bpf: Adjust low/high watermarks in bpf_mem_cache

The same low/high watermarks for every bucket in bpf_mem_cache consume
significant amount of memory. Preallocating 64 elements of 4096 bytes each in
the free list is not efficient. Make low/high watermarks and batching value
dependent on element size. This change brings significant memory savings.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220902211058.60789-9-alexei.starovoitov@gmail.com

kernel/bpf/memalloc.c

@@ -100,6 +100,7 @@ struct bpf_mem_cache {
 	int unit_size;
 	/* count of objects in free_llist */
 	int free_cnt;
+	int low_watermark, high_watermark, batch;
 };
 
 struct bpf_mem_caches {
@@ -118,14 +119,6 @@ static struct llist_node notrace *__llist_del_first(struct llist_head *head)
 	return entry;
 }
 
-#define BATCH 48
-#define LOW_WATERMARK 32
-#define HIGH_WATERMARK 96
-/* Assuming the average number of elements per bucket is 64, when all buckets
- * are used the total memory will be: 64*16*32 + 64*32*32 + 64*64*32 + ... +
- * 64*4096*32 ~ 20Mbyte
- */
-
 static void *__alloc(struct bpf_mem_cache *c, int node)
 {
 	/* Allocate, but don't deplete atomic reserves that typical
@@ -220,7 +213,7 @@ static void free_bulk(struct bpf_mem_cache *c)
 		if (IS_ENABLED(CONFIG_PREEMPT_RT))
 			local_irq_restore(flags);
 		free_one(c, llnode);
-	} while (cnt > (HIGH_WATERMARK + LOW_WATERMARK) / 2);
+	} while (cnt > (c->high_watermark + c->low_watermark) / 2);
 
 	/* and drain free_llist_extra */
 	llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
@@ -234,12 +227,12 @@ static void bpf_mem_refill(struct irq_work *work)
 
 	/* Racy access to free_cnt. It doesn't need to be 100% accurate */
 	cnt = c->free_cnt;
-	if (cnt < LOW_WATERMARK)
+	if (cnt < c->low_watermark)
 		/* irq_work runs on this cpu and kmalloc will allocate
 		 * from the current numa node which is what we want here.
 		 */
-		alloc_bulk(c, BATCH, NUMA_NO_NODE);
-	else if (cnt > HIGH_WATERMARK)
+		alloc_bulk(c, c->batch, NUMA_NO_NODE);
+	else if (cnt > c->high_watermark)
 		free_bulk(c);
 }
 
@@ -248,9 +241,38 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
 	irq_work_queue(&c->refill_work);
 }
 
+/* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket
+ * the freelist cache will be elem_size * 64 (or less) on each cpu.
+ *
+ * For bpf programs that don't have statically known allocation sizes and
+ * assuming (low_mark + high_mark) / 2 as an average number of elements per
+ * bucket and all buckets are used the total amount of memory in freelists
+ * on each cpu will be:
+ * 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096
+ * == ~ 116 Kbyte using below heuristic.
+ * Initialized, but unused bpf allocator (not bpf map specific one) will
+ * consume ~ 11 Kbyte per cpu.
+ * Typical case will be between 11K and 116K closer to 11K.
+ * bpf progs can and should share bpf_mem_cache when possible.
+ */
+
 static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 {
 	init_irq_work(&c->refill_work, bpf_mem_refill);
+	if (c->unit_size <= 256) {
+		c->low_watermark = 32;
+		c->high_watermark = 96;
+	} else {
+		/* When page_size == 4k, order-0 cache will have low_mark == 2
+		 * and high_mark == 6 with batch alloc of 3 individual pages at
+		 * a time.
+		 * 8k allocs and above low == 1, high == 3, batch == 1.
+		 */
+		c->low_watermark = max(32 * 256 / c->unit_size, 1);
+		c->high_watermark = max(96 * 256 / c->unit_size, 3);
+	}
+	c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
+
 	/* To avoid consuming memory assume that 1st run of bpf
 	 * prog won't be doing more than 4 map_update_elem from
 	 * irq disabled region
@@ -392,7 +414,7 @@ static void notrace *unit_alloc(struct bpf_mem_cache *c)
 
 	WARN_ON(cnt < 0);
 
-	if (cnt < LOW_WATERMARK)
+	if (cnt < c->low_watermark)
 		irq_work_raise(c);
 	return llnode;
 }
@@ -425,7 +447,7 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
 	local_dec(&c->active);
 	local_irq_restore(flags);
 
-	if (cnt > HIGH_WATERMARK)
+	if (cnt > c->high_watermark)
 		/* free few objects from current cpu into global kmalloc pool */
 		irq_work_raise(c);
 }