc_resp_size);
> +		if (rc < 0) {
> +			dev_dbg(dev, "Failed to get DC config: %d\n", rc);
> +			return rc;
> +		}
> +
> +		mds->nr_dc_region += rc;
> +
> +		if (mds->nr_dc_region < 1 || mds->nr_dc_region > CXL_MAX_DC_REGION) {
> +			dev_err(dev, "Invalid num of dynamic capacity regions %d\n",
> +				mds->nr_dc_region);
> +			return -EINVAL;
> +		}
> +
> +		for (i = start_region, j = 0; i < mds->nr_dc_region; i++, j++) {
> +			rc = cxl_dc_save_region_info(mds, i, &dc_resp->region[j]);
> +			if (rc) {
> +				dev_dbg(dev, "Failed to save region info: %d\n", rc);
> +				return rc;
> +			}
> +		}
> +
> +		start_region = mds->nr_dc_region;
> +
> +	} while (mds->nr_dc_region < dc_resp->avail_region_count);
> +
> +	mds->dynamic_cap =
> +		mds->dc_region[mds->nr_dc_region - 1].base +
> +		mds->dc_region[mds->nr_dc_region - 1].decode_len -
> +		mds->dc_region[0].base;
> +	dev_dbg(dev, "Total dynamic capacity: %#llx\n", mds->dynamic_cap);
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_dev_dynamic_capacity_identify, CXL);



> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index 79a67cff9143..4624cf612c1e 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h

>  /**
>   * struct cxl_memdev_state - Generic Type-3 Memory Device Class driver data
>   *
> @@ -467,6 +482,8 @@ struct cxl_dev_state {
>   * @enabled_cmds: Hardware commands found enabled in CEL.
>   * @exclusive_cmds: Commands that are kernel-internal only
>   * @total_bytes: sum of all possible capacities
> + * @static_cap: Sum of static RAM and PMEM capacities
> + * @dynamic_cap: Complete DPA range occupied by DC regions
>   * @volatile_only_bytes: hard volatile capacity
>   * @persistent_only_bytes: hard persistent capacity
>   * @partition_align_bytes: alignment size for partition-able capacity
> @@ -474,6 +491,8 @@ struct cxl_dev_state {
>   * @active_persistent_bytes: sum of hard + soft persistent
>   * @next_volatile_bytes: volatile capacity change pending device reset
>   * @next_persistent_bytes: persistent capacity change pending device reset

Looks like we have some ordering issues ram_perf and pmem_perf (at least)
that we should fix up as a precursor. I sent a reply to the QoS patch
that added these.

> + * @nr_dc_region: number of DC regions implemented in the memory device
> + * @dc_region: array containing info about the DC regions
>   * @event: event log driver state
>   * @poison: poison driver state info
>   * @security: security driver state info
> @@ -494,7 +513,10 @@ struct cxl_memdev_state {
>  	DECLARE_BITMAP(dcd_cmds, CXL_DCD_ENABLED_MAX);
>  	DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX);
>  	DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX);
> +
Trivial but this is an unrelated change and shouldn't be in this patch.

>  	u64 total_bytes;
> +	u64 static_cap;
> +	u64 dynamic_cap;
>  	u64 volatile_only_bytes;
>  	u64 persistent_only_bytes;
>  	u64 partition_align_bytes;
> @@ -506,6 +528,9 @@ struct cxl_memdev_state {
>  	struct cxl_dpa_perf ram_perf;
>  	struct cxl_dpa_perf pmem_perf;
>  
> +	u8 nr_dc_region;
> +	struct cxl_dc_region_info dc_region[CXL_MAX_DC_REGION];
> +
>  	struct cxl_event_state event;
>  	struct cxl_poison_state poison;
>  	struct cxl_security_state security;

> +
> +/* See CXL 3.0 Table 125 get dynamic capacity config Output Payload */
> +struct cxl_mbox_get_dc_config_out {
> +	u8 avail_region_count;
> +	u8 rsvd[7];
> +	struct cxl_dc_region_config {
> +		__le64 region_base;
> +		__le64 region_decode_length;
> +		__le64 region_length;
> +		__le64 region_block_size;
> +		__le32 region_dsmad_handle;
> +		u8 flags;
> +		u8 rsvd[3];
> +	} __packed region[];
> +} __packed;
> +#define CXL_DYNAMIC_CAPACITY_SANITIZE_ON_RELEASE_FLAG BIT(0)
> +#define CXL_REGIONS_RETURNED(size_out) \
> +	((size_out - 8) / sizeof(struct cxl_dc_region_config))

Can we make that 8 self documenting?
offsetof(struct cxl_dc_region_config, region) perhaps?

> +