bpf: Introduce SK_BPF_MEMCG_FLAGS and SK_BPF_MEMCG_SOCK_ISOLATED.

We will decouple sockets from the global protocol memory accounting
if sockets have SK_BPF_MEMCG_SOCK_ISOLATED.

This can be flagged (and cleared) at the BPF_CGROUP_INET_SOCK_CREATE
hook by bpf_setsockopt() and is inherited to child sockets.

  u32 flags = SK_BPF_MEMCG_SOCK_ISOLATED;

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

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.

Given sk->sk_memcg can be accessed in the fast path, it would
be preferable to place the flag field in the same cache line as
sk->sk_memcg.

However, struct sock does not have such a 1-byte hole.

Let's store the flag in the lowest bit of sk->sk_memcg and add
a helper to check the bit.

In the next patch, if mem_cgroup_sk_isolated() returns true,
the socket will not be charged to sk->sk_prot->memory_allocated.

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

Author: q2ven

include/net/sock.h

@@ -2596,17 +2596,53 @@ 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)
 {
 	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;

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

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);
 }
 

net/core/sock.c

@@ -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);

net/ipv4/af_inet.c

@@ -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.
 			 */

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