[PATCH 1/3] iommu: match the original algorithm

[Cong Wang]

The IOVA cache algorithm implemented in IOMMU code does not
exactly match the original algorithm described in the paper.

Particularly, it doesn't need to free the loaded empty magazine
when trying to put it back to global depot.

This patch makes it exactly match the original algorithm.

Cc: Joerg Roedel <joro@xxxxxxxxxx>
Signed-off-by: Cong Wang <xiyou.wangcong@xxxxxxxxx>
---
 drivers/iommu/iova.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 41c605b0058f..92f72a85e62a 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -900,7 +900,7 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
 
 	if (!iova_magazine_full(cpu_rcache->loaded)) {
 		can_insert = true;
-	} else if (!iova_magazine_full(cpu_rcache->prev)) {
+	} else if (iova_magazine_empty(cpu_rcache->prev)) {
 		swap(cpu_rcache->prev, cpu_rcache->loaded);
 		can_insert = true;
 	} else {
@@ -909,8 +909,9 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
 		if (new_mag) {
 			spin_lock(&rcache->lock);
 			if (rcache->depot_size < MAX_GLOBAL_MAGS) {
-				rcache->depot[rcache->depot_size++] =
-						cpu_rcache->loaded;
+				swap(rcache->depot[rcache->depot_size], cpu_rcache->prev);
+				swap(cpu_rcache->prev, cpu_rcache->loaded);
+				rcache->depot_size++;
 			} else {
 				mag_to_free = cpu_rcache->loaded;
 			}
@@ -963,14 +964,15 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
 
 	if (!iova_magazine_empty(cpu_rcache->loaded)) {
 		has_pfn = true;
-	} else if (!iova_magazine_empty(cpu_rcache->prev)) {
+	} else if (iova_magazine_full(cpu_rcache->prev)) {
 		swap(cpu_rcache->prev, cpu_rcache->loaded);
 		has_pfn = true;
 	} else {
 		spin_lock(&rcache->lock);
 		if (rcache->depot_size > 0) {
-			iova_magazine_free(cpu_rcache->loaded);
-			cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
+			swap(rcache->depot[rcache->depot_size - 1], cpu_rcache->prev);
+			swap(cpu_rcache->prev, cpu_rcache->loaded);
+			rcache->depot_size--;
 			has_pfn = true;
 		}
 		spin_unlock(&rcache->lock);
-- 
2.21.0