Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 65 insertions, 30 deletions

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 10b964600..d30e453d0 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -11,6 +11,7 @@
 #include <linux/smp.h>
 #include <linux/bitops.h>
 #include <linux/cpu.h>
+#include <linux/workqueue.h>
 
 /* The anchor node sits above the top of the usable address space */
 #define IOVA_ANCHOR	~0UL
@@ -622,15 +623,21 @@ EXPORT_SYMBOL_GPL(reserve_iova);
 /*
  * As kmalloc's buffer size is fixed to power of 2, 127 is chosen to
  * assure size of 'iova_magazine' to be 1024 bytes, so that no memory
- * will be wasted.
+ * will be wasted. Since only full magazines are inserted into the depot,
+ * we don't need to waste PFN capacity on a separate list head either.
  */
 #define IOVA_MAG_SIZE 127
-#define MAX_GLOBAL_MAGS 32	/* magazines per bin */
+
+#define IOVA_DEPOT_DELAY msecs_to_jiffies(100)
 
 struct iova_magazine {
-	unsigned long size;
+	union {
+		unsigned long size;
+		struct iova_magazine *next;
+	};
 	unsigned long pfns[IOVA_MAG_SIZE];
 };
+static_assert(!(sizeof(struct iova_magazine) & (sizeof(struct iova_magazine) - 1)));
 
 struct iova_cpu_rcache {
 	spinlock_t lock;
@@ -640,9 +647,11 @@ struct iova_cpu_rcache {
 
 struct iova_rcache {
 	spinlock_t lock;
-	unsigned long depot_size;
-	struct iova_magazine *depot[MAX_GLOBAL_MAGS];
+	unsigned int depot_size;
+	struct iova_magazine *depot;
 	struct iova_cpu_rcache __percpu *cpu_rcaches;
+	struct iova_domain *iovad;
+	struct delayed_work work;
 };
 
 static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
@@ -717,6 +726,41 @@ static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
 	mag->pfns[mag->size++] = pfn;
 }
 
+static struct iova_magazine *iova_depot_pop(struct iova_rcache *rcache)
+{
+	struct iova_magazine *mag = rcache->depot;
+
+	rcache->depot = mag->next;
+	mag->size = IOVA_MAG_SIZE;
+	rcache->depot_size--;
+	return mag;
+}
+
+static void iova_depot_push(struct iova_rcache *rcache, struct iova_magazine *mag)
+{
+	mag->next = rcache->depot;
+	rcache->depot = mag;
+	rcache->depot_size++;
+}
+
+static void iova_depot_work_func(struct work_struct *work)
+{
+	struct iova_rcache *rcache = container_of(work, typeof(*rcache), work.work);
+	struct iova_magazine *mag = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rcache->lock, flags);
+	if (rcache->depot_size > num_online_cpus())
+		mag = iova_depot_pop(rcache);
+	spin_unlock_irqrestore(&rcache->lock, flags);
+
+	if (mag) {
+		iova_magazine_free_pfns(mag, rcache->iovad);
+		iova_magazine_free(mag);
+		schedule_delayed_work(&rcache->work, IOVA_DEPOT_DELAY);
+	}
+}
+
 int iova_domain_init_rcaches(struct iova_domain *iovad)
 {
 	unsigned int cpu;
@@ -734,7 +778,8 @@ int iova_domain_init_rcaches(struct iova_domain *iovad)
 
 		rcache = &iovad->rcaches[i];
 		spin_lock_init(&rcache->lock);
-		rcache->depot_size = 0;
+		rcache->iovad = iovad;
+		INIT_DELAYED_WORK(&rcache->work, iova_depot_work_func);
 		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache),
 						     cache_line_size());
 		if (!rcache->cpu_rcaches) {
@@ -776,7 +821,6 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
 				 struct iova_rcache *rcache,
 				 unsigned long iova_pfn)
 {
-	struct iova_magazine *mag_to_free = NULL;
 	struct iova_cpu_rcache *cpu_rcache;
 	bool can_insert = false;
 	unsigned long flags;
@@ -794,13 +838,9 @@ 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;
-			} else {
-				mag_to_free = cpu_rcache->loaded;
-			}
+			iova_depot_push(rcache, cpu_rcache->loaded);
 			spin_unlock(&rcache->lock);
+			schedule_delayed_work(&rcache->work, IOVA_DEPOT_DELAY);
 
 			cpu_rcache->loaded = new_mag;
 			can_insert = true;
@@ -812,11 +852,6 @@ static bool __iova_rcache_insert(struct iova_domain *iovad,
 
 	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
 
-	if (mag_to_free) {
-		iova_magazine_free_pfns(mag_to_free, iovad);
-		iova_magazine_free(mag_to_free);
-	}
-
 	return can_insert;
 }
 
@@ -854,9 +889,9 @@ static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
 		has_pfn = true;
 	} else {
 		spin_lock(&rcache->lock);
-		if (rcache->depot_size > 0) {
+		if (rcache->depot) {
 			iova_magazine_free(cpu_rcache->loaded);
-			cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
+			cpu_rcache->loaded = iova_depot_pop(rcache);
 			has_pfn = true;
 		}
 		spin_unlock(&rcache->lock);
@@ -895,9 +930,8 @@ static void free_iova_rcaches(struct iova_domain *iovad)
 	struct iova_rcache *rcache;
 	struct iova_cpu_rcache *cpu_rcache;
 	unsigned int cpu;
-	int i, j;
 
-	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+	for (int i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
 		rcache = &iovad->rcaches[i];
 		if (!rcache->cpu_rcaches)
 			break;
@@ -907,8 +941,9 @@ static void free_iova_rcaches(struct iova_domain *iovad)
 			iova_magazine_free(cpu_rcache->prev);
 		}
 		free_percpu(rcache->cpu_rcaches);
-		for (j = 0; j < rcache->depot_size; ++j)
-			iova_magazine_free(rcache->depot[j]);
+		cancel_delayed_work_sync(&rcache->work);
+		while (rcache->depot)
+			iova_magazine_free(iova_depot_pop(rcache));
 	}
 
 	kfree(iovad->rcaches);
@@ -942,16 +977,16 @@ static void free_global_cached_iovas(struct iova_domain *iovad)
 {
 	struct iova_rcache *rcache;
 	unsigned long flags;
-	int i, j;
 
-	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+	for (int i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
 		rcache = &iovad->rcaches[i];
 		spin_lock_irqsave(&rcache->lock, flags);
-		for (j = 0; j < rcache->depot_size; ++j) {
-			iova_magazine_free_pfns(rcache->depot[j], iovad);
-			iova_magazine_free(rcache->depot[j]);
+		while (rcache->depot) {
+			struct iova_magazine *mag = iova_depot_pop(rcache);
+
+			iova_magazine_free_pfns(mag, iovad);
+			iova_magazine_free(mag);
 		}
-		rcache->depot_size = 0;
 		spin_unlock_irqrestore(&rcache->lock, flags);
 	}
 }