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>

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fe0bf482fdf892e126636f94b5260cf89f888648..4385418118f66699b6c9f30865f2119bfa8ae2e3 100644 (file)
--- a/include/linux/bpf.h
+++ b/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 */

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 1db156405b68b339ca68a196f714be6d29b556b6..490d03a4581aa6c307a6be01826216113fde2588 100644 (file)
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -395,7 +395,8 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
                unit_size = size;
 
 #ifdef CONFIG_MEMCG_KMEM
-               objcg = get_obj_cgroup_from_current();
+               if (memcg_bpf_enabled())
+                       objcg = get_obj_cgroup_from_current();
 #endif
                for_each_possible_cpu(cpu) {
                        c = per_cpu_ptr(pc, cpu);

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9d94a35d8b0f93be7e67553551db8cf657c0aa6a..cda8d00f376221ab5bd5e33aa190004b90e87cb8 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/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;
@@ -418,7 +418,8 @@ 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.
         */
-       map->objcg = get_obj_cgroup_from_current();
+       if (memcg_bpf_enabled())
+               map->objcg = get_obj_cgroup_from_current();
 }
 
 static void bpf_map_release_memcg(struct bpf_map *map)