From: Stefano Brivio <sbrivio@redhat.com>
To: passt-dev@passt.top
Subject: [PATCH 08/24] udp: Split buffer queueing/writing parts of udp_sock_handler()
Date: Fri, 25 Mar 2022 23:52:44 +0100 [thread overview]
Message-ID: <20220325225300.2803584-9-sbrivio@redhat.com> (raw)
In-Reply-To: <20220325225300.2803584-1-sbrivio@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 14624 bytes --]
...it became too hard to follow: split it off to
udp_sock_fill_data_v{4,6}.
While at it, use IN6_ARE_ADDR_EQUAL(a, b), courtesy of netinet/in.h,
instead of open-coded memcmp().
Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com>
---
udp.c | 364 +++++++++++++++++++++++++++++++---------------------------
1 file changed, 193 insertions(+), 171 deletions(-)
diff --git a/udp.c b/udp.c
index ce536a6..ebbcda1 100644
--- a/udp.c
+++ b/udp.c
@@ -655,6 +655,177 @@ static void udp_sock_handler_splice(struct ctx *c, union epoll_ref ref,
sendmmsg(s, udp_mmh_sendto, n, MSG_NOSIGNAL);
}
+/**
+ * udp_sock_fill_data_v4() - Fill and queue one buffer. In pasta mode, write it
+ * @c: Execution context
+ * @n: Index of buffer in udp4_l2_buf pool
+ * @ref: epoll reference from socket
+ * @msg_idx: Index within message being prepared (spans multiple buffers)
+ * @msg_len: Length of current message being prepared for sending
+ * @now: Current timestamp
+ */
+static void udp_sock_fill_data_v4(struct ctx *c, int n, union epoll_ref ref,
+ int *msg_idx, int *msg_bufs, ssize_t *msg_len,
+ struct timespec *now)
+{
+ struct msghdr *mh = &udp6_l2_mh_tap[*msg_idx].msg_hdr;
+ struct udp4_l2_buf_t *b = &udp4_l2_buf[n];
+ size_t ip_len, buf_len;
+ in_port_t src_port;
+ in_addr_t src;
+
+ ip_len = udp4_l2_mh_sock[n].msg_len + sizeof(b->iph) + sizeof(b->uh);
+
+ b->iph.tot_len = htons(ip_len);
+
+ src = ntohl(b->s_in.sin_addr.s_addr);
+ src_port = htons(b->s_in.sin_port);
+
+ if (src >> IN_CLASSA_NSHIFT == IN_LOOPBACKNET ||
+ src == INADDR_ANY || src == ntohl(c->addr4_seen)) {
+ b->iph.saddr = c->gw4;
+ udp_tap_map[V4][src_port].ts_local = now->tv_sec;
+
+ if (b->s_in.sin_addr.s_addr == c->addr4_seen)
+ udp_tap_map[V4][src_port].loopback = 0;
+ else
+ udp_tap_map[V4][src_port].loopback = 1;
+
+ bitmap_set(udp_act[V4][UDP_ACT_TAP], src_port);
+ } else if (c->dns4_fwd &&
+ src == ntohl(c->dns4[0]) && ntohs(src_port) == 53) {
+ b->iph.saddr = c->dns4_fwd;
+ } else {
+ b->iph.saddr = b->s_in.sin_addr.s_addr;
+ }
+
+ udp_update_check4(b);
+ b->uh.source = b->s_in.sin_port;
+ b->uh.dest = htons(ref.r.p.udp.udp.port);
+ b->uh.len = htons(udp4_l2_mh_sock[n].msg_len + sizeof(b->uh));
+
+ if (c->mode == MODE_PASTA) {
+ if (write(c->fd_tap, &b->eh, sizeof(b->eh) + ip_len) < 0)
+ debug("tap write: %s", strerror(errno));
+ pcap((char *)&b->eh, sizeof(b->eh) + ip_len);
+
+ return;
+ }
+
+ b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
+ buf_len = sizeof(uint32_t) + sizeof(struct ethhdr) + ip_len;
+ udp4_l2_iov_tap[n].iov_len = buf_len;
+
+ /* With bigger messages, qemu closes the connection. */
+ if (*msg_bufs && *msg_len + buf_len > SHRT_MAX) {
+ mh->msg_iovlen = *msg_bufs;
+
+ (*msg_idx)++;
+ udp4_l2_mh_tap[*msg_idx].msg_hdr.msg_iov = &udp4_l2_iov_tap[n];
+ *msg_len = *msg_bufs = 0;
+ }
+
+ *msg_len += buf_len;
+ (*msg_bufs)++;
+}
+
+/**
+ * udp_sock_fill_data_v4() - Fill and queue one buffer. In pasta mode, write it
+ * @c: Execution context
+ * @n: Index of buffer in udp4_l2_buf pool
+ * @ref: epoll reference from socket
+ * @msg_idx: Index within message being prepared (spans multiple buffers)
+ * @msg_len: Length of current message being prepared for sending
+ * @now: Current timestamp
+ */
+static void udp_sock_fill_data_v6(struct ctx *c, int n, union epoll_ref ref,
+ int *msg_idx, int *msg_bufs, ssize_t *msg_len,
+ struct timespec *now)
+{
+ struct msghdr *mh = &udp6_l2_mh_tap[*msg_idx].msg_hdr;
+ struct udp6_l2_buf_t *b = &udp6_l2_buf[n];
+ size_t ip_len, buf_len;
+ struct in6_addr *src;
+ in_port_t src_port;
+
+ src = &b->s_in6.sin6_addr;
+ src_port = ntohs(b->s_in6.sin6_port);
+
+ ip_len = udp6_l2_mh_sock[n].msg_len + sizeof(b->ip6h) + sizeof(b->uh);
+
+ b->ip6h.payload_len = htons(udp6_l2_mh_sock[n].msg_len + sizeof(b->uh));
+
+ if (IN6_IS_ADDR_LINKLOCAL(src)) {
+ b->ip6h.daddr = c->addr6_ll_seen;
+ b->ip6h.saddr = b->s_in6.sin6_addr;
+ } else if (IN6_IS_ADDR_LOOPBACK(src) ||
+ IN6_ARE_ADDR_EQUAL(src, &c->addr6_seen) ||
+ IN6_ARE_ADDR_EQUAL(src, &c->addr6)) {
+ b->ip6h.daddr = c->addr6_ll_seen;
+
+ if (IN6_IS_ADDR_LINKLOCAL(&c->gw6))
+ b->ip6h.saddr = c->gw6;
+ else
+ b->ip6h.saddr = c->addr6_ll;
+
+ udp_tap_map[V6][src_port].ts_local = now->tv_sec;
+
+ if (IN6_IS_ADDR_LOOPBACK(src))
+ udp_tap_map[V6][src_port].loopback = 1;
+ else
+ udp_tap_map[V6][src_port].loopback = 0;
+
+ if (IN6_ARE_ADDR_EQUAL(src, &c->addr6))
+ udp_tap_map[V6][src_port].gua = 1;
+ else
+ udp_tap_map[V6][src_port].gua = 0;
+
+ bitmap_set(udp_act[V6][UDP_ACT_TAP], src_port);
+ } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->dns6_fwd) &&
+ IN6_ARE_ADDR_EQUAL(src, &c->dns6_fwd) && src_port == 53) {
+ b->ip6h.daddr = c->addr6_seen;
+ b->ip6h.saddr = c->dns6_fwd;
+ } else {
+ b->ip6h.daddr = c->addr6_seen;
+ b->ip6h.saddr = b->s_in6.sin6_addr;
+ }
+
+ b->uh.source = b->s_in6.sin6_port;
+ b->uh.dest = htons(ref.r.p.udp.udp.port);
+ b->uh.len = b->ip6h.payload_len;
+
+ b->ip6h.hop_limit = IPPROTO_UDP;
+ b->ip6h.version = b->ip6h.nexthdr = b->uh.check = 0;
+ b->uh.check = csum(&b->ip6h, ip_len, 0);
+ b->ip6h.version = 6;
+ b->ip6h.nexthdr = IPPROTO_UDP;
+ b->ip6h.hop_limit = 255;
+
+ if (c->mode == MODE_PASTA) {
+ if (write(c->fd_tap, &b->eh, sizeof(b->eh) + ip_len) < 0)
+ debug("tap write: %s", strerror(errno));
+ pcap((char *)&b->eh, sizeof(b->eh) + ip_len);
+
+ return;
+ }
+
+ b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
+ buf_len = sizeof(uint32_t) + sizeof(struct ethhdr) + ip_len;
+ udp6_l2_iov_tap[n].iov_len = buf_len;
+
+ /* With bigger messages, qemu closes the connection. */
+ if (*msg_bufs && *msg_len + buf_len > SHRT_MAX) {
+ mh->msg_iovlen = *msg_bufs;
+
+ (*msg_idx)++;
+ udp6_l2_mh_tap[*msg_idx].msg_hdr.msg_iov = &udp6_l2_iov_tap[n];
+ *msg_len = *msg_bufs = 0;
+ }
+
+ *msg_len += buf_len;
+ (*msg_bufs)++;
+}
+
/**
* udp_sock_handler() - Handle new data from socket
* @c: Execution context
@@ -668,10 +839,10 @@ static void udp_sock_handler_splice(struct ctx *c, union epoll_ref ref,
void udp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
struct timespec *now)
{
- int iov_in_msg, msg_i = 0, ret;
- ssize_t n, msglen, missing = 0;
+ ssize_t n, msg_len = 0, missing = 0;
+ int msg_bufs = 0, msg_i = 0, ret;
struct mmsghdr *tap_mmh;
- struct msghdr *cur_mh;
+ struct msghdr *last_mh;
unsigned int i;
if (events == EPOLLERR)
@@ -687,183 +858,34 @@ void udp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
if (n <= 0)
return;
- cur_mh = &udp6_l2_mh_tap[msg_i].msg_hdr;
- cur_mh->msg_iov = &udp6_l2_iov_tap[0];
- msg_i = msglen = iov_in_msg = 0;
+ udp6_l2_mh_tap[0].msg_hdr.msg_iov = &udp6_l2_iov_tap[0];
for (i = 0; i < (unsigned)n; i++) {
- struct udp6_l2_buf_t *b = &udp6_l2_buf[i];
- size_t ip_len, iov_len;
-
- ip_len = udp6_l2_mh_sock[i].msg_len +
- sizeof(b->ip6h) + sizeof(b->uh);
-
- b->ip6h.payload_len = htons(udp6_l2_mh_sock[i].msg_len +
- sizeof(b->uh));
-
- if (IN6_IS_ADDR_LINKLOCAL(&b->s_in6.sin6_addr)) {
- b->ip6h.daddr = c->addr6_ll_seen;
- b->ip6h.saddr = b->s_in6.sin6_addr;
- } else if (IN6_IS_ADDR_LOOPBACK(&b->s_in6.sin6_addr) ||
- !memcmp(&b->s_in6.sin6_addr, &c->addr6_seen,
- sizeof(c->addr6)) ||
- !memcmp(&b->s_in6.sin6_addr, &c->addr6,
- sizeof(c->addr6))) {
- in_port_t src = htons(b->s_in6.sin6_port);
-
- b->ip6h.daddr = c->addr6_ll_seen;
-
- if (IN6_IS_ADDR_LINKLOCAL(&c->gw6))
- b->ip6h.saddr = c->gw6;
- else
- b->ip6h.saddr = c->addr6_ll;
-
- udp_tap_map[V6][src].ts_local = now->tv_sec;
-
- if (IN6_IS_ADDR_LOOPBACK(&b->s_in6.sin6_addr))
- udp_tap_map[V6][src].loopback = 1;
- else
- udp_tap_map[V6][src].loopback = 0;
-
- if (!memcmp(&b->s_in6.sin6_addr, &c->addr6,
- sizeof(c->addr6)))
- udp_tap_map[V6][src].gua = 1;
- else
- udp_tap_map[V6][src].gua = 0;
-
- bitmap_set(udp_act[V6][UDP_ACT_TAP], src);
- } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->dns6_fwd) &&
- !memcmp(&b->s_in6.sin6_addr, &c->dns6_fwd,
- sizeof(c->dns6_fwd)) &&
- ntohs(b->s_in6.sin6_port) == 53) {
- b->ip6h.daddr = c->addr6_seen;
- b->ip6h.saddr = c->dns6_fwd;
- } else {
- b->ip6h.daddr = c->addr6_seen;
- b->ip6h.saddr = b->s_in6.sin6_addr;
- }
-
- b->uh.source = b->s_in6.sin6_port;
- b->uh.dest = htons(ref.r.p.udp.udp.port);
- b->uh.len = b->ip6h.payload_len;
-
- b->ip6h.hop_limit = IPPROTO_UDP;
- b->ip6h.version = 0;
- b->ip6h.nexthdr = 0;
- b->uh.check = 0;
- b->uh.check = csum(&b->ip6h, ip_len, 0);
- b->ip6h.version = 6;
- b->ip6h.nexthdr = IPPROTO_UDP;
- b->ip6h.hop_limit = 255;
-
- if (c->mode == MODE_PASTA) {
- ip_len += sizeof(struct ethhdr);
- if (write(c->fd_tap, &b->eh, ip_len) < 0)
- debug("tap write: %s", strerror(errno));
- pcap((char *)&b->eh, ip_len);
- continue;
- }
-
- b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
- iov_len = sizeof(uint32_t) + sizeof(struct ethhdr) +
- ip_len;
- udp6_l2_iov_tap[i].iov_len = iov_len;
-
- /* With bigger messages, qemu closes the connection. */
- if (iov_in_msg && msglen + iov_len > SHRT_MAX) {
- cur_mh->msg_iovlen = iov_in_msg;
-
- cur_mh = &udp6_l2_mh_tap[++msg_i].msg_hdr;
- msglen = iov_in_msg = 0;
- cur_mh->msg_iov = &udp6_l2_iov_tap[i];
- }
-
- msglen += iov_len;
- iov_in_msg++;
+ udp_sock_fill_data_v6(c, i, ref,
+ &msg_i, &msg_bufs, &msg_len, now);
}
+ udp6_l2_mh_tap[msg_i].msg_hdr.msg_iovlen = msg_bufs;
tap_mmh = udp6_l2_mh_tap;
} else {
n = recvmmsg(ref.r.s, udp4_l2_mh_sock, UDP_TAP_FRAMES, 0, NULL);
if (n <= 0)
return;
- cur_mh = &udp4_l2_mh_tap[msg_i].msg_hdr;
- cur_mh->msg_iov = &udp4_l2_iov_tap[0];
- msg_i = msglen = iov_in_msg = 0;
+ udp6_l2_mh_tap[0].msg_hdr.msg_iov = &udp6_l2_iov_tap[0];
for (i = 0; i < (unsigned)n; i++) {
- struct udp4_l2_buf_t *b = &udp4_l2_buf[i];
- size_t ip_len, iov_len;
- in_addr_t s_addr;
-
- ip_len = udp4_l2_mh_sock[i].msg_len +
- sizeof(b->iph) + sizeof(b->uh);
-
- b->iph.tot_len = htons(ip_len);
-
- s_addr = ntohl(b->s_in.sin_addr.s_addr);
- if (s_addr >> IN_CLASSA_NSHIFT == IN_LOOPBACKNET ||
- s_addr == INADDR_ANY ||
- s_addr == ntohl(c->addr4_seen)) {
- in_port_t src = htons(b->s_in.sin_port);
-
- b->iph.saddr = c->gw4;
- udp_tap_map[V4][src].ts_local = now->tv_sec;
-
- if (b->s_in.sin_addr.s_addr == c->addr4_seen)
- udp_tap_map[V4][src].loopback = 0;
- else
- udp_tap_map[V4][src].loopback = 1;
-
- bitmap_set(udp_act[V4][UDP_ACT_TAP], src);
- } else if (c->dns4_fwd &&
- s_addr == ntohl(c->dns4[0]) &&
- ntohs(b->s_in.sin_port) == 53) {
- b->iph.saddr = c->dns4_fwd;
- } else {
- b->iph.saddr = b->s_in.sin_addr.s_addr;
- }
-
- udp_update_check4(b);
- b->uh.source = b->s_in.sin_port;
- b->uh.dest = htons(ref.r.p.udp.udp.port);
- b->uh.len = ntohs(udp4_l2_mh_sock[i].msg_len +
- sizeof(b->uh));
-
- if (c->mode == MODE_PASTA) {
- ip_len += sizeof(struct ethhdr);
- if (write(c->fd_tap, &b->eh, ip_len) < 0)
- debug("tap write: %s", strerror(errno));
- pcap((char *)&b->eh, ip_len);
- continue;
- }
-
- b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
- iov_len = sizeof(uint32_t) + sizeof(struct ethhdr) +
- ip_len;
- udp4_l2_iov_tap[i].iov_len = iov_len;
-
- /* With bigger messages, qemu closes the connection. */
- if (iov_in_msg && msglen + iov_len > SHRT_MAX) {
- cur_mh->msg_iovlen = iov_in_msg;
-
- cur_mh = &udp4_l2_mh_tap[++msg_i].msg_hdr;
- msglen = iov_in_msg = 0;
- cur_mh->msg_iov = &udp4_l2_iov_tap[i];
- }
-
- msglen += iov_len;
- iov_in_msg++;
+ udp_sock_fill_data_v4(c, i, ref,
+ &msg_i, &msg_bufs, &msg_len, now);
}
+ udp4_l2_mh_tap[msg_i].msg_hdr.msg_iovlen = msg_bufs;
tap_mmh = udp4_l2_mh_tap;
}
if (c->mode == MODE_PASTA)
return;
- cur_mh->msg_iovlen = iov_in_msg;
ret = sendmmsg(c->fd_tap, tap_mmh, msg_i + 1,
MSG_NOSIGNAL | MSG_DONTWAIT);
if (ret <= 0)
@@ -887,25 +909,25 @@ void udp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
*
* re-send everything from here: ^-- ----- ------
*/
- cur_mh = &tap_mmh[ret - 1].msg_hdr;
- for (i = 0, msglen = 0; i < cur_mh->msg_iovlen; i++) {
+ last_mh = &tap_mmh[ret - 1].msg_hdr;
+ for (i = 0, msg_len = 0; i < last_mh->msg_iovlen; i++) {
if (missing <= 0) {
- msglen += cur_mh->msg_iov[i].iov_len;
- missing = msglen - tap_mmh[ret - 1].msg_len;
+ msg_len += last_mh->msg_iov[i].iov_len;
+ missing = msg_len - tap_mmh[ret - 1].msg_len;
}
if (missing > 0) {
uint8_t **iov_base;
int first_offset;
- iov_base = (uint8_t **)&cur_mh->msg_iov[i].iov_base;
- first_offset = cur_mh->msg_iov[i].iov_len - missing;
+ iov_base = (uint8_t **)&last_mh->msg_iov[i].iov_base;
+ first_offset = last_mh->msg_iov[i].iov_len - missing;
*iov_base += first_offset;
- cur_mh->msg_iov[i].iov_len = missing;
+ last_mh->msg_iov[i].iov_len = missing;
- cur_mh->msg_iov = &cur_mh->msg_iov[i];
+ last_mh->msg_iov = &last_mh->msg_iov[i];
- sendmsg(c->fd_tap, cur_mh, MSG_NOSIGNAL);
+ sendmsg(c->fd_tap, last_mh, MSG_NOSIGNAL);
*iov_base -= first_offset;
break;
@@ -997,7 +1019,7 @@ int udp_tap_handler(struct ctx *c, int af, void *addr,
sa = (struct sockaddr *)&s_in6;
sl = sizeof(s_in6);
- if (!memcmp(addr, &c->gw6, sizeof(c->gw6)) && !c->no_map_gw) {
+ if (IN6_ARE_ADDR_EQUAL(addr, &c->gw6) && !c->no_map_gw) {
if (!udp_tap_map[V6][dst].ts_local ||
udp_tap_map[V6][dst].loopback)
s_in6.sin6_addr = in6addr_loopback;
@@ -1005,7 +1027,7 @@ int udp_tap_handler(struct ctx *c, int af, void *addr,
s_in6.sin6_addr = c->addr6;
else
s_in6.sin6_addr = c->addr6_seen;
- } else if (!memcmp(addr, &c->dns6_fwd, sizeof(c->dns6_fwd)) &&
+ } else if (IN6_ARE_ADDR_EQUAL(addr, &c->dns6_fwd) &&
ntohs(s_in6.sin6_port) == 53) {
s_in6.sin6_addr = c->dns6[0];
} else if (IN6_IS_ADDR_LINKLOCAL(&s_in6.sin6_addr)) {
--
@@ -655,6 +655,177 @@ static void udp_sock_handler_splice(struct ctx *c, union epoll_ref ref,
sendmmsg(s, udp_mmh_sendto, n, MSG_NOSIGNAL);
}
+/**
+ * udp_sock_fill_data_v4() - Fill and queue one buffer. In pasta mode, write it
+ * @c: Execution context
+ * @n: Index of buffer in udp4_l2_buf pool
+ * @ref: epoll reference from socket
+ * @msg_idx: Index within message being prepared (spans multiple buffers)
+ * @msg_len: Length of current message being prepared for sending
+ * @now: Current timestamp
+ */
+static void udp_sock_fill_data_v4(struct ctx *c, int n, union epoll_ref ref,
+ int *msg_idx, int *msg_bufs, ssize_t *msg_len,
+ struct timespec *now)
+{
+ struct msghdr *mh = &udp6_l2_mh_tap[*msg_idx].msg_hdr;
+ struct udp4_l2_buf_t *b = &udp4_l2_buf[n];
+ size_t ip_len, buf_len;
+ in_port_t src_port;
+ in_addr_t src;
+
+ ip_len = udp4_l2_mh_sock[n].msg_len + sizeof(b->iph) + sizeof(b->uh);
+
+ b->iph.tot_len = htons(ip_len);
+
+ src = ntohl(b->s_in.sin_addr.s_addr);
+ src_port = htons(b->s_in.sin_port);
+
+ if (src >> IN_CLASSA_NSHIFT == IN_LOOPBACKNET ||
+ src == INADDR_ANY || src == ntohl(c->addr4_seen)) {
+ b->iph.saddr = c->gw4;
+ udp_tap_map[V4][src_port].ts_local = now->tv_sec;
+
+ if (b->s_in.sin_addr.s_addr == c->addr4_seen)
+ udp_tap_map[V4][src_port].loopback = 0;
+ else
+ udp_tap_map[V4][src_port].loopback = 1;
+
+ bitmap_set(udp_act[V4][UDP_ACT_TAP], src_port);
+ } else if (c->dns4_fwd &&
+ src == ntohl(c->dns4[0]) && ntohs(src_port) == 53) {
+ b->iph.saddr = c->dns4_fwd;
+ } else {
+ b->iph.saddr = b->s_in.sin_addr.s_addr;
+ }
+
+ udp_update_check4(b);
+ b->uh.source = b->s_in.sin_port;
+ b->uh.dest = htons(ref.r.p.udp.udp.port);
+ b->uh.len = htons(udp4_l2_mh_sock[n].msg_len + sizeof(b->uh));
+
+ if (c->mode == MODE_PASTA) {
+ if (write(c->fd_tap, &b->eh, sizeof(b->eh) + ip_len) < 0)
+ debug("tap write: %s", strerror(errno));
+ pcap((char *)&b->eh, sizeof(b->eh) + ip_len);
+
+ return;
+ }
+
+ b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
+ buf_len = sizeof(uint32_t) + sizeof(struct ethhdr) + ip_len;
+ udp4_l2_iov_tap[n].iov_len = buf_len;
+
+ /* With bigger messages, qemu closes the connection. */
+ if (*msg_bufs && *msg_len + buf_len > SHRT_MAX) {
+ mh->msg_iovlen = *msg_bufs;
+
+ (*msg_idx)++;
+ udp4_l2_mh_tap[*msg_idx].msg_hdr.msg_iov = &udp4_l2_iov_tap[n];
+ *msg_len = *msg_bufs = 0;
+ }
+
+ *msg_len += buf_len;
+ (*msg_bufs)++;
+}
+
+/**
+ * udp_sock_fill_data_v4() - Fill and queue one buffer. In pasta mode, write it
+ * @c: Execution context
+ * @n: Index of buffer in udp4_l2_buf pool
+ * @ref: epoll reference from socket
+ * @msg_idx: Index within message being prepared (spans multiple buffers)
+ * @msg_len: Length of current message being prepared for sending
+ * @now: Current timestamp
+ */
+static void udp_sock_fill_data_v6(struct ctx *c, int n, union epoll_ref ref,
+ int *msg_idx, int *msg_bufs, ssize_t *msg_len,
+ struct timespec *now)
+{
+ struct msghdr *mh = &udp6_l2_mh_tap[*msg_idx].msg_hdr;
+ struct udp6_l2_buf_t *b = &udp6_l2_buf[n];
+ size_t ip_len, buf_len;
+ struct in6_addr *src;
+ in_port_t src_port;
+
+ src = &b->s_in6.sin6_addr;
+ src_port = ntohs(b->s_in6.sin6_port);
+
+ ip_len = udp6_l2_mh_sock[n].msg_len + sizeof(b->ip6h) + sizeof(b->uh);
+
+ b->ip6h.payload_len = htons(udp6_l2_mh_sock[n].msg_len + sizeof(b->uh));
+
+ if (IN6_IS_ADDR_LINKLOCAL(src)) {
+ b->ip6h.daddr = c->addr6_ll_seen;
+ b->ip6h.saddr = b->s_in6.sin6_addr;
+ } else if (IN6_IS_ADDR_LOOPBACK(src) ||
+ IN6_ARE_ADDR_EQUAL(src, &c->addr6_seen) ||
+ IN6_ARE_ADDR_EQUAL(src, &c->addr6)) {
+ b->ip6h.daddr = c->addr6_ll_seen;
+
+ if (IN6_IS_ADDR_LINKLOCAL(&c->gw6))
+ b->ip6h.saddr = c->gw6;
+ else
+ b->ip6h.saddr = c->addr6_ll;
+
+ udp_tap_map[V6][src_port].ts_local = now->tv_sec;
+
+ if (IN6_IS_ADDR_LOOPBACK(src))
+ udp_tap_map[V6][src_port].loopback = 1;
+ else
+ udp_tap_map[V6][src_port].loopback = 0;
+
+ if (IN6_ARE_ADDR_EQUAL(src, &c->addr6))
+ udp_tap_map[V6][src_port].gua = 1;
+ else
+ udp_tap_map[V6][src_port].gua = 0;
+
+ bitmap_set(udp_act[V6][UDP_ACT_TAP], src_port);
+ } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->dns6_fwd) &&
+ IN6_ARE_ADDR_EQUAL(src, &c->dns6_fwd) && src_port == 53) {
+ b->ip6h.daddr = c->addr6_seen;
+ b->ip6h.saddr = c->dns6_fwd;
+ } else {
+ b->ip6h.daddr = c->addr6_seen;
+ b->ip6h.saddr = b->s_in6.sin6_addr;
+ }
+
+ b->uh.source = b->s_in6.sin6_port;
+ b->uh.dest = htons(ref.r.p.udp.udp.port);
+ b->uh.len = b->ip6h.payload_len;
+
+ b->ip6h.hop_limit = IPPROTO_UDP;
+ b->ip6h.version = b->ip6h.nexthdr = b->uh.check = 0;
+ b->uh.check = csum(&b->ip6h, ip_len, 0);
+ b->ip6h.version = 6;
+ b->ip6h.nexthdr = IPPROTO_UDP;
+ b->ip6h.hop_limit = 255;
+
+ if (c->mode == MODE_PASTA) {
+ if (write(c->fd_tap, &b->eh, sizeof(b->eh) + ip_len) < 0)
+ debug("tap write: %s", strerror(errno));
+ pcap((char *)&b->eh, sizeof(b->eh) + ip_len);
+
+ return;
+ }
+
+ b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
+ buf_len = sizeof(uint32_t) + sizeof(struct ethhdr) + ip_len;
+ udp6_l2_iov_tap[n].iov_len = buf_len;
+
+ /* With bigger messages, qemu closes the connection. */
+ if (*msg_bufs && *msg_len + buf_len > SHRT_MAX) {
+ mh->msg_iovlen = *msg_bufs;
+
+ (*msg_idx)++;
+ udp6_l2_mh_tap[*msg_idx].msg_hdr.msg_iov = &udp6_l2_iov_tap[n];
+ *msg_len = *msg_bufs = 0;
+ }
+
+ *msg_len += buf_len;
+ (*msg_bufs)++;
+}
+
/**
* udp_sock_handler() - Handle new data from socket
* @c: Execution context
@@ -668,10 +839,10 @@ static void udp_sock_handler_splice(struct ctx *c, union epoll_ref ref,
void udp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
struct timespec *now)
{
- int iov_in_msg, msg_i = 0, ret;
- ssize_t n, msglen, missing = 0;
+ ssize_t n, msg_len = 0, missing = 0;
+ int msg_bufs = 0, msg_i = 0, ret;
struct mmsghdr *tap_mmh;
- struct msghdr *cur_mh;
+ struct msghdr *last_mh;
unsigned int i;
if (events == EPOLLERR)
@@ -687,183 +858,34 @@ void udp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
if (n <= 0)
return;
- cur_mh = &udp6_l2_mh_tap[msg_i].msg_hdr;
- cur_mh->msg_iov = &udp6_l2_iov_tap[0];
- msg_i = msglen = iov_in_msg = 0;
+ udp6_l2_mh_tap[0].msg_hdr.msg_iov = &udp6_l2_iov_tap[0];
for (i = 0; i < (unsigned)n; i++) {
- struct udp6_l2_buf_t *b = &udp6_l2_buf[i];
- size_t ip_len, iov_len;
-
- ip_len = udp6_l2_mh_sock[i].msg_len +
- sizeof(b->ip6h) + sizeof(b->uh);
-
- b->ip6h.payload_len = htons(udp6_l2_mh_sock[i].msg_len +
- sizeof(b->uh));
-
- if (IN6_IS_ADDR_LINKLOCAL(&b->s_in6.sin6_addr)) {
- b->ip6h.daddr = c->addr6_ll_seen;
- b->ip6h.saddr = b->s_in6.sin6_addr;
- } else if (IN6_IS_ADDR_LOOPBACK(&b->s_in6.sin6_addr) ||
- !memcmp(&b->s_in6.sin6_addr, &c->addr6_seen,
- sizeof(c->addr6)) ||
- !memcmp(&b->s_in6.sin6_addr, &c->addr6,
- sizeof(c->addr6))) {
- in_port_t src = htons(b->s_in6.sin6_port);
-
- b->ip6h.daddr = c->addr6_ll_seen;
-
- if (IN6_IS_ADDR_LINKLOCAL(&c->gw6))
- b->ip6h.saddr = c->gw6;
- else
- b->ip6h.saddr = c->addr6_ll;
-
- udp_tap_map[V6][src].ts_local = now->tv_sec;
-
- if (IN6_IS_ADDR_LOOPBACK(&b->s_in6.sin6_addr))
- udp_tap_map[V6][src].loopback = 1;
- else
- udp_tap_map[V6][src].loopback = 0;
-
- if (!memcmp(&b->s_in6.sin6_addr, &c->addr6,
- sizeof(c->addr6)))
- udp_tap_map[V6][src].gua = 1;
- else
- udp_tap_map[V6][src].gua = 0;
-
- bitmap_set(udp_act[V6][UDP_ACT_TAP], src);
- } else if (!IN6_IS_ADDR_UNSPECIFIED(&c->dns6_fwd) &&
- !memcmp(&b->s_in6.sin6_addr, &c->dns6_fwd,
- sizeof(c->dns6_fwd)) &&
- ntohs(b->s_in6.sin6_port) == 53) {
- b->ip6h.daddr = c->addr6_seen;
- b->ip6h.saddr = c->dns6_fwd;
- } else {
- b->ip6h.daddr = c->addr6_seen;
- b->ip6h.saddr = b->s_in6.sin6_addr;
- }
-
- b->uh.source = b->s_in6.sin6_port;
- b->uh.dest = htons(ref.r.p.udp.udp.port);
- b->uh.len = b->ip6h.payload_len;
-
- b->ip6h.hop_limit = IPPROTO_UDP;
- b->ip6h.version = 0;
- b->ip6h.nexthdr = 0;
- b->uh.check = 0;
- b->uh.check = csum(&b->ip6h, ip_len, 0);
- b->ip6h.version = 6;
- b->ip6h.nexthdr = IPPROTO_UDP;
- b->ip6h.hop_limit = 255;
-
- if (c->mode == MODE_PASTA) {
- ip_len += sizeof(struct ethhdr);
- if (write(c->fd_tap, &b->eh, ip_len) < 0)
- debug("tap write: %s", strerror(errno));
- pcap((char *)&b->eh, ip_len);
- continue;
- }
-
- b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
- iov_len = sizeof(uint32_t) + sizeof(struct ethhdr) +
- ip_len;
- udp6_l2_iov_tap[i].iov_len = iov_len;
-
- /* With bigger messages, qemu closes the connection. */
- if (iov_in_msg && msglen + iov_len > SHRT_MAX) {
- cur_mh->msg_iovlen = iov_in_msg;
-
- cur_mh = &udp6_l2_mh_tap[++msg_i].msg_hdr;
- msglen = iov_in_msg = 0;
- cur_mh->msg_iov = &udp6_l2_iov_tap[i];
- }
-
- msglen += iov_len;
- iov_in_msg++;
+ udp_sock_fill_data_v6(c, i, ref,
+ &msg_i, &msg_bufs, &msg_len, now);
}
+ udp6_l2_mh_tap[msg_i].msg_hdr.msg_iovlen = msg_bufs;
tap_mmh = udp6_l2_mh_tap;
} else {
n = recvmmsg(ref.r.s, udp4_l2_mh_sock, UDP_TAP_FRAMES, 0, NULL);
if (n <= 0)
return;
- cur_mh = &udp4_l2_mh_tap[msg_i].msg_hdr;
- cur_mh->msg_iov = &udp4_l2_iov_tap[0];
- msg_i = msglen = iov_in_msg = 0;
+ udp6_l2_mh_tap[0].msg_hdr.msg_iov = &udp6_l2_iov_tap[0];
for (i = 0; i < (unsigned)n; i++) {
- struct udp4_l2_buf_t *b = &udp4_l2_buf[i];
- size_t ip_len, iov_len;
- in_addr_t s_addr;
-
- ip_len = udp4_l2_mh_sock[i].msg_len +
- sizeof(b->iph) + sizeof(b->uh);
-
- b->iph.tot_len = htons(ip_len);
-
- s_addr = ntohl(b->s_in.sin_addr.s_addr);
- if (s_addr >> IN_CLASSA_NSHIFT == IN_LOOPBACKNET ||
- s_addr == INADDR_ANY ||
- s_addr == ntohl(c->addr4_seen)) {
- in_port_t src = htons(b->s_in.sin_port);
-
- b->iph.saddr = c->gw4;
- udp_tap_map[V4][src].ts_local = now->tv_sec;
-
- if (b->s_in.sin_addr.s_addr == c->addr4_seen)
- udp_tap_map[V4][src].loopback = 0;
- else
- udp_tap_map[V4][src].loopback = 1;
-
- bitmap_set(udp_act[V4][UDP_ACT_TAP], src);
- } else if (c->dns4_fwd &&
- s_addr == ntohl(c->dns4[0]) &&
- ntohs(b->s_in.sin_port) == 53) {
- b->iph.saddr = c->dns4_fwd;
- } else {
- b->iph.saddr = b->s_in.sin_addr.s_addr;
- }
-
- udp_update_check4(b);
- b->uh.source = b->s_in.sin_port;
- b->uh.dest = htons(ref.r.p.udp.udp.port);
- b->uh.len = ntohs(udp4_l2_mh_sock[i].msg_len +
- sizeof(b->uh));
-
- if (c->mode == MODE_PASTA) {
- ip_len += sizeof(struct ethhdr);
- if (write(c->fd_tap, &b->eh, ip_len) < 0)
- debug("tap write: %s", strerror(errno));
- pcap((char *)&b->eh, ip_len);
- continue;
- }
-
- b->vnet_len = htonl(ip_len + sizeof(struct ethhdr));
- iov_len = sizeof(uint32_t) + sizeof(struct ethhdr) +
- ip_len;
- udp4_l2_iov_tap[i].iov_len = iov_len;
-
- /* With bigger messages, qemu closes the connection. */
- if (iov_in_msg && msglen + iov_len > SHRT_MAX) {
- cur_mh->msg_iovlen = iov_in_msg;
-
- cur_mh = &udp4_l2_mh_tap[++msg_i].msg_hdr;
- msglen = iov_in_msg = 0;
- cur_mh->msg_iov = &udp4_l2_iov_tap[i];
- }
-
- msglen += iov_len;
- iov_in_msg++;
+ udp_sock_fill_data_v4(c, i, ref,
+ &msg_i, &msg_bufs, &msg_len, now);
}
+ udp4_l2_mh_tap[msg_i].msg_hdr.msg_iovlen = msg_bufs;
tap_mmh = udp4_l2_mh_tap;
}
if (c->mode == MODE_PASTA)
return;
- cur_mh->msg_iovlen = iov_in_msg;
ret = sendmmsg(c->fd_tap, tap_mmh, msg_i + 1,
MSG_NOSIGNAL | MSG_DONTWAIT);
if (ret <= 0)
@@ -887,25 +909,25 @@ void udp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
*
* re-send everything from here: ^-- ----- ------
*/
- cur_mh = &tap_mmh[ret - 1].msg_hdr;
- for (i = 0, msglen = 0; i < cur_mh->msg_iovlen; i++) {
+ last_mh = &tap_mmh[ret - 1].msg_hdr;
+ for (i = 0, msg_len = 0; i < last_mh->msg_iovlen; i++) {
if (missing <= 0) {
- msglen += cur_mh->msg_iov[i].iov_len;
- missing = msglen - tap_mmh[ret - 1].msg_len;
+ msg_len += last_mh->msg_iov[i].iov_len;
+ missing = msg_len - tap_mmh[ret - 1].msg_len;
}
if (missing > 0) {
uint8_t **iov_base;
int first_offset;
- iov_base = (uint8_t **)&cur_mh->msg_iov[i].iov_base;
- first_offset = cur_mh->msg_iov[i].iov_len - missing;
+ iov_base = (uint8_t **)&last_mh->msg_iov[i].iov_base;
+ first_offset = last_mh->msg_iov[i].iov_len - missing;
*iov_base += first_offset;
- cur_mh->msg_iov[i].iov_len = missing;
+ last_mh->msg_iov[i].iov_len = missing;
- cur_mh->msg_iov = &cur_mh->msg_iov[i];
+ last_mh->msg_iov = &last_mh->msg_iov[i];
- sendmsg(c->fd_tap, cur_mh, MSG_NOSIGNAL);
+ sendmsg(c->fd_tap, last_mh, MSG_NOSIGNAL);
*iov_base -= first_offset;
break;
@@ -997,7 +1019,7 @@ int udp_tap_handler(struct ctx *c, int af, void *addr,
sa = (struct sockaddr *)&s_in6;
sl = sizeof(s_in6);
- if (!memcmp(addr, &c->gw6, sizeof(c->gw6)) && !c->no_map_gw) {
+ if (IN6_ARE_ADDR_EQUAL(addr, &c->gw6) && !c->no_map_gw) {
if (!udp_tap_map[V6][dst].ts_local ||
udp_tap_map[V6][dst].loopback)
s_in6.sin6_addr = in6addr_loopback;
@@ -1005,7 +1027,7 @@ int udp_tap_handler(struct ctx *c, int af, void *addr,
s_in6.sin6_addr = c->addr6;
else
s_in6.sin6_addr = c->addr6_seen;
- } else if (!memcmp(addr, &c->dns6_fwd, sizeof(c->dns6_fwd)) &&
+ } else if (IN6_ARE_ADDR_EQUAL(addr, &c->dns6_fwd) &&
ntohs(s_in6.sin6_port) == 53) {
s_in6.sin6_addr = c->dns6[0];
} else if (IN6_IS_ADDR_LINKLOCAL(&s_in6.sin6_addr)) {
--
2.35.1
next prev parent reply other threads:[~2022-03-25 22:52 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-25 22:52 [PATCH 00/24] Boundary-checked "packets", TCP timerfd timeouts, assorted fixes Stefano Brivio
2022-03-25 22:52 ` [PATCH 01/24] conf, util, tap: Implement --trace option for extra verbose logging Stefano Brivio
2022-03-25 22:52 ` [PATCH 02/24] pcap: Fix mistake in printed string Stefano Brivio
2022-03-25 22:52 ` [PATCH 03/24] util: Drop CHECK_SET_MIN_MAX{,_PROTO_FD} macros Stefano Brivio
2022-03-25 22:52 ` [PATCH 04/24] util: Use standard int types Stefano Brivio
2022-03-25 22:52 ` [PATCH 05/24] tcp: Refactor to use events instead of states, split out spliced implementation Stefano Brivio
2022-03-25 22:52 ` [PATCH 06/24] test/lib/video: Fill in href attributes of video shortcuts Stefano Brivio
2022-03-25 22:52 ` [PATCH 07/24] udp: Drop _splice from recv, send, sendto static buffer names Stefano Brivio
2022-03-25 22:52 ` Stefano Brivio [this message]
2022-03-25 22:52 ` [PATCH 09/24] dhcpv6, tap, tcp: Use IN6_ARE_ADDR_EQUAL instead of open-coded memcmp() Stefano Brivio
2022-03-25 22:52 ` [PATCH 10/24] udp: Use flags for local, loopback, and configured unicast binds Stefano Brivio
2022-03-25 22:52 ` [PATCH 11/24] Makefile: Enable a few hardening flags Stefano Brivio
2022-03-25 22:52 ` [PATCH 12/24] test: Add asciinema(1) as requirement for CI in README Stefano Brivio
2022-03-25 22:52 ` [PATCH 13/24] test, seccomp, Makefile: Switch to valgrind runs for passt functional tests Stefano Brivio
2022-03-25 22:52 ` [PATCH 14/24] tcp, udp, util: Enforce 24-bit limit on socket numbers Stefano Brivio
2022-03-25 22:52 ` [PATCH 15/24] tcp: Rework timers to use timerfd instead of periodic bitmap scan Stefano Brivio
2022-03-25 22:52 ` [PATCH 16/24] tcp_splice: Close sockets right away on high number of open files Stefano Brivio
2022-03-25 22:52 ` [PATCH 17/24] test/perf: Work-around for virtio_net hang before long streams from guest Stefano Brivio
2022-03-25 22:52 ` [PATCH 18/24] README: Avoid "here" links Stefano Brivio
2022-03-25 22:52 ` [PATCH 19/24] README: Update Interfaces and Availability sections Stefano Brivio
2022-03-25 22:52 ` [PATCH 20/24] tcp: Fit struct tcp_conn into a single 64-byte cacheline Stefano Brivio
2022-03-25 22:52 ` [PATCH 21/24] dhcp: Minimum option length implied by RFC 951 is 60 bytes, not 62 Stefano Brivio
2022-03-25 22:52 ` [PATCH 22/24] tcp, tcp_splice: Use less awkward syntax to swap in/out sockets from pools Stefano Brivio
2022-03-25 22:52 ` [PATCH 23/24] util: Fix function declaration style of write_pidfile() Stefano Brivio
2022-03-25 22:53 ` [PATCH 24/24] treewide: Packet abstraction with mandatory boundary checks Stefano Brivio
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=20220325225300.2803584-9-sbrivio@redhat.com \
--to=sbrivio@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).