Change epoll_del() to accept the epoll file descriptor directly instead of the full context structure. This simplifies the interface and aligns with the threading refactoring by reducing dependency on the context structure for basic epoll operations as we will manage an epollfd per thread. Signed-off-by: Laurent Vivier Reviewed-by: David Gibson --- icmp.c | 2 +- tap.c | 2 +- tcp.c | 6 +++--- tcp_splice.c | 4 ++-- udp_flow.c | 4 ++-- util.c | 6 +++--- util.h | 2 +- vhost_user.c | 6 +++--- 8 files changed, 16 insertions(+), 16 deletions(-) diff --git a/icmp.c b/icmp.c index 6dffafb0bf54..bd3108a21675 100644 --- a/icmp.c +++ b/icmp.c @@ -151,7 +151,7 @@ unexpected: static void icmp_ping_close(const struct ctx *c, const struct icmp_ping_flow *pingf) { - epoll_del(c, pingf->sock); + epoll_del(c->epollfd, pingf->sock); close(pingf->sock); flow_hash_remove(c, FLOW_SIDX(pingf, INISIDE)); } diff --git a/tap.c b/tap.c index f3d1f66041f8..9812f120d426 100644 --- a/tap.c +++ b/tap.c @@ -1142,7 +1142,7 @@ void tap_sock_reset(struct ctx *c) } /* Close the connected socket, wait for a new connection */ - epoll_del(c, c->fd_tap); + epoll_del(c->epollfd, c->fd_tap); close(c->fd_tap); c->fd_tap = -1; if (c->mode == MODE_VU) diff --git a/tcp.c b/tcp.c index 0f9e9b3fdc03..745353f782f5 100644 --- a/tcp.c +++ b/tcp.c @@ -511,9 +511,9 @@ static int tcp_epoll_ctl(const struct ctx *c, struct tcp_tap_conn *conn) if (conn->events == CLOSED) { if (conn->in_epoll) - epoll_del(c, conn->sock); + epoll_del(c->epollfd, conn->sock); if (conn->timer != -1) - epoll_del(c, conn->timer); + epoll_del(c->epollfd, conn->timer); return 0; } @@ -3476,7 +3476,7 @@ int tcp_flow_migrate_source_ext(const struct ctx *c, if (c->migrate_no_linger) close(s); else - epoll_del(c, s); + epoll_del(c->epollfd, s); /* Adjustments unrelated to FIN segments: sequence numbers we dumped are * based on the end of the queues. diff --git a/tcp_splice.c b/tcp_splice.c index 26cb63064583..666ee62b738f 100644 --- a/tcp_splice.c +++ b/tcp_splice.c @@ -204,8 +204,8 @@ static void conn_flag_do(const struct ctx *c, struct tcp_splice_conn *conn, } if (flag == CLOSING) { - epoll_del(c, conn->s[0]); - epoll_del(c, conn->s[1]); + epoll_del(c->epollfd, conn->s[0]); + epoll_del(c->epollfd, conn->s[1]); } } diff --git a/udp_flow.c b/udp_flow.c index cef3fb588bbe..84973f807167 100644 --- a/udp_flow.c +++ b/udp_flow.c @@ -51,7 +51,7 @@ void udp_flow_close(const struct ctx *c, struct udp_flow *uflow) flow_foreach_sidei(sidei) { flow_hash_remove(c, FLOW_SIDX(uflow, sidei)); if (uflow->s[sidei] >= 0) { - epoll_del(c, uflow->s[sidei]); + epoll_del(c->epollfd, uflow->s[sidei]); close(uflow->s[sidei]); uflow->s[sidei] = -1; } @@ -88,7 +88,7 @@ static int udp_flow_sock(const struct ctx *c, if (flowside_connect(c, s, pif, side) < 0) { int rc = -errno; - epoll_del(c, s); + epoll_del(c->epollfd, s); close(s); flow_dbg_perror(uflow, "Couldn't connect flow socket"); diff --git a/util.c b/util.c index c492f904b3fc..1067486be414 100644 --- a/util.c +++ b/util.c @@ -996,12 +996,12 @@ void raw_random(void *buf, size_t buflen) /** * epoll_del() - Remove a file descriptor from our passt epoll - * @c: Execution context + * @epollfd: epoll file descriptor to remove from * @fd: File descriptor to remove */ -void epoll_del(const struct ctx *c, int fd) +void epoll_del(int epollfd, int fd) { - epoll_ctl(c->epollfd, EPOLL_CTL_DEL, fd, NULL); + epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, NULL); } diff --git a/util.h b/util.h index 22eaac56e719..c61cbef357aa 100644 --- a/util.h +++ b/util.h @@ -300,7 +300,7 @@ static inline bool mod_between(unsigned x, unsigned i, unsigned j, unsigned m) #define FPRINTF(f, ...) (void)fprintf(f, __VA_ARGS__) void raw_random(void *buf, size_t buflen); -void epoll_del(const struct ctx *c, int fd); +void epoll_del(int epollfd, int fd); /* * Starting from glibc 2.40.9000 and commit 25a5eb4010df ("string: strerror, diff --git a/vhost_user.c b/vhost_user.c index 223332d5018e..f8324c59cc6c 100644 --- a/vhost_user.c +++ b/vhost_user.c @@ -733,7 +733,7 @@ static bool vu_get_vring_base_exec(struct vu_dev *vdev, vdev->vq[idx].call_fd = -1; } if (vdev->vq[idx].kick_fd != -1) { - epoll_del(vdev->context, vdev->vq[idx].kick_fd); + epoll_del(vdev->context->epollfd, vdev->vq[idx].kick_fd); close(vdev->vq[idx].kick_fd); vdev->vq[idx].kick_fd = -1; } @@ -801,7 +801,7 @@ static bool vu_set_vring_kick_exec(struct vu_dev *vdev, vu_check_queue_msg_file(vmsg); if (vdev->vq[idx].kick_fd != -1) { - epoll_del(vdev->context, vdev->vq[idx].kick_fd); + epoll_del(vdev->context->epollfd, vdev->vq[idx].kick_fd); close(vdev->vq[idx].kick_fd); vdev->vq[idx].kick_fd = -1; } @@ -1093,7 +1093,7 @@ void vu_cleanup(struct vu_dev *vdev) vq->err_fd = -1; } if (vq->kick_fd != -1) { - epoll_del(vdev->context, vq->kick_fd); + epoll_del(vdev->context->epollfd, vq->kick_fd); close(vq->kick_fd); vq->kick_fd = -1; } -- 2.51.0

Move epoll_add() calls from sock_l4_sa() to the protocol-specific code (icmp.c, pif.c, udp_flow.c) to give callers more control over epoll registration. This allows sock_l4_sa() to focus solely on socket creation and binding, while epoll management happens at a higher level. Remove the data parameter from sock_l4_sa() and flowside_sock_l4() as it's no longer needed - callers now construct the full epoll_ref and register the socket themselves after creation. Signed-off-by: Laurent Vivier Reviewed-by: David Gibson --- flow.c | 10 ++++------ flow.h | 2 +- icmp.c | 15 +++++++++++---- pif.c | 32 +++++++++++++++++++++++++------- udp_flow.c | 16 ++++++++++++++-- util.c | 10 +--------- util.h | 2 +- 7 files changed, 57 insertions(+), 30 deletions(-) diff --git a/flow.c b/flow.c index feefda3ce74e..b14e9d8b63ff 100644 --- a/flow.c +++ b/flow.c @@ -163,7 +163,6 @@ static void flowside_from_af(struct flowside *side, sa_family_t af, * @type: Socket epoll type * @sa: Socket address * @sl: Length of @sa - * @data: epoll reference data */ struct flowside_sock_args { const struct ctx *c; @@ -173,7 +172,6 @@ struct flowside_sock_args { const struct sockaddr *sa; socklen_t sl; const char *path; - uint32_t data; }; /** flowside_sock_splice() - Create and bind socket for PIF_SPLICE based on flowside @@ -188,7 +186,7 @@ static int flowside_sock_splice(void *arg) ns_enter(a->c); a->fd = sock_l4_sa(a->c, a->type, a->sa, a->sl, NULL, - a->sa->sa_family == AF_INET6, a->data); + a->sa->sa_family == AF_INET6); a->err = errno; return 0; @@ -205,7 +203,7 @@ static int flowside_sock_splice(void *arg) * (if specified). */ int flowside_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif, - const struct flowside *tgt, uint32_t data) + const struct flowside *tgt) { const char *ifname = NULL; union sockaddr_inany sa; @@ -225,12 +223,12 @@ int flowside_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif, ifname = c->ip6.ifname_out; return sock_l4_sa(c, type, &sa, sl, ifname, - sa.sa_family == AF_INET6, data); + sa.sa_family == AF_INET6); case PIF_SPLICE: { struct flowside_sock_args args = { .c = c, .type = type, - .sa = &sa.sa, .sl = sl, .data = data, + .sa = &sa.sa, .sl = sl, }; NS_CALL(flowside_sock_splice, &args); errno = args.err; diff --git a/flow.h b/flow.h index cac618ad0ca1..ef138b83add8 100644 --- a/flow.h +++ b/flow.h @@ -167,7 +167,7 @@ static inline bool flowside_eq(const struct flowside *left, } int flowside_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif, - const struct flowside *tgt, uint32_t data); + const struct flowside *tgt); int flowside_connect(const struct ctx *c, int s, uint8_t pif, const struct flowside *tgt); diff --git a/icmp.c b/icmp.c index c26561da80bf..d7c64739876f 100644 --- a/icmp.c +++ b/icmp.c @@ -170,10 +170,10 @@ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c, { uint8_t proto = af == AF_INET ? IPPROTO_ICMP : IPPROTO_ICMPV6; uint8_t flowtype = af == AF_INET ? FLOW_PING4 : FLOW_PING6; - union epoll_ref ref = { .type = EPOLL_TYPE_PING }; union flow *flow = flow_alloc(); struct icmp_ping_flow *pingf; const struct flowside *tgt; + union epoll_ref ref; if (!flow) return NULL; @@ -194,9 +194,7 @@ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c, pingf->seq = -1; - ref.flowside = FLOW_SIDX(flow, TGTSIDE); - pingf->sock = flowside_sock_l4(c, EPOLL_TYPE_PING, PIF_HOST, - tgt, ref.data); + pingf->sock = flowside_sock_l4(c, EPOLL_TYPE_PING, PIF_HOST, tgt); if (pingf->sock < 0) { warn("Cannot open \"ping\" socket. You might need to:"); @@ -208,6 +206,15 @@ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c, if (pingf->sock > FD_REF_MAX) goto cancel; + ref.type = EPOLL_TYPE_PING; + ref.flowside = FLOW_SIDX(flow, TGTSIDE); + ref.fd = pingf->sock; + + if (epoll_add(c->epollfd, EPOLLIN, ref) < 0) { + close(pingf->sock); + goto cancel; + } + flow_dbg(pingf, "new socket %i for echo ID %"PRIu16, pingf->sock, id); flow_hash_insert(c, FLOW_SIDX(pingf, INISIDE)); diff --git a/pif.c b/pif.c index 592fafaab58a..331942e70710 100644 --- a/pif.c +++ b/pif.c @@ -5,6 +5,7 @@ * Passt/pasta interface types and IDs */ +#include #include #include #include @@ -14,7 +15,7 @@ #include "siphash.h" #include "ip.h" #include "inany.h" -#include "passt.h" +#include "epoll_ctl.h" const char *pif_type_str[] = { [PIF_NONE] = "<none>", @@ -83,7 +84,9 @@ int pif_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif, .sa6.sin6_addr = in6addr_any, .sa6.sin6_port = htons(port), }; + union epoll_ref ref; socklen_t sl; + int ret; ASSERT(pif_is_socket(pif)); @@ -93,11 +96,26 @@ int pif_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif, ASSERT(addr && inany_is_loopback(addr)); } - if (!addr) - return sock_l4_sa(c, type, &sa, sizeof(sa.sa6), - ifname, false, data); + if (!addr) { + ref.fd = sock_l4_sa(c, type, &sa, sizeof(sa.sa6), + ifname, false); + } else { + pif_sockaddr(c, &sa, &sl, pif, addr, port); + ref.fd = sock_l4_sa(c, type, &sa, sl, + ifname, sa.sa_family == AF_INET6); + } + + if (ref.fd < 0) + return ref.fd; + + ref.type = type; + ref.data = data; + + ret = epoll_add(c->epollfd, EPOLLIN, ref); + if (ret < 0) { + close(ref.fd); + return ret; + } - pif_sockaddr(c, &sa, &sl, pif, addr, port); - return sock_l4_sa(c, type, &sa, sl, - ifname, sa.sa_family == AF_INET6, data); + return ref.fd; } diff --git a/udp_flow.c b/udp_flow.c index d9c75f1bb1d8..00e231fe1b01 100644 --- a/udp_flow.c +++ b/udp_flow.c @@ -78,16 +78,28 @@ static int udp_flow_sock(const struct ctx *c, flow_sidx_t sidx; uint32_t data; } fref = { .sidx = FLOW_SIDX(uflow, sidei) }; + union epoll_ref ref; + int rc; int s; - s = flowside_sock_l4(c, EPOLL_TYPE_UDP, pif, side, fref.data); + s = flowside_sock_l4(c, EPOLL_TYPE_UDP, pif, side); if (s < 0) { flow_dbg_perror(uflow, "Couldn't open flow specific socket"); return s; } + ref.type = EPOLL_TYPE_UDP; + ref.data = fref.data; + ref.fd = s; + + rc = epoll_add(c->epollfd, EPOLLIN, ref); + if (rc < 0) { + close(s); + return rc; + } + if (flowside_connect(c, s, pif, side) < 0) { - int rc = -errno; + rc = -errno; epoll_del(c->epollfd, s); close(s); diff --git a/util.c b/util.c index e3f24f7b7e47..707ab3388d13 100644 --- a/util.c +++ b/util.c @@ -47,16 +47,14 @@ * @sl: Length of @sa * @ifname: Interface for binding, NULL for any * @v6only: Set IPV6_V6ONLY socket option - * @data: epoll reference portion for protocol handlers * * Return: newly created socket, negative error code on failure */ int sock_l4_sa(const struct ctx *c, enum epoll_type type, const void *sa, socklen_t sl, - const char *ifname, bool v6only, uint32_t data) + const char *ifname, bool v6only) { sa_family_t af = ((const struct sockaddr *)sa)->sa_family; - union epoll_ref ref = { .type = type, .data = data }; bool freebind = false; int fd, y = 1, ret; uint8_t proto; @@ -99,8 +97,6 @@ int sock_l4_sa(const struct ctx *c, enum epoll_type type, return -EBADF; } - ref.fd = fd; - if (v6only) if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &y, sizeof(y))) debug("Failed to set IPV6_V6ONLY on socket %i", fd); @@ -171,10 +167,6 @@ int sock_l4_sa(const struct ctx *c, enum epoll_type type, return ret; } - ret = epoll_add(c->epollfd, EPOLLIN, ref); - if (ret < 0) - return ret; - return fd; } diff --git a/util.h b/util.h index 8e4b4c5c6032..9108f8f19e14 100644 --- a/util.h +++ b/util.h @@ -207,7 +207,7 @@ struct ctx; int sock_l4_sa(const struct ctx *c, enum epoll_type type, const void *sa, socklen_t sl, - const char *ifname, bool v6only, uint32_t data); + const char *ifname, bool v6only); int sock_unix(char *sock_path); void sock_probe_mem(struct ctx *c); long timespec_diff_ms(const struct timespec *a, const struct timespec *b); -- 2.51.0

Store the epoll id in the flow_common structure for ICMP ping flows using flow_epollid_set() and retrieve the corresponding epoll file descriptor with flow_epollfd() instead of passing c->epollfd directly. This makes ICMP consistent with the recent TCP changes and follows the pattern established in previous commit. Signed-off-by: Laurent Vivier Reviewed-by: David Gibson --- icmp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/icmp.c b/icmp.c index d7c64739876f..d6fee38dd802 100644 --- a/icmp.c +++ b/icmp.c @@ -149,7 +149,7 @@ unexpected: static void icmp_ping_close(const struct ctx *c, const struct icmp_ping_flow *pingf) { - epoll_del(c->epollfd, pingf->sock); + epoll_del(flow_epollfd(&pingf->f), pingf->sock); close(pingf->sock); flow_hash_remove(c, FLOW_SIDX(pingf, INISIDE)); } @@ -206,11 +206,13 @@ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c, if (pingf->sock > FD_REF_MAX) goto cancel; + flow_epollid_set(&pingf->f, EPOLLFD_ID_DEFAULT); + ref.type = EPOLL_TYPE_PING; ref.flowside = FLOW_SIDX(flow, TGTSIDE); ref.fd = pingf->sock; - if (epoll_add(c->epollfd, EPOLLIN, ref) < 0) { + if (epoll_add(flow_epollfd(&pingf->f), EPOLLIN, ref) < 0) { close(pingf->sock); goto cancel; } -- 2.51.0

Extract the epoll event processing logic from main() into a separate passt_worker() function. This refactoring prepares the code for future threading support where passt_worker() will be called as a worker thread callback. The new function handles: - Processing epoll events and dispatching to protocol handlers - Event statistics tracking and printing - Post-handler periodic tasks (timers, deferred work) - Migration handling No functional changes, purely a code restructuring. Signed-off-by: Laurent Vivier --- passt.c | 160 +++++++++++++++++++++++++++++++------------------------- 1 file changed, 88 insertions(+), 72 deletions(-) diff --git a/passt.c b/passt.c index f1d78b79e2c3..5eabfa8f0c51 100644 --- a/passt.c +++ b/passt.c @@ -229,6 +229,92 @@ static void print_stats(const struct ctx *c, const struct passt_stats *stats, lines_printed++; } +/** + * passt_worker() - Process epoll events and handle protocol operations + * @opaque: Pointer to execution context (struct ctx) + * @nfds: Number of file descriptors ready (epoll_wait return value) + * @events: epoll_event array of ready file descriptors + */ +static void passt_worker(void *opaque, int nfds, struct epoll_event *events) +{ + static struct passt_stats stats = { 0 }; + struct ctx *c = opaque; + struct timespec now; + int i; + + if (clock_gettime(CLOCK_MONOTONIC, &now)) + err_perror("Failed to get CLOCK_MONOTONIC time"); + + for (i = 0; i < nfds; i++) { + union epoll_ref ref = *((union epoll_ref *)&events[i].data.u64); + uint32_t eventmask = events[i].events; + + trace("%s: epoll event on %s %i (events: 0x%08x)", + c->mode == MODE_PASTA ? "pasta" : "passt", + EPOLL_TYPE_STR(ref.type), ref.fd, eventmask); + + switch (ref.type) { + case EPOLL_TYPE_TAP_PASTA: + tap_handler_pasta(c, eventmask, &now); + break; + case EPOLL_TYPE_TAP_PASST: + tap_handler_passt(c, eventmask, &now); + break; + case EPOLL_TYPE_TAP_LISTEN: + tap_listen_handler(c, eventmask); + break; + case EPOLL_TYPE_NSQUIT_INOTIFY: + pasta_netns_quit_inotify_handler(c, ref.fd); + break; + case EPOLL_TYPE_NSQUIT_TIMER: + pasta_netns_quit_timer_handler(c, ref); + break; + case EPOLL_TYPE_TCP: + tcp_sock_handler(c, ref, eventmask); + break; + case EPOLL_TYPE_TCP_SPLICE: + tcp_splice_sock_handler(c, ref, eventmask); + break; + case EPOLL_TYPE_TCP_LISTEN: + tcp_listen_handler(c, ref, &now); + break; + case EPOLL_TYPE_TCP_TIMER: + tcp_timer_handler(c, ref); + break; + case EPOLL_TYPE_UDP_LISTEN: + udp_listen_sock_handler(c, ref, eventmask, &now); + break; + case EPOLL_TYPE_UDP: + udp_sock_handler(c, ref, eventmask, &now); + break; + case EPOLL_TYPE_PING: + icmp_sock_handler(c, ref); + break; + case EPOLL_TYPE_VHOST_CMD: + vu_control_handler(c->vdev, c->fd_tap, eventmask); + break; + case EPOLL_TYPE_VHOST_KICK: + vu_kick_cb(c->vdev, ref, &now); + break; + case EPOLL_TYPE_REPAIR_LISTEN: + repair_listen_handler(c, eventmask); + break; + case EPOLL_TYPE_REPAIR: + repair_handler(c, eventmask); + break; + default: + /* Can't happen */ + ASSERT(0); + } + stats.events[ref.type]++; + print_stats(c, &stats, &now); + } + + post_handler(c, &now); + + migrate_handler(c); +} + /** * main() - Entry point and main loop * @argc: Argument count @@ -246,8 +332,7 @@ static void print_stats(const struct ctx *c, const struct passt_stats *stats, int main(int argc, char **argv) { struct epoll_event events[NUM_EPOLL_EVENTS]; - struct passt_stats stats = { 0 }; - int nfds, i, devnull_fd = -1; + int nfds, devnull_fd = -1; struct ctx c = { 0 }; struct rlimit limit; struct timespec now; @@ -355,77 +440,8 @@ loop: if (nfds == -1 && errno != EINTR) die_perror("epoll_wait() failed in main loop"); - if (clock_gettime(CLOCK_MONOTONIC, &now)) - err_perror("Failed to get CLOCK_MONOTONIC time"); - - for (i = 0; i < nfds; i++) { - union epoll_ref ref = *((union epoll_ref *)&events[i].data.u64); - uint32_t eventmask = events[i].events; - - trace("%s: epoll event on %s %i (events: 0x%08x)", - c.mode == MODE_PASTA ? "pasta" : "passt", - EPOLL_TYPE_STR(ref.type), ref.fd, eventmask); - - switch (ref.type) { - case EPOLL_TYPE_TAP_PASTA: - tap_handler_pasta(&c, eventmask, &now); - break; - case EPOLL_TYPE_TAP_PASST: - tap_handler_passt(&c, eventmask, &now); - break; - case EPOLL_TYPE_TAP_LISTEN: - tap_listen_handler(&c, eventmask); - break; - case EPOLL_TYPE_NSQUIT_INOTIFY: - pasta_netns_quit_inotify_handler(&c, ref.fd); - break; - case EPOLL_TYPE_NSQUIT_TIMER: - pasta_netns_quit_timer_handler(&c, ref); - break; - case EPOLL_TYPE_TCP: - tcp_sock_handler(&c, ref, eventmask); - break; - case EPOLL_TYPE_TCP_SPLICE: - tcp_splice_sock_handler(&c, ref, eventmask); - break; - case EPOLL_TYPE_TCP_LISTEN: - tcp_listen_handler(&c, ref, &now); - break; - case EPOLL_TYPE_TCP_TIMER: - tcp_timer_handler(&c, ref); - break; - case EPOLL_TYPE_UDP_LISTEN: - udp_listen_sock_handler(&c, ref, eventmask, &now); - break; - case EPOLL_TYPE_UDP: - udp_sock_handler(&c, ref, eventmask, &now); - break; - case EPOLL_TYPE_PING: - icmp_sock_handler(&c, ref); - break; - case EPOLL_TYPE_VHOST_CMD: - vu_control_handler(c.vdev, c.fd_tap, eventmask); - break; - case EPOLL_TYPE_VHOST_KICK: - vu_kick_cb(c.vdev, ref, &now); - break; - case EPOLL_TYPE_REPAIR_LISTEN: - repair_listen_handler(&c, eventmask); - break; - case EPOLL_TYPE_REPAIR: - repair_handler(&c, eventmask); - break; - default: - /* Can't happen */ - ASSERT(0); - } - stats.events[ref.type]++; - print_stats(&c, &stats, &now); - } - - post_handler(&c, &now); - migrate_handler(&c); + passt_worker(&c, nfds, events); goto loop; } -- 2.51.0

On Tue, Oct 21, 2025 at 11:01:11PM +0200, Laurent Vivier wrote:

Centralize epoll_add() and epoll_del() helper functions into new epoll_ctl.c/h files.

This also moves the union epoll_ref definition from passt.h to epoll_ctl.h where it's more logically placed.

The new epoll_add() helper simplifies adding file descriptors to epoll by taking an epoll_ref and events, handling error reporting consistently across all call sites.

Signed-off-by: Laurent Vivier

Reviewed-by: David Gibson

--- Makefile | 22 +++++++++++----------- epoll_ctl.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ epoll_ctl.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ icmp.c | 4 +--- passt.c | 2 +- passt.h | 34 ---------------------------------- pasta.c | 7 +++---- repair.c | 18 +++++++----------- tap.c | 13 ++++--------- tcp.c | 2 +- tcp_splice.c | 2 +- udp.c | 2 +- udp_flow.c | 1 + util.c | 22 +++------------------- util.h | 4 +++- vhost_user.c | 8 ++------ vu_common.c | 2 +- 17 files changed, 136 insertions(+), 103 deletions(-) create mode 100644 epoll_ctl.c create mode 100644 epoll_ctl.h

diff --git a/Makefile b/Makefile index 3328f8324140..91e037b8fd3c 100644 --- a/Makefile +++ b/Makefile @@ -37,23 +37,23 @@ FLAGS += -DPAGE_SIZE=$(shell getconf PAGE_SIZE) FLAGS += -DVERSION=\"$(VERSION)\" FLAGS += -DDUAL_STACK_SOCKETS=$(DUAL_STACK_SOCKETS)

-PASST_SRCS = arch.c arp.c checksum.c conf.c dhcp.c dhcpv6.c flow.c fwd.c \ - icmp.c igmp.c inany.c iov.c ip.c isolation.c lineread.c log.c mld.c \ - ndp.c netlink.c migrate.c packet.c passt.c pasta.c pcap.c pif.c \ - repair.c tap.c tcp.c tcp_buf.c tcp_splice.c tcp_vu.c udp.c udp_flow.c \ - udp_vu.c util.c vhost_user.c virtio.c vu_common.c +PASST_SRCS = arch.c arp.c checksum.c conf.c dhcp.c dhcpv6.c epoll_ctl.c \ + flow.c fwd.c icmp.c igmp.c inany.c iov.c ip.c isolation.c lineread.c \ + log.c mld.c ndp.c netlink.c migrate.c packet.c passt.c pasta.c pcap.c \ + pif.c repair.c tap.c tcp.c tcp_buf.c tcp_splice.c tcp_vu.c udp.c \ + udp_flow.c udp_vu.c util.c vhost_user.c virtio.c vu_common.c QRAP_SRCS = qrap.c PASST_REPAIR_SRCS = passt-repair.c SRCS = $(PASST_SRCS) $(QRAP_SRCS) $(PASST_REPAIR_SRCS)

MANPAGES = passt.1 pasta.1 qrap.1 passt-repair.1

-PASST_HEADERS = arch.h arp.h checksum.h conf.h dhcp.h dhcpv6.h flow.h fwd.h \ - flow_table.h icmp.h icmp_flow.h inany.h iov.h ip.h isolation.h \ - lineread.h log.h migrate.h ndp.h netlink.h packet.h passt.h pasta.h \ - pcap.h pif.h repair.h siphash.h tap.h tcp.h tcp_buf.h tcp_conn.h \ - tcp_internal.h tcp_splice.h tcp_vu.h udp.h udp_flow.h udp_internal.h \ - udp_vu.h util.h vhost_user.h virtio.h vu_common.h +PASST_HEADERS = arch.h arp.h checksum.h conf.h dhcp.h dhcpv6.h epoll_ctl.h \ + flow.h fwd.h flow_table.h icmp.h icmp_flow.h inany.h iov.h ip.h \ + isolation.h lineread.h log.h migrate.h ndp.h netlink.h packet.h \ + passt.h pasta.h pcap.h pif.h repair.h siphash.h tap.h tcp.h tcp_buf.h \ + tcp_conn.h tcp_internal.h tcp_splice.h tcp_vu.h udp.h udp_flow.h \ + udp_internal.h udp_vu.h util.h vhost_user.h virtio.h vu_common.h HEADERS = $(PASST_HEADERS) seccomp.h

C := \#include \nint main(){int a=getrandom(0, 0, 0);} diff --git a/epoll_ctl.c b/epoll_ctl.c new file mode 100644 index 000000000000..728a2afe1f6b --- /dev/null +++ b/epoll_ctl.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* epoll_ctl.c - epoll manipulation helpers + * + * Copyright Red Hat + * Author: Laurent Vivier + */ + +#include + +#include "epoll_ctl.h" + +/** + * epoll_add() - Add a file descriptor to an epollfd + * @epollfd: epoll file descriptor to add to + * @events: epoll events + * @ref: epoll reference for the file descriptor (includes fd and metadata) + * + * Return: 0 on success, negative errno on failure + */ +int epoll_add(int epollfd, uint32_t events, union epoll_ref ref) +{ + struct epoll_event ev; + int ret; + + ev.events = events; + ev.data.u64 = ref.u64; + + ret = epoll_ctl(epollfd, EPOLL_CTL_ADD, ref.fd, &ev); + if (ret == -1) { + ret = -errno; + err("Failed to add fd to epoll: %s", strerror_(-ret)); + } + + return ret; +} + +/** + * epoll_del() - Remove a file descriptor from an epollfd + * @epollfd: epoll file descriptor to remove from + * @fd: File descriptor to remove + */ +void epoll_del(int epollfd, int fd) +{ + epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, NULL); +} diff --git a/epoll_ctl.h b/epoll_ctl.h new file mode 100644 index 000000000000..2d7e7123ae9d --- /dev/null +++ b/epoll_ctl.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * Copyright Red Hat + * Author: Laurent Vivier + */ + +#ifndef EPOLL_CTL_H +#define EPOLL_CTL_H + +#include + +#include "util.h" +#include "passt.h" +#include "epoll_type.h" +#include "flow.h" +#include "tcp.h" +#include "udp.h" + +/** + * union epoll_ref - Breakdown of reference for epoll fd bookkeeping + * @type: Type of fd (tells us what to do with events) + * @fd: File descriptor number (implies < 2^24 total descriptors) + * @flow: Index of the flow this fd is linked to + * @tcp_listen: TCP-specific reference part for listening sockets + * @udp: UDP-specific reference part + * @data: Data handled by protocol handlers + * @nsdir_fd: netns dirfd for fallback timer checking if namespace is gone + * @queue: vhost-user queue index for this fd + * @u64: Opaque reference for epoll_ctl() and epoll_wait() + */ +union epoll_ref { + struct { + enum epoll_type type:8; + int32_t fd:FD_REF_BITS; + union { + uint32_t flow; + flow_sidx_t flowside; + union tcp_listen_epoll_ref tcp_listen; + union udp_listen_epoll_ref udp; + uint32_t data; + int nsdir_fd; + int queue; + }; + }; + uint64_t u64; +}; +static_assert(sizeof(union epoll_ref) <= sizeof(union epoll_data), + "epoll_ref must have same size as epoll_data"); + +int epoll_add(int epollfd, uint32_t events, union epoll_ref ref); +void epoll_del(int epollfd, int fd); +#endif /* EPOLL_CTL_H */ diff --git a/icmp.c b/icmp.c index bd3108a21675..c26561da80bf 100644 --- a/icmp.c +++ b/icmp.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include @@ -23,10 +22,8 @@ #include #include #include -#include #include #include -#include #include

#include @@ -41,6 +38,7 @@ #include "inany.h" #include "icmp.h" #include "flow_table.h" +#include "epoll_ctl.h"

#define ICMP_ECHO_TIMEOUT 60 /* s, timeout for ICMP socket activity */ #define ICMP_NUM_IDS (1U << 16) diff --git a/passt.c b/passt.c index bdb7b6935f0c..af928111786b 100644 --- a/passt.c +++ b/passt.c @@ -19,7 +19,6 @@ * created in a separate network namespace). */

-#include #include #include #include @@ -53,6 +52,7 @@ #include "vu_common.h" #include "migrate.h" #include "repair.h" +#include "epoll_ctl.h"

#define NUM_EPOLL_EVENTS 8

diff --git a/passt.h b/passt.h index 0075eb4b3b16..befe56bb167b 100644 --- a/passt.h +++ b/passt.h @@ -35,40 +35,6 @@ union epoll_ref; #define MAC_OUR_LAA \ ((uint8_t [ETH_ALEN]){0x9a, 0x55, 0x9a, 0x55, 0x9a, 0x55})

-/** - * union epoll_ref - Breakdown of reference for epoll fd bookkeeping - * @type: Type of fd (tells us what to do with events) - * @fd: File descriptor number (implies < 2^24 total descriptors) - * @flow: Index of the flow this fd is linked to - * @tcp_listen: TCP-specific reference part for listening sockets - * @udp: UDP-specific reference part - * @icmp: ICMP-specific reference part - * @data: Data handled by protocol handlers - * @nsdir_fd: netns dirfd for fallback timer checking if namespace is gone - * @queue: vhost-user queue index for this fd - * @u64: Opaque reference for epoll_ctl() and epoll_wait() - */ -union epoll_ref { - struct { - enum epoll_type type:8; -#define FD_REF_BITS 24 -#define FD_REF_MAX ((int)MAX_FROM_BITS(FD_REF_BITS)) - int32_t fd:FD_REF_BITS; - union { - uint32_t flow; - flow_sidx_t flowside; - union tcp_listen_epoll_ref tcp_listen; - union udp_listen_epoll_ref udp; - uint32_t data; - int nsdir_fd; - int queue; - }; - }; - uint64_t u64; -}; -static_assert(sizeof(union epoll_ref) <= sizeof(union epoll_data), - "epoll_ref must have same size as epoll_data"); - /* Large enough for ~128 maximum size frames */ #define PKT_BUF_BYTES (8UL << 20)

diff --git a/pasta.c b/pasta.c index 687406b6e736..e8636f45df2f 100644 --- a/pasta.c +++ b/pasta.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include @@ -49,6 +48,7 @@ #include "isolation.h" #include "netlink.h" #include "log.h" +#include "epoll_ctl.h"

#define HOSTNAME_PREFIX "pasta-"

@@ -444,7 +444,6 @@ static int pasta_netns_quit_timer(void) */ void pasta_netns_quit_init(const struct ctx *c) { - struct epoll_event ev = { .events = EPOLLIN }; int flags = O_NONBLOCK | O_CLOEXEC; struct statfs s = { 0 }; bool try_inotify = true; @@ -487,8 +486,8 @@ void pasta_netns_quit_init(const struct ctx *c) die("netns monitor file number %i too big, exiting", fd);

ref.fd = fd; - ev.data.u64 = ref.u64; - epoll_ctl(c->epollfd, EPOLL_CTL_ADD, fd, &ev); + + epoll_add(c->epollfd, EPOLLIN, ref); }

/** diff --git a/repair.c b/repair.c index f6b1bf36479c..69c530773173 100644 --- a/repair.c +++ b/repair.c @@ -22,6 +22,7 @@ #include "inany.h" #include "flow.h" #include "flow_table.h" +#include "epoll_ctl.h"

#include "repair.h"

@@ -47,7 +48,6 @@ static int repair_nfds; void repair_sock_init(const struct ctx *c) { union epoll_ref ref = { .type = EPOLL_TYPE_REPAIR_LISTEN }; - struct epoll_event ev = { 0 };

if (c->fd_repair_listen == -1) return; @@ -58,10 +58,8 @@ void repair_sock_init(const struct ctx *c) }

ref.fd = c->fd_repair_listen; - ev.events = EPOLLIN | EPOLLHUP | EPOLLET; - ev.data.u64 = ref.u64; - if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_repair_listen, &ev)) - err_perror("repair helper socket epoll_ctl(), won't migrate"); + if (epoll_add(c->epollfd, EPOLLIN | EPOLLHUP | EPOLLET, ref)) + err("repair helper socket epoll_ctl(), won't migrate"); }

/** @@ -74,7 +72,6 @@ void repair_sock_init(const struct ctx *c) int repair_listen_handler(struct ctx *c, uint32_t events) { union epoll_ref ref = { .type = EPOLL_TYPE_REPAIR }; - struct epoll_event ev = { 0 }; struct ucred ucred; socklen_t len; int rc; @@ -112,11 +109,10 @@ int repair_listen_handler(struct ctx *c, uint32_t events) info("Accepted TCP_REPAIR helper, PID %i", ucred.pid);

ref.fd = c->fd_repair; - ev.events = EPOLLHUP | EPOLLET; - ev.data.u64 = ref.u64; - if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_repair, &ev)) { - rc = errno; - debug_perror("epoll_ctl() on TCP_REPAIR helper socket"); + + rc = epoll_add(c->epollfd, EPOLLHUP | EPOLLET, ref); + if (rc < 0) { + debug("epoll_ctl() on TCP_REPAIR helper socket"); close(c->fd_repair); c->fd_repair = -1; return rc; diff --git a/tap.c b/tap.c index 9812f120d426..314c2aebd39d 100644 --- a/tap.c +++ b/tap.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -61,6 +60,7 @@ #include "log.h" #include "vhost_user.h" #include "vu_common.h" +#include "epoll_ctl.h"

/* Maximum allowed frame lengths (including L2 header) */

@@ -1327,14 +1327,12 @@ static void tap_backend_show_hints(struct ctx *c) static void tap_sock_unix_init(const struct ctx *c) { union epoll_ref ref = { .type = EPOLL_TYPE_TAP_LISTEN }; - struct epoll_event ev = { 0 };

listen(c->fd_tap_listen, 0);

ref.fd = c->fd_tap_listen; - ev.events = EPOLLIN | EPOLLET; - ev.data.u64 = ref.u64; - epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap_listen, &ev); + + epoll_add(c->epollfd, EPOLLIN | EPOLLET, ref); }

/** @@ -1343,7 +1341,6 @@ static void tap_sock_unix_init(const struct ctx *c) */ static void tap_start_connection(const struct ctx *c) { - struct epoll_event ev = { 0 }; union epoll_ref ref = { 0 };

ref.fd = c->fd_tap; @@ -1359,9 +1356,7 @@ static void tap_start_connection(const struct ctx *c) break; }

- ev.events = EPOLLIN | EPOLLRDHUP; - ev.data.u64 = ref.u64; - epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev); + epoll_add(c->epollfd, EPOLLIN | EPOLLRDHUP, ref);

if (c->ifi4) arp_send_init_req(c); diff --git a/tcp.c b/tcp.c index 745353f782f5..db9f17c0622f 100644 --- a/tcp.c +++ b/tcp.c @@ -279,7 +279,6 @@ #include #include #include -#include #include #include #include @@ -309,6 +308,7 @@ #include "tcp_internal.h" #include "tcp_buf.h" #include "tcp_vu.h" +#include "epoll_ctl.h"

/* * The size of TCP header (including options) is given by doff (Data Offset) diff --git a/tcp_splice.c b/tcp_splice.c index 666ee62b738f..6f21184bdc55 100644 --- a/tcp_splice.c +++ b/tcp_splice.c @@ -44,7 +44,6 @@ #include #include #include -#include #include #include

@@ -56,6 +55,7 @@ #include "siphash.h" #include "inany.h" #include "flow.h" +#include "epoll_ctl.h"

#include "flow_table.h"

diff --git a/udp.c b/udp.c index 86585b7e0942..3812d5c2336f 100644 --- a/udp.c +++ b/udp.c @@ -94,7 +94,6 @@ #include #include #include -#include #include #include #include @@ -115,6 +114,7 @@ #include "flow_table.h" #include "udp_internal.h" #include "udp_vu.h" +#include "epoll_ctl.h"

#define UDP_MAX_FRAMES 32 /* max # of frames to receive at once */

diff --git a/udp_flow.c b/udp_flow.c index 84973f807167..d9c75f1bb1d8 100644 --- a/udp_flow.c +++ b/udp_flow.c @@ -15,6 +15,7 @@ #include "passt.h" #include "flow_table.h" #include "udp_internal.h" +#include "epoll_ctl.h"

#define UDP_CONN_TIMEOUT 180 /* s, timeout for ephemeral or local bind */

diff --git a/util.c b/util.c index 1067486be414..e3f24f7b7e47 100644 --- a/util.c +++ b/util.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -35,6 +34,7 @@ #include "packet.h" #include "log.h" #include "pcap.h" +#include "epoll_ctl.h" #ifdef HAS_GETRANDOM #include #endif @@ -58,7 +58,6 @@ int sock_l4_sa(const struct ctx *c, enum epoll_type type, sa_family_t af = ((const struct sockaddr *)sa)->sa_family; union epoll_ref ref = { .type = type, .data = data }; bool freebind = false; - struct epoll_event ev; int fd, y = 1, ret; uint8_t proto; int socktype; @@ -172,13 +171,9 @@ int sock_l4_sa(const struct ctx *c, enum epoll_type type, return ret; }

- ev.events = EPOLLIN; - ev.data.u64 = ref.u64; - if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, fd, &ev) == -1) { - ret = -errno; - warn("L4 epoll_ctl: %s", strerror_(-ret)); + ret = epoll_add(c->epollfd, EPOLLIN, ref); + if (ret < 0) return ret; - }

return fd; } @@ -994,17 +989,6 @@ void raw_random(void *buf, size_t buflen) die("Unexpected EOF on random data source"); }

-/** - * epoll_del() - Remove a file descriptor from our passt epoll - * @epollfd: epoll file descriptor to remove from - * @fd: File descriptor to remove - */ -void epoll_del(int epollfd, int fd) -{ - epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, NULL); - -} - /** * encode_domain_name() - Encode domain name according to RFC 1035, section 3.1 * @buf: Buffer to fill in with encoded domain name diff --git a/util.h b/util.h index c61cbef357aa..8e4b4c5c6032 100644 --- a/util.h +++ b/util.h @@ -193,6 +193,9 @@ int do_clone(int (*fn)(void *), char *stack_area, size_t stack_size, int flags, #define SNDBUF_BIG (4ULL * 1024 * 1024) #define SNDBUF_SMALL (128ULL * 1024)

+#define FD_REF_BITS 24 +#define FD_REF_MAX ((int)MAX_FROM_BITS(FD_REF_BITS)) + #include #include #include @@ -300,7 +303,6 @@ static inline bool mod_between(unsigned x, unsigned i, unsigned j, unsigned m) #define FPRINTF(f, ...) (void)fprintf(f, __VA_ARGS__)

void raw_random(void *buf, size_t buflen); -void epoll_del(int epollfd, int fd);

/* * Starting from glibc 2.40.9000 and commit 25a5eb4010df ("string: strerror, diff --git a/vhost_user.c b/vhost_user.c index f8324c59cc6c..aa7c869d9e56 100644 --- a/vhost_user.c +++ b/vhost_user.c @@ -32,8 +32,6 @@ #include #include #include -#include -#include #include #include #include @@ -45,6 +43,7 @@ #include "vhost_user.h" #include "pcap.h" #include "migrate.h" +#include "epoll_ctl.h"

/* vhost-user version we are compatible with */ #define VHOST_USER_VERSION 1 @@ -753,11 +752,8 @@ static void vu_set_watch(const struct vu_dev *vdev, int idx) .fd = vdev->vq[idx].kick_fd, .queue = idx }; - struct epoll_event ev = { 0 };

- ev.data.u64 = ref.u64; - ev.events = EPOLLIN; - epoll_ctl(vdev->context->epollfd, EPOLL_CTL_ADD, ref.fd, &ev); + epoll_add(vdev->context->epollfd, EPOLLIN, ref); }

/** diff --git a/vu_common.c b/vu_common.c index b716070ea3c3..b13b7c308fd8 100644 --- a/vu_common.c +++ b/vu_common.c @@ -6,7 +6,6 @@ */

#include -#include #include #include #include @@ -19,6 +18,7 @@ #include "pcap.h" #include "vu_common.h" #include "migrate.h" +#include "epoll_ctl.h"

#define VU_MAX_TX_BUFFER_NB 2

-- 2.51.0

-- David Gibson (he or they) | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you, not the other way | around. http://www.ozlabs.org/~dgibson

On Tue, Oct 21, 2025 at 11:01:16PM +0200, Laurent Vivier wrote:

Extract the epoll event processing logic from main() into a separate passt_worker() function. This refactoring prepares the code for future threading support where passt_worker() will be called as a worker thread callback.

The new function handles: - Processing epoll events and dispatching to protocol handlers - Event statistics tracking and printing - Post-handler periodic tasks (timers, deferred work) - Migration handling

No functional changes, purely a code restructuring.

Signed-off-by: Laurent Vivier

Reviewed-by: David Gibson

--- passt.c | 160 +++++++++++++++++++++++++++++++------------------------- 1 file changed, 88 insertions(+), 72 deletions(-)

diff --git a/passt.c b/passt.c index f1d78b79e2c3..5eabfa8f0c51 100644 --- a/passt.c +++ b/passt.c @@ -229,6 +229,92 @@ static void print_stats(const struct ctx *c, const struct passt_stats *stats, lines_printed++; }

+/** + * passt_worker() - Process epoll events and handle protocol operations + * @opaque: Pointer to execution context (struct ctx) + * @nfds: Number of file descriptors ready (epoll_wait return value) + * @events: epoll_event array of ready file descriptors + */ +static void passt_worker(void *opaque, int nfds, struct epoll_event *events) +{ + static struct passt_stats stats = { 0 }; + struct ctx *c = opaque; + struct timespec now; + int i; + + if (clock_gettime(CLOCK_MONOTONIC, &now)) + err_perror("Failed to get CLOCK_MONOTONIC time"); + + for (i = 0; i < nfds; i++) { + union epoll_ref ref = *((union epoll_ref *)&events[i].data.u64); + uint32_t eventmask = events[i].events; + + trace("%s: epoll event on %s %i (events: 0x%08x)", + c->mode == MODE_PASTA ? "pasta" : "passt", + EPOLL_TYPE_STR(ref.type), ref.fd, eventmask); + + switch (ref.type) { + case EPOLL_TYPE_TAP_PASTA: + tap_handler_pasta(c, eventmask, &now); + break; + case EPOLL_TYPE_TAP_PASST: + tap_handler_passt(c, eventmask, &now); + break; + case EPOLL_TYPE_TAP_LISTEN: + tap_listen_handler(c, eventmask); + break; + case EPOLL_TYPE_NSQUIT_INOTIFY: + pasta_netns_quit_inotify_handler(c, ref.fd); + break; + case EPOLL_TYPE_NSQUIT_TIMER: + pasta_netns_quit_timer_handler(c, ref); + break; + case EPOLL_TYPE_TCP: + tcp_sock_handler(c, ref, eventmask); + break; + case EPOLL_TYPE_TCP_SPLICE: + tcp_splice_sock_handler(c, ref, eventmask); + break; + case EPOLL_TYPE_TCP_LISTEN: + tcp_listen_handler(c, ref, &now); + break; + case EPOLL_TYPE_TCP_TIMER: + tcp_timer_handler(c, ref); + break; + case EPOLL_TYPE_UDP_LISTEN: + udp_listen_sock_handler(c, ref, eventmask, &now); + break; + case EPOLL_TYPE_UDP: + udp_sock_handler(c, ref, eventmask, &now); + break; + case EPOLL_TYPE_PING: + icmp_sock_handler(c, ref); + break; + case EPOLL_TYPE_VHOST_CMD: + vu_control_handler(c->vdev, c->fd_tap, eventmask); + break; + case EPOLL_TYPE_VHOST_KICK: + vu_kick_cb(c->vdev, ref, &now); + break; + case EPOLL_TYPE_REPAIR_LISTEN: + repair_listen_handler(c, eventmask); + break; + case EPOLL_TYPE_REPAIR: + repair_handler(c, eventmask); + break; + default: + /* Can't happen */ + ASSERT(0); + } + stats.events[ref.type]++; + print_stats(c, &stats, &now); + } + + post_handler(c, &now); + + migrate_handler(c); +} + /** * main() - Entry point and main loop * @argc: Argument count @@ -246,8 +332,7 @@ static void print_stats(const struct ctx *c, const struct passt_stats *stats, int main(int argc, char **argv) { struct epoll_event events[NUM_EPOLL_EVENTS]; - struct passt_stats stats = { 0 }; - int nfds, i, devnull_fd = -1; + int nfds, devnull_fd = -1; struct ctx c = { 0 }; struct rlimit limit; struct timespec now; @@ -355,77 +440,8 @@ loop: if (nfds == -1 && errno != EINTR) die_perror("epoll_wait() failed in main loop");

- if (clock_gettime(CLOCK_MONOTONIC, &now)) - err_perror("Failed to get CLOCK_MONOTONIC time"); - - for (i = 0; i < nfds; i++) { - union epoll_ref ref = *((union epoll_ref *)&events[i].data.u64); - uint32_t eventmask = events[i].events; - - trace("%s: epoll event on %s %i (events: 0x%08x)", - c.mode == MODE_PASTA ? "pasta" : "passt", - EPOLL_TYPE_STR(ref.type), ref.fd, eventmask); - - switch (ref.type) { - case EPOLL_TYPE_TAP_PASTA: - tap_handler_pasta(&c, eventmask, &now); - break; - case EPOLL_TYPE_TAP_PASST: - tap_handler_passt(&c, eventmask, &now); - break; - case EPOLL_TYPE_TAP_LISTEN: - tap_listen_handler(&c, eventmask); - break; - case EPOLL_TYPE_NSQUIT_INOTIFY: - pasta_netns_quit_inotify_handler(&c, ref.fd); - break; - case EPOLL_TYPE_NSQUIT_TIMER: - pasta_netns_quit_timer_handler(&c, ref); - break; - case EPOLL_TYPE_TCP: - tcp_sock_handler(&c, ref, eventmask); - break; - case EPOLL_TYPE_TCP_SPLICE: - tcp_splice_sock_handler(&c, ref, eventmask); - break; - case EPOLL_TYPE_TCP_LISTEN: - tcp_listen_handler(&c, ref, &now); - break; - case EPOLL_TYPE_TCP_TIMER: - tcp_timer_handler(&c, ref); - break; - case EPOLL_TYPE_UDP_LISTEN: - udp_listen_sock_handler(&c, ref, eventmask, &now); - break; - case EPOLL_TYPE_UDP: - udp_sock_handler(&c, ref, eventmask, &now); - break; - case EPOLL_TYPE_PING: - icmp_sock_handler(&c, ref); - break; - case EPOLL_TYPE_VHOST_CMD: - vu_control_handler(c.vdev, c.fd_tap, eventmask); - break; - case EPOLL_TYPE_VHOST_KICK: - vu_kick_cb(c.vdev, ref, &now); - break; - case EPOLL_TYPE_REPAIR_LISTEN: - repair_listen_handler(&c, eventmask); - break; - case EPOLL_TYPE_REPAIR: - repair_handler(&c, eventmask); - break; - default: - /* Can't happen */ - ASSERT(0); - } - stats.events[ref.type]++; - print_stats(&c, &stats, &now); - } - - post_handler(&c, &now);

- migrate_handler(&c); + passt_worker(&c, nfds, events);

goto loop; } -- 2.51.0

-- David Gibson (he or they) | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you, not the other way | around. http://www.ozlabs.org/~dgibson