svn commit: r287775 - in head/sys: net netinet

[Alexander V. Chernikov]

14.09.2015, 11:36, "Hans Petter Selasky" <hselasky at FreeBSD.org>:
> Author: hselasky
> Date: Mon Sep 14 08:36:22 2015
> New Revision: 287775
> URL: https://svnweb.freebsd.org/changeset/base/287775
>
> Log:
>   Update TSO limits to include all headers.
>
>   To make driver programming easier the TSO limits are changed to
>   reflect the values used in the BUSDMA tag a network adapter driver is
>   using. The TCP/IP network stack will subtract space for all linklevel
>   and protocol level headers and ensure that the full mbuf chain passed
>   to the network adapter fits within the given limits.
>
>   Implementation notes:
>
>   If a network adapter driver needs to fixup the first mbuf in order to
>   support VLAN tag insertion, the size of the VLAN tag should be
>   subtracted from the TSO limit. Else not.
>
>   Network adapters which typically inline the complete header mbuf could
>   technically transmit one more segment. This patch does not implement a
>   mechanism to recover the last segment for data transmission. It is
>   believed when sufficiently large mbuf clusters are used, the segment
>   limit will not be reached and recovering the last segment will not
>   have any effect.
>
>   The current TSO algorithm tries to send MTU-sized packets, where the
>   MTU typically is 1500 bytes, which gives 1448 bytes of TCP data
>   payload per packet for IPv4. That means if the TSO length limitiation
>   is set to 65536 bytes, there will be a data payload remainder of
>   (65536 - 1500) mod 1448 bytes which is equal to 324 bytes. Trying to
>   recover total TSO length due to inlining mbuf header data will not
>   have any effect, because adding or removing the ETH/IP/TCP headers
>   to or from 324 bytes will not cause more or less TCP payload to be
>   TSO'ed.
>
>   Existing network adapter limits will be updated separately.
>
>   Differential Revision: https://reviews.freebsd.org/D3458
Probably different revision id ?

>   Reviewed by: rmacklem
>   MFC after: 2 weeks
>
> Modified:
>   head/sys/net/if_var.h
>   head/sys/netinet/tcp_output.c
>
> Modified: head/sys/net/if_var.h
> ==============================================================================
> --- head/sys/net/if_var.h Mon Sep 14 08:01:05 2015 (r287774)
> +++ head/sys/net/if_var.h Mon Sep 14 08:36:22 2015 (r287775)
> @@ -243,11 +243,12 @@ struct ifnet {
>           * count limit does not apply. If all three fields are zero,
>           * there is no TSO limit.
>           *
> - * NOTE: The TSO limits only apply to the data payload part of
> - * a TCP/IP packet. That means there is no need to subtract
> - * space for ethernet-, vlan-, IP- or TCP- headers from the
> - * TSO limits unless the hardware driver in question requires
> - * so.
> + * NOTE: The TSO limits should reflect the values used in the
> + * BUSDMA tag a network adapter is using to load a mbuf chain
> + * for transmission. The TCP/IP network stack will subtract
> + * space for all linklevel and protocol level headers and
> + * ensure that the full mbuf chain passed to the network
> + * adapter fits within the given limits.
>           */
>          u_int if_hw_tsomax; /* TSO maximum size in bytes */
>          u_int if_hw_tsomaxsegcount; /* TSO maximum segment count */
>
> Modified: head/sys/netinet/tcp_output.c
> ==============================================================================
> --- head/sys/netinet/tcp_output.c Mon Sep 14 08:01:05 2015 (r287774)
> +++ head/sys/netinet/tcp_output.c Mon Sep 14 08:36:22 2015 (r287775)
> @@ -811,7 +811,8 @@ send:
>                           */
>                          if (if_hw_tsomax != 0) {
>                                  /* compute maximum TSO length */
> - max_len = (if_hw_tsomax - hdrlen);
> + max_len = (if_hw_tsomax - hdrlen -
> + max_linkhdr);
>                                  if (max_len <= 0) {
>                                          len = 0;
>                                  } else if (len > max_len) {
> @@ -826,6 +827,15 @@ send:
>                           */
>                          if (if_hw_tsomaxsegcount != 0 &&
>                              if_hw_tsomaxsegsize != 0) {
> + /*
> + * Subtract one segment for the LINK
> + * and TCP/IP headers mbuf that will
> + * be prepended to this mbuf chain
> + * after the code in this section
> + * limits the number of mbufs in the
> + * chain to if_hw_tsomaxsegcount.
> + */
> + if_hw_tsomaxsegcount -= 1;
>                                  max_len = 0;
>                                  mb = sbsndmbuf(&so->so_snd, off, &moff);