We don't handle defragmentation of IP packets coming from the tap side,
and we're unlikely to any time soon (with our large MTU, it's not useful
for practical use cases). Currently, however, we simply ignore the
fragmentation flags and treat fragments as though they were whole IP
packets. This isn't ideal and can lead to rather cryptic behaviour if we
do receive IP fragments.
Change the code to explicitly drop fragmented packets, and print a rate
limited warning if we do encounter them.
Link: https://bugs.passt.top/show_bug.cgi?id=62
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Since commit 0515adceaa ("passt, pasta: Namespace-based sandboxing,
defer seccomp policy application"), it makes no sense to close and
reopen the tap device on error: we don't have access to /dev/net/tun
after the initial setup phase.
If we hit ENOBUFS while writing (as reported: in one case because
the kernel actually ran out of memory, with another case under
investigation), or ENOSPC, we're supposed to drop whatever data we
were trying to send: there's no room for it.
Handle EINTR just like we handled EAGAIN/EWOULDBLOCK: there's no
particular reason why sending the same data should fail again.
Anything else I can think of would be an unrecoverable error: exit
with failure then.
While at it, drop a useless cast on the write() call: it takes a
const void * anyway.
Reported-by: Gianluca Stivan <me@yawnt.com>
Reported-by: Chris Kuhn <kuhnchris@kuhnchris.eu>
Fixes: 0515adceaa ("passt, pasta: Namespace-based sandboxing, defer seccomp policy application")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
When we receive packets from the tap side, we update the addr_seen fields
to reflect the last known address of the guest or ns. For ip4.addr_seen
we, sensibly, only update if the address we've just seen isn't 0 (0.0.0.0).
This case can occur during early DHCP transactions.
We have no equivalent case for IPv6. We're less likely to hit this,
because DHCPv6 uses link-local addresses, however we can see an source
address of :: with certain multicast operations. This can bite us if we
try to make an incoming connection very early after starting pasta with
--config-net: we may have only seen some of those multicast packets,
updated addr_seen to :: and not had any "real" packets to update it to a
global address. I've seen this with some of the avocado test conversions.
In any case, it can never make sense to update addr_seen to ::, so
explicitly exclude that case.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
In practical terms, passt doesn't benefit from the additional
protection offered by the AGPL over the GPL, because it's not
suitable to be executed over a computer network.
Further, restricting the distribution under the version 3 of the GPL
wouldn't provide any practical advantage either, as long as the passt
codebase is concerned, and might cause unnecessary compatibility
dilemmas.
Change licensing terms to the GNU General Public License Version 2,
or any later version, with written permission from all current and
past contributors, namely: myself, David Gibson, Laine Stump, Andrea
Bolognani, Paul Holzinger, Richard W.M. Jones, Chris Kuhn, Florian
Weimer, Giuseppe Scrivano, Stefan Hajnoczi, and Vasiliy Ulyanov.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Commit 89e38f55 "treewide: Fix header includes to build with musl" added
extra #includes to work with musl. Unfortunately with the cppcheck version
I'm using (cppcheck-2.9-1.fc37.x86_64 in Fedora 37) this causes weird false
positives: specifically cppcheck seems to hit a #error in <bits/unistd.h>
complaining about including it directly instead of via <unistd.h> (which is
not something we're doing).
I have no idea why that would be happening; but I'm guessing it has to be
a bug in the cpp implementation in that cppcheck version. In any case,
it's possible to work around this by moving the include of <unistd.h>
before the include of <signal.h>. So, do that.
Fixes: 89e38f5540 ("treewide: Fix header includes to build with musl")
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Roughly inspired from a patch by Chris Kuhn: fix up includes so that
we can build against musl: glibc is more lenient as headers generally
include a larger amount of other headers.
Compared to the original patch, I only included what was needed
directly in C files, instead of adding blanket includes in local
header files. It's a bit more involved, but more consistent with the
current (not ideal) situation.
Reported-by: Chris Kuhn <kuhnchris+github@kuhnchris.eu>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
If we define die() as a variadic macro, passing __VA_ARGS__ to err(),
and calling exit() outside err() itself, we can drop the workarounds
introduced in commit 36f0199f6e ("conf, tap: Silence two false
positive invalidFunctionArg from cppcheck").
Suggested-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
The newly introduced die() calls exit(), but cppcheck doesn't see it
and warns about possibly invalid arguments used after the check which
triggers die(). Add return statements to silence the warnings.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
The goto here really doesn't improve clarity or brevity at all. Use a
clearer construct.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
In tap_send_frames() we send a number of frames to the tap device, then
also write them to the pcap capture file (if configured). However the tap
send can partially fail (short write()s or similar), meaning that some
of the requested frames weren't actually sent, but we still write those
frames to the capture file.
We do give a debug message in this case, but it's misleading to add frames
that we know weren't sent to the capture file. Rework to avoid this.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
David points out that using multiple counters to go over the iov
array, namely 'i' and 'iov', makes mistakes easier. We can't just use
'iov', unless we reserve an element with zero iov_len at the end,
which isn't really justified.
Simply use 'i' to iterate over the array.
Link: https://archives.passt.top/passt-dev/Y+mfenvLn3VJ7Dg5@yekko/
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
This actually leaves us with 0 uses of err(), but someone could want
to use it in the future, so we may as well leave it around.
Signed-off-by: Laine Stump <laine@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
...instead of repeatedly sending out the first one in iov.
Fixes: e21ee41ac3 ("tcp: Combine two parts of pasta tap send path together")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
In passt mode, when writing frames to the qemu socket, we might get a short
send. If we ignored this and carried on, the qemu socket would get out of
sync, because the bytes we actually sent wouldn't correspond to the length
header we already sent. tap_send_frames_passt() handles that by doing a
a blocking send to complete the message, but it has a few flaws:
* We only attempt to resend once: although it's unlikely in practice,
nothing prevents the blocking send() from also being short
* We print a debug error if send() returns non-zero.. but send() returns
the number of bytes sent, so we actually want it to return the length
of the remaining data.
Correct those flaws and also be a bit more thorough about reporting
problems here.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Currently tap_send_frames() expects the frames it is given to include the
vnet_len field, even in pasta mode which doesn't use it (although it need
not be initialized in that case). To match, tap_iov_base() and
tap_iov_len() construct the frame in that way.
This will inconvenience future changes, so alter things to set the buffers
to include just the frame needed by the tap backend type.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Currently both the TCP and UDP code need to deal in various places with the
details of the L2 headers, and also the tap-specific "vnet_len" header.
This makes abstracting the tap interface to new backends (e.g. vhost-user
or tun) more difficult.
To improve this abstraction, create a new 'tap_hdr' structure which
represents both L2 (always Ethernet at the moment, but might be vary in
future) and any additional tap specific headers (such as the qemu socket's
vnet_len field). Provide helper functions and macros to initialize, update
and use it.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
The functions which do the final steps of sending TCP packets on through
the tap interface - tcp_l2_buf_flush*() - no longer have anything that's
actually specific to TCP in them, other than comments and names. Move them
all to tap.c.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
In the case where the client writes a packet and then closes the
socket, because we receive EPOLLIN|EPOLLRDHUP together we have a
choice of whether to close the socket immediately, or read the packet
and then close the socket. Choose the latter.
This should improve fuzzing coverage and arguably is a better choice
even for regular use since dropping packets on close is bad.
See-also: https://archives.passt.top/passt-dev/20221117171805.3746f53a@elisabeth/
Signed-off-by: Richard W.M. Jones <rjones@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This passes a fully connected stream socket to passt.
Signed-off-by: Richard W.M. Jones <rjones@redhat.com>
[sbrivio: reuse fd_tap instead of adding a new descriptor,
imply --one-off on --fd, add to optstring and usage()]
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This reverts commit 198f87835d ("tap: Return -EIO from
tap_handler_passt() on inconsistent packet stream") and commit
510dace86c ("tap: Keep stream consistent if qemu length descriptor
spans two recv() calls").
I can hit occasional failures in perf/passt_tcp tests where we seem
to be getting excess data at the end of a recv(), and for some reason
I couldn't figure out yet, if we just ignore it, subsequent recv()
calls from qemu return correct data. If we close the connection, qemu
can't talk to us anymore, of course.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
If stderr is closed, after we fork to background, glibc's
implementation of perror() will try to re-open it by calling dup(),
upon which the seccomp filter causes the process to terminate,
because dup() is not included in the list of allowed syscalls.
Replace perror() calls that might happen after isolation_postfork().
We could probably replace all of them, but early ones need a bit more
attention as we have to check whether log.c functions work in early
stages.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
While it's important to fail in that case, it makes little sense to
fail quietly: it's better to tell qemu explicitly that something went
wrong and that we won't recover, by closing the socket.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
I got all paranoid after triggering a divide-by-zero general
protection fault in passt with a qemu version without the virtio_net
TX hang fix, while flooding UDP. I start thinking this was actually
coming from some random changes I was playing with, but before
reaching this conclusion I reviewed once more the relatively short
path in tap_handler_passt() before we start using packet_*()
functions, and found this.
Never observed in practice, but artificially reproduced with changes
in qemu's socket interface: if we don't receive from qemu a complete
length descriptor in one recv() call, or if we receive a partial one
at the end of one call, we currently disregard the rest, which would
make the stream inconsistent.
Nothing really bad happens, except that from that point on we would
disregard all the packets we get until, if ever, we get the stream
back in sync by chance.
Force reading a complete packet length descriptor with a blocking
recv(), if needed -- not just a complete packet later.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
We can't get rid of qrap quite yet, but at least we should start
telling users it's not going to be needed anymore starting from qemu
7.2.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
We recently converted to using struct in_addr rather than bare in_addr_t
or uint32_t to represent IPv4 addresses in network order. This makes it
harder forget to apply the correct endian conversions.
We omitted the IPv4 addresses stored in struct tap4_l4_t, however. Convert
those as well.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
We recently corrected some errors handling the endianness of IPv4
addresses. These are very easy errors to make since although we mostly
store them in network endianness, we sometimes need to manipulate them in
host endianness.
To reduce the chances of making such mistakes again, change to always using
a (struct in_addr) instead of a bare in_addr_t or uint32_t to store network
endian addresses. This makes it harder to accidentally do arithmetic or
comparisons on such addresses as if they were host endian.
We introduce a number of IN4_IS_ADDR_*() helpers to make it easier to
directly work with struct in_addr values. This has the additional benefit
of making the IPv4 and IPv6 paths more visually similar.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
On ramfs, connecting to a non-existent UNIX domain socket yields
EACCESS, instead of ENOENT. This is visible if we use passt directly
on rootfs (a ramfs instance) from an initramfs image.
It's probably wrong for ramfs to return EACCES, but given the
simplicity of the filesystem, I doubt we should try to fix it there
at the possible cost of added complexity.
Also, this whole beauty should go away once qrap-less usage is
established, so just accept EACCES as indication that a conflicting
socket does not, in fact, exist.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
This only worked for ICMPv6: ICMP packets have no TCP-style header,
so they are handled as a special case before packet sequences are
formed, and the call to tap_packet_debug() was missing.
Fixes: bb70811183 ("treewide: Packet abstraction with mandatory boundary checks")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
The IPv4 specific dhcp() manually constructs L2 and IP headers to send its
DHCP reply packet, unlike its IPv6 equivalent in dhcpv6.c which uses the
tap_udp6_send() helper. Now that we've broaded the parameters to
tap_udp4_send() we can use it in dhcp() to avoid some duplicated logic.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
tap_ip4_send() has special case logic to compute the checksums for UDP
and ICMP packets, which is a mild layering violation. By using a suitable
helper we can split it into tap_udp4_send() and tap_icmp4_send() functions
without greatly increasing the code size, this removing that layering
violation.
We make some small changes to the interface while there. In both cases
we make the destination IPv4 address a parameter, which will be useful
later. For the UDP variant we make it take just the UDP payload, and it
will generate the UDP header. For the ICMP variant we pass in the ICMP
header as before. The inconsistency is because that's what seems to be
the more natural way to invoke the function in the callers in each case.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
ndp() takes a parameter giving the ethernet source address of the packet
it is to respond to, which it uses to determine the destination address to
send the reply packet to.
This is not necessary, because the address will always be the guest's
MAC address. Even if the guest has just changed MAC address, then either
tap_handler_passt() or tap_handler_pasta() - which are the only call paths
leading to ndp() will have updated c->mac_guest with the new value.
So, remove the parameter, and just use c->mac_guest, making it more
consistent with other paths where we construct packets to send inwards.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
tap_ip6_send() has special case logic to compute the checksums for UDP
and ICMP packets, which is a mild layering violation. By using a suitable
helper we can split it into tap_udp6_send() and tap_icmp6_send() functions
without greatly increasing the code size, this removing that layering
violation.
We make some small changes to the interface while there. In both cases
we make the destination IPv6 address a parameter, which will be useful
later. For the UDP variant we make it take just the UDP payload, and it
will generate the UDP header. For the ICMP variant we pass in the ICMP
header as before. The inconsistency is because that's what seems to be
the more natural way to invoke the function in the callers in each case.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
The IPv4 and IPv6 paths in tap_ip_send() have very little in common, and
it turns out that every caller (statically) knows if it is using IPv4 or
IPv6. So split into separate tap_ip4_send() and tap_ip6_send() functions.
Use a new tap_l2_hdr() function for the very small common part.
While we're there, make some minor cleanups:
- We were double writing some fields in the IPv6 header, so that it
temporary matched the pseudo-header for checksum calculation. With
recent checksum reworks, this isn't neccessary any more.
- We don't use any IPv4 header options, so use some sizeof() constructs
instead of some open coded values for header length.
- The comment used to say that the flow label was for TCP over IPv6, but
in fact the only thing we used it for was DHCPv6 over UDP traffic
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Callers of tap_send() can optionally use a small optimization by adding
extra space for the 4 byte length header used on the qemu socket interface.
tap_ip_send() is currently the only user of this, but this is used only
for "slow path" ICMP and DHCP packets, so there's not a lot of value to
the optimization.
Worse, having the two paths here complicates the interface and makes future
cleanups difficult, so just remove it. I have some plans to bring back the
optimization in a more general way in future, but for now it's just in the
way.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
tap_ip_send() is never used for TCP packets, we're unlikely to use it for
that in future, and the handling of TCP packets makes other cleanups
unnecessarily awkward. Remove it.
This is the only user of csum_tcp4(), so we can remove that as well.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
tap_ip_send() doesn't take a destination address, because it's specifically
for inbound packets, and the IP addresses of the guest/namespace are
already known to us. Rather than open-coding this destination address
logic, make helper functions for it which will enable some later cleanups.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
We calculate IPv4 header checksums in at least two places, in dhcp() and
in tap_ip_send. Add a helper to handle this calculation in both places.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
At least two places in passt fill in UDP over IPv4 checksums, although
since UDP checksums are optional with IPv4 that just amounts to storing
a 0 (in tap_ip_send()) or leaving a 0 from an earlier initialization (in
dhcp()). For consistency, add a helper for this "calculation".
Just for the heck of it, add the option (compile time disabled for now) to
calculate real UDP checksums.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Add a helper for calculating UDP checksums when used over IPv6
For future flexibility, the new helper takes parameters for the fields in
the IPv6 pseudo-header, so an IPv6 header or pseudo-header doesn't need to
be explicitly constructed. It also allows the UDP header and payload to
be in separate buffers, although we don't use this yet.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Although tap_ip_send() is currently the only place calculating ICMP
checksums, create a helper function for symmetry with ICMPv6. For
future flexibility it allows the ICMPv6 header and payload to be in
separate buffers.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
At least two places in passt calculate ICMPv6 checksums, ndp() and
tap_ip_send(). Add a helper to handle this calculation in both places.
For future flexibility, the new helper takes parameters for the fields in
the IPv6 pseudo-header, so an IPv6 header or pseudo-header doesn't need to
be explicitly constructed. It also allows the ICMPv6 header and payload to
be in separate buffers, although we don't use this yet.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Even if CAP_NET_BIND_SERVICE is granted, we'll lose the capability in
the target user namespace as we isolate the process, which means
we're unable to bind to low ports at that point.
Bind inbound ports, and only those, before isolate_user(). Keep the
handling of outbound ports (for pasta mode only) after the setup of
the namespace, because that's where we'll bind them.
To this end, initialise the netlink socket for the init namespace
before isolate_user() as well, as we actually need to know the
addresses of the upstream interface before binding ports, in case
they're not explicitly passed by the user.
As we now call nl_sock_init() twice, checking its return code from
conf() twice looks a bit heavy: make it exit(), instead, as we
can't do much if we don't have netlink sockets.
While at it:
- move the v4_only && v6_only options check just after the first
option processing loop, as this is more strictly related to
option parsing proper
- update the man page, explaining that CAP_NET_BIND_SERVICE is
*not* the preferred way to bind ports, because passt and pasta
can be abused to allow other processes to make effective usage
of it. Add a note about the recommended sysctl instead
- simplify nl_sock_init_do() now that it's called once for each
case
Reported-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This is a minor optimisation possibility I spotted while trying to
debug a hang in tap4_handler(): if we run out of space for packet
sequences, it's fine to add packets to an existing per-sequence pool.
We should check the count of packet sequences only once we realise
that we actually need a new packet sequence.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This is practical to avoid explicit lifecycle management in users,
e.g. libvirtd, and is trivial to implement.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Logging to file is going to add some further complexity that we don't
want to squeeze into util.c.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Minor style improvement suggested by cppcheck.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reported by Coverity (CWE-119):
Negative value used as argument to a function expecting a
positive value (for example, size of buffer or allocation)
and harmless, because getsockopt() would return -EBADF if the
socket is -1, so we wouldn't print anything.
Check if accept4() returns a valid socket before calling getsockopt()
on it.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
The context structure contains a batch of fields specific to IPv4 and to
IPv6 connectivity. Split those out into a sub-structure.
This allows the conf_ip4() and conf_ip6() functions, which take the
entire context but touch very little of it, to be given more specific
parameters, making it clearer what it affects without stepping through the
code.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
After recent changes, conf_ip() now has essentially entirely disjoint paths
for IPv4 and IPv6 configuration. So, it's cleaner to split them out into
different functions conf_ip4() and conf_ip6().
Splitting these out also lets us make the interface a bit nicer, having
them return success or failure directly, rather than manipulating c->v4
and c->v6 to indicate success/failure of the two versions.
Since these functions may also initialize the interface index for each
protocol, it turns out we can then drop c->v4 and c->v6 entirely, replacing
tests on those with tests on whether c->ifi4 or c->ifi6 is non-zero (since
a 0 interface index is never valid).
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
[sbrivio: Whitespace fixes]
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
In pasta mode, the guest's MAC address is set up in pasta_ns_cobf() called
from tap_sock_tun_init(). If we have a guest MAC configured with
--ns-mac-addr, this will set the given MAC on the kernel tuntap device, or
if we haven't configured one it will update our record of the guest MAC to
the kernel assigned one from the device.
For passt, we don't initially know the guest's MAC until we receive packets
from it, so we have to initially use a broadcast address. This is - oddly
- set up in an entirely different place, in conf_ip() conditional on the
mode.
Move it to the logically matching place for passt - tap_sock_unix_init().
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
...namely, as connections are discarded or accepted. This was quite
useful to debug an issue with libvirtd failing to start qemu (because
passt refused the new connection) as a previous qemu instance was
still active.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
All instances were harmless, but it might be useful to have some
debug messages here and there. Reported by Coverity.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
read() will return zero if we pass a zero length, which makes no
sense: instead, track explicitly that we exhausted the buffer, flush
packets to handlers and redo.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
If the tun interface disappears, we'll call tap_ns_tun() after the
seccomp profile is applied: add ioctl() and openat() to it.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
The existing sizes provide no measurable differences in throughput
and packet rates at this point. They were probably needed as batched
implementations were not complete, but they can be decreased quite a
bit now.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Implement a packet abstraction providing boundary and size checks
based on packet descriptors: packets stored in a buffer can be queued
into a pool (without storage of its own), and data can be retrieved
referring to an index in the pool, specifying offset and length.
Checks ensure data is not read outside the boundaries of buffer and
descriptors, and that packets added to a pool are within the buffer
range with valid offset and indices.
This implies a wider rework: usage of the "queueing" part of the
abstraction mostly affects tap_handler_{passt,pasta}() functions and
their callees, while the "fetching" part affects all the guest or tap
facing implementations: TCP, UDP, ICMP, ARP, NDP, DHCP and DHCPv6
handlers.
Suggested-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
With a lot of concurrent connections, the bitmap scan approach is
not really sustainable.
Switch to per-connection timerfd timers, set based on events and on
two new flags, ACK_FROM_TAP_DUE and ACK_TO_TAP_DUE. Timers are added
to the common epoll list, and implement the existing timeouts.
While at it, drop the CONN_ prefix from flag names, otherwise they
get quite long, and fix the logic to decide if a connection has a
local, possibly unreachable endpoint: we shouldn't go through the
rest of tcp_conn_from_tap() if we reset the connection due to a
successful bind(2), and we'll get EACCES if the port number is low.
Suggested by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
--debug can be a bit too noisy, especially as single packets or
socket messages are logged: implement a new option, --trace,
implying --debug, that enables all debug messages.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
To reach (at least) a conceptually equivalent security level as
implemented by --enable-sandbox in slirp4netns, we need to create a
new mount namespace and pivot_root() into a new (empty) mountpoint, so
that passt and pasta can't access any filesystem resource after
initialisation.
While at it, also detach IPC, PID (only for passt, to prevent
vulnerabilities based on the knowledge of a target PID), and UTS
namespaces.
With this approach, if we apply the seccomp filters right after the
configuration step, the number of allowed syscalls grows further. To
prevent this, defer the application of seccomp policies after the
initialisation phase, before the main loop, that's where we expect bad
things to happen, potentially. This way, we get back to 22 allowed
syscalls for passt and 34 for pasta, on x86_64.
While at it, move #syscalls notes to specific code paths wherever it
conceptually makes sense.
We have to open all the file handles we'll ever need before
sandboxing:
- the packet capture file can only be opened once, drop instance
numbers from the default path and use the (pre-sandbox) PID instead
- /proc/net/tcp{,v6} and /proc/net/udp{,v6}, for automatic detection
of bound ports in pasta mode, are now opened only once, before
sandboxing, and their handles are stored in the execution context
- the UNIX domain socket for passt is also bound only once, before
sandboxing: to reject clients after the first one, instead of
closing the listening socket, keep it open, accept and immediately
discard new connection if we already have a valid one
Clarify the (unchanged) behaviour for --netns-only in the man page.
To actually make passt and pasta processes run in a separate PID
namespace, we need to unshare(CLONE_NEWPID) before forking to
background (if configured to do so). Introduce a small daemon()
implementation, __daemon(), that additionally saves the PID file
before forking. While running in foreground, the process itself can't
move to a new PID namespace (a process can't change the notion of its
own PID): mention that in the man page.
For some reason, fork() in a detached PID namespace causes SIGTERM
and SIGQUIT to be ignored, even if the handler is still reported as
SIG_DFL: add a signal handler that just exits.
We can now drop most of the pasta_child_handler() implementation,
that took care of terminating all processes running in the same
namespace, if pasta started a shell: the shell itself is now the
init process in that namespace, and all children will terminate
once the init process exits.
Issuing 'echo $$' in a detached PID namespace won't return the
actual namespace PID as seen from the init namespace: adapt
demo and test setup scripts to reflect that.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
clang-tidy from LLVM 13.0.1 reports some new warnings from these
checkers:
- altera-unroll-loops, altera-id-dependent-backward-branch: ignore
for the moment being, add a TODO item
- bugprone-easily-swappable-parameters: ignore, nothing to do about
those
- readability-function-cognitive-complexity: ignore for the moment
being, add a TODO item
- altera-struct-pack-align: ignore, alignment is forced in protocol
headers
- concurrency-mt-unsafe: ignore for the moment being, add a TODO
item
Fix bugprone-implicit-widening-of-multiplication-result warnings,
though, that's doable and they seem to make sense.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
The existing behaviour is not really practical: an automated agent in
charge of starting both qemu and passt would need to fork itself to
start passt, because passt won't fork to background until qemu
connects, and the agent needs to unblock to start qemu.
Instead of waiting for a connection to daemonise, do it right away as
soon as a socket is available: that can be considered an initialised
state already.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Depending on the C library, but not necessarily in all the
functions we use, statx() might be used instead of stat(),
getdents() instead of getdents64(), readlinkat() instead of
readlink(), openat() instead of open().
On aarch64, it's clone() and not fork(), and dup3() instead of
dup2() -- just allow the existing alternative instead of dealing
with per-arch selections.
Since glibc commit 9a7565403758 ("posix: Consolidate fork
implementation"), we need to allow set_robust_list() for
fork()/clone(), even in a single-threaded context.
On some architectures, epoll_pwait() is provided instead of
epoll_wait(), but never both. Same with newfstat() and
fstat(), sigreturn() and rt_sigreturn(), getdents64() and
getdents(), readlink() and readlinkat(), unlink() and
unlinkat(), whereas pipe() might not be available, but
pipe2() always is, exclusively or not.
Seen on Fedora 34: newfstatat() is used on top of fstat().
syslog() is an actual system call on some glibc/arch combinations,
instead of a connect()/send() implementation.
On ppc64 and ppc64le, _llseek(), recv(), send() and getuid()
are used. For ppc64 only: ugetrlimit() for the getrlimit()
implementation, plus sigreturn() and fcntl64().
On s390x, additionally, we need to allow socketcall() (on top
of socket()), and sigreturn() also for passt (not just for
pasta).
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This is the only remaining Linux-specific include -- drop it to avoid
clang-tidy warnings and to make code more portable.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
...mostly false positives, but a number of very relevant ones too,
in tcp_get_sndbuf(), tcp_conn_from_tap(), and siphash PREAMBLE().
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Unions and structs, you all have names now.
Take the chance to enable bugprone-reserved-identifier,
cert-dcl37-c, and cert-dcl51-cpp checkers in clang-tidy.
Provide a ffsl() weak declaration using gcc built-in.
Start reordering includes, but that's not enough for the
llvm-include-order checker yet.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
List of allowed syscalls comes from comments in the form:
#syscalls <list>
for syscalls needed both in passt and pasta mode, and:
#syscalls:pasta <list>
#syscalls:passt <list>
for syscalls specifically needed in pasta or passt mode only.
seccomp.sh builds a list of BPF statements from those comments,
prefixed by a binary search tree to keep lookup fast.
While at it, clean up a bit the Makefile using wildcards.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Move netlink routines to their own file, and use netlink to configure
or fetch all the information we need, except for the TUNSETIFF ioctl.
Move pasta-specific functions to their own file as well, add
parameters and calls to configure the tap interface in the namespace.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Based on a patch from Giuseppe Scrivano, this adds the ability to:
- specify paths and names of target namespaces to join, instead of
a PID, also for user namespaces, with --userns
- request to join or create a network namespace only, without
entering or creating a user namespace, with --netns-only
- specify the base directory for netns mountpoints, with --nsrun-dir
Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
[sbrivio: reworked logic to actually join the given namespaces when
they're not created, implemented --netns-only and --nsrun-dir,
updated pasta demo script and man page]
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
In case we need to reinitialise the tap interface, make that
relatively transparent to processes running in the namespace.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Until now, messages would be passed to protocol handlers in a single
batch only if they happened to be dequeued in a row. Packets
interleaved between different connections would result in multiple
calls to the same protocol handler for a single connection.
Instead, keep track of incoming packet descriptors, arrange them in
sequences, and call protocol handlers only as we completely sorted
input messages in batches.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
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>
...boom. To make it slightly more reasonable, shrink struct tap_msg
down a bit, and move the main message array away from the stack of
tap_handler_passt().
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
If we can't bind() ping sockets, the echo identifier sent out from
the socket won't be the original one seen from the tap. Binding a
ping socket doesn't require any security capability, but it might
still fail due to a broken SELinux policy, see for example:
https://bugzilla.redhat.com/show_bug.cgi?id=1848929
Track the ICMP echo identifier as part of the epoll reference for
the socket and replace it in the reply on mismatch. We won't send
out the original identifier as sent from the guest, but still better
than missing replies.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
If a tap protocol handler doesn't consume the full batch of packets
in one go, we already overrode the destination address in the packet
buffer with the address which is configured at start. If we re-enter
the tap handler, we shouldn't use the address from the packet buffers
anymore to set the observed address of the guest: that's not the
address observed from the guest, it's the configured one now.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This isn't optional: TCP streams must carry a unique, hard-to-guess,
non-zero label for each direction. Linux, probably among others,
will otherwise refuse to associate packets in a given stream to the
same connection.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Provide an AVX2-based function using compiler intrinsics for
TCP/IP-style checksums. The load/unpack/add idea and implementation
is largely based on code from BESS (the Berkeley Extensible Software
Switch) licensed as 3-Clause BSD, with a number of modifications to
further decrease pipeline stalls and to minimise cache pollution.
This speeds up considerably data paths from sockets to tap
interfaces, decreasing overhead for checksum computation, with
16-64KiB packet buffers, from approximately 11% to 7%. The rest is
just syscalls at this point.
While at it, provide convenience targets in the Makefile for avx2,
avx2_debug, and debug targets -- these simply add target-specific
CFLAGS to the build.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Packets are received directly onto pre-cooked, static buffers
for IPv4 (with partial checksum pre-calculation) and IPv6 frames,
with pre-filled Ethernet addresses and, partially, IP headers,
and sent out from the same buffers with sendmmsg(), for both
passt and pasta (non-local traffic only) modes.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
PASTA (Pack A Subtle Tap Abstraction) provides quasi-native host
connectivity to an otherwise disconnected, unprivileged network
and user namespace, similarly to slirp4netns. Given that the
implementation is largely overlapping with PASST, no separate binary
is built: 'pasta' (and 'passt4netns' for clarity) both link to
'passt', and the mode of operation is selected depending on how the
binary is invoked. Usage example:
$ unshare -rUn
# echo $$
1871759
$ ./pasta 1871759 # From another terminal
# udhcpc -i pasta0 2>/dev/null
# ping -c1 pasta.pizza
PING pasta.pizza (64.190.62.111) 56(84) bytes of data.
64 bytes from 64.190.62.111 (64.190.62.111): icmp_seq=1 ttl=255 time=34.6 ms
--- pasta.pizza ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 34.575/34.575/34.575/0.000 ms
# ping -c1 spaghetti.pizza
PING spaghetti.pizza(2606:4700:3034::6815:147a (2606:4700:3034::6815:147a)) 56 data bytes
64 bytes from 2606:4700:3034::6815:147a (2606:4700:3034::6815:147a): icmp_seq=1 ttl=255 time=29.0 ms
--- spaghetti.pizza ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 28.967/28.967/28.967/0.000 ms
This entails a major rework, especially with regard to the storage of
tracked connections and to the semantics of epoll(7) references.
Indexing TCP and UDP bindings merely by socket proved to be
inflexible and unsuitable to handle different connection flows: pasta
also provides Layer-2 to Layer-2 socket mapping between init and a
separate namespace for local connections, using a pair of splice()
system calls for TCP, and a recvmmsg()/sendmmsg() pair for UDP local
bindings. For instance, building on the previous example:
# ip link set dev lo up
# iperf3 -s
$ iperf3 -c ::1 -Z -w 32M -l 1024k -P2 | tail -n4
[SUM] 0.00-10.00 sec 52.3 GBytes 44.9 Gbits/sec 283 sender
[SUM] 0.00-10.43 sec 52.3 GBytes 43.1 Gbits/sec receiver
iperf Done.
epoll(7) references now include a generic part in order to
demultiplex data to the relevant protocol handler, using 24
bits for the socket number, and an opaque portion reserved for
usage by the single protocol handlers, in order to track sockets
back to corresponding connections and bindings.
A number of fixes pertaining to TCP state machine and congestion
window handling are also included here.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
With -DDEBUG, passt now saves guest-side traffic captures in
pcap format at /tmp/passt_<ISO8601 timestamp>.pcap. The timestamp
refers to time and date of start-up.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
As we support UDP forwarding for packets that are sent to local
ports, we actually need some kind of connection tracking for UDP.
While at it, this commit introduces a number of vaguely related fixes
for issues observed while trying this out. In detail:
- implement an explicit, albeit minimalistic, connection tracking
for UDP, to allow usage of ephemeral ports by the guest and by
the host at the same time, by binding them dynamically as needed,
and to allow mapping address changes for packets with a loopback
address as destination
- set the guest MAC address whenever we receive a packet from tap
instead of waiting for an ARP request, and set it to broadcast on
start, otherwise DHCPv6 might not work if all DHCPv6 requests time
out before the guest starts talking IPv4
- split context IPv6 address into address we assign, global or site
address seen on tap, and link-local address seen on tap, and make
sure we use the addresses we've seen as destination (link-local
choice depends on source address). Similarly, for IPv4, split into
address we assign and address we observe, and use the address we
observe as destination
- introduce a clock_gettime() syscall right after epoll_wait() wakes
up, so that we can remove all the other ones and pass the current
timestamp to tap and socket handlers -- this is additionally needed
by UDP to time out bindings to ephemeral ports and mappings between
loopback address and a local address
- rename sock_l4_add() to sock_l4(), no semantic changes intended
- include <arpa/inet.h> in passt.c before kernel headers so that we
can use <netinet/in.h> macros to check IPv6 address types, and
remove a duplicate <linux/ip.h> inclusion
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Avoid a bunch of syscalls on forwarding paths by:
- storing minimum and maximum file descriptor numbers for each
protocol, fall back to SO_PROTOCOL query only on overlaps
- allocating a larger receive buffer -- this can result in more
coalesced packets than sendmmsg() can take (UIO_MAXIOV, i.e. 1024),
so make sure we don't exceed that within a single call to protocol
tap handlers
- nesting the handling loop in tap_handler() in the receive loop,
so that we have better chances of filling our receive buffer in
fewer calls
- skipping the recvfrom() in the UDP handler on EPOLLERR -- there's
nothing to be done in that case
and while at it:
- restore the 20ms timer interval for periodic (TCP) events, I
accidentally changed that to 100ms in an earlier commit
- attempt using SO_ZEROCOPY for UDP -- if it's not available,
sendmmsg() will succeed anyway
- fix the handling of the status code from sendmmsg(), if it fails,
we'll try to discard the first message, hence return 1 from the
UDP handler
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
This is a reimplementation, partially building on the earlier draft,
that uses L4 sockets (SOCK_DGRAM, SOCK_STREAM) instead of SOCK_RAW,
providing L4-L2 translation functionality without requiring any
security capability.
Conceptually, this follows the design presented at:
https://gitlab.com/abologna/kubevirt-and-kvm/-/blob/master/Networking.md
The most significant novelty here comes from TCP and UDP translation
layers. In particular, the TCP state and translation logic follows
the intent of being minimalistic, without reimplementing a full TCP
stack in either direction, and synchronising as much as possible the
TCP dynamic and flows between guest and host kernel.
Another important introduction concerns addressing, port translation
and forwarding. The Layer 4 implementations now attempt to bind on
all unbound ports, in order to forward connections in a transparent
way.
While at it:
- the qemu 'tap' back-end can't be used as-is by qrap anymore,
because of explicit checks now introduced in qemu to ensure that
the corresponding file descriptor is actually a tap device. For
this reason, qrap now operates on a 'socket' back-end type,
accounting for and building the additional header reporting
frame length
- provide a demo script that sets up namespaces, addresses and
routes, and starts the daemon. A virtual machine started in the
network namespace, wrapped by qrap, will now directly interface
with passt and communicate using Layer 4 sockets provided by the
host kernel.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
