iommu/arm-smmu: Convert to a global static identity domain

Create a global static identity domain with it's own
arm_smmu_attach_dev_identity() that simply calls
arm_smmu_master_install_s2crs() with the identity parameters.

This is done by giving the attach path for identity its own unique
implementation that simply calls arm_smmu_master_install_s2crs().

Remove ARM_SMMU_DOMAIN_BYPASS and all checks of IOMMU_DOMAIN_IDENTITY.
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/2-v2-c86cc8c2230e+160bb-smmu_newapi_jgg@nvidia.com
[will: Move duplicated autosuspend logic into a helper function]
Signed-off-by: Will Deacon <will@kernel.org>

drivers/iommu/arm/arm-smmu/arm-smmu.c

@@ -82,6 +82,23 @@ static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 		pm_runtime_put_autosuspend(smmu->dev);
 }
 
+static void arm_smmu_rpm_use_autosuspend(struct arm_smmu_device *smmu)
+{
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+}
+
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
@@ -624,12 +641,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
-		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
-		smmu_domain->smmu = smmu;
-		goto out_unlock;
-	}
-
 	/*
 	 * Mapping the requested stage onto what we support is surprisingly
 	 * complicated, mainly because the spec allows S1+S2 SMMUs without
@@ -825,7 +836,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	int ret, irq;
 
-	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
+	if (!smmu)
 		return;
 
 	ret = arm_smmu_rpm_get(smmu);
@@ -854,7 +865,7 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
+	if (type != IOMMU_DOMAIN_UNMANAGED) {
 		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
 			return NULL;
 	}
@@ -1145,32 +1156,45 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	arm_smmu_master_install_s2crs(cfg,
-				      smmu_domain->stage ==
-						      ARM_SMMU_DOMAIN_BYPASS ?
-					      S2CR_TYPE_BYPASS :
-					      S2CR_TYPE_TRANS,
+	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_TRANS,
 				      smmu_domain->cfg.cbndx, fwspec);
-
-	/*
-	 * Setup an autosuspend delay to avoid bouncing runpm state.
-	 * Otherwise, if a driver for a suspended consumer device
-	 * unmaps buffers, it will runpm resume/suspend for each one.
-	 *
-	 * For example, when used by a GPU device, when an application
-	 * or game exits, it can trigger unmapping 100s or 1000s of
-	 * buffers.  With a runpm cycle for each buffer, that adds up
-	 * to 5-10sec worth of reprogramming the context bank, while
-	 * the system appears to be locked up to the user.
-	 */
-	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
-	pm_runtime_use_autosuspend(smmu->dev);
-
+	arm_smmu_rpm_use_autosuspend(smmu);
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
 }
 
+static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
+					struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_device *smmu;
+	int ret;
+
+	if (!cfg)
+		return -ENODEV;
+	smmu = cfg->smmu;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return ret;
+
+	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_BYPASS, 0, fwspec);
+	arm_smmu_rpm_use_autosuspend(smmu);
+	arm_smmu_rpm_put(smmu);
+	return 0;
+}
+
+static const struct iommu_domain_ops arm_smmu_identity_ops = {
+	.attach_dev = arm_smmu_attach_dev_identity,
+};
+
+static struct iommu_domain arm_smmu_identity_domain = {
+	.type = IOMMU_DOMAIN_IDENTITY,
+	.ops = &arm_smmu_identity_ops,
+};
+
 static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
 			      int prot, gfp_t gfp, size_t *mapped)
@@ -1557,6 +1581,7 @@ static int arm_smmu_def_domain_type(struct device *dev)
 }
 
 static struct iommu_ops arm_smmu_ops = {
+	.identity_domain	= &arm_smmu_identity_domain,
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
 	.probe_device		= arm_smmu_probe_device,

drivers/iommu/arm/arm-smmu/arm-smmu.h

@@ -361,7 +361,6 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
 	ARM_SMMU_DOMAIN_NESTED,
-	ARM_SMMU_DOMAIN_BYPASS,
 };
 
 struct arm_smmu_domain {