[PATCH bpf-next v2 0/5] tcp: increase flexibility of EBPF congestion control initialization

[PATCH bpf-next v2 0/5] tcp: increase flexibility of EBPF congestion control initialization

[Neal Cardwell]

From: Neal Cardwell <ncardwell@google.com>

This patch series reorganizes TCP congestion control initialization so that if
EBPF code called by tcp_init_transfer() sets the congestion control algorithm
by calling setsockopt(TCP_CONGESTION) then the TCP stack initializes the
congestion control module immediately, instead of having tcp_init_transfer()
later initialize the congestion control module.

This increases flexibility for the EBPF code that runs at connection
establishment time, and simplifies the code.

This has the following benefits:

(1) This allows CC module customizations made by the EBPF called in
    tcp_init_transfer() to persist, and not be wiped out by a later
    call to tcp_init_congestion_control() in tcp_init_transfer().

(2) Does not flip the order of EBPF and CC init, to avoid causing bugs
    for existing code upstream that depends on the current order.

(3) Does not cause 2 initializations for for CC in the case where the
    EBPF called in tcp_init_transfer() wants to set the CC to a new CC
    algorithm.

(4) Allows follow-on simplifications to the code in net/core/filter.c
    and net/ipv4/tcp_cong.c, which currently both have some complexity
    to special-case CC initialization to avoid double CC
    initialization if EBPF sets the CC.

changes in v2:

o rebase onto bpf-next

o add another follow-on simplification suggested by Martin KaFai Lau:
   "tcp: simplify tcp_set_congestion_control() load=false case"

Neal Cardwell (5):
  tcp: only init congestion control if not initialized already
  tcp: simplify EBPF TCP_CONGESTION to always init CC
  tcp: simplify tcp_set_congestion_control(): always reinitialize
  tcp: simplify _bpf_setsockopt(): remove flags argument
  tcp: simplify tcp_set_congestion_control() load=false case

 include/net/inet_connection_sock.h |  3 ++-
 include/net/tcp.h                  |  2 +-
 net/core/filter.c                  | 18 ++++--------------
 net/ipv4/tcp.c                     |  3 ++-
 net/ipv4/tcp_cong.c                | 27 +++++++--------------------
 net/ipv4/tcp_input.c               |  4 +++-
 6 files changed, 19 insertions(+), 38 deletions(-)

-- 
2.28.0.526.ge36021eeef-goog

[PATCH bpf-next v2 1/5] tcp: only init congestion control if not initialized already

[Neal Cardwell]

From: Neal Cardwell <ncardwell@google.com>

Change tcp_init_transfer() to only initialize congestion control if it
has not been initialized already.

With this new approach, we can arrange things so that if the EBPF code
sets the congestion control by calling setsockopt(TCP_CONGESTION) then
tcp_init_transfer() will not re-initialize the CC module.

This is an approach that has the following beneficial properties:

(1) This allows CC module customizations made by the EBPF called in
    tcp_init_transfer() to persist, and not be wiped out by a later
    call to tcp_init_congestion_control() in tcp_init_transfer().

(2) Does not flip the order of EBPF and CC init, to avoid causing bugs
    for existing code upstream that depends on the current order.

(3) Does not cause 2 initializations for for CC in the case where the
    EBPF called in tcp_init_transfer() wants to set the CC to a new CC
    algorithm.

(4) Allows follow-on simplifications to the code in net/core/filter.c
    and net/ipv4/tcp_cong.c, which currently both have some complexity
    to special-case CC initialization to avoid double CC
    initialization if EBPF sets the CC.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
---
 include/net/inet_connection_sock.h | 3 ++-
 net/ipv4/tcp.c                     | 1 +
 net/ipv4/tcp_cong.c                | 3 ++-
 net/ipv4/tcp_input.c               | 4 +++-
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c738abeb3265..dc763ca9413c 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -96,7 +96,8 @@ struct inet_connection_sock {
 	void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
 	struct hlist_node         icsk_listen_portaddr_node;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state:6,
+	__u8			  icsk_ca_state:5,
+				  icsk_ca_initialized:1,
 				  icsk_ca_setsockopt:1,
 				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57a568875539..7360d3db2b61 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2698,6 +2698,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	if (icsk->icsk_ca_ops->release)
 		icsk->icsk_ca_ops->release(sk);
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	icsk->icsk_ca_initialized = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 62878cf26d9c..d18d7a1ce4ce 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -176,7 +176,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 
 void tcp_init_congestion_control(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
@@ -185,6 +185,7 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_xmit(sk);
 	else
 		INET_ECN_dontxmit(sk);
+	icsk->icsk_ca_initialized = 1;
 }
 
 static void tcp_reinit_congestion_control(struct sock *sk,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4337841faeff..0e5ac0d33fd3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5894,8 +5894,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 		tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
+	icsk->icsk_ca_initialized = 0;
 	bpf_skops_established(sk, bpf_op, skb);
-	tcp_init_congestion_control(sk);
+	if (!icsk->icsk_ca_initialized)
+		tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
 
-- 
2.28.0.526.ge36021eeef-goog

[PATCH bpf-next v2 2/5] tcp: simplify EBPF TCP_CONGESTION to always init CC

[Neal Cardwell]

From: Neal Cardwell <ncardwell@google.com>

Now that the previous patch ensures we don't initialize the congestion
control twice, when EBPF sets the congestion control algorithm at
connection establishment we can simplify the code by simply
initializing the congestion control module at that time.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
---
 net/core/filter.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 47eef9a0be6a..067f6759a68f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4313,8 +4313,6 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-#define SOCKOPT_CC_REINIT (1 << 0)
-
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			   char *optval, int optlen, u32 flags)
 {
@@ -4449,13 +4447,12 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
 			char name[TCP_CA_NAME_MAX];
-			bool reinit = flags & SOCKOPT_CC_REINIT;
 
 			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,
-							 reinit, true);
+							 true, true);
 		} else {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
@@ -4652,8 +4649,6 @@ BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
 	u32 flags = 0;
-	if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
-		flags |= SOCKOPT_CC_REINIT;
 	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen,
 			       flags);
 }
-- 
2.28.0.526.ge36021eeef-goog

Re: [PATCH bpf-next v2 1/5] tcp: only init congestion control if not initialized already

[Neal Cardwell]

On Thu, Sep 10, 2020 at 3:20 PM Neal Cardwell
<ncardwell.kernel@gmail.com> wrote:
>
> From: Neal Cardwell <ncardwell@google.com>
>
> Change tcp_init_transfer() to only initialize congestion control if it
> has not been initialized already.

Please ignore this v2 patch series.

My e-mails from ncardwell@google.com stopped being accepted at
netdev@vger.kernel.org mid-way through processing  the v2 patch series
(between patches 2 and 3), confusing patchwork about which patches
belonged to the v2 patch series. I tried resending the remaining
patches from gmail.com, but this confused patchwork about what patches
belonged to which series.

I have resubmitted the v2 patch series as patch series v3 entirely
sent from @gmail.com.

Here is v3; please use this one:
  https://patchwork.ozlabs.org/project/netdev/list/?series=200962

thanks!
neal

[PATCH bpf-next v2 1/5] tcp: only init congestion control if not initialized already

[Neal Cardwell]

Change tcp_init_transfer() to only initialize congestion control if it
has not been initialized already.

With this new approach, we can arrange things so that if the EBPF code
sets the congestion control by calling setsockopt(TCP_CONGESTION) then
tcp_init_transfer() will not re-initialize the CC module.

This is an approach that has the following beneficial properties:

(1) This allows CC module customizations made by the EBPF called in
    tcp_init_transfer() to persist, and not be wiped out by a later
    call to tcp_init_congestion_control() in tcp_init_transfer().

(2) Does not flip the order of EBPF and CC init, to avoid causing bugs
    for existing code upstream that depends on the current order.

(3) Does not cause 2 initializations for for CC in the case where the
    EBPF called in tcp_init_transfer() wants to set the CC to a new CC
    algorithm.

(4) Allows follow-on simplifications to the code in net/core/filter.c
    and net/ipv4/tcp_cong.c, which currently both have some complexity
    to special-case CC initialization to avoid double CC
    initialization if EBPF sets the CC.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
---
 include/net/inet_connection_sock.h | 3 ++-
 net/ipv4/tcp.c                     | 1 +
 net/ipv4/tcp_cong.c                | 3 ++-
 net/ipv4/tcp_input.c               | 4 +++-
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c738abeb3265..dc763ca9413c 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -96,7 +96,8 @@ struct inet_connection_sock {
 	void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
 	struct hlist_node         icsk_listen_portaddr_node;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state:6,
+	__u8			  icsk_ca_state:5,
+				  icsk_ca_initialized:1,
 				  icsk_ca_setsockopt:1,
 				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 57a568875539..7360d3db2b61 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2698,6 +2698,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	if (icsk->icsk_ca_ops->release)
 		icsk->icsk_ca_ops->release(sk);
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	icsk->icsk_ca_initialized = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 62878cf26d9c..d18d7a1ce4ce 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -176,7 +176,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 
 void tcp_init_congestion_control(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
@@ -185,6 +185,7 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_xmit(sk);
 	else
 		INET_ECN_dontxmit(sk);
+	icsk->icsk_ca_initialized = 1;
 }
 
 static void tcp_reinit_congestion_control(struct sock *sk,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4337841faeff..0e5ac0d33fd3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5894,8 +5894,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 		tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
+	icsk->icsk_ca_initialized = 0;
 	bpf_skops_established(sk, bpf_op, skb);
-	tcp_init_congestion_control(sk);
+	if (!icsk->icsk_ca_initialized)
+		tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
 
-- 
2.28.0.526.ge36021eeef-goog