Add basic driver initialization, documentation, and device creation
and basic documentation.
Signed-off-by: Stephen Hemminger <step...@networkplumber.org>
---
MAINTAINERS | 6 +
doc/guides/nics/features/ioring.ini | 9 +
doc/guides/nics/index.rst | 1 +
doc/guides/nics/ioring.rst | 66 +++++++
drivers/net/ioring/meson.build | 15 ++
drivers/net/ioring/rte_eth_ioring.c | 262 ++++++++++++++++++++++++++++
drivers/net/meson.build | 1 +
7 files changed, 360 insertions(+)
create mode 100644 doc/guides/nics/features/ioring.ini
create mode 100644 doc/guides/nics/ioring.rst
create mode 100644 drivers/net/ioring/meson.build
create mode 100644 drivers/net/ioring/rte_eth_ioring.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 82f6e2f917..78bf70c5a0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -853,6 +853,12 @@ F: drivers/net/intel/ipn3ke/
F: doc/guides/nics/ipn3ke.rst
F: doc/guides/nics/features/ipn3ke.ini
+Ioring - EXPERIMENTAL
+M: Stephen Hemminger <step...@networkplumber.org>
+F: drivers/net/ioring/
+F: doc/guides/nics/ioring.rst
+F: doc/guides/nics/features/ioring.ini
+
Marvell cnxk
M: Nithin Dabilpuram <ndabilpu...@marvell.com>
M: Kiran Kumar K <kirankum...@marvell.com>
diff --git a/doc/guides/nics/features/ioring.ini
b/doc/guides/nics/features/ioring.ini
new file mode 100644
index 0000000000..c4c57caaa4
--- /dev/null
+++ b/doc/guides/nics/features/ioring.ini
@@ -0,0 +1,9 @@
+;
+; Supported features of the 'ioring' driver.
+;
+; Refer to default.ini for the full list of available PMD features.
+;
+[Features]
+Linux = Y
+x86-64 = Y
+Usage doc = Y
diff --git a/doc/guides/nics/index.rst b/doc/guides/nics/index.rst
index 10a2eca3b0..afb6bf289b 100644
--- a/doc/guides/nics/index.rst
+++ b/doc/guides/nics/index.rst
@@ -41,6 +41,7 @@ Network Interface Controller Drivers
igc
intel_vf
ionic
+ ioring
ipn3ke
ixgbe
mana
diff --git a/doc/guides/nics/ioring.rst b/doc/guides/nics/ioring.rst
new file mode 100644
index 0000000000..7d37a6bb37
--- /dev/null
+++ b/doc/guides/nics/ioring.rst
@@ -0,0 +1,66 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+
+IORING Poll Mode Driver
+=======================
+
+The IORING Poll Mode Driver (PMD) is a simplified and improved version of the
TAP PMD. It is a
+virtual device that uses Linux ioring to inject packets into the Linux kernel.
+It is useful when writing DPDK applications, that need to support interaction
+with the Linux TCP/IP stack for control plane or tunneling.
+
+The IORING PMD creates a kernel network device that can be
+managed by standard tools such as ``ip`` and ``ethtool`` commands.
+
+From a DPDK application, the IORING device looks like a DPDK ethdev.
+It supports the standard DPDK API's to query for information, statistics,
+and send/receive packets.
+
+Requirements
+------------
+
+The IORING requires the io_uring library (liburing) which provides the helper
+functions to manage io_uring with the kernel.
+
+For more info on io_uring, please see:
+
+https://kernel.dk/io_uring.pdf
+
+
+Arguments
+---------
+
+IORING devices are created with the command line ``--vdev=net_ioring0`` option.
+This option may be specified more than once by repeating with a different
``net_ioringX`` device.
+
+By default, the Linux interfaces are named ``enio0``, ``enio1``, etc.
+The interface name can be specified by adding the ``iface=foo0``, for example::
+
+ --vdev=net_ioring0,iface=io0 --vdev=net_ioring1,iface=io1, ...
+
+The PMD inherits the MAC address assigned by the kernel which will be
+a locally assigned random Ethernet address.
+
+Normally, when the DPDK application exits, the IORING device is removed.
+But this behavior can be overridden by the use of the persist flag, example::
+
+ --vdev=net_ioring0,iface=io0,persist ...
+
+
+Multi-process sharing
+---------------------
+
+The IORING device does not support secondary process (yet).
+
+
+Limitations
+-----------
+
+- IO uring requires io_uring support. This was add in Linux kernl version 5.1
+ Also, IO uring maybe disabled in some environments or by security policies.
+
+- Since IORING device uses a file descriptor to talk to the kernel,
+ the same number of queues must be specified for receive and transmit.
+
+- No flow support. Receive queue selection for incoming packets is determined
+ by the Linux kernel. See kernel documentation for more info:
+ https://www.kernel.org/doc/html/latest/networking/scaling.html
diff --git a/drivers/net/ioring/meson.build b/drivers/net/ioring/meson.build
new file mode 100644
index 0000000000..264554d069
--- /dev/null
+++ b/drivers/net/ioring/meson.build
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2024 Stephen Hemminger
+
+if not is_linux
+ build = false
+ reason = 'only supported on Linux'
+endif
+
+dep = dependency('liburing', required:false)
+reason = 'missing dependency, "liburing"'
+build = dep.found()
+ext_deps += dep
+
+sources = files('rte_eth_ioring.c')
+require_iova_in_mbuf = false
diff --git a/drivers/net/ioring/rte_eth_ioring.c
b/drivers/net/ioring/rte_eth_ioring.c
new file mode 100644
index 0000000000..4d5a5174db
--- /dev/null
+++ b/drivers/net/ioring/rte_eth_ioring.c
@@ -0,0 +1,262 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) Stephen Hemminger
+ */
+
+#include <ctype.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/if.h>
+#include <linux/if_tun.h>
+
+#include <bus_vdev_driver.h>
+#include <ethdev_driver.h>
+#include <ethdev_vdev.h>
+#include <rte_common.h>
+#include <rte_dev.h>
+#include <rte_eal.h>
+#include <rte_ethdev.h>
+#include <rte_ether.h>
+#include <rte_kvargs.h>
+#include <rte_log.h>
+
+#define IORING_DEFAULT_IFNAME "itap%d"
+
+RTE_LOG_REGISTER_DEFAULT(ioring_logtype, NOTICE);
+#define RTE_LOGTYPE_IORING ioring_logtype
+#define PMD_LOG(level, ...) RTE_LOG_LINE_PREFIX(level, IORING, "%s(): ",
__func__, __VA_ARGS__)
+
+#define IORING_IFACE_ARG "iface"
+#define IORING_PERSIST_ARG "persist"
+
+static const char * const valid_arguments[] = {
+ IORING_IFACE_ARG,
+ IORING_PERSIST_ARG,
+ NULL
+};
+
+struct pmd_internals {
+ int keep_fd; /* keep alive file descriptor */
+ char ifname[IFNAMSIZ]; /* name assigned by kernel */
+ struct rte_ether_addr eth_addr; /* address assigned by kernel */
+};
+
+/* Creates a new tap device, name returned in ifr */
+static int
+tap_open(const char *name, struct ifreq *ifr, uint8_t persist)
+{
+ static const char tun_dev[] = "/dev/net/tun";
+ int tap_fd;
+
+ tap_fd = open(tun_dev, O_RDWR | O_CLOEXEC | O_NONBLOCK);
+ if (tap_fd < 0) {
+ PMD_LOG(ERR, "Open %s failed: %s", tun_dev, strerror(errno));
+ return -1;
+ }
+
+ int features = 0;
+ if (ioctl(tap_fd, TUNGETFEATURES, &features) < 0) {
+ PMD_LOG(ERR, "ioctl(TUNGETFEATURES) %s", strerror(errno));
+ goto error;
+ }
+
+ int flags = IFF_TAP | IFF_MULTI_QUEUE | IFF_NO_PI;
+ if ((features & flags) != flags) {
+ PMD_LOG(ERR, "TUN features %#x missing support for %#x",
+ features, features & flags);
+ goto error;
+ }
+
+#ifdef IFF_NAPI
+ /* If kernel supports using NAPI enable it */
+ if (features & IFF_NAPI)
+ flags |= IFF_NAPI;
+#endif
+ /*
+ * Sets the device name and packet format.
+ * Do not want the protocol information (PI)
+ */
+ strlcpy(ifr->ifr_name, name, IFNAMSIZ);
+ ifr->ifr_flags = flags;
+ if (ioctl(tap_fd, TUNSETIFF, ifr) < 0) {
+ PMD_LOG(ERR, "ioctl(TUNSETIFF) %s: %s",
+ ifr->ifr_name, strerror(errno));
+ goto error;
+ }
+
+ /* (Optional) keep the device after application exit */
+ if (persist && ioctl(tap_fd, TUNSETPERSIST, 1) < 0) {
+ PMD_LOG(ERR, "ioctl(TUNSETPERIST) %s: %s",
+ ifr->ifr_name, strerror(errno));
+ goto error;
+ }
+
+ return tap_fd;
+error:
+ close(tap_fd);
+ return -1;
+}
+
+static int
+eth_dev_close(struct rte_eth_dev *dev)
+{
+ struct pmd_internals *pmd = dev->data->dev_private;
+
+ PMD_LOG(INFO, "Closing %s", pmd->ifname);
+
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY)
+ return 0;
+
+ /* mac_addrs must not be freed alone because part of dev_private */
+ dev->data->mac_addrs = NULL;
+
+ if (pmd->keep_fd != -1) {
+ close(pmd->keep_fd);
+ pmd->keep_fd = -1;
+ }
+
+ return 0;
+}
+
+static const struct eth_dev_ops ops = {
+ .dev_close = eth_dev_close,
+};
+
+static int
+ioring_create(struct rte_eth_dev *dev, const char *tap_name, uint8_t persist)
+{
+ struct rte_eth_dev_data *data = dev->data;
+ struct pmd_internals *pmd = data->dev_private;
+
+ pmd->keep_fd = -1;
+
+ data->dev_flags = RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS;
+ dev->dev_ops = &ops;
+
+ /* Get the initial fd used to keep the tap device around */
+ struct ifreq ifr = { };
+ pmd->keep_fd = tap_open(tap_name, &ifr, persist);
+ if (pmd->keep_fd < 0)
+ goto error;
+
+ strlcpy(pmd->ifname, ifr.ifr_name, IFNAMSIZ);
+
+ /* Read the MAC address assigned by the kernel */
+ if (ioctl(pmd->keep_fd, SIOCGIFHWADDR, &ifr) < 0) {
+ PMD_LOG(ERR, "Unable to get MAC address for %s: %s",
+ ifr.ifr_name, strerror(errno));
+ goto error;
+ }
+ memcpy(&pmd->eth_addr, &ifr.ifr_hwaddr.sa_data, RTE_ETHER_ADDR_LEN);
+ data->mac_addrs = &pmd->eth_addr;
+
+ /* Detach this instance, not used for traffic */
+ ifr.ifr_flags = IFF_DETACH_QUEUE;
+ if (ioctl(pmd->keep_fd, TUNSETQUEUE, &ifr) < 0) {
+ PMD_LOG(ERR, "Unable to detach keep-alive queue for %s: %s",
+ ifr.ifr_name, strerror(errno));
+ goto error;
+ }
+
+ PMD_LOG(DEBUG, "%s setup", ifr.ifr_name);
+ return 0;
+
+error:
+ if (pmd->keep_fd != -1)
+ close(pmd->keep_fd);
+ return -1;
+}
+
+static int
+parse_iface_arg(const char *key __rte_unused, const char *value, void
*extra_args)
+{
+ char *name = extra_args;
+
+ /* must not be null string */
+ if (name == NULL || name[0] == '\0' ||
+ strnlen(name, IFNAMSIZ) == IFNAMSIZ)
+ return -EINVAL;
+
+ strlcpy(name, value, IFNAMSIZ);
+ return 0;
+}
+
+static int
+ioring_probe(struct rte_vdev_device *vdev)
+{
+ const char *name = rte_vdev_device_name(vdev);
+ const char *params = rte_vdev_device_args(vdev);
+ struct rte_kvargs *kvlist = NULL;
+ struct rte_eth_dev *eth_dev = NULL;
+ char tap_name[IFNAMSIZ] = IORING_DEFAULT_IFNAME;
+ uint8_t persist = 0;
+ int ret;
+
+ PMD_LOG(INFO, "Initializing %s", name);
+
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY)
+ return -1; /* TODO */
+
+ if (params != NULL) {
+ kvlist = rte_kvargs_parse(params, valid_arguments);
+ if (kvlist == NULL)
+ return -1;
+
+ if (rte_kvargs_count(kvlist, IORING_IFACE_ARG) == 1) {
+ ret = rte_kvargs_process_opt(kvlist, IORING_IFACE_ARG,
+ &parse_iface_arg,
tap_name);
+ if (ret < 0)
+ goto error;
+ }
+
+ if (rte_kvargs_count(kvlist, IORING_PERSIST_ARG) == 1)
+ persist = 1;
+ }
+
+ eth_dev = rte_eth_vdev_allocate(vdev, sizeof(struct pmd_internals));
+ if (eth_dev == NULL) {
+ PMD_LOG(ERR, "%s Unable to allocate device struct", tap_name);
+ goto error;
+ }
+
+ if (ioring_create(eth_dev, tap_name, persist) < 0)
+ goto error;
+
+ rte_eth_dev_probing_finish(eth_dev);
+ return 0;
+
+error:
+ if (eth_dev != NULL)
+ rte_eth_dev_release_port(eth_dev);
+ rte_kvargs_free(kvlist);
+ return -1;
+}
+
+static int
+ioring_remove(struct rte_vdev_device *dev)
+{
+ struct rte_eth_dev *eth_dev;
+
+ eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
+ if (eth_dev == NULL)
+ return 0;
+
+ eth_dev_close(eth_dev);
+ rte_eth_dev_release_port(eth_dev);
+ return 0;
+}
+
+static struct rte_vdev_driver pmd_ioring_drv = {
+ .probe = ioring_probe,
+ .remove = ioring_remove,
+};
+
+RTE_PMD_REGISTER_VDEV(net_ioring, pmd_ioring_drv);
+RTE_PMD_REGISTER_ALIAS(net_ioring, eth_ioring);
+RTE_PMD_REGISTER_PARAM_STRING(net_ioring, IORING_IFACE_ARG "=<string> ");
diff --git a/drivers/net/meson.build b/drivers/net/meson.build
index 460eb69e5b..2e39136a5b 100644
--- a/drivers/net/meson.build
+++ b/drivers/net/meson.build
@@ -34,6 +34,7 @@ drivers = [
'intel/ixgbe',
'intel/cpfl', # depends on idpf, so must come after it
'ionic',
+ 'ioring',
'mana',
'memif',
'mlx4',
--
2.47.2
