iommu/vt-d: Add qi_batch for dmar_domain

Introduces a qi_batch structure to hold batched cache invalidation
descriptors on a per-dmar_domain basis. A fixed-size descriptor
array is used for simplicity. The qi_batch is allocated when the
first cache tag is added to the domain and freed during
iommu_free_domain().

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Link: https://lore.kernel.org/r/20240815065221.50328-4-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

5 files changed, 27 insertions, 1 deletions

diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c
index 08f7ce2c16c3..2e997d782beb 100644
--- a/drivers/iommu/intel/cache.c
+++ b/drivers/iommu/intel/cache.c
@@ -190,6 +190,13 @@ int cache_tag_assign_domain(struct dmar_domain *domain,
 	u16 did = domain_get_id_for_dev(domain, dev);
 	int ret;
 
+	/* domain->qi_bach will be freed in iommu_free_domain() path. */
+	if (!domain->qi_batch) {
+		domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_KERNEL);
+		if (!domain->qi_batch)
+			return -ENOMEM;
+	}
+
 	ret = __cache_tag_assign_domain(domain, did, dev, pasid);
 	if (ret || domain->domain.type != IOMMU_DOMAIN_NESTED)
 		return ret;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index dfd33adffb14..038a81efaaf7 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1572,6 +1572,7 @@ static void domain_exit(struct dmar_domain *domain)
 	if (WARN_ON(!list_empty(&domain->devices)))
 		return;
 
+	kfree(domain->qi_batch);
 	kfree(domain);
 }
 
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 74634805abd1..d21eca94cb8f 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -584,6 +584,19 @@ struct iommu_domain_info {
 					 * to VT-d spec, section 9.3 */
 };
 
+/*
+ * We start simply by using a fixed size for the batched descriptors. This
+ * size is currently sufficient for our needs. Future improvements could
+ * involve dynamically allocating the batch buffer based on actual demand,
+ * allowing us to adjust the batch size for optimal performance in different
+ * scenarios.
+ */
+#define QI_MAX_BATCHED_DESC_COUNT 16
+struct qi_batch {
+	struct qi_desc descs[QI_MAX_BATCHED_DESC_COUNT];
+	unsigned int index;
+};
+
 struct dmar_domain {
 	int	nid;			/* node id */
 	struct xarray iommu_array;	/* Attached IOMMU array */
@@ -608,6 +621,7 @@ struct dmar_domain {
 
 	spinlock_t cache_lock;		/* Protect the cache tag list */
 	struct list_head cache_tags;	/* Cache tag list */
+	struct qi_batch *qi_batch;	/* Batched QI descriptors */
 
 	int		iommu_superpage;/* Level of superpages supported:
 					   0 == 4KiB (no superpages), 1 == 2MiB,
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index 36a91b1b52be..433c58944401 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -83,6 +83,7 @@ static void intel_nested_domain_free(struct iommu_domain *domain)
 	spin_lock(&s2_domain->s1_lock);
 	list_del(&dmar_domain->s2_link);
 	spin_unlock(&s2_domain->s1_lock);
+	kfree(dmar_domain->qi_batch);
 	kfree(dmar_domain);
 }
 
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index ef12e95e400a..078d1e32a24e 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -184,7 +184,10 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 
 static void intel_mm_free_notifier(struct mmu_notifier *mn)
 {
-	kfree(container_of(mn, struct dmar_domain, notifier));
+	struct dmar_domain *domain = container_of(mn, struct dmar_domain, notifier);
+
+	kfree(domain->qi_batch);
+	kfree(domain);
 }
 
 static const struct mmu_notifier_ops intel_mmuops = {