Commit graph

811 commits

Author SHA1 Message Date
Stefano Brivio
7ecf693297 pasta, tcp: Don't set TCP_CORK on spliced sockets
...throughput isn't everything: this leads (of course) to horrible
latency with small, sparse messages. As a consequence, there's no
need to set TCP_NODELAY either.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-16 08:49:58 +02:00
Stefano Brivio
a7eb8bb2f6 tcp: Fix setting window from maximum ACK sequence in batch
If we're at the first message in a batch, it's safe to get the
window value from it, and there's no need to subtract anything for
a comparison on that's not even done -- we'll override it later in
any case if we find messages with a higher ACK sequence number.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-16 08:20:50 +02:00
Stefano Brivio
3be131280d pasta, tcp: Set pipe descriptor numbers to -1 after closing
...so that we don't try to close them again, even if harmless.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-16 08:19:39 +02:00
Stefano Brivio
d481578882 pasta, tcp: Drop EPOLLET for spliced, established connections
...tcp_handler_splice() doesn't guarantee we read all the available
data, the sending buffer might be full.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-16 08:17:18 +02:00
Stefano Brivio
45d9b0000e tcp: Read SO_SNDBUF unconditionally
Checking it only when the cached value is smaller than the current
window of the receiver is not enough: it might shrink further while
the receiver window is growing.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-16 08:14:01 +02:00
Stefano Brivio
474b8e6fb7 pasta: Clean up FIN connection flags once a connection is deleted
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-15 10:43:59 +02:00
Stefano Brivio
57d17292f9 pasta: Set spliced connection flag in epoll reference on compaction
...otherwise, we'll mix indices with non-spliced connections.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-15 10:41:31 +02:00
Stefano Brivio
a041f6d920 pasta: Clean up namespace processes on exit, reap zombies from clone()
If pasta created the namespace, it's probably expected that processes
started in the same namespace are terminated once pasta exits. Scan
procfs namespace links for corresponding processes, send SIGQUIT and
SIGKILL (after one second) if found.

While at it, make the signal handler reap otherwise-zombies resulting
from clone().

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-15 00:32:23 +02:00
Stefano Brivio
7d81b3c646 checksum: Add checksum.h
I forgot to commit this.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-14 19:02:36 +02:00
Stefano Brivio
9af8e0a1a7 tcp: Request retransmission with updated sequence also on partial write to socket
If we couldn't write the whole batch of received packets to the socket,
and we have missing segments, we still need to request their
retransmission right away, otherwise it will take ages for the guest to
figure out we're missing them.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-14 16:57:50 +02:00
Stefano Brivio
a616357c86 tcp: In ESTABLISHED state, acknowledge segments as they're sent to the socket
...instead of waiting for the remote peer to do that -- it's
especially important in case we request retransmissions from the
guest, but it also helps speeding up slow start. This should
probably be a configurable behaviour in the future.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-14 16:57:50 +02:00
Stefano Brivio
621c589d36 tcp: Properly time out ACK wait from tap
Seen with iperf3: a control connection is established, no data flows
for a while, all segments are acknowledged. The socket starts closing
it, and we immediately time out because the last ACK from tap was one
minute before that.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-14 16:57:50 +02:00
Stefano Brivio
7c82ea4dd9 tcp: Don't mistake a FIN segment with no data for a Fast Retransmit request
It carries no data and usually duplicates the previous ACK sequence,
but it's just a FIN.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-14 16:57:50 +02:00
Stefano Brivio
c162f1e801 tcp: Check errno on sendmmsg() failure, not just the return value
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-14 16:57:50 +02:00
Stefano Brivio
2c009e8e6f tcp: Make sure sending window is initialised before sending to tap
Seen with iperf3: the first packet from socket (data connection) is
65520 bytes and doesn't fit in the window.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-14 16:57:50 +02:00
Stefano Brivio
e0530a802f qrap: Set x-txburst as temporary workaround for virtio-net TX stall
Flooding a virtio-net interface connected to a socket back-end results
in a TX stall I'm still debugging. The stall goes away by setting a
higher value for x-txburst (256 by default).

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
3994fc8f58 udp: Reset iov_base after sending partial message on sendmmsg() failure
We set the length while processing messges, but the starting address is
pre-initialised.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
ecf1f97564 udp: Fix comparison of seen IPv4 address for local connections
c->addr4_seen is stored in network order.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
e58828f340 tcp: Fixes for closing states, spliced connections, out-of-order packets, etc.
This fixes a number of issues found with some heavier testing with
uperf and neper:

- in most closing states, we can still accept data, check for EPOLLIN
  when appropriate

- introduce a new state, ESTABLISHED_SOCK_FIN_SENT, to track the fact
  we already sent a FIN segment to the tap device, for proper sequence
  number bookkeeping

- for pasta mode only: spliced connections also need tracking of
  (inferred) FIN segments and clean half-pipe shutdowns

- streamline resetting epoll_wait bitmaps with a new function,
  tcp_tap_epoll_mask(), instead of repeating the logic all over the
  place

- set EPOLLET for tap connections too, whenever we are waiting for
  EPOLLRDHUP or an event from the tap to proceed with data transfer,
  to avoid useless loops with EPOLLIN set

- impose an additional limit on the sending window advertised to the
  guest, given by SO_SNDBUF: it makes no sense to completely fill
  the sending buffer and send a zero window: stop a bit before we
  hit that

- handle *all* interrupted system calls as needed

- simplify the logic for reordering of out-of-order segments received
  from tap: it's not a corner case, and the previous logic allowed
  for deadloops

- fix comparison of seen IPv4 address when we get a new connection
  from a socket directed to the configured guest address

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
5e23b1ef44 tap: Fix calculation of number of tap scatter-gather IO messages
Messages are typically smaller than ETH_MAX_MTU.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
089dec90ca pasta: Set ping_group_range upon namespace creation
...this allows processes running as the only group available in the
namespace to create ICMP Echo sockets.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
9d19f5bc73 passt: Add epoll event indication and passt/pasta mode in socket debug message
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
3df5debf37 conf: Fix help message about default behaviour for UDP port forwarding
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
ec2b58ea4d conf, dhcp, ndp: Fix message about default MTU, make NDP consistent
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
8e9333616a udp: Fix retry mechanism on partial sendmmsg()
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
04d62bb013 qrap: Drop debugging left-overs, enable timeout for connect() too
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
b15e97cb9d conf: Introduce PASST_LEGACY_NO_OPTIONS ifdef for legacy
Before introducing options, the default behaviour in passt mode was
to forward all ports, to run in foreground and to log to stderr.
Make it a bit more convenient to restore that at build time.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-09 15:40:04 +02:00
Stefano Brivio
647a413794 tcp, udp: Restore usage of gateway for guest to connect to local host
This went lost in a recent rework: if the guest wants to connect
directly to the host, it can use the address of the default gateway.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
f29c48db6b Makefile: Make sure destination directories exist on install
Mostly theoretical, but convenient for testing.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
77d4efa236 udp: Handle partial failure in sendmmsg() to UNIX domain socket
Similarly to the handling introduced by commit "tcp: Proper error
handling for sendmmsg() to UNIX domain socket" for TCP, we need to
deal with partial sendmmsg() failures for UDP as well.

Here, we can lose messages, but we need to make sure that the last
message is delivered completely, otherwise qemu will fail to
reassemble further packets. For UDP, this is somewhat complicated
by the fact that one message might include multiple datagrams, and
we need to respect message boundaries: go through headers, and
calculate what we need to re-send, if anything.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
cd04d238b2 doc/demo: Also forward all UDP ports from namespace
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
564fbca39a doc/demo: Explicitly run in foreground, drop pipe to cat
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
e1c94637ad dhcp: Send option 121 if the default gateway is not on the assigned subnet
This enables CirrOS with udhcpc to set up a route to a gateway
that's not on the assigned subnet, together with:
	https://bugs.launchpad.net/cirros/+bug/1190372

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
7eb155ab8f conf: Fix check for IPv6 DNS address being already set
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
64c0f20ab3 arp: Don't resolve own, configured IPv4 address
DHCP clients might try to resolve the assigned address to check if it's
already in use: don't resolve the configured IPv4 address.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
77c72b31ed Makefile: Quick hack to build convenience Debian and RPM packages
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
b9c6fca469 Makefile: Add install, uninstall targets
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
da20f57f19 passt, qrap: Add man pages
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
05432945bb qrap: Minor fixes in comments and usage message
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
d5b3467056 pasta: If a new namespace is created, wait for it to be ready before proceeding
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
088d19fbb8 conf: Minor fixes for usage message
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
2166c5872e arp: Don't answer announcements from guest or namespace
Depending on the configuration, the host might have the same address.
Don't answer them to avoid a duplicate IP address detection.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
1e49d194d0 passt, pasta: Introduce command-line options and port re-mapping
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 17:00:27 +02:00
Stefano Brivio
1b1b27c06a tcp: Fixes for early data in SOCK_SYN_SENT, closing states, clamping window
More details here after rebase.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 16:49:21 +02:00
Stefano Brivio
75a7239e5b tap: Make sure we don't receive frames bigger than ETH_MAX_MTU from qemu
And while at it, remove some attributes that are not needed anymore
after introducing command line options.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 16:49:21 +02:00
Stefano Brivio
353185cd36 dhcpv6: Fix parsing for IA_ADDR suboptions of IA_NA/IA_TA
Once we're past the IA_NA or IA_TA option itself, before we start
looking for IA_ADDR suboptions, we need to subtract the length
of the option we parsed so far, otherwise we might end up reading
past the end of the message, or miss some parts.

While at it, streamline calculations in dhcpv6_opt().

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-09-01 16:49:21 +02:00
Stefano Brivio
d2272f74f7 tcp: Proper error handling for sendmmsg() to UNIX domain socket
As data from socket is forwarded to the guest, sendmmsg() might send
fewer bytes than requested in three different ways:

- failing altogether with a negative error code -- ignore that,
  we'll get an error on the UNIX domain socket later if there's
  really an issue with it and reset the connection to the guest

- sending less than 'vlen' messages -- instead of assuming success
  in that case and waiting for the guest to send a duplicate ACK
  indicating missing data, update the sequence number according to
  what was actually sent and spare some retransmissions

- somewhat unexpectedly to me, sending 'vlen' or less than 'vlen'
  messages, returning up to 'vlen', with the last message being
  partially sent, and no further indication of errors other than
  the returned msg_len for the last partially sent message being
  less than iov_len.

  In this case, we would assume success and proceed as nothing
  happened. However, qemu would fail to parse any further message,
  having received a partial descriptor, and eventually close the
  connection, logging:

	serious error: oversized packet received,connection terminated.

  as the length descriptor for the next message would be sourced
  from the middle of the next successfully sent message, not from
  its header.

  Handle this by checking the msg_len returned for the last (even
  partially) sent message, and force re-sending the missing bytes,
  if any, with a blocking sendmsg() -- qemu must not receive
  anything else than that anyway.

While at it, allow to send up to 64KiB for each message, the
previous 32KiB limit isn't actually required, and just switch to a
new message at each iteration on sending buffers, they are already
MSS-sized anyway, so the check in the loop isn't really needed.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-08-26 23:30:22 +02:00
Stefano Brivio
cc2ebfd5f2 tcp: Never send ACK because of pending unacknowleged data when sending SYN
With a kernel older than 5.3 (no_snd_wnd set), ack_pending in
tcp_send_to_tap() might be true at the beginning of a new connection
initiated by a socket. This means we send the first SYN segment to the
tap together with ACK set, which is clearly invalid and triggers the
receiver to reply with an RST segment right away.

Set ack_pending to 0 whenever we're sending a SYN segment. In case of a
SYN, ACK segment sent by the caller, the caller passes the ACK flag
explicitly.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-08-24 18:27:24 +02:00
Stefano Brivio
f2e3b9defd tcp: Drop EPOLLET for non-spliced connections
Socket-facing functions don't guarantee that all data is handled before
they return: stick to level-triggered mode for TCP sockets.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-08-24 18:24:11 +02:00
Stefano Brivio
ce24fe0b3f util: Don't close ping sockets if bind() fails
...they're still usable, thanks to the workaround implemented in
icmp_tap_handler().

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-08-04 01:44:58 +02:00