Re-apply: tcp: enforce receive buffer memory limits by allowing the tcp window to shrink

Due to a mistake when merging

Signed-off-by: hmtheboy154 <buingoc67@gmail.com>

Author: dmfreemon

Documentation/networking/ip-sysctl.rst

@@ -967,6 +967,21 @@ tcp_tw_reuse - INTEGER
 tcp_window_scaling - BOOLEAN
 	Enable window scaling as defined in RFC1323.
 
+tcp_shrink_window - BOOLEAN
+	This changes how the TCP receive window is calculated.
+
+	RFC 7323, section 2.4, says there are instances when a retracted
+	window can be offered, and that TCP implementations MUST ensure
+	that they handle a shrinking window, as specified in RFC 1122.
+
+	- 0 - Disabled.	The window is never shrunk.
+	- 1 - Enabled.	The window is shrunk when necessary to remain within
+			the memory limit set by autotuning (sk_rcvbuf).
+			This only occurs if a non-zero receive window
+			scaling factor is also in effect.
+
+	Default: 0
+
 tcp_wmem - vector of 3 INTEGERs: min, default, max
 	min: Amount of memory reserved for send buffers for TCP sockets.
 	Each TCP socket has rights to use it due to fact of its birth.

include/net/netns/ipv4.h

@@ -65,6 +65,7 @@ struct netns_ipv4 {
 #endif
 	bool			fib_has_custom_local_routes;
 	bool			fib_offload_disabled;
+	u8			sysctl_tcp_shrink_window;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	atomic_t		fib_num_tclassid_users;
 #endif

net/ipv4/tcp_ipv4.c

@@ -3230,6 +3230,8 @@ static int __net_init tcp_sk_init(struct net *net)
 	else
 		net->ipv4.tcp_congestion_control = &tcp_reno;
 
+	net->ipv4.sysctl_tcp_shrink_window = 0;
+
 	return 0;
 }
 

net/ipv4/tcp_output.c

@@ -259,8 +259,8 @@ static u16 tcp_select_window(struct sock *sk)
 	u32 old_win = tp->rcv_wnd;
 	u32 cur_win = tcp_receive_window(tp);
 	u32 new_win = __tcp_select_window(sk);
+	struct net *net = sock_net(sk);
 
-	/* Never shrink the offered window */
 	if (new_win < cur_win) {
 		/* Danger Will Robinson!
 		 * Don't update rcv_wup/rcv_wnd here or else
@@ -269,19 +269,22 @@ static u16 tcp_select_window(struct sock *sk)
 		 *
 		 * Relax Will Robinson.
 		 */
-		if (new_win == 0)
-			NET_INC_STATS(sock_net(sk),
-				      LINUX_MIB_TCPWANTZEROWINDOWADV);
-		new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) || !tp->rx_opt.rcv_wscale) {
+			/* Never shrink the offered window */
+			if (new_win == 0)
+				NET_INC_STATS(net, LINUX_MIB_TCPWANTZEROWINDOWADV);
+			new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale);
+		}
 	}
+
 	tp->rcv_wnd = new_win;
 	tp->rcv_wup = tp->rcv_nxt;
 
 	/* Make sure we do not exceed the maximum possible
 	 * scaled window.
 	 */
 	if (!tp->rx_opt.rcv_wscale &&
-	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
+	    READ_ONCE(net->ipv4.sysctl_tcp_workaround_signed_windows))
 		new_win = min(new_win, MAX_TCP_WINDOW);
 	else
 		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -293,10 +296,9 @@ static u16 tcp_select_window(struct sock *sk)
 	if (new_win == 0) {
 		tp->pred_flags = 0;
 		if (old_win)
-			NET_INC_STATS(sock_net(sk),
-				      LINUX_MIB_TCPTOZEROWINDOWADV);
+			NET_INC_STATS(net, LINUX_MIB_TCPTOZEROWINDOWADV);
 	} else if (old_win == 0) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV);
+		NET_INC_STATS(net, LINUX_MIB_TCPFROMZEROWINDOWADV);
 	}
 
 	return new_win;
@@ -2990,6 +2992,7 @@ u32 __tcp_select_window(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct net *net = sock_net(sk);
 	/* MSS for the peer's data.  Previous versions used mss_clamp
 	 * here.  I don't know if the value based on our guesses
 	 * of peer's MSS is better for the performance.  It's more correct
@@ -3011,6 +3014,15 @@ u32 __tcp_select_window(struct sock *sk)
 		if (mss <= 0)
 			return 0;
 	}
+
+	/* Only allow window shrink if the sysctl is enabled and we have
+	 * a non-zero scaling factor in effect.
+	 */
+	if (READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) && tp->rx_opt.rcv_wscale)
+		goto shrink_window_allowed;
+
+	/* do not allow window to shrink */
+
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
@@ -3065,6 +3077,36 @@ u32 __tcp_select_window(struct sock *sk)
 	}
 
 	return window;
+
+shrink_window_allowed:
+	/* new window should always be an exact multiple of scaling factor */
+	free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale);
+
+	if (free_space < (full_space >> 1)) {
+		icsk->icsk_ack.quick = 0;
+
+		if (tcp_under_memory_pressure(sk))
+			tcp_adjust_rcv_ssthresh(sk);
+
+		/* if free space is too low, return a zero window */
+		if (free_space < (allowed_space >> 4) || free_space < mss ||
+			free_space < (1 << tp->rx_opt.rcv_wscale))
+			return 0;
+	}
+
+	if (free_space > tp->rcv_ssthresh) {
+		free_space = tp->rcv_ssthresh;
+		/* new window should always be an exact multiple of scaling factor
+		 *
+		 * For this case, we ALIGN "up" (increase free_space) because
+		 * we know free_space is not zero here, it has been reduced from
+		 * the memory-based limit, and rcv_ssthresh is not a hard limit
+		 * (unlike sk_rcvbuf).
+		 */
+		free_space = ALIGN(free_space, (1 << tp->rx_opt.rcv_wscale));
+	}
+
+	return free_space;
 }
 
 void tcp_skb_collapse_tstamp(struct sk_buff *skb,