[PATCH v4 bpf-next 02/15] bpf: net: Avoid sk_setsockopt() taking sk lock when called from bpf

[Martin KaFai Lau <kafai@xxxxxx>]

Most of the code in bpf_setsockopt(SOL_SOCKET) are duplicated from
the sk_setsockopt().  The number of supported optnames are
increasing ever and so as the duplicated code.

One issue in reusing sk_setsockopt() is that the bpf prog
has already acquired the sk lock.  This patch adds a
has_current_bpf_ctx() to tell if the sk_setsockopt() is called from
a bpf prog.  The bpf prog calling bpf_setsockopt() is either running
in_task() or in_serving_softirq().  Both cases have the current->bpf_ctx
initialized.  Thus, the has_current_bpf_ctx() only needs to
test !!current->bpf_ctx.

This patch also adds sockopt_{lock,release}_sock() helpers
for sk_setsockopt() to use.  These helpers will test
has_current_bpf_ctx() before acquiring/releasing the lock.  They are
in EXPORT_SYMBOL for the ipv6 module to use in a latter patch.

Note on the change in sock_setbindtodevice().  sockopt_lock_sock()
is done in sock_setbindtodevice() instead of doing the lock_sock
in sock_bindtoindex(..., lock_sk = true).

Reviewed-by: Stanislav Fomichev <sdf@xxxxxxxxxx>
Signed-off-by: Martin KaFai Lau <kafai@xxxxxx>
---
 include/linux/bpf.h | 13 +++++++++++++
 include/net/sock.h  |  3 +++
 net/core/sock.c     | 30 +++++++++++++++++++++++++++---
 3 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a627a02cf8ab..39bd36359c1e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1966,6 +1966,15 @@ static inline bool unprivileged_ebpf_enabled(void)
 	return !sysctl_unprivileged_bpf_disabled;
 }
 
+/* Not all bpf prog type has the bpf_ctx.
+ * For the bpf prog type that has initialized the bpf_ctx,
+ * this function can be used to decide if a kernel function
+ * is called by a bpf program.
+ */
+static inline bool has_current_bpf_ctx(void)
+{
+	return !!current->bpf_ctx;
+}
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -2175,6 +2184,10 @@ static inline bool unprivileged_ebpf_enabled(void)
 	return false;
 }
 
+static inline bool has_current_bpf_ctx(void)
+{
+	return false;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
diff --git a/include/net/sock.h b/include/net/sock.h
index a7273b289188..b2ff230860c6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1721,6 +1721,9 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow)
 	}
 }
 
+void sockopt_lock_sock(struct sock *sk);
+void sockopt_release_sock(struct sock *sk);
+
 /* Used by processes to "lock" a socket state, so that
  * interrupts and bottom half handlers won't change it
  * from under us. It essentially blocks any incoming
diff --git a/net/core/sock.c b/net/core/sock.c
index 20269c37ab3b..d3683228376f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -703,7 +703,9 @@ static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen)
 			goto out;
 	}
 
-	return sock_bindtoindex(sk, index, true);
+	sockopt_lock_sock(sk);
+	ret = sock_bindtoindex_locked(sk, index);
+	sockopt_release_sock(sk);
 out:
 #endif
 
@@ -1036,6 +1038,28 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+void sockopt_lock_sock(struct sock *sk)
+{
+	/* When current->bpf_ctx is set, the setsockopt is called from
+	 * a bpf prog.  bpf has ensured the sk lock has been
+	 * acquired before calling setsockopt().
+	 */
+	if (has_current_bpf_ctx())
+		return;
+
+	lock_sock(sk);
+}
+EXPORT_SYMBOL(sockopt_lock_sock);
+
+void sockopt_release_sock(struct sock *sk)
+{
+	if (has_current_bpf_ctx())
+		return;
+
+	release_sock(sk);
+}
+EXPORT_SYMBOL(sockopt_release_sock);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -1067,7 +1091,7 @@ static int sk_setsockopt(struct sock *sk, int level, int optname,
 
 	valbool = val ? 1 : 0;
 
-	lock_sock(sk);
+	sockopt_lock_sock(sk);
 
 	switch (optname) {
 	case SO_DEBUG:
@@ -1496,7 +1520,7 @@ static int sk_setsockopt(struct sock *sk, int level, int optname,
 		ret = -ENOPROTOOPT;
 		break;
 	}
-	release_sock(sk);
+	sockopt_release_sock(sk);
 	return ret;
 }
 
-- 
2.30.2