Re: [RFC PATCH 7/9] cxl/pci: Add atomic notifier callback for CXL PCIe port AER internal errors

[Terry Bowman <Terry.Bowman@amd.com>]

On 6/26/24 01:22, Li, Ming4 wrote:
> On 6/18/2024 4:04 AM, Terry Bowman wrote:
>> CXL root ports, CXL downstream switch ports, and CXL upstream switch
>> ports are bound to the PCIe port bus driver, portdrv. portdrv provides
>> an atomic notifier chain for reporting PCIe port device AER
>> correctable internal errors (CIE) and AER uncorrectable internal
>> errors (UIE).
>>
>> CXL PCIe port devices use AER CIE/UIE to report CXL RAS.[1]
>>
>> Add a cxl_pci atomic notification callback for handling the portdrv's
>> AER UIE/CIE notifications.
>>
>> Register the atomic notification callback in the cxl_pci module's
>> load. Unregister the callback in the cxl_pci driver's unload.
>>
>> Implement the callback to check if the device parameter is a valid
>> CXL PCIe port. If it is valid then make the notification callback call
>> __cxl_handle_cor_ras() or __cxl_handle_ras() depending on the AER
>> type.
>>
>> [1] CXL3.1 - 12.2.2 CXL Root Ports, Downstream Switch Ports, and
>>              Upstream Switch Ports
>>
>> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
>> ---
>>  drivers/cxl/core/core.h |  4 ++
>>  drivers/cxl/core/pci.c  | 97 ++++++++++++++++++++++++++++++++++++++---
>>  drivers/cxl/core/port.c |  6 +--
>>  drivers/cxl/cxl.h       |  5 +++
>>  drivers/cxl/cxlpci.h    |  2 +
>>  drivers/cxl/pci.c       | 19 +++++++-
>>  6 files changed, 123 insertions(+), 10 deletions(-)
>>
>> diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
>> index bc5a95665aa0..69bef1db6ee0 100644
>> --- a/drivers/cxl/core/core.h
>> +++ b/drivers/cxl/core/core.h
>> @@ -94,4 +94,8 @@ int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr,
>>  				       enum access_coordinate_class access);
>>  bool cxl_need_node_perf_attrs_update(int nid);
>>  
>> +struct cxl_dport *find_dport(struct cxl_port *port, int id);
>> +struct cxl_port *find_cxl_port(struct device *dport_dev,
>> +			       struct cxl_dport **dport);
>> +
>>  #endif /* __CXL_CORE_H__ */
>> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
>> index 59a317ab84bb..e630eccb733d 100644
>> --- a/drivers/cxl/core/pci.c
>> +++ b/drivers/cxl/core/pci.c
>> @@ -689,7 +689,6 @@ EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
>>  static void __cxl_handle_cor_ras(struct device *dev,
>>  				 void __iomem *ras_base)
>>  {
>> -	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
>>  	void __iomem *addr;
>>  	u32 status;
>>  
>> @@ -698,10 +697,17 @@ static void __cxl_handle_cor_ras(struct device *dev,
>>  
>>  	addr = ras_base + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
>>  	status = readl(addr);
>> -	if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
>> -		writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
>> +
>> +	if (!(status & CXL_RAS_CORRECTABLE_STATUS_MASK))
>> +		return;
>> +
>> +	writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
>> +	if (is_cxl_memdev(dev)) {
>> +		struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
>> +
>>  		trace_cxl_aer_correctable_error(cxlmd, status);
>> -	}
>> +	} else if (dev_is_pci(dev))
>> +		trace_cxl_port_aer_correctable_error(dev, status);
>>  }
>>  
>>  static void cxl_handle_endpoint_cor_ras(struct cxl_dev_state *cxlds)
>> @@ -733,7 +739,6 @@ static void header_log_copy(void __iomem *ras_base, u32 *log)
>>  static bool __cxl_handle_ras(struct device *dev,
>>  			     void __iomem *ras_base)
>>  {
>> -	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
>>  	u32 hl[CXL_HEADERLOG_SIZE_U32];
>>  	void __iomem *addr;
>>  	u32 status;
>> @@ -759,7 +764,13 @@ static bool __cxl_handle_ras(struct device *dev,
>>  	}
>>  
>>  	header_log_copy(ras_base, hl);
>> -	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe, hl);
>> +	if (is_cxl_memdev(dev)) {
>> +		struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
>> +
>> +		trace_cxl_aer_uncorrectable_error(cxlmd, status, fe, hl);
>> +	} else if (dev_is_pci(dev))
>> +		trace_cxl_port_aer_uncorrectable_error(dev, status);
>> +
>>  	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
>>  
>>  	return true;
>> @@ -882,6 +893,80 @@ static bool cxl_handle_rdport_ras(struct cxl_dev_state *cxlds,
>>  	return __cxl_handle_ras(&cxlds->cxlmd->dev, dport->regs.ras);
>>  }
>>  
>> +static int match_uport(struct device *dev, void *data)
>> +{
>> +	struct device *uport_dev = (struct device *)data;
>> +	struct cxl_port *port;
>> +
>> +	if (!is_cxl_port(dev))
>> +		return 0;
>> +
>> +	port = to_cxl_port(dev);
>> +
>> +	return (port->uport_dev == uport_dev);
>> +}
>> +
>> +static struct cxl_port *pci_to_cxl_uport(struct pci_dev *pdev)
>> +{
>> +	struct cxl_dport *dport;
>> +	struct device *port_dev;
>> +	struct cxl_port *port;
>> +
>> +	port = find_cxl_port(pdev->dev.parent, &dport);
>> +	if (!port)
>> +		return NULL;
>> +	put_device(&port->dev);
>> +
>> +	port_dev = device_find_child(&port->dev, &pdev->dev, match_uport);
>> +	if (!port_dev)
>> +		return NULL;
> 
>  seems like just a bus_find_device(&cxl_bus_type, NULL, &pdev->dev, match_uport) can replace these find_cxl_port() and device_find_child().
> 
> 

That would be a good improvement/optimization. I'll look into making that change.

>> +	put_device(port_dev);
>> +
>> +	port = to_cxl_port(port_dev);
>> +
>> +	return port;
>> +}
>> +
>> +static void __iomem *cxl_pci_port_ras(struct pci_dev *pdev)
>> +{
>> +	void __iomem *ras_base = NULL;
>> +
>> +	if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) ||
>> +	    (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)) {
>> +		struct cxl_dport *dport;
>> +
>> +		find_cxl_port(&pdev->dev, &dport);
>> +		ras_base = dport ? dport->regs.ras : NULL;
> 
> Need put_device(&port->dev) after find_cxl_port(), use scope-based resource management __free() here should be better.
> 
> 

Thanks.

Regards,
Terry