mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-08-31 08:15:07 -04:00
Code Issues Packages Projects Releases Wiki Activity

tcp: honor BPF_SOCK_OPS_RWND_INIT on the active connect path

Browse Source 
BPF_SOCK_OPS_RWND_INIT lets a sockops BPF program pick the initial TCP
receive window, e.g. to advertise a larger window up front in environments
where that is known to be safe. Today it is only effective for the passive
(listener) side; on the active (connect) side the value is computed and
then silently discarded.

On the passive path tcp_openreq_init_rwin() inflates full_space when the
program returns a non-zero window, so tcp_select_initial_window() can offer
it:

	else if (full_space < (u64)rcv_wnd * mss)
		full_space = min_t(u64, (u64)rcv_wnd * mss, INT_MAX);

tcp_select_initial_window() only clamps the requested window *down* to the
available space, so without inflating the space first the BPF reply can
never raise the offered window above tcp_full_space(sk).

tcp_connect_init() calls tcp_rwnd_init_bpf() but never inflates full_space,
so on connect() the requested window is clamped back to tcp_full_space(sk)
(~64KB at the default rcvbuf) and the program's value is ignored.

Inflate full_space in tcp_connect_init() as well; tp->advmss is the mss the
listener path uses (both are tcp_mss_clamp(tp, dst_metric_advmss(dst))).
Read full_space after tcp_rwnd_init_bpf() so a program that also adjusts
SO_RCVBUF is still reflected. Compute the inflated value in u64 and clamp
to INT_MAX to avoid overflow (full_space is int, rcv_wnd is u32), and
apply the same overflow fix to the existing listener-side computation.

tcp_select_initial_window() itself also computes init_rcv_wnd * mss in
32-bit when clamping the offered window down to the requested value. A
large requested window (init_rcv_wnd greater than ~2.9M segments at
1460 mss) wraps this multiply and collapses the offered window to a tiny
value, so compute it in u64 as well.

Signed-off-by: Tejas Birajdar <tejasbirajdar@meta.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20260730220055.2946171-1-tejasbirajdar@meta.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Tejas Birajdar
2026-07-30 15:00:55 -07:00
committed by Jakub Kicinski
parent c206fc0705
commit ca10634ebc
2 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
net/ipv4/tcp_minisocks.c
View File

@@ -453,8 +453,8 @@ void tcp_openreq_init_rwin(struct request_sock *req,
rcv_wnd = tcp_rwnd_init_bpf((struct sock *)req);
if (rcv_wnd == 0)
rcv_wnd = dst_metric(dst, RTAX_INITRWND);
else if (full_space < rcv_wnd * mss)
full_space = rcv_wnd * mss;
else if (full_space < (u64)rcv_wnd * mss)
full_space = min_t(u64, (u64)rcv_wnd * mss, INT_MAX);
/* tcp_full_space because it is guaranteed to be the first packet */
tcp_select_initial_window(sk_listener, full_space,

8
net/ipv4/tcp_output.c
View File

@@ -251,7 +251,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
(*rcv_wnd) = space;
if (init_rcv_wnd)
*rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
*rcv_wnd = min_t(u64, *rcv_wnd, (u64)init_rcv_wnd * mss);
*rcv_wscale = 0;
if (wscale_ok) {
@@ -4103,6 +4103,7 @@ static void tcp_connect_init(struct sock *sk)
const struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_sock *tp = tcp_sk(sk);
__u8 rcv_wscale;
int full_space;
u16 user_mss;
u32 rcv_wnd;
@@ -4137,10 +4138,13 @@ static void tcp_connect_init(struct sock *sk)
WRITE_ONCE(tp->window_clamp, tcp_full_space(sk));
rcv_wnd = tcp_rwnd_init_bpf(sk);
full_space = tcp_full_space(sk);
if (rcv_wnd == 0)
rcv_wnd = dst_metric(dst, RTAX_INITRWND);
else if (full_space < (u64)rcv_wnd * tp->advmss)
full_space = min_t(u64, (u64)rcv_wnd * tp->advmss, INT_MAX);
tcp_select_initial_window(sk, tcp_full_space(sk),
tcp_select_initial_window(sk, full_space,
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,