iommu/arm-smmu-v3: Add support for dirty tracking in domain alloc

This provides all the infrastructure to enable dirty tracking if the
hardware has the capability and domain alloc request for it.

Also, add a device_iommu_capable() check in iommufd core for
IOMMU_CAP_DIRTY_TRACKING before we request a user domain with dirty
tracking support.

Please note, we still report no support for IOMMU_CAP_DIRTY_TRACKING
as it will finally be enabled in a subsequent patch.
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Link: https://lore.kernel.org/r/20240703101604.2576-5-shameerali.kolothum.thodi@huawei.comSigned-off-by: Will Deacon <will@kernel.org>

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -27,6 +27,7 @@
 #include <linux/pci-ats.h>
 #include <linux/platform_device.h>
 #include <kunit/visibility.h>
+#include <uapi/linux/iommufd.h>
 
 #include "arm-smmu-v3.h"
 #include "../../dma-iommu.h"
@@ -37,6 +38,7 @@ MODULE_PARM_DESC(disable_msipolling,
 	"Disable MSI-based polling for CMD_SYNC completion.");
 
 static struct iommu_ops arm_smmu_ops;
+static struct iommu_dirty_ops arm_smmu_dirty_ops;
 
 enum arm_smmu_msi_index {
 	EVTQ_MSI_INDEX,
@@ -82,7 +84,7 @@ static struct arm_smmu_option_prop arm_smmu_options[] = {
 };
 
 static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
-				    struct arm_smmu_device *smmu);
+				    struct arm_smmu_device *smmu, u32 flags);
 static int arm_smmu_alloc_cd_tables(struct arm_smmu_master *master);
 
 static void parse_driver_options(struct arm_smmu_device *smmu)
@@ -2282,7 +2284,7 @@ static struct iommu_domain *arm_smmu_domain_alloc_paging(struct device *dev)
 		struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 		int ret;
 
-		ret = arm_smmu_domain_finalise(smmu_domain, master->smmu);
+		ret = arm_smmu_domain_finalise(smmu_domain, master->smmu, 0);
 		if (ret) {
 			kfree(smmu_domain);
 			return ERR_PTR(ret);
@@ -2346,15 +2348,15 @@ static int arm_smmu_domain_finalise_s2(struct arm_smmu_device *smmu,
 }
 
 static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
-				    struct arm_smmu_device *smmu)
+				    struct arm_smmu_device *smmu, u32 flags)
 {
 	int ret;
-	unsigned long ias, oas;
 	enum io_pgtable_fmt fmt;
 	struct io_pgtable_cfg pgtbl_cfg;
 	struct io_pgtable_ops *pgtbl_ops;
 	int (*finalise_stage_fn)(struct arm_smmu_device *smmu,
 				 struct arm_smmu_domain *smmu_domain);
+	bool enable_dirty = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
 
 	/* Restrict the stage to what we can actually support */
 	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
@@ -2362,17 +2364,31 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
 	if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S2))
 		smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
 
+	pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= smmu->pgsize_bitmap,
+		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENCY,
+		.tlb		= &arm_smmu_flush_ops,
+		.iommu_dev	= smmu->dev,
+	};
+
 	switch (smmu_domain->stage) {
-	case ARM_SMMU_DOMAIN_S1:
-		ias = (smmu->features & ARM_SMMU_FEAT_VAX) ? 52 : 48;
-		ias = min_t(unsigned long, ias, VA_BITS);
-		oas = smmu->ias;
+	case ARM_SMMU_DOMAIN_S1: {
+		unsigned long ias = (smmu->features &
+				     ARM_SMMU_FEAT_VAX) ? 52 : 48;
+
+		pgtbl_cfg.ias = min_t(unsigned long, ias, VA_BITS);
+		pgtbl_cfg.oas = smmu->ias;
+		if (enable_dirty)
+			pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_HD;
 		fmt = ARM_64_LPAE_S1;
 		finalise_stage_fn = arm_smmu_domain_finalise_s1;
 		break;
+	}
 	case ARM_SMMU_DOMAIN_S2:
-		ias = smmu->ias;
-		oas = smmu->oas;
+		if (enable_dirty)
+			return -EOPNOTSUPP;
+		pgtbl_cfg.ias = smmu->ias;
+		pgtbl_cfg.oas = smmu->oas;
 		fmt = ARM_64_LPAE_S2;
 		finalise_stage_fn = arm_smmu_domain_finalise_s2;
 		break;
@@ -2380,15 +2396,6 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
 		return -EINVAL;
 	}
 
-	pgtbl_cfg = (struct io_pgtable_cfg) {
-		.pgsize_bitmap	= smmu->pgsize_bitmap,
-		.ias		= ias,
-		.oas		= oas,
-		.coherent_walk	= smmu->features & ARM_SMMU_FEAT_COHERENCY,
-		.tlb		= &arm_smmu_flush_ops,
-		.iommu_dev	= smmu->dev,
-	};
-
 	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
 	if (!pgtbl_ops)
 		return -ENOMEM;
@@ -2396,6 +2403,8 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain,
 	smmu_domain->domain.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
 	smmu_domain->domain.geometry.aperture_end = (1UL << pgtbl_cfg.ias) - 1;
 	smmu_domain->domain.geometry.force_aperture = true;
+	if (enable_dirty && smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
+		smmu_domain->domain.dirty_ops = &arm_smmu_dirty_ops;
 
 	ret = finalise_stage_fn(smmu, smmu_domain);
 	if (ret < 0) {
@@ -2745,7 +2754,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	mutex_lock(&smmu_domain->init_mutex);
 
 	if (!smmu_domain->smmu) {
-		ret = arm_smmu_domain_finalise(smmu_domain, smmu);
+		ret = arm_smmu_domain_finalise(smmu_domain, smmu, 0);
 	} else if (smmu_domain->smmu != smmu)
 		ret = -EINVAL;
 
@@ -2810,7 +2819,7 @@ static int arm_smmu_s1_set_dev_pasid(struct iommu_domain *domain,
 
 	mutex_lock(&smmu_domain->init_mutex);
 	if (!smmu_domain->smmu)
-		ret = arm_smmu_domain_finalise(smmu_domain, smmu);
+		ret = arm_smmu_domain_finalise(smmu_domain, smmu, 0);
 	else if (smmu_domain->smmu != smmu)
 		ret = -EINVAL;
 	mutex_unlock(&smmu_domain->init_mutex);
@@ -3028,10 +3037,13 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
 			   const struct iommu_user_data *user_data)
 {
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+	const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
 	struct arm_smmu_domain *smmu_domain;
 	int ret;
 
-	if (flags || parent || user_data)
+	if (flags & ~PAGING_FLAGS)
+		return ERR_PTR(-EOPNOTSUPP);
+	if (parent || user_data)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	smmu_domain = arm_smmu_domain_alloc();
@@ -3040,7 +3052,7 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags,
 
 	smmu_domain->domain.type = IOMMU_DOMAIN_UNMANAGED;
 	smmu_domain->domain.ops = arm_smmu_ops.default_domain_ops;
-	ret = arm_smmu_domain_finalise(smmu_domain, master->smmu);
+	ret = arm_smmu_domain_finalise(smmu_domain, master->smmu, flags);
 	if (ret)
 		goto err_free;
 	return &smmu_domain->domain;
@@ -3295,6 +3307,27 @@ static void arm_smmu_release_device(struct device *dev)
 	kfree(master);
 }
 
+static int arm_smmu_read_and_clear_dirty(struct iommu_domain *domain,
+					 unsigned long iova, size_t size,
+					 unsigned long flags,
+					 struct iommu_dirty_bitmap *dirty)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+
+	return ops->read_and_clear_dirty(ops, iova, size, flags, dirty);
+}
+
+static int arm_smmu_set_dirty_tracking(struct iommu_domain *domain,
+				       bool enabled)
+{
+	/*
+	 * Always enabled and the dirty bitmap is cleared prior to
+	 * set_dirty_tracking().
+	 */
+	return 0;
+}
+
 static struct iommu_group *arm_smmu_device_group(struct device *dev)
 {
 	struct iommu_group *group;
@@ -3453,6 +3486,11 @@ static struct iommu_ops arm_smmu_ops = {
 	}
 };
 
+static struct iommu_dirty_ops arm_smmu_dirty_ops = {
+	.read_and_clear_dirty	= arm_smmu_read_and_clear_dirty,
+	.set_dirty_tracking     = arm_smmu_set_dirty_tracking,
+};
+
 /* Probing and initialisation functions */
 static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 				   struct arm_smmu_queue *q,

drivers/iommu/iommufd/hw_pagetable.c

@@ -114,6 +114,9 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 		return ERR_PTR(-EOPNOTSUPP);
 	if (flags & ~valid_flags)
 		return ERR_PTR(-EOPNOTSUPP);
+	if ((flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) &&
+	    !device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING))
+		return ERR_PTR(-EOPNOTSUPP);
 
 	hwpt_paging = __iommufd_object_alloc(
 		ictx, hwpt_paging, IOMMUFD_OBJ_HWPT_PAGING, common.obj);

include/linux/io-pgtable.h

@@ -85,6 +85,8 @@ struct io_pgtable_cfg {
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability
 	 *	attributes set in the TCR for a non-coherent page-table walker.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_HD: Enables dirty tracking in stage 1 pagetable.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS			BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS		BIT(1)
@@ -92,6 +94,7 @@ struct io_pgtable_cfg {
 	#define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1		BIT(5)
 	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA		BIT(6)
+	#define IO_PGTABLE_QUIRK_ARM_HD			BIT(7)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;