[PATCH v2 1/2] iommu/io-pgtable-arm: Convert to IOMMU API TLB sync

[PATCH v2 1/2] iommu/io-pgtable-arm: Convert to IOMMU API TLB sync

[Robin Murphy]

Now that the core API issues its own post-unmap TLB sync call, push that
operation out from the io-pgtable-arm internals into the users. For now,
we leave the invalidation implicit in the unmap operation, since none of
the current users would benefit much from any change to that.

CC: Magnus Damm <damm+renesas@opensource.se>
CC: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---

v2: Wire up .flush_iotlb_all and cope with uninitialised domains

 drivers/iommu/arm-smmu-v3.c    | 10 ++++++++++
 drivers/iommu/arm-smmu.c       | 20 +++++++++++++++-----
 drivers/iommu/io-pgtable-arm.c |  7 +------
 drivers/iommu/ipmmu-vmsa.c     | 10 ++++++++++
 4 files changed, 36 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index e67ba6c40faf..ee0c7b73cff7 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1743,6 +1743,14 @@ 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_device *smmu = to_smmu_domain(domain)->smmu;
+
+	if (smmu)
+		__arm_smmu_tlb_sync(smmu);
+}
+
 static phys_addr_t
 arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
@@ -1963,6 +1971,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 3bdb799d3b4b..e4a82d70d446 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -250,6 +250,7 @@ enum arm_smmu_domain_stage {
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
+	const struct iommu_gather_ops	*tlb_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	struct mutex			init_mutex; /* Protects smmu pointer */
@@ -735,7 +736,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	enum io_pgtable_fmt fmt;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	const struct iommu_gather_ops *tlb_ops;
 
 	mutex_lock(&smmu_domain->init_mutex);
 	if (smmu_domain->smmu)
@@ -813,7 +813,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			ias = min(ias, 32UL);
 			oas = min(oas, 32UL);
 		}
-		tlb_ops = &arm_smmu_s1_tlb_ops;
+		smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops;
 		break;
 	case ARM_SMMU_DOMAIN_NESTED:
 		/*
@@ -833,9 +833,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			oas = min(oas, 40UL);
 		}
 		if (smmu->version == ARM_SMMU_V2)
-			tlb_ops = &arm_smmu_s2_tlb_ops_v2;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2;
 		else
-			tlb_ops = &arm_smmu_s2_tlb_ops_v1;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1;
 		break;
 	default:
 		ret = -EINVAL;
@@ -863,7 +863,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
 		.oas		= oas,
-		.tlb		= tlb_ops,
+		.tlb		= smmu_domain->tlb_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
@@ -1259,6 +1259,14 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	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);
+
+	if (smmu_domain->tlb_ops)
+		smmu_domain->tlb_ops->tlb_sync(smmu_domain);
+}
+
 static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 					      dma_addr_t iova)
 {
@@ -1562,6 +1570,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index e8018a308868..51e5c43caed1 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -609,7 +609,6 @@ 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 +616,7 @@ 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 unmapped;
+	return __arm_lpae_unmap(data, iova, size, lvl, ptep);
 }
 
 static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 195d6e93ac71..af8140054273 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -619,6 +619,14 @@ static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
 	return domain->iop->unmap(domain->iop, iova, size);
 }
 
+static void ipmmu_iotlb_sync(struct iommu_domain *io_domain)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	if (domain->mmu)
+		ipmmu_tlb_flush_all(domain);
+}
+
 static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
 				      dma_addr_t iova)
 {
@@ -876,6 +884,8 @@ static const struct iommu_ops ipmmu_ops = {
 	.detach_dev = ipmmu_detach_device,
 	.map = ipmmu_map,
 	.unmap = ipmmu_unmap,
+	.flush_iotlb_all = ipmmu_iotlb_sync,
+	.iotlb_sync = ipmmu_iotlb_sync,
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = ipmmu_iova_to_phys,
 	.add_device = ipmmu_add_device_dma,
-- 
2.13.4.dirty

[PATCH v2 2/2] iommu/io-pgtable-arm-v7s: Convert to IOMMU API TLB sync

[Robin Murphy]

Now that the core API issues its own post-unmap TLB sync call, push that
operation out from the io-pgtable-arm-v7s internals into the users. For
now, we leave the invalidation implicit in the unmap operation, since
none of the current users would benefit much from any change to that.

Note that the conversion of msm_iommu is implicit, since that apparently
has no specific TLB sync operation anyway.

CC: Yong Wu <yong.wu@mediatek.com>
CC: Rob Clark <robdclark@gmail.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---

v2: Wire up .flush_iotlb_all and cope with uninitialised domains

 drivers/iommu/io-pgtable-arm-v7s.c |  7 +------
 drivers/iommu/mtk_iommu.c          |  7 +++++++
 drivers/iommu/qcom_iommu.c         | 15 +++++++++++++++
 3 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index d665d0dc16e8..397531da8d9c 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -660,16 +660,11 @@ static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			 size_t size)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
-	size_t unmapped;
 
 	if (WARN_ON(upper_32_bits(iova)))
 		return 0;
 
-	unmapped = __arm_v7s_unmap(data, iova, size, 1, data->pgd);
-	if (unmapped)
-		io_pgtable_tlb_sync(&data->iop);
-
-	return unmapped;
+	return __arm_v7s_unmap(data, iova, size, 1, data->pgd);
 }
 
 static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index bd515be5b380..d0c8dfbbd74d 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -391,6 +391,11 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 	return unmapsz;
 }
 
+static void mtk_iommu_iotlb_sync(struct iommu_domain *domain)
+{
+	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+}
+
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t iova)
 {
@@ -490,6 +495,8 @@ static struct iommu_ops mtk_iommu_ops = {
 	.map		= mtk_iommu_map,
 	.unmap		= mtk_iommu_unmap,
 	.map_sg		= default_iommu_map_sg,
+	.flush_iotlb_all = mtk_iommu_iotlb_sync,
+	.iotlb_sync	= mtk_iommu_iotlb_sync,
 	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.add_device	= mtk_iommu_add_device,
 	.remove_device	= mtk_iommu_remove_device,
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c8a587d034b0..4a2c4378b3db 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -443,6 +443,19 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
+static void qcom_iommu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops,
+						  struct io_pgtable, ops);
+	if (!qcom_domain->pgtbl_ops)
+		return;
+
+	pm_runtime_get_sync(qcom_domain->iommu->dev);
+	qcom_iommu_tlb_sync(pgtable->cookie);
+	pm_runtime_put_sync(qcom_domain->iommu->dev);
+}
+
 static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
@@ -570,6 +583,8 @@ static const struct iommu_ops qcom_iommu_ops = {
 	.map		= qcom_iommu_map,
 	.unmap		= qcom_iommu_unmap,
 	.map_sg		= default_iommu_map_sg,
+	.flush_iotlb_all = qcom_iommu_iotlb_sync,
+	.iotlb_sync	= qcom_iommu_iotlb_sync,
 	.iova_to_phys	= qcom_iommu_iova_to_phys,
 	.add_device	= qcom_iommu_add_device,
 	.remove_device	= qcom_iommu_remove_device,
-- 
2.13.4.dirty

[PATCH v2 1/2] iommu/io-pgtable-arm: Convert to IOMMU API TLB sync

[Joerg Roedel]

On Thu, Sep 28, 2017 at 03:55:01PM +0100, Robin Murphy wrote:
> Now that the core API issues its own post-unmap TLB sync call, push that
> operation out from the io-pgtable-arm internals into the users. For now,
> we leave the invalidation implicit in the unmap operation, since none of
> the current users would benefit much from any change to that.
> 
> CC: Magnus Damm <damm+renesas@opensource.se>
> CC: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>


Applied both, thanks.