bpf: Introduce SK_BPF_MEMCG_FLAGS and SK_BPF_MEMCG_EXCLUSIVE.

If a socket has sk->sk_memcg with SK_MEMCG_EXCLUSIVE, it is decoupled
from the global protocol memory accounting.

This is controlled by net.core.memcg_exclusive sysctl, but it lacks
flexibility.

Let's support flagging (and clearing) SK_MEMCG_EXCLUSIVE via
bpf_setsockopt() at the BPF_CGROUP_INET_SOCK_CREATE hook.

  u32 flags = SK_BPF_MEMCG_EXCLUSIVE;

  bpf_setsockopt(ctx, SOL_SOCKET, SK_BPF_MEMCG_FLAGS,
                 &flags, sizeof(flags));

As with net.core.memcg_exclusive, this is inherited to child sockets,
and BPF always takes precedence over sysctl at socket(2) and accept(2).

SK_BPF_MEMCG_FLAGS is only supported at BPF_CGROUP_INET_SOCK_CREATE
and not supported on other hooks for some reasons:

  1. UDP charges memory under sk->sk_receive_queue.lock instead
     of lock_sock()

  2. For TCP child sockets, memory accounting is adjusted only in
     __inet_accept() which sk->sk_memcg allocation is deferred to

  3. Modifying the flag after skb is charged to sk requires such
     adjustment during bpf_setsockopt() and complicates the logic
     unnecessarily

We can support other hooks later if a real use case justifies that.

Most changes are inline and hard to trace, but a microbenchmark on
__sk_mem_raise_allocated() during neper/tcp_stream showed that more
samples completed faster with SK_MEMCG_EXCLUSIVE.  This will be more
visible under tcp_mem pressure.

  # bpftrace -e 'kprobe:__sk_mem_raise_allocated { @start[tid] = nsecs; }
    kretprobe:__sk_mem_raise_allocated /@start[tid]/
    { @EnD[tid] = nsecs - @start[tid]; @times = hist(@EnD[tid]); delete(@start[tid]); }'
  # tcp_stream -6 -F 1000 -N -T 256

Without bpf prog:

  [128, 256)          3846 |                                                    |
  [256, 512)       1505326 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
  [512, 1K)        1371006 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@     |
  [1K, 2K)          198207 |@@@@@@                                              |
  [2K, 4K)           31199 |@                                                   |

With bpf prog in the next patch:
  (must be attached before tcp_stream)
  # bpftool prog load sk_memcg.bpf.o /sys/fs/bpf/sk_memcg type cgroup/sock_create
  # bpftool cgroup attach /sys/fs/cgroup/test cgroup_inet_sock_create pinned /sys/fs/bpf/sk_memcg

  [128, 256)          6413 |                                                    |
  [256, 512)       1868425 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
  [512, 1K)        1101697 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@                      |
  [1K, 2K)          117031 |@@@@                                                |
  [2K, 4K)           11773 |                                                    |

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>

Author: q2ven

include/uapi/linux/bpf.h

@@ -7182,6 +7182,7 @@ enum {
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 	SK_BPF_CB_FLAGS		= 1009, /* Get or set sock ops flags in socket */
+	SK_BPF_MEMCG_FLAGS	= 1010, /* Get or Set flags saved in sk->sk_memcg */
 };
 
 enum {
@@ -7204,6 +7205,11 @@ enum {
 						 */
 };
 
+enum {
+	SK_BPF_MEMCG_EXCLUSIVE	= (1UL << 0),
+	SK_BPF_MEMCG_FLAG_MAX	= (1UL << 1),
+};
+
 struct bpf_perf_event_value {
 	__u64 counter;
 	__u64 enabled;

mm/memcontrol.c

@@ -4997,6 +4997,9 @@ EXPORT_SYMBOL(memcg_sockets_enabled_key);
 
 static void mem_cgroup_sk_set(struct sock *sk, struct mem_cgroup *memcg)
 {
+	BUILD_BUG_ON((unsigned short)SK_MEMCG_EXCLUSIVE != SK_BPF_MEMCG_EXCLUSIVE);
+	BUILD_BUG_ON((unsigned short)SK_MEMCG_FLAG_MAX != SK_BPF_MEMCG_FLAG_MAX);
+
 	sk->sk_memcg = memcg;
 
 	if (READ_ONCE(sock_net(sk)->core.sysctl_memcg_exclusive))

net/core/filter.c

@@ -5723,9 +5723,39 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+static int sk_bpf_set_get_memcg_flags(struct sock *sk,
+				      char *optval, int optlen,
+				      bool getopt)
+{
+	u32 flags;
+
+	if (optlen != sizeof(u32))
+		return -EINVAL;
+
+	if (!sk_has_account(sk))
+		return -EOPNOTSUPP;
+
+	if (getopt) {
+		*(u32 *)optval = mem_cgroup_sk_get_flags(sk);
+		return 0;
+	}
+
+	flags = *(u32 *)optval;
+	if (flags >= SK_BPF_MEMCG_FLAG_MAX)
+		return -EINVAL;
+
+	mem_cgroup_sk_set_flags(sk, flags);
+
+	return 0;
+}
+
 BPF_CALL_5(bpf_sock_create_setsockopt, struct sock *, sk, int, level,
 	   int, optname, char *, optval, int, optlen)
 {
+	if (IS_ENABLED(CONFIG_MEMCG) &&
+	    level == SOL_SOCKET && optname == SK_BPF_MEMCG_FLAGS)
+		return sk_bpf_set_get_memcg_flags(sk, optval, optlen, false);
+
 	return __bpf_setsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -5743,6 +5773,10 @@ static const struct bpf_func_proto bpf_sock_create_setsockopt_proto = {
 BPF_CALL_5(bpf_sock_create_getsockopt, struct sock *, sk, int, level,
 	   int, optname, char *, optval, int, optlen)
 {
+	if (IS_ENABLED(CONFIG_MEMCG) &&
+	    level == SOL_SOCKET && optname == SK_BPF_MEMCG_FLAGS)
+		return sk_bpf_set_get_memcg_flags(sk, optval, optlen, true);
+
 	return __bpf_getsockopt(sk, level, optname, optval, optlen);
 }
 

tools/include/uapi/linux/bpf.h

@@ -7182,6 +7182,7 @@ enum {
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 	SK_BPF_CB_FLAGS		= 1009, /* Get or set sock ops flags in socket */
+	SK_BPF_MEMCG_FLAGS	= 1010, /* Get or Set flags saved in sk->sk_memcg */
 };
 
 enum {
@@ -7204,6 +7205,11 @@ enum {
 						 */
 };
 
+enum {
+	SK_BPF_MEMCG_EXCLUSIVE	= (1UL << 0),
+	SK_BPF_MEMCG_FLAG_MAX	= (1UL << 1),
+};
+
 struct bpf_perf_event_value {
 	__u64 counter;
 	__u64 enabled;