[v3,4/6] iommu/qcom: Index contexts by asid number to allow asid 0

Message ID 20221115101122.155440-5-angelogioacchino.delregno@collabora.com
State New
Headers
Series Add support for Qualcomm's legacy IOMMU v2 |

Commit Message

AngeloGioacchino Del Regno Nov. 15, 2022, 10:11 a.m. UTC
  This driver was indexing the contexts by asid-1, which is probably
done under the assumption that the first ASID is always 1.

Unfortunately this is not always true: at least for MSM8956 and
MSM8976's GPU IOMMU, the gpu_user context's ASID number is zero.
To allow using a zero asid number, index the contexts by `asid`
instead of by `asid - 1`.

Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
[Marijn: Rebased over next-20221111]
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 drivers/iommu/arm/arm-smmu/qcom_iommu.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)
  

Comments

Dmitry Baryshkov March 7, 2023, 4:53 p.m. UTC | #1
On 15/11/2022 12:11, AngeloGioacchino Del Regno wrote:
> This driver was indexing the contexts by asid-1, which is probably
> done under the assumption that the first ASID is always 1.
> 
> Unfortunately this is not always true: at least for MSM8956 and
> MSM8976's GPU IOMMU, the gpu_user context's ASID number is zero.
> To allow using a zero asid number, index the contexts by `asid`
> instead of by `asid - 1`.
> 
> Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
> [Marijn: Rebased over next-20221111]
> Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
> ---
>   drivers/iommu/arm/arm-smmu/qcom_iommu.c | 24 ++++++++++++------------
>   1 file changed, 12 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
> index 49f4308f1bd2..94f51cafee17 100644
> --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
> +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
> @@ -52,7 +52,7 @@ struct qcom_iommu_dev {
>   	void __iomem		*local_base;
>   	u32			 sec_id;
>   	u8			 num_ctxs;
> -	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid-1 */
> +	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid */
>   };
>   
>   struct qcom_iommu_ctx {
> @@ -94,7 +94,7 @@ static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid
>   	struct qcom_iommu_dev *qcom_iommu = d->iommu;
>   	if (!qcom_iommu)
>   		return NULL;
> -	return qcom_iommu->ctxs[asid - 1];
> +	return qcom_iommu->ctxs[asid];
>   }
>   
>   static inline void
> @@ -563,12 +563,10 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
>   	qcom_iommu = platform_get_drvdata(iommu_pdev);
>   
>   	/* make sure the asid specified in dt is valid, so we don't have
> -	 * to sanity check this elsewhere, since 'asid - 1' is used to
> -	 * index into qcom_iommu->ctxs:
> +	 * to sanity check this elsewhere:
>   	 */
> -	if (WARN_ON(asid < 1) ||
> -	    WARN_ON(asid > qcom_iommu->num_ctxs) ||
> -	    WARN_ON(qcom_iommu->ctxs[asid - 1] == NULL)) {
> +	if (WARN_ON(asid >= qcom_iommu->num_ctxs) ||

Could you please change qcom_iommu to store max_asid rather than 
num_ctxs. This piece becomes logical then.

Looks good to me otherwise.

> +	    WARN_ON(qcom_iommu->ctxs[asid] == NULL)) {
>   		put_device(&iommu_pdev->dev);
>   		return -EINVAL;
>   	}
> @@ -726,7 +724,7 @@ static int qcom_iommu_ctx_probe(struct platform_device *pdev)
>   
>   	dev_dbg(dev, "found asid %u\n", ctx->asid);
>   
> -	qcom_iommu->ctxs[ctx->asid - 1] = ctx;
> +	qcom_iommu->ctxs[ctx->asid] = ctx;
>   
>   	return 0;
>   }
> @@ -738,7 +736,7 @@ static int qcom_iommu_ctx_remove(struct platform_device *pdev)
>   
>   	platform_set_drvdata(pdev, NULL);
>   
> -	qcom_iommu->ctxs[ctx->asid - 1] = NULL;
> +	qcom_iommu->ctxs[ctx->asid] = NULL;
>   
>   	return 0;
>   }
> @@ -779,7 +777,7 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
>   	struct device *dev = &pdev->dev;
>   	struct resource *res;
>   	struct clk *clk;
> -	int ret, max_asid = 0;
> +	int ret, num_ctxs, max_asid = 0;
>   
>   	/* find the max asid (which is 1:1 to ctx bank idx), so we know how
>   	 * many child ctx devices we have:
> @@ -787,11 +785,13 @@ static int qcom_iommu_device_probe(struct platform_device *pdev)
>   	for_each_child_of_node(dev->of_node, child)
>   		max_asid = max(max_asid, get_asid(child));
>   
> -	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid),
> +	num_ctxs = max_asid + 1;
> +
> +	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, num_ctxs),
>   				  GFP_KERNEL);
>   	if (!qcom_iommu)
>   		return -ENOMEM;
> -	qcom_iommu->num_ctxs = max_asid;
> +	qcom_iommu->num_ctxs = num_ctxs;
>   	qcom_iommu->dev = dev;
>   
>   	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
  

Patch

diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 49f4308f1bd2..94f51cafee17 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -52,7 +52,7 @@  struct qcom_iommu_dev {
 	void __iomem		*local_base;
 	u32			 sec_id;
 	u8			 num_ctxs;
-	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid-1 */
+	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid */
 };
 
 struct qcom_iommu_ctx {
@@ -94,7 +94,7 @@  static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid
 	struct qcom_iommu_dev *qcom_iommu = d->iommu;
 	if (!qcom_iommu)
 		return NULL;
-	return qcom_iommu->ctxs[asid - 1];
+	return qcom_iommu->ctxs[asid];
 }
 
 static inline void
@@ -563,12 +563,10 @@  static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	qcom_iommu = platform_get_drvdata(iommu_pdev);
 
 	/* make sure the asid specified in dt is valid, so we don't have
-	 * to sanity check this elsewhere, since 'asid - 1' is used to
-	 * index into qcom_iommu->ctxs:
+	 * to sanity check this elsewhere:
 	 */
-	if (WARN_ON(asid < 1) ||
-	    WARN_ON(asid > qcom_iommu->num_ctxs) ||
-	    WARN_ON(qcom_iommu->ctxs[asid - 1] == NULL)) {
+	if (WARN_ON(asid >= qcom_iommu->num_ctxs) ||
+	    WARN_ON(qcom_iommu->ctxs[asid] == NULL)) {
 		put_device(&iommu_pdev->dev);
 		return -EINVAL;
 	}
@@ -726,7 +724,7 @@  static int qcom_iommu_ctx_probe(struct platform_device *pdev)
 
 	dev_dbg(dev, "found asid %u\n", ctx->asid);
 
-	qcom_iommu->ctxs[ctx->asid - 1] = ctx;
+	qcom_iommu->ctxs[ctx->asid] = ctx;
 
 	return 0;
 }
@@ -738,7 +736,7 @@  static int qcom_iommu_ctx_remove(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, NULL);
 
-	qcom_iommu->ctxs[ctx->asid - 1] = NULL;
+	qcom_iommu->ctxs[ctx->asid] = NULL;
 
 	return 0;
 }
@@ -779,7 +777,7 @@  static int qcom_iommu_device_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct clk *clk;
-	int ret, max_asid = 0;
+	int ret, num_ctxs, max_asid = 0;
 
 	/* find the max asid (which is 1:1 to ctx bank idx), so we know how
 	 * many child ctx devices we have:
@@ -787,11 +785,13 @@  static int qcom_iommu_device_probe(struct platform_device *pdev)
 	for_each_child_of_node(dev->of_node, child)
 		max_asid = max(max_asid, get_asid(child));
 
-	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid),
+	num_ctxs = max_asid + 1;
+
+	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, num_ctxs),
 				  GFP_KERNEL);
 	if (!qcom_iommu)
 		return -ENOMEM;
-	qcom_iommu->num_ctxs = max_asid;
+	qcom_iommu->num_ctxs = num_ctxs;
 	qcom_iommu->dev = dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);