Add Tcp and bbr patches.

Documentation/networking/ip-sysctl.rst

@@ -922,6 +922,81 @@ tcp_rx_skb_cache - BOOLEAN
 
 	Default: 0 (disabled)
 
+tcp_plb_enabled - BOOLEAN
+	If set and the underlying congestion control (e.g. DCTCP) supports
+	and enables PLB feature, TCP PLB (Protective Load Balancing) is
+	enabled. PLB is described in the following paper:
+	https://doi.org/10.1145/3544216.3544226. Based on PLB parameters,
+	upon sensing sustained congestion, TCP triggers a change in
+	flow label field for outgoing IPv6 packets. A change in flow label
+	field potentially changes the path of outgoing packets for switches
+	that use ECMP/WCMP for routing.
+
+	PLB changes socket txhash which results in a change in IPv6 Flow Label
+	field, and currently no-op for IPv4 headers. It is possible
+	to apply PLB for IPv4 with other network header fields (e.g. TCP
+	or IPv4 options) or using encapsulation where outer header is used
+	by switches to determine next hop. In either case, further host
+	and switch side changes will be needed.
+
+	When set, PLB assumes that congestion signal (e.g. ECN) is made
+	available and used by congestion control module to estimate a
+	congestion measure (e.g. ce_ratio). PLB needs a congestion measure to
+	make repathing decisions.
+
+	Default: FALSE
+
+tcp_plb_idle_rehash_rounds - INTEGER
+	Number of consecutive congested rounds (RTT) seen after which
+	a rehash can be performed, given there are no packets in flight.
+	This is referred to as M in PLB paper:
+	https://doi.org/10.1145/3544216.3544226.
+
+	Possible Values: 0 - 31
+
+	Default: 3
+
+tcp_plb_rehash_rounds - INTEGER
+	Number of consecutive congested rounds (RTT) seen after which
+	a forced rehash can be performed. Be careful when setting this
+	parameter, as a small value increases the risk of retransmissions.
+	This is referred to as N in PLB paper:
+	https://doi.org/10.1145/3544216.3544226.
+
+	Possible Values: 0 - 31
+
+	Default: 12
+
+tcp_plb_suspend_rto_sec - INTEGER
+	Time, in seconds, to suspend PLB in event of an RTO. In order to avoid
+	having PLB repath onto a connectivity "black hole", after an RTO a TCP
+	connection suspends PLB repathing for a random duration between 1x and
+	2x of this parameter. Randomness is added to avoid concurrent rehashing
+	of multiple TCP connections. This should be set corresponding to the
+	amount of time it takes to repair a failed link.
+
+	Possible Values: 0 - 255
+
+	Default: 60
+
+tcp_plb_cong_thresh - INTEGER
+	Fraction of packets marked with congestion over a round (RTT) to
+	tag that round as congested. This is referred to as K in the PLB paper:
+	https://doi.org/10.1145/3544216.3544226.
+
+	The 0-1 fraction range is mapped to 0-256 range to avoid floating
+	point operations. For example, 128 means that if at least 50% of
+	the packets in a round were marked as congested then the round
+	will be tagged as congested.
+
+	Setting threshold to 0 means that PLB repaths every RTT regardless
+	of congestion. This is not intended behavior for PLB and should be
+	used only for experimentation purpose.
+
+	Possible Values: 0 - 256
+
+	Default: 128
+
 UDP variables
 =============
 

arch/arm64/configs/rockchip_linux_defconfig

@@ -891,3 +891,17 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_FUNCTION_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_LKDTM=y
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_TCP_CONG_BBR=y
+# CONFIG_DEFAULT_CUBIC is not set
+CONFIG_DEFAULT_BBR=y
+CONFIG_DEFAULT_TCP_CONG="bbr"
+# CONFIG_NET_SCH_MULTIQ is not set
+# CONFIG_NET_SCH_SFQ is not set
+# CONFIG_NET_SCH_TBF is not set
+# CONFIG_NET_SCH_NETEM is not set
+# CONFIG_NET_SCH_CODEL is not set
+CONFIG_NET_SCH_DEFAULT=y
+CONFIG_DEFAULT_FQ_CODEL=y
+CONFIG_DEFAULT_NET_SCH="fq_codel"
+# CONFIG_NET_SCH_FQ is not set

include/linux/tcp.h

@@ -226,7 +226,9 @@ struct tcp_sock {
 	u8	compressed_ack;
 	u8	dup_ack_counter:2,
 		tlp_retrans:1,	/* TLP is a retransmission */
-		unused:5;
+		fast_ack_mode:2, /* which fast ack mode ? */
+		tlp_orig_data_app_limited:1, /* app-limited before TLP rtx? */
+		unused:2;
 	u32	chrono_start;	/* Start time in jiffies of a TCP chrono */
 	u32	chrono_stat[3];	/* Time in jiffies for chrono_stat stats */
 	u8	chrono_type:2,	/* current chronograph type */
@@ -395,6 +397,7 @@ struct tcp_sock {
 		u32		  probe_seq_start;
 		u32		  probe_seq_end;
 	} mtu_probe;
+	u32     plb_rehash;     /* PLB-triggered rehash attempts */
 	u32	mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG
 			   * while socket was owned by user.
 			   */

include/linux/wait.h

@@ -164,6 +164,7 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 
 extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void add_wait_queue_exclusive_lifo(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
 static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
@@ -1155,6 +1156,7 @@ do {										\
  */
 void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
 bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
+void prepare_to_wait_exclusive_lifo(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
 long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state);
 void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout);

include/net/af_unix.h

@@ -20,13 +20,12 @@ struct sock *unix_peer_get(struct sock *sk);
 #define UNIX_HASH_BITS	8
 
 extern unsigned int unix_tot_inflight;
-extern spinlock_t unix_table_lock;
+extern spinlock_t unix_table_locks[2 * UNIX_HASH_SIZE];
 extern struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
 
 struct unix_address {
 	refcount_t	refcnt;
 	int		len;
-	unsigned int	hash;
 	struct sockaddr_un name[];
 };
 

include/net/inet_connection_sock.h

@@ -139,8 +139,8 @@ struct inet_connection_sock {
 
 	ANDROID_KABI_RESERVE(1);
 
-	u64			  icsk_ca_priv[104 / sizeof(u64)];
-#define ICSK_CA_PRIV_SIZE      (13 * sizeof(u64))
+#define ICSK_CA_PRIV_SIZE      (144)
+	u64			  icsk_ca_priv[ICSK_CA_PRIV_SIZE / sizeof(u64)];
 };
 
 #define ICSK_TIME_RETRANS	1	/* Retransmit timer */

include/net/netns/ipv4.h

@@ -185,6 +185,11 @@ struct netns_ipv4 {
 	atomic_t tfo_active_disable_times;
 	unsigned long tfo_active_disable_stamp;
 	int sysctl_tcp_reflect_tos;
+	u8 sysctl_tcp_plb_enabled;
+	u8 sysctl_tcp_plb_idle_rehash_rounds;
+	u8 sysctl_tcp_plb_rehash_rounds;
+	u8 sysctl_tcp_plb_suspend_rto_sec;
+	int sysctl_tcp_plb_cong_thresh;
 
 	int sysctl_udp_wmem_min;
 	int sysctl_udp_rmem_min;