The CXL drivers do not contain error handlers for CXL PCIe port
device protocol errors. These are needed in order to handle and log
RAS protocol errors.

Add CXL PCIe port protocol error handlers to the CXL driver.

Provide access to RAS registers for the specific CXL PCIe port types:
root port, upstream switch port, and downstream switch port.

Also, register and unregister the CXL PCIe port error handlers with
the AER service driver using register_cxl_port_err_hndlrs() and
unregister_cxl_port_err_hndlrs(). Invoke the registration from
cxl_pci_driver_init() and the unregistration from cxl_pci_driver_exit().

[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/pci.c | 83 ++++++++++++++++++++++++++++++++++++++++++
 drivers/cxl/cxl.h      |  5 +++
 drivers/cxl/pci.c      |  8 ++++
 3 files changed, 96 insertions(+)

diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index c3c82c051d73..7e3770f7a955 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -815,6 +815,89 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 	}
 }
 
+static int match_uport(struct device *dev, const 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 void __iomem *cxl_pci_port_ras(struct pci_dev *pdev)
+{
+	void __iomem *ras_base;
+	struct cxl_port *port;
+
+	if (!pdev)
+		return NULL;
+
+	if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) ||
+	    (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)) {
+		struct cxl_dport *dport;
+
+		port = find_cxl_port(&pdev->dev, &dport);
+		ras_base = dport ? dport->regs.ras : NULL;
+		put_device(&port->dev);
+		return ras_base;
+	} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_UPSTREAM) {
+		struct device *port_dev __free(put_device);
+
+		port_dev = bus_find_device(&cxl_bus_type, NULL, &pdev->dev, match_uport);
+		if (!port_dev)
+			return NULL;
+
+		port = to_cxl_port(port_dev);
+		if (!port)
+			return NULL;
+
+		ras_base = port ? port->uport_regs.ras : NULL;
+		return ras_base;
+	}
+
+	return NULL;
+}
+
+void cxl_cor_port_err_detected(struct pci_dev *pdev)
+{
+	void __iomem *ras_base = cxl_pci_port_ras(pdev);
+
+	__cxl_handle_cor_ras(&pdev->dev, ras_base);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cor_port_err_detected, CXL);
+
+pci_ers_result_t cxl_port_err_detected(struct pci_dev *pdev, pci_channel_state_t state)
+{
+	void __iomem *ras_base = cxl_pci_port_ras(pdev);
+	bool ue;
+
+	ue = __cxl_handle_ras(&pdev->dev, ras_base);
+	if (ue)
+		return PCI_ERS_RESULT_PANIC;
+
+	switch (state) {
+	case pci_channel_io_normal:
+		dev_err(&pdev->dev, "%s():%d: pci_channel_io_normal\n",
+			__func__, __LINE__);
+		return PCI_ERS_RESULT_CAN_RECOVER;
+	case pci_channel_io_frozen:
+		dev_err(&pdev->dev, "%s():%d: pci_channel_io_frozen\n",
+			__func__, __LINE__);
+		return PCI_ERS_RESULT_NEED_RESET;
+	case pci_channel_io_perm_failure:
+		dev_err(&pdev->dev, "%s():%d: pci_channel_io_perm_failure\n",
+			__func__, __LINE__);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_port_err_detected, CXL);
+
 void cxl_uport_init_aer(struct cxl_port *port)
 {
 	/* uport may have more than 1 downstream EP. Check if already mapped. */
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 7a5f2c33223e..06fcde4b88b5 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -10,6 +10,7 @@
 #include <linux/bitops.h>
 #include <linux/log2.h>
 #include <linux/node.h>
+#include <linux/pci.h>
 #include <linux/io.h>
 
 extern const struct nvdimm_security_ops *cxl_security_ops;
@@ -901,6 +902,10 @@ void cxl_coordinates_combine(struct access_coordinate *out,
 
 bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
 
+pci_ers_result_t cxl_port_err_detected(struct pci_dev *pdev,
+				       pci_channel_state_t state);
+void cxl_cor_port_err_detected(struct pci_dev *pdev);
+
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
  * of these symbols in tools/testing/cxl/.
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 4be35dc22202..9179b34c35bb 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -978,6 +978,11 @@ static void cxl_reset_done(struct pci_dev *pdev)
 	}
 }
 
+static struct cxl_port_err_hndlrs cxl_port_hndlrs = {
+	.error_detected = cxl_port_err_detected,
+	.cor_error_detected = cxl_cor_port_err_detected
+};
+
 static const struct pci_error_handlers cxl_error_handlers = {
 	.error_detected	= cxl_error_detected,
 	.slot_reset	= cxl_slot_reset,
@@ -1054,11 +1059,14 @@ static int __init cxl_pci_driver_init(void)
 	if (rc)
 		pci_unregister_driver(&cxl_pci_driver);
 
+	register_cxl_port_hndlrs(&cxl_port_hndlrs);
+
 	return rc;
 }
 
 static void __exit cxl_pci_driver_exit(void)
 {
+	unregister_cxl_port_hndlrs();
 	cxl_cper_unregister_work(&cxl_cper_work);
 	cancel_work_sync(&cxl_cper_work);
 	pci_unregister_driver(&cxl_pci_driver);
-- 
2.34.1

On Tue, 8 Oct 2024 17:16:54 -0500
Terry Bowman <terry.bowman@amd.com> wrote:

> The CXL drivers do not contain error handlers for CXL PCIe port
> device protocol errors. These are needed in order to handle and log
> RAS protocol errors.
> 
> Add CXL PCIe port protocol error handlers to the CXL driver.
> 
> Provide access to RAS registers for the specific CXL PCIe port types:
> root port, upstream switch port, and downstream switch port.
> 
> Also, register and unregister the CXL PCIe port error handlers with
> the AER service driver using register_cxl_port_err_hndlrs() and
> unregister_cxl_port_err_hndlrs(). Invoke the registration from
> cxl_pci_driver_init() and the unregistration from cxl_pci_driver_exit().
> 
> [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>
A few comments inline.

Jonathan

> ---
>  drivers/cxl/core/pci.c | 83 ++++++++++++++++++++++++++++++++++++++++++
>  drivers/cxl/cxl.h      |  5 +++
>  drivers/cxl/pci.c      |  8 ++++
>  3 files changed, 96 insertions(+)
> 
> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
> index c3c82c051d73..7e3770f7a955 100644
> --- a/drivers/cxl/core/pci.c
> +++ b/drivers/cxl/core/pci.c
> @@ -815,6 +815,89 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
>  	}
>  }
>  
> +static int match_uport(struct device *dev, const 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 void __iomem *cxl_pci_port_ras(struct pci_dev *pdev)
> +{
> +	void __iomem *ras_base;
> +	struct cxl_port *port;
> +
> +	if (!pdev)
> +		return NULL;
Why would this happen?  Seems an odd check to have so maybe a comment.

> +
> +	if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) ||
> +	    (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)) {
> +		struct cxl_dport *dport;
> +
> +		port = find_cxl_port(&pdev->dev, &dport);
Can in theory fail.
> +		ras_base = dport ? dport->regs.ras : NULL;
> +		put_device(&port->dev);
If it fails this is a null pointer dereference.

> +		return ras_base;
> +	} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_UPSTREAM) {
> +		struct device *port_dev __free(put_device);

Should be combined with the next line. We want it to be hard for anyone
to put code in between!

> +
> +		port_dev = bus_find_device(&cxl_bus_type, NULL, &pdev->dev, match_uport);
> +		if (!port_dev)
> +			return NULL;
> +
> +		port = to_cxl_port(port_dev);
> +		if (!port)
> +			return NULL;
> +
> +		ras_base = port ? port->uport_regs.ras : NULL;

Given check above, port exists. Remove one of the two
checks.

> +		return ras_base;
> +	}
> +
> +	return NULL;
> +}

Hi Jonathan,

On 10/17/2024 8:57 AM, Jonathan Cameron wrote:
> On Tue, 8 Oct 2024 17:16:54 -0500
> Terry Bowman <terry.bowman@amd.com> wrote:
> 
>> The CXL drivers do not contain error handlers for CXL PCIe port
>> device protocol errors. These are needed in order to handle and log
>> RAS protocol errors.
>>
>> Add CXL PCIe port protocol error handlers to the CXL driver.
>>
>> Provide access to RAS registers for the specific CXL PCIe port types:
>> root port, upstream switch port, and downstream switch port.
>>
>> Also, register and unregister the CXL PCIe port error handlers with
>> the AER service driver using register_cxl_port_err_hndlrs() and
>> unregister_cxl_port_err_hndlrs(). Invoke the registration from
>> cxl_pci_driver_init() and the unregistration from cxl_pci_driver_exit().
>>
>> [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>
> A few comments inline.
> 
> Jonathan
> 
>> ---
>>   drivers/cxl/core/pci.c | 83 ++++++++++++++++++++++++++++++++++++++++++
>>   drivers/cxl/cxl.h      |  5 +++
>>   drivers/cxl/pci.c      |  8 ++++
>>   3 files changed, 96 insertions(+)
>>
>> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
>> index c3c82c051d73..7e3770f7a955 100644
>> --- a/drivers/cxl/core/pci.c
>> +++ b/drivers/cxl/core/pci.c
>> @@ -815,6 +815,89 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
>>   	}
>>   }
>>   
>> +static int match_uport(struct device *dev, const 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 void __iomem *cxl_pci_port_ras(struct pci_dev *pdev)
>> +{
>> +	void __iomem *ras_base;
>> +	struct cxl_port *port;
>> +
>> +	if (!pdev)
>> +		return NULL;
> Why would this happen?  Seems an odd check to have so maybe a comment.
> 


This is called directly from cxl_port_err_detected() and cxl_cor_port_err_detected().
We moved the pdev validation check into cxl_pci_port_ras().


>> +
>> +	if ((pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) ||
>> +	    (pci_pcie_type(pdev) == PCI_EXP_TYPE_DOWNSTREAM)) {
>> +		struct cxl_dport *dport;
>> +
>> +		port = find_cxl_port(&pdev->dev, &dport);
> Can in theory fail>> +		ras_base = dport ? dport->regs.ras : NULL;
>> +		put_device(&port->dev);
> If it fails this is a null pointer dereference.
> 
>> +		return ras_base;
>> +	} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_UPSTREAM) {
>> +		struct device *port_dev __free(put_device);
> 
> Should be combined with the next line. We want it to be hard for anyone
> to put code in between!
> 
>> +
>> +		port_dev = bus_find_device(&cxl_bus_type, NULL, &pdev->dev, match_uport);
>> +		if (!port_dev)
>> +			return NULL;
>> +
>> +		port = to_cxl_port(port_dev);
>> +		if (!port)
>> +			return NULL;
>> +
>> +		ras_base = port ? port->uport_regs.ras : NULL;
> 
> Given check above, port exists. Remove one of the two
> checks.
> 
>> +		return ras_base;
>> +	}
>> +
>> +	return NULL;
>> +}

I have v2 changed (not posted yet) to use the following at the top of the function for the
if and else blocks using 'port'. Is not needed for dport.

struct cxl_port *port __free(put_cxl_port) = NULL;

Regards,
Terry