-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
*/
#include <stdint.h>
#include <sys/eventfd.h>
#include <sys/types.h>
#include <sys/stat.h>
-#include <unistd.h>
+
+#include <rte_eal_memconfig.h>
#include "vhost.h"
#include "virtio_user_dev.h"
#include "../virtio_ethdev.h"
+#define VIRTIO_USER_MEM_EVENT_CLB_NAME "virtio_user_mem_event_clb"
+
static int
virtio_user_create_queue(struct virtio_user_dev *dev, uint32_t queue_sel)
{
* firstly because vhost depends on this msg to allocate virtqueue
* pair.
*/
- int callfd;
struct vhost_vring_file file;
- /* May use invalid flag, but some backend leverages kickfd and callfd as
- * criteria to judge if dev is alive. so finally we use real event_fd.
- */
- callfd = eventfd(0, EFD_CLOEXEC | EFD_NONBLOCK);
- if (callfd < 0) {
- PMD_DRV_LOG(ERR, "callfd error, %s", strerror(errno));
- return -1;
- }
file.index = queue_sel;
- file.fd = callfd;
+ file.fd = dev->callfds[queue_sel];
dev->ops->send_request(dev, VHOST_USER_SET_VRING_CALL, &file);
- dev->callfds[queue_sel] = callfd;
return 0;
}
static int
virtio_user_kick_queue(struct virtio_user_dev *dev, uint32_t queue_sel)
{
- int kickfd;
struct vhost_vring_file file;
struct vhost_vring_state state;
struct vring *vring = &dev->vrings[queue_sel];
* lastly because vhost depends on this msg to judge if
* virtio is ready.
*/
- kickfd = eventfd(0, EFD_CLOEXEC | EFD_NONBLOCK);
- if (kickfd < 0) {
- PMD_DRV_LOG(ERR, "kickfd error, %s", strerror(errno));
- return -1;
- }
file.index = queue_sel;
- file.fd = kickfd;
+ file.fd = dev->kickfds[queue_sel];
dev->ops->send_request(dev, VHOST_USER_SET_VRING_KICK, &file);
- dev->kickfds[queue_sel] = kickfd;
return 0;
}
return 0;
}
+int
+is_vhost_user_by_type(const char *path)
+{
+ struct stat sb;
+
+ if (stat(path, &sb) == -1)
+ return 0;
+
+ return S_ISSOCK(sb.st_mode);
+}
+
int
virtio_user_start_device(struct virtio_user_dev *dev)
{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
uint64_t features;
int ret;
+ /*
+ * XXX workaround!
+ *
+ * We need to make sure that the locks will be
+ * taken in the correct order to avoid deadlocks.
+ *
+ * Before releasing this lock, this thread should
+ * not trigger any memory hotplug events.
+ *
+ * This is a temporary workaround, and should be
+ * replaced when we get proper supports from the
+ * memory subsystem in the future.
+ */
+ rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+ pthread_mutex_lock(&dev->mutex);
+
+ if (is_vhost_user_by_type(dev->path) && dev->vhostfd < 0)
+ goto error;
+
+ /* Do not check return as already done in init, or reset in stop */
+ dev->ops->send_request(dev, VHOST_USER_SET_OWNER, NULL);
+
/* Step 0: tell vhost to create queues */
if (virtio_user_queue_setup(dev, virtio_user_create_queue) < 0)
goto error;
features &= ~(1ull << VIRTIO_NET_F_MAC);
/* Strip VIRTIO_NET_F_CTRL_VQ, as devices do not really need to know */
features &= ~(1ull << VIRTIO_NET_F_CTRL_VQ);
+ features &= ~(1ull << VIRTIO_NET_F_STATUS);
ret = dev->ops->send_request(dev, VHOST_USER_SET_FEATURES, &features);
if (ret < 0)
goto error;
*/
dev->ops->enable_qp(dev, 0, 1);
+ dev->started = true;
+ pthread_mutex_unlock(&dev->mutex);
+ rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+
return 0;
error:
+ pthread_mutex_unlock(&dev->mutex);
+ rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
/* TODO: free resource here or caller to check */
return -1;
}
{
uint32_t i;
- for (i = 0; i < dev->max_queue_pairs * 2; ++i) {
- close(dev->callfds[i]);
- close(dev->kickfds[i]);
- }
-
+ pthread_mutex_lock(&dev->mutex);
for (i = 0; i < dev->max_queue_pairs; ++i)
dev->ops->enable_qp(dev, i, 0);
- free(dev->ifname);
- dev->ifname = NULL;
+ if (dev->ops->send_request(dev, VHOST_USER_RESET_OWNER, NULL) < 0) {
+ PMD_DRV_LOG(INFO, "Failed to reset the device\n");
+ pthread_mutex_unlock(&dev->mutex);
+ return -1;
+ }
+ dev->started = false;
+ pthread_mutex_unlock(&dev->mutex);
return 0;
}
}
static int
-is_vhost_user_by_type(const char *path)
+virtio_user_dev_init_notify(struct virtio_user_dev *dev)
{
- struct stat sb;
+ uint32_t i, j;
+ int callfd;
+ int kickfd;
- if (stat(path, &sb) == -1)
- return 0;
+ for (i = 0; i < VIRTIO_MAX_VIRTQUEUES; ++i) {
+ if (i >= dev->max_queue_pairs * 2) {
+ dev->kickfds[i] = -1;
+ dev->callfds[i] = -1;
+ continue;
+ }
- return S_ISSOCK(sb.st_mode);
+ /* May use invalid flag, but some backend uses kickfd and
+ * callfd as criteria to judge if dev is alive. so finally we
+ * use real event_fd.
+ */
+ callfd = eventfd(0, EFD_CLOEXEC | EFD_NONBLOCK);
+ if (callfd < 0) {
+ PMD_DRV_LOG(ERR, "callfd error, %s", strerror(errno));
+ break;
+ }
+ kickfd = eventfd(0, EFD_CLOEXEC | EFD_NONBLOCK);
+ if (kickfd < 0) {
+ PMD_DRV_LOG(ERR, "kickfd error, %s", strerror(errno));
+ break;
+ }
+ dev->callfds[i] = callfd;
+ dev->kickfds[i] = kickfd;
+ }
+
+ if (i < VIRTIO_MAX_VIRTQUEUES) {
+ for (j = 0; j <= i; ++j) {
+ close(dev->callfds[j]);
+ close(dev->kickfds[j]);
+ }
+
+ return -1;
+ }
+
+ return 0;
}
static int
-virtio_user_dev_setup(struct virtio_user_dev *dev)
+virtio_user_fill_intr_handle(struct virtio_user_dev *dev)
{
- uint32_t i, q;
+ uint32_t i;
+ struct rte_eth_dev *eth_dev = &rte_eth_devices[dev->port_id];
- dev->vhostfd = -1;
- for (i = 0; i < VIRTIO_MAX_VIRTQUEUES * 2 + 1; ++i) {
- dev->kickfds[i] = -1;
- dev->callfds[i] = -1;
+ if (!eth_dev->intr_handle) {
+ eth_dev->intr_handle = malloc(sizeof(*eth_dev->intr_handle));
+ if (!eth_dev->intr_handle) {
+ PMD_DRV_LOG(ERR, "fail to allocate intr_handle");
+ return -1;
+ }
+ memset(eth_dev->intr_handle, 0, sizeof(*eth_dev->intr_handle));
}
+ for (i = 0; i < dev->max_queue_pairs; ++i)
+ eth_dev->intr_handle->efds[i] = dev->callfds[i];
+ eth_dev->intr_handle->nb_efd = dev->max_queue_pairs;
+ eth_dev->intr_handle->max_intr = dev->max_queue_pairs + 1;
+ eth_dev->intr_handle->type = RTE_INTR_HANDLE_VDEV;
+ /* For virtio vdev, no need to read counter for clean */
+ eth_dev->intr_handle->efd_counter_size = 0;
+ eth_dev->intr_handle->fd = -1;
+ if (dev->vhostfd >= 0)
+ eth_dev->intr_handle->fd = dev->vhostfd;
+ else if (dev->is_server)
+ eth_dev->intr_handle->fd = dev->listenfd;
+
+ return 0;
+}
+
+static void
+virtio_user_mem_event_cb(enum rte_mem_event type __rte_unused,
+ const void *addr __rte_unused,
+ size_t len __rte_unused,
+ void *arg)
+{
+ struct virtio_user_dev *dev = arg;
+ struct rte_memseg_list *msl;
+ uint16_t i;
+
+ /* ignore externally allocated memory */
+ msl = rte_mem_virt2memseg_list(addr);
+ if (msl->external)
+ return;
+
+ pthread_mutex_lock(&dev->mutex);
+
+ if (dev->started == false)
+ goto exit;
+
+ /* Step 1: pause the active queues */
+ for (i = 0; i < dev->queue_pairs; i++)
+ dev->ops->enable_qp(dev, i, 0);
+
+ /* Step 2: update memory regions */
+ dev->ops->send_request(dev, VHOST_USER_SET_MEM_TABLE, NULL);
+
+ /* Step 3: resume the active queues */
+ for (i = 0; i < dev->queue_pairs; i++)
+ dev->ops->enable_qp(dev, i, 1);
+
+exit:
+ pthread_mutex_unlock(&dev->mutex);
+}
+
+static int
+virtio_user_dev_setup(struct virtio_user_dev *dev)
+{
+ uint32_t q;
+
+ dev->vhostfd = -1;
dev->vhostfds = NULL;
dev->tapfds = NULL;
- if (is_vhost_user_by_type(dev->path)) {
- dev->ops = &ops_user;
- } else {
- dev->ops = &ops_kernel;
-
- dev->vhostfds = malloc(dev->max_queue_pairs * sizeof(int));
- dev->tapfds = malloc(dev->max_queue_pairs * sizeof(int));
- if (!dev->vhostfds || !dev->tapfds) {
- PMD_INIT_LOG(ERR, "Failed to malloc");
+ if (dev->is_server) {
+ if (access(dev->path, F_OK) == 0 &&
+ !is_vhost_user_by_type(dev->path)) {
+ PMD_DRV_LOG(ERR, "Server mode doesn't support vhost-kernel!");
return -1;
}
-
- for (q = 0; q < dev->max_queue_pairs; ++q) {
- dev->vhostfds[q] = -1;
- dev->tapfds[q] = -1;
+ dev->ops = &virtio_ops_user;
+ } else {
+ if (is_vhost_user_by_type(dev->path)) {
+ dev->ops = &virtio_ops_user;
+ } else {
+ dev->ops = &virtio_ops_kernel;
+
+ dev->vhostfds = malloc(dev->max_queue_pairs *
+ sizeof(int));
+ dev->tapfds = malloc(dev->max_queue_pairs *
+ sizeof(int));
+ if (!dev->vhostfds || !dev->tapfds) {
+ PMD_INIT_LOG(ERR, "Failed to malloc");
+ return -1;
+ }
+
+ for (q = 0; q < dev->max_queue_pairs; ++q) {
+ dev->vhostfds[q] = -1;
+ dev->tapfds[q] = -1;
+ }
}
}
- return dev->ops->setup(dev);
+ if (dev->ops->setup(dev) < 0)
+ return -1;
+
+ if (virtio_user_dev_init_notify(dev) < 0)
+ return -1;
+
+ if (virtio_user_fill_intr_handle(dev) < 0)
+ return -1;
+
+ return 0;
}
+/* Use below macro to filter features from vhost backend */
+#define VIRTIO_USER_SUPPORTED_FEATURES \
+ (1ULL << VIRTIO_NET_F_MAC | \
+ 1ULL << VIRTIO_NET_F_STATUS | \
+ 1ULL << VIRTIO_NET_F_MQ | \
+ 1ULL << VIRTIO_NET_F_CTRL_MAC_ADDR | \
+ 1ULL << VIRTIO_NET_F_CTRL_VQ | \
+ 1ULL << VIRTIO_NET_F_CTRL_RX | \
+ 1ULL << VIRTIO_NET_F_CTRL_VLAN | \
+ 1ULL << VIRTIO_NET_F_CSUM | \
+ 1ULL << VIRTIO_NET_F_HOST_TSO4 | \
+ 1ULL << VIRTIO_NET_F_HOST_TSO6 | \
+ 1ULL << VIRTIO_NET_F_MRG_RXBUF | \
+ 1ULL << VIRTIO_RING_F_INDIRECT_DESC | \
+ 1ULL << VIRTIO_NET_F_GUEST_CSUM | \
+ 1ULL << VIRTIO_NET_F_GUEST_TSO4 | \
+ 1ULL << VIRTIO_NET_F_GUEST_TSO6 | \
+ 1ULL << VIRTIO_F_IN_ORDER | \
+ 1ULL << VIRTIO_F_VERSION_1)
+
int
virtio_user_dev_init(struct virtio_user_dev *dev, char *path, int queues,
- int cq, int queue_size, const char *mac)
+ int cq, int queue_size, const char *mac, char **ifname,
+ int mrg_rxbuf, int in_order)
{
+ pthread_mutex_init(&dev->mutex, NULL);
snprintf(dev->path, PATH_MAX, "%s", path);
+ dev->started = 0;
dev->max_queue_pairs = queues;
dev->queue_pairs = 1; /* mq disabled by default */
dev->queue_size = queue_size;
dev->mac_specified = 0;
+ dev->unsupported_features = 0;
parse_mac(dev, mac);
+ if (*ifname) {
+ dev->ifname = *ifname;
+ *ifname = NULL;
+ }
+
if (virtio_user_dev_setup(dev) < 0) {
PMD_INIT_LOG(ERR, "backend set up fails");
return -1;
}
- if (dev->ops->send_request(dev, VHOST_USER_SET_OWNER, NULL) < 0) {
- PMD_INIT_LOG(ERR, "set_owner fails: %s", strerror(errno));
- return -1;
+
+ if (!dev->is_server) {
+ if (dev->ops->send_request(dev, VHOST_USER_SET_OWNER,
+ NULL) < 0) {
+ PMD_INIT_LOG(ERR, "set_owner fails: %s",
+ strerror(errno));
+ return -1;
+ }
+
+ if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
+ &dev->device_features) < 0) {
+ PMD_INIT_LOG(ERR, "get_features failed: %s",
+ strerror(errno));
+ return -1;
+ }
+ } else {
+ /* We just pretend vhost-user can support all these features.
+ * Note that this could be problematic that if some feature is
+ * negotiated but not supported by the vhost-user which comes
+ * later.
+ */
+ dev->device_features = VIRTIO_USER_SUPPORTED_FEATURES;
}
- if (dev->ops->send_request(dev, VHOST_USER_GET_FEATURES,
- &dev->device_features) < 0) {
- PMD_INIT_LOG(ERR, "get_features failed: %s", strerror(errno));
- return -1;
+ if (!mrg_rxbuf) {
+ dev->device_features &= ~(1ull << VIRTIO_NET_F_MRG_RXBUF);
+ dev->unsupported_features |= (1ull << VIRTIO_NET_F_MRG_RXBUF);
+ }
+
+ if (!in_order) {
+ dev->device_features &= ~(1ull << VIRTIO_F_IN_ORDER);
+ dev->unsupported_features |= (1ull << VIRTIO_F_IN_ORDER);
}
- if (dev->mac_specified)
+
+ if (dev->mac_specified) {
dev->device_features |= (1ull << VIRTIO_NET_F_MAC);
+ } else {
+ dev->device_features &= ~(1ull << VIRTIO_NET_F_MAC);
+ dev->unsupported_features |= (1ull << VIRTIO_NET_F_MAC);
+ }
if (cq) {
/* device does not really need to know anything about CQ,
dev->device_features &= ~(1ull << VIRTIO_NET_F_GUEST_ANNOUNCE);
dev->device_features &= ~(1ull << VIRTIO_NET_F_MQ);
dev->device_features &= ~(1ull << VIRTIO_NET_F_CTRL_MAC_ADDR);
+ dev->unsupported_features |= (1ull << VIRTIO_NET_F_CTRL_VQ);
+ dev->unsupported_features |= (1ull << VIRTIO_NET_F_CTRL_RX);
+ dev->unsupported_features |= (1ull << VIRTIO_NET_F_CTRL_VLAN);
+ dev->unsupported_features |=
+ (1ull << VIRTIO_NET_F_GUEST_ANNOUNCE);
+ dev->unsupported_features |= (1ull << VIRTIO_NET_F_MQ);
+ dev->unsupported_features |=
+ (1ull << VIRTIO_NET_F_CTRL_MAC_ADDR);
+ }
+
+ /* The backend will not report this feature, we add it explicitly */
+ if (is_vhost_user_by_type(dev->path))
+ dev->device_features |= (1ull << VIRTIO_NET_F_STATUS);
+
+ dev->device_features &= VIRTIO_USER_SUPPORTED_FEATURES;
+ dev->unsupported_features |= ~VIRTIO_USER_SUPPORTED_FEATURES;
+
+ if (rte_mem_event_callback_register(VIRTIO_USER_MEM_EVENT_CLB_NAME,
+ virtio_user_mem_event_cb, dev)) {
+ if (rte_errno != ENOTSUP) {
+ PMD_INIT_LOG(ERR, "Failed to register mem event"
+ " callback\n");
+ return -1;
+ }
}
return 0;
virtio_user_stop_device(dev);
+ rte_mem_event_callback_unregister(VIRTIO_USER_MEM_EVENT_CLB_NAME, dev);
+
+ for (i = 0; i < dev->max_queue_pairs * 2; ++i) {
+ close(dev->callfds[i]);
+ close(dev->kickfds[i]);
+ }
+
close(dev->vhostfd);
+ if (dev->is_server && dev->listenfd >= 0) {
+ close(dev->listenfd);
+ dev->listenfd = -1;
+ }
+
if (dev->vhostfds) {
for (i = 0; i < dev->max_queue_pairs; ++i)
close(dev->vhostfds[i]);
free(dev->vhostfds);
free(dev->tapfds);
}
+
+ free(dev->ifname);
+
+ if (dev->is_server)
+ unlink(dev->path);
}
-static uint8_t
+uint8_t
virtio_user_handle_mq(struct virtio_user_dev *dev, uint16_t q_pairs)
{
uint16_t i;
return -1;
}
- for (i = 0; i < q_pairs; ++i)
- ret |= dev->ops->enable_qp(dev, i, 1);
- for (i = q_pairs; i < dev->max_queue_pairs; ++i)
- ret |= dev->ops->enable_qp(dev, i, 0);
-
+ /* Server mode can't enable queue pairs if vhostfd is invalid,
+ * always return 0 in this case.
+ */
+ if (!dev->is_server || dev->vhostfd >= 0) {
+ for (i = 0; i < q_pairs; ++i)
+ ret |= dev->ops->enable_qp(dev, i, 1);
+ for (i = q_pairs; i < dev->max_queue_pairs; ++i)
+ ret |= dev->ops->enable_qp(dev, i, 0);
+ }
dev->queue_pairs = q_pairs;
return ret;