From 0ea488ff8d23c93da383fcf424825c298b13b1fb Mon Sep 17 00:00:00 2001
From: John Fastabend <john.fastabend@gmail.com>
Date: Thu, 5 Jul 2018 08:50:15 -0700
Subject: bpf: sockmap, convert bpf_compute_data_pointers to bpf_*_sk_skb
In commit
'bpf: bpf_compute_data uses incorrect cb structure' (8108a7751512)
we added the routine bpf_compute_data_end_sk_skb() to compute the
correct data_end values, but this has since been lost. In kernel
v4.14 this was correct and the above patch was applied in it
entirety. Then when v4.14 was merged into v4.15-rc1 net-next tree
we lost the piece that renamed bpf_compute_data_pointers to the
new function bpf_compute_data_end_sk_skb. This was done here,
e1ea2f9856b7 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net")
When it conflicted with the following rename patch,
6aaae2b6c433 ("bpf: rename bpf_compute_data_end into bpf_compute_data_pointers")
Finally, after a refactor I thought even the function
bpf_compute_data_end_sk_skb() was no longer needed and it was
erroneously removed.
However, we never reverted the sk_skb_convert_ctx_access() usage of
tcp_skb_cb which had been committed and survived the merge conflict.
Here we fix this by adding back the helper and *_data_end_sk_skb()
usage. Using the bpf_skc_data_end mapping is not correct because it
expects a qdisc_skb_cb object but at the sock layer this is not the
case. Even though it happens to work here because we don't overwrite
any data in-use at the socket layer and the cb structure is cleared
later this has potential to create some subtle issues. But, even
more concretely the filter.c access check uses tcp_skb_cb.
And by some act of chance though,
struct bpf_skb_data_end {
struct qdisc_skb_cb qdisc_cb; /* 0 28 */
/* XXX 4 bytes hole, try to pack */
void * data_meta; /* 32 8 */
void * data_end; /* 40 8 */
/* size: 48, cachelines: 1, members: 3 */
/* sum members: 44, holes: 1, sum holes: 4 */
/* last cacheline: 48 bytes */
};
and then tcp_skb_cb,
struct tcp_skb_cb {
[...]
struct {
__u32 flags; /* 24 4 */
struct sock * sk_redir; /* 32 8 */
void * data_end; /* 40 8 */
} bpf; /* 24 */
};
So when we use offset_of() to track down the byte offset we get 40 in
either case and everything continues to work. Fix this mess and use
correct structures its unclear how long this might actually work for
until someone moves the structs around.
Reported-by: Martin KaFai Lau <kafai@fb.com>
Fixes: e1ea2f9856b7 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net")
Fixes: 6aaae2b6c433 ("bpf: rename bpf_compute_data_end into bpf_compute_data_pointers")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/net/tcp.h | 4 ++++
1 file changed, 4 insertions(+)
(limited to 'include/net/tcp.h')
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 800582b5dd54..af3ec72d5d41 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -828,6 +828,10 @@ struct tcp_skb_cb {
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+ TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
#if IS_ENABLED(CONFIG_IPV6)
/* This is the variant of inet6_iif() that must be used by TCP,
--
cgit v1.2.3
From a69258f7aa2623e0930212f09c586fd06674ad79 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 12 Jul 2018 06:04:53 -0700
Subject: tcp: remove DELAYED ACK events in DCTCP
After fixing the way DCTCP tracking delayed ACKs, the delayed-ACK
related callbacks are no longer needed
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/tcp.h | 2 --
net/ipv4/tcp_dctcp.c | 25 -------------------------
net/ipv4/tcp_output.c | 4 ----
3 files changed, 31 deletions(-)
(limited to 'include/net/tcp.h')
diff --git a/include/net/tcp.h b/include/net/tcp.h
index af3ec72d5d41..3482d13d655b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -912,8 +912,6 @@ enum tcp_ca_event {
CA_EVENT_LOSS, /* loss timeout */
CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */
CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */
- CA_EVENT_DELAYED_ACK, /* Delayed ack is sent */
- CA_EVENT_NON_DELAYED_ACK,
};
/* Information about inbound ACK, passed to cong_ops->in_ack_event() */
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 89f88b0d8167..5869f89ca656 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -55,7 +55,6 @@ struct dctcp {
u32 dctcp_alpha;
u32 next_seq;
u32 ce_state;
- u32 delayed_ack_reserved;
u32 loss_cwnd;
};
@@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk)
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
- ca->delayed_ack_reserved = 0;
ca->loss_cwnd = 0;
ca->ce_state = 0;
@@ -250,25 +248,6 @@ static void dctcp_state(struct sock *sk, u8 new_state)
}
}
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
- struct dctcp *ca = inet_csk_ca(sk);
-
- switch (ev) {
- case CA_EVENT_DELAYED_ACK:
- if (!ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 1;
- break;
- case CA_EVENT_NON_DELAYED_ACK:
- if (ca->delayed_ack_reserved)
- ca->delayed_ack_reserved = 0;
- break;
- default:
- /* Don't care for the rest. */
- break;
- }
-}
-
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
switch (ev) {
@@ -278,10 +257,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
case CA_EVENT_ECN_NO_CE:
dctcp_ce_state_1_to_0(sk);
break;
- case CA_EVENT_DELAYED_ACK:
- case CA_EVENT_NON_DELAYED_ACK:
- dctcp_update_ack_reserved(sk, ev);
- break;
default:
/* Don't care for the rest. */
break;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e08b409c71e..00e5a300ddb9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3523,8 +3523,6 @@ void tcp_send_delayed_ack(struct sock *sk)
int ato = icsk->icsk_ack.ato;
unsigned long timeout;
- tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
if (ato > TCP_DELACK_MIN) {
const struct tcp_sock *tp = tcp_sk(sk);
int max_ato = HZ / 2;
@@ -3581,8 +3579,6 @@ void tcp_send_ack(struct sock *sk)
if (sk->sk_state == TCP_CLOSE)
return;
- tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
/* We are not putting this on the write queue, so
* tcp_transmit_skb() will set the ownership to this
* sock.
--
cgit v1.2.3