[PATCH v2 2/3] iommu/arm-smmu-v3: add support for unmap an iova range with only one tlb sync

[Will Deacon]

On Tue, Sep 12, 2017 at 09:00:37PM +0800, Zhen Lei wrote:
> This patch is base on: 
> (add02cfdc9bc2 "iommu: Introduce Interface for IOMMU TLB Flushing")
> 
> Because iotlb_sync is moved out of ".unmap = arm_smmu_unmap", some interval
> ".unmap" calls should explicitly followed by a iotlb_sync operation.
> 
> Signed-off-by: Zhen Lei <thunder.leizhen at huawei.com>
> ---
>  drivers/iommu/arm-smmu-v3.c    | 10 ++++++++++
>  drivers/iommu/io-pgtable-arm.c | 30 ++++++++++++++++++++----------
>  drivers/iommu/io-pgtable.h     |  1 +
>  3 files changed, 31 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
> index ef42c4b..e92828e 100644
> --- a/drivers/iommu/arm-smmu-v3.c
> +++ b/drivers/iommu/arm-smmu-v3.c
> @@ -1772,6 +1772,15 @@ arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
>  	return ops->unmap(ops, iova, size);
>  }
>  
> +static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
> +{
> +	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
> +	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
> +
> +	if (ops && ops->iotlb_sync)
> +		ops->iotlb_sync(ops);
> +}
> +
>  static phys_addr_t
>  arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
>  {
> @@ -1991,6 +2000,7 @@ static struct iommu_ops arm_smmu_ops = {
>  	.attach_dev		= arm_smmu_attach_dev,
>  	.map			= arm_smmu_map,
>  	.unmap			= arm_smmu_unmap,
> +	.iotlb_sync		= arm_smmu_iotlb_sync,
>  	.map_sg			= default_iommu_map_sg,
>  	.iova_to_phys		= arm_smmu_iova_to_phys,
>  	.add_device		= arm_smmu_add_device,
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index e8018a3..805efc9 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -304,6 +304,8 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
>  		WARN_ON(!selftest_running);
>  		return -EEXIST;
>  	} else if (iopte_type(pte, lvl) == ARM_LPAE_PTE_TYPE_TABLE) {
> +		size_t unmapped;
> +
>  		/*
>  		 * We need to unmap and free the old table before
>  		 * overwriting it with a block entry.
> @@ -312,7 +314,9 @@ static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
>  		size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
>  
>  		tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
> -		if (WARN_ON(__arm_lpae_unmap(data, iova, sz, lvl, tblp) != sz))
> +		unmapped = __arm_lpae_unmap(data, iova, sz, lvl, tblp);
> +		io_pgtable_tlb_sync(&data->iop);
> +		if (WARN_ON(unmapped != sz))
>  			return -EINVAL;
>  	}
>  
> @@ -584,7 +588,6 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
>  			/* Also flush any partial walks */
>  			io_pgtable_tlb_add_flush(iop, iova, size,
>  						ARM_LPAE_GRANULE(data), false);
> -			io_pgtable_tlb_sync(iop);
>  			ptep = iopte_deref(pte, data);
>  			__arm_lpae_free_pgtable(data, lvl + 1, ptep);
>  		} else {
> @@ -609,7 +612,6 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
>  static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
>  			  size_t size)
>  {
> -	size_t unmapped;
>  	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
>  	arm_lpae_iopte *ptep = data->pgd;
>  	int lvl = ARM_LPAE_START_LVL(data);
> @@ -617,11 +619,14 @@ static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
>  	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
>  		return 0;
>  
> -	unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep);
> -	if (unmapped)
> -		io_pgtable_tlb_sync(&data->iop);
> +	return __arm_lpae_unmap(data, iova, size, lvl, ptep);
> +}

This change is already queued in Joerg's tree, due to a patch from Robin.

Will