[PATCH v4 bpf-next/net 3/5] bpf: Introduce SK_BPF_MEMCG_FLAGS and SK_BPF_MEMCG_SOCK_ISOLATED.

@@ -2596,10 +2596,41 @@ static inline gfp_t gfp_memcg_charge(void)
 	return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
 }
 
+#define SK_BPF_MEMCG_FLAG_MASK	(SK_BPF_MEMCG_FLAG_MAX - 1)
+#define SK_BPF_MEMCG_PTR_MASK	~SK_BPF_MEMCG_FLAG_MASK
+
 #ifdef CONFIG_MEMCG
 static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk)
 {
+#ifdef CONFIG_CGROUP_BPF
+	unsigned long val = (unsigned long)sk->sk_memcg;
+
+	val &= SK_BPF_MEMCG_PTR_MASK;
+	return (struct mem_cgroup *)val;
+#else
 	return sk->sk_memcg;
+#endif
+}
+
+static inline void mem_cgroup_sk_set_flags(struct sock *sk, unsigned short flags)
+{
+#ifdef CONFIG_CGROUP_BPF
+	unsigned long val = (unsigned long)mem_cgroup_from_sk(sk);
+
+	val |= flags;
+	sk->sk_memcg = (struct mem_cgroup *)val;
+#endif
+}
+
+static inline unsigned short mem_cgroup_sk_get_flags(const struct sock *sk)
+{
+#ifdef CONFIG_CGROUP_BPF
+	unsigned long val = (unsigned long)sk->sk_memcg;
+
+	return val & SK_BPF_MEMCG_FLAG_MASK;
+#else
+	return 0;
+#endif
 }
 
 static inline bool mem_cgroup_sk_enabled(const struct sock *sk)

@@ -2607,6 +2638,11 @@ static inline bool mem_cgroup_sk_enabled(const struct sock *sk)
 	return mem_cgroup_sockets_enabled && mem_cgroup_from_sk(sk);
 }
 
+static inline bool mem_cgroup_sk_isolated(const struct sock *sk)
+{
+	return mem_cgroup_sk_get_flags(sk) & SK_BPF_MEMCG_SOCK_ISOLATED;
+}
+
 static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_sk(sk);

@@ -2629,11 +2665,25 @@ static inline struct mem_cgroup *mem_cgroup_from_sk(const struct sock *sk)
 	return NULL;
 }
 
+static inline void mem_cgroup_sk_set_flags(struct sock *sk, unsigned short flags)
+{
+}
+
+static inline unsigned short mem_cgroup_sk_get_flags(const struct sock *sk)
+{
+	return 0;
+}
+
 static inline bool mem_cgroup_sk_enabled(const struct sock *sk)
 {
 	return false;
 }
 
+static inline bool mem_cgroup_sk_isolated(const struct sock *sk)
+{
+	return false;
+}
+
 static inline bool mem_cgroup_sk_under_memory_pressure(const struct sock *sk)
 {
 	return false;

@@ -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_SOCK_ISOLATED	= (1UL << 0),
+	SK_BPF_MEMCG_FLAG_MAX		= (1UL << 1),
+};
+
 struct bpf_perf_event_value {
 	__u64 counter;
 	__u64 enabled;

@@ -5267,6 +5267,35 @@ static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt)
 	return 0;
 }
 
+static int sk_bpf_get_memcg_flags(struct sock *sk, char *optval)
+{
+	if (!sk_has_account(sk))
+		return -EOPNOTSUPP;
+
+	*(u32 *)optval = mem_cgroup_sk_get_flags(sk);
+
+	return 0;
+}
+
+static int sk_bpf_set_memcg_flags(struct sock *sk, char *optval, int optlen)
+{
+	u32 flags;
+
+	if (optlen != sizeof(u32))
+		return -EINVAL;
+
+	if (!sk_has_account(sk))
+		return -EOPNOTSUPP;
+
+	flags = *(u32 *)optval;
+	if (flags >= SK_BPF_MEMCG_FLAG_MAX)
+		return -EINVAL;
+
+	mem_cgroup_sk_set_flags(sk, flags);
+
+	return 0;
+}
+
 static int sol_socket_sockopt(struct sock *sk, int optname,
 			      char *optval, int *optlen,
 			      bool getopt)

@@ -5284,6 +5313,7 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
 	case SO_BINDTOIFINDEX:
 	case SO_TXREHASH:
 	case SK_BPF_CB_FLAGS:
+	case SK_BPF_MEMCG_FLAGS:
 		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;

@@ -5293,8 +5323,15 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
 		return -EINVAL;
 	}
 
-	if (optname == SK_BPF_CB_FLAGS)
+	switch (optname) {
+	case SK_BPF_CB_FLAGS:
 		return sk_bpf_set_get_cb_flags(sk, optval, getopt);
+	case SK_BPF_MEMCG_FLAGS:
+		if (!IS_ENABLED(CONFIG_MEMCG) || !getopt)
+			return -EOPNOTSUPP;
+
+		return sk_bpf_get_memcg_flags(sk, optval);
+	}
 
 	if (getopt) {
 		if (optname == SO_BINDTODEVICE)

@@ -5726,6 +5763,10 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
 BPF_CALL_5(bpf_unlocked_sock_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_memcg_flags(sk, optval, optlen);
+
 	return __bpf_setsockopt(sk, level, optname, optval, optlen);
 }
 

@@ -2515,6 +2515,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 #ifdef CONFIG_MEMCG
 	/* sk->sk_memcg will be populated at accept() time */
 	newsk->sk_memcg = NULL;
+	mem_cgroup_sk_set_flags(newsk, mem_cgroup_sk_get_flags(sk));
 #endif
 
 	cgroup_sk_clone(&newsk->sk_cgrp_data);

@@ -758,12 +758,16 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new
 	    (!IS_ENABLED(CONFIG_IP_SCTP) ||
 	     sk_is_tcp(newsk) || sk_is_mptcp(newsk))) {
 		gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL;
+		unsigned short flags;
 
+		flags = mem_cgroup_sk_get_flags(newsk);
 		mem_cgroup_sk_alloc(newsk);
 
 		if (mem_cgroup_from_sk(newsk)) {
 			int amt;
 
+			mem_cgroup_sk_set_flags(newsk, flags);
+
 			/* The socket has not been accepted yet, no need
 			 * to look at newsk->sk_wmem_queued.
 			 */

@@ -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_SOCK_ISOLATED	= (1UL << 0),
+	SK_BPF_MEMCG_FLAG_MAX		= (1UL << 1),
+};
+
 struct bpf_perf_event_value {
 	__u64 counter;
 	__u64 enabled;