[PATCH] S2io: Large Receive Offload (LRO) feature(v2) for Neterion (s2io) 10GbE Xfram...

[PATCH] S2io: Large Receive Offload (LRO) feature(v2) for Neterion (s2io) 10GbE Xframe PCI-X and PCI-E NICs

Hi,
Below is a patch for the Large Receive Offload feature.
Please review and let us know your comments.

LRO algorithm was described in an OLS 2005 presentation, located at
ftp.s2io.com
user: linuxdocs
password: HALdocs

The same ftp site has Programming Manual for Xframe-I ASIC.
LRO feature is supported on Neterion Xframe-I, Xframe-II and
Xframe-Express 10GbE NICs.

Brief description:
The Large Receive Offload(LRO) feature is a stateless offload
that is complementary to TSO feature but on the receive path.
The idea is to combine and collapse(upto 64K maximum) in the
driver, in-sequence TCP packets belonging to the same session.
It is mainly designed to improve 1500 mtu receive performance,
since Jumbo frame performance is already close to 10GbE line
rate. Some performance numbers are attached below.

Implementation details:
1. Handle packet chains from multiple sessions(current default
MAX_LRO_SESSSIONS=32).
2. Examine each packet for eligiblity to aggregate. A packet is
considered eligible if it meets all the below criteria.
  a. It is a TCP/IP packet and L2 type is not LLC or SNAP.
  b. The packet has no checksum errors(L3 and L4).
  c. There are no IP options. The only TCP option supported is timestamps.
  d. Search and locate the LRO object corresponding to this
     socket and ensure packet is in TCP sequence.
  e. It's not a special packet(SYN, FIN, RST, URG, PSH etc. flags are not set).
  f. TCP payload is non-zero(It's not a pure ACK).
  g. It's not an IP-fragmented packet.
3. If a packet is found eligible, the LRO object is updated with
   information such as next sequence number expected, current length
   of aggregated packet and so on. If not eligible or max packets
   reached, update IP and TCP headers of first packet in the chain
   and pass it up to stack.
4. The frag_list in skb structure is used to chain packets into one
   large packet.

Kernel changes required: None

Performance results:
Main focus of the initial testing was on 1500 mtu receiver, since this
is a bottleneck not covered by the existing stateless offloads.

There are couple disclaimers about the performance results below:
1. Your mileage will vary!!!! We initially concentrated on couple pci-x
2.0 platforms that are powerful enough to push 10 GbE NIC and do not
have bottlenecks other than cpu%;  testing on other platforms is still
in progress. On some lower end systems we are seeing lower gains.

2. Current LRO implementation is still (for the most part) software based,
and therefore performance potential of the feature is far from being realized.
Full hw implementation of LRO is expected in the next version of Xframe ASIC.

Performance delta(with MTU=1500) going from LRO disabled to enabled:
IBM 2-way Xeon (x366) : 3.5 to 7.1 Gbps
2-way Opteron : 4.5 to 6.1 Gbps

Signed-off-by: Ravinandan Arakali <ravinandan.arakali@neterion.com>
Signed-off-by: Jeff Garzik <jgarzik@pobox.com>