[2/2] cxl: fix possible null-ptr-deref in cxl_pci_init_afu|adapter()

If device_register() fails in cxl_pci_afu|adapter(), the device
is not added, device_unregister() can not be called in the error
path, otherwise it will cause a null-ptr-deref because of removing
not added device.

As comment of device_register() says, it should use put_device() to give
up the reference in the error path. So split device_unregister() into
device_del() and put_device(), then goes to put dev when register fails.

Fixes: f204e0b8cedd ("cxl: Driver code for powernv PCIe based cards for userspace access")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
---
 drivers/misc/cxl/pci.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

On 11/11/2022 15:54, Yang Yingliang wrote:
> If device_register() fails in cxl_pci_afu|adapter(), the device
> is not added, device_unregister() can not be called in the error
> path, otherwise it will cause a null-ptr-deref because of removing
> not added device.
> 
> As comment of device_register() says, it should use put_device() to give
> up the reference in the error path. So split device_unregister() into
> device_del() and put_device(), then goes to put dev when register fails.
> 
> Fixes: f204e0b8cedd ("cxl: Driver code for powernv PCIe based cards for userspace access")
> Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
> ---


Acked-by: Frederic Barrat <fbarrat@linux.ibm.com>

   Fred


>   drivers/misc/cxl/pci.c | 20 ++++++++++++--------
>   1 file changed, 12 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
> index 3de0aea62ade..6d495d641c95 100644
> --- a/drivers/misc/cxl/pci.c
> +++ b/drivers/misc/cxl/pci.c
> @@ -1164,10 +1164,10 @@ static int pci_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
>   	 * if it returns an error!
>   	 */
>   	if ((rc = cxl_register_afu(afu)))
> -		goto err_put1;
> +		goto err_put_dev;
>   
>   	if ((rc = cxl_sysfs_afu_add(afu)))
> -		goto err_put1;
> +		goto err_del_dev;
>   
>   	adapter->afu[afu->slice] = afu;
>   
> @@ -1176,10 +1176,12 @@ static int pci_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
>   
>   	return 0;
>   
> -err_put1:
> +err_del_dev:
> +	device_del(&afu->dev);
> +err_put_dev:
>   	pci_deconfigure_afu(afu);
>   	cxl_debugfs_afu_remove(afu);
> -	device_unregister(&afu->dev);
> +	put_device(&afu->dev);
>   	return rc;
>   
>   err_free_native:
> @@ -1667,23 +1669,25 @@ static struct cxl *cxl_pci_init_adapter(struct pci_dev *dev)
>   	 * even if it returns an error!
>   	 */
>   	if ((rc = cxl_register_adapter(adapter)))
> -		goto err_put1;
> +		goto err_put_dev;
>   
>   	if ((rc = cxl_sysfs_adapter_add(adapter)))
> -		goto err_put1;
> +		goto err_del_dev;
>   
>   	/* Release the context lock as adapter is configured */
>   	cxl_adapter_context_unlock(adapter);
>   
>   	return adapter;
>   
> -err_put1:
> +err_del_dev:
> +	device_del(&adapter->dev);
> +err_put_dev:
>   	/* This should mirror cxl_remove_adapter, except without the
>   	 * sysfs parts
>   	 */
>   	cxl_debugfs_adapter_remove(adapter);
>   	cxl_deconfigure_adapter(adapter);
> -	device_unregister(&adapter->dev);
> +	put_device(&adapter->dev);
>   	return ERR_PTR(rc);
>   
>   err_release:

On Fri, 2022-11-11 at 22:54 +0800, Yang Yingliang wrote:
> If device_register() fails in cxl_pci_afu|adapter(), the device
> is not added, device_unregister() can not be called in the error
> path, otherwise it will cause a null-ptr-deref because of removing
> not added device.
> 
> As comment of device_register() says, it should use put_device() to
> give
> up the reference in the error path. So split device_unregister() into
> device_del() and put_device(), then goes to put dev when register
> fails.
> 
> Fixes: f204e0b8cedd ("cxl: Driver code for powernv PCIe based cards
> for userspace access")
> Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>

See reply to patch #1.

This patch puts a few things between the device_del() call and the
put_device() call, but that looks fine - we don't touch afu->dev in the
middle.

Thanks for the fix!

Acked-by: Andrew Donnellan <ajd@linux.ibm.com>

> ---
>  drivers/misc/cxl/pci.c | 20 ++++++++++++--------
>  1 file changed, 12 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
> index 3de0aea62ade..6d495d641c95 100644
> --- a/drivers/misc/cxl/pci.c
> +++ b/drivers/misc/cxl/pci.c
> @@ -1164,10 +1164,10 @@ static int pci_init_afu(struct cxl *adapter,
> int slice, struct pci_dev *dev)
>          * if it returns an error!
>          */
>         if ((rc = cxl_register_afu(afu)))
> -               goto err_put1;
> +               goto err_put_dev;
>  
>         if ((rc = cxl_sysfs_afu_add(afu)))
> -               goto err_put1;
> +               goto err_del_dev;
>  
>         adapter->afu[afu->slice] = afu;
>  
> @@ -1176,10 +1176,12 @@ static int pci_init_afu(struct cxl *adapter,
> int slice, struct pci_dev *dev)
>  
>         return 0;
>  
> -err_put1:
> +err_del_dev:
> +       device_del(&afu->dev);
> +err_put_dev:
>         pci_deconfigure_afu(afu);
>         cxl_debugfs_afu_remove(afu);
> -       device_unregister(&afu->dev);
> +       put_device(&afu->dev);
>         return rc;
>  
>  err_free_native:
> @@ -1667,23 +1669,25 @@ static struct cxl
> *cxl_pci_init_adapter(struct pci_dev *dev)
>          * even if it returns an error!
>          */
>         if ((rc = cxl_register_adapter(adapter)))
> -               goto err_put1;
> +               goto err_put_dev;
>  
>         if ((rc = cxl_sysfs_adapter_add(adapter)))
> -               goto err_put1;
> +               goto err_del_dev;
>  
>         /* Release the context lock as adapter is configured */
>         cxl_adapter_context_unlock(adapter);
>  
>         return adapter;
>  
> -err_put1:
> +err_del_dev:
> +       device_del(&adapter->dev);
> +err_put_dev:
>         /* This should mirror cxl_remove_adapter, except without the
>          * sysfs parts
>          */
>         cxl_debugfs_adapter_remove(adapter);
>         cxl_deconfigure_adapter(adapter);
> -       device_unregister(&adapter->dev);
> +       put_device(&adapter->dev);
>         return ERR_PTR(rc);
>  
>  err_release: