Re: [PATCH v11 15/23] cxl/pci: Map CXL Endpoint Port and CXL Switch Port RAS registers

["Bowman, Terry" <terry.bowman@amd.com>]

On 8/28/2025 6:05 PM, Dave Jiang wrote:
>
> On 8/26/25 6:35 PM, Terry Bowman wrote:
>> CXL Endpoint (EP) Ports may include Root Ports (RP) or Downstream Switch
>> Ports (DSP). CXL RPs and DSPs contain RAS registers that require memory
>> mapping to enable RAS logging. This initialization is currently missing and
>> must be added for CXL RPs and DSPs.
>>
>> Update cxl_dport_init_ras_reporting() to support RP and DSP RAS mapping.
>> Add alongside the existing Restricted CXL Host Downstream Port RAS mapping.
>>
>> Update cxl_endpoint_port_probe() to invoke cxl_dport_init_ras_reporting().
>> This will initiate the RAS mapping for CXL RPs and DSPs when each CXL EP is
>> created and added to the EP port.
>>
>> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
>> ---
>> Changes in v10->v11:
>> - Use local pointer for readability in cxl_switch_port_init_ras() (Jonathan Cameron)
>> - Rename port to be ep in cxl_endpoint_port_init_ras() (Dave Jiang)
>> - Rename dport to be parent_dport in cxl_endpoint_port_init_ras()
>>   and cxl_switch_port_init_ras() (Dave Jiang)
>> - Port helper changes were in cxl/port.c, now in core/ras.c (Dave Jiang)
>> ---
>>  drivers/cxl/core/core.h |  7 ++++++
>>  drivers/cxl/core/ras.c  | 47 +++++++++++++++++++++++++++++++++++++++++
>>  drivers/cxl/cxl.h       |  2 ++
>>  drivers/cxl/cxlpci.h    |  4 ----
>>  drivers/cxl/mem.c       |  4 +++-
>>  drivers/cxl/port.c      |  5 +++++
>>  6 files changed, 64 insertions(+), 5 deletions(-)
>>
>> diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
>> index 2c81a43d7b05..2fa76a913264 100644
>> --- a/drivers/cxl/core/core.h
>> +++ b/drivers/cxl/core/core.h
>> @@ -146,6 +146,9 @@ int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port,
>>  #ifdef CONFIG_CXL_RAS
>>  int cxl_ras_init(void);
>>  void cxl_ras_exit(void);
>> +void cxl_switch_port_init_ras(struct cxl_port *port);
>> +void cxl_endpoint_port_init_ras(struct cxl_port *ep);
>> +void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host);
>>  #else
>>  static inline int cxl_ras_init(void)
>>  {
>> @@ -155,6 +158,10 @@ static inline int cxl_ras_init(void)
>>  static inline void cxl_ras_exit(void)
>>  {
>>  }
>> +static inline void cxl_switch_port_init_ras(struct cxl_port *port) { }
>> +static inline void cxl_endpoint_port_init_ras(struct cxl_port *ep) { }
>> +static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
>> +						struct device *host) { }
>>  #endif // CONFIG_CXL_RAS
>>  
>>  int cxl_gpf_port_setup(struct cxl_dport *dport);
>> diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
>> index 69559043b772..42b6e0b092d5 100644
>> --- a/drivers/cxl/core/ras.c
>> +++ b/drivers/cxl/core/ras.c
>> @@ -284,6 +284,53 @@ void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
>>  }
>>  EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, "CXL");
>>  
>> +static void cxl_uport_init_ras_reporting(struct cxl_port *port,
>> +					 struct device *host)
>> +{
>> +	struct cxl_register_map *map = &port->reg_map;
>> +
>> +	map->host = host;
>> +	if (cxl_map_component_regs(map, &port->uport_regs,
>> +				   BIT(CXL_CM_CAP_CAP_ID_RAS)))
>> +		dev_dbg(&port->dev, "Failed to map RAS capability\n");
>> +}
>> +
>> +void cxl_switch_port_init_ras(struct cxl_port *port)
>> +{
>> +	struct cxl_dport *parent_dport = port->parent_dport;
>> +
>> +	if (is_cxl_root(to_cxl_port(port->dev.parent)))
>> +		return;
>> +
>> +	/* May have parent DSP or RP */
>> +	if (parent_dport && dev_is_pci(parent_dport->dport_dev)) {
>> +		struct pci_dev *pdev = to_pci_dev(parent_dport->dport_dev);
>> +
>> +		if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) ||
>> +		    (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM))
>> +			cxl_dport_init_ras_reporting(parent_dport, &port->dev);
>> +	}
>> +
>> +	cxl_uport_init_ras_reporting(port, &port->dev);
>> +}
>> +EXPORT_SYMBOL_NS_GPL(cxl_switch_port_init_ras, "CXL");
>> +
>> +void cxl_endpoint_port_init_ras(struct cxl_port *ep)
>> +{
>> +	struct cxl_dport *parent_dport;
>> +	struct cxl_memdev *cxlmd = to_cxl_memdev(ep->uport_dev);
>> +	struct cxl_port *parent_port __free(put_cxl_port) =
>> +		cxl_mem_find_port(cxlmd, &parent_dport);
>> +
>> +	if (!parent_dport || !dev_is_pci(parent_dport->dport_dev)) {
>> +		dev_err(&ep->dev, "CXL port topology not found\n");
>> +		return;
>> +	}
>> +
>> +	cxl_dport_init_ras_reporting(parent_dport, cxlmd->cxlds->dev);
>> +}
>> +EXPORT_SYMBOL_NS_GPL(cxl_endpoint_port_init_ras, "CXL");
>> +
>>  static void cxl_handle_cor_ras(struct device *dev, u64 serial, void __iomem *ras_base)
>>  {
>>  	void __iomem *addr;
>> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
>> index 8f6224ac6785..32fccad9a7f6 100644
>> --- a/drivers/cxl/cxl.h
>> +++ b/drivers/cxl/cxl.h
>> @@ -586,6 +586,7 @@ struct cxl_dax_region {
>>   * @parent_dport: dport that points to this port in the parent
>>   * @decoder_ida: allocator for decoder ids
>>   * @reg_map: component and ras register mapping parameters
>> + * @uport_regs: mapped component registers
>>   * @nr_dports: number of entries in @dports
>>   * @hdm_end: track last allocated HDM decoder instance for allocation ordering
>>   * @commit_end: cursor to track highest committed decoder for commit ordering
>> @@ -606,6 +607,7 @@ struct cxl_port {
>>  	struct cxl_dport *parent_dport;
>>  	struct ida decoder_ida;
>>  	struct cxl_register_map reg_map;
>> +	struct cxl_component_regs uport_regs;
>>  	int nr_dports;
>>  	int hdm_end;
>>  	int commit_end;
>> diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h
>> index ad24d81e9eaa..a6da0abfa506 100644
>> --- a/drivers/cxl/cxlpci.h
>> +++ b/drivers/cxl/cxlpci.h
>> @@ -84,7 +84,6 @@ void read_cdat_data(struct cxl_port *port);
>>  void cxl_cor_error_detected(struct pci_dev *pdev);
>>  pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
>>  				    pci_channel_state_t state);
>> -void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host);
>>  #else
>>  static inline void cxl_cor_error_detected(struct pci_dev *pdev) { }
>>  
>> @@ -93,9 +92,6 @@ static inline pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
>>  {
>>  	return PCI_ERS_RESULT_NONE;
>>  }
>> -
>> -static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport,
>> -						struct device *host) { }
>>  #endif
>>  
>>  #endif /* __CXL_PCI_H__ */
>> diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
>> index 6e6777b7bafb..f7dc0ba8905d 100644
>> --- a/drivers/cxl/mem.c
>> +++ b/drivers/cxl/mem.c
>> @@ -7,6 +7,7 @@
>>  
>>  #include "cxlmem.h"
>>  #include "cxlpci.h"
>> +#include "core/core.h"
>>  
>>  /**
>>   * DOC: cxl mem
>> @@ -166,7 +167,8 @@ static int cxl_mem_probe(struct device *dev)
>>  	else
>>  		endpoint_parent = &parent_port->dev;
>>  
>> -	cxl_dport_init_ras_reporting(dport, dev);
>> +	if (dport->rch)
>> +		cxl_dport_init_ras_reporting(dport, dev);
> So the endpoint port probe calls this via cxl_endpoint_port_init_ras(), and if it's RCH the memedev probe also calls this. Trying to understand why it happens for both drivers for the RCH case... 

This is legacy and I was trying to leave it intact without changes unless 
necessary. But, it can be cleaned-up. I can remove here and will leave the 
call from  endpoint creation in port.c for RCH and VH. I will add an RCH 
check used in discovering the RCD endpoint parent correctly. Thanks for 
pointing out.

Terry