github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-11-07 06:17:02 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

bpf: make tcp_tso_autosize() available to BPF congestion controls

Browse Source 
Expose tcp_tso_autosize() as a BPF kfunc and register it in the TCP
congestion-control kfunc set. This allows BPF congestion controls to
reuse the kernel TSO autosizing logic while applying their own
minimum TSO segment policy.

To make the kfunc robust against BPF-provided inputs, min_tso_segs is
sanitized to at least 1 and mss_now == 0 returns the sanitized minimum
value instead of performing autosizing.

Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Chia-Yu Chang 2026-08-31 18:52:30 +02:00 committed by Jakub Kicinski
parent cb145191e9
commit f69a094441
2 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
net/ipv4/bpf_tcp_ca.c
View File

@ -194,6 +194,7 @@ BTF_ID_FLAGS(func, tcp_reno_cong_avoid)
BTF_ID_FLAGS(func, tcp_reno_undo_cwnd)
BTF_ID_FLAGS(func, tcp_slow_start)
BTF_ID_FLAGS(func, tcp_cong_avoid_ai)
BTF_ID_FLAGS(func, tcp_tso_autosize)
BTF_KFUNCS_END(bpf_tcp_ca_check_kfunc_ids)
static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = {

14
net/ipv4/tcp_output.c
View File

@ -2252,13 +2252,21 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
* in bigger TSO bursts. We we cut the RTT-based allowance in half
* 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.
*
* The min_tso_segs is floored to 1 to avoid surprising conversion. Also,
* BPF callers may pass mss_now == 0. In that case the function returns the
* sanitized min_tso_segs value and skips autosizing.
*/
u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
int min_tso_segs)
__bpf_kfunc u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
int min_tso_segs)
{
u32 min_tso = max(min_tso_segs, 1);
unsigned long bytes;
u32 r;
if (unlikely(!mss_now))
return min_tso;
bytes = READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift);
r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log);
@ -2267,7 +2275,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
bytes = min_t(unsigned long, bytes, sk->sk_gso_max_size);
return max_t(u32, bytes / mss_now, min_tso_segs);
return max_t(u32, bytes / mss_now, min_tso);
}
EXPORT_SYMBOL_GPL(tcp_tso_autosize);