mirrors/passt
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

tcp: Rework timers to use timerfd instead of periodic bitmap scan

Browse source 
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>
This commit is contained in:
Stefano Brivio 2022-03-18 12:18:19 +01:00
parent 3eb19cfd8a
commit be5bbb9b06
5 changed files with 288 additions and 241 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -287,11 +287,9 @@ speeding up local connections, and usually requiring NAT. _pasta_:
* ✅ all capabilities dropped, other than `CAP_NET_BIND_SERVICE` (if granted)
* ✅ with default options, user, mount, IPC, UTS, PID namespaces are detached
* ✅ no external dependencies (other than a standard C library)
* ✅ restrictive seccomp profiles (22 syscalls allowed for _passt_, 34 for
* ✅ restrictive seccomp profiles (25 syscalls allowed for _passt_, 37 for
_pasta_ on x86_64)
* ✅ static checkers in continuous integration (clang-tidy, cppcheck)
* 🛠️ rework of TCP state machine (flags instead of states), TCP timers, and code
de-duplication
* 🛠️ clearly defined packet abstraction
* 🛠️ ~5 000 LoC target
* ⌚ [fuzzing](https://bugs.passt.top/show_bug.cgi?id=9), _packetdrill_ tests

12
passt.c
View file

@ -119,12 +119,12 @@ static void post_handler(struct ctx *c, struct timespec *now)
#define CALL_PROTO_HANDLER(c, now, lc, uc) \
do { \
extern void \
lc ## _defer_handler (struct ctx *, struct timespec *) \
lc ## _defer_handler (struct ctx *c) \
__attribute__ ((weak)); \
\
if (!c->no_ ## lc) { \
if (lc ## _defer_handler) \
lc ## _defer_handler(c, now); \
lc ## _defer_handler(c); \
\
if (timespec_diff_ms((now), &c->lc.timer_run) \
>= uc ## _TIMER_INTERVAL) { \
@ -134,8 +134,11 @@ static void post_handler(struct ctx *c, struct timespec *now)
} \
} while (0)
/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
CALL_PROTO_HANDLER(c, now, tcp, TCP);
/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
CALL_PROTO_HANDLER(c, now, udp, UDP);
/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
CALL_PROTO_HANDLER(c, now, icmp, ICMP);
#undef CALL_PROTO_HANDLER
@ -380,8 +383,8 @@ int main(int argc, char **argv)
clock_gettime(CLOCK_MONOTONIC, &now);
if ((!c.no_udp && udp_sock_init(&c, &now)) ||
(!c.no_tcp && tcp_sock_init(&c, &now)))
if ((!c.no_udp && udp_sock_init(&c)) ||
(!c.no_tcp && tcp_sock_init(&c)))
exit(EXIT_FAILURE);
proto_update_l2_buf(c.mac_guest, c.mac, &c.addr4);
@ -425,6 +428,7 @@ int main(int argc, char **argv)
timer_init(&c, &now);
loop:
/* NOLINTNEXTLINE(bugprone-branch-clone): intervals can be the same */
nfds = epoll_wait(c.epollfd, events, EPOLL_EVENTS, TIMER_INTERVAL);
if (nfds == -1 && errno != EINTR) {
perror("epoll_wait");

2
tap.c
View file

@ -939,7 +939,7 @@ void tap_sock_init(struct ctx *c)
* @c: Execution context
* @fd: File descriptor where event occurred
* @events: epoll events
* @now: Current timestamp
* @now: Current timestamp, can be NULL on EPOLLERR
*/
void tap_handler(struct ctx *c, int fd, uint32_t events, struct timespec *now)
{

503
tcp.c
View file

File diff suppressed because it is too large Load diff

8
tcp.h
View file

@ -6,7 +6,9 @@
#ifndef TCP_H
#define TCP_H
#define TCP_TIMER_INTERVAL 20 /* ms */
#define REFILL_INTERVAL 1000 /* ms */
#define PORT_DETECT_INTERVAL 1000
#define TCP_TIMER_INTERVAL MIN(REFILL_INTERVAL, PORT_DETECT_INTERVAL)
#define TCP_MAX_CONNS (128 * 1024)
#define TCP_MAX_SOCKS (TCP_MAX_CONNS + USHRT_MAX * 2)
@ -21,7 +23,7 @@ int tcp_tap_handler(struct ctx *c, int af, void *addr,
struct tap_l4_msg *msg, int count, struct timespec *now);
int tcp_sock_init(struct ctx *c, struct timespec *now);
void tcp_timer(struct ctx *c, struct timespec *now);
void tcp_defer_handler(struct ctx *c, struct timespec *now);
void tcp_defer_handler(struct ctx *c);
void tcp_sock_set_bufsize(struct ctx *c, int s);
void tcp_update_l2_buf(unsigned char *eth_d, unsigned char *eth_s,
@ -34,6 +36,7 @@ void tcp_remap_to_init(in_port_t port, in_port_t delta);
* @listen: Set if this file descriptor is a listening socket
* @splice: Set if descriptor is associated to a spliced connection
* @v6: Set for IPv6 sockets or connections
* @timer: Reference is a timerfd descriptor for connection
* @index: Index of connection in table, or port for bound sockets
* @u32: Opaque u32 value of reference
*/
@ -42,6 +45,7 @@ union tcp_epoll_ref {
uint32_t listen:1,
splice:1,
v6:1,
timer:1,
index:20;
} tcp;
uint32_t u32;