* [PATCH v2 1/6] util: Simplify epoll_del() interface to take epollfd directly
2025-10-07 16:40 [PATCH v2 0/6] Refactor epoll handling in preparation for multithreading Laurent Vivier
@ 2025-10-07 16:40 ` Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 2/6] epoll_ctl: Extract epoll operations Laurent Vivier
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Laurent Vivier @ 2025-10-07 16:40 UTC (permalink / raw)
To: passt-dev; +Cc: Laurent Vivier, David Gibson
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 <lvivier@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
---
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 95d309bd1938..134c37a72979 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 48b1ef29bfe8..04725deabb65 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;
}
@@ -3445,7 +3445,7 @@ 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..88a91b1100f5 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 add to
* @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 fa343a86fac2..1221ac1abcd0 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;
}
@@ -1092,7 +1092,7 @@ 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;
}
--
2.50.1
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH v2 2/6] epoll_ctl: Extract epoll operations
2025-10-07 16:40 [PATCH v2 0/6] Refactor epoll handling in preparation for multithreading Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 1/6] util: Simplify epoll_del() interface to take epollfd directly Laurent Vivier
@ 2025-10-07 16:40 ` Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 3/6] util: Move epoll registration out of sock_l4_sa() Laurent Vivier
` (3 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Laurent Vivier @ 2025-10-07 16:40 UTC (permalink / raw)
To: passt-dev; +Cc: Laurent Vivier
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 <lvivier@redhat.com>
---
Makefile | 22 +++++++++++-----------
epoll_ctl.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
epoll_ctl.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
icmp.c | 4 +---
passt.c | 2 +-
passt.h | 34 ----------------------------------
pasta.c | 7 +++----
repair.c | 14 +++++---------
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, 134 insertions(+), 101 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 <sys/random.h>\nint main(){int a=getrandom(0, 0, 0);}
diff --git a/epoll_ctl.c b/epoll_ctl.c
new file mode 100644
index 000000000000..0a06350f87a5
--- /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 <lvivier@redhat.com>
+ */
+
+#include <errno.h>
+
+#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;
+ warn("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..cf92b0f63f26
--- /dev/null
+++ b/epoll_ctl.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later
+ * Copyright Red Hat
+ * Author: Laurent Vivier <lvivier@redhat.com>
+ */
+
+#ifndef EPOLL_CTL_H
+#define EPOLL_CTL_H
+
+#include <sys/epoll.h>
+
+#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 <errno.h>
#include <net/ethernet.h>
#include <net/if.h>
-#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
#include <stdio.h>
@@ -23,10 +22,8 @@
#include <stdint.h>
#include <stddef.h>
#include <string.h>
-#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/socket.h>
-#include <unistd.h>
#include <time.h>
#include <linux/icmpv6.h>
@@ -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 31fbb75b1b12..e595f13a56f7 100644
--- a/passt.c
+++ b/passt.c
@@ -19,7 +19,6 @@
* created in a separate network namespace).
*/
-#include <sys/epoll.h>
#include <fcntl.h>
#include <sys/mman.h>
#include <sys/resource.h>
@@ -53,6 +52,7 @@
#include "vu_common.h"
#include "migrate.h"
#include "repair.h"
+#include "epoll_ctl.h"
#define 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..e905f6d33b95 100644
--- a/pasta.c
+++ b/pasta.c
@@ -27,7 +27,6 @@
#include <stdint.h>
#include <unistd.h>
#include <syslog.h>
-#include <sys/epoll.h>
#include <sys/inotify.h>
#include <sys/mount.h>
#include <sys/timerfd.h>
@@ -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..c8f4737fa62a 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;
@@ -58,9 +58,7 @@ 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))
+ if (epoll_add(c->epollfd, EPOLLIN | EPOLLHUP | EPOLLET, &ref))
err_perror("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;
@@ -112,10 +109,9 @@ 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;
+
+ rc = epoll_add(c->epollfd, EPOLLHUP | EPOLLET, &ref);
+ if (rc < 0) {
debug_perror("epoll_ctl() on TCP_REPAIR helper socket");
close(c->fd_repair);
c->fd_repair = -1;
diff --git a/tap.c b/tap.c
index 134c37a72979..873874796f79 100644
--- a/tap.c
+++ b/tap.c
@@ -26,7 +26,6 @@
#include <netinet/in.h>
#include <arpa/inet.h>
#include <stdint.h>
-#include <sys/epoll.h>
#include <sys/ioctl.h>
#include <sys/types.h>
#include <sys/stat.h>
@@ -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 04725deabb65..25223e0a0b6e 100644
--- a/tcp.c
+++ b/tcp.c
@@ -279,7 +279,6 @@
#include <stdbool.h>
#include <stddef.h>
#include <string.h>
-#include <sys/epoll.h>
#include <sys/ioctl.h>
#include <sys/socket.h>
#include <sys/timerfd.h>
@@ -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 <net/ethernet.h>
#include <netinet/in.h>
#include <netinet/tcp.h>
-#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/socket.h>
@@ -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 <stdint.h>
#include <stddef.h>
#include <string.h>
-#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/uio.h>
@@ -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 88a91b1100f5..b2490123590a 100644
--- a/util.c
+++ b/util.c
@@ -18,7 +18,6 @@
#include <unistd.h>
#include <arpa/inet.h>
#include <net/ethernet.h>
-#include <sys/epoll.h>
#include <sys/uio.h>
#include <fcntl.h>
#include <string.h>
@@ -35,6 +34,7 @@
#include "packet.h"
#include "log.h"
#include "pcap.h"
+#include "epoll_ctl.h"
#ifdef HAS_GETRANDOM
#include <sys/random.h>
#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 add to
- * @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 <net/if.h>
#include <limits.h>
#include <stdint.h>
@@ -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 1221ac1abcd0..42ceb456615f 100644
--- a/vhost_user.c
+++ b/vhost_user.c
@@ -32,8 +32,6 @@
#include <inttypes.h>
#include <time.h>
#include <net/ethernet.h>
-#include <netinet/in.h>
-#include <sys/epoll.h>
#include <sys/eventfd.h>
#include <sys/mman.h>
#include <linux/vhost_types.h>
@@ -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 <errno.h>
-#include <unistd.h>
#include <sys/uio.h>
#include <sys/eventfd.h>
#include <netinet/if_ether.h>
@@ -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
--
2.50.1
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH v2 3/6] util: Move epoll registration out of sock_l4_sa()
2025-10-07 16:40 [PATCH v2 0/6] Refactor epoll handling in preparation for multithreading Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 1/6] util: Simplify epoll_del() interface to take epollfd directly Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 2/6] epoll_ctl: Extract epoll operations Laurent Vivier
@ 2025-10-07 16:40 ` Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 4/6] tcp, flow: Replace per-connection in_epoll flag with epollfd in flow_common Laurent Vivier
` (2 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: Laurent Vivier @ 2025-10-07 16:40 UTC (permalink / raw)
To: passt-dev; +Cc: Laurent Vivier
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 <lvivier@redhat.com>
---
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..56dfac6c958e 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..17b41705183c 100644
--- a/pif.c
+++ b/pif.c
@@ -5,6 +5,7 @@
* Passt/pasta interface types and IDs
*/
+#include <errno.h>
#include <stdint.h>
#include <assert.h>
#include <netinet/in.h>
@@ -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..caaf3dababb1 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 b2490123590a..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);
--
2.50.1
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH v2 4/6] tcp, flow: Replace per-connection in_epoll flag with epollfd in flow_common
2025-10-07 16:40 [PATCH v2 0/6] Refactor epoll handling in preparation for multithreading Laurent Vivier
` (2 preceding siblings ...)
2025-10-07 16:40 ` [PATCH v2 3/6] util: Move epoll registration out of sock_l4_sa() Laurent Vivier
@ 2025-10-07 16:40 ` Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 5/6] icmp: Use epollfd from flow_common structure Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 6/6] udp: " Laurent Vivier
5 siblings, 0 replies; 7+ messages in thread
From: Laurent Vivier @ 2025-10-07 16:40 UTC (permalink / raw)
To: passt-dev; +Cc: Laurent Vivier
The in_epoll boolean flag in tcp_tap_conn and tcp_splice_conn only tracked
whether a connection was registered with epoll, not which epoll instance.
This limited flexibility for future multi-epoll support.
Replace the boolean with an epollfd field in flow_common that stores the
actual epoll fd. Use EPOLLFD_INVALID to indicate when a flow is not
registered with any epoll instance.
Add flow_epollfd_valid() to check if a flow is registered with epoll, and
flow_set_epollfd() to register a flow with an epoll instance.
This change also simplifies tcp_timer_ctl() and conn_flag_do() by removing
the need to pass the context 'c', since the epoll fd is now directly
accessible from the connection structure.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
flow.c | 26 +++++++++++++++++++++++++-
flow.h | 8 ++++++++
tcp.c | 36 ++++++++++++++++++------------------
tcp_conn.h | 8 +-------
tcp_splice.c | 23 +++++++++++------------
5 files changed, 63 insertions(+), 38 deletions(-)
diff --git a/flow.c b/flow.c
index b14e9d8b63ff..ed9f4417cfef 100644
--- a/flow.c
+++ b/flow.c
@@ -347,6 +347,29 @@ static void flow_set_state(struct flow_common *f, enum flow_state state)
flow_log_details_(f, LOG_DEBUG, MAX(state, oldstate));
}
+/**
+ * flow_epollfd_valid() - Check if flow is registered with an epoll instance
+ * @f: Flow to check
+ *
+ * Return: true if flow is registered with epoll, false otherwise
+ */
+bool flow_epollfd_valid(const struct flow_common *f)
+{
+ return f->epollfd != EPOLLFD_INVALID;
+}
+
+/**
+ * flow_set_epollfd() - Set the epoll instance for a flow
+ * @f: Flow to update
+ * @epollfd: epoll file descriptor to register with
+ */
+void flow_set_epollfd(struct flow_common *f, int epollfd)
+{
+ ASSERT((unsigned)epollfd < EPOLLFD_MAX);
+
+ f->epollfd = epollfd;
+}
+
/**
* flow_initiate_() - Move flow to INI, setting pif[INISIDE]
* @flow: Flow to change state
@@ -548,6 +571,7 @@ union flow *flow_alloc(void)
flow_new_entry = flow;
memset(flow, 0, sizeof(*flow));
+ flow->f.epollfd = EPOLLFD_INVALID;
flow_set_state(&flow->f, FLOW_STATE_NEW);
return flow;
@@ -827,7 +851,7 @@ void flow_defer_handler(const struct ctx *c, const struct timespec *now)
case FLOW_TCP_SPLICE:
closed = tcp_splice_flow_defer(&flow->tcp_splice);
if (!closed && timer)
- tcp_splice_timer(c, &flow->tcp_splice);
+ tcp_splice_timer(&flow->tcp_splice);
break;
case FLOW_PING4:
case FLOW_PING6:
diff --git a/flow.h b/flow.h
index ef138b83add8..41d1daba8918 100644
--- a/flow.h
+++ b/flow.h
@@ -177,6 +177,7 @@ int flowside_connect(const struct ctx *c, int s,
* @type: Type of packet flow
* @pif[]: Interface for each side of the flow
* @side[]: Information for each side of the flow
+ * @epollfd: epoll instance flow is registered with (EPOLLFD_INVALID if not)
*/
struct flow_common {
#ifdef __GNUC__
@@ -192,8 +193,13 @@ struct flow_common {
#endif
uint8_t pif[SIDES];
struct flowside side[SIDES];
+#define FLOW_EPOLLFD_BITS 8
+ unsigned int epollfd:FLOW_EPOLLFD_BITS;
};
+#define EPOLLFD_MAX ((1 << FLOW_EPOLLFD_BITS) - 1)
+#define EPOLLFD_INVALID EPOLLFD_MAX
+
#define FLOW_INDEX_BITS 17 /* 128k - 1 */
#define FLOW_MAX MAX_FROM_BITS(FLOW_INDEX_BITS)
@@ -249,6 +255,8 @@ flow_sidx_t flow_lookup_sa(const struct ctx *c, uint8_t proto, uint8_t pif,
union flow;
void flow_init(void);
+bool flow_epollfd_valid(const struct flow_common *f);
+void flow_set_epollfd(struct flow_common *f, int epollfd);
void flow_defer_handler(const struct ctx *c, const struct timespec *now);
int flow_migrate_source_early(struct ctx *c, const struct migrate_stage *stage,
int fd);
diff --git a/tcp.c b/tcp.c
index 25223e0a0b6e..e0694eb8830a 100644
--- a/tcp.c
+++ b/tcp.c
@@ -504,25 +504,26 @@ static uint32_t tcp_conn_epoll_events(uint8_t events, uint8_t conn_flags)
*/
static int tcp_epoll_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
{
- int m = conn->in_epoll ? EPOLL_CTL_MOD : EPOLL_CTL_ADD;
+ int m = flow_epollfd_valid(&conn->f) ? EPOLL_CTL_MOD : EPOLL_CTL_ADD;
union epoll_ref ref = { .type = EPOLL_TYPE_TCP, .fd = conn->sock,
.flowside = FLOW_SIDX(conn, !TAPSIDE(conn)), };
struct epoll_event ev = { .data.u64 = ref.u64 };
+ int epollfd = flow_epollfd_valid(&conn->f) ? conn->f.epollfd : c->epollfd;
if (conn->events == CLOSED) {
- if (conn->in_epoll)
- epoll_del(c->epollfd, conn->sock);
+ if (flow_epollfd_valid(&conn->f))
+ epoll_del(epollfd, conn->sock);
if (conn->timer != -1)
- epoll_del(c->epollfd, conn->timer);
+ epoll_del(epollfd, conn->timer);
return 0;
}
ev.events = tcp_conn_epoll_events(conn->events, conn->flags);
- if (epoll_ctl(c->epollfd, m, conn->sock, &ev))
+ if (epoll_ctl(epollfd, m, conn->sock, &ev))
return -errno;
- conn->in_epoll = true;
+ flow_set_epollfd(&conn->f, epollfd);
if (conn->timer != -1) {
union epoll_ref ref_t = { .type = EPOLL_TYPE_TCP_TIMER,
@@ -531,7 +532,7 @@ static int tcp_epoll_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
struct epoll_event ev_t = { .data.u64 = ref_t.u64,
.events = EPOLLIN | EPOLLET };
- if (epoll_ctl(c->epollfd, EPOLL_CTL_MOD, conn->timer, &ev_t))
+ if (epoll_ctl(conn->f.epollfd, EPOLL_CTL_MOD, conn->timer, &ev_t))
return -errno;
}
@@ -540,12 +541,11 @@ static int tcp_epoll_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
/**
* tcp_timer_ctl() - Set timerfd based on flags/events, create timerfd if needed
- * @c: Execution context
* @conn: Connection pointer
*
* #syscalls timerfd_create timerfd_settime
*/
-static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
+static void tcp_timer_ctl(struct tcp_tap_conn *conn)
{
struct itimerspec it = { { 0 }, { 0 } };
@@ -570,7 +570,7 @@ static void tcp_timer_ctl(const struct ctx *c, struct tcp_tap_conn *conn)
}
conn->timer = fd;
- if (epoll_ctl(c->epollfd, EPOLL_CTL_ADD, conn->timer, &ev)) {
+ if (epoll_ctl(conn->f.epollfd, EPOLL_CTL_ADD, conn->timer, &ev)) {
flow_dbg_perror(conn, "failed to add timer");
close(conn->timer);
conn->timer = -1;
@@ -628,7 +628,7 @@ void conn_flag_do(const struct ctx *c, struct tcp_tap_conn *conn,
* flags and factor this into the logic below.
*/
if (flag == ACK_FROM_TAP_DUE)
- tcp_timer_ctl(c, conn);
+ tcp_timer_ctl(conn);
return;
}
@@ -644,7 +644,7 @@ void conn_flag_do(const struct ctx *c, struct tcp_tap_conn *conn,
if (flag == ACK_FROM_TAP_DUE || flag == ACK_TO_TAP_DUE ||
(flag == ~ACK_FROM_TAP_DUE && (conn->flags & ACK_TO_TAP_DUE)) ||
(flag == ~ACK_TO_TAP_DUE && (conn->flags & ACK_FROM_TAP_DUE)))
- tcp_timer_ctl(c, conn);
+ tcp_timer_ctl(conn);
}
/**
@@ -699,7 +699,7 @@ void conn_event_do(const struct ctx *c, struct tcp_tap_conn *conn,
tcp_epoll_ctl(c, conn);
if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_ACKED))
- tcp_timer_ctl(c, conn);
+ tcp_timer_ctl(conn);
}
/**
@@ -1732,7 +1732,7 @@ static int tcp_data_from_tap(const struct ctx *c, struct tcp_tap_conn *conn,
seq, conn->seq_from_tap);
tcp_send_flag(c, conn, ACK);
- tcp_timer_ctl(c, conn);
+ tcp_timer_ctl(conn);
if (p->count == 1) {
tcp_tap_window_update(c, conn,
@@ -2375,7 +2375,7 @@ void tcp_timer_handler(const struct ctx *c, union epoll_ref ref)
if (conn->flags & ACK_TO_TAP_DUE) {
tcp_send_flag(c, conn, ACK_IF_NEEDED);
- tcp_timer_ctl(c, conn);
+ tcp_timer_ctl(conn);
} else if (conn->flags & ACK_FROM_TAP_DUE) {
if (!(conn->events & ESTABLISHED)) {
flow_dbg(conn, "handshake timeout");
@@ -2397,7 +2397,7 @@ void tcp_timer_handler(const struct ctx *c, union epoll_ref ref)
return;
tcp_data_from_sock(c, conn);
- tcp_timer_ctl(c, conn);
+ tcp_timer_ctl(conn);
}
} else {
struct itimerspec new = { { 0 }, { ACT_TIMEOUT, 0 } };
@@ -3445,7 +3445,7 @@ int tcp_flow_migrate_source_ext(const struct ctx *c,
if (c->migrate_no_linger)
close(s);
else
- epoll_del(c->epollfd, s);
+ epoll_del(conn->f.epollfd, s);
/* Adjustments unrelated to FIN segments: sequence numbers we dumped are
* based on the end of the queues.
@@ -3594,7 +3594,7 @@ static int tcp_flow_repair_connect(const struct ctx *c,
return rc;
}
- conn->in_epoll = 0;
+ conn->f.epollfd = EPOLLFD_INVALID;
conn->timer = -1;
conn->listening_sock = -1;
diff --git a/tcp_conn.h b/tcp_conn.h
index 38b5c541f003..81333122d531 100644
--- a/tcp_conn.h
+++ b/tcp_conn.h
@@ -12,7 +12,6 @@
/**
* struct tcp_tap_conn - Descriptor for a TCP connection (not spliced)
* @f: Generic flow information
- * @in_epoll: Is the connection in the epoll set?
* @retrans: Number of retransmissions occurred due to ACK_TIMEOUT
* @ws_from_tap: Window scaling factor advertised from tap/guest
* @ws_to_tap: Window scaling factor advertised to tap/guest
@@ -36,8 +35,6 @@ struct tcp_tap_conn {
/* Must be first element */
struct flow_common f;
- bool in_epoll :1;
-
#define TCP_RETRANS_BITS 3
unsigned int retrans :TCP_RETRANS_BITS;
#define TCP_MAX_RETRANS MAX_FROM_BITS(TCP_RETRANS_BITS)
@@ -196,7 +193,6 @@ struct tcp_tap_transfer_ext {
* @written: Bytes written (not fully written from one other side read)
* @events: Events observed/actions performed on connection
* @flags: Connection flags (attributes, not events)
- * @in_epoll: Is the connection in the epoll set?
*/
struct tcp_splice_conn {
/* Must be first element */
@@ -220,8 +216,6 @@ struct tcp_splice_conn {
#define RCVLOWAT_SET(sidei_) ((sidei_) ? BIT(1) : BIT(0))
#define RCVLOWAT_ACT(sidei_) ((sidei_) ? BIT(3) : BIT(2))
#define CLOSING BIT(4)
-
- bool in_epoll :1;
};
/* Socket pools */
@@ -245,7 +239,7 @@ int tcp_flow_migrate_target_ext(struct ctx *c, struct tcp_tap_conn *conn, int fd
bool tcp_flow_is_established(const struct tcp_tap_conn *conn);
bool tcp_splice_flow_defer(struct tcp_splice_conn *conn);
-void tcp_splice_timer(const struct ctx *c, struct tcp_splice_conn *conn);
+void tcp_splice_timer(struct tcp_splice_conn *conn);
int tcp_conn_pool_sock(int pool[]);
int tcp_conn_sock(sa_family_t af);
int tcp_sock_refill_pool(int pool[], sa_family_t af);
diff --git a/tcp_splice.c b/tcp_splice.c
index 6f21184bdc55..6c7c54815ba7 100644
--- a/tcp_splice.c
+++ b/tcp_splice.c
@@ -149,7 +149,7 @@ static void tcp_splice_conn_epoll_events(uint16_t events,
static int tcp_splice_epoll_ctl(const struct ctx *c,
struct tcp_splice_conn *conn)
{
- int m = conn->in_epoll ? EPOLL_CTL_MOD : EPOLL_CTL_ADD;
+ int m = flow_epollfd_valid(&conn->f) ? EPOLL_CTL_MOD : EPOLL_CTL_ADD;
const union epoll_ref ref[SIDES] = {
{ .type = EPOLL_TYPE_TCP_SPLICE, .fd = conn->s[0],
.flowside = FLOW_SIDX(conn, 0) },
@@ -158,28 +158,28 @@ static int tcp_splice_epoll_ctl(const struct ctx *c,
};
struct epoll_event ev[SIDES] = { { .data.u64 = ref[0].u64 },
{ .data.u64 = ref[1].u64 } };
+ int epollfd = flow_epollfd_valid(&conn->f) ? conn->f.epollfd : c->epollfd;
tcp_splice_conn_epoll_events(conn->events, ev);
- if (epoll_ctl(c->epollfd, m, conn->s[0], &ev[0]) ||
- epoll_ctl(c->epollfd, m, conn->s[1], &ev[1])) {
+
+ if (epoll_ctl(epollfd, m, conn->s[0], &ev[0]) ||
+ epoll_ctl(epollfd, m, conn->s[1], &ev[1])) {
int ret = -errno;
flow_perror(conn, "ERROR on epoll_ctl()");
return ret;
}
-
- conn->in_epoll = true;
+ flow_set_epollfd(&conn->f, epollfd);
return 0;
}
/**
* conn_flag_do() - Set/unset given flag, log, update epoll on CLOSING flag
- * @c: Execution context
* @conn: Connection pointer
* @flag: Flag to set, or ~flag to unset
*/
-static void conn_flag_do(const struct ctx *c, struct tcp_splice_conn *conn,
+static void conn_flag_do(struct tcp_splice_conn *conn,
unsigned long flag)
{
if (flag & (flag - 1)) {
@@ -204,15 +204,15 @@ static void conn_flag_do(const struct ctx *c, struct tcp_splice_conn *conn,
}
if (flag == CLOSING) {
- epoll_del(c->epollfd, conn->s[0]);
- epoll_del(c->epollfd, conn->s[1]);
+ epoll_del(conn->f.epollfd, conn->s[0]);
+ epoll_del(conn->f.epollfd, conn->s[1]);
}
}
#define conn_flag(c, conn, flag) \
do { \
flow_trace(conn, "flag at %s:%i", __func__, __LINE__); \
- conn_flag_do(c, conn, flag); \
+ conn_flag_do(conn, flag); \
} while (0)
/**
@@ -751,10 +751,9 @@ void tcp_splice_init(struct ctx *c)
/**
* tcp_splice_timer() - Timer for spliced connections
- * @c: Execution context
* @conn: Connection to handle
*/
-void tcp_splice_timer(const struct ctx *c, struct tcp_splice_conn *conn)
+void tcp_splice_timer(struct tcp_splice_conn *conn)
{
unsigned sidei;
--
2.50.1
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH v2 5/6] icmp: Use epollfd from flow_common structure
2025-10-07 16:40 [PATCH v2 0/6] Refactor epoll handling in preparation for multithreading Laurent Vivier
` (3 preceding siblings ...)
2025-10-07 16:40 ` [PATCH v2 4/6] tcp, flow: Replace per-connection in_epoll flag with epollfd in flow_common Laurent Vivier
@ 2025-10-07 16:40 ` Laurent Vivier
2025-10-07 16:40 ` [PATCH v2 6/6] udp: " Laurent Vivier
5 siblings, 0 replies; 7+ messages in thread
From: Laurent Vivier @ 2025-10-07 16:40 UTC (permalink / raw)
To: passt-dev; +Cc: Laurent Vivier
Store epollfd in the flow_common structure for ICMP ping flows and use
it for epoll operations 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 <lvivier@redhat.com>
---
icmp.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/icmp.c b/icmp.c
index 56dfac6c958e..6d099efde95b 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(pingf->f.epollfd, 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_set_epollfd(&pingf->f, c->epollfd);
+
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(pingf->f.epollfd, EPOLLIN, &ref) < 0) {
close(pingf->sock);
goto cancel;
}
--
2.50.1
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH v2 6/6] udp: Use epollfd from flow_common structure
2025-10-07 16:40 [PATCH v2 0/6] Refactor epoll handling in preparation for multithreading Laurent Vivier
` (4 preceding siblings ...)
2025-10-07 16:40 ` [PATCH v2 5/6] icmp: Use epollfd from flow_common structure Laurent Vivier
@ 2025-10-07 16:40 ` Laurent Vivier
5 siblings, 0 replies; 7+ messages in thread
From: Laurent Vivier @ 2025-10-07 16:40 UTC (permalink / raw)
To: passt-dev; +Cc: Laurent Vivier
Update UDP flow handling to use the epollfd field from the flow_common
structure instead of accessing it from the context. This aligns UDP with
the recent changes to TCP and ICMP flow management.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
udp_flow.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/udp_flow.c b/udp_flow.c
index caaf3dababb1..2814373e4173 100644
--- a/udp_flow.c
+++ b/udp_flow.c
@@ -52,7 +52,7 @@ 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->epollfd, uflow->s[sidei]);
+ epoll_del(uflow->f.epollfd, uflow->s[sidei]);
close(uflow->s[sidei]);
uflow->s[sidei] = -1;
}
@@ -92,7 +92,9 @@ static int udp_flow_sock(const struct ctx *c,
ref.data = fref.data;
ref.fd = s;
- rc = epoll_add(c->epollfd, EPOLLIN, &ref);
+ flow_set_epollfd(&uflow->f, c->epollfd);
+
+ rc = epoll_add(uflow->f.epollfd, EPOLLIN, &ref);
if (rc < 0) {
close(s);
return rc;
@@ -101,7 +103,7 @@ static int udp_flow_sock(const struct ctx *c,
if (flowside_connect(c, s, pif, side) < 0) {
rc = -errno;
- epoll_del(c->epollfd, s);
+ epoll_del(uflow->f.epollfd, s);
close(s);
flow_dbg_perror(uflow, "Couldn't connect flow socket");
--
2.50.1
^ permalink raw reply [flat|nested] 7+ messages in thread