d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Handle a rare edge case with nearly full TCP receive buffers. If a TCP

Browse Source 
buffer fills up causing the remote sender to enter into persist mode, but
there is still room available in the receive buffer when a window probe
arrives (either due to window scaling, or due to the local application
very slowing draining data from the receive buffer), then the single byte
of data in the window probe is accepted.  However, this can cause rcv_nxt
to be greater than rcv_adv.  This condition will only last until the next
ACK packet is pushed out via tcp_output(), and since the previous ACK
advertised a zero window, the ACK should be pushed out while the TCP
pcb is write-locked.

During the window while rcv_nxt is greather than rcv_adv, a few places
would compute the remaining receive window via rcv_adv - rcv_nxt.
However, this value was then (uint32_t)-1.  On a 64 bit machine this
could expand to a positive 2^32 - 1 when cast to a long.  In particular,
when calculating the receive window in tcp_output(), the result would be
that the receive window was computed as 2^32 - 1 resulting in advertising
a far larger window to the remote peer than actually existed.

Fix various places that compute the remaining receive window to either
assert that it is not negative (i.e. rcv_nxt <= rcv_adv), or treat the
window as full if rcv_nxt is greather than rcv_adv.

Reviewed by:	bz
MFC after:	1 month
This commit is contained in:
jhb 2011-05-02 21:05:52 +00:00
parent 96038e6533
commit 7c6829ee7d
3 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
sys/netinet/tcp_input.c
View File

@ -1831,6 +1831,9 @@ tcp_do_segment(struct mbuf *m, struct tcphdr *th, struct socket *so,
win = sbspace(&so->so_rcv);
if (win < 0)
win = 0;
KASSERT(SEQ_GEQ(tp->rcv_adv, tp->rcv_nxt),
("tcp_input negative window: tp %p rcv_nxt %u rcv_adv %u", tp,
tp->rcv_adv, tp->rcv_nxt));
tp->rcv_wnd = imax(win, (int)(tp->rcv_adv - tp->rcv_nxt));
/* Reset receive buffer auto scaling when not in bulk receive mode. */
@ -2868,7 +2871,10 @@ dodata: /* XXX */
* buffer size.
* XXX: Unused.
*/
len = so->so_rcv.sb_hiwat - (tp->rcv_adv - tp->rcv_nxt);
if (SEQ_GT(tp->rcv_adv, tp->rcv_nxt))
len = so->so_rcv.sb_hiwat - (tp->rcv_adv - tp->rcv_nxt);
else
len = so->so_rcv.sb_hiwat;
#endif
} else {
m_freem(m);

17
sys/netinet/tcp_output.c
View File

@ -561,15 +561,21 @@ after_sack_rexmit:
* taking into account that we are limited by
* TCP_MAXWIN << tp->rcv_scale.
*/
long adv = min(recwin, (long)TCP_MAXWIN << tp->rcv_scale) -
(tp->rcv_adv - tp->rcv_nxt);
long adv;
int oldwin;
adv = min(recwin, (long)TCP_MAXWIN << tp->rcv_scale);
if (SEQ_GT(tp->rcv_adv, tp->rcv_nxt)) {
oldwin = (tp->rcv_adv - tp->rcv_nxt);
adv -= oldwin;
} else
oldwin = 0;
/*
* If the new window size ends up being the same as the old
* size when it is scaled, then don't force a window update.
*/
if ((tp->rcv_adv - tp->rcv_nxt) >> tp->rcv_scale ==
(adv + tp->rcv_adv - tp->rcv_nxt) >> tp->rcv_scale)
if (oldwin >> tp->rcv_scale == (adv + oldwin) >> tp->rcv_scale)
goto dontupdate;
if (adv >= (long) (2 * tp->t_maxseg))
goto send;
@ -1008,7 +1014,8 @@ send:
if (recwin < (long)(so->so_rcv.sb_hiwat / 4) &&
recwin < (long)tp->t_maxseg)
recwin = 0;
if (recwin < (long)(tp->rcv_adv - tp->rcv_nxt))
if (SEQ_GT(tp->rcv_adv, tp->rcv_nxt) &&
recwin < (long)(tp->rcv_adv - tp->rcv_nxt))
recwin = (long)(tp->rcv_adv - tp->rcv_nxt);
if (recwin > (long)TCP_MAXWIN << tp->rcv_scale)
recwin = (long)TCP_MAXWIN << tp->rcv_scale;

3
sys/netinet/tcp_timewait.c
View File

@ -242,6 +242,9 @@ tcp_twstart(struct tcpcb *tp)
/*
* Recover last window size sent.
*/
KASSERT(SEQ_GEQ(tp->rcv_adv, tp->rcv_nxt),
("tcp_twstart negative window: tp %p rcv_nxt %u rcv_adv %u", tp,
tp->rcv_adv, tp->rcv_nxt));
tw->last_win = (tp->rcv_adv - tp->rcv_nxt) >> tp->rcv_scale;
/*