packet: introduce PACKET_QDISC_BYPASS socket option

This patch introduces a PACKET_QDISC_BYPASS socket option, that
allows for using a similar xmit() function as in pktgen instead
of taking the dev_queue_xmit() path. This can be very useful when
PF_PACKET applications are required to be used in a similar
scenario as pktgen, but with full, flexible packet payload that
needs to be provided, for example.

On default, nothing changes in behaviour for normal PF_PACKET
TX users, so everything stays as is for applications. New users,
however, can now set PACKET_QDISC_BYPASS if needed to prevent
own packets from i) reentering packet_rcv() and ii) to directly
push the frame to the driver.

In doing so we can increase pps (here 64 byte packets) for
PF_PACKET a bit:

  # CPUs -- QDISC_BYPASS   -- qdisc path -- qdisc path[**]
  1 CPU  ==  1,509,628 pps --  1,208,708 --  1,247,436
  2 CPUs ==  3,198,659 pps --  2,536,012 --  1,605,779
  3 CPUs ==  4,787,992 pps --  3,788,740 --  1,735,610
  4 CPUs ==  6,173,956 pps --  4,907,799 --  1,909,114
  5 CPUs ==  7,495,676 pps --  5,956,499 --  2,014,422
  6 CPUs ==  9,001,496 pps --  7,145,064 --  2,155,261
  7 CPUs == 10,229,776 pps --  8,190,596 --  2,220,619
  8 CPUs == 11,040,732 pps --  9,188,544 --  2,241,879
  9 CPUs == 12,009,076 pps -- 10,275,936 --  2,068,447
 10 CPUs == 11,380,052 pps -- 11,265,337 --  1,578,689
 11 CPUs == 11,672,676 pps -- 11,845,344 --  1,297,412
 [...]
 20 CPUs == 11,363,192 pps -- 11,014,933 --  1,245,081

 [**]: qdisc path with packet_rcv(), how probably most people
       seem to use it (hopefully not anymore if not needed)

The test was done using a modified trafgen, sending a simple
static 64 bytes packet, on all CPUs.  The trick in the fast
"qdisc path" case, is to avoid reentering packet_rcv() by
setting the RAW socket protocol to zero, like:
socket(PF_PACKET, SOCK_RAW, 0);

Tradeoffs are documented as well in this patch, clearly, if
queues are busy, we will drop more packets, tc disciplines are
ignored, and these packets are not visible to taps anymore. For
a pktgen like scenario, we argue that this is acceptable.

The pointer to the xmit function has been placed in packet
socket structure hole between cached_dev and prot_hook that
is hot anyway as we're working on cached_dev in each send path.

Done in joint work together with Jesper Dangaard Brouer.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 21 insertions, 0 deletions

diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 8e48e3b14227..4288ffafba9f 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -953,6 +953,27 @@ int main(int argc, char **argp)
 }
 
 -------------------------------------------------------------------------------
++ PACKET_QDISC_BYPASS
+-------------------------------------------------------------------------------
+
+If there is a requirement to load the network with many packets in a similar
+fashion as pktgen does, you might set the following option after socket
+creation:
+
+    int one = 1;
+    setsockopt(fd, SOL_PACKET, PACKET_QDISC_BYPASS, &one, sizeof(one));
+
+This has the side-effect, that packets sent through PF_PACKET will bypass the
+kernel's qdisc layer and are forcedly pushed to the driver directly. Meaning,
+packet are not buffered, tc disciplines are ignored, increased loss can occur
+and such packets are also not visible to other PF_PACKET sockets anymore. So,
+you have been warned; generally, this can be useful for stress testing various
+components of a system.
+
+On default, PACKET_QDISC_BYPASS is disabled and needs to be explicitly enabled
+on PF_PACKET sockets.
+
+-------------------------------------------------------------------------------
 + PACKET_TIMESTAMP
 -------------------------------------------------------------------------------