Fanout uses a per net global namespace. A process that intends to create
a new fanout group can accidentally join an existing group. It is not
possible to detect this.
Add socket option PACKET_FANOUT_FLAG_UNIQUEID. When specified the
supplied fanout group id must be set to 0, and the kernel chooses an id
that is not already in use. This is an ephemeral flag so that
other sockets can be added to this group using setsockopt, but NOT
specifying this flag. The current getsockopt(..., PACKET_FANOUT, ...)
can be used to retrieve the new group id.
We assume that there are not a lot of fanout groups and that this is not
a high frequency call.
The method assigns ids starting at zero and increases until it finds an
unused id. It keeps track of the last assigned id, and uses it as a
starting point to find new ids.
Signed-off-by: Mike Maloney <maloney@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add fanout mode PACKET_FANOUT_EBPF that accepts an en extended BPF
program to select a socket.
Update the internal eBPF program by passing to socket option
SOL_PACKET/PACKET_FANOUT_DATA a file descriptor returned by bpf().
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add fanout mode PACKET_FANOUT_CBPF that accepts a classic BPF program
to select a socket.
This avoids having to keep adding special case fanout modes. One
example use case is application layer load balancing. The QUIC
protocol, for instance, encodes a connection ID in UDP payload.
Also add socket option SOL_PACKET/PACKET_FANOUT_DATA that updates data
associated with the socket group. Fanout mode PACKET_FANOUT_CBPF is the
only user so far.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rollover indicates exceptional conditions. Export a counter to inform
socket owners of this state.
If no socket with sufficient room is found, rollover fails. Also count
these events.
Finally, also count when flows are rolled over early thanks to huge
flow detection, to validate its correctness.
Tested:
Read counters in bench_rollover on all other tests in the patchset
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce TP_STATUS_CSUM_VALID tp_status flag to tell the
af_packet user that at least the transport header checksum
has been already validated.
For now, the flag may be set for incoming packets only.
Signed-off-by: Alexander Drozdov <al.drozdov@gmail.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
No device driver will ever return an skb_shared_info structure with
syststamp non-zero, so remove the branch that tests for this and
optionally marks the packet timestamp as TP_STATUS_TS_SYS_HARDWARE.
Do not remove the definition TP_STATUS_TS_SYS_HARDWARE, as processes
may refer to it.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds a queue mapping mode to the fanout operation of af_packet
sockets. This allows user space af_packet users to better filter on flows
ingressing and egressing via a specific hardware queue, and avoids the potential
packet reordering that can occur when FANOUT_CPU is being used and irq affinity
varies.
Tested successfully by myself. applies to net-next
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to facilitate development for netlink protocol dissector,
fill the unused field skb->pkt_type of the cloned skb with a hint
of the address space of the new owner (receiver) socket in the
notion of "to kernel" resp. "to user".
At the time we invoke __netlink_deliver_tap_skb(), we already have
set the new skb owner via netlink_skb_set_owner_r(), so we can use
that for netlink_is_kernel() probing.
In normal PF_PACKET network traffic, this field denotes if the
packet is destined for us (PACKET_HOST), if it's broadcast
(PACKET_BROADCAST), etc.
As we only have 3 bit reserved, we can use the value (= 6) of
PACKET_FASTROUTE as it's _not used_ anywhere in the whole kernel
and not supported anywhere, and packets of such type were never
exposed to user space, so there are no overlapping users of such
kind. Thus, as wished, that seems the only way to make both
PACKET_* values non-overlapping and therefore device agnostic.
By using those two flags for netlink skbs on nlmon devices, they
can be made available and picked up via sll_pkttype (previously
unused in netlink context) in struct sockaddr_ll. We now have
these two directions:
- PACKET_USER (= 6) -> to user space
- PACKET_KERNEL (= 7) -> to kernel space
Partial `ip a` example strace for sa_family=AF_NETLINK with
detected nl msg direction:
syscall: direction:
sendto(3, ...) = 40 /* to kernel */
recvmsg(3, ...) = 3404 /* to user */
recvmsg(3, ...) = 1120 /* to user */
recvmsg(3, ...) = 20 /* to user */
sendto(3, ...) = 40 /* to kernel */
recvmsg(3, ...) = 168 /* to user */
recvmsg(3, ...) = 144 /* to user */
recvmsg(3, ...) = 20 /* to user */
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
This enables userspace to get VLAN TPID as well as the VLAN TCI.
Signed-off-by: Atzm Watanabe <atzm@stratosphere.co.jp>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT.
Explicitly defining and zeroing the gap of this makes additional changes
easier.
Signed-off-by: Atzm Watanabe <atzm@stratosphere.co.jp>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
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>
We currently allow for different fanout scheduling policies in pf_packet
such as scheduling by skb's rxhash, round-robin, by cpu, and rollover.
Also allow for a random, equidistributed selection of the socket from the
fanout process group.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, there is no way to find out which timestamp is reported in
tpacket{,2,3}_hdr's tp_sec, tp_{n,u}sec members. It can be one of
SOF_TIMESTAMPING_SYS_HARDWARE, SOF_TIMESTAMPING_RAW_HARDWARE,
SOF_TIMESTAMPING_SOFTWARE, or a fallback variant late call from the
PF_PACKET code in software.
Therefore, report in the tp_status member of the ring buffer which
timestamp has been reported for RX and TX path. This should not break
anything for the following reasons: i) in RX ring path, the user needs
to test for tp_status & TP_STATUS_USER, and later for other flags as
well such as TP_STATUS_VLAN_VALID et al, so adding other flags will
do no harm; ii) in TX ring path, time stamps with PACKET_TIMESTAMP
socketoption are not available resp. had no effect except that the
application setting this is buggy. Next to TP_STATUS_AVAILABLE, the
user also should check for other flags such as TP_STATUS_WRONG_FORMAT
to reclaim frames to the application. Thus, in case TX ts are turned
off (default case), nothing happens to the application logic, and in
case we want to use this new feature, we now can also check which of
the ts source is reported in the status field as provided in the docs.
Reported-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This makes it more readable and clearer what bits are still free to
use. The compiler reduces this to a constant for us anyway.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Changes:
v3->v2: rebase (no other changes)
passes selftest
v2->v1: read f->num_members only once
fix bug: test rollover mode + flag
Minimize packet drop in a fanout group. If one socket is full,
roll over packets to another from the group. Maintain flow
affinity during normal load using an rxhash fanout policy, while
dispersing unexpected traffic storms that hit a single cpu, such
as spoofed-source DoS flows. Rollover breaks affinity for flows
arriving at saturated sockets during those conditions.
The patch adds a fanout policy ROLLOVER that rotates between sockets,
filling each socket before moving to the next. It also adds a fanout
flag ROLLOVER. If passed along with any other fanout policy, the
primary policy is applied until the chosen socket is full. Then,
rollover selects another socket, to delay packet drop until the
entire system is saturated.
Probing sockets is not free. Selecting the last used socket, as
rollover does, is a greedy approach that maximizes chance of
success, at the cost of extreme load imbalance. In practice, with
sufficiently long queues to absorb bursts, sockets are drained in
parallel and load balance looks uniform in `top`.
To avoid contention, scales counters with number of sockets and
accesses them lockfree. Values are bounds checked to ensure
correctness.
Tested using an application with 9 threads pinned to CPUs, one socket
per thread and sufficient busywork per packet operation to limits each
thread to handling 32 Kpps. When sent 500 Kpps single UDP stream
packets, a FANOUT_CPU setup processes 32 Kpps in total without this
patch, 270 Kpps with the patch. Tested with read() and with a packet
ring (V1).
Also, passes psock_fanout.c unit test added to selftests.
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The tx data offset of packet mmap tx ring used to be :
(TPACKET2_HDRLEN - sizeof(struct sockaddr_ll))
The problem is that, with SOCK_RAW socket, the payload (14 bytes after
the beginning of the user data) is misaligned.
This patch allows to let the user gives an offset for it's tx data if
he desires.
Set sock option PACKET_TX_HAS_OFF to 1, then specify in each frame of
your tx ring tp_net for SOCK_DGRAM, or tp_mac for SOCK_RAW.
Signed-off-by: Paul Chavent <paul.chavent@onera.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
