git: 96eb0d90cd75 - main - tcp: With the right options in the kernel cc_cubic stays in slowstart always.

The branch main has been updated by rrs:

URL: https://cgit.FreeBSD.org/src/commit/?id=96eb0d90cd75c56517bef952a03240f82f525d2e

commit 96eb0d90cd75c56517bef952a03240f82f525d2e
Author:     Randall Stewart <rrs@FreeBSD.org>
AuthorDate: 2023-06-28 15:18:47 +0000
Commit:     Randall Stewart <rrs@FreeBSD.org>
CommitDate: 2023-06-28 15:18:47 +0000

    tcp: With the right options in the kernel cc_cubic stays in slowstart always.
    
    So this is a subtle bug I have found in cubic. If you compile a number of options into the kernel (accounting and tracking) then
    all of the kernel code "knows" the proper offset of t_rttupdatecnt however cubic does not see the options (and htcp too) and thus
    will look for the count in the wrong place seeing 0. Which then means it never builds an MIN RTT which then means it
    always hangs in slowstart.
    
    The solution is to put all options that effect tcpcb size into the opt_global.h so that the kernel
    has a consistent view of the tcpcb size.
    
    Reviewed by: tuexen, rscheff
    Sponsored by: Netflix Inc
    Differential Revision:https://reviews.freebsd.org/D40761
---
 sys/conf/options | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sys/conf/options b/sys/conf/options
index 7a34fa0f7333..6f1a488bf33f 100644
--- a/sys/conf/options
+++ b/sys/conf/options
@@ -229,7 +229,7 @@ SYSVSHM		opt_sysvipc.h
 SW_WATCHDOG	opt_watchdog.h
 TCPHPTS         opt_inet.h
 TCP_REQUEST_TRK opt_global.h
-TCP_ACCOUNTING	opt_inet.h
+TCP_ACCOUNTING	opt_global.h
 #
 # TCP SaD Detection is an experimental Sack attack Detection (SaD)
 # algorithm that uses "normal" behaviour with SACK's to detect