iommu/vt-d: Link cache tags of same iommu unit together

Cache tag invalidation requests for a domain are accumulated until a
different iommu unit is found when traversing the cache_tags linked list.
But cache tags of same iommu unit can be distributed in the linked list,
this make batched flush less efficient. E.g., one device backed by iommu0
is attached to a domain in between two devices attaching backed by iommu1.

Group cache tags together for same iommu unit in cache_tag_assign() to
maximize the performance of batched flush.

Co-developed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/r/20241219054358.8654-1-zhenzhong.duan@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c
index 09694cca8752dfe27d54952b6048545ff2a8adbe..fc35cba5914532ab45cbee5e91eb5aec8e1a4f6e 100644 (file)
--- a/drivers/iommu/intel/cache.c
+++ b/drivers/iommu/intel/cache.c
@@ -47,6 +47,7 @@ static int cache_tag_assign(struct dmar_domain *domain, u16 did,
        struct device_domain_info *info = dev_iommu_priv_get(dev);
        struct intel_iommu *iommu = info->iommu;
        struct cache_tag *tag, *temp;
+       struct list_head *prev;
        unsigned long flags;
 
        tag = kzalloc(sizeof(*tag), GFP_KERNEL);
@@ -65,6 +66,7 @@ static int cache_tag_assign(struct dmar_domain *domain, u16 did,
                tag->dev = iommu->iommu.dev;
 
        spin_lock_irqsave(&domain->cache_lock, flags);
+       prev = &domain->cache_tags;
        list_for_each_entry(temp, &domain->cache_tags, node) {
                if (cache_tage_match(temp, did, iommu, dev, pasid, type)) {
                        temp->users++;
@@ -73,8 +75,15 @@ static int cache_tag_assign(struct dmar_domain *domain, u16 did,
                        trace_cache_tag_assign(temp);
                        return 0;
                }
+               if (temp->iommu == iommu)
+                       prev = &temp->node;
        }
-       list_add_tail(&tag->node, &domain->cache_tags);
+       /*
+        * Link cache tags of same iommu unit together, so corresponding
+        * flush ops can be batched for iommu unit.
+        */
+       list_add(&tag->node, prev);
+
        spin_unlock_irqrestore(&domain->cache_lock, flags);
        trace_cache_tag_assign(tag);