Since it's not currently safe to take device_lock() in the IOMMU probe
path, that can race against really_probe() setting dev->driver before
attempting to bind. The race itself isn't so bad, since we're only
concerned with dereferencing dev->driver itself anyway, but sadly my
attempt to implement the check with minimal churn leads to a kind of
TOCTOU issue, where dev->driver becomes valid after to_cdx_driver(NULL)
is already computed, and thus the check fails to work as intended.

Will and I both hit this with the platform bus, but the pattern here is
the same, so fix it for correctness too.

Reported-by: Will McVicker <willmcvicker@google.com>
Fixes: bcb81ac6ae3c ("iommu: Get DT/ACPI parsing into the proper probe path")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
 drivers/cdx/cdx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 092306ca2541..8aa92a198b71 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -348,7 +348,7 @@ static void cdx_shutdown(struct device *dev)
 
 static int cdx_dma_configure(struct device *dev)
 {
-	struct cdx_driver *cdx_drv = to_cdx_driver(dev->driver);
+	const struct device_driver *drv = READ_ONCE(dev->driver);
 	struct cdx_device *cdx_dev = to_cdx_device(dev);
 	struct cdx_controller *cdx = cdx_dev->cdx;
 	u32 input_id = cdx_dev->req_id;
@@ -360,8 +360,8 @@ static int cdx_dma_configure(struct device *dev)
 		return ret;
 	}
 
-	/* @cdx_drv may not be valid when we're called from the IOMMU layer */
-	if (!ret && dev->driver && !cdx_drv->driver_managed_dma) {
+	/* @drv may not be valid when we're called from the IOMMU layer */
+	if (!ret && drv && !to_cdx_driver(drv)->driver_managed_dma) {
 		ret = iommu_device_use_default_domain(dev);
 		if (ret)
 			arch_teardown_dma_ops(dev);
-- 
2.39.2.101.g768bb238c484.dirty

On 04/25/2025, Robin Murphy wrote:
> Since it's not currently safe to take device_lock() in the IOMMU probe
> path, that can race against really_probe() setting dev->driver before
> attempting to bind. The race itself isn't so bad, since we're only
> concerned with dereferencing dev->driver itself anyway, but sadly my
> attempt to implement the check with minimal churn leads to a kind of
> TOCTOU issue, where dev->driver becomes valid after to_cdx_driver(NULL)
> is already computed, and thus the check fails to work as intended.
> 
> Will and I both hit this with the platform bus, but the pattern here is
> the same, so fix it for correctness too.

Thanks!

Reviewed-by: Will McVicker <willmcvicker@google.com>

> 
> Reported-by: Will McVicker <willmcvicker@google.com>
> Fixes: bcb81ac6ae3c ("iommu: Get DT/ACPI parsing into the proper probe path")
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>
> ---
>  drivers/cdx/cdx.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
> index 092306ca2541..8aa92a198b71 100644
> --- a/drivers/cdx/cdx.c
> +++ b/drivers/cdx/cdx.c
> @@ -348,7 +348,7 @@ static void cdx_shutdown(struct device *dev)
>  
>  static int cdx_dma_configure(struct device *dev)
>  {
> -	struct cdx_driver *cdx_drv = to_cdx_driver(dev->driver);
> +	const struct device_driver *drv = READ_ONCE(dev->driver);
>  	struct cdx_device *cdx_dev = to_cdx_device(dev);
>  	struct cdx_controller *cdx = cdx_dev->cdx;
>  	u32 input_id = cdx_dev->req_id;
> @@ -360,8 +360,8 @@ static int cdx_dma_configure(struct device *dev)
>  		return ret;
>  	}
>  
> -	/* @cdx_drv may not be valid when we're called from the IOMMU layer */
> -	if (!ret && dev->driver && !cdx_drv->driver_managed_dma) {
> +	/* @drv may not be valid when we're called from the IOMMU layer */
> +	if (!ret && drv && !to_cdx_driver(drv)->driver_managed_dma) {
>  		ret = iommu_device_use_default_domain(dev);
>  		if (ret)
>  			arch_teardown_dma_ops(dev);
> -- 
> 2.39.2.101.g768bb238c484.dirty
>