[PATCH 04/13] iommu/vt-d: Add pasid replace helpers

Lu Baolu posted 13 patches 2 weeks, 1 day ago
[PATCH 04/13] iommu/vt-d: Add pasid replace helpers
Posted by Lu Baolu 2 weeks, 1 day ago
From: Yi Liu <yi.l.liu@intel.com>

pasid replacement allows converting a present pasid entry to be FS, SS,
PT or nested, hence add helpers for such operations.

Suggested-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20241107122234.7424-5-yi.l.liu@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/pasid.c | 190 ++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel/pasid.h |  15 +++
 2 files changed, 205 insertions(+)

diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 6841b9892d55..0f2a926d3bd5 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -389,6 +389,50 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	return 0;
 }
 
+int intel_pasid_replace_first_level(struct intel_iommu *iommu,
+				    struct device *dev, pgd_t *pgd,
+				    u32 pasid, u16 did, u16 old_did,
+				    int flags)
+{
+	struct pasid_entry *pte, new_pte;
+
+	if (!ecap_flts(iommu->ecap)) {
+		pr_err("No first level translation support on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	if ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)) {
+		pr_err("No 5-level paging support for first-level on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	pasid_pte_config_first_level(iommu, &new_pte, pgd, did, flags);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
+	WARN_ON(old_did != pasid_get_domain_id(pte));
+
+	*pte = new_pte;
+	spin_unlock(&iommu->lock);
+
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
+
+	return 0;
+}
+
 /*
  * Set up the scalable mode pasid entry for second only translation type.
  */
@@ -456,6 +500,57 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	return 0;
 }
 
+int intel_pasid_replace_second_level(struct intel_iommu *iommu,
+				     struct dmar_domain *domain,
+				     struct device *dev, u16 old_did,
+				     u32 pasid)
+{
+	struct pasid_entry *pte, new_pte;
+	struct dma_pte *pgd;
+	u64 pgd_val;
+	u16 did;
+
+	/*
+	 * If hardware advertises no support for second level
+	 * translation, return directly.
+	 */
+	if (!ecap_slts(iommu->ecap)) {
+		pr_err("No second level translation support on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	pgd = domain->pgd;
+	pgd_val = virt_to_phys(pgd);
+	did = domain_id_iommu(domain, iommu);
+
+	pasid_pte_config_second_level(iommu, &new_pte, pgd_val,
+				      domain->agaw, did,
+				      domain->dirty_tracking);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
+	WARN_ON(old_did != pasid_get_domain_id(pte));
+
+	*pte = new_pte;
+	spin_unlock(&iommu->lock);
+
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
+
+	return 0;
+}
+
 /*
  * Set up dirty tracking on a second only or nested translation type.
  */
@@ -568,6 +663,38 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 	return 0;
 }
 
+int intel_pasid_replace_pass_through(struct intel_iommu *iommu,
+				     struct device *dev, u16 old_did,
+				     u32 pasid)
+{
+	struct pasid_entry *pte, new_pte;
+	u16 did = FLPT_DEFAULT_DID;
+
+	pasid_pte_config_pass_through(iommu, &new_pte, did);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
+	WARN_ON(old_did != pasid_get_domain_id(pte));
+
+	*pte = new_pte;
+	spin_unlock(&iommu->lock);
+
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
+
+	return 0;
+}
+
 /*
  * Set the page snoop control for a pasid entry which has been set up.
  */
@@ -698,6 +825,69 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 	return 0;
 }
 
+int intel_pasid_replace_nested(struct intel_iommu *iommu,
+			       struct device *dev, u32 pasid,
+			       u16 old_did, struct dmar_domain *domain)
+{
+	struct iommu_hwpt_vtd_s1 *s1_cfg = &domain->s1_cfg;
+	struct dmar_domain *s2_domain = domain->s2_domain;
+	u16 did = domain_id_iommu(domain, iommu);
+	struct pasid_entry *pte, new_pte;
+
+	/* Address width should match the address width supported by hardware */
+	switch (s1_cfg->addr_width) {
+	case ADDR_WIDTH_4LEVEL:
+		break;
+	case ADDR_WIDTH_5LEVEL:
+		if (!cap_fl5lp_support(iommu->cap)) {
+			dev_err_ratelimited(dev,
+					    "5-level paging not supported\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err_ratelimited(dev, "Invalid stage-1 address width %d\n",
+				    s1_cfg->addr_width);
+		return -EINVAL;
+	}
+
+	if ((s1_cfg->flags & IOMMU_VTD_S1_SRE) && !ecap_srs(iommu->ecap)) {
+		pr_err_ratelimited("No supervisor request support on %s\n",
+				   iommu->name);
+		return -EINVAL;
+	}
+
+	if ((s1_cfg->flags & IOMMU_VTD_S1_EAFE) && !ecap_eafs(iommu->ecap)) {
+		pr_err_ratelimited("No extended access flag support on %s\n",
+				   iommu->name);
+		return -EINVAL;
+	}
+
+	pasid_pte_config_nestd(iommu, &new_pte, s1_cfg, s2_domain, did);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
+	WARN_ON(old_did != pasid_get_domain_id(pte));
+
+	*pte = new_pte;
+	spin_unlock(&iommu->lock);
+
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
+
+	return 0;
+}
+
 /*
  * Interfaces to setup or teardown a pasid table to the scalable-mode
  * context table entry:
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index dde6d3ba5ae0..06d1f7006d01 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -303,6 +303,21 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain);
+int intel_pasid_replace_first_level(struct intel_iommu *iommu,
+				    struct device *dev, pgd_t *pgd,
+				    u32 pasid, u16 did, u16 old_did,
+				    int flags);
+int intel_pasid_replace_second_level(struct intel_iommu *iommu,
+				     struct dmar_domain *domain,
+				     struct device *dev, u16 old_did,
+				     u32 pasid);
+int intel_pasid_replace_pass_through(struct intel_iommu *iommu,
+				     struct device *dev, u16 old_did,
+				     u32 pasid);
+int intel_pasid_replace_nested(struct intel_iommu *iommu,
+			       struct device *dev, u32 pasid,
+			       u16 old_did, struct dmar_domain *domain);
+
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
-- 
2.43.0