diff mbox series

[V12,8/9] cxl/port: Retry reading CDAT on failure

Message ID 20220628041527.742333-9-ira.weiny@intel.com (mailing list archive)
State Superseded
Headers show
Series CXL: Read CDAT and DSMAS data | expand

Commit Message

Ira Weiny June 28, 2022, 4:15 a.m. UTC
From: Ira Weiny <ira.weiny@intel.com>

The CDAT read may fail for a number of reasons but mainly it is possible
to get different parts of a valid state.  The checksum in the CDAT table
protects against this.

Now that the cdat data is validated, issue a retry if the CDAT read
fails.  For now 5 retries are implemented.

Reviewed-by: Ben Widawsky <bwidawsk@kernel.org>
Reviewed-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

---
Changes from V10
	Pick up review tag and fix commit message

Changes from V9
	Alison Schofield/Davidlohr Bueso
		Print debug on each iteration and error only after failure

Changes from V8
	Move code to cxl/core/pci.c

Changes from V6
	Move to pci.c
	Fix retries count
	Change to 5 retries

Changes from V5:
	New patch -- easy to push off or drop.
---
 drivers/cxl/core/pci.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

Comments

Jonathan Cameron June 28, 2022, 2:57 p.m. UTC | #1
On Mon, 27 Jun 2022 21:15:26 -0700
ira.weiny@intel.com wrote:

> From: Ira Weiny <ira.weiny@intel.com>
> 
> The CDAT read may fail for a number of reasons but mainly it is possible
> to get different parts of a valid state.  The checksum in the CDAT table
> protects against this.
> 
> Now that the cdat data is validated, issue a retry if the CDAT read
> fails.  For now 5 retries are implemented.
> 
> Reviewed-by: Ben Widawsky <bwidawsk@kernel.org>
> Reviewed-by: Alison Schofield <alison.schofield@intel.com>
> Signed-off-by: Ira Weiny <ira.weiny@intel.com>


> 
> ---
> Changes from V10
> 	Pick up review tag and fix commit message
> 
> Changes from V9
> 	Alison Schofield/Davidlohr Bueso
> 		Print debug on each iteration and error only after failure
> 
> Changes from V8
> 	Move code to cxl/core/pci.c
> 
> Changes from V6
> 	Move to pci.c
> 	Fix retries count
> 	Change to 5 retries
> 
> Changes from V5:
> 	New patch -- easy to push off or drop.
> ---
>  drivers/cxl/core/pci.c | 41 ++++++++++++++++++++++++++++++-----------
>  1 file changed, 30 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
> index 6d775cc3dca1..d7c2a415cc5f 100644
> --- a/drivers/cxl/core/pci.c
> +++ b/drivers/cxl/core/pci.c
> @@ -618,36 +618,30 @@ static int cxl_cdat_read_table(struct device *dev,
>  	return rc;
>  }
>  
> -/**
> - * read_cdat_data - Read the CDAT data on this port
> - * @port: Port to read data from
> - *
> - * This call will sleep waiting for responses from the DOE mailbox.
> - */
> -void read_cdat_data(struct cxl_port *port)
> +static int __read_cdat_data(struct cxl_port *port)
>  {
>  	static struct pci_doe_mb *cdat_mb;
>  	struct device *dev = &port->dev;
>  	struct device *uport = port->uport;
>  	size_t cdat_length;
> -	int ret;
> +	int ret = 0;
Fairly sure there isn't a path in which ret isn't set...


Mixing ret and rc is a bit inconsistent, maybe scrub patch set for
one or the other. (My fault originally I think :)


>  
>  	cdat_mb = find_cdat_mb(uport);
>  	if (!cdat_mb) {
>  		dev_dbg(dev, "No CDAT mailbox\n");
> -		return;
> +		return -EIO;
>  	}
>  
>  	port->cdat_sup = true;
>  
>  	if (cxl_cdat_get_length(dev, cdat_mb, &cdat_length)) {
>  		dev_dbg(dev, "No CDAT length\n");
> -		return;
> +		return -EIO;
>  	}
>  
>  	port->cdat.table = devm_kzalloc(dev, cdat_length, GFP_KERNEL);
>  	if (!port->cdat.table)
> -		return;
> +		return -ENOMEM;
>  
>  	port->cdat.length = cdat_length;
>  	ret = cxl_cdat_read_table(dev, cdat_mb, &port->cdat);
> @@ -658,5 +652,30 @@ void read_cdat_data(struct cxl_port *port)
>  		port->cdat.length = 0;
>  		dev_err(dev, "CDAT data read error\n");
>  	}
> +
> +	return ret;
> +}
> +
> +/**
> + * read_cdat_data - Read the CDAT data on this port
> + * @port: Port to read data from
> + *
> + * This call will sleep waiting for responses from the DOE mailbox.
> + */
> +void read_cdat_data(struct cxl_port *port)
> +{
> +	int retries = 5;
> +	int rc;
> +
> +	while (retries--) {
> +		rc = __read_cdat_data(port);
> +		if (!rc)
> +			return;
> +		dev_dbg(&port->dev,
> +			"CDAT data read error rc=%d (retries %d)\n",
> +			rc, retries);
> +	}
> +	dev_err(&port->dev, "CDAT data read failed after %d retries\n",
> +		retries);
>  }
>  EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
Ira Weiny June 30, 2022, 3:40 a.m. UTC | #2
On Tue, Jun 28, 2022 at 03:57:20PM +0100, Jonathan Cameron wrote:
> On Mon, 27 Jun 2022 21:15:26 -0700
> ira.weiny@intel.com wrote:
> 

[snip]

> >  
> > -/**
> > - * read_cdat_data - Read the CDAT data on this port
> > - * @port: Port to read data from
> > - *
> > - * This call will sleep waiting for responses from the DOE mailbox.
> > - */
> > -void read_cdat_data(struct cxl_port *port)
> > +static int __read_cdat_data(struct cxl_port *port)
> >  {
> >  	static struct pci_doe_mb *cdat_mb;
> >  	struct device *dev = &port->dev;
> >  	struct device *uport = port->uport;
> >  	size_t cdat_length;
> > -	int ret;
> > +	int ret = 0;
> Fairly sure there isn't a path in which ret isn't set...
> 

Yep.

> 
> Mixing ret and rc is a bit inconsistent, maybe scrub patch set for
> one or the other. (My fault originally I think :)

Ok PCI uses both ret and rc.  :-(  But CXL seems to be consistent with rc.  So
I've used rc with the new series which I think satisfies both subsystems.

Thanks again for the detail review of the series.  Hopefully there will be a
new version out tomorrow.
Ira

> 
> 
> >  
> >  	cdat_mb = find_cdat_mb(uport);
> >  	if (!cdat_mb) {
> >  		dev_dbg(dev, "No CDAT mailbox\n");
> > -		return;
> > +		return -EIO;
> >  	}
> >  
> >  	port->cdat_sup = true;
> >  
> >  	if (cxl_cdat_get_length(dev, cdat_mb, &cdat_length)) {
> >  		dev_dbg(dev, "No CDAT length\n");
> > -		return;
> > +		return -EIO;
> >  	}
> >  
> >  	port->cdat.table = devm_kzalloc(dev, cdat_length, GFP_KERNEL);
> >  	if (!port->cdat.table)
> > -		return;
> > +		return -ENOMEM;
> >  
> >  	port->cdat.length = cdat_length;
> >  	ret = cxl_cdat_read_table(dev, cdat_mb, &port->cdat);
> > @@ -658,5 +652,30 @@ void read_cdat_data(struct cxl_port *port)
> >  		port->cdat.length = 0;
> >  		dev_err(dev, "CDAT data read error\n");
> >  	}
> > +
> > +	return ret;
> > +}
> > +
> > +/**
> > + * read_cdat_data - Read the CDAT data on this port
> > + * @port: Port to read data from
> > + *
> > + * This call will sleep waiting for responses from the DOE mailbox.
> > + */
> > +void read_cdat_data(struct cxl_port *port)
> > +{
> > +	int retries = 5;
> > +	int rc;
> > +
> > +	while (retries--) {
> > +		rc = __read_cdat_data(port);
> > +		if (!rc)
> > +			return;
> > +		dev_dbg(&port->dev,
> > +			"CDAT data read error rc=%d (retries %d)\n",
> > +			rc, retries);
> > +	}
> > +	dev_err(&port->dev, "CDAT data read failed after %d retries\n",
> > +		retries);
> >  }
> >  EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);
>
diff mbox series

Patch

diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 6d775cc3dca1..d7c2a415cc5f 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -618,36 +618,30 @@  static int cxl_cdat_read_table(struct device *dev,
 	return rc;
 }
 
-/**
- * read_cdat_data - Read the CDAT data on this port
- * @port: Port to read data from
- *
- * This call will sleep waiting for responses from the DOE mailbox.
- */
-void read_cdat_data(struct cxl_port *port)
+static int __read_cdat_data(struct cxl_port *port)
 {
 	static struct pci_doe_mb *cdat_mb;
 	struct device *dev = &port->dev;
 	struct device *uport = port->uport;
 	size_t cdat_length;
-	int ret;
+	int ret = 0;
 
 	cdat_mb = find_cdat_mb(uport);
 	if (!cdat_mb) {
 		dev_dbg(dev, "No CDAT mailbox\n");
-		return;
+		return -EIO;
 	}
 
 	port->cdat_sup = true;
 
 	if (cxl_cdat_get_length(dev, cdat_mb, &cdat_length)) {
 		dev_dbg(dev, "No CDAT length\n");
-		return;
+		return -EIO;
 	}
 
 	port->cdat.table = devm_kzalloc(dev, cdat_length, GFP_KERNEL);
 	if (!port->cdat.table)
-		return;
+		return -ENOMEM;
 
 	port->cdat.length = cdat_length;
 	ret = cxl_cdat_read_table(dev, cdat_mb, &port->cdat);
@@ -658,5 +652,30 @@  void read_cdat_data(struct cxl_port *port)
 		port->cdat.length = 0;
 		dev_err(dev, "CDAT data read error\n");
 	}
+
+	return ret;
+}
+
+/**
+ * read_cdat_data - Read the CDAT data on this port
+ * @port: Port to read data from
+ *
+ * This call will sleep waiting for responses from the DOE mailbox.
+ */
+void read_cdat_data(struct cxl_port *port)
+{
+	int retries = 5;
+	int rc;
+
+	while (retries--) {
+		rc = __read_cdat_data(port);
+		if (!rc)
+			return;
+		dev_dbg(&port->dev,
+			"CDAT data read error rc=%d (retries %d)\n",
+			rc, retries);
+	}
+	dev_err(&port->dev, "CDAT data read failed after %d retries\n",
+		retries);
 }
 EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL);