Re: [PATCH v7 1/8] cxl: Add BI register probing and port initialization

[Richard Cheng <icheng@nvidia.com>]

On Tue, Jul 28, 2026 at 07:41:29AM +0800, Davidlohr Bueso wrote:
> Add register probing for BI Route Table and BI Decoder capability
> structures in cxl_probe_component_regs(), and helpers to map them.
> 
> cxl_dport_map_bi() maps the BI Decoder of a downstream port (root
> port or switch DSP) at dport-creation time via cxl_port_add_dport();
> cxl_port_map_bi() maps a port's own BI capability during port probe
> when the upstream link is in 256B Flit operation -- BI Decoder for
> an endpoint, BI RT for a switch USP.
> 
> Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
> ---
>  drivers/cxl/core/core.h |  1 +
>  drivers/cxl/core/pci.c  | 38 ++++++++++++++++++++++++++++++++++
>  drivers/cxl/core/port.c |  4 +++-
>  drivers/cxl/core/regs.c | 14 +++++++++++++
>  drivers/cxl/cxl.h       |  7 +++++++
>  drivers/cxl/port.c      | 45 +++++++++++++++++++++++++++++++++++++++++
>  include/cxl/cxl.h       |  6 ++++++
>  7 files changed, 114 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
> index 07555ae63859..e36b55fd63bd 100644
> --- a/drivers/cxl/core/core.h
> +++ b/drivers/cxl/core/core.h
> @@ -209,6 +209,7 @@ static inline void devm_cxl_dport_ras_setup(struct cxl_dport *dport) { }
>  #endif /* CONFIG_CXL_RAS */
>  
>  int cxl_gpf_port_setup(struct cxl_dport *dport);
> +void devm_cxl_dport_bi_setup(struct cxl_dport *dport);
>  
>  struct cxl_hdm;
>  int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm,
> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
> index e4338fd7e01b..f82559d8a8c5 100644
> --- a/drivers/cxl/core/pci.c
> +++ b/drivers/cxl/core/pci.c
> @@ -926,3 +926,41 @@ int cxl_port_get_possible_dports(struct cxl_port *port)
>  
>  	return ctx.count;
>  }
> +
> +static void cxl_dport_map_bi(struct cxl_dport *dport)
> +{
> +	struct cxl_register_map *map = &dport->reg_map;
> +	struct device *dev = dport->dport_dev;
> +
> +	if (!map->component_map.bi_decoder.valid) {
> +		dev_dbg(dev, "BI Decoder registers not found\n");
> +		return;
> +	}
> +
> +	if (cxl_map_component_regs(map, &dport->regs.component,
> +				   BIT(CXL_CM_CAP_CAP_ID_BI_DECODER)))
> +		dev_dbg(dev, "Failed to map BI Decoder capability\n");
> +}
> +
> +/**
> + * devm_cxl_dport_bi_setup - Map BI Decoder registers on a CXL dport
> + * @dport: the cxl_dport that needs to be initialized
> + *
> + * Must be called while the dport's devres group is open so iomap
> + * allocations are released on dport removal.
> + */
> +void devm_cxl_dport_bi_setup(struct cxl_dport *dport)
> +{
> +	if (!dev_is_pci(dport->dport_dev))
> +		return;
> +
> +	switch (pci_pcie_type(to_pci_dev(dport->dport_dev))) {
> +	case PCI_EXP_TYPE_ROOT_PORT:
> +	case PCI_EXP_TYPE_DOWNSTREAM:
> +		dport->reg_map.host = dport_to_host(dport);
> +		cxl_dport_map_bi(dport);
> +		break;
> +	default:
> +		break;
> +	}
> +}
> diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
> index 1215ee4f4035..b2f8fb9547d3 100644
> --- a/drivers/cxl/core/port.c
> +++ b/drivers/cxl/core/port.c
> @@ -1242,8 +1242,10 @@ __devm_cxl_add_dport(struct cxl_port *port, struct device *dport_dev,
>  
>  	cxl_debugfs_create_dport_dir(dport);
>  
> -	if (!dport->rch)
> +	if (!dport->rch) {
>  		devm_cxl_dport_ras_setup(dport);
> +		devm_cxl_dport_bi_setup(dport);
> +	}
>  
>  	/* keep the group, and mark the end of devm actions */
>  	cxl_dport_close_dr_group(dport, no_free_ptr(dport_dr_group));
> diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
> index 93710cf4f0a6..a6caa793e7a4 100644
> --- a/drivers/cxl/core/regs.c
> +++ b/drivers/cxl/core/regs.c
> @@ -92,6 +92,18 @@ void cxl_probe_component_regs(struct device *dev, void __iomem *base,
>  			length = CXL_RAS_CAPABILITY_LENGTH;
>  			rmap = &map->ras;
>  			break;
> +		case CXL_CM_CAP_CAP_ID_BI_RT:
> +			dev_dbg(dev, "found BI RT capability (0x%x)\n",
> +				offset);
> +			length = CXL_BI_RT_CAPABILITY_LENGTH;
> +			rmap = &map->bi_rt;
> +			break;
> +		case CXL_CM_CAP_CAP_ID_BI_DECODER:
> +			dev_dbg(dev, "found BI Decoder capability (0x%x)\n",
> +				offset);
> +			length = CXL_BI_DECODER_CAPABILITY_LENGTH;
> +			rmap = &map->bi_decoder;
> +			break;
>  		default:
>  			dev_dbg(dev, "Unknown CM cap ID: %d (0x%x)\n", cap_id,
>  				offset);
> @@ -211,6 +223,8 @@ int cxl_map_component_regs(const struct cxl_register_map *map,
>  	} mapinfo[] = {
>  		{ &map->component_map.hdm_decoder, &regs->hdm_decoder },
>  		{ &map->component_map.ras, &regs->ras },
> +		{ &map->component_map.bi_rt, &regs->bi_rt },
> +		{ &map->component_map.bi_decoder, &regs->bi_decoder },
>  	};
>  	int i;
>  
> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
> index c0e5308e4d1b..f9fcb6387fc8 100644
> --- a/drivers/cxl/cxl.h
> +++ b/drivers/cxl/cxl.h
> @@ -39,9 +39,16 @@ extern const struct nvdimm_security_ops *cxl_security_ops;
>  #define   CXL_CM_CAP_HDR_ARRAY_SIZE_MASK GENMASK(31, 24)
>  #define CXL_CM_CAP_PTR_MASK GENMASK(31, 20)
>  
> +/* CXL 4.0 8.2.4 Table 8-74 */
>  #define   CXL_CM_CAP_CAP_ID_RAS 0x2
>  #define   CXL_CM_CAP_CAP_ID_HDM 0x5
>  #define   CXL_CM_CAP_CAP_HDM_VERSION 1
> +#define   CXL_CM_CAP_CAP_ID_BI_RT 0xB
> +#define   CXL_CM_CAP_CAP_ID_BI_DECODER 0xC
> +
> +/* CXL 4.0 8.2.4.26 / 8.2.4.27 BI Capability Structures */
> +#define CXL_BI_RT_CAPABILITY_LENGTH 0xC
> +#define CXL_BI_DECODER_CAPABILITY_LENGTH 0xC
>  
>  /* HDM decoders CXL 2.0 8.2.5.12 CXL HDM Decoder Capability Structure */
>  #define CXL_HDM_DECODER_CAP_OFFSET 0x0
> diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
> index 99cf77b6b699..a527dd13fb68 100644
> --- a/drivers/cxl/port.c
> +++ b/drivers/cxl/port.c
> @@ -58,6 +58,47 @@ static int discover_region(struct device *dev, void *unused)
>  	return 0;
>  }
>  
> +static void cxl_port_map_bi(struct cxl_port *port)
> +{
> +	struct cxl_register_map *map = &port->reg_map;
> +	struct cxl_dport *parent_dport = port->parent_dport;
> +	struct device *udev;
> +	int cap_id;
> +
> +	/* no upstream BI registers above host bridges or the cxl_root */
> +	if (!parent_dport || is_cxl_root(parent_dport->port))
> +		return;
> +
> +	udev = is_cxl_endpoint(port) ?
> +		port->uport_dev->parent : port->uport_dev;
> +	if (!dev_is_pci(udev))
> +		return;
> +
> +	/* BI requires 256B Flit on the upstream link */
> +	if (!cxl_pci_flit_256(to_pci_dev(udev)))
> +		return;
> +
> +	/* map this port's own BI capability */
> +	if (is_cxl_endpoint(port)) {
> +		if (!map->component_map.bi_decoder.valid) {
> +			dev_dbg(&port->dev, "BI Decoder registers not found\n");
> +			return;
> +		}
> +		cap_id = CXL_CM_CAP_CAP_ID_BI_DECODER;
> +	} else {
> +		if (!map->component_map.bi_rt.valid) {
> +			dev_dbg(&port->dev, "BI RT registers not found\n");
> +			return;
> +		}
> +		cap_id = CXL_CM_CAP_CAP_ID_BI_RT;
> +	}
> +
> +	map->host = &port->dev;
> +	if (cxl_map_component_regs(map, &port->regs, BIT(cap_id)))
> +		dev_dbg(&port->dev, "Failed to map BI capability 0x%x\n",
> +			cap_id);

Do we need to distinguish an optional absent BI RT from an advertised BI RT
that failed to map?

In both cases port->regs.bi_rt is NULL, then cxl_is_bi_capable() accepts a NULL BI
pointer for a USP, and __cxl_bi_ctrl_dport() consequently skips __cxl_bi_commit_rt().

So a mapping failure of a present BI RT can be treated like the switch do not need a
route table.

I think we should treat mapping failure of BI RT differently.

Best regards,
Richard Cheng.

> +}
> +
>  static int cxl_switch_port_probe(struct cxl_port *port)
>  {
>  	/* Reset nr_dports for rebind of driver */
> @@ -128,6 +169,8 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
>  	read_cdat_data(port);
>  	cxl_endpoint_parse_cdat(port);
>  
> +	cxl_port_map_bi(port);
> +
>  	get_device(&cxlmd->dev);
>  	rc = devm_add_action_or_reset(&port->dev, schedule_detach, cxlmd);
>  	if (rc)
> @@ -252,6 +295,8 @@ static struct cxl_dport *cxl_port_add_dport(struct cxl_port *port,
>  		 * on failure, or the device does not implement RAS registers.
>  		 */
>  		devm_cxl_port_ras_setup(port);
> +
> +		cxl_port_map_bi(port);
>  	}
>  
>  	dport = devm_cxl_add_dport_by_dev(port, dport_dev);
> diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
> index 016c74fb747c..2816954680b3 100644
> --- a/include/cxl/cxl.h
> +++ b/include/cxl/cxl.h
> @@ -34,10 +34,14 @@ struct cxl_regs {
>  	 * Common set of CXL Component register block base pointers
>  	 * @hdm_decoder: CXL 2.0 8.2.5.12 CXL HDM Decoder Capability Structure
>  	 * @ras: CXL 2.0 8.2.5.9 CXL RAS Capability Structure
> +	 * @bi_rt: CXL 4.0 8.2.4.26 CXL BI Route Table Capability Structure
> +	 * @bi_decoder: CXL 4.0 8.2.4.27 CXL BI Decoder Capability Structure
>  	 */
>  	struct_group_tagged(cxl_component_regs, component,
>  		void __iomem *hdm_decoder;
>  		void __iomem *ras;
> +		void __iomem *bi_rt;
> +		void __iomem *bi_decoder;
>  	);
>  	/*
>  	 * Common set of CXL Device register block base pointers
> @@ -80,6 +84,8 @@ struct cxl_reg_map {
>  struct cxl_component_reg_map {
>  	struct cxl_reg_map hdm_decoder;
>  	struct cxl_reg_map ras;
> +	struct cxl_reg_map bi_rt;
> +	struct cxl_reg_map bi_decoder;
>  };
>  
>  struct cxl_device_reg_map {
> -- 
> 2.39.5
>