[PATCH 13/15] cxl/pci: Add trace logging for CXL PCIe port RAS errors

Terry Bowman posted 15 patches 1 month, 2 weeks ago
There is a newer version of this series
[PATCH 13/15] cxl/pci: Add trace logging for CXL PCIe port RAS errors
Posted by Terry Bowman 1 month, 2 weeks ago
The CXL drivers use kernel trace functions for logging endpoint and
RCH downstream port RAS errors. However, similar functionality is
required for CXL root ports, CXL downstream switch ports, and CXL
upstream switch ports.

Introduce trace logging functions for both RAS correctable and
uncorrectable errors specific to CXL PCIe ports. Additionally, update
the PCIe port error handlers to invoke these new trace functions.

Signed-off-by: Terry Bowman <terry.bowman@amd.com>
---
 drivers/cxl/core/pci.c   | 16 ++++++++++----
 drivers/cxl/core/trace.h | 47 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 7e3770f7a955..4706113d2582 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -697,10 +697,14 @@ 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))
 		trace_cxl_aer_correctable_error(to_cxl_memdev(dev), 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)
@@ -756,7 +760,11 @@ static bool __cxl_handle_ras(struct device *dev, void __iomem *ras_base)
 	}
 
 	header_log_copy(ras_base, hl);
-	trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
+	if (is_cxl_memdev(dev))
+		trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
+	else if (dev_is_pci(dev))
+		trace_cxl_port_aer_uncorrectable_error(dev, status, fe, hl);
+
 	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
 
 	return true;
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 9167cfba7f59..6305c0eea627 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -48,6 +48,34 @@
 	{ CXL_RAS_UC_IDE_RX_ERR, "IDE Rx Error" }			  \
 )
 
+TRACE_EVENT(cxl_port_aer_uncorrectable_error,
+	    TP_PROTO(struct device *dev, u32 status, u32 fe, u32 *hl),
+	TP_ARGS(dev, status, fe, hl),
+	TP_STRUCT__entry(
+		__string(devname, dev_name(dev))
+		__string(host, dev_name(dev->parent))
+		__field(u32, status)
+		__field(u32, first_error)
+		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
+	),
+	TP_fast_assign(
+		__assign_str(devname);
+		__assign_str(host);
+		__entry->status = status;
+		__entry->first_error = fe;
+		/*
+		 * Embed the 512B headerlog data for user app retrieval and
+		 * parsing, but no need to print this in the trace buffer.
+		 */
+		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
+	),
+	TP_printk("device=%s host=%s status: '%s' first_error: '%s'",
+		  __get_str(devname), __get_str(host),
+		  show_uc_errs(__entry->status),
+		  show_uc_errs(__entry->first_error)
+	)
+);
+
 TRACE_EVENT(cxl_aer_uncorrectable_error,
 	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status, u32 fe, u32 *hl),
 	TP_ARGS(cxlmd, status, fe, hl),
@@ -96,6 +124,25 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
 	{ CXL_RAS_CE_PHYS_LAYER_ERR, "Received Error From Physical Layer" }	\
 )
 
+TRACE_EVENT(cxl_port_aer_correctable_error,
+	TP_PROTO(struct device *dev, u32 status),
+	TP_ARGS(dev, status),
+	TP_STRUCT__entry(
+		__string(devname, dev_name(dev))
+		__string(host, dev_name(dev->parent))
+		__field(u32, status)
+	),
+	TP_fast_assign(
+		__assign_str(devname);
+		__assign_str(host);
+		__entry->status = status;
+	),
+	TP_printk("device=%s host=%s status='%s'",
+		  __get_str(devname), __get_str(host),
+		  show_ce_errs(__entry->status)
+	)
+);
+
 TRACE_EVENT(cxl_aer_correctable_error,
 	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status),
 	TP_ARGS(cxlmd, status),
-- 
2.34.1
Re: [PATCH 13/15] cxl/pci: Add trace logging for CXL PCIe port RAS errors
Posted by Jonathan Cameron 1 month, 1 week ago
On Tue, 8 Oct 2024 17:16:55 -0500
Terry Bowman <terry.bowman@amd.com> wrote:

> The CXL drivers use kernel trace functions for logging endpoint and
> RCH downstream port RAS errors. However, similar functionality is
> required for CXL root ports, CXL downstream switch ports, and CXL
> upstream switch ports.
> 
> Introduce trace logging functions for both RAS correctable and
> uncorrectable errors specific to CXL PCIe ports. Additionally, update
> the PCIe port error handlers to invoke these new trace functions.
> 
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>

+CC Shiju Jose

Shiju,

Could you check the tracepoints / vs rasdaemon etc

Terry,

Just a patch ordering question from me.

> ---
>  drivers/cxl/core/pci.c   | 16 ++++++++++----
>  drivers/cxl/core/trace.h | 47 ++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 59 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
> index 7e3770f7a955..4706113d2582 100644
> --- a/drivers/cxl/core/pci.c
> +++ b/drivers/cxl/core/pci.c
> @@ -697,10 +697,14 @@ 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;

Add a blank line here to make that early exit easier to spot.

> +	writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
> +
> +	if (is_cxl_memdev(dev))
>  		trace_cxl_aer_correctable_error(to_cxl_memdev(dev), status);
So after previous patch, this code will be called for ports without this
check in here?  Perhaps the two patches need to be swapped in order?


However, we already know the type of device at the callers. Maybe just
pass that in here.
> -	}
> +	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)
> @@ -756,7 +760,11 @@ static bool __cxl_handle_ras(struct device *dev, void __iomem *ras_base)
>  	}
>  
>  	header_log_copy(ras_base, hl);
> -	trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
> +	if (is_cxl_memdev(dev))
> +		trace_cxl_aer_uncorrectable_error(to_cxl_memdev(dev), status, fe, hl);
> +	else if (dev_is_pci(dev))
> +		trace_cxl_port_aer_uncorrectable_error(dev, status, fe, hl);
> +
>  	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);
>  
>  	return true;
> diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
> index 9167cfba7f59..6305c0eea627 100644
> --- a/drivers/cxl/core/trace.h
> +++ b/drivers/cxl/core/trace.h
> @@ -48,6 +48,34 @@
>  	{ CXL_RAS_UC_IDE_RX_ERR, "IDE Rx Error" }			  \
>  )
>  
> +TRACE_EVENT(cxl_port_aer_uncorrectable_error,
> +	    TP_PROTO(struct device *dev, u32 status, u32 fe, u32 *hl),
> +	TP_ARGS(dev, status, fe, hl),
> +	TP_STRUCT__entry(
> +		__string(devname, dev_name(dev))
> +		__string(host, dev_name(dev->parent))
> +		__field(u32, status)
> +		__field(u32, first_error)
> +		__array(u32, header_log, CXL_HEADERLOG_SIZE_U32)
> +	),
> +	TP_fast_assign(
> +		__assign_str(devname);
> +		__assign_str(host);
> +		__entry->status = status;
> +		__entry->first_error = fe;
> +		/*
> +		 * Embed the 512B headerlog data for user app retrieval and
> +		 * parsing, but no need to print this in the trace buffer.
> +		 */
> +		memcpy(__entry->header_log, hl, CXL_HEADERLOG_SIZE);
> +	),
> +	TP_printk("device=%s host=%s status: '%s' first_error: '%s'",
> +		  __get_str(devname), __get_str(host),
> +		  show_uc_errs(__entry->status),
> +		  show_uc_errs(__entry->first_error)
> +	)
> +);
> +
>  TRACE_EVENT(cxl_aer_uncorrectable_error,
>  	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status, u32 fe, u32 *hl),
>  	TP_ARGS(cxlmd, status, fe, hl),
> @@ -96,6 +124,25 @@ TRACE_EVENT(cxl_aer_uncorrectable_error,
>  	{ CXL_RAS_CE_PHYS_LAYER_ERR, "Received Error From Physical Layer" }	\
>  )
>  
> +TRACE_EVENT(cxl_port_aer_correctable_error,
> +	TP_PROTO(struct device *dev, u32 status),
> +	TP_ARGS(dev, status),
> +	TP_STRUCT__entry(
> +		__string(devname, dev_name(dev))
> +		__string(host, dev_name(dev->parent))
> +		__field(u32, status)
> +	),
> +	TP_fast_assign(
> +		__assign_str(devname);
> +		__assign_str(host);
> +		__entry->status = status;
> +	),
> +	TP_printk("device=%s host=%s status='%s'",
> +		  __get_str(devname), __get_str(host),
> +		  show_ce_errs(__entry->status)
> +	)
> +);
> +
>  TRACE_EVENT(cxl_aer_correctable_error,
>  	TP_PROTO(const struct cxl_memdev *cxlmd, u32 status),
>  	TP_ARGS(cxlmd, status),