1
0
mirror of https://passt.top/passt synced 2024-12-22 21:55:22 +00:00
passt/udp.h

68 lines
2.0 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later
* Copyright (c) 2021 Red Hat GmbH
* Author: Stefano Brivio <sbrivio@redhat.com>
*/
#ifndef UDP_H
#define UDP_H
udp: Connection tracking for ephemeral, local ports, and related fixes 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>
2021-04-29 14:59:20 +00:00
#define UDP_TIMER_INTERVAL 1000 /* ms */
void udp_portmap_clear(void);
void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events,
const struct timespec *now);
int udp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af,
const void *saddr, const void *daddr,
const struct pool *p, int idx, const struct timespec *now);
int udp_sock_init(const struct ctx *c, int ns, sa_family_t af,
const void *addr, const char *ifname, in_port_t port);
int udp_init(struct ctx *c);
void udp_timer(struct ctx *c, const struct timespec *now);
void udp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s);
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 06:34:53 +00:00
/**
* union udp_epoll_ref - epoll reference portion for TCP connections
* @port: Source port for connected sockets, bound port otherwise
* @pif: pif for this socket
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 06:34:53 +00:00
* @bound: Set if this file descriptor is a bound socket
* @splice: Set if descriptor packets to be "spliced"
* @orig: Set if a spliced socket which can originate "connections"
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 06:34:53 +00:00
* @v6: Set for IPv6 sockets or connections
* @u32: Opaque u32 value of reference
*/
union udp_epoll_ref {
struct {
in_port_t port;
uint8_t pif;
bool splice:1,
orig:1,
v6:1;
};
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 06:34:53 +00:00
uint32_t u32;
};
/**
* udp_fwd_ports - UDP specific port forwarding configuration
* @f: Generic forwarding configuration
* @rdelta: Reversed delta map to translate source ports on return packets
*/
struct udp_fwd_ports {
struct fwd_ports f;
in_port_t rdelta[NUM_PORTS];
};
/**
* struct udp_ctx - Execution context for UDP
* @fwd_in: Port forwarding configuration for inbound packets
* @fwd_out: Port forwarding configuration for outbound packets
udp: Connection tracking for ephemeral, local ports, and related fixes 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>
2021-04-29 14:59:20 +00:00
* @timer_run: Timestamp of most recent timer run
*/
struct udp_ctx {
struct udp_fwd_ports fwd_in;
struct udp_fwd_ports fwd_out;
udp: Connection tracking for ephemeral, local ports, and related fixes 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>
2021-04-29 14:59:20 +00:00
struct timespec timer_run;
};
#endif /* UDP_H */