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>

1 files changed, 23 insertions, 2 deletions

diff --git a/util.h b/util.h
index 3e24c9a..c4d947a 100644
--- a/util.h
+++ b/util.h
@@ -29,24 +29,45 @@ void debug(const char *format, ...);
 #define MAX(x, y)		(((x) > (y)) ? (x) : (y))
 #endif
 
+#define SWAP(a, b)							\
+	do {								\
+		typeof(a) __x = (a); (a) = (b); (b) = __x;		\
+	} while (0)							\
+
 #define STRINGIFY(x)	#x
 #define STR(x)		STRINGIFY(x)
 
+#define V4		0
+#define V6		1
+#define IP_VERSIONS	2
+
 #define ARRAY_SIZE(a)		((int)(sizeof(a) / sizeof((a)[0])))
 
 #define IN_INTERVAL(a, b, x)	((x) >= (a) && (x) <= (b))
 #define FD_PROTO(x, proto)						\
 	(IN_INTERVAL(c->proto.fd_min, c->proto.fd_max, (x)))
 
-#define PORT_IS_EPHEMERAL(port) ((port) >= (1 << 15) + (1 << 14)) /* RFC 6335 */
+#define PORT_EPHEMERAL_MIN	((1 << 15) + (1 << 14))		/* RFC 6335 */
+#define PORT_IS_EPHEMERAL(port) ((port) >= PORT_EPHEMERAL_MIN)
+
+#define NS_FN_STACK_SIZE	(RLIMIT_STACK_VAL * 1024 / 4)
 
 #include <linux/ipv6.h>
 #include <net/if.h>
 #include <linux/ip.h>
+#include <limits.h>
+
+struct ctx;
 
 uint16_t csum_fold(uint32_t sum);
 uint16_t csum_ip4(void *buf, size_t len);
 void csum_tcp4(struct iphdr *iph);
 char *ipv6_l4hdr(struct ipv6hdr *ip6h, uint8_t *proto);
-int sock_l4(struct ctx *c, int af, uint16_t proto, uint16_t port);
+int sock_l4(struct ctx *c, int af, uint8_t proto, uint16_t port, int lo,
+	    uint32_t data);
 int timespec_diff_ms(struct timespec *a, struct timespec *b);
+void bitmap_set(uint8_t *map, int bit);
+void bitmap_clear(uint8_t *map, int bit);
+int bitmap_isset(uint8_t *map, int bit);
+void procfs_scan_listen(char *name, uint8_t *map);
+int ns_enter(int target_pid);