From 24426654ed3ae83d1127511891fb782c54f49203 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 16 Aug 2022 23:17:17 -0700
Subject: bpf: net: Avoid sk_setsockopt() taking sk lock when called from bpf

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@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220817061717.4175589-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/sock.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index 05a1bbdf5805..352b9458fdc6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1749,6 +1749,9 @@ 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
-- 
cgit v1.2.3


From e42c7beee71d0d84a6193357e3525d0cf2a3e168 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 16 Aug 2022 23:17:23 -0700
Subject: bpf: net: Consider has_current_bpf_ctx() when testing capable() in
 sk_setsockopt()

When bpf program calling bpf_setsockopt(SOL_SOCKET),
it could be run in softirq and doesn't make sense to do the capable
check.  There was a similar situation in bpf_setsockopt(TCP_CONGESTION).
In commit 8d650cdedaab ("tcp: fix tcp_set_congestion_control() use from bpf hook"),
tcp_set_congestion_control(..., cap_net_admin) was added to skip
the cap check for bpf prog.

This patch adds sockopt_ns_capable() and sockopt_capable() for
the sk_setsockopt() to use.  They will consider the
has_current_bpf_ctx() before doing the ns_capable() and capable() test.
They are in EXPORT_SYMBOL for the ipv6 module to use in a latter patch.

Suggested-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220817061723.4175820-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/sock.h |  2 ++
 net/core/sock.c    | 38 +++++++++++++++++++++++++-------------
 2 files changed, 27 insertions(+), 13 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index 352b9458fdc6..13089d88a2e2 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1751,6 +1751,8 @@ 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);
+bool sockopt_ns_capable(struct user_namespace *ns, int cap);
+bool sockopt_capable(int cap);
 
 /* Used by processes to "lock" a socket state, so that
  * interrupts and bottom half handlers won't change it
diff --git a/net/core/sock.c b/net/core/sock.c
index d3683228376f..7ea46e4700fd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1060,6 +1060,18 @@ void sockopt_release_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(sockopt_release_sock);
 
+bool sockopt_ns_capable(struct user_namespace *ns, int cap)
+{
+	return has_current_bpf_ctx() || ns_capable(ns, cap);
+}
+EXPORT_SYMBOL(sockopt_ns_capable);
+
+bool sockopt_capable(int cap)
+{
+	return has_current_bpf_ctx() || capable(cap);
+}
+EXPORT_SYMBOL(sockopt_capable);
+
 /*
  *	This is meant for all protocols to use and covers goings on
  *	at the socket level. Everything here is generic.
@@ -1095,7 +1107,7 @@ static int sk_setsockopt(struct sock *sk, int level, int optname,
 
 	switch (optname) {
 	case SO_DEBUG:
-		if (val && !capable(CAP_NET_ADMIN))
+		if (val && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EACCES;
 		else
 			sock_valbool_flag(sk, SOCK_DBG, valbool);
@@ -1139,7 +1151,7 @@ set_sndbuf:
 		break;
 
 	case SO_SNDBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1161,7 +1173,7 @@ set_sndbuf:
 		break;
 
 	case SO_RCVBUFFORCE:
-		if (!capable(CAP_NET_ADMIN)) {
+		if (!sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1188,8 +1200,8 @@ set_sndbuf:
 
 	case SO_PRIORITY:
 		if ((val >= 0 && val <= 6) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
-		    ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
+		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
 			sk->sk_priority = val;
 		else
 			ret = -EPERM;
@@ -1334,8 +1346,8 @@ set_sndbuf:
 			clear_bit(SOCK_PASSSEC, &sock->flags);
 		break;
 	case SO_MARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1343,8 +1355,8 @@ set_sndbuf:
 		__sock_set_mark(sk, val);
 		break;
 	case SO_RCVMARK:
-		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
@@ -1378,7 +1390,7 @@ set_sndbuf:
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	case SO_BUSY_POLL:
 		/* allow unprivileged users to decrease the value */
-		if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
+		if ((val > sk->sk_ll_usec) && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else {
 			if (val < 0)
@@ -1388,13 +1400,13 @@ set_sndbuf:
 		}
 		break;
 	case SO_PREFER_BUSY_POLL:
-		if (valbool && !capable(CAP_NET_ADMIN))
+		if (valbool && !sockopt_capable(CAP_NET_ADMIN))
 			ret = -EPERM;
 		else
 			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
 		break;
 	case SO_BUSY_POLL_BUDGET:
-		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !sockopt_capable(CAP_NET_ADMIN)) {
 			ret = -EPERM;
 		} else {
 			if (val < 0 || val > U16_MAX)
@@ -1465,7 +1477,7 @@ set_sndbuf:
 		 * scheduler has enough safe guards.
 		 */
 		if (sk_txtime.clockid != CLOCK_MONOTONIC &&
-		    !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
 			ret = -EPERM;
 			break;
 		}
-- 
cgit v1.2.3


From 29003875bd5bab262a29d1c6e76a2124bd07e4c2 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 16 Aug 2022 23:18:04 -0700
Subject: bpf: Change bpf_setsockopt(SOL_SOCKET) to reuse sk_setsockopt()

After the prep work in the previous patches,
this patch removes most of the dup code from bpf_setsockopt(SOL_SOCKET)
and reuses them from sk_setsockopt().

The sock ptr test is added to the SO_RCVLOWAT because
the sk->sk_socket could be NULL in some of the bpf hooks.

The existing optname white-list is refactored into a new
function sol_socket_setsockopt().

Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220817061804.4178920-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/sock.h |   2 +
 net/core/filter.c  | 124 +++++++++++++----------------------------------------
 net/core/sock.c    |   6 +--
 3 files changed, 34 insertions(+), 98 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index 13089d88a2e2..ee44b424d952 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1828,6 +1828,8 @@ void sock_pfree(struct sk_buff *skb);
 #define sock_edemux sock_efree
 #endif
 
+int sk_setsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, unsigned int optlen);
 int sock_setsockopt(struct socket *sock, int level, int op,
 		    sockptr_t optval, unsigned int optlen);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index a663d7b96bad..6f5bcc8df487 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5013,109 +5013,43 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+static int sol_socket_setsockopt(struct sock *sk, int optname,
+				 char *optval, int optlen)
+{
+	switch (optname) {
+	case SO_SNDBUF:
+	case SO_RCVBUF:
+	case SO_KEEPALIVE:
+	case SO_PRIORITY:
+	case SO_REUSEPORT:
+	case SO_RCVLOWAT:
+	case SO_MARK:
+	case SO_MAX_PACING_RATE:
+	case SO_BINDTOIFINDEX:
+	case SO_TXREHASH:
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	case SO_BINDTODEVICE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sk_setsockopt(sk, SOL_SOCKET, optname,
+			     KERNEL_SOCKPTR(optval), optlen);
+}
+
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
-	char devname[IFNAMSIZ];
-	int val, valbool;
-	struct net *net;
-	int ifindex;
-	int ret = 0;
+	int val, ret = 0;
 
 	if (!sk_fullsock(sk))
 		return -EINVAL;
 
 	if (level == SOL_SOCKET) {
-		if (optlen != sizeof(int) && optname != SO_BINDTODEVICE)
-			return -EINVAL;
-		val = *((int *)optval);
-		valbool = val ? 1 : 0;
-
-		/* Only some socketops are supported */
-		switch (optname) {
-		case SO_RCVBUF:
-			val = min_t(u32, val, sysctl_rmem_max);
-			val = min_t(int, val, INT_MAX / 2);
-			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
-			WRITE_ONCE(sk->sk_rcvbuf,
-				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
-			break;
-		case SO_SNDBUF:
-			val = min_t(u32, val, sysctl_wmem_max);
-			val = min_t(int, val, INT_MAX / 2);
-			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-			WRITE_ONCE(sk->sk_sndbuf,
-				   max_t(int, val * 2, SOCK_MIN_SNDBUF));
-			break;
-		case SO_MAX_PACING_RATE: /* 32bit version */
-			if (val != ~0U)
-				cmpxchg(&sk->sk_pacing_status,
-					SK_PACING_NONE,
-					SK_PACING_NEEDED);
-			sk->sk_max_pacing_rate = (val == ~0U) ?
-						 ~0UL : (unsigned int)val;
-			sk->sk_pacing_rate = min(sk->sk_pacing_rate,
-						 sk->sk_max_pacing_rate);
-			break;
-		case SO_PRIORITY:
-			sk->sk_priority = val;
-			break;
-		case SO_RCVLOWAT:
-			if (val < 0)
-				val = INT_MAX;
-			if (sk->sk_socket && sk->sk_socket->ops->set_rcvlowat)
-				ret = sk->sk_socket->ops->set_rcvlowat(sk, val);
-			else
-				WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
-			break;
-		case SO_MARK:
-			if (sk->sk_mark != val) {
-				sk->sk_mark = val;
-				sk_dst_reset(sk);
-			}
-			break;
-		case SO_BINDTODEVICE:
-			optlen = min_t(long, optlen, IFNAMSIZ - 1);
-			strncpy(devname, optval, optlen);
-			devname[optlen] = 0;
-
-			ifindex = 0;
-			if (devname[0] != '\0') {
-				struct net_device *dev;
-
-				ret = -ENODEV;
-
-				net = sock_net(sk);
-				dev = dev_get_by_name(net, devname);
-				if (!dev)
-					break;
-				ifindex = dev->ifindex;
-				dev_put(dev);
-			}
-			fallthrough;
-		case SO_BINDTOIFINDEX:
-			if (optname == SO_BINDTOIFINDEX)
-				ifindex = val;
-			ret = sock_bindtoindex(sk, ifindex, false);
-			break;
-		case SO_KEEPALIVE:
-			if (sk->sk_prot->keepalive)
-				sk->sk_prot->keepalive(sk, valbool);
-			sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
-			break;
-		case SO_REUSEPORT:
-			sk->sk_reuseport = valbool;
-			break;
-		case SO_TXREHASH:
-			if (val < -1 || val > 1) {
-				ret = -EINVAL;
-				break;
-			}
-			sk->sk_txrehash = (u8)val;
-			break;
-		default:
-			ret = -EINVAL;
-		}
+		return sol_socket_setsockopt(sk, optname, optval, optlen);
 	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) {
 		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
 			return -EINVAL;
diff --git a/net/core/sock.c b/net/core/sock.c
index 7ea46e4700fd..2a6f84702eb9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1077,8 +1077,8 @@ EXPORT_SYMBOL(sockopt_capable);
  *	at the socket level. Everything here is generic.
  */
 
-static int sk_setsockopt(struct sock *sk, int level, int optname,
-			 sockptr_t optval, unsigned int optlen)
+int sk_setsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, unsigned int optlen)
 {
 	struct so_timestamping timestamping;
 	struct socket *sock = sk->sk_socket;
@@ -1264,7 +1264,7 @@ set_sndbuf:
 	case SO_RCVLOWAT:
 		if (val < 0)
 			val = INT_MAX;
-		if (sock->ops->set_rcvlowat)
+		if (sock && sock->ops->set_rcvlowat)
 			ret = sock->ops->set_rcvlowat(sk, val);
 		else
 			WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
-- 
cgit v1.2.3


From 0c751f7071ef98d334ed06ca3f8f4cc1f7458cf5 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 16 Aug 2022 23:18:19 -0700
Subject: bpf: Change bpf_setsockopt(SOL_TCP) to reuse do_tcp_setsockopt()

After the prep work in the previous patches,
this patch removes all the dup code from bpf_setsockopt(SOL_TCP)
and reuses the do_tcp_setsockopt().

The existing optname white-list is refactored into a new
function sol_tcp_setsockopt().  The sol_tcp_setsockopt()
also calls the bpf_sol_tcp_setsockopt() to handle
the TCP_BPF_XXX specific optnames.

bpf_setsockopt(TCP_SAVE_SYN) now also allows a value 2 to
save the eth header also and it comes for free from
do_tcp_setsockopt().

Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220817061819.4180146-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/tcp.h |  2 ++
 net/core/filter.c | 97 +++++++++++++++++--------------------------------------
 net/ipv4/tcp.c    |  4 +--
 3 files changed, 34 insertions(+), 69 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d10962b9f0d0..c03a50c72f40 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -405,6 +405,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock,
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 bool tcp_bpf_bypass_getsockopt(int level, int optname);
+int do_tcp_setsockopt(struct sock *sk, int level, int optname,
+		      sockptr_t optval, unsigned int optlen);
 int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen);
 void tcp_set_keepalive(struct sock *sk, int val);
diff --git a/net/core/filter.c b/net/core/filter.c
index bb135d456a53..66877605bb78 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5086,6 +5086,34 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
 	return 0;
 }
 
+static int sol_tcp_setsockopt(struct sock *sk, int optname,
+			      char *optval, int optlen)
+{
+	if (sk->sk_prot->setsockopt != tcp_setsockopt)
+		return -EINVAL;
+
+	switch (optname) {
+	case TCP_KEEPIDLE:
+	case TCP_KEEPINTVL:
+	case TCP_KEEPCNT:
+	case TCP_SYNCNT:
+	case TCP_WINDOW_CLAMP:
+	case TCP_USER_TIMEOUT:
+	case TCP_NOTSENT_LOWAT:
+	case TCP_SAVE_SYN:
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	case TCP_CONGESTION:
+		break;
+	default:
+		return bpf_sol_tcp_setsockopt(sk, optname, optval, optlen);
+	}
+
+	return do_tcp_setsockopt(sk, SOL_TCP, optname,
+				 KERNEL_SOCKPTR(optval), optlen);
+}
+
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
@@ -5138,73 +5166,8 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 		default:
 			ret = -EINVAL;
 		}
-	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
-		   sk->sk_prot->setsockopt == tcp_setsockopt) {
-		if (optname >= TCP_BPF_IW)
-			return bpf_sol_tcp_setsockopt(sk, optname,
-						      optval, optlen);
-
-		if (optname == TCP_CONGESTION) {
-			char name[TCP_CA_NAME_MAX];
-
-			strncpy(name, optval, min_t(long, optlen,
-						    TCP_CA_NAME_MAX-1));
-			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false, true);
-		} else {
-			struct inet_connection_sock *icsk = inet_csk(sk);
-			struct tcp_sock *tp = tcp_sk(sk);
-
-			if (optlen != sizeof(int))
-				return -EINVAL;
-
-			val = *((int *)optval);
-			/* Only some options are supported */
-			switch (optname) {
-			case TCP_SAVE_SYN:
-				if (val < 0 || val > 1)
-					ret = -EINVAL;
-				else
-					tp->save_syn = val;
-				break;
-			case TCP_KEEPIDLE:
-				ret = tcp_sock_set_keepidle_locked(sk, val);
-				break;
-			case TCP_KEEPINTVL:
-				if (val < 1 || val > MAX_TCP_KEEPINTVL)
-					ret = -EINVAL;
-				else
-					tp->keepalive_intvl = val * HZ;
-				break;
-			case TCP_KEEPCNT:
-				if (val < 1 || val > MAX_TCP_KEEPCNT)
-					ret = -EINVAL;
-				else
-					tp->keepalive_probes = val;
-				break;
-			case TCP_SYNCNT:
-				if (val < 1 || val > MAX_TCP_SYNCNT)
-					ret = -EINVAL;
-				else
-					icsk->icsk_syn_retries = val;
-				break;
-			case TCP_USER_TIMEOUT:
-				if (val < 0)
-					ret = -EINVAL;
-				else
-					icsk->icsk_user_timeout = val;
-				break;
-			case TCP_NOTSENT_LOWAT:
-				tp->notsent_lowat = val;
-				sk->sk_write_space(sk);
-				break;
-			case TCP_WINDOW_CLAMP:
-				ret = tcp_set_window_clamp(sk, val);
-				break;
-			default:
-				ret = -EINVAL;
-			}
-		}
+	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) {
+		return sol_tcp_setsockopt(sk, optname, optval, optlen);
 	} else {
 		ret = -EINVAL;
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cfed84b1883f..a6986f201f92 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3479,8 +3479,8 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 /*
  *	Socket option code for TCP.
  */
-static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
-		sockptr_t optval, unsigned int optlen)
+int do_tcp_setsockopt(struct sock *sk, int level, int optname,
+		      sockptr_t optval, unsigned int optlen)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
-- 
cgit v1.2.3


From ee7f1e1302f5cb29168f70827c12855f1d8c9845 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 16 Aug 2022 23:18:26 -0700
Subject: bpf: Change bpf_setsockopt(SOL_IP) to reuse do_ip_setsockopt()

After the prep work in the previous patches,
this patch removes the dup code from bpf_setsockopt(SOL_IP)
and reuses the implementation in do_ip_setsockopt().

The existing optname white-list is refactored into a new
function sol_ip_setsockopt().

NOTE,
the current bpf_setsockopt(IP_TOS) is quite different from the
the do_ip_setsockopt(IP_TOS).  For example, it does not take
the INET_ECN_MASK into the account for tcp and also does not adjust
sk->sk_priority.  It looks like the current bpf_setsockopt(IP_TOS)
was referencing the IPV6_TCLASS implementation instead of IP_TOS.
This patch tries to rectify that by using the do_ip_setsockopt(IP_TOS).
While this is a behavior change,  the do_ip_setsockopt(IP_TOS) behavior
is arguably what the user is expecting.  At least, the INET_ECN_MASK bits
should be masked out for tcp.

Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220817061826.4180990-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/ip.h       |  2 ++
 net/core/filter.c      | 40 ++++++++++++++++++++--------------------
 net/ipv4/ip_sockglue.c |  4 ++--
 3 files changed, 24 insertions(+), 22 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ip.h b/include/net/ip.h
index 1c979fd1904c..34fa5b0f0a0e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -743,6 +743,8 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 DECLARE_STATIC_KEY_FALSE(ip4_min_ttl);
+int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		     unsigned int optlen);
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		  unsigned int optlen);
 int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
diff --git a/net/core/filter.c b/net/core/filter.c
index 66877605bb78..4d1b42b8f4a8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5114,6 +5114,25 @@ static int sol_tcp_setsockopt(struct sock *sk, int optname,
 				 KERNEL_SOCKPTR(optval), optlen);
 }
 
+static int sol_ip_setsockopt(struct sock *sk, int optname,
+			     char *optval, int optlen)
+{
+	if (sk->sk_family != AF_INET)
+		return -EINVAL;
+
+	switch (optname) {
+	case IP_TOS:
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return do_ip_setsockopt(sk, SOL_IP, optname,
+				KERNEL_SOCKPTR(optval), optlen);
+}
+
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
@@ -5125,26 +5144,7 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 	if (level == SOL_SOCKET) {
 		return sol_socket_setsockopt(sk, optname, optval, optlen);
 	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) {
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
-			return -EINVAL;
-
-		val = *((int *)optval);
-		/* Only some options are supported */
-		switch (optname) {
-		case IP_TOS:
-			if (val < -1 || val > 0xff) {
-				ret = -EINVAL;
-			} else {
-				struct inet_sock *inet = inet_sk(sk);
-
-				if (val == -1)
-					val = 0;
-				inet->tos = val;
-			}
-			break;
-		default:
-			ret = -EINVAL;
-		}
+		return sol_ip_setsockopt(sk, optname, optval, optlen);
 	} else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) {
 		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
 			return -EINVAL;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index a3c496580e6b..751fa69cb557 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -888,8 +888,8 @@ static int compat_ip_mcast_join_leave(struct sock *sk, int optname,
 
 DEFINE_STATIC_KEY_FALSE(ip4_min_ttl);
 
-static int do_ip_setsockopt(struct sock *sk, int level, int optname,
-		sockptr_t optval, unsigned int optlen)
+int do_ip_setsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, unsigned int optlen)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
-- 
cgit v1.2.3


From 75b64b68ee3f9fe90ad8f21e5c5c92de58abf725 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 16 Aug 2022 23:18:34 -0700
Subject: bpf: Change bpf_setsockopt(SOL_IPV6) to reuse do_ipv6_setsockopt()

After the prep work in the previous patches,
this patch removes the dup code from bpf_setsockopt(SOL_IPV6)
and reuses the implementation in do_ipv6_setsockopt().

ipv6 could be compiled as a module.  Like how other code solved it
with stubs in ipv6_stubs.h, this patch adds the do_ipv6_setsockopt
to the ipv6_bpf_stub.

The current bpf_setsockopt(IPV6_TCLASS) does not take the
INET_ECN_MASK into the account for tcp.  The
do_ipv6_setsockopt(IPV6_TCLASS) will handle it correctly.

The existing optname white-list is refactored into a new
function sol_ipv6_setsockopt().

After this last SOL_IPV6 dup code removal, the __bpf_setsockopt()
is simplified enough that the extra "{ }" around the if statement
can be removed.

Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/r/20220817061834.4181198-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/ipv6.h       |  2 ++
 include/net/ipv6_stubs.h |  2 ++
 net/core/filter.c        | 56 ++++++++++++++++++++++--------------------------
 net/ipv6/af_inet6.c      |  1 +
 net/ipv6/ipv6_sockglue.c |  4 ++--
 5 files changed, 33 insertions(+), 32 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index de9dcc5652c4..c110d9032083 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1156,6 +1156,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
  */
 DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount);
 
+int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
+		       unsigned int optlen);
 int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		    unsigned int optlen);
 int ipv6_getsockopt(struct sock *sk, int level, int optname,
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 45e0339be6fa..8692698b01cf 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -81,6 +81,8 @@ struct ipv6_bpf_stub {
 				     const struct in6_addr *daddr, __be16 dport,
 				     int dif, int sdif, struct udp_table *tbl,
 				     struct sk_buff *skb);
+	int (*ipv6_setsockopt)(struct sock *sk, int level, int optname,
+			       sockptr_t optval, unsigned int optlen);
 };
 extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 4d1b42b8f4a8..23282b8cf61e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5133,45 +5133,41 @@ static int sol_ip_setsockopt(struct sock *sk, int optname,
 				KERNEL_SOCKPTR(optval), optlen);
 }
 
+static int sol_ipv6_setsockopt(struct sock *sk, int optname,
+			       char *optval, int optlen)
+{
+	if (sk->sk_family != AF_INET6)
+		return -EINVAL;
+
+	switch (optname) {
+	case IPV6_TCLASS:
+		if (optlen != sizeof(int))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return ipv6_bpf_stub->ipv6_setsockopt(sk, SOL_IPV6, optname,
+					      KERNEL_SOCKPTR(optval), optlen);
+}
+
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
-	int val, ret = 0;
-
 	if (!sk_fullsock(sk))
 		return -EINVAL;
 
-	if (level == SOL_SOCKET) {
+	if (level == SOL_SOCKET)
 		return sol_socket_setsockopt(sk, optname, optval, optlen);
-	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) {
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP)
 		return sol_ip_setsockopt(sk, optname, optval, optlen);
-	} else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) {
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
-			return -EINVAL;
-
-		val = *((int *)optval);
-		/* Only some options are supported */
-		switch (optname) {
-		case IPV6_TCLASS:
-			if (val < -1 || val > 0xff) {
-				ret = -EINVAL;
-			} else {
-				struct ipv6_pinfo *np = inet6_sk(sk);
-
-				if (val == -1)
-					val = 0;
-				np->tclass = val;
-			}
-			break;
-		default:
-			ret = -EINVAL;
-		}
-	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) {
+	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
+		return sol_ipv6_setsockopt(sk, optname, optval, optlen);
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP)
 		return sol_tcp_setsockopt(sk, optname, optval, optlen);
-	} else {
-		ret = -EINVAL;
-	}
-	return ret;
+
+	return -EINVAL;
 }
 
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2ce0c44d0081..cadc97852787 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1057,6 +1057,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
 	.inet6_bind = __inet6_bind,
 	.udp6_lib_lookup = __udp6_lib_lookup,
+	.ipv6_setsockopt = do_ipv6_setsockopt,
 };
 
 static int __init inet6_init(void)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d23de48ff612..a4535bdbd310 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -391,8 +391,8 @@ sticky_done:
 	return err;
 }
 
-static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
-		   sockptr_t optval, unsigned int optlen)
+int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, unsigned int optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
-- 
cgit v1.2.3


From 6dadbe4bac68309eb46ab0f30e8ff47a789df49a Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Thu, 1 Sep 2022 17:28:53 -0700
Subject: bpf: net: Change do_ipv6_getsockopt() to take the sockptr_t argument

Similar to the earlier patch that changes sk_getsockopt() to
take the sockptr_t argument .  This patch also changes
do_ipv6_getsockopt() to take the sockptr_t argument such that
a latter patch can make bpf_getsockopt(SOL_IPV6) to reuse
do_ipv6_getsockopt().

Note on the change in ip6_mc_msfget().  This function is to
return an array of sockaddr_storage in optval.  This function
is shared between ipv6_get_msfilter() and compat_ipv6_get_msfilter().
However, the sockaddr_storage is stored at different offset of the
optval because of the difference between group_filter and
compat_group_filter.  Thus, a new 'ss_offset' argument is
added to ip6_mc_msfget().

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20220902002853.2892532-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/mroute6.h  |  4 +--
 include/net/ipv6.h       |  2 +-
 net/ipv6/ip6mr.c         | 10 +++----
 net/ipv6/ipv6_sockglue.c | 69 ++++++++++++++++++++++++++----------------------
 net/ipv6/mcast.c         |  8 +++---
 5 files changed, 50 insertions(+), 43 deletions(-)

(limited to 'include/net')

diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index bc351a85ce9b..8f2b307fb124 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -27,7 +27,7 @@ struct sock;
 
 #ifdef CONFIG_IPV6_MROUTE
 extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int);
-extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
+extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t);
 extern int ip6_mr_input(struct sk_buff *skb);
 extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg);
 extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
@@ -42,7 +42,7 @@ static inline int ip6_mroute_setsockopt(struct sock *sock, int optname,
 
 static inline
 int ip6_mroute_getsockopt(struct sock *sock,
-			  int optname, char __user *optval, int __user *optlen)
+			  int optname, sockptr_t optval, sockptr_t optlen)
 {
 	return -ENOPROTOOPT;
 }
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index c110d9032083..a4f24573ed7a 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1209,7 +1209,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk,
 int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf,
 		  struct sockaddr_storage *list);
 int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
-		  struct sockaddr_storage __user *p);
+		  sockptr_t optval, size_t ss_offset);
 
 #ifdef CONFIG_PROC_FS
 int ac6_proc_init(struct net *net);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index a9ba41648e36..516e83b52f26 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1827,8 +1827,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
  *	Getsock opt support for the multicast routing system.
  */
 
-int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
-			  int __user *optlen)
+int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
+			  sockptr_t optlen)
 {
 	int olr;
 	int val;
@@ -1859,16 +1859,16 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
 		return -ENOPROTOOPT;
 	}
 
-	if (get_user(olr, optlen))
+	if (copy_from_sockptr(&olr, optlen, sizeof(int)))
 		return -EFAULT;
 
 	olr = min_t(int, olr, sizeof(int));
 	if (olr < 0)
 		return -EINVAL;
 
-	if (put_user(olr, optlen))
+	if (copy_to_sockptr(optlen, &olr, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, olr))
+	if (copy_to_sockptr(optval, &val, olr))
 		return -EFAULT;
 	return 0;
 }
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4ab284a4adf8..4d9fadef2d3e 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1030,7 +1030,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 EXPORT_SYMBOL(ipv6_setsockopt);
 
 static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
-				  int optname, char __user *optval, int len)
+				  int optname, sockptr_t optval, int len)
 {
 	struct ipv6_opt_hdr *hdr;
 
@@ -1058,45 +1058,44 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt,
 		return 0;
 
 	len = min_t(unsigned int, len, ipv6_optlen(hdr));
-	if (copy_to_user(optval, hdr, len))
+	if (copy_to_sockptr(optval, hdr, len))
 		return -EFAULT;
 	return len;
 }
 
-static int ipv6_get_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen, int len)
+static int ipv6_get_msfilter(struct sock *sk, sockptr_t optval,
+			     sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct group_filter, gf_slist_flex);
-	struct group_filter __user *p = optval;
 	struct group_filter gsf;
 	int num;
 	int err;
 
 	if (len < size0)
 		return -EINVAL;
-	if (copy_from_user(&gsf, p, size0))
+	if (copy_from_sockptr(&gsf, optval, size0))
 		return -EFAULT;
 	if (gsf.gf_group.ss_family != AF_INET6)
 		return -EADDRNOTAVAIL;
 	num = gsf.gf_numsrc;
 	lock_sock(sk);
-	err = ip6_mc_msfget(sk, &gsf, p->gf_slist_flex);
+	err = ip6_mc_msfget(sk, &gsf, optval, size0);
 	if (!err) {
 		if (num > gsf.gf_numsrc)
 			num = gsf.gf_numsrc;
-		if (put_user(GROUP_FILTER_SIZE(num), optlen) ||
-		    copy_to_user(p, &gsf, size0))
+		len = GROUP_FILTER_SIZE(num);
+		if (copy_to_sockptr(optlen, &len, sizeof(int)) ||
+		    copy_to_sockptr(optval, &gsf, size0))
 			err = -EFAULT;
 	}
 	release_sock(sk);
 	return err;
 }
 
-static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval,
-		int __user *optlen, int len)
+static int compat_ipv6_get_msfilter(struct sock *sk, sockptr_t optval,
+				    sockptr_t optlen, int len)
 {
 	const int size0 = offsetof(struct compat_group_filter, gf_slist_flex);
-	struct compat_group_filter __user *p = optval;
 	struct compat_group_filter gf32;
 	struct group_filter gf;
 	int err;
@@ -1105,7 +1104,7 @@ static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval,
 	if (len < size0)
 		return -EINVAL;
 
-	if (copy_from_user(&gf32, p, size0))
+	if (copy_from_sockptr(&gf32, optval, size0))
 		return -EFAULT;
 	gf.gf_interface = gf32.gf_interface;
 	gf.gf_fmode = gf32.gf_fmode;
@@ -1116,22 +1115,24 @@ static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval,
 		return -EADDRNOTAVAIL;
 
 	lock_sock(sk);
-	err = ip6_mc_msfget(sk, &gf, p->gf_slist_flex);
+	err = ip6_mc_msfget(sk, &gf, optval, size0);
 	release_sock(sk);
 	if (err)
 		return err;
 	if (num > gf.gf_numsrc)
 		num = gf.gf_numsrc;
 	len = GROUP_FILTER_SIZE(num) - (sizeof(gf)-sizeof(gf32));
-	if (put_user(len, optlen) ||
-	    put_user(gf.gf_fmode, &p->gf_fmode) ||
-	    put_user(gf.gf_numsrc, &p->gf_numsrc))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode),
+				   &gf.gf_fmode, sizeof(gf32.gf_fmode)) ||
+	    copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc),
+				   &gf.gf_numsrc, sizeof(gf32.gf_numsrc)))
 		return -EFAULT;
 	return 0;
 }
 
 static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
-		    char __user *optval, int __user *optlen)
+			      sockptr_t optval, sockptr_t optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	int len;
@@ -1140,7 +1141,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 	if (ip6_mroute_opt(optname))
 		return ip6_mroute_getsockopt(sk, optname, optval, optlen);
 
-	if (get_user(len, optlen))
+	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 	switch (optname) {
 	case IPV6_ADDRFORM:
@@ -1164,10 +1165,15 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (sk->sk_type != SOCK_STREAM)
 			return -ENOPROTOOPT;
 
-		msg.msg_control_user = optval;
+		if (optval.is_kernel) {
+			msg.msg_control_is_user = false;
+			msg.msg_control = optval.kernel;
+		} else {
+			msg.msg_control_is_user = true;
+			msg.msg_control_user = optval.user;
+		}
 		msg.msg_controllen = len;
 		msg.msg_flags = 0;
-		msg.msg_control_is_user = true;
 
 		lock_sock(sk);
 		skb = np->pktoptions;
@@ -1210,7 +1216,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 			}
 		}
 		len -= msg.msg_controllen;
-		return put_user(len, optlen);
+		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
 	case IPV6_MTU:
 	{
@@ -1270,7 +1276,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		/* check if ipv6_getsockopt_sticky() returns err code */
 		if (len < 0)
 			return len;
-		return put_user(len, optlen);
+		return copy_to_sockptr(optlen, &len, sizeof(int));
 	}
 
 	case IPV6_RECVHOPOPTS:
@@ -1324,9 +1330,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (!mtuinfo.ip6m_mtu)
 			return -ENOTCONN;
 
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &mtuinfo, len))
+		if (copy_to_sockptr(optval, &mtuinfo, len))
 			return -EFAULT;
 
 		return 0;
@@ -1403,7 +1409,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (len < sizeof(freq))
 			return -EINVAL;
 
-		if (copy_from_user(&freq, optval, sizeof(freq)))
+		if (copy_from_sockptr(&freq, optval, sizeof(freq)))
 			return -EFAULT;
 
 		if (freq.flr_action != IPV6_FL_A_GET)
@@ -1418,9 +1424,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (val < 0)
 			return val;
 
-		if (put_user(len, optlen))
+		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_user(optval, &freq, len))
+		if (copy_to_sockptr(optval, &freq, len))
 			return -EFAULT;
 
 		return 0;
@@ -1472,9 +1478,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		return -ENOPROTOOPT;
 	}
 	len = min_t(unsigned int, sizeof(int), len);
-	if (put_user(len, optlen))
+	if (copy_to_sockptr(optlen, &len, sizeof(int)))
 		return -EFAULT;
-	if (copy_to_user(optval, &val, len))
+	if (copy_to_sockptr(optval, &val, len))
 		return -EFAULT;
 	return 0;
 }
@@ -1490,7 +1496,8 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
 
-	err = do_ipv6_getsockopt(sk, level, optname, optval, optlen);
+	err = do_ipv6_getsockopt(sk, level, optname,
+				 USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IPV6_2292PKTOPTIONS) {
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 87c699d57b36..0566ab03ddbe 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -580,7 +580,7 @@ done:
 }
 
 int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
-		  struct sockaddr_storage __user *p)
+		  sockptr_t optval, size_t ss_offset)
 {
 	struct ipv6_pinfo *inet6 = inet6_sk(sk);
 	const struct in6_addr *group;
@@ -612,8 +612,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 
 	copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc;
 	gsf->gf_numsrc = count;
-
-	for (i = 0; i < copycount; i++, p++) {
+	for (i = 0; i < copycount; i++) {
 		struct sockaddr_in6 *psin6;
 		struct sockaddr_storage ss;
 
@@ -621,8 +620,9 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 		memset(&ss, 0, sizeof(ss));
 		psin6->sin6_family = AF_INET6;
 		psin6->sin6_addr = psl->sl_addr[i];
-		if (copy_to_user(p, &ss, sizeof(ss)))
+		if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss)))
 			return -EFAULT;
+		ss_offset += sizeof(ss);
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 65ddc82d3b96be5555a36de4e2b4547433a00532 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Thu, 1 Sep 2022 17:29:12 -0700
Subject: bpf: Change bpf_getsockopt(SOL_SOCKET) to reuse sk_getsockopt()

This patch changes bpf_getsockopt(SOL_SOCKET) to reuse
sk_getsockopt().  It removes all duplicated code from
bpf_getsockopt(SOL_SOCKET).

Before this patch, there were some optnames available to
bpf_setsockopt(SOL_SOCKET) but missing in bpf_getsockopt(SOL_SOCKET).
It surprises users from time to time.  For example, SO_REUSEADDR,
SO_KEEPALIVE, SO_RCVLOWAT, and SO_MAX_PACING_RATE.  This patch
automatically closes this gap without duplicating more code.
The only exception is SO_BINDTODEVICE because it needs to acquire a
blocking lock.  Thus, SO_BINDTODEVICE is not supported.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20220902002912.2894040-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/sock.h |  2 ++
 net/core/filter.c  | 57 ++++++++++++++++++++++--------------------------------
 net/core/sock.c    |  4 ++--
 3 files changed, 27 insertions(+), 36 deletions(-)

(limited to 'include/net')

diff --git a/include/net/sock.h b/include/net/sock.h
index ee44b424d952..ea7965524133 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1833,6 +1833,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 int sock_setsockopt(struct socket *sock, int level, int op,
 		    sockptr_t optval, unsigned int optlen);
 
+int sk_getsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, sockptr_t optlen);
 int sock_getsockopt(struct socket *sock, int level, int op,
 		    char __user *optval, int __user *optlen);
 int sock_gettstamp(struct socket *sock, void __user *userstamp,
diff --git a/net/core/filter.c b/net/core/filter.c
index 55795815cc44..9b26653a7e1f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5017,8 +5017,9 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-static int sol_socket_setsockopt(struct sock *sk, int optname,
-				 char *optval, int optlen)
+static int sol_socket_sockopt(struct sock *sk, int optname,
+			      char *optval, int *optlen,
+			      bool getopt)
 {
 	switch (optname) {
 	case SO_REUSEADDR:
@@ -5032,7 +5033,7 @@ static int sol_socket_setsockopt(struct sock *sk, int optname,
 	case SO_MAX_PACING_RATE:
 	case SO_BINDTOIFINDEX:
 	case SO_TXREHASH:
-		if (optlen != sizeof(int))
+		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;
 	case SO_BINDTODEVICE:
@@ -5041,8 +5042,16 @@ static int sol_socket_setsockopt(struct sock *sk, int optname,
 		return -EINVAL;
 	}
 
+	if (getopt) {
+		if (optname == SO_BINDTODEVICE)
+			return -EINVAL;
+		return sk_getsockopt(sk, SOL_SOCKET, optname,
+				     KERNEL_SOCKPTR(optval),
+				     KERNEL_SOCKPTR(optlen));
+	}
+
 	return sk_setsockopt(sk, SOL_SOCKET, optname,
-			     KERNEL_SOCKPTR(optval), optlen);
+			     KERNEL_SOCKPTR(optval), *optlen);
 }
 
 static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
@@ -5168,7 +5177,7 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 		return -EINVAL;
 
 	if (level == SOL_SOCKET)
-		return sol_socket_setsockopt(sk, optname, optval, optlen);
+		return sol_socket_sockopt(sk, optname, optval, &optlen, false);
 	else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP)
 		return sol_ip_setsockopt(sk, optname, optval, optlen);
 	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
@@ -5190,38 +5199,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 static int __bpf_getsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
+	int err = 0, saved_optlen = optlen;
+
 	if (!sk_fullsock(sk))
 		goto err_clear;
 
 	if (level == SOL_SOCKET) {
-		if (optlen != sizeof(int))
-			goto err_clear;
-
-		switch (optname) {
-		case SO_RCVBUF:
-			*((int *)optval) = sk->sk_rcvbuf;
-			break;
-		case SO_SNDBUF:
-			*((int *)optval) = sk->sk_sndbuf;
-			break;
-		case SO_MARK:
-			*((int *)optval) = sk->sk_mark;
-			break;
-		case SO_PRIORITY:
-			*((int *)optval) = sk->sk_priority;
-			break;
-		case SO_BINDTOIFINDEX:
-			*((int *)optval) = sk->sk_bound_dev_if;
-			break;
-		case SO_REUSEPORT:
-			*((int *)optval) = sk->sk_reuseport;
-			break;
-		case SO_TXREHASH:
-			*((int *)optval) = sk->sk_txrehash;
-			break;
-		default:
-			goto err_clear;
-		}
+		err = sol_socket_sockopt(sk, optname, optval, &optlen, true);
 	} else if (IS_ENABLED(CONFIG_INET) &&
 		   level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
 		struct inet_connection_sock *icsk;
@@ -5278,7 +5262,12 @@ static int __bpf_getsockopt(struct sock *sk, int level, int optname,
 	} else {
 		goto err_clear;
 	}
-	return 0;
+
+	if (err)
+		optlen = 0;
+	if (optlen < saved_optlen)
+		memset(optval + optlen, 0, saved_optlen - optlen);
+	return err;
 err_clear:
 	memset(optval, 0, optlen);
 	return -EINVAL;
diff --git a/net/core/sock.c b/net/core/sock.c
index 7fa30fd4b37f..68e4662eb2eb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1583,8 +1583,8 @@ static int groups_to_user(sockptr_t dst, const struct group_info *src)
 	return 0;
 }
 
-static int sk_getsockopt(struct sock *sk, int level, int optname,
-			 sockptr_t optval, sockptr_t optlen)
+int sk_getsockopt(struct sock *sk, int level, int optname,
+		  sockptr_t optval, sockptr_t optlen)
 {
 	struct socket *sock = sk->sk_socket;
 
-- 
cgit v1.2.3


From 273b7f0fb44847c41814a59901977be284daa447 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Thu, 1 Sep 2022 17:29:18 -0700
Subject: bpf: Change bpf_getsockopt(SOL_TCP) to reuse do_tcp_getsockopt()

This patch changes bpf_getsockopt(SOL_TCP) to reuse
do_tcp_getsockopt().  It removes the duplicated code from
bpf_getsockopt(SOL_TCP).

Before this patch, there were some optnames available to
bpf_setsockopt(SOL_TCP) but missing in bpf_getsockopt(SOL_TCP).
For example, TCP_NODELAY, TCP_MAXSEG, TCP_KEEPIDLE, TCP_KEEPINTVL,
and a few more.  It surprises users from time to time.  This patch
automatically closes this gap without duplicating more code.

bpf_getsockopt(TCP_SAVED_SYN) does not free the saved_syn,
so it stays in sol_tcp_sockopt().

For string name value like TCP_CONGESTION, bpf expects it
is always null terminated, so sol_tcp_sockopt() decrements
optlen by one before calling do_tcp_getsockopt() and
the 'if (optlen < saved_optlen) memset(..,0,..);'
in __bpf_getsockopt() will always do a null termination.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20220902002918.2894511-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/tcp.h |  2 ++
 net/core/filter.c | 74 ++++++++++++++++++++++++++++++++-----------------------
 net/ipv4/tcp.c    |  4 +--
 3 files changed, 47 insertions(+), 33 deletions(-)

(limited to 'include/net')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c03a50c72f40..735e957f7f4b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -402,6 +402,8 @@ void tcp_init_sock(struct sock *sk);
 void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb);
 __poll_t tcp_poll(struct file *file, struct socket *sock,
 		      struct poll_table_struct *wait);
+int do_tcp_getsockopt(struct sock *sk, int level,
+		      int optname, sockptr_t optval, sockptr_t optlen);
 int tcp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen);
 bool tcp_bpf_bypass_getsockopt(int level, int optname);
diff --git a/net/core/filter.c b/net/core/filter.c
index 9b26653a7e1f..beadd5b83e6c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5100,8 +5100,9 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
 	return 0;
 }
 
-static int sol_tcp_setsockopt(struct sock *sk, int optname,
-			      char *optval, int optlen)
+static int sol_tcp_sockopt(struct sock *sk, int optname,
+			   char *optval, int *optlen,
+			   bool getopt)
 {
 	if (sk->sk_prot->setsockopt != tcp_setsockopt)
 		return -EINVAL;
@@ -5118,17 +5119,51 @@ static int sol_tcp_setsockopt(struct sock *sk, int optname,
 	case TCP_USER_TIMEOUT:
 	case TCP_NOTSENT_LOWAT:
 	case TCP_SAVE_SYN:
-		if (optlen != sizeof(int))
+		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;
 	case TCP_CONGESTION:
+		if (*optlen < 2)
+			return -EINVAL;
+		break;
+	case TCP_SAVED_SYN:
+		if (*optlen < 1)
+			return -EINVAL;
 		break;
 	default:
-		return bpf_sol_tcp_setsockopt(sk, optname, optval, optlen);
+		if (getopt)
+			return -EINVAL;
+		return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen);
+	}
+
+	if (getopt) {
+		if (optname == TCP_SAVED_SYN) {
+			struct tcp_sock *tp = tcp_sk(sk);
+
+			if (!tp->saved_syn ||
+			    *optlen > tcp_saved_syn_len(tp->saved_syn))
+				return -EINVAL;
+			memcpy(optval, tp->saved_syn->data, *optlen);
+			/* It cannot free tp->saved_syn here because it
+			 * does not know if the user space still needs it.
+			 */
+			return 0;
+		}
+
+		if (optname == TCP_CONGESTION) {
+			if (!inet_csk(sk)->icsk_ca_ops)
+				return -EINVAL;
+			/* BPF expects NULL-terminated tcp-cc string */
+			optval[--(*optlen)] = '\0';
+		}
+
+		return do_tcp_getsockopt(sk, SOL_TCP, optname,
+					 KERNEL_SOCKPTR(optval),
+					 KERNEL_SOCKPTR(optlen));
 	}
 
 	return do_tcp_setsockopt(sk, SOL_TCP, optname,
-				 KERNEL_SOCKPTR(optval), optlen);
+				 KERNEL_SOCKPTR(optval), *optlen);
 }
 
 static int sol_ip_setsockopt(struct sock *sk, int optname,
@@ -5183,7 +5218,7 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
 		return sol_ipv6_setsockopt(sk, optname, optval, optlen);
 	else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP)
-		return sol_tcp_setsockopt(sk, optname, optval, optlen);
+		return sol_tcp_sockopt(sk, optname, optval, &optlen, false);
 
 	return -EINVAL;
 }
@@ -5206,31 +5241,8 @@ static int __bpf_getsockopt(struct sock *sk, int level, int optname,
 
 	if (level == SOL_SOCKET) {
 		err = sol_socket_sockopt(sk, optname, optval, &optlen, true);
-	} else if (IS_ENABLED(CONFIG_INET) &&
-		   level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) {
-		struct inet_connection_sock *icsk;
-		struct tcp_sock *tp;
-
-		switch (optname) {
-		case TCP_CONGESTION:
-			icsk = inet_csk(sk);
-
-			if (!icsk->icsk_ca_ops || optlen <= 1)
-				goto err_clear;
-			strncpy(optval, icsk->icsk_ca_ops->name, optlen);
-			optval[optlen - 1] = 0;
-			break;
-		case TCP_SAVED_SYN:
-			tp = tcp_sk(sk);
-
-			if (optlen <= 0 || !tp->saved_syn ||
-			    optlen > tcp_saved_syn_len(tp->saved_syn))
-				goto err_clear;
-			memcpy(optval, tp->saved_syn->data, optlen);
-			break;
-		default:
-			goto err_clear;
-		}
+	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) {
+		err = sol_tcp_sockopt(sk, optname, optval, &optlen, true);
 	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) {
 		struct inet_sock *inet = inet_sk(sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 45c737ee95a1..a822cc627e2a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4043,8 +4043,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 	return stats;
 }
 
-static int do_tcp_getsockopt(struct sock *sk, int level,
-			     int optname, sockptr_t optval, sockptr_t optlen)
+int do_tcp_getsockopt(struct sock *sk, int level,
+		      int optname, sockptr_t optval, sockptr_t optlen)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-- 
cgit v1.2.3


From fd969f25fe24be515278d28cbf86dde39be8a495 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Thu, 1 Sep 2022 17:29:25 -0700
Subject: bpf: Change bpf_getsockopt(SOL_IP) to reuse do_ip_getsockopt()

This patch changes bpf_getsockopt(SOL_IP) to reuse
do_ip_getsockopt() and remove the duplicated code.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20220902002925.2895416-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/ip.h       |  2 ++
 net/core/filter.c      | 30 ++++++++++++------------------
 net/ipv4/ip_sockglue.c |  4 ++--
 3 files changed, 16 insertions(+), 20 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ip.h b/include/net/ip.h
index 34fa5b0f0a0e..038097c2a152 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -747,6 +747,8 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		     unsigned int optlen);
 int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		  unsigned int optlen);
+int do_ip_getsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, sockptr_t optlen);
 int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 		  int __user *optlen);
 int ip_ra_control(struct sock *sk, unsigned char on,
diff --git a/net/core/filter.c b/net/core/filter.c
index beadd5b83e6c..33275460fe66 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5166,23 +5166,29 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 				 KERNEL_SOCKPTR(optval), *optlen);
 }
 
-static int sol_ip_setsockopt(struct sock *sk, int optname,
-			     char *optval, int optlen)
+static int sol_ip_sockopt(struct sock *sk, int optname,
+			  char *optval, int *optlen,
+			  bool getopt)
 {
 	if (sk->sk_family != AF_INET)
 		return -EINVAL;
 
 	switch (optname) {
 	case IP_TOS:
-		if (optlen != sizeof(int))
+		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;
 	default:
 		return -EINVAL;
 	}
 
+	if (getopt)
+		return do_ip_getsockopt(sk, SOL_IP, optname,
+					KERNEL_SOCKPTR(optval),
+					KERNEL_SOCKPTR(optlen));
+
 	return do_ip_setsockopt(sk, SOL_IP, optname,
-				KERNEL_SOCKPTR(optval), optlen);
+				KERNEL_SOCKPTR(optval), *optlen);
 }
 
 static int sol_ipv6_setsockopt(struct sock *sk, int optname,
@@ -5214,7 +5220,7 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 	if (level == SOL_SOCKET)
 		return sol_socket_sockopt(sk, optname, optval, &optlen, false);
 	else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP)
-		return sol_ip_setsockopt(sk, optname, optval, optlen);
+		return sol_ip_sockopt(sk, optname, optval, &optlen, false);
 	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
 		return sol_ipv6_setsockopt(sk, optname, optval, optlen);
 	else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP)
@@ -5244,19 +5250,7 @@ static int __bpf_getsockopt(struct sock *sk, int level, int optname,
 	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) {
 		err = sol_tcp_sockopt(sk, optname, optval, &optlen, true);
 	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) {
-		struct inet_sock *inet = inet_sk(sk);
-
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET)
-			goto err_clear;
-
-		/* Only some options are supported */
-		switch (optname) {
-		case IP_TOS:
-			*((int *)optval) = (int)inet->tos;
-			break;
-		default:
-			goto err_clear;
-		}
+		err = sol_ip_sockopt(sk, optname, optval, &optlen, true);
 	} else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5d134a75cad0..47830f3fea1b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1524,8 +1524,8 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval,
 	return 0;
 }
 
-static int do_ip_getsockopt(struct sock *sk, int level, int optname,
-			    sockptr_t optval, sockptr_t optlen)
+int do_ip_getsockopt(struct sock *sk, int level, int optname,
+		     sockptr_t optval, sockptr_t optlen)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	bool needs_rtnl = getsockopt_needs_rtnl(optname);
-- 
cgit v1.2.3


From 38566ec06f52250c4abaa7447aae676e0b881c46 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Thu, 1 Sep 2022 17:29:31 -0700
Subject: bpf: Change bpf_getsockopt(SOL_IPV6) to reuse do_ipv6_getsockopt()

This patch changes bpf_getsockopt(SOL_IPV6) to reuse
do_ipv6_getsockopt().  It removes the duplicated code from
bpf_getsockopt(SOL_IPV6).

This also makes bpf_getsockopt(SOL_IPV6) supporting the same
set of optnames as in bpf_setsockopt(SOL_IPV6).  In particular,
this adds IPV6_AUTOFLOWLABEL support to bpf_getsockopt(SOL_IPV6).

ipv6 could be compiled as a module.  Like how other code solved it
with stubs in ipv6_stubs.h, this patch adds the do_ipv6_getsockopt
to the ipv6_bpf_stub.

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20220902002931.2896218-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/net/ipv6.h       |  2 ++
 include/net/ipv6_stubs.h |  2 ++
 net/core/filter.c        | 55 +++++++++++++++++++++---------------------------
 net/ipv6/af_inet6.c      |  1 +
 net/ipv6/ipv6_sockglue.c |  4 ++--
 5 files changed, 31 insertions(+), 33 deletions(-)

(limited to 'include/net')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a4f24573ed7a..d664ba5812d8 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1160,6 +1160,8 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval
 		       unsigned int optlen);
 int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		    unsigned int optlen);
+int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, sockptr_t optlen);
 int ipv6_getsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, int __user *optlen);
 
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 8692698b01cf..c48186bf4737 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -83,6 +83,8 @@ struct ipv6_bpf_stub {
 				     struct sk_buff *skb);
 	int (*ipv6_setsockopt)(struct sock *sk, int level, int optname,
 			       sockptr_t optval, unsigned int optlen);
+	int (*ipv6_getsockopt)(struct sock *sk, int level, int optname,
+			       sockptr_t optval, sockptr_t optlen);
 };
 extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 33275460fe66..ee768bb5b5ab 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5191,8 +5191,9 @@ static int sol_ip_sockopt(struct sock *sk, int optname,
 				KERNEL_SOCKPTR(optval), *optlen);
 }
 
-static int sol_ipv6_setsockopt(struct sock *sk, int optname,
-			       char *optval, int optlen)
+static int sol_ipv6_sockopt(struct sock *sk, int optname,
+			    char *optval, int *optlen,
+			    bool getopt)
 {
 	if (sk->sk_family != AF_INET6)
 		return -EINVAL;
@@ -5200,15 +5201,20 @@ static int sol_ipv6_setsockopt(struct sock *sk, int optname,
 	switch (optname) {
 	case IPV6_TCLASS:
 	case IPV6_AUTOFLOWLABEL:
-		if (optlen != sizeof(int))
+		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;
 	default:
 		return -EINVAL;
 	}
 
+	if (getopt)
+		return ipv6_bpf_stub->ipv6_getsockopt(sk, SOL_IPV6, optname,
+						      KERNEL_SOCKPTR(optval),
+						      KERNEL_SOCKPTR(optlen));
+
 	return ipv6_bpf_stub->ipv6_setsockopt(sk, SOL_IPV6, optname,
-					      KERNEL_SOCKPTR(optval), optlen);
+					      KERNEL_SOCKPTR(optval), *optlen);
 }
 
 static int __bpf_setsockopt(struct sock *sk, int level, int optname,
@@ -5222,7 +5228,7 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 	else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP)
 		return sol_ip_sockopt(sk, optname, optval, &optlen, false);
 	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
-		return sol_ipv6_setsockopt(sk, optname, optval, optlen);
+		return sol_ipv6_sockopt(sk, optname, optval, &optlen, false);
 	else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP)
 		return sol_tcp_sockopt(sk, optname, optval, &optlen, false);
 
@@ -5240,43 +5246,30 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 static int __bpf_getsockopt(struct sock *sk, int level, int optname,
 			    char *optval, int optlen)
 {
-	int err = 0, saved_optlen = optlen;
+	int err, saved_optlen = optlen;
 
-	if (!sk_fullsock(sk))
-		goto err_clear;
+	if (!sk_fullsock(sk)) {
+		err = -EINVAL;
+		goto done;
+	}
 
-	if (level == SOL_SOCKET) {
+	if (level == SOL_SOCKET)
 		err = sol_socket_sockopt(sk, optname, optval, &optlen, true);
-	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) {
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP)
 		err = sol_tcp_sockopt(sk, optname, optval, &optlen, true);
-	} else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) {
+	else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP)
 		err = sol_ip_sockopt(sk, optname, optval, &optlen, true);
-	} else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
-
-		if (optlen != sizeof(int) || sk->sk_family != AF_INET6)
-			goto err_clear;
-
-		/* Only some options are supported */
-		switch (optname) {
-		case IPV6_TCLASS:
-			*((int *)optval) = (int)np->tclass;
-			break;
-		default:
-			goto err_clear;
-		}
-	} else {
-		goto err_clear;
-	}
+	else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6)
+		err = sol_ipv6_sockopt(sk, optname, optval, &optlen, true);
+	else
+		err = -EINVAL;
 
+done:
 	if (err)
 		optlen = 0;
 	if (optlen < saved_optlen)
 		memset(optval + optlen, 0, saved_optlen - optlen);
 	return err;
-err_clear:
-	memset(optval, 0, optlen);
-	return -EINVAL;
 }
 
 static int _bpf_getsockopt(struct sock *sk, int level, int optname,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index cadc97852787..19732b5dce23 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1058,6 +1058,7 @@ static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
 	.inet6_bind = __inet6_bind,
 	.udp6_lib_lookup = __udp6_lib_lookup,
 	.ipv6_setsockopt = do_ipv6_setsockopt,
+	.ipv6_getsockopt = do_ipv6_getsockopt,
 };
 
 static int __init inet6_init(void)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index d9887e3a6077..1193f5a5247d 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1131,8 +1131,8 @@ static int compat_ipv6_get_msfilter(struct sock *sk, sockptr_t optval,
 	return 0;
 }
 
-static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
-			      sockptr_t optval, sockptr_t optlen)
+int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
+		       sockptr_t optval, sockptr_t optlen)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	int len;
-- 
cgit v1.2.3