iommu/iova: Separate out rcache init

Currently the rcache structures are allocated for all IOVA domains, even if
they do not use "fast" alloc+free interface. This is wasteful of memory.

In addition, fails in init_iova_rcaches() are not handled safely, which is
less than ideal.

Make "fast" users call a separate rcache init explicitly, which includes
error checking.

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/1643882360-241739-1-git-send-email-john.garry@huawei.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

1 files changed, 59 insertions, 14 deletions

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index b28c9435b898..7e9c3a97c040 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -15,13 +15,14 @@
 /* The anchor node sits above the top of the usable address space */
 #define IOVA_ANCHOR	~0UL
 
+#define IOVA_RANGE_CACHE_MAX_SIZE 6	/* log of max cached IOVA range size (in pages) */
+
 static bool iova_rcache_insert(struct iova_domain *iovad,
 			       unsigned long pfn,
 			       unsigned long size);
 static unsigned long iova_rcache_get(struct iova_domain *iovad,
 				     unsigned long size,
 				     unsigned long limit_pfn);
-static void init_iova_rcaches(struct iova_domain *iovad);
 static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 
@@ -64,8 +65,6 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
 	rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
 	rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
-	cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, &iovad->cpuhp_dead);
-	init_iova_rcaches(iovad);
 }
 EXPORT_SYMBOL_GPL(init_iova_domain);
 
@@ -488,6 +487,13 @@ free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
 }
 EXPORT_SYMBOL_GPL(free_iova_fast);
 
+static void iova_domain_free_rcaches(struct iova_domain *iovad)
+{
+	cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
+					    &iovad->cpuhp_dead);
+	free_iova_rcaches(iovad);
+}
+
 /**
  * put_iova_domain - destroys the iova domain
  * @iovad: - iova domain in question.
@@ -497,9 +503,9 @@ void put_iova_domain(struct iova_domain *iovad)
 {
 	struct iova *iova, *tmp;
 
-	cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
-					    &iovad->cpuhp_dead);
-	free_iova_rcaches(iovad);
+	if (iovad->rcaches)
+		iova_domain_free_rcaches(iovad);
+
 	rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
 		free_iova_mem(iova);
 }
@@ -608,6 +614,7 @@ EXPORT_SYMBOL_GPL(reserve_iova);
  */
 
 #define IOVA_MAG_SIZE 128
+#define MAX_GLOBAL_MAGS 32	/* magazines per bin */
 
 struct iova_magazine {
 	unsigned long size;
@@ -620,6 +627,13 @@ struct iova_cpu_rcache {
 	struct iova_magazine *prev;
 };
 
+struct iova_rcache {
+	spinlock_t lock;
+	unsigned long depot_size;
+	struct iova_magazine *depot[MAX_GLOBAL_MAGS];
+	struct iova_cpu_rcache __percpu *cpu_rcaches;
+};
+
 static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
 {
 	return kzalloc(sizeof(struct iova_magazine), flags);
@@ -693,28 +707,54 @@ static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
 	mag->pfns[mag->size++] = pfn;
 }
 
-static void init_iova_rcaches(struct iova_domain *iovad)
+int iova_domain_init_rcaches(struct iova_domain *iovad)
 {
-	struct iova_cpu_rcache *cpu_rcache;
-	struct iova_rcache *rcache;
 	unsigned int cpu;
-	int i;
+	int i, ret;
+
+	iovad->rcaches = kcalloc(IOVA_RANGE_CACHE_MAX_SIZE,
+				 sizeof(struct iova_rcache),
+				 GFP_KERNEL);
+	if (!iovad->rcaches)
+		return -ENOMEM;
 
 	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+		struct iova_cpu_rcache *cpu_rcache;
+		struct iova_rcache *rcache;
+
 		rcache = &iovad->rcaches[i];
 		spin_lock_init(&rcache->lock);
 		rcache->depot_size = 0;
-		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache), cache_line_size());
-		if (WARN_ON(!rcache->cpu_rcaches))
-			continue;
+		rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache),
+						     cache_line_size());
+		if (!rcache->cpu_rcaches) {
+			ret = -ENOMEM;
+			goto out_err;
+		}
 		for_each_possible_cpu(cpu) {
 			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+
 			spin_lock_init(&cpu_rcache->lock);
 			cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL);
 			cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL);
+			if (!cpu_rcache->loaded || !cpu_rcache->prev) {
+				ret = -ENOMEM;
+				goto out_err;
+			}
 		}
 	}
+
+	ret = cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
+					       &iovad->cpuhp_dead);
+	if (ret)
+		goto out_err;
+	return 0;
+
+out_err:
+	free_iova_rcaches(iovad);
+	return ret;
 }
+EXPORT_SYMBOL_GPL(iova_domain_init_rcaches);
 
 /*
  * Try inserting IOVA range starting with 'iova_pfn' into 'rcache', and
@@ -831,7 +871,7 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 {
 	unsigned int log_size = order_base_2(size);
 
-	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
+	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE || !iovad->rcaches)
 		return 0;
 
 	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
@@ -849,6 +889,8 @@ static void free_iova_rcaches(struct iova_domain *iovad)
 
 	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
 		rcache = &iovad->rcaches[i];
+		if (!rcache->cpu_rcaches)
+			break;
 		for_each_possible_cpu(cpu) {
 			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
 			iova_magazine_free(cpu_rcache->loaded);
@@ -858,6 +900,9 @@ static void free_iova_rcaches(struct iova_domain *iovad)
 		for (j = 0; j < rcache->depot_size; ++j)
 			iova_magazine_free(rcache->depot[j]);
 	}
+
+	kfree(iovad->rcaches);
+	iovad->rcaches = NULL;
 }
 
 /*