diff mbox series

[v2,04/14] PCI/AER: Modify AER driver logging to report CXL or PCIe bus error type

Message ID 20241025210305.27499-5-terry.bowman@amd.com (mailing list archive)
State Superseded
Delegated to: Bjorn Helgaas
Headers show
Series Enable CXL PCIe port protocol error handling and logging | expand

Commit Message

Bowman, Terry Oct. 25, 2024, 9:02 p.m. UTC 
The AER driver and aer_event tracing currently log 'PCIe Bus Type'
for all errors.

Update the driver and aer_event tracing to log 'CXL Bus Type' for CXL devices.

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
---
 drivers/pci/pcie/aer.c  | 14 ++++++++------
 include/ras/ras_event.h |  9 ++++++---
 2 files changed, 14 insertions(+), 9 deletions(-)

Comments

Jonathan Cameron Oct. 30, 2024, 2:56 p.m. UTC | #1 
On Fri, 25 Oct 2024 16:02:55 -0500
Terry Bowman <terry.bowman@amd.com> wrote:

> The AER driver and aer_event tracing currently log 'PCIe Bus Type'
> for all errors.
> 
> Update the driver and aer_event tracing to log 'CXL Bus Type' for CXL devices.
> 
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Looks fine to me.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

+CC Mauro and Shiju.  I assume this will be easy to add to rasdaemon
useage of this tracepoint?

> ---
>  drivers/pci/pcie/aer.c  | 14 ++++++++------
>  include/ras/ras_event.h |  9 ++++++---
>  2 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index fe6edf26279e..53e9a11f6c0f 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -699,13 +699,14 @@ static void __aer_print_error(struct pci_dev *dev,
>  
>  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  {
> +	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
>  	int layer, agent;
>  	int id = pci_dev_id(dev);
>  	const char *level;
>  
>  	if (!info->status) {
> -		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
> -			aer_error_severity_string[info->severity]);
> +		pci_err(dev, "%s Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
> +			bus_type, aer_error_severity_string[info->severity]);
>  		goto out;
>  	}
>  
> @@ -714,8 +715,8 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  
>  	level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR;
>  
> -	pci_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
> -		   aer_error_severity_string[info->severity],
> +	pci_printk(level, dev, "%s Bus Error: severity=%s, type=%s, (%s)\n",
> +		   bus_type, aer_error_severity_string[info->severity],
>  		   aer_error_layer[layer], aer_agent_string[agent]);
>  
>  	pci_printk(level, dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
> @@ -730,7 +731,7 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  	if (info->id && info->error_dev_num > 1 && info->id == id)
>  		pci_err(dev, "  Error of this Agent is reported first\n");
>  
> -	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
> +	trace_aer_event(dev_name(&dev->dev), bus_type, (info->status & ~info->mask),
>  			info->severity, info->tlp_header_valid, &info->tlp);
>  }
>  
> @@ -764,6 +765,7 @@ EXPORT_SYMBOL_GPL(cper_severity_to_aer);
>  void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  		   struct aer_capability_regs *aer)
>  {
> +	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
>  	int layer, agent, tlp_header_valid = 0;
>  	u32 status, mask;
>  	struct aer_err_info info;
> @@ -798,7 +800,7 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  	if (tlp_header_valid)
>  		__print_tlp_header(dev, &aer->header_log);
>  
> -	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
> +	trace_aer_event(dev_name(&dev->dev), bus_type, (status & ~mask),
>  			aer_severity, tlp_header_valid, &aer->header_log);
>  }
>  EXPORT_SYMBOL_NS_GPL(pci_print_aer, CXL);
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index e5f7ee0864e7..1bf8e7050ba8 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -297,15 +297,17 @@ TRACE_EVENT(non_standard_event,
>  
>  TRACE_EVENT(aer_event,
>  	TP_PROTO(const char *dev_name,
> +		 const char *bus_type,
>  		 const u32 status,
>  		 const u8 severity,
>  		 const u8 tlp_header_valid,
>  		 struct pcie_tlp_log *tlp),
>  
> -	TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp),
> +	TP_ARGS(dev_name, bus_type, status, severity, tlp_header_valid, tlp),
>  
>  	TP_STRUCT__entry(
>  		__string(	dev_name,	dev_name	)
> +		__string(	bus_type,	bus_type	)
>  		__field(	u32,		status		)
>  		__field(	u8,		severity	)
>  		__field(	u8, 		tlp_header_valid)
> @@ -314,6 +316,7 @@ TRACE_EVENT(aer_event,
>  
>  	TP_fast_assign(
>  		__assign_str(dev_name);
> +		__assign_str(bus_type);
>  		__entry->status		= status;
>  		__entry->severity	= severity;
>  		__entry->tlp_header_valid = tlp_header_valid;
> @@ -325,8 +328,8 @@ TRACE_EVENT(aer_event,
>  		}
>  	),
>  
> -	TP_printk("%s PCIe Bus Error: severity=%s, %s, TLP Header=%s\n",
> -		__get_str(dev_name),
> +	TP_printk("%s %s Bus Error: severity=%s, %s, TLP Header=%s\n",
> +		__get_str(dev_name), __get_str(bus_type),
>  		__entry->severity == AER_CORRECTABLE ? "Corrected" :
>  			__entry->severity == AER_FATAL ?
>  			"Fatal" : "Uncorrected, non-fatal",
Dave Jiang Oct. 31, 2024, 4:27 p.m. UTC | #2 
On 10/25/24 2:02 PM, Terry Bowman wrote:
> The AER driver and aer_event tracing currently log 'PCIe Bus Type'
> for all errors.
> 
> Update the driver and aer_event tracing to log 'CXL Bus Type' for CXL devices.
> 
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>

> ---
>  drivers/pci/pcie/aer.c  | 14 ++++++++------
>  include/ras/ras_event.h |  9 ++++++---
>  2 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index fe6edf26279e..53e9a11f6c0f 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -699,13 +699,14 @@ static void __aer_print_error(struct pci_dev *dev,
>  
>  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  {
> +	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
>  	int layer, agent;
>  	int id = pci_dev_id(dev);
>  	const char *level;
>  
>  	if (!info->status) {
> -		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
> -			aer_error_severity_string[info->severity]);
> +		pci_err(dev, "%s Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
> +			bus_type, aer_error_severity_string[info->severity]);
>  		goto out;
>  	}
>  
> @@ -714,8 +715,8 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  
>  	level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR;
>  
> -	pci_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
> -		   aer_error_severity_string[info->severity],
> +	pci_printk(level, dev, "%s Bus Error: severity=%s, type=%s, (%s)\n",
> +		   bus_type, aer_error_severity_string[info->severity],
>  		   aer_error_layer[layer], aer_agent_string[agent]);
>  
>  	pci_printk(level, dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
> @@ -730,7 +731,7 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  	if (info->id && info->error_dev_num > 1 && info->id == id)
>  		pci_err(dev, "  Error of this Agent is reported first\n");
>  
> -	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
> +	trace_aer_event(dev_name(&dev->dev), bus_type, (info->status & ~info->mask),
>  			info->severity, info->tlp_header_valid, &info->tlp);
>  }
>  
> @@ -764,6 +765,7 @@ EXPORT_SYMBOL_GPL(cper_severity_to_aer);
>  void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  		   struct aer_capability_regs *aer)
>  {
> +	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
>  	int layer, agent, tlp_header_valid = 0;
>  	u32 status, mask;
>  	struct aer_err_info info;
> @@ -798,7 +800,7 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  	if (tlp_header_valid)
>  		__print_tlp_header(dev, &aer->header_log);
>  
> -	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
> +	trace_aer_event(dev_name(&dev->dev), bus_type, (status & ~mask),
>  			aer_severity, tlp_header_valid, &aer->header_log);
>  }
>  EXPORT_SYMBOL_NS_GPL(pci_print_aer, CXL);
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index e5f7ee0864e7..1bf8e7050ba8 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -297,15 +297,17 @@ TRACE_EVENT(non_standard_event,
>  
>  TRACE_EVENT(aer_event,
>  	TP_PROTO(const char *dev_name,
> +		 const char *bus_type,
>  		 const u32 status,
>  		 const u8 severity,
>  		 const u8 tlp_header_valid,
>  		 struct pcie_tlp_log *tlp),
>  
> -	TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp),
> +	TP_ARGS(dev_name, bus_type, status, severity, tlp_header_valid, tlp),
>  
>  	TP_STRUCT__entry(
>  		__string(	dev_name,	dev_name	)
> +		__string(	bus_type,	bus_type	)
>  		__field(	u32,		status		)
>  		__field(	u8,		severity	)
>  		__field(	u8, 		tlp_header_valid)
> @@ -314,6 +316,7 @@ TRACE_EVENT(aer_event,
>  
>  	TP_fast_assign(
>  		__assign_str(dev_name);
> +		__assign_str(bus_type);
>  		__entry->status		= status;
>  		__entry->severity	= severity;
>  		__entry->tlp_header_valid = tlp_header_valid;
> @@ -325,8 +328,8 @@ TRACE_EVENT(aer_event,
>  		}
>  	),
>  
> -	TP_printk("%s PCIe Bus Error: severity=%s, %s, TLP Header=%s\n",
> -		__get_str(dev_name),
> +	TP_printk("%s %s Bus Error: severity=%s, %s, TLP Header=%s\n",
> +		__get_str(dev_name), __get_str(bus_type),
>  		__entry->severity == AER_CORRECTABLE ? "Corrected" :
>  			__entry->severity == AER_FATAL ?
>  			"Fatal" : "Uncorrected, non-fatal",
Fan Ni Oct. 31, 2024, 9:27 p.m. UTC | #3 
On Fri, Oct 25, 2024 at 04:02:55PM -0500, Terry Bowman wrote:
> The AER driver and aer_event tracing currently log 'PCIe Bus Type'
> for all errors.
> 
> Update the driver and aer_event tracing to log 'CXL Bus Type' for CXL devices.
> 
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
> ---

Reviewed-by: Fan Ni <fan.ni@samsung.com>

>  drivers/pci/pcie/aer.c  | 14 ++++++++------
>  include/ras/ras_event.h |  9 ++++++---
>  2 files changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index fe6edf26279e..53e9a11f6c0f 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -699,13 +699,14 @@ static void __aer_print_error(struct pci_dev *dev,
>  
>  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  {
> +	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
>  	int layer, agent;
>  	int id = pci_dev_id(dev);
>  	const char *level;
>  
>  	if (!info->status) {
> -		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
> -			aer_error_severity_string[info->severity]);
> +		pci_err(dev, "%s Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
> +			bus_type, aer_error_severity_string[info->severity]);
>  		goto out;
>  	}
>  
> @@ -714,8 +715,8 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  
>  	level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR;
>  
> -	pci_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
> -		   aer_error_severity_string[info->severity],
> +	pci_printk(level, dev, "%s Bus Error: severity=%s, type=%s, (%s)\n",
> +		   bus_type, aer_error_severity_string[info->severity],
>  		   aer_error_layer[layer], aer_agent_string[agent]);
>  
>  	pci_printk(level, dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
> @@ -730,7 +731,7 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  	if (info->id && info->error_dev_num > 1 && info->id == id)
>  		pci_err(dev, "  Error of this Agent is reported first\n");
>  
> -	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
> +	trace_aer_event(dev_name(&dev->dev), bus_type, (info->status & ~info->mask),
>  			info->severity, info->tlp_header_valid, &info->tlp);
>  }
>  
> @@ -764,6 +765,7 @@ EXPORT_SYMBOL_GPL(cper_severity_to_aer);
>  void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  		   struct aer_capability_regs *aer)
>  {
> +	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
>  	int layer, agent, tlp_header_valid = 0;
>  	u32 status, mask;
>  	struct aer_err_info info;
> @@ -798,7 +800,7 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  	if (tlp_header_valid)
>  		__print_tlp_header(dev, &aer->header_log);
>  
> -	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
> +	trace_aer_event(dev_name(&dev->dev), bus_type, (status & ~mask),
>  			aer_severity, tlp_header_valid, &aer->header_log);
>  }
>  EXPORT_SYMBOL_NS_GPL(pci_print_aer, CXL);
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index e5f7ee0864e7..1bf8e7050ba8 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -297,15 +297,17 @@ TRACE_EVENT(non_standard_event,
>  
>  TRACE_EVENT(aer_event,
>  	TP_PROTO(const char *dev_name,
> +		 const char *bus_type,
>  		 const u32 status,
>  		 const u8 severity,
>  		 const u8 tlp_header_valid,
>  		 struct pcie_tlp_log *tlp),
>  
> -	TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp),
> +	TP_ARGS(dev_name, bus_type, status, severity, tlp_header_valid, tlp),
>  
>  	TP_STRUCT__entry(
>  		__string(	dev_name,	dev_name	)
> +		__string(	bus_type,	bus_type	)
>  		__field(	u32,		status		)
>  		__field(	u8,		severity	)
>  		__field(	u8, 		tlp_header_valid)
> @@ -314,6 +316,7 @@ TRACE_EVENT(aer_event,
>  
>  	TP_fast_assign(
>  		__assign_str(dev_name);
> +		__assign_str(bus_type);
>  		__entry->status		= status;
>  		__entry->severity	= severity;
>  		__entry->tlp_header_valid = tlp_header_valid;
> @@ -325,8 +328,8 @@ TRACE_EVENT(aer_event,
>  		}
>  	),
>  
> -	TP_printk("%s PCIe Bus Error: severity=%s, %s, TLP Header=%s\n",
> -		__get_str(dev_name),
> +	TP_printk("%s %s Bus Error: severity=%s, %s, TLP Header=%s\n",
> +		__get_str(dev_name), __get_str(bus_type),
>  		__entry->severity == AER_CORRECTABLE ? "Corrected" :
>  			__entry->severity == AER_FATAL ?
>  			"Fatal" : "Uncorrected, non-fatal",
> -- 
> 2.34.1
>
diff mbox series

Patch

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index fe6edf26279e..53e9a11f6c0f 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -699,13 +699,14 @@  static void __aer_print_error(struct pci_dev *dev,
 
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 {
+	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
 	int layer, agent;
 	int id = pci_dev_id(dev);
 	const char *level;
 
 	if (!info->status) {
-		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
-			aer_error_severity_string[info->severity]);
+		pci_err(dev, "%s Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
+			bus_type, aer_error_severity_string[info->severity]);
 		goto out;
 	}
 
@@ -714,8 +715,8 @@  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 
 	level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR;
 
-	pci_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
-		   aer_error_severity_string[info->severity],
+	pci_printk(level, dev, "%s Bus Error: severity=%s, type=%s, (%s)\n",
+		   bus_type, aer_error_severity_string[info->severity],
 		   aer_error_layer[layer], aer_agent_string[agent]);
 
 	pci_printk(level, dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
@@ -730,7 +731,7 @@  void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	if (info->id && info->error_dev_num > 1 && info->id == id)
 		pci_err(dev, "  Error of this Agent is reported first\n");
 
-	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
+	trace_aer_event(dev_name(&dev->dev), bus_type, (info->status & ~info->mask),
 			info->severity, info->tlp_header_valid, &info->tlp);
 }
 
@@ -764,6 +765,7 @@  EXPORT_SYMBOL_GPL(cper_severity_to_aer);
 void pci_print_aer(struct pci_dev *dev, int aer_severity,
 		   struct aer_capability_regs *aer)
 {
+	const char *bus_type = pcie_is_cxl(dev) ? "CXL"  : "PCIe";
 	int layer, agent, tlp_header_valid = 0;
 	u32 status, mask;
 	struct aer_err_info info;
@@ -798,7 +800,7 @@  void pci_print_aer(struct pci_dev *dev, int aer_severity,
 	if (tlp_header_valid)
 		__print_tlp_header(dev, &aer->header_log);
 
-	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
+	trace_aer_event(dev_name(&dev->dev), bus_type, (status & ~mask),
 			aer_severity, tlp_header_valid, &aer->header_log);
 }
 EXPORT_SYMBOL_NS_GPL(pci_print_aer, CXL);
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index e5f7ee0864e7..1bf8e7050ba8 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -297,15 +297,17 @@  TRACE_EVENT(non_standard_event,
 
 TRACE_EVENT(aer_event,
 	TP_PROTO(const char *dev_name,
+		 const char *bus_type,
 		 const u32 status,
 		 const u8 severity,
 		 const u8 tlp_header_valid,
 		 struct pcie_tlp_log *tlp),
 
-	TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp),
+	TP_ARGS(dev_name, bus_type, status, severity, tlp_header_valid, tlp),
 
 	TP_STRUCT__entry(
 		__string(	dev_name,	dev_name	)
+		__string(	bus_type,	bus_type	)
 		__field(	u32,		status		)
 		__field(	u8,		severity	)
 		__field(	u8, 		tlp_header_valid)
@@ -314,6 +316,7 @@  TRACE_EVENT(aer_event,
 
 	TP_fast_assign(
 		__assign_str(dev_name);
+		__assign_str(bus_type);
 		__entry->status		= status;
 		__entry->severity	= severity;
 		__entry->tlp_header_valid = tlp_header_valid;
@@ -325,8 +328,8 @@  TRACE_EVENT(aer_event,
 		}
 	),
 
-	TP_printk("%s PCIe Bus Error: severity=%s, %s, TLP Header=%s\n",
-		__get_str(dev_name),
+	TP_printk("%s %s Bus Error: severity=%s, %s, TLP Header=%s\n",
+		__get_str(dev_name), __get_str(bus_type),
 		__entry->severity == AER_CORRECTABLE ? "Corrected" :
 			__entry->severity == AER_FATAL ?
 			"Fatal" : "Uncorrected, non-fatal",