Re: [PATCH v14 16/16] PCI/CXL: Restore CXL state after CXL bus reset

[Bjorn Helgaas <helgaas@kernel.org>]

On Thu, Oct 01, 2026 at 09:22:27AM +0000, Srirangan Madhavan wrote:
> CXL bus reset can clear HDM decoder programming and CXL Device DVSEC
> control state. Restore the cached state after a successful cxl_bus reset
> while IOMMU exclusion remains active.
> 
> Restore PCI configuration first so HDM MMIO is accessible, and preserve a
> disabled state if restoration fails.
> 
> Tested-by: Richard Cheng <icheng@nvidia.com>
> Signed-off-by: Srirangan Madhavan <smadhavan@nvidia.com>

Acked-by: Bjorn Helgaas <bhelgaas@google.com>	# pci/pci.c

> ---
>  drivers/cxl/core/resource.c | 23 +++++++++++++++++++++--
>  drivers/pci/pci.c           |  8 ++++++++
>  include/cxl/cxl.h           | 17 +++++++++++++++++
>  3 files changed, 46 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/cxl/core/resource.c b/drivers/cxl/core/resource.c
> index efbab341b30f..3422139ae3ab 100644
> --- a/drivers/cxl/core/resource.c
> +++ b/drivers/cxl/core/resource.c
> @@ -625,12 +625,12 @@ static int cxl_restore_hdm_decoder(struct pci_dev *pdev, void __iomem *hdm,
>  	return 0;
>  }
>  
> -static int cxl_snapshot_hdm(struct pci_dev *pdev,
> -			    struct cxl_hdm_info **snapshot)
> +int cxl_snapshot_hdm(struct pci_dev *pdev, struct cxl_hdm_info **snapshot)
>  {
>  	struct cxl_hdm_info *info;
>  	size_t size;
>  
> +	device_lock_assert(&pdev->dev);
>  	guard(rwsem_read)(&cxl_rwsem.dpa);
>  	info = pdev->hdm;
>  	if (!info)
> @@ -798,6 +798,25 @@ static int cxl_reset_save_restored_state(struct pci_dev *pdev, u16 command)
>  	return rc;
>  }
>  
> +int cxl_restore_state_after_pci_reset(struct pci_dev *pdev,
> +				      struct cxl_hdm_info *snapshot)
> +{
> +	u16 command;
> +	int rc;
> +
> +	device_lock_assert(&pdev->dev);
> +	guard(rwsem_write)(&cxl_rwsem.region);
> +
> +	cxl_restore_pci_state_for_hdm_restore(pdev, &command);
> +	rc = cxl_restore_state(pdev, snapshot);
> +	if (rc) {
> +		cxl_reset_save_disabled_state(pdev);
> +		return rc;
> +	}
> +
> +	return cxl_reset_save_restored_state(pdev, command);
> +}
> +
>  /*
>   * CXL r4.0 sec 9.7.2 defines the reset completion timeout encodings.
>   * Sec 9.7.3 leaves config-space access behavior undefined for 100 ms after
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index dc57a202c91f..6928c99aa785 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -5015,6 +5015,7 @@ static int pci_reset_bus_function(struct pci_dev *dev, bool probe)
>  
>  static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
>  {
> +	struct cxl_hdm_info *snapshot __free(kfree) = NULL;
>  	struct pci_dev *bridge;
>  	u16 dvsec, reg, val;
>  	int rc;
> @@ -5037,6 +5038,10 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
>  	if (rc)
>  		return -ENOTTY;
>  
> +	rc = cxl_snapshot_hdm(dev, &snapshot);
> +	if (rc && rc != -ENXIO)
> +		return rc;
> +
>  	rc = pci_dev_reset_iommu_prepare(dev);
>  	if (rc) {
>  		pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", rc);
> @@ -5057,6 +5062,9 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe)
>  		pci_write_config_word(bridge, dvsec + PCI_DVSEC_CXL_PORT_CTL,
>  				      reg);
>  
> +	if (!rc && snapshot)
> +		rc = cxl_restore_state_after_pci_reset(dev, snapshot);
> +
>  	pci_dev_reset_iommu_done(dev);
>  	return rc;
>  }
> diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
> index 9904eaed5af1..b83cfaed618f 100644
> --- a/include/cxl/cxl.h
> +++ b/include/cxl/cxl.h
> @@ -207,6 +207,9 @@ struct cxl_register_map {
>  #ifdef CONFIG_CXL_RESET
>  void pci_cxl_hdm_cache_init(struct pci_dev *pdev);
>  void pci_cxl_hdm_cache_release(struct pci_dev *pdev);
> +int cxl_snapshot_hdm(struct pci_dev *pdev, struct cxl_hdm_info **snapshot);
> +int cxl_restore_state_after_pci_reset(struct pci_dev *pdev,
> +				      struct cxl_hdm_info *snapshot);
>  int cxl_reset_function(struct pci_dev *pdev, bool probe);
>  #else
>  static inline void pci_cxl_hdm_cache_init(struct pci_dev *pdev)
> @@ -217,6 +220,20 @@ static inline void pci_cxl_hdm_cache_release(struct pci_dev *pdev)
>  {
>  }
>  
> +static inline int cxl_snapshot_hdm(struct pci_dev *pdev,
> +				   struct cxl_hdm_info **snapshot)
> +{
> +	*snapshot = NULL;
> +	return -ENXIO;
> +}
> +
> +static inline int
> +cxl_restore_state_after_pci_reset(struct pci_dev *pdev,
> +				  struct cxl_hdm_info *snapshot)
> +{
> +	return 0;
> +}
> +
>  static inline int cxl_reset_function(struct pci_dev *pdev, bool probe)
>  {
>  	return -ENOTTY;
> -- 
> 2.43.0
>