bpf: allow to disable bpf map memory accounting

We can simply set root memcg as the map's memcg to disable bpf memory
accounting. bpf_map_area_alloc is a little special as it gets the memcg
from current rather than from the map, so we need to disable GFP_ACCOUNT
specifically for it.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Link: https://lore.kernel.org/r/20230210154734.4416-4-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -28,6 +28,7 @@
 #include <linux/btf.h>
 #include <linux/rcupdate_trace.h>
 #include <linux/static_call.h>
+#include <linux/memcontrol.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -2933,4 +2934,11 @@ static inline bool type_is_alloc(u32 type)
 	return type & MEM_ALLOC;
 }
 
+static inline gfp_t bpf_memcg_flags(gfp_t flags)
+{
+	if (memcg_bpf_enabled())
+		return flags | __GFP_ACCOUNT;
+	return flags;
+}
+
 #endif /* _LINUX_BPF_H */

kernel/bpf/memalloc.c

@@ -395,6 +395,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 		unit_size = size;
 
 #ifdef CONFIG_MEMCG_KMEM
+		if (memcg_bpf_enabled())
 			objcg = get_obj_cgroup_from_current();
 #endif
 		for_each_possible_cpu(cpu) {

kernel/bpf/syscall.c

@@ -309,7 +309,7 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
 	 * __GFP_RETRY_MAYFAIL to avoid such situations.
 	 */
 
-	const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT;
+	gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO);
 	unsigned int flags = 0;
 	unsigned long align = 1;
 	void *area;
@@ -418,6 +418,7 @@ static void bpf_map_save_memcg(struct bpf_map *map)
 	 * So we have to check map->objcg for being NULL each time it's
 	 * being used.
 	 */
+	if (memcg_bpf_enabled())
 		map->objcg = get_obj_cgroup_from_current();
 }