[v6] Make ELOG and GHES log and trace consistently

[PATCH 4/6 v6] acpi/ghes: Add helper for CXL protocol errors checks

Posted by Fabio M. De Francesco 3 months, 2 weeks ago

Move the CPER CXL protocol errors validity out of
cxl_cper_post_prot_err() to cxl_cper_sec_prot_err_valid() and limit the
serial number check only to CXL agents that are CXL devices (UEFI v2.10,
Appendix N.2.13).

Signed-off-by: Fabio M. De Francesco <fabio.m.de.francesco@linux.intel.com>
---
 drivers/acpi/apei/ghes.c | 32 ++++++++++++++++++++++----------
 include/cxl/event.h      | 10 ++++++++++
 2 files changed, 32 insertions(+), 10 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index d6fe5f020e96..e69ae864f43d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -706,30 +706,42 @@ static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
 static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
 struct work_struct *cxl_cper_prot_err_work;
 
-static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
-				   int severity)
+int cxl_cper_sec_prot_err_valid(struct cxl_cper_sec_prot_err *prot_err)
 {
-	struct cxl_cper_prot_err_work_data wd;
-	u8 *dvsec_start, *cap_start;
-
 	if (!(prot_err->valid_bits & PROT_ERR_VALID_AGENT_ADDRESS)) {
 		pr_err_ratelimited("CXL CPER invalid agent type\n");
-		return;
+		return -EINVAL;
 	}
 
 	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
 		pr_err_ratelimited("CXL CPER invalid protocol error log\n");
-		return;
+		return -EINVAL;
 	}
 
 	if (prot_err->err_len != sizeof(struct cxl_ras_capability_regs)) {
 		pr_err_ratelimited("CXL CPER invalid RAS Cap size (%u)\n",
 				   prot_err->err_len);
-		return;
+		return -EINVAL;
 	}
 
-	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
-		pr_warn(FW_WARN "CXL CPER no device serial number\n");
+	if ((prot_err->agent_type == RCD || prot_err->agent_type == DEVICE ||
+	     prot_err->agent_type == LD || prot_err->agent_type == FMLD) &&
+	    !(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
+		pr_warn_ratelimited(FW_WARN
+				    "CXL CPER no device serial number\n");
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_cper_sec_prot_err_valid);
+
+static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				   int severity)
+{
+	struct cxl_cper_prot_err_work_data wd;
+	u8 *dvsec_start, *cap_start;
+
+	if (cxl_cper_sec_prot_err_valid(prot_err))
+		return;
 
 	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
 
diff --git a/include/cxl/event.h b/include/cxl/event.h
index 6fd90f9cc203..4d7d1036ea9c 100644
--- a/include/cxl/event.h
+++ b/include/cxl/event.h
@@ -320,4 +320,14 @@ static inline int cxl_cper_prot_err_kfifo_get(struct cxl_cper_prot_err_work_data
 }
 #endif
 
+#ifdef CONFIG_ACPI_APEI_PCIEAER
+int cxl_cper_sec_prot_err_valid(struct cxl_cper_sec_prot_err *prot_err);
+#else
+static inline int
+cxl_cper_sec_prot_err_valid(struct cxl_cper_sec_prot_err *prot_err)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 #endif /* _LINUX_CXL_EVENT_H */
-- 
2.51.0

Re: [PATCH 4/6 v6] acpi/ghes: Add helper for CXL protocol errors checks

Posted by Jonathan Cameron 3 months, 1 week ago

On Thu, 23 Oct 2025 14:25:39 +0200
"Fabio M. De Francesco" <fabio.m.de.francesco@linux.intel.com> wrote:

> Move the CPER CXL protocol errors validity out of

validity check

> cxl_cper_post_prot_err() to cxl_cper_sec_prot_err_valid() and limit the

to new cxl_cper_sec_prot_err_valid() 

as otherwise it sounds like it already exists.

> serial number check only to CXL agents that are CXL devices (UEFI v2.10,
> Appendix N.2.13).

Perhaps a little more here on why.  I assume because you are going to have
a second user for it, but good to say that. Also serves to justify the
export.

> 
> Signed-off-by: Fabio M. De Francesco <fabio.m.de.francesco@linux.intel.com>
> ---
>  drivers/acpi/apei/ghes.c | 32 ++++++++++++++++++++++----------
>  include/cxl/event.h      | 10 ++++++++++
>  2 files changed, 32 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index d6fe5f020e96..e69ae864f43d 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -706,30 +706,42 @@ static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
>  static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
>  struct work_struct *cxl_cper_prot_err_work;
>  
> -static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
> -				   int severity)
> +int cxl_cper_sec_prot_err_valid(struct cxl_cper_sec_prot_err *prot_err)

Useful to return an error number?  Or would a bool be better given it is either
valid or not?

Otherwise looks good to me,

Jonathan

>  {
> -	struct cxl_cper_prot_err_work_data wd;
> -	u8 *dvsec_start, *cap_start;
> -
>  	if (!(prot_err->valid_bits & PROT_ERR_VALID_AGENT_ADDRESS)) {
>  		pr_err_ratelimited("CXL CPER invalid agent type\n");
> -		return;
> +		return -EINVAL;
>  	}
>  
>  	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
>  		pr_err_ratelimited("CXL CPER invalid protocol error log\n");
> -		return;
> +		return -EINVAL;
>  	}
>  
>  	if (prot_err->err_len != sizeof(struct cxl_ras_capability_regs)) {
>  		pr_err_ratelimited("CXL CPER invalid RAS Cap size (%u)\n",
>  				   prot_err->err_len);
> -		return;
> +		return -EINVAL;
>  	}
>  
> -	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
> -		pr_warn(FW_WARN "CXL CPER no device serial number\n");
> +	if ((prot_err->agent_type == RCD || prot_err->agent_type == DEVICE ||
> +	     prot_err->agent_type == LD || prot_err->agent_type == FMLD) &&
> +	    !(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
> +		pr_warn_ratelimited(FW_WARN
> +				    "CXL CPER no device serial number\n");
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(cxl_cper_sec_prot_err_valid);
> +
> +static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
> +				   int severity)
> +{
> +	struct cxl_cper_prot_err_work_data wd;
> +	u8 *dvsec_start, *cap_start;
> +
> +	if (cxl_cper_sec_prot_err_valid(prot_err))
> +		return;
>  
>  	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
>

Re: [PATCH 4/6 v6] acpi/ghes: Add helper for CXL protocol errors checks

Posted by Fabio M. De Francesco 3 months ago

On Tuesday, October 28, 2025 3:54:15 PM Central European Standard Time Jonathan Cameron wrote:
> On Thu, 23 Oct 2025 14:25:39 +0200
> "Fabio M. De Francesco" <fabio.m.de.francesco@linux.intel.com> wrote:
> 
> > Move the CPER CXL protocol errors validity out of
> 
> validity check
> 
> > cxl_cper_post_prot_err() to cxl_cper_sec_prot_err_valid() and limit the
> 
> to new cxl_cper_sec_prot_err_valid() 
> 
> as otherwise it sounds like it already exists.
> 
> > serial number check only to CXL agents that are CXL devices (UEFI v2.10,
> > Appendix N.2.13).
> 
> Perhaps a little more here on why.  I assume because you are going to have
> a second user for it, but good to say that. Also serves to justify the
> export.
> 
Hi Jonathan,

All the corrections you made will be applied to the next version.
> > 
> > Signed-off-by: Fabio M. De Francesco <fabio.m.de.francesco@linux.intel.com>
> > ---
> >  drivers/acpi/apei/ghes.c | 32 ++++++++++++++++++++++----------
> >  include/cxl/event.h      | 10 ++++++++++
> >  2 files changed, 32 insertions(+), 10 deletions(-)
> > 
> > diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> > index d6fe5f020e96..e69ae864f43d 100644
> > --- a/drivers/acpi/apei/ghes.c
> > +++ b/drivers/acpi/apei/ghes.c
> > @@ -706,30 +706,42 @@ static DEFINE_KFIFO(cxl_cper_prot_err_fifo, struct cxl_cper_prot_err_work_data,
> >  static DEFINE_SPINLOCK(cxl_cper_prot_err_work_lock);
> >  struct work_struct *cxl_cper_prot_err_work;
> >  
> > -static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
> > -				   int severity)
> > +int cxl_cper_sec_prot_err_valid(struct cxl_cper_sec_prot_err *prot_err)
> 
> Useful to return an error number?  Or would a bool be better given it is either
> valid or not?
> 
I prefer to return more information when reasonable and leave the callers free
to use or ignore the specific error number.

Fabio
>
> Otherwise looks good to me,
> 
> Jonathan
> 
> >  {
> > -	struct cxl_cper_prot_err_work_data wd;
> > -	u8 *dvsec_start, *cap_start;
> > -
> >  	if (!(prot_err->valid_bits & PROT_ERR_VALID_AGENT_ADDRESS)) {
> >  		pr_err_ratelimited("CXL CPER invalid agent type\n");
> > -		return;
> > +		return -EINVAL;
> >  	}
> >  
> >  	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
> >  		pr_err_ratelimited("CXL CPER invalid protocol error log\n");
> > -		return;
> > +		return -EINVAL;
> >  	}
> >  
> >  	if (prot_err->err_len != sizeof(struct cxl_ras_capability_regs)) {
> >  		pr_err_ratelimited("CXL CPER invalid RAS Cap size (%u)\n",
> >  				   prot_err->err_len);
> > -		return;
> > +		return -EINVAL;
> >  	}
> >  
> > -	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
> > -		pr_warn(FW_WARN "CXL CPER no device serial number\n");
> > +	if ((prot_err->agent_type == RCD || prot_err->agent_type == DEVICE ||
> > +	     prot_err->agent_type == LD || prot_err->agent_type == FMLD) &&
> > +	    !(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER))
> > +		pr_warn_ratelimited(FW_WARN
> > +				    "CXL CPER no device serial number\n");
> > +
> > +	return 0;
> > +}
> > +EXPORT_SYMBOL_GPL(cxl_cper_sec_prot_err_valid);
> > +
> > +static void cxl_cper_post_prot_err(struct cxl_cper_sec_prot_err *prot_err,
> > +				   int severity)
> > +{
> > +	struct cxl_cper_prot_err_work_data wd;
> > +	u8 *dvsec_start, *cap_start;
> > +
> > +	if (cxl_cper_sec_prot_err_valid(prot_err))
> > +		return;
> >  
> >  	guard(spinlock_irqsave)(&cxl_cper_prot_err_work_lock);
> >  
> 
> 
>

[PATCH 1/6 v6] ACPI: extlog: Trace CPER Non-standard Section Body
[PATCH 2/6 v6] ACPI: extlog: Trace CPER PCI Express Error Section
[PATCH 3/6 v6] acpi/ghes: Make GHES select ACPI_APEI_PCIEAER
[PATCH 4/6 v6] acpi/ghes: Add helper for CXL protocol errors checks
[PATCH 5/6 v6] acpi/ghes: Add helper to copy CXL protocol error info to work struct
[PATCH 6/6 v6] ACPI: extlog: Trace CPER CXL Protocol Error Section