[PATCH net v3 1/2] tcp: fix use-after-free in do_tcp_getsockopt(TCP_CONGESTION)

[Cen Zhang (Microsoft)]

From: "Cen Zhang (Microsoft Security FORGE Labs)" <blbllhy@xxxxxxxxx>

do_tcp_getsockopt() reads icsk->icsk_ca_ops->name without holding
rcu_read_lock(). Since commit 0baf26b0fcd7 ("bpf: tcp: Support
tcp_congestion_ops in bpf"), icsk_ca_ops can point to dynamically
allocated BPF struct_ops memory that may be freed concurrently via
setsockopt(TCP_CONGESTION), leading to a use-after-free.

  BUG: KASAN: slab-use-after-free in _copy_to_user+0x37/0x60
  Read of size 16 at addr ffff888013505260 by task exploit/149
   _copy_to_user+0x37/0x60
   do_tcp_getsockopt+0x158a/0x2460 (net/ipv4/tcp.c:4585)
   tcp_getsockopt+0x91/0xf0
   __sys_getsockopt+0xf7/0x170

Fix this by holding rcu_read_lock() around the ca_ops->name access,
using READ_ONCE() to load icsk_ca_ops, and copying the name to a
stack buffer before releasing the lock. Also annotate the relevant
icsk_ca_ops stores with WRITE_ONCE() to fix the accompanying KCSAN
data-race issue.

Fixes: 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf")
Suggested-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Reported-by: Xiang Mei (Microsoft) <xmei5@xxxxxxx>
Link: https://lore.kernel.org/all/20260821182449.79785-2-blbllhy@xxxxxxxxx/
Cc: AutonomousCodeSecurity@xxxxxxxxxxxxx
Cc: stable@xxxxxxxxxxxxxxx
Assisted-by: GitHub-Copilot:claude-opus-4.6
Reviewed-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Signed-off-by: Cen Zhang (Microsoft Security FORGE Labs) <blbllhy@xxxxxxxxx>
---
Note: The adjacent TCP_ULP case has a similar read pattern on
icsk_ulp_ops->name, but icsk_ulp_ops always points to static
module data (no BPF struct_ops equivalent), so it is not affected.

Changes in v3:
- Fix the build failure by loading icsk_ca_ops inline.
- Drop the unrelated WRITE_ONCE() conversion in mptcp_ca_reset().

Changes in v2:
- Add READ_ONCE() for the icsk_ca_ops load.
- Add WRITE_ONCE() for every explicit icsk_ca_ops store.
---
 net/ipv4/tcp.c           | 14 +++++++++++---
 net/ipv4/tcp_cong.c      |  4 ++--
 net/ipv4/tcp_dctcp.c     |  2 +-
 net/ipv4/tcp_minisocks.c |  2 +-
 net/ipv4/tcp_output.c    |  2 +-
 5 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 455441f1b..55ca74f60 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4576,16 +4576,24 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 		val = !inet_csk_in_pingpong_mode(sk);
 		break;
 
-	case TCP_CONGESTION:
+	case TCP_CONGESTION: {
+		char ca_name[TCP_CA_NAME_MAX] = {};
+
 		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
 		len = min_t(unsigned int, len, TCP_CA_NAME_MAX);
 		if (copy_to_sockptr(optlen, &len, sizeof(int)))
 			return -EFAULT;
-		if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len))
+
+		rcu_read_lock();
+		memcpy(ca_name, READ_ONCE(icsk->icsk_ca_ops)->name,
+		       sizeof(ca_name));
+		rcu_read_unlock();
+
+		if (copy_to_sockptr(optval, ca_name, len))
 			return -EFAULT;
 		return 0;
-
+	}
 	case TCP_ULP:
 		if (copy_from_sockptr(&len, optlen, sizeof(int)))
 			return -EFAULT;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index e9f6c77e0..8e83ef81f 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -223,7 +223,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 	ca = rcu_dereference(net->ipv4.tcp_congestion_control);
 	if (unlikely(!bpf_try_module_get(ca, ca->owner)))
 		ca = &tcp_reno;
-	icsk->icsk_ca_ops = ca;
+	WRITE_ONCE(icsk->icsk_ca_ops, ca);
 	rcu_read_unlock();
 
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
@@ -253,7 +253,7 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_cleanup_congestion_control(sk);
-	icsk->icsk_ca_ops = ca;
+	WRITE_ONCE(icsk->icsk_ca_ops, ca);
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 274e628e7..99f68c299 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -111,7 +111,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk)
 	/* No ECN support? Fall back to Reno. Also need to clear
 	 * ECT from sk since it is set during 3WHS for DCTCP.
 	 */
-	inet_csk(sk)->icsk_ca_ops = &dctcp_reno;
+	WRITE_ONCE(inet_csk(sk)->icsk_ca_ops, &dctcp_reno);
 	INET_ECN_dontxmit(sk);
 }
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 6ab3e3a0b..def3b25ab 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -507,7 +507,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
 		ca = tcp_ca_find_key(ca_key);
 		if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
 			icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
-			icsk->icsk_ca_ops = ca;
+			WRITE_ONCE(icsk->icsk_ca_ops, ca);
 			ca_got_dst = true;
 		}
 		rcu_read_unlock();
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d7c1444b5..e72ebfe7b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4092,7 +4092,7 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
 	if (likely(ca && bpf_try_module_get(ca, ca->owner))) {
 		bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner);
 		icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
-		icsk->icsk_ca_ops = ca;
+		WRITE_ONCE(icsk->icsk_ca_ops, ca);
 	}
 	rcu_read_unlock();
 }
-- 
2.43.0