passt: New design and implementation with native Layer 4 sockets
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>
2021-02-16 07:25:09 +01:00
|
|
|
// SPDX-License-Identifier: AGPL-3.0-or-later
|
|
|
|
|
|
2020-07-20 16:41:49 +02:00
|
|
|
/* PASST - Plug A Simple Socket Transport
|
passt: Add PASTA mode, major rework
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>
2021-07-17 08:34:53 +02:00
|
|
|
* for qemu/UNIX domain socket mode
|
|
|
|
|
*
|
|
|
|
|
* PASTA - Pack A Subtle Tap Abstraction
|
|
|
|
|
* for network namespace/tap device mode
|
2020-07-20 16:27:43 +02:00
|
|
|
*
|
|
|
|
|
* arp.c - ARP implementation
|
|
|
|
|
*
|
passt: New design and implementation with native Layer 4 sockets
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>
2021-02-16 07:25:09 +01:00
|
|
|
* Copyright (c) 2020-2021 Red Hat GmbH
|
2020-07-20 16:27:43 +02:00
|
|
|
* Author: Stefano Brivio <sbrivio@redhat.com>
|
|
|
|
|
*/
|
|
|
|
|
|
2021-10-21 04:26:08 +02:00
|
|
|
#include <arpa/inet.h>
|
|
|
|
|
#include <limits.h>
|
|
|
|
|
#include <net/if.h>
|
|
|
|
|
#include <net/if_arp.h>
|
|
|
|
|
#include <netinet/if_ether.h>
|
2020-07-20 16:27:43 +02:00
|
|
|
#include <stddef.h>
|
|
|
|
|
#include <stdint.h>
|
2021-10-21 04:26:08 +02:00
|
|
|
#include <stdio.h>
|
2020-07-20 16:27:43 +02:00
|
|
|
#include <unistd.h>
|
|
|
|
|
#include <string.h>
|
2021-10-21 04:26:08 +02:00
|
|
|
|
2020-07-21 10:48:24 +02:00
|
|
|
#include <linux/ipv6.h>
|
2020-07-20 16:27:43 +02:00
|
|
|
|
passt: Add PASTA mode, major rework
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>
2021-07-17 08:34:53 +02:00
|
|
|
#include "util.h"
|
2021-10-21 04:26:08 +02:00
|
|
|
#include "arp.h"
|
2020-07-20 16:27:43 +02:00
|
|
|
#include "dhcp.h"
|
2021-10-21 04:26:08 +02:00
|
|
|
#include "passt.h"
|
passt: New design and implementation with native Layer 4 sockets
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>
2021-02-16 07:25:09 +01:00
|
|
|
#include "tap.h"
|
2020-07-20 16:27:43 +02:00
|
|
|
|
|
|
|
|
/**
|
passt: New design and implementation with native Layer 4 sockets
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>
2021-02-16 07:25:09 +01:00
|
|
|
* arp() - Check if this is an ARP message, reply as needed
|
2020-07-20 16:27:43 +02:00
|
|
|
* @c: Execution context
|
|
|
|
|
* @len: Total L2 packet length
|
|
|
|
|
* @eh: Packet buffer, Ethernet header
|
|
|
|
|
*
|
|
|
|
|
* Return: 0 if it's not an ARP message, 1 if handled, -1 on failure
|
|
|
|
|
*/
|
passt: Assorted fixes from "fresh eyes" review
A bunch of fixes not worth single commits at this stage, notably:
- make buffer, length parameter ordering consistent in ARP, DHCP,
NDP handlers
- strict checking of buffer, message and option length in DHCP
handler (a malicious client could have easily crashed it)
- set up forwarding for IPv4 and IPv6, and masquerading with nft for
IPv4, from demo script
- get rid of separate slow and fast timers, we don't save any
overhead that way
- stricter checking of buffer lengths as passed to tap handlers
- proper dequeuing from qemu socket back-end: I accidentally trashed
messages that were bundled up together in a single tap read
operation -- the length header tells us what's the size of the next
frame, but there's no apparent limit to the number of messages we
get with one single receive
- rework some bits of the TCP state machine, now passive and active
connection closes appear to be robust -- introduce a new
FIN_WAIT_1_SOCK_FIN state indicating a FIN_WAIT_1 with a FIN flag
from socket
- streamline TCP option parsing routine
- track TCP state changes to stderr (this is temporary, proper
debugging and syslogging support pending)
- observe that multiplying a number by four might very well change
its value, and this happens to be the case for the data offset
from the TCP header as we check if it's the same as the total
length to find out if it's a duplicated ACK segment
- recent estimates suggest that the duration of a millisecond is
closer to a million nanoseconds than a thousand of them, this
trend is now reflected into the timespec_diff_ms() convenience
routine
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
2021-02-21 11:33:38 +01:00
|
|
|
int arp(struct ctx *c, struct ethhdr *eh, size_t len)
|
2020-07-20 16:27:43 +02:00
|
|
|
{
|
|
|
|
|
struct arphdr *ah = (struct arphdr *)(eh + 1);
|
|
|
|
|
struct arpmsg *am = (struct arpmsg *)(ah + 1);
|
|
|
|
|
unsigned char swap[4];
|
|
|
|
|
|
|
|
|
|
if (eh->h_proto != htons(ETH_P_ARP))
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
if (len < sizeof(*eh) + sizeof(*ah) + sizeof(*am))
|
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
|
|
if (ah->ar_hrd != htons(ARPHRD_ETHER) ||
|
|
|
|
|
ah->ar_pro != htons(ETH_P_IP) ||
|
|
|
|
|
ah->ar_hln != ETH_ALEN || ah->ar_pln != 4 ||
|
|
|
|
|
ah->ar_op != htons(ARPOP_REQUEST))
|
|
|
|
|
return 1;
|
|
|
|
|
|
2021-08-19 19:44:31 +02:00
|
|
|
/* Discard announcements (but not 0.0.0.0 "probes"): we might have the
|
|
|
|
|
* same IP address, hide that.
|
|
|
|
|
*/
|
|
|
|
|
if (*((uint32_t *)&am->sip) && !memcmp(am->sip, am->tip, 4))
|
|
|
|
|
return 1;
|
|
|
|
|
|
2021-08-20 01:13:02 +02:00
|
|
|
/* Don't resolve our own address, either. */
|
|
|
|
|
if (!memcmp(am->tip, &c->addr4, 4))
|
|
|
|
|
return 1;
|
|
|
|
|
|
2020-07-20 16:27:43 +02:00
|
|
|
ah->ar_op = htons(ARPOP_REPLY);
|
|
|
|
|
memcpy(am->tha, am->sha, ETH_ALEN);
|
|
|
|
|
memcpy(am->sha, c->mac, ETH_ALEN);
|
|
|
|
|
|
|
|
|
|
memcpy(swap, am->tip, 4);
|
|
|
|
|
memcpy(am->tip, am->sip, 4);
|
|
|
|
|
memcpy(am->sip, swap, 4);
|
|
|
|
|
|
|
|
|
|
len = sizeof(*eh) + sizeof(*ah) + sizeof(*am);
|
|
|
|
|
memcpy(eh->h_dest, eh->h_source, ETH_ALEN);
|
|
|
|
|
memcpy(eh->h_source, c->mac, ETH_ALEN);
|
|
|
|
|
|
passt: Add PASTA mode, major rework
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>
2021-07-17 08:34:53 +02:00
|
|
|
if (tap_send(c, eh, len, 0) < 0)
|
2020-07-20 16:27:43 +02:00
|
|
|
perror("ARP: send");
|
|
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
|
}
|