4 files changed, 68 insertions, 42 deletions

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 9b9d13ec5a88..55690af1b25d 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -193,6 +193,8 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain,
 {
 	struct adreno_smmu_priv *priv;
 
+	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;
+
 	/* Only enable split pagetables for the GPU device (SID 0) */
 	if (!qcom_adreno_smmu_is_gpu_device(dev))
 		return 0;
@@ -235,6 +237,14 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ }
 };
 
+static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
+{
+	smmu_domain->cfg.flush_walk_prefer_tlbiasid = true;
+
+	return 0;
+}
+
 static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
 {
 	unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1);
@@ -358,6 +368,7 @@ static int qcom_smmu500_reset(struct arm_smmu_device *smmu)
 }
 
 static const struct arm_smmu_impl qcom_smmu_impl = {
+	.init_context = qcom_smmu_init_context,
 	.cfg_probe = qcom_smmu_cfg_probe,
 	.def_domain_type = qcom_smmu_def_domain_type,
 	.reset = qcom_smmu500_reset,
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index f22dbeb1e510..4bc75c4ce402 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -327,9 +327,16 @@ static void arm_smmu_tlb_inv_range_s2(unsigned long iova, size_t size,
 static void arm_smmu_tlb_inv_walk_s1(unsigned long iova, size_t size,
 				     size_t granule, void *cookie)
 {
-	arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
-				  ARM_SMMU_CB_S1_TLBIVA);
-	arm_smmu_tlb_sync_context(cookie);
+	struct arm_smmu_domain *smmu_domain = cookie;
+	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+
+	if (cfg->flush_walk_prefer_tlbiasid) {
+		arm_smmu_tlb_inv_context_s1(cookie);
+	} else {
+		arm_smmu_tlb_inv_range_s1(iova, size, granule, cookie,
+					  ARM_SMMU_CB_S1_TLBIVA);
+		arm_smmu_tlb_sync_context(cookie);
+	}
 }
 
 static void arm_smmu_tlb_add_page_s1(struct iommu_iotlb_gather *gather,
@@ -765,9 +772,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.iommu_dev	= smmu->dev,
 	};
 
-	if (!iommu_get_dma_strict(domain))
-		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
-
 	if (smmu->impl && smmu->impl->init_context) {
 		ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg, dev);
 		if (ret)
@@ -868,10 +872,11 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED &&
-	    type != IOMMU_DOMAIN_DMA &&
-	    type != IOMMU_DOMAIN_IDENTITY)
-		return NULL;
+	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
+		if (using_legacy_binding ||
+		    (type != IOMMU_DOMAIN_DMA && type != IOMMU_DOMAIN_DMA_FQ))
+			return NULL;
+	}
 	/*
 	 * Allocate the domain and initialise some of its data structures.
 	 * We can't really do anything meaningful until we've added a
@@ -881,12 +886,6 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 	if (!smmu_domain)
 		return NULL;
 
-	if (type == IOMMU_DOMAIN_DMA && (using_legacy_binding ||
-	    iommu_get_dma_cookie(&smmu_domain->domain))) {
-		kfree(smmu_domain);
-		return NULL;
-	}
-
 	mutex_init(&smmu_domain->init_mutex);
 	spin_lock_init(&smmu_domain->cb_lock);
 
@@ -901,7 +900,6 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	 * Free the domain resources. We assume that all devices have
 	 * already been detached.
 	 */
-	iommu_put_dma_cookie(domain);
 	arm_smmu_destroy_domain_context(domain);
 	kfree(smmu_domain);
 }
@@ -1198,8 +1196,9 @@ rpm_put:
 	return ret;
 }
 
-static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+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)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
@@ -1209,14 +1208,15 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
 		return -ENODEV;
 
 	arm_smmu_rpm_get(smmu);
-	ret = ops->map(ops, iova, paddr, size, prot, gfp);
+	ret = ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot, gfp, mapped);
 	arm_smmu_rpm_put(smmu);
 
 	return ret;
 }
 
-static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
-			     size_t size, struct iommu_iotlb_gather *gather)
+static size_t arm_smmu_unmap_pages(struct iommu_domain *domain, unsigned long iova,
+				   size_t pgsize, size_t pgcount,
+				   struct iommu_iotlb_gather *iotlb_gather)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
@@ -1226,7 +1226,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 		return 0;
 
 	arm_smmu_rpm_get(smmu);
-	ret = ops->unmap(ops, iova, size, gather);
+	ret = ops->unmap_pages(ops, iova, pgsize, pgcount, iotlb_gather);
 	arm_smmu_rpm_put(smmu);
 
 	return ret;
@@ -1320,9 +1320,6 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
 
-	if (domain->type == IOMMU_DOMAIN_IDENTITY)
-		return iova;
-
 	if (!ops)
 		return 0;
 
@@ -1478,16 +1475,21 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	struct iommu_group *group = NULL;
 	int i, idx;
 
+	mutex_lock(&smmu->stream_map_mutex);
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (group && smmu->s2crs[idx].group &&
-		    group != smmu->s2crs[idx].group)
+		    group != smmu->s2crs[idx].group) {
+			mutex_unlock(&smmu->stream_map_mutex);
 			return ERR_PTR(-EINVAL);
+		}
 
 		group = smmu->s2crs[idx].group;
 	}
 
-	if (group)
+	if (group) {
+		mutex_unlock(&smmu->stream_map_mutex);
 		return iommu_group_ref_get(group);
+	}
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
@@ -1501,6 +1503,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 		for_each_cfg_sme(cfg, fwspec, i, idx)
 			smmu->s2crs[idx].group = group;
 
+	mutex_unlock(&smmu->stream_map_mutex);
 	return group;
 }
 
@@ -1582,8 +1585,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.domain_alloc		= arm_smmu_domain_alloc,
 	.domain_free		= arm_smmu_domain_free,
 	.attach_dev		= arm_smmu_attach_dev,
-	.map			= arm_smmu_map,
-	.unmap			= arm_smmu_unmap,
+	.map_pages		= arm_smmu_map_pages,
+	.unmap_pages		= arm_smmu_unmap_pages,
 	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
 	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
@@ -2281,18 +2284,38 @@ static int __maybe_unused arm_smmu_runtime_suspend(struct device *dev)
 
 static int __maybe_unused arm_smmu_pm_resume(struct device *dev)
 {
+	int ret;
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
+	ret = clk_bulk_prepare(smmu->num_clks, smmu->clks);
+	if (ret)
+		return ret;
+
 	if (pm_runtime_suspended(dev))
 		return 0;
 
-	return arm_smmu_runtime_resume(dev);
+	ret = arm_smmu_runtime_resume(dev);
+	if (ret)
+		clk_bulk_unprepare(smmu->num_clks, smmu->clks);
+
+	return ret;
 }
 
 static int __maybe_unused arm_smmu_pm_suspend(struct device *dev)
 {
+	int ret = 0;
+	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
 	if (pm_runtime_suspended(dev))
-		return 0;
+		goto clk_unprepare;
+
+	ret = arm_smmu_runtime_suspend(dev);
+	if (ret)
+		return ret;
 
-	return arm_smmu_runtime_suspend(dev);
+clk_unprepare:
+	clk_bulk_unprepare(smmu->num_clks, smmu->clks);
+	return ret;
 }
 
 static const struct dev_pm_ops arm_smmu_pm_ops = {
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index a50271595960..432de2f742c3 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -346,6 +346,7 @@ struct arm_smmu_cfg {
 	};
 	enum arm_smmu_cbar_type		cbar;
 	enum arm_smmu_context_fmt	fmt;
+	bool				flush_walk_prefer_tlbiasid;
 };
 #define ARM_SMMU_INVALID_IRPTNDX	0xff
 
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 021cf8f65ffc..b91874cb6cf3 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -10,7 +10,6 @@
 #include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/dma-iommu.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -335,12 +334,6 @@ static struct iommu_domain *qcom_iommu_domain_alloc(unsigned type)
 	if (!qcom_domain)
 		return NULL;
 
-	if (type == IOMMU_DOMAIN_DMA &&
-	    iommu_get_dma_cookie(&qcom_domain->domain)) {
-		kfree(qcom_domain);
-		return NULL;
-	}
-
 	mutex_init(&qcom_domain->init_mutex);
 	spin_lock_init(&qcom_domain->pgtbl_lock);
 
@@ -351,8 +344,6 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain)
 {
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 
-	iommu_put_dma_cookie(domain);
-
 	if (qcom_domain->iommu) {
 		/*
 		 * NOTE: unmap can be called after client device is powered