Hans Petter Selasky wrote:
> On 09/13/14 18:54, Adrian Chadd wrote:
> > Hi,
> >
> > Just for the record:
> >
> > * I'm glad you're tackling the TSO config stuff;
> > * I'm not glad you're trying to pack it into a u_int rather than
> > creating a new structure and adding fields for it.
> >
> > I appreciate that you're trying to rush this in before 10.1, but
> > this
> > is exactly why things shouldn't be rushed in before release
> > deadlines.
> > :)
> >
> > I'd really like to see this be broken out as a structure and the
> > bit
> > shifting games for what really shouldn't be packed into a u_int
> > fixed.
> > Otherwise this is going to be deadweight that has to persist past
> > 11.0.
> >
>
> Hi Adrian,
>
> I can make that change for -current, making the new structure and
> such.
> This change was intended for 10 where there is only one u_int for
> this
> information. Or do you want me to change that in 10 too?
>
> --HPS
>
>
>
Btw, your patch calls sbsndptr() in tcp_output(), which advances
sb_sndptroff and sb_sndptr by the length.
Then it loops around and reduces the length for the case where
there are too many mbufs in the chain.
I don't know this algorithm well enough to know if advancing
sb_sndptroff and sb_sndptr by too much for this case will
cause a problem?
I avoided the question by implementing sbsndmbuf() that was cloned
from sbsndptr() to avoid this when I did my draft patch. It is in
the attached patch, in case it is useful. (It avoids updating
sb_sndptroff and sb_sndptr.)
rick
--- kern/uipc_sockbuf.c.sav 2014-01-30 20:27:17.000000000 -0500
+++ kern/uipc_sockbuf.c 2014-01-30 22:12:08.000000000 -0500
@@ -965,6 +965,39 @@ sbsndptr(struct sockbuf *sb, u_int off,
}
/*
+ * Return the first mbuf for the provided offset.
+ */
+struct mbuf *
+sbsndmbuf(struct sockbuf *sb, u_int off, long *first_len)
+{
+ struct mbuf *m;
+
+ KASSERT(sb->sb_mb != NULL, ("%s: sb_mb is NULL", __func__));
+
+ *first_len = 0;
+ /*
+ * Is off below stored offset? Happens on retransmits.
+ * If so, just use sb_mb.
+ */
+ if (sb->sb_sndptr == NULL || sb->sb_sndptroff > off)
+ m = sb->sb_mb;
+ else {
+ m = sb->sb_sndptr;
+ off -= sb->sb_sndptroff;
+ }
+ while (off > 0 && m != NULL) {
+ if (off < m->m_len)
+ break;
+ off -= m->m_len;
+ m = m->m_next;
+ }
+ if (m != NULL)
+ *first_len = m->m_len - off;
+
+ return (m);
+}
+
+/*
* Drop a record off the front of a sockbuf and move the next record to the
* front.
*/
--- sys/sockbuf.h.sav 2014-01-30 20:42:28.000000000 -0500
+++ sys/sockbuf.h 2014-01-30 22:08:43.000000000 -0500
@@ -153,6 +153,8 @@ int sbreserve_locked(struct sockbuf *sb,
struct thread *td);
struct mbuf *
sbsndptr(struct sockbuf *sb, u_int off, u_int len, u_int *moff);
+struct mbuf *
+ sbsndmbuf(struct sockbuf *sb, u_int off, long *first_len);
void sbtoxsockbuf(struct sockbuf *sb, struct xsockbuf *xsb);
int sbwait(struct sockbuf *sb);
int sblock(struct sockbuf *sb, int flags);
--- netinet/tcp_input.c.sav 2014-01-30 19:37:52.000000000 -0500
+++ netinet/tcp_input.c 2014-01-30 19:39:07.000000000 -0500
@@ -3627,6 +3627,7 @@ tcp_mss(struct tcpcb *tp, int offer)
if (cap.ifcap & CSUM_TSO) {
tp->t_flags |= TF_TSO;
tp->t_tsomax = cap.tsomax;
+ tp->t_tsomaxsegs = cap.tsomaxsegs;
}
}
--- netinet/tcp_output.c.sav 2014-01-30 18:55:15.000000000 -0500
+++ netinet/tcp_output.c 2014-01-30 22:18:56.000000000 -0500
@@ -166,8 +166,8 @@ int
tcp_output(struct tcpcb *tp)
{
struct socket *so = tp->t_inpcb->inp_socket;
- long len, recwin, sendwin;
- int off, flags, error = 0; /* Keep compiler happy */
+ long len, recwin, sendwin, tso_tlen;
+ int cnt, off, flags, error = 0; /* Keep compiler happy */
struct mbuf *m;
struct ip *ip = NULL;
struct ipovly *ipov = NULL;
@@ -780,6 +780,24 @@ send:
}
/*
+ * Limit the number of TSO transmit segments (mbufs
+ * in mbuf list) to tp->t_tsomaxsegs.
+ */
+ cnt = 0;
+ m = sbsndmbuf(&so->so_snd, off, &tso_tlen);
+ while (m != NULL && cnt < tp->t_tsomaxsegs &&
+ tso_tlen < len) {
+ if (cnt > 0)
+ tso_tlen += m->m_len;
+ cnt++;
+ m = m->m_next;
+ }
+ if (m != NULL && tso_tlen < len) {
+ len = tso_tlen;
+ sendalot = 1;
+ }
+
+ /*
* Prevent the last segment from being
* fractional unless the send sockbuf can
* be emptied.
--- netinet/tcp_subr.c.sav 2014-01-30 19:44:35.000000000 -0500
+++ netinet/tcp_subr.c 2014-01-30 20:56:12.000000000 -0500
@@ -1800,6 +1800,12 @@ tcp_maxmtu(struct in_conninfo *inc, stru
ifp->if_hwassist & CSUM_TSO)
cap->ifcap |= CSUM_TSO;
cap->tsomax = ifp->if_hw_tsomax;
+#ifdef notyet
+ cap->tsomaxsegs = ifp->if_hw_tsomaxsegs;
+#endif
+ if (cap->tsomaxsegs == 0)
+ cap->tsomaxsegs =
+ TCPTSO_MAX_TX_SEGS_DEFAULT;
}
RTFREE(sro.ro_rt);
}
--- netinet/tcp_var.h.sav 2014-01-30 19:39:22.000000000 -0500
+++ netinet/tcp_var.h 2014-01-30 20:52:57.000000000 -0500
@@ -209,6 +209,7 @@ struct tcpcb {
u_int t_keepcnt; /* number of keepalives before close */
u_int t_tsomax; /* tso burst length limit */
+ u_int t_tsomaxsegs; /* tso burst segment limit */
uint32_t t_ispare[8]; /* 5 UTO, 3 TBD */
void *t_pspare2[4]; /* 4 TBD */
@@ -268,6 +269,11 @@ struct tcpcb {
#define TCPOOB_HAVEDATA 0x01
#define TCPOOB_HADDATA 0x02
+/*
+ * Default value for TSO maximum number of transmit segments (count of mbufs).
+ */
+#define TCPTSO_MAX_TX_SEGS_DEFAULT 30
+
#ifdef TCP_SIGNATURE
/*
* Defines which are needed by the xform_tcp module and tcp_[in|out]put
@@ -333,6 +339,7 @@ struct hc_metrics_lite { /* must stay in
struct tcp_ifcap {
int ifcap;
u_int tsomax;
+ u_int tsomaxsegs;
};
#ifndef _NETINET_IN_PCB_H_
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/svn-src-head
To unsubscribe, send any mail to "[email protected]"
