[PATCH] cxl: Add endpoint decoder flags clear when PCI reset happens

[PATCH] cxl: Add endpoint decoder flags clear when PCI reset happens

[Dave Jiang]

When a PCI reset happens, the lock and enable flags of the CXL device
should be cleared to avoid stale state flags after reset. Add flag
clearing during cxl_reset_done() to clear the relevant endpoint
decoder flags for all decoders of the endpoint device.

Reproted-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/cxl.h |  1 +
 drivers/cxl/pci.c | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 9b947286eb9b..d4be082876f2 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -333,6 +333,7 @@ int cxl_dport_map_rcd_linkcap(struct pci_dev *pdev, struct cxl_dport *dport);
 #define CXL_DECODER_F_LOCK  BIT(4)
 #define CXL_DECODER_F_ENABLE    BIT(5)
 #define CXL_DECODER_F_NORMALIZED_ADDRESSING BIT(6)
+#define CXL_DECODER_F_CLEAR_MASK (CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK)
 
 enum cxl_decoder_type {
 	CXL_DECODER_DEVMEM = 2,
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index fbb300a01830..ac71dadfee7d 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1030,6 +1030,19 @@ static void cxl_error_resume(struct pci_dev *pdev)
 		 dev->driver ? "successful" : "failed");
 }
 
+static int cxl_decoder_clear_flags(struct device *dev, void *data)
+{
+	struct cxl_endpoint_decoder *cxled;
+
+	if (!is_endpoint_decoder(dev))
+		return 0;
+
+	cxled = to_cxl_endpoint_decoder(dev);
+	cxled->cxld.flags &= ~CXL_DECODER_F_CLEAR_MASK;
+
+	return 0;
+}
+
 static void cxl_reset_done(struct pci_dev *pdev)
 {
 	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
@@ -1045,6 +1058,9 @@ static void cxl_reset_done(struct pci_dev *pdev)
 	guard(device)(&cxlmd->dev);
 	if (cxlmd->endpoint &&
 	    cxl_endpoint_decoder_reset_detected(cxlmd->endpoint)) {
+		device_for_each_child(&cxlmd->endpoint->dev, NULL,
+				      cxl_decoder_clear_flags);
+
 		dev_crit(dev, "SBR happened without memory regions removal.\n");
 		dev_crit(dev, "System may be unstable if regions hosted system memory.\n");
 		add_taint(TAINT_USER, LOCKDEP_STILL_OK);

base-commit: 11439c4635edd669ae435eec308f4ab8a0804808
-- 
2.53.0

Re: [PATCH] cxl: Add endpoint decoder flags clear when PCI reset happens

[Alison Schofield]

On Wed, Mar 11, 2026 at 03:47:05PM -0700, Dave Jiang wrote:
> When a PCI reset happens, the lock and enable flags of the CXL device
> should be cleared to avoid stale state flags after reset. Add flag
> clearing during cxl_reset_done() to clear the relevant endpoint
> decoder flags for all decoders of the endpoint device.

Some opinions in code below, but with or without any changes:

Reviewed-by: Alison Schofield <alison.schofield@intel.com>

> 
> Reproted-by: Dan Williams <dan.j.williams@intel.com>
> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> ---
>  drivers/cxl/cxl.h |  1 +
>  drivers/cxl/pci.c | 16 ++++++++++++++++
>  2 files changed, 17 insertions(+)
> 
> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
> index 9b947286eb9b..d4be082876f2 100644
> --- a/drivers/cxl/cxl.h
> +++ b/drivers/cxl/cxl.h
> @@ -333,6 +333,7 @@ int cxl_dport_map_rcd_linkcap(struct pci_dev *pdev, struct cxl_dport *dport);
>  #define CXL_DECODER_F_LOCK  BIT(4)
>  #define CXL_DECODER_F_ENABLE    BIT(5)
>  #define CXL_DECODER_F_NORMALIZED_ADDRESSING BIT(6)
> +#define CXL_DECODER_F_CLEAR_MASK (CXL_DECODER_F_ENABLE | CXL_DECODER_F_LOCK)

Maybe the RESET_MASK to tie it to the reset context.

>  
>  enum cxl_decoder_type {
>  	CXL_DECODER_DEVMEM = 2,
> diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
> index fbb300a01830..ac71dadfee7d 100644
> --- a/drivers/cxl/pci.c
> +++ b/drivers/cxl/pci.c
> @@ -1030,6 +1030,19 @@ static void cxl_error_resume(struct pci_dev *pdev)
>  		 dev->driver ? "successful" : "failed");
>  }
>  
> +static int cxl_decoder_clear_flags(struct device *dev, void *data)
> +{
> +	struct cxl_endpoint_decoder *cxled;
> +
> +	if (!is_endpoint_decoder(dev))
> +		return 0;
> +
> +	cxled = to_cxl_endpoint_decoder(dev);
> +	cxled->cxld.flags &= ~CXL_DECODER_F_CLEAR_MASK;
> +
> +	return 0;
> +}

Above is close to being a reusable helper where data can be the bits
to clear. Then the name cxl_decoder_clear_flags() makes more sense.
If it's special only for reset, decoder_reset_flags makes more sense.

> +
>  static void cxl_reset_done(struct pci_dev *pdev)
>  {
>  	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
> @@ -1045,6 +1058,9 @@ static void cxl_reset_done(struct pci_dev *pdev)
>  	guard(device)(&cxlmd->dev);
>  	if (cxlmd->endpoint &&
>  	    cxl_endpoint_decoder_reset_detected(cxlmd->endpoint)) {
> +		device_for_each_child(&cxlmd->endpoint->dev, NULL,
> +				      cxl_decoder_clear_flags);
> +
>  		dev_crit(dev, "SBR happened without memory regions removal.\n");
>  		dev_crit(dev, "System may be unstable if regions hosted system memory.\n");
>  		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
> 
> base-commit: 11439c4635edd669ae435eec308f4ab8a0804808
> -- 
> 2.53.0
> 
>