[PATCH v2 1/1] iommu/arm-smmu-v3: Fix error case of range command

[Will Deacon]

On Fri, Aug 04, 2023 at 05:31:20PM +0800, zhurui wrote:
> When tg != 0 but ttl, scale, num all 0 in a range tlbi command, it
> is reserved and will cause the CERROR_ILL error. This case means
> that the size to be invalidated is only one page size, and the
> range invalidation is meaningless here. So we set tg to 0 in this
> case to do an non-range invalidation instead.
> 
> Cc: Will Deacon <will at kernel.org>
> Cc: Robin Murphy <robin.murphy at arm.com>
> Cc: Joerg Roedel <joro at 8bytes.org>
> Cc: Lu Baolu <baolu.lu at linux.intel.com>
> Cc: Jason Gunthorpe <jgg at ziepe.ca>
> Cc: Yicong Yang <yangyicong at hisilicon.com>
> Cc: Tomas Krcka <krckatom at amazon.de>
> Cc: Jean-Philippe Brucker <jean-philippe at linaro.org>
> Cc: Nicolin Chen <nicolinc at nvidia.com>
> Cc: Rui Zhu <zhurui3 at huawei.com>
> 
> Signed-off-by: Rui Zhu <zhurui3 at huawei.com>
> ---
> ChangeLog:
> v1-->v2:
> 	1. Change from "Revert" to modify the problematic case
> 
>  drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 9 ++++++---
>  1 file changed, 6 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> index 9b0dc3505601..5e56c7e85819 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -1895,9 +1895,6 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
>                 /* Get the leaf page size */
>                 tg = __ffs(smmu_domain->domain.pgsize_bitmap);
> 
> -               /* Convert page size of 12,14,16 (log2) to 1,2,3 */
> -               cmd->tlbi.tg = (tg - 10) / 2;
> -
>                 /*
>                  * Determine what level the granule is at. For non-leaf, io-pgtable
>                  * assumes .tlb_flush_walk can invalidate multiple levels at once,
> @@ -1930,6 +1927,12 @@ static void __arm_smmu_tlb_inv_range(struct arm_smmu_cmdq_ent *cmd,
>                         num = (num_pages >> scale) & CMDQ_TLBI_RANGE_NUM_MAX;
>                         cmd->tlbi.num = num - 1;
> 
> +                       /* Prevent error caused by one page tlbi with leaf 0 */
> +                       if (scale == 0 && num == 1 && cmd->tlbi.leaf == 0)
> +                               cmd->tlbi.tg = 0;

This should only be true for the last iteration, right (i.e. when num_pages
== 1)? In which case, I'd prefer to leave the old code as-is and just add:

	/* Single-page leaf invalidation requires a TG field of 0 */
	if (num_pages == 1 && !cmd->tlbi.leaf)
		cmd->tlbi.tg = 0;

here.

Will