@@ -390,6 +390,40 @@ 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, int flags)
+{
+ struct pasid_entry *pte;
+ u16 old_did;
+
+ if (!ecap_flts(iommu->ecap) ||
+ ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)))
+ return -EINVAL;
+
+ 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;
+ }
+
+ old_did = pasid_get_domain_id(pte);
+
+ pasid_pte_config_first_level(iommu, pte, pgd, did, flags);
+ spin_unlock(&iommu->lock);
+
+ intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+ intel_drain_pasid_prq(dev, pasid);
+
+ return 0;
+}
+
/*
* Skip top levels of page tables for iommu which has less agaw
* than default. Unnecessary for PT mode.
@@ -483,6 +517,55 @@ 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, u32 pasid)
+{
+ struct pasid_entry *pte;
+ struct dma_pte *pgd;
+ u16 did, old_did;
+ u64 pgd_val;
+ int agaw;
+
+ /*
+ * If hardware advertises no support for second level
+ * translation, return directly.
+ */
+ if (!ecap_slts(iommu->ecap))
+ return -EINVAL;
+
+ pgd = domain->pgd;
+ agaw = iommu_skip_agaw(domain, iommu, &pgd);
+ if (agaw < 0)
+ return -EINVAL;
+
+ pgd_val = virt_to_phys(pgd);
+ did = domain_id_iommu(domain, iommu);
+
+ 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;
+ }
+
+ old_did = pasid_get_domain_id(pte);
+
+ pasid_pte_config_second_level(iommu, pte, pgd_val, agaw,
+ did, domain->dirty_tracking);
+ spin_unlock(&iommu->lock);
+
+ intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+ intel_drain_pasid_prq(dev, pasid);
+
+ return 0;
+}
+
/*
* Set up dirty tracking on a second only or nested translation type.
*/
@@ -595,6 +678,35 @@ 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, u32 pasid)
+{
+ u16 did = FLPT_DEFAULT_DID, old_did;
+ struct pasid_entry *pte;
+
+ 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;
+ }
+
+ old_did = pasid_get_domain_id(pte);
+
+ pasid_pte_config_pass_through(iommu, pte, did);
+ spin_unlock(&iommu->lock);
+
+ intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+ intel_drain_pasid_prq(dev, pasid);
+
+ return 0;
+}
+
/*
* Set the page snoop control for a pasid entry which has been set up.
*/
@@ -725,6 +837,67 @@ 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,
+ struct dmar_domain *domain)
+{
+ struct iommu_hwpt_vtd_s1 *s1_cfg = &domain->s1_cfg;
+ u16 did = domain_id_iommu(domain, iommu), old_did;
+ struct dmar_domain *s2_domain = domain->s2_domain;
+ struct pasid_entry *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;
+ }
+
+ 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;
+ }
+
+ old_did = pasid_get_domain_id(pte);
+
+ pasid_pte_config_nestd(iommu, pte, s1_cfg, s2_domain, did);
+ spin_unlock(&iommu->lock);
+
+ intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+ intel_drain_pasid_prq(dev, pasid);
+
+ return 0;
+}
+
/*
* Interfaces to setup or teardown a pasid table to the scalable-mode
* context table entry:
@@ -303,6 +303,18 @@ 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, int flags);
+int intel_pasid_replace_second_level(struct intel_iommu *iommu,
+ struct dmar_domain *domain,
+ struct device *dev, u32 pasid);
+int intel_pasid_replace_pass_through(struct intel_iommu *iommu,
+ struct device *dev, u32 pasid);
+int intel_pasid_replace_nested(struct intel_iommu *iommu,
+ struct device *dev, u32 pasid,
+ struct dmar_domain *domain);
+
void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
struct device *dev, u32 pasid,
bool fault_ignore);
pasid replacement allows converting a present pasid entry to be FS, SS, PT or nested, hence add helpers for such operations. This simplifies the callers as well since the caller can switch the pasid to the new domain by one-shot. Suggested-by: Lu Baolu <baolu.lu@linux.intel.com> Signed-off-by: Yi Liu <yi.l.liu@intel.com> --- drivers/iommu/intel/pasid.c | 173 ++++++++++++++++++++++++++++++++++++ drivers/iommu/intel/pasid.h | 12 +++ 2 files changed, 185 insertions(+)