From: Laurent Vivier <lvivier@redhat.com>
To: passt-dev@passt.top
Cc: Laurent Vivier <lvivier@redhat.com>
Subject: [PATCH 2/5] util: Move epoll registration out of sock_l4_sa()
Date: Fri, 3 Oct 2025 17:27:14 +0200 [thread overview]
Message-ID: <20251003152717.2437765-3-lvivier@redhat.com> (raw)
In-Reply-To: <20251003152717.2437765-1-lvivier@redhat.com>
Move epoll_ctl() 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 <lvivier@redhat.com>
---
flow.c | 10 ++++------
flow.h | 2 +-
icmp.c | 19 +++++++++++++++----
pif.c | 34 ++++++++++++++++++++++++++++------
udp_flow.c | 17 ++++++++++++++++-
util.c | 15 +--------------
util.h | 2 +-
7 files changed, 66 insertions(+), 33 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 bd3108a21675..d6f0abe68269 100644
--- a/icmp.c
+++ b/icmp.c
@@ -172,10 +172,11 @@ 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;
+ struct epoll_event ev;
+ union epoll_ref ref;
if (!flow)
return NULL;
@@ -196,9 +197,7 @@ 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:");
@@ -210,6 +209,18 @@ 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;
+
+ ev.events = EPOLLIN;
+ ev.data.u64 = ref.u64;
+ if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, pingf->sock, &ev) == -1) {
+ warn_perror("L4 epoll_ctl");
+ 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..906be4025f58 100644
--- a/pif.c
+++ b/pif.c
@@ -5,9 +5,11 @@
* Passt/pasta interface types and IDs
*/
+#include <errno.h>
#include <stdint.h>
#include <assert.h>
#include <netinet/in.h>
+#include <sys/epoll.h>
#include "util.h"
#include "pif.h"
@@ -83,6 +85,8 @@ 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),
};
+ struct epoll_event ev;
+ union epoll_ref ref;
socklen_t sl;
ASSERT(pif_is_socket(pif));
@@ -93,11 +97,29 @@ 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;
+
+ ev.events = EPOLLIN;
+ ev.data.u64 = ref.u64;
+ if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, ref.fd, &ev) == -1) {
+ int ret = -errno;
+ close(ref.fd);
+ warn("L4 epoll_ctl: %s", strerror_(-ret));
+ 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 84973f807167..f99994523a6c 100644
--- a/udp_flow.c
+++ b/udp_flow.c
@@ -77,14 +77,29 @@ static int udp_flow_sock(const struct ctx *c,
flow_sidx_t sidx;
uint32_t data;
} fref = { .sidx = FLOW_SIDX(uflow, sidei) };
+ struct epoll_event ev;
+ union epoll_ref ref;
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;
+
+ ev.events = EPOLLIN;
+ ev.data.u64 = ref.u64;
+ if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, s, &ev) == -1) {
+ int rc = -errno;
+ close(s);
+ warn("L4 epoll_ctl: %s", strerror_(-rc));
+ return rc;
+ }
+
if (flowside_connect(c, s, pif, side) < 0) {
int rc = -errno;
diff --git a/util.c b/util.c
index 88a91b1100f5..17c062c85bf8 100644
--- a/util.c
+++ b/util.c
@@ -47,18 +47,15 @@
* @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;
- struct epoll_event ev;
int fd, y = 1, ret;
uint8_t proto;
int socktype;
@@ -100,8 +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);
@@ -172,14 +167,6 @@ 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));
- return ret;
- }
-
return fd;
}
diff --git a/util.h b/util.h
index c61cbef357aa..89478de023f9 100644
--- a/util.h
+++ b/util.h
@@ -204,7 +204,7 @@ 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);
--
2.50.1
next prev parent reply other threads:[~2025-10-03 15:27 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-03 15:27 [PATCH 0/5] Refactor epoll handling in preparation for multithreading Laurent Vivier
2025-10-03 15:27 ` [PATCH 1/5] util: Simplify epoll_del() interface to take epollfd directly Laurent Vivier
2025-10-07 5:26 ` David Gibson
2025-10-03 15:27 ` Laurent Vivier [this message]
2025-10-07 5:57 ` [PATCH 2/5] util: Move epoll registration out of sock_l4_sa() David Gibson
2025-10-03 15:27 ` [PATCH 3/5] tcp, flow: Replace per-connection in_epoll flag with epollfd in flow_common Laurent Vivier
2025-10-07 6:07 ` David Gibson
2025-10-07 9:51 ` Stefano Brivio
2025-10-03 15:27 ` [PATCH 4/5] icmp: Use epollfd from flow_common structure Laurent Vivier
2025-10-03 15:27 ` [PATCH 5/5] udp: " Laurent Vivier
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251003152717.2437765-3-lvivier@redhat.com \
--to=lvivier@redhat.com \
--cc=passt-dev@passt.top \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://passt.top/passt
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).