[PATCH net v5 2/2] selftests: net: add a vhost-net test for the tun NAPI queue bound

[Antonio Quartulli <antonio@mandelbit.com>]

Send 16k packets from vhost-net into a tap device with IFF_NAPI and
netdev_max_backlog set to 8, in the three ways vhost-net passes packets
to tun: batches of XDP buffers, one packet per sendmsg() with MSG_MORE,
and zerocopy buffers. Check that excess packets are dropped and counted,
that the queue keeps draining while vhost-net keeps sending, that every
packet is either delivered or dropped, and that every buffer comes back
to the ring. If a dropped zerocopy buffer is never completed, the test
fails, and closing vhost-net then blocks until the buffer is released.

The zerocopy variant needs vhost_net loaded with experimental_zcopytx
set and is skipped otherwise; with it, vhost-net does not batch and the
batch variant is skipped instead.

The test drives a minimal split virtqueue itself, in little-endian as
VIRTIO_F_VERSION_1 requires. It needs root and CONFIG_VHOST_NET.
netdev_max_backlog is global: the test lowers it only once setup has
succeeded and restores it first in teardown, and should not run in
parallel with other tests.

Written and tested with the help of an AI coding assistant (Claude
Code).

Signed-off-by: Antonio Quartulli <antonio@mandelbit.com>
---
 tools/testing/selftests/net/.gitignore  |   1 +
 tools/testing/selftests/net/Makefile    |   1 +
 tools/testing/selftests/net/config      |   1 +
 tools/testing/selftests/net/tun_vhost.c | 409 ++++++++++++++++++++++++
 4 files changed, 412 insertions(+)
 create mode 100644 tools/testing/selftests/net/tun_vhost.c

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 21412510ac26..aafd07910058 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -54,6 +54,7 @@ timestamping
 tls
 tools
 tun
+tun_vhost
 txring_overwrite
 txtimestamp
 udp_splice_checksum
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 9180b9bec515..babb684d6f77 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -202,6 +202,7 @@ TEST_GEN_PROGS := \
 	tap \
 	tcp_port_share \
 	tls \
+	tun_vhost \
 	udp_splice_checksum \
 # end of TEST_GEN_PROGS
 
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index d4416f8bdcfd..9afa82dea11d 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -135,6 +135,7 @@ CONFIG_TRACEPOINTS=y
 CONFIG_TUN=y
 CONFIG_USER_NS=y
 CONFIG_VETH=y
+CONFIG_VHOST_NET=m
 CONFIG_VLAN_8021Q=y
 CONFIG_VXLAN=m
 CONFIG_XFRM_INTERFACE=m
diff --git a/tools/testing/selftests/net/tun_vhost.c b/tools/testing/selftests/net/tun_vhost.c
new file mode 100644
index 000000000000..ed35435df90e
--- /dev/null
+++ b/tools/testing/selftests/net/tun_vhost.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Send packets from vhost-net into a tap device with IFF_NAPI and check
+ * that the NAPI queue is bounded by netdev_max_backlog: excess packets
+ * are dropped and counted, and every buffer is returned to the driver,
+ * zerocopy ones included.
+ *
+ * vhost-net passes packets to tun in three ways:
+ *  - batch: batches of XDP buffers (tun_xdp_one()), the default when the
+ *    socket send buffer is unlimited and zerocopy is disabled
+ *  - copy: one packet per sendmsg(), when the send buffer is limited
+ *  - zerocopy: one packet per sendmsg() with a ubuf_info to complete,
+ *    only with vhost_net experimental_zcopytx set (else skipped)
+ *
+ * Tun schedules NAPI after a batch, after the last of a series of MSG_MORE
+ * packets, once more than NAPI_POLL_WEIGHT (64) packets are queued, and
+ * when it drops a packet because the queue is full. With netdev_max_backlog
+ * below 64, the queue always overflows and only the last of these keeps it
+ * draining while the sender keeps sending.
+ *
+ * netdev_max_backlog is global: the test lowers it for the whole system
+ * while it runs, so it should not run in parallel with other tests.
+ *
+ * Author: Antonio Quartulli <antonio@mandelbit.com>
+ */
+
+#define _GNU_SOURCE
+#include <endian.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/if_tun.h>
+#include <linux/vhost.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_net.h>
+#include <linux/virtio_ring.h>
+#include <sys/eventfd.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+
+#include "kselftest_harness.h"
+
+#define TV_IFNAME	"tvh0"
+#define TV_RING_NUM	256
+#define TV_BUF_SIZE	2048
+#define TV_HDR_LEN	sizeof(struct virtio_net_hdr_v1)
+#define TV_PKTS		(64 * TV_RING_NUM)
+#define TV_BACKLOG	"8"
+#define TV_TX_VQ	1
+
+static const unsigned char tv_mac_tap[ETH_ALEN] = { 2, 0, 0, 0, 0, 1 };
+static const unsigned char tv_mac_dst[ETH_ALEN] = { 2, 0, 0, 0, 0, 2 };
+static const unsigned char tv_mac_src[ETH_ALEN] = { 2, 0, 0, 0, 0, 3 };
+
+/* TX virtqueue, little-endian as negotiated with VIRTIO_F_VERSION_1 */
+struct tv_ring {
+	void *mem;
+	struct vring vr;
+	char *bufs;
+	int kick;
+	int call;
+	unsigned short avail_idx;
+	unsigned short used_idx;
+	/* descriptors not owned by vhost: buffers may come back in any order */
+	unsigned short free[TV_RING_NUM];
+	int nfree;
+};
+
+struct tv_stats {
+	unsigned long long rx_packets;
+	unsigned long long rx_dropped;
+};
+
+static int tv_read_stats(const char *ifname, struct tv_stats *st)
+{
+	char line[512], *p;
+	FILE *f;
+	int ret = -1;
+
+	f = fopen("/proc/net/dev", "r");
+	if (!f)
+		return -1;
+	while (fgets(line, sizeof(line), f)) {
+		p = strchr(line, ':');
+		if (!p)
+			continue;
+		*p = '\0';
+		if (strcmp(line + strspn(line, " "), ifname))
+			continue;
+		if (sscanf(p + 1, "%*u %llu %*u %llu", &st->rx_packets,
+			   &st->rx_dropped) == 2)
+			ret = 0;
+		break;
+	}
+	fclose(f);
+	return ret;
+}
+
+FIXTURE(tun_vhost)
+{
+	int backlog_fd;
+	char backlog[32];
+	int tap;
+	int vhost;
+	struct tv_ring ring;
+};
+
+FIXTURE_VARIANT(tun_vhost)
+{
+	bool batch;
+	bool limit_sndbuf;
+	bool zerocopy;
+	int pktlen;
+};
+
+FIXTURE_VARIANT_ADD(tun_vhost, batch)
+{
+	.batch = true,
+	.pktlen = 64,
+};
+
+FIXTURE_VARIANT_ADD(tun_vhost, copy)
+{
+	.limit_sndbuf = true,
+	.pktlen = 64,
+};
+
+FIXTURE_VARIANT_ADD(tun_vhost, zerocopy)
+{
+	.limit_sndbuf = true,
+	.zerocopy = true,
+	.pktlen = 1000,
+};
+
+/* vhost-net uses zerocopy for any non-zero value */
+static bool tv_zerocopy_enabled(void)
+{
+	char buf[16] = {};
+	int fd;
+
+	fd = open("/sys/module/vhost_net/parameters/experimental_zcopytx",
+		  O_RDONLY);
+	if (fd < 0)
+		return false;
+	if (read(fd, buf, sizeof(buf) - 1) <= 0)
+		buf[0] = '\0';
+	close(fd);
+	return atoi(buf) != 0;
+}
+
+static int tv_vhost_setup(int vhost, int tap, struct tv_ring *r)
+{
+	struct vhost_vring_state state = { .index = TV_TX_VQ };
+	struct vhost_vring_file file = { .index = TV_TX_VQ };
+	struct vhost_vring_addr addr = { .index = TV_TX_VQ };
+	size_t memsz = sizeof(struct vhost_memory) +
+		       sizeof(struct vhost_memory_region);
+	unsigned long long features;
+	struct vhost_memory *mem;
+	int ret;
+
+	if (ioctl(vhost, VHOST_SET_OWNER, NULL) ||
+	    ioctl(vhost, VHOST_GET_FEATURES, &features) ||
+	    !(features & (1ULL << VIRTIO_F_VERSION_1)))
+		return -1;
+	features = 1ULL << VIRTIO_F_VERSION_1;
+	if (ioctl(vhost, VHOST_SET_FEATURES, &features))
+		return -1;
+
+	/* buffer addresses are passed as is: map them 1:1 */
+	mem = calloc(1, memsz);
+	if (!mem)
+		return -1;
+	mem->nregions = 1;
+	mem->regions[0].guest_phys_addr = (unsigned long)r->bufs;
+	mem->regions[0].userspace_addr = (unsigned long)r->bufs;
+	mem->regions[0].memory_size = TV_RING_NUM * TV_BUF_SIZE;
+	ret = ioctl(vhost, VHOST_SET_MEM_TABLE, mem);
+	free(mem);
+	if (ret)
+		return -1;
+
+	state.num = TV_RING_NUM;
+	if (ioctl(vhost, VHOST_SET_VRING_NUM, &state))
+		return -1;
+	state.num = 0;
+	if (ioctl(vhost, VHOST_SET_VRING_BASE, &state))
+		return -1;
+	addr.desc_user_addr = (unsigned long)r->vr.desc;
+	addr.avail_user_addr = (unsigned long)r->vr.avail;
+	addr.used_user_addr = (unsigned long)r->vr.used;
+	if (ioctl(vhost, VHOST_SET_VRING_ADDR, &addr))
+		return -1;
+	file.fd = r->kick;
+	if (ioctl(vhost, VHOST_SET_VRING_KICK, &file))
+		return -1;
+	file.fd = r->call;
+	if (ioctl(vhost, VHOST_SET_VRING_CALL, &file))
+		return -1;
+	file.fd = tap;
+	return ioctl(vhost, VHOST_NET_SET_BACKEND, &file);
+}
+
+static int tv_ring_init(struct tv_ring *r)
+{
+	int i;
+
+	if (posix_memalign((void **)&r->bufs, 4096, TV_RING_NUM * TV_BUF_SIZE))
+		return -1;
+	memset(r->bufs, 0, TV_RING_NUM * TV_BUF_SIZE);
+
+	/* every buffer: zeroed vnet header + IPv4 frame for another host,
+	 * which the stack drops without counting it in rx_dropped
+	 */
+	for (i = 0; i < TV_RING_NUM; i++) {
+		unsigned char *eth = (unsigned char *)r->bufs +
+				     i * TV_BUF_SIZE + TV_HDR_LEN;
+
+		memcpy(eth, tv_mac_dst, ETH_ALEN);
+		memcpy(eth + ETH_ALEN, tv_mac_src, ETH_ALEN);
+		eth[12] = ETH_P_IP >> 8;
+		eth[13] = ETH_P_IP & 0xff;
+		eth[14] = 0x45;
+		r->free[i] = i;
+	}
+	r->nfree = TV_RING_NUM;
+
+	if (posix_memalign(&r->mem, 4096, vring_size(TV_RING_NUM, 4096)))
+		return -1;
+	memset(r->mem, 0, vring_size(TV_RING_NUM, 4096));
+	vring_init(&r->vr, TV_RING_NUM, r->mem, 4096);
+
+	r->kick = eventfd(0, EFD_NONBLOCK);
+	r->call = eventfd(0, EFD_NONBLOCK);
+	return r->kick < 0 || r->call < 0 ? -1 : 0;
+}
+
+/* save the global netdev_max_backlog, to restore it in teardown */
+static int tv_backlog_save(int *fd, char *old, size_t size)
+{
+	ssize_t n;
+
+	/* only visible from init_net: keep it open across unshare() */
+	*fd = open("/proc/sys/net/core/netdev_max_backlog", O_RDWR);
+	if (*fd < 0)
+		return -1;
+	n = read(*fd, old, size - 1);
+	if (n <= 0)
+		return -1;
+	old[n] = '\0';
+	return 0;
+}
+
+FIXTURE_SETUP(tun_vhost)
+{
+	struct ifreq ifr = {};
+	int hdrlen = TV_HDR_LEN;
+	int sndbuf = 1 << 20;
+	int fd;
+
+	self->backlog_fd = -1;
+	self->vhost = open("/dev/vhost-net", O_RDWR);
+	if (self->vhost < 0)
+		SKIP(return, "no /dev/vhost-net");
+	if (variant->zerocopy && !tv_zerocopy_enabled())
+		SKIP(return, "vhost_net experimental_zcopytx not enabled");
+	if (variant->batch && tv_zerocopy_enabled())
+		SKIP(return, "vhost_net does not batch with zerocopy");
+
+	ASSERT_EQ(tv_backlog_save(&self->backlog_fd, self->backlog,
+				  sizeof(self->backlog)), 0);
+	ASSERT_EQ(unshare(CLONE_NEWNET), 0);
+
+	self->tap = open("/dev/net/tun", O_RDWR);
+	ASSERT_GE(self->tap, 0);
+	ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR | IFF_NAPI;
+	memcpy(ifr.ifr_name, TV_IFNAME, sizeof(TV_IFNAME));
+	ASSERT_EQ(ioctl(self->tap, TUNSETIFF, &ifr), 0);
+	ASSERT_EQ(ioctl(self->tap, TUNSETVNETHDRSZ, &hdrlen), 0);
+	if (variant->limit_sndbuf)
+		ASSERT_EQ(ioctl(self->tap, TUNSETSNDBUF, &sndbuf), 0);
+
+	fd = socket(AF_INET, SOCK_DGRAM, 0);
+	ASSERT_GE(fd, 0);
+	ifr.ifr_hwaddr.sa_family = ARPHRD_ETHER;
+	memcpy(ifr.ifr_hwaddr.sa_data, tv_mac_tap, ETH_ALEN);
+	ASSERT_EQ(ioctl(fd, SIOCSIFHWADDR, &ifr), 0);
+	ASSERT_EQ(ioctl(fd, SIOCGIFFLAGS, &ifr), 0);
+	ifr.ifr_flags |= IFF_UP;
+	ASSERT_EQ(ioctl(fd, SIOCSIFFLAGS, &ifr), 0);
+	close(fd);
+
+	ASSERT_EQ(tv_ring_init(&self->ring), 0);
+	ASSERT_EQ(tv_vhost_setup(self->vhost, self->tap, &self->ring), 0);
+}
+
+FIXTURE_TEARDOWN(tun_vhost)
+{
+	/* restore first: closing vhost may block if buffers are not returned */
+	if (self->backlog_fd >= 0) {
+		if (pwrite(self->backlog_fd, self->backlog,
+			   strlen(self->backlog), 0) < 0)
+			TH_LOG("cannot restore netdev_max_backlog to %s",
+			       self->backlog);
+		close(self->backlog_fd);
+	}
+	close(self->vhost);
+	close(self->tap);
+}
+
+/* queue up to @n buffers, return how many */
+static int tv_post(struct tv_ring *r, int pktlen, int n)
+{
+	unsigned long long one = 1;
+	int i;
+
+	for (i = 0; i < n && r->nfree; i++) {
+		unsigned short id = r->free[--r->nfree];
+
+		r->vr.desc[id].addr = htole64((unsigned long)r->bufs +
+					      id * TV_BUF_SIZE);
+		r->vr.desc[id].len = htole32(TV_HDR_LEN + pktlen);
+		r->vr.desc[id].flags = 0;
+		r->vr.avail->ring[r->avail_idx % TV_RING_NUM] = htole16(id);
+		r->avail_idx++;
+	}
+	__atomic_store_n(&r->vr.avail->idx, htole16(r->avail_idx),
+			 __ATOMIC_RELEASE);
+	if (i && write(r->kick, &one, sizeof(one)) != sizeof(one))
+		return -1;
+	return i;
+}
+
+/* reap returned buffers, waiting up to @ms for at least one */
+static int tv_reap(struct tv_ring *r, int ms)
+{
+	struct pollfd pfd = { .fd = r->call, .events = POLLIN };
+	unsigned short used;
+	unsigned long long v;
+	int n = 0;
+
+	for (;;) {
+		used = le16toh(__atomic_load_n(&r->vr.used->idx,
+					       __ATOMIC_ACQUIRE));
+		while (r->used_idx != used) {
+			struct vring_used_elem *e;
+
+			e = &r->vr.used->ring[r->used_idx % TV_RING_NUM];
+			r->free[r->nfree++] = le32toh(e->id);
+			r->used_idx++;
+			n++;
+		}
+		if (n)
+			return n;
+		if (ms <= 0 || poll(&pfd, 1, 100) < 0)
+			return 0;
+		if (pfd.revents & POLLIN && read(r->call, &v, sizeof(v)) < 0)
+			return -1;
+		ms -= 100;
+	}
+}
+
+TEST_F(tun_vhost, napi_queue_bounded)
+{
+	struct tv_stats before, after;
+	unsigned long long delivered, dropped;
+	int posted = 0, reaped = 0, n;
+
+	ASSERT_EQ(tv_read_stats(TV_IFNAME, &before), 0);
+	/* lowered only now, so that a failed setup leaves it alone */
+	ASSERT_EQ(pwrite(self->backlog_fd, TV_BACKLOG, strlen(TV_BACKLOG), 0),
+		  strlen(TV_BACKLOG));
+
+	while (reaped < TV_PKTS) {
+		n = tv_post(&self->ring, variant->pktlen, TV_PKTS - posted);
+		ASSERT_GE(n, 0);
+		posted += n;
+		n = tv_reap(&self->ring, 5000);
+		ASSERT_GE(n, 0);
+		if (!n) {
+			TH_LOG("%d of %d buffers not returned",
+			       posted - reaped, posted);
+			ASSERT_GT(n, 0);
+		}
+		reaped += n;
+	}
+
+	ASSERT_EQ(tv_read_stats(TV_IFNAME, &after), 0);
+	delivered = after.rx_packets - before.rx_packets;
+	dropped = after.rx_dropped - before.rx_dropped;
+	TH_LOG("sent %d, delivered %llu, dropped %llu", TV_PKTS, delivered,
+	       dropped);
+	/* bounded, */
+	EXPECT_GT(dropped, 0);
+	/* still draining, */
+	EXPECT_GE(delivered, TV_PKTS / 64);
+	/* and every packet accounted for */
+	EXPECT_EQ(delivered + dropped, TV_PKTS);
+}
+
+TEST_HARNESS_MAIN
-- 
2.56.0