From: Chia-Yu Chang <[email protected]>
This patch replaces existing min_tso_segs() with tso_segs() CC callback
for CC algorithm to provide explicit tso segment number of each data
burst and overrides tcp_tso_autosize().
This change provides below impacts on BPF struct_ops users:
- The callback is renamed from min_tso_segs() to tso_segs()
- The signature gains an extra u32 mss_now argument
- The return value semantics is changed from "floor value passed into
tcp_tso_autosize()" to "final tso_segs value", bypassing autosizing
As a result, BPF programs shall be updated, because returning a small
constant will now directly limit the final tso_segs value instead of
specifying the minimum value passed to tcp_tso_autosize().
Signed-off-by: Ilpo Järvinen <[email protected]>
Signed-off-by: Chia-Yu Chang <[email protected]>
Reviewed-by: Emil Tsalapatis <[email protected]>
---
v7:
- Update the comments for tso_segs()
- Restore bpf_tcp_ca_tso_segs() to return 0
- Move READ_ONCE() to the else branch if ca_ops->tso_segs() is undefined
- Update tcp_tso_autosize() to use EXPORT_SYMBOL_GPL
v6:
- Add clamp_t to avoid returning 0 by ca_ops->tso_segs()
- Update commit message
v5:
- Revert back to v3 and add Reviewed-by tag
v4:
- Use union for both min_tso_segs() and tso_segs() and a
v3:
- Update bpf_tcp_ca_tso_segs() to use tcp_tso_autosize()
- Add divide by 0 protection in case of mss_now=0
v2:
- Export tcp_tso_autosize()
---
include/net/tcp.h | 12 ++++++++++--
net/ipv4/bpf_tcp_ca.c | 4 ++--
net/ipv4/tcp_bbr.c | 13 ++++++++++---
net/ipv4/tcp_output.c | 18 +++++++++---------
.../testing/selftests/bpf/progs/tcp_ca_kfunc.c | 8 ++++----
5 files changed, 35 insertions(+), 20 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2c5b889530b5..37b95b98f9f9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -824,6 +824,9 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
unsigned int tcp_current_mss(struct sock *sk);
u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when);
+u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
+ int min_tso_segs);
+
/* Bound MSS / TSO packet size with the half of the window */
static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
{
@@ -1361,8 +1364,13 @@ struct tcp_congestion_ops {
/* hook for packet ack accounting (optional) */
void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
- /* override sysctl_tcp_min_tso_segs (optional) */
- u32 (*min_tso_segs)(struct sock *sk);
+ /* Override tcp_tso_autosize (optional)
+ *
+ * If provided, this callback returns the final TSO segment count
+ * and bypasses tcp_tso_autosize() entirely. Implementations must
+ * handle the mss_now==0 case and derive an appropriate value.
+ */
+ u32 (*tso_segs)(struct sock *sk, u32 mss_now);
/* new value of cwnd after loss (required) */
u32 (*undo_cwnd)(struct sock *sk);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 791e15063237..ed4fea98dfde 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -284,7 +284,7 @@ static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *samp
{
}
-static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk)
+static u32 bpf_tcp_ca_tso_segs(struct sock *sk, u32 mss_now)
{
return 0;
}
@@ -320,7 +320,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = {
.cwnd_event_tx_start = bpf_tcp_ca_cwnd_event_tx_start,
.in_ack_event = bpf_tcp_ca_in_ack_event,
.pkts_acked = bpf_tcp_ca_pkts_acked,
- .min_tso_segs = bpf_tcp_ca_min_tso_segs,
+ .tso_segs = bpf_tcp_ca_tso_segs,
.cong_control = bpf_tcp_ca_cong_control,
.undo_cwnd = bpf_tcp_ca_undo_cwnd,
.sndbuf_expand = bpf_tcp_ca_sndbuf_expand,
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 82378a2bfd1e..ecf11be46f38 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -297,11 +297,18 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
}
/* override sysctl_tcp_min_tso_segs */
-__bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk)
+static u32 bbr_min_tso_segs(struct sock *sk)
{
return READ_ONCE(sk->sk_pacing_rate) < (bbr_min_tso_rate >> 3) ? 1 : 2;
}
+__bpf_kfunc static u32 bbr_tso_segs(struct sock *sk, u32 mss_now)
+{
+ if (unlikely(!mss_now))
+ return bbr_min_tso_segs(sk);
+ return tcp_tso_autosize(sk, mss_now, bbr_min_tso_segs(sk));
+}
+
static u32 bbr_tso_segs_goal(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -1151,7 +1158,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = {
.undo_cwnd = bbr_undo_cwnd,
.cwnd_event_tx_start = bbr_cwnd_event_tx_start,
.ssthresh = bbr_ssthresh,
- .min_tso_segs = bbr_min_tso_segs,
+ .tso_segs = bbr_tso_segs,
.get_info = bbr_get_info,
.set_state = bbr_set_state,
};
@@ -1163,7 +1170,7 @@ BTF_ID_FLAGS(func, bbr_sndbuf_expand)
BTF_ID_FLAGS(func, bbr_undo_cwnd)
BTF_ID_FLAGS(func, bbr_cwnd_event_tx_start)
BTF_ID_FLAGS(func, bbr_ssthresh)
-BTF_ID_FLAGS(func, bbr_min_tso_segs)
+BTF_ID_FLAGS(func, bbr_tso_segs)
BTF_ID_FLAGS(func, bbr_set_state)
BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fcaa04e65189..7d3e0e715c4b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2253,8 +2253,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
* for every 2^9 usec (aka 512 us) of RTT, so that the RTT-based allowance
* is below 1500 bytes after 6 * ~500 usec = 3ms.
*/
-static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
- int min_tso_segs)
+u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
+ int min_tso_segs)
{
unsigned long bytes;
u32 r;
@@ -2269,6 +2269,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
return max_t(u32, bytes / mss_now, min_tso_segs);
}
+EXPORT_SYMBOL_GPL(tcp_tso_autosize);
/* Return the number of segments we want in the skb we are transmitting.
* See if congestion control module wants to decide; otherwise, autosize.
@@ -2276,14 +2277,13 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
{
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
- u32 min_tso, tso_segs;
+ u32 tso_segs;
- min_tso = ca_ops->min_tso_segs ?
- ca_ops->min_tso_segs(sk) :
- READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
-
- tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
- return min_t(u32, tso_segs, sk->sk_gso_max_segs);
+ tso_segs = ca_ops->tso_segs ?
+ ca_ops->tso_segs(sk, mss_now) :
+ tcp_tso_autosize(sk, mss_now,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs));
+ return clamp_t(u32, tso_segs, 1, sk->sk_gso_max_segs);
}
/* Returns the portion of skb which can be sent right away */
diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
index 0a3e9d35bf6f..58262e490336 100644
--- a/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
+++ b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
@@ -10,7 +10,7 @@ extern u32 bbr_sndbuf_expand(struct sock *sk) __ksym;
extern u32 bbr_undo_cwnd(struct sock *sk) __ksym;
extern void bbr_cwnd_event_tx_start(struct sock *sk) __ksym;
extern u32 bbr_ssthresh(struct sock *sk) __ksym;
-extern u32 bbr_min_tso_segs(struct sock *sk) __ksym;
+extern u32 bbr_tso_segs(struct sock *sk, u32 mss_now) __ksym;
extern void bbr_set_state(struct sock *sk, u8 new_state) __ksym;
extern void dctcp_init(struct sock *sk) __ksym;
@@ -90,9 +90,9 @@ u32 BPF_PROG(ssthresh, struct sock *sk)
}
SEC("struct_ops")
-u32 BPF_PROG(min_tso_segs, struct sock *sk)
+u32 BPF_PROG(tso_segs, struct sock *sk, u32 mss_now)
{
- return bbr_min_tso_segs(sk);
+ return bbr_tso_segs(sk, mss_now);
}
SEC("struct_ops")
@@ -120,7 +120,7 @@ struct tcp_congestion_ops tcp_ca_kfunc = {
.cwnd_event = (void *)cwnd_event,
.cwnd_event_tx_start = (void *)cwnd_event_tx_start,
.ssthresh = (void *)ssthresh,
- .min_tso_segs = (void *)min_tso_segs,
+ .tso_segs = (void *)tso_segs,
.set_state = (void *)set_state,
.pkts_acked = (void *)pkts_acked,
.name = "tcp_ca_kfunc",
--
2.34.1
lmpx.com only provides a reader for public news (NNTP) servers. It is not
affiliated with the servers or forums shown here and is not responsible for
the content of articles, which is written by their respective authors.