Merge branch 'vsock-virtio' into main

Luigi Leonardi says:

====================
vsock: avoid queuing on intermediate queue if possible

This series introduces an optimization for vsock/virtio to reduce latency
and increase the throughput: When the guest sends a packet to the host,
and the intermediate queue (send_pkt_queue) is empty, if there is enough
space, the packet is put directly in the virtqueue.

v3->v4
While running experiments on fio with 64B payload, I realized that there
was a mistake in my fio configuration, so I re-ran all the experiments
and now the latency numbers are indeed lower with the patch applied.
I also noticed that I was kicking the host without the lock.

- Fixed a configuration mistake on fio and re-ran all experiments.
- Fio latency measurement using 64B payload.
- virtio_transport_send_skb_fast_path sends kick with the tx_lock acquired
- Addressed all minor style changes requested by maintainer.
- Rebased on latest net-next
- Link to v3: https://lore.kernel.org/r/20240711-pinna-v3-0-697d4164fe80@outlook.com

v2->v3
- Performed more experiments using iperf3 using multiple streams
- Handling of reply packets removed from virtio_transport_send_skb,
  as is needed just by the worker.
- Removed atomic_inc/atomic_sub when queuing directly to the vq.
- Introduced virtio_transport_send_skb_fast_path that handles the
  steps for sending on the vq.
- Fixed a missing mutex_unlock in error path.
- Changed authorship of the second commit
- Rebased on latest net-next

v1->v2
In this v2 I replaced a mutex_lock with a mutex_trylock because it was
insidea RCU critical section. I also added a check on tx_run, so if the
module is being removed the packet is not queued. I'd like to thank Stefano
for reporting the tx_run issue.

Applied all Stefano's suggestions:
    - Minor code style changes
    - Minor commit text rewrite
Performed more experiments:
     - Check if all the packets go directly to the vq (Matias' suggestion)
     - Used iperf3 to see if there is any improvement in overall throughput
      from guest to host
     - Pinned the vhost process to a pCPU.
     - Run fio using 512B payload
Rebased on latest net-next
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 85 insertions, 0 deletions

diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index f851f8961247..8d38dbf8f41f 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -20,6 +20,8 @@
 #include <sys/mman.h>
 #include <poll.h>
 #include <signal.h>
+#include <sys/ioctl.h>
+#include <linux/sockios.h>
 
 #include "vsock_test_zerocopy.h"
 #include "timeout.h"
@@ -1238,6 +1240,79 @@ static void test_double_bind_connect_client(const struct test_opts *opts)
 	}
 }
 
+#define MSG_BUF_IOCTL_LEN 64
+static void test_unsent_bytes_server(const struct test_opts *opts, int type)
+{
+	unsigned char buf[MSG_BUF_IOCTL_LEN];
+	int client_fd;
+
+	client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type);
+	if (client_fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	recv_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf));
+	control_writeln("RECEIVED");
+
+	close(client_fd);
+}
+
+static void test_unsent_bytes_client(const struct test_opts *opts, int type)
+{
+	unsigned char buf[MSG_BUF_IOCTL_LEN];
+	int ret, fd, sock_bytes_unsent;
+
+	fd = vsock_connect(opts->peer_cid, opts->peer_port, type);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	for (int i = 0; i < sizeof(buf); i++)
+		buf[i] = rand() & 0xFF;
+
+	send_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
+	control_expectln("RECEIVED");
+
+	ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+	if (ret < 0) {
+		if (errno == EOPNOTSUPP) {
+			fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
+		} else {
+			perror("ioctl");
+			exit(EXIT_FAILURE);
+		}
+	} else if (ret == 0 && sock_bytes_unsent != 0) {
+		fprintf(stderr,
+			"Unexpected 'SIOCOUTQ' value, expected 0, got %i\n",
+			sock_bytes_unsent);
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+}
+
+static void test_stream_unsent_bytes_client(const struct test_opts *opts)
+{
+	test_unsent_bytes_client(opts, SOCK_STREAM);
+}
+
+static void test_stream_unsent_bytes_server(const struct test_opts *opts)
+{
+	test_unsent_bytes_server(opts, SOCK_STREAM);
+}
+
+static void test_seqpacket_unsent_bytes_client(const struct test_opts *opts)
+{
+	test_unsent_bytes_client(opts, SOCK_SEQPACKET);
+}
+
+static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts)
+{
+	test_unsent_bytes_server(opts, SOCK_SEQPACKET);
+}
+
 #define RCVLOWAT_CREDIT_UPD_BUF_SIZE	(1024 * 128)
 /* This define is the same as in 'include/linux/virtio_vsock.h':
  * it is used to decide when to send credit update message during
@@ -1523,6 +1598,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_rcvlowat_def_cred_upd_client,
 		.run_server = test_stream_cred_upd_on_low_rx_bytes,
 	},
+	{
+		.name = "SOCK_STREAM ioctl(SIOCOUTQ) 0 unsent bytes",
+		.run_client = test_stream_unsent_bytes_client,
+		.run_server = test_stream_unsent_bytes_server,
+	},
+	{
+		.name = "SOCK_SEQPACKET ioctl(SIOCOUTQ) 0 unsent bytes",
+		.run_client = test_seqpacket_unsent_bytes_client,
+		.run_server = test_seqpacket_unsent_bytes_server,
+	},
 	{},
 };