[PATCH v1 16/16] iommu/arm-smmu-v3: Allow ATS for IOMMU_DOMAIN_NESTED

[Nicolin Chen]

From: Jason Gunthorpe <jgg at nvidia.com>

Now, ATC invalidation can be done with the VIOMMU invalidation op. A guest
owned IOMMU_DOMAIN_NESTED can do an ATS too. Allow it to pass in the EATS
field via the vSTE words.

Signed-off-by: Jason Gunthorpe <jgg at nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc at nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 15 ++++++++++++---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  1 +
 2 files changed, 13 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 be4f849f1a48..ce84f0c04022 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3189,8 +3189,6 @@ static int arm_smmu_attach_dev_nested(struct iommu_domain *domain,
 		.master = master,
 		.old_domain = iommu_get_domain_for_dev(dev),
 		.ssid = IOMMU_NO_PASID,
-		/* Currently invalidation of ATC is not supported */
-		.disable_ats = true,
 	};
 	struct arm_smmu_ste ste;
 	int ret;
@@ -3200,6 +3198,15 @@ static int arm_smmu_attach_dev_nested(struct iommu_domain *domain,
 		return -EINVAL;
 
 	mutex_lock(&arm_smmu_asid_lock);
+	/*
+	 * The VM has to control the actual ATS state at the PCI device because
+	 * we forward the invalidations directly from the VM. If the VM doesn't
+	 * think ATS is on it will not generate ATC flushes and the ATC will
+	 * become incoherent. Since we can't access the actual virtual PCI ATS
+	 * config bit here base this off the EATS value in the STE. If the EATS
+	 * is set then the VM must generate ATC flushes.
+	 */
+	state.disable_ats = !nested_domain->enable_ats;
 	ret = arm_smmu_attach_prepare(&state, domain);
 	if (ret) {
 		mutex_unlock(&arm_smmu_asid_lock);
@@ -3420,8 +3427,9 @@ arm_smmu_domain_alloc_nesting(struct device *dev, u32 flags,
 	    cfg != STRTAB_STE_0_CFG_S1_TRANS)
 		return ERR_PTR(-EIO);
 
+	/* Only Full ATS or ATS UR is supported */
 	eats = FIELD_GET(STRTAB_STE_1_EATS, le64_to_cpu(arg.ste[1]));
-	if (eats != STRTAB_STE_1_EATS_ABT)
+	if (eats != STRTAB_STE_1_EATS_ABT && eats != STRTAB_STE_1_EATS_TRANS)
 		return ERR_PTR(-EIO);
 
 	if (cfg != STRTAB_STE_0_CFG_S1_TRANS)
@@ -3434,6 +3442,7 @@ arm_smmu_domain_alloc_nesting(struct device *dev, u32 flags,
 	nested_domain->domain.type = IOMMU_DOMAIN_NESTED;
 	nested_domain->domain.ops = &arm_smmu_nested_ops;
 	nested_domain->s2_parent = smmu_parent;
+	nested_domain->enable_ats = eats == STRTAB_STE_1_EATS_TRANS;
 	nested_domain->ste[0] = arg.ste[0];
 	nested_domain->ste[1] = arg.ste[1] & ~cpu_to_le64(STRTAB_STE_1_EATS);
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index a3fb08e0a195..65f90b00e16d 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -811,6 +811,7 @@ struct arm_smmu_domain {
 struct arm_smmu_nested_domain {
 	struct iommu_domain domain;
 	struct arm_smmu_domain *s2_parent;
+	u8 enable_ats : 1;
 
 	__le64 ste[2];
 };
-- 
2.43.0