* Copyright 2019 Mellanox Technologies, Ltd
*/
#include <unistd.h>
+#include <net/if.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <netinet/in.h>
#include <rte_malloc.h>
#include <rte_log.h>
#include <rte_errno.h>
+#include <rte_string_fns.h>
#include <rte_bus_pci.h>
-#include <rte_pci.h>
+#include <rte_eal_paging.h>
#include <mlx5_glue.h>
#include <mlx5_common.h>
+#include <mlx5_common_defs.h>
#include <mlx5_devx_cmds.h>
#include <mlx5_prm.h>
#include <mlx5_nl.h>
#include "mlx5_vdpa_utils.h"
#include "mlx5_vdpa.h"
+#define MLX5_VDPA_DRIVER_NAME vdpa_mlx5
#define MLX5_VDPA_DEFAULT_FEATURES ((1ULL << VHOST_USER_F_PROTOCOL_FEATURES) | \
(1ULL << VIRTIO_F_ANY_LAYOUT) | \
(1ULL << VIRTIO_NET_F_MQ) | \
(1ULL << VIRTIO_NET_F_GUEST_ANNOUNCE) | \
(1ULL << VIRTIO_F_ORDER_PLATFORM) | \
- (1ULL << VHOST_F_LOG_ALL))
+ (1ULL << VHOST_F_LOG_ALL) | \
+ (1ULL << VIRTIO_NET_F_MTU))
#define MLX5_VDPA_PROTOCOL_FEATURES \
((1ULL << VHOST_USER_PROTOCOL_F_SLAVE_REQ) | \
(1ULL << VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD) | \
(1ULL << VHOST_USER_PROTOCOL_F_HOST_NOTIFIER) | \
(1ULL << VHOST_USER_PROTOCOL_F_LOG_SHMFD) | \
- (1ULL << VHOST_USER_PROTOCOL_F_MQ))
+ (1ULL << VHOST_USER_PROTOCOL_F_MQ) | \
+ (1ULL << VHOST_USER_PROTOCOL_F_NET_MTU) | \
+ (1ULL << VHOST_USER_PROTOCOL_F_STATUS))
+
+#define MLX5_VDPA_DEFAULT_NO_TRAFFIC_MAX 16LLU
TAILQ_HEAD(mlx5_vdpa_privs, mlx5_vdpa_priv) priv_list =
TAILQ_HEAD_INITIALIZER(priv_list);
static pthread_mutex_t priv_list_lock = PTHREAD_MUTEX_INITIALIZER;
-int mlx5_vdpa_logtype;
+
+struct mlx5_vdpa_conf_thread_mng conf_thread_mng;
+
+static void mlx5_vdpa_dev_release(struct mlx5_vdpa_priv *priv);
static struct mlx5_vdpa_priv *
-mlx5_vdpa_find_priv_resource_by_did(int did)
+mlx5_vdpa_find_priv_resource_by_vdev(struct rte_vdpa_device *vdev)
{
struct mlx5_vdpa_priv *priv;
int found = 0;
pthread_mutex_lock(&priv_list_lock);
TAILQ_FOREACH(priv, &priv_list, next) {
- if (did == priv->id) {
+ if (vdev == priv->vdev) {
found = 1;
break;
}
}
pthread_mutex_unlock(&priv_list_lock);
if (!found) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
rte_errno = EINVAL;
return NULL;
}
}
static int
-mlx5_vdpa_get_queue_num(int did, uint32_t *queue_num)
+mlx5_vdpa_get_queue_num(struct rte_vdpa_device *vdev, uint32_t *queue_num)
{
- struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
if (priv == NULL) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -1;
}
- *queue_num = priv->caps.max_num_virtio_queues;
+ *queue_num = priv->caps.max_num_virtio_queues / 2;
return 0;
}
static int
-mlx5_vdpa_get_vdpa_features(int did, uint64_t *features)
+mlx5_vdpa_get_vdpa_features(struct rte_vdpa_device *vdev, uint64_t *features)
{
- struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
if (priv == NULL) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -1;
}
*features = MLX5_VDPA_DEFAULT_FEATURES;
}
static int
-mlx5_vdpa_get_protocol_features(int did, uint64_t *features)
+mlx5_vdpa_get_protocol_features(struct rte_vdpa_device *vdev,
+ uint64_t *features)
{
- struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
if (priv == NULL) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -1;
}
*features = MLX5_VDPA_PROTOCOL_FEATURES;
static int
mlx5_vdpa_set_vring_state(int vid, int vring, int state)
{
- int did = rte_vhost_get_vdpa_device_id(vid);
- struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
- struct mlx5_vdpa_virtq *virtq = NULL;
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
+ struct mlx5_vdpa_virtq *virtq;
+ int ret;
if (priv == NULL) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -EINVAL;
}
- SLIST_FOREACH(virtq, &priv->virtq_list, next)
- if (virtq->index == vring)
- break;
- if (!virtq) {
- DRV_LOG(ERR, "Invalid or unconfigured vring id: %d.", vring);
- return -EINVAL;
+ if (vring >= (int)priv->caps.max_num_virtio_queues) {
+ DRV_LOG(ERR, "Too big vring id: %d.", vring);
+ return -E2BIG;
}
- return mlx5_vdpa_virtq_enable(virtq, state);
+ virtq = &priv->virtqs[vring];
+ pthread_mutex_lock(&virtq->virtq_lock);
+ ret = mlx5_vdpa_virtq_enable(priv, vring, state);
+ pthread_mutex_unlock(&virtq->virtq_lock);
+ return ret;
}
static int
mlx5_vdpa_features_set(int vid)
{
- int did = rte_vhost_get_vdpa_device_id(vid);
- struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
uint64_t log_base, log_size;
uint64_t features;
int ret;
if (priv == NULL) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -EINVAL;
}
ret = rte_vhost_get_negotiated_features(vid, &features);
return 0;
}
+static int
+mlx5_vdpa_mtu_set(struct mlx5_vdpa_priv *priv)
+{
+ struct ifreq request;
+ uint16_t vhost_mtu = 0;
+ uint16_t kern_mtu = 0;
+ int ret = rte_vhost_get_mtu(priv->vid, &vhost_mtu);
+ int sock;
+ int retries = MLX5_VDPA_MAX_RETRIES;
+
+ if (ret) {
+ DRV_LOG(DEBUG, "Cannot get vhost MTU - %d.", ret);
+ return ret;
+ }
+ if (!vhost_mtu) {
+ DRV_LOG(DEBUG, "Vhost MTU is 0.");
+ return ret;
+ }
+ ret = mlx5_get_ifname_sysfs
+ (mlx5_os_get_ctx_device_name(priv->cdev->ctx),
+ request.ifr_name);
+ if (ret) {
+ DRV_LOG(DEBUG, "Cannot get kernel IF name - %d.", ret);
+ return ret;
+ }
+ sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
+ if (sock == -1) {
+ DRV_LOG(DEBUG, "Cannot open IF socket.");
+ return sock;
+ }
+ while (retries--) {
+ ret = ioctl(sock, SIOCGIFMTU, &request);
+ if (ret == -1)
+ break;
+ kern_mtu = request.ifr_mtu;
+ DRV_LOG(DEBUG, "MTU: current %d requested %d.", (int)kern_mtu,
+ (int)vhost_mtu);
+ if (kern_mtu == vhost_mtu)
+ break;
+ request.ifr_mtu = vhost_mtu;
+ ret = ioctl(sock, SIOCSIFMTU, &request);
+ if (ret == -1)
+ break;
+ request.ifr_mtu = 0;
+ usleep(MLX5_VDPA_USEC);
+ }
+ close(sock);
+ return kern_mtu == vhost_mtu ? 0 : -1;
+}
+
+static void
+mlx5_vdpa_dev_cache_clean(struct mlx5_vdpa_priv *priv)
+{
+ /* Clean pre-created resource in dev removal only. */
+ if (!priv->queues)
+ mlx5_vdpa_virtqs_cleanup(priv);
+ mlx5_vdpa_mem_dereg(priv);
+}
+
static int
mlx5_vdpa_dev_close(int vid)
{
- int did = rte_vhost_get_vdpa_device_id(vid);
- struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
int ret = 0;
if (priv == NULL) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -1;
}
- if (priv->configured)
- ret |= mlx5_vdpa_lm_log(priv);
mlx5_vdpa_cqe_event_unset(priv);
- ret |= mlx5_vdpa_steer_unset(priv);
+ if (priv->state == MLX5_VDPA_STATE_CONFIGURED) {
+ ret |= mlx5_vdpa_lm_log(priv);
+ priv->state = MLX5_VDPA_STATE_IN_PROGRESS;
+ }
+ pthread_mutex_lock(&priv->steer_update_lock);
+ mlx5_vdpa_steer_unset(priv);
+ pthread_mutex_unlock(&priv->steer_update_lock);
mlx5_vdpa_virtqs_release(priv);
- mlx5_vdpa_event_qp_global_release(priv);
- mlx5_vdpa_mem_dereg(priv);
- priv->configured = 0;
+ mlx5_vdpa_drain_cq(priv);
+ if (priv->lm_mr.addr)
+ mlx5_os_wrapped_mkey_destroy(&priv->lm_mr);
+ priv->state = MLX5_VDPA_STATE_PROBED;
+ if (!priv->connected)
+ mlx5_vdpa_dev_cache_clean(priv);
priv->vid = 0;
+ DRV_LOG(INFO, "vDPA device %d was closed.", vid);
return ret;
}
static int
mlx5_vdpa_dev_config(int vid)
{
- int did = rte_vhost_get_vdpa_device_id(vid);
- struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
if (priv == NULL) {
- DRV_LOG(ERR, "Invalid device id: %d.", did);
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
return -EINVAL;
}
- if (priv->configured && mlx5_vdpa_dev_close(vid)) {
+ if (priv->state == MLX5_VDPA_STATE_CONFIGURED &&
+ mlx5_vdpa_dev_close(vid)) {
DRV_LOG(ERR, "Failed to reconfigure vid %d.", vid);
return -1;
}
priv->vid = vid;
- if (mlx5_vdpa_mem_register(priv) || mlx5_vdpa_virtqs_prepare(priv) ||
- mlx5_vdpa_steer_setup(priv) || mlx5_vdpa_cqe_event_setup(priv)) {
+ priv->connected = true;
+ if (mlx5_vdpa_mtu_set(priv))
+ DRV_LOG(WARNING, "MTU cannot be set on device %s.",
+ vdev->device->name);
+ if (mlx5_vdpa_mem_register(priv) ||
+ mlx5_vdpa_virtqs_prepare(priv) || mlx5_vdpa_steer_setup(priv) ||
+ mlx5_vdpa_cqe_event_setup(priv)) {
mlx5_vdpa_dev_close(vid);
return -1;
}
- priv->configured = 1;
+ priv->state = MLX5_VDPA_STATE_CONFIGURED;
+ DRV_LOG(INFO, "vDPA device %d was configured.", vid);
return 0;
}
-static struct rte_vdpa_dev_ops mlx5_vdpa_ops = {
- .get_queue_num = mlx5_vdpa_get_queue_num,
- .get_features = mlx5_vdpa_get_vdpa_features,
- .get_protocol_features = mlx5_vdpa_get_protocol_features,
- .dev_conf = mlx5_vdpa_dev_config,
- .dev_close = mlx5_vdpa_dev_close,
- .set_vring_state = mlx5_vdpa_set_vring_state,
- .set_features = mlx5_vdpa_features_set,
- .migration_done = NULL,
- .get_vfio_group_fd = NULL,
- .get_vfio_device_fd = NULL,
- .get_notify_area = NULL,
-};
-
-static struct ibv_device *
-mlx5_vdpa_get_ib_device_match(struct rte_pci_addr *addr)
+static int
+mlx5_vdpa_get_device_fd(int vid)
{
- int n;
- struct ibv_device **ibv_list = mlx5_glue->get_device_list(&n);
- struct ibv_device *ibv_match = NULL;
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
- if (!ibv_list) {
- rte_errno = ENOSYS;
- return NULL;
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
+ return -EINVAL;
}
- while (n-- > 0) {
- struct rte_pci_addr pci_addr;
+ return ((struct ibv_context *)priv->cdev->ctx)->cmd_fd;
+}
- DRV_LOG(DEBUG, "Checking device \"%s\"..", ibv_list[n]->name);
- if (mlx5_dev_to_pci_addr(ibv_list[n]->ibdev_path, &pci_addr))
- continue;
- if (memcmp(addr, &pci_addr, sizeof(pci_addr)))
- continue;
- ibv_match = ibv_list[n];
- break;
+static int
+mlx5_vdpa_get_notify_area(int vid, int qid, uint64_t *offset, uint64_t *size)
+{
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
+
+ RTE_SET_USED(qid);
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
+ return -EINVAL;
}
- if (!ibv_match)
- rte_errno = ENOENT;
- mlx5_glue->free_device_list(ibv_list);
- return ibv_match;
+ if (!priv->var) {
+ DRV_LOG(ERR, "VAR was not created for device %s, is the device"
+ " configured?.", vdev->device->name);
+ return -EINVAL;
+ }
+ *offset = priv->var->mmap_off;
+ *size = priv->var->length;
+ return 0;
}
-/* Try to disable ROCE by Netlink\Devlink. */
static int
-mlx5_vdpa_nl_roce_disable(const char *addr)
+mlx5_vdpa_get_stats_names(struct rte_vdpa_device *vdev,
+ struct rte_vdpa_stat_name *stats_names,
+ unsigned int size)
{
- int nlsk_fd = mlx5_nl_init(NETLINK_GENERIC);
- int devlink_id;
- int enable;
- int ret;
+ static const char *mlx5_vdpa_stats_names[MLX5_VDPA_STATS_MAX] = {
+ "received_descriptors",
+ "completed_descriptors",
+ "bad descriptor errors",
+ "exceed max chain",
+ "invalid buffer",
+ "completion errors",
+ };
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
+ unsigned int i;
- if (nlsk_fd < 0)
- return nlsk_fd;
- devlink_id = mlx5_nl_devlink_family_id_get(nlsk_fd);
- if (devlink_id < 0) {
- ret = devlink_id;
- DRV_LOG(DEBUG, "Failed to get devlink id for ROCE operations by"
- " Netlink.");
- goto close;
- }
- ret = mlx5_nl_enable_roce_get(nlsk_fd, devlink_id, addr, &enable);
- if (ret) {
- DRV_LOG(DEBUG, "Failed to get ROCE enable by Netlink: %d.",
- ret);
- goto close;
- } else if (!enable) {
- DRV_LOG(INFO, "ROCE has already disabled(Netlink).");
- goto close;
- }
- ret = mlx5_nl_enable_roce_set(nlsk_fd, devlink_id, addr, 0);
- if (ret)
- DRV_LOG(DEBUG, "Failed to disable ROCE by Netlink: %d.", ret);
- else
- DRV_LOG(INFO, "ROCE is disabled by Netlink successfully.");
-close:
- close(nlsk_fd);
- return ret;
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device: %s.", vdev->device->name);
+ return -ENODEV;
+ }
+ if (!stats_names)
+ return MLX5_VDPA_STATS_MAX;
+ size = RTE_MIN(size, (unsigned int)MLX5_VDPA_STATS_MAX);
+ for (i = 0; i < size; ++i)
+ strlcpy(stats_names[i].name, mlx5_vdpa_stats_names[i],
+ RTE_VDPA_STATS_NAME_SIZE);
+ return size;
}
-/* Try to disable ROCE by sysfs. */
static int
-mlx5_vdpa_sys_roce_disable(const char *addr)
+mlx5_vdpa_get_stats(struct rte_vdpa_device *vdev, int qid,
+ struct rte_vdpa_stat *stats, unsigned int n)
{
- FILE *file_o;
- int enable;
- int ret;
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
- MKSTR(file_p, "/sys/bus/pci/devices/%s/roce_enable", addr);
- file_o = fopen(file_p, "rb");
- if (!file_o) {
- rte_errno = ENOTSUP;
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device: %s.", vdev->device->name);
+ return -ENODEV;
+ }
+ if (qid >= (int)priv->caps.max_num_virtio_queues) {
+ DRV_LOG(ERR, "Too big vring id: %d for device %s.", qid,
+ vdev->device->name);
+ return -E2BIG;
+ }
+ if (!priv->caps.queue_counters_valid) {
+ DRV_LOG(ERR, "Virtq statistics is not supported for device %s.",
+ vdev->device->name);
return -ENOTSUP;
}
- ret = fscanf(file_o, "%d", &enable);
- if (ret != 1) {
- rte_errno = EINVAL;
- ret = EINVAL;
- goto close;
- } else if (!enable) {
- ret = 0;
- DRV_LOG(INFO, "ROCE has already disabled(sysfs).");
- goto close;
- }
- fclose(file_o);
- file_o = fopen(file_p, "wb");
- if (!file_o) {
- rte_errno = ENOTSUP;
+ return mlx5_vdpa_virtq_stats_get(priv, qid, stats, n);
+}
+
+static int
+mlx5_vdpa_reset_stats(struct rte_vdpa_device *vdev, int qid)
+{
+ struct mlx5_vdpa_priv *priv =
+ mlx5_vdpa_find_priv_resource_by_vdev(vdev);
+
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device: %s.", vdev->device->name);
+ return -ENODEV;
+ }
+ if (qid >= (int)priv->caps.max_num_virtio_queues) {
+ DRV_LOG(ERR, "Too big vring id: %d for device %s.", qid,
+ vdev->device->name);
+ return -E2BIG;
+ }
+ if (!priv->caps.queue_counters_valid) {
+ DRV_LOG(ERR, "Virtq statistics is not supported for device %s.",
+ vdev->device->name);
return -ENOTSUP;
}
- fprintf(file_o, "0\n");
- ret = 0;
-close:
- if (ret)
- DRV_LOG(DEBUG, "Failed to disable ROCE by sysfs: %d.", ret);
- else
- DRV_LOG(INFO, "ROCE is disabled by sysfs successfully.");
- fclose(file_o);
- return ret;
+ return mlx5_vdpa_virtq_stats_reset(priv, qid);
}
-#define MLX5_VDPA_MAX_RETRIES 20
-#define MLX5_VDPA_USEC 1000
static int
-mlx5_vdpa_roce_disable(struct rte_pci_addr *addr, struct ibv_device **ibv)
+mlx5_vdpa_dev_cleanup(int vid)
{
- char addr_name[64] = {0};
-
- rte_pci_device_name(addr, addr_name, sizeof(addr_name));
- /* Firstly try to disable ROCE by Netlink and fallback to sysfs. */
- if (mlx5_vdpa_nl_roce_disable(addr_name) == 0 ||
- mlx5_vdpa_sys_roce_disable(addr_name) == 0) {
- /*
- * Succeed to disable ROCE, wait for the IB device to appear
- * again after reload.
- */
- int r;
- struct ibv_device *ibv_new;
-
- for (r = MLX5_VDPA_MAX_RETRIES; r; r--) {
- ibv_new = mlx5_vdpa_get_ib_device_match(addr);
- if (ibv_new) {
- *ibv = ibv_new;
- return 0;
+ struct rte_vdpa_device *vdev = rte_vhost_get_vdpa_device(vid);
+ struct mlx5_vdpa_priv *priv;
+
+ if (vdev == NULL)
+ return -1;
+ priv = mlx5_vdpa_find_priv_resource_by_vdev(vdev);
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid vDPA device: %s.", vdev->device->name);
+ return -1;
+ }
+ if (priv->state == MLX5_VDPA_STATE_PROBED)
+ mlx5_vdpa_dev_cache_clean(priv);
+ priv->connected = false;
+ return 0;
+}
+
+static struct rte_vdpa_dev_ops mlx5_vdpa_ops = {
+ .get_queue_num = mlx5_vdpa_get_queue_num,
+ .get_features = mlx5_vdpa_get_vdpa_features,
+ .get_protocol_features = mlx5_vdpa_get_protocol_features,
+ .dev_conf = mlx5_vdpa_dev_config,
+ .dev_close = mlx5_vdpa_dev_close,
+ .dev_cleanup = mlx5_vdpa_dev_cleanup,
+ .set_vring_state = mlx5_vdpa_set_vring_state,
+ .set_features = mlx5_vdpa_features_set,
+ .migration_done = NULL,
+ .get_vfio_group_fd = NULL,
+ .get_vfio_device_fd = mlx5_vdpa_get_device_fd,
+ .get_notify_area = mlx5_vdpa_get_notify_area,
+ .get_stats_names = mlx5_vdpa_get_stats_names,
+ .get_stats = mlx5_vdpa_get_stats,
+ .reset_stats = mlx5_vdpa_reset_stats,
+};
+
+static int
+mlx5_vdpa_args_check_handler(const char *key, const char *val, void *opaque)
+{
+ struct mlx5_vdpa_priv *priv = opaque;
+ unsigned long tmp;
+ int n_cores = sysconf(_SC_NPROCESSORS_ONLN);
+
+ errno = 0;
+ tmp = strtoul(val, NULL, 0);
+ if (errno) {
+ DRV_LOG(WARNING, "%s: \"%s\" is an invalid integer.", key, val);
+ return -errno;
+ }
+ if (strcmp(key, "event_mode") == 0) {
+ if (tmp <= MLX5_VDPA_EVENT_MODE_ONLY_INTERRUPT)
+ priv->event_mode = (int)tmp;
+ else
+ DRV_LOG(WARNING, "Invalid event_mode %s.", val);
+ } else if (strcmp(key, "event_us") == 0) {
+ priv->event_us = (uint32_t)tmp;
+ } else if (strcmp(key, "no_traffic_time") == 0) {
+ priv->no_traffic_max = (uint32_t)tmp;
+ } else if (strcmp(key, "event_core") == 0) {
+ if (tmp >= (unsigned long)n_cores)
+ DRV_LOG(WARNING, "Invalid event_core %s.", val);
+ else
+ priv->event_core = tmp;
+ } else if (strcmp(key, "max_conf_threads") == 0) {
+ if (tmp) {
+ priv->use_c_thread = true;
+ if (!conf_thread_mng.initializer_priv) {
+ conf_thread_mng.initializer_priv = priv;
+ if (tmp > MLX5_VDPA_MAX_C_THRD) {
+ DRV_LOG(WARNING,
+ "Invalid max_conf_threads %s "
+ "and set max_conf_threads to %d",
+ val, MLX5_VDPA_MAX_C_THRD);
+ tmp = MLX5_VDPA_MAX_C_THRD;
+ }
+ conf_thread_mng.max_thrds = tmp;
+ } else if (tmp != conf_thread_mng.max_thrds) {
+ DRV_LOG(WARNING,
+ "max_conf_threads is PMD argument and not per device, "
+ "only the first device configuration set it, current value is %d "
+ "and will not be changed to %d.",
+ conf_thread_mng.max_thrds, (int)tmp);
}
- usleep(MLX5_VDPA_USEC);
+ } else {
+ priv->use_c_thread = false;
}
- DRV_LOG(ERR, "Cannot much device %s after ROCE disable, "
- "retries exceed %d", addr_name, MLX5_VDPA_MAX_RETRIES);
- rte_errno = EAGAIN;
+ } else if (strcmp(key, "hw_latency_mode") == 0) {
+ priv->hw_latency_mode = (uint32_t)tmp;
+ } else if (strcmp(key, "hw_max_latency_us") == 0) {
+ priv->hw_max_latency_us = (uint32_t)tmp;
+ } else if (strcmp(key, "hw_max_pending_comp") == 0) {
+ priv->hw_max_pending_comp = (uint32_t)tmp;
+ } else if (strcmp(key, "queue_size") == 0) {
+ priv->queue_size = (uint16_t)tmp;
+ } else if (strcmp(key, "queues") == 0) {
+ priv->queues = (uint16_t)tmp;
+ } else {
+ DRV_LOG(WARNING, "Invalid key %s.", key);
}
- return -rte_errno;
+ return 0;
+}
+
+static void
+mlx5_vdpa_config_get(struct mlx5_kvargs_ctrl *mkvlist,
+ struct mlx5_vdpa_priv *priv)
+{
+ const char **params = (const char *[]){
+ "event_core",
+ "event_mode",
+ "event_us",
+ "hw_latency_mode",
+ "hw_max_latency_us",
+ "hw_max_pending_comp",
+ "no_traffic_time",
+ "queue_size",
+ "queues",
+ "max_conf_threads",
+ NULL,
+ };
+
+ priv->event_mode = MLX5_VDPA_EVENT_MODE_FIXED_TIMER;
+ priv->event_us = 0;
+ priv->event_core = -1;
+ priv->no_traffic_max = MLX5_VDPA_DEFAULT_NO_TRAFFIC_MAX;
+ if (mkvlist == NULL)
+ return;
+ mlx5_kvargs_process(mkvlist, params, mlx5_vdpa_args_check_handler,
+ priv);
+ if (!priv->event_us &&
+ priv->event_mode == MLX5_VDPA_EVENT_MODE_DYNAMIC_TIMER)
+ priv->event_us = MLX5_VDPA_DEFAULT_TIMER_STEP_US;
+ if ((priv->queue_size && !priv->queues) ||
+ (!priv->queue_size && priv->queues)) {
+ priv->queue_size = 0;
+ priv->queues = 0;
+ DRV_LOG(WARNING, "Please provide both queue_size and queues.");
+ }
+ DRV_LOG(DEBUG, "event mode is %d.", priv->event_mode);
+ DRV_LOG(DEBUG, "event_us is %u us.", priv->event_us);
+ DRV_LOG(DEBUG, "no traffic max is %u.", priv->no_traffic_max);
+ DRV_LOG(DEBUG, "queues is %u, queue_size is %u.", priv->queues,
+ priv->queue_size);
}
-/**
- * DPDK callback to register a PCI device.
- *
- * This function spawns vdpa device out of a given PCI device.
- *
- * @param[in] pci_drv
- * PCI driver structure (mlx5_vpda_driver).
- * @param[in] pci_dev
- * PCI device information.
- *
- * @return
- * 0 on success, 1 to skip this driver, a negative errno value otherwise
- * and rte_errno is set.
- */
static int
-mlx5_vdpa_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
- struct rte_pci_device *pci_dev __rte_unused)
+mlx5_vdpa_virtq_resource_prepare(struct mlx5_vdpa_priv *priv)
{
- struct ibv_device *ibv;
- struct mlx5_vdpa_priv *priv = NULL;
- struct ibv_context *ctx = NULL;
- struct mlx5_hca_attr attr;
- int ret;
+ struct mlx5_vdpa_virtq *virtq;
+ uint32_t index;
+ uint32_t i;
+
+ for (index = 0; index < priv->caps.max_num_virtio_queues * 2;
+ index++) {
+ virtq = &priv->virtqs[index];
+ pthread_mutex_init(&virtq->virtq_lock, NULL);
+ }
+ if (!priv->queues)
+ return 0;
+ for (index = 0; index < (priv->queues * 2); ++index) {
+ virtq = &priv->virtqs[index];
+ int ret = mlx5_vdpa_event_qp_prepare(priv, priv->queue_size,
+ -1, virtq);
+
+ if (ret) {
+ DRV_LOG(ERR, "Failed to create event QPs for virtq %d.",
+ index);
+ return -1;
+ }
+ if (priv->caps.queue_counters_valid) {
+ if (!virtq->counters)
+ virtq->counters =
+ mlx5_devx_cmd_create_virtio_q_counters
+ (priv->cdev->ctx);
+ if (!virtq->counters) {
+ DRV_LOG(ERR, "Failed to create virtq couners for virtq"
+ " %d.", index);
+ return -1;
+ }
+ }
+ for (i = 0; i < RTE_DIM(virtq->umems); ++i) {
+ uint32_t size;
+ void *buf;
+ struct mlx5dv_devx_umem *obj;
+
+ size = priv->caps.umems[i].a * priv->queue_size +
+ priv->caps.umems[i].b;
+ buf = rte_zmalloc(__func__, size, 4096);
+ if (buf == NULL) {
+ DRV_LOG(ERR, "Cannot allocate umem %d memory for virtq"
+ " %u.", i, index);
+ return -1;
+ }
+ obj = mlx5_glue->devx_umem_reg(priv->cdev->ctx, buf,
+ size, IBV_ACCESS_LOCAL_WRITE);
+ if (obj == NULL) {
+ rte_free(buf);
+ DRV_LOG(ERR, "Failed to register umem %d for virtq %u.",
+ i, index);
+ return -1;
+ }
+ virtq->umems[i].size = size;
+ virtq->umems[i].buf = buf;
+ virtq->umems[i].obj = obj;
+ }
+ }
+ return 0;
+}
- if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_VDPA) {
- DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5"
- " driver.");
- return 1;
- }
- ibv = mlx5_vdpa_get_ib_device_match(&pci_dev->addr);
- if (!ibv) {
- DRV_LOG(ERR, "No matching IB device for PCI slot "
- PCI_PRI_FMT ".", pci_dev->addr.domain,
- pci_dev->addr.bus, pci_dev->addr.devid,
- pci_dev->addr.function);
+static int
+mlx5_vdpa_create_dev_resources(struct mlx5_vdpa_priv *priv)
+{
+ struct mlx5_devx_tis_attr tis_attr = {0};
+ struct ibv_context *ctx = priv->cdev->ctx;
+ uint32_t i;
+ int retry;
+
+ for (retry = 0; retry < 7; retry++) {
+ priv->var = mlx5_glue->dv_alloc_var(ctx, 0);
+ if (priv->var != NULL)
+ break;
+ DRV_LOG(WARNING, "Failed to allocate VAR, retry %d.", retry);
+ /* Wait Qemu release VAR during vdpa restart, 0.1 sec based. */
+ usleep(100000U << retry);
+ }
+ if (!priv->var) {
+ DRV_LOG(ERR, "Failed to allocate VAR %u.", errno);
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ /* Always map the entire page. */
+ priv->virtq_db_addr = mmap(NULL, priv->var->length, PROT_READ |
+ PROT_WRITE, MAP_SHARED, ctx->cmd_fd,
+ priv->var->mmap_off);
+ if (priv->virtq_db_addr == MAP_FAILED) {
+ DRV_LOG(ERR, "Failed to map doorbell page %u.", errno);
+ priv->virtq_db_addr = NULL;
+ rte_errno = errno;
+ return -rte_errno;
+ }
+ /* Add within page offset for 64K page system. */
+ priv->virtq_db_addr = (char *)priv->virtq_db_addr +
+ ((rte_mem_page_size() - 1) & priv->caps.doorbell_bar_offset);
+ DRV_LOG(DEBUG, "VAR address of doorbell mapping is %p.",
+ priv->virtq_db_addr);
+ priv->td = mlx5_devx_cmd_create_td(ctx);
+ if (!priv->td) {
+ DRV_LOG(ERR, "Failed to create transport domain.");
+ rte_errno = errno;
+ return -rte_errno;
+ }
+ tis_attr.transport_domain = priv->td->id;
+ for (i = 0; i < priv->num_lag_ports; i++) {
+ /* 0 is auto affinity, non-zero value to propose port. */
+ tis_attr.lag_tx_port_affinity = i + 1;
+ priv->tiss[i] = mlx5_devx_cmd_create_tis(ctx, &tis_attr);
+ if (!priv->tiss[i]) {
+ DRV_LOG(ERR, "Failed to create TIS %u.", i);
+ return -rte_errno;
+ }
+ }
+ priv->null_mr = mlx5_glue->alloc_null_mr(priv->cdev->pd);
+ if (!priv->null_mr) {
+ DRV_LOG(ERR, "Failed to allocate null MR.");
+ rte_errno = errno;
return -rte_errno;
- } else {
- DRV_LOG(INFO, "PCI information matches for device \"%s\".",
- ibv->name);
}
- if (mlx5_vdpa_roce_disable(&pci_dev->addr, &ibv) != 0) {
- DRV_LOG(WARNING, "Failed to disable ROCE for \"%s\".",
- ibv->name);
+ DRV_LOG(DEBUG, "Dump fill Mkey = %u.", priv->null_mr->lkey);
+#ifdef HAVE_MLX5DV_DR
+ priv->steer.domain = mlx5_glue->dr_create_domain(ctx,
+ MLX5DV_DR_DOMAIN_TYPE_NIC_RX);
+ if (!priv->steer.domain) {
+ DRV_LOG(ERR, "Failed to create Rx domain.");
+ rte_errno = errno;
return -rte_errno;
}
- ctx = mlx5_glue->dv_open_device(ibv);
- if (!ctx) {
- DRV_LOG(ERR, "Failed to open IB device \"%s\".", ibv->name);
- rte_errno = ENODEV;
+#endif
+ priv->steer.tbl = mlx5_glue->dr_create_flow_tbl(priv->steer.domain, 0);
+ if (!priv->steer.tbl) {
+ DRV_LOG(ERR, "Failed to create table 0 with Rx domain.");
+ rte_errno = errno;
return -rte_errno;
}
- priv = rte_zmalloc("mlx5 vDPA device private", sizeof(*priv),
+ if (mlx5_vdpa_err_event_setup(priv) != 0)
+ return -rte_errno;
+ if (mlx5_vdpa_event_qp_global_prepare(priv))
+ return -rte_errno;
+ if (mlx5_vdpa_virtq_resource_prepare(priv))
+ return -rte_errno;
+ return 0;
+}
+
+static int
+mlx5_vdpa_dev_probe(struct mlx5_common_device *cdev,
+ struct mlx5_kvargs_ctrl *mkvlist)
+{
+ struct mlx5_vdpa_priv *priv = NULL;
+ struct mlx5_hca_attr *attr = &cdev->config.hca_attr;
+
+ if (!attr->vdpa.valid || !attr->vdpa.max_num_virtio_queues) {
+ DRV_LOG(ERR, "Not enough capabilities to support vdpa, maybe "
+ "old FW/OFED version?");
+ rte_errno = ENOTSUP;
+ return -rte_errno;
+ }
+ if (!attr->vdpa.queue_counters_valid)
+ DRV_LOG(DEBUG, "No capability to support virtq statistics.");
+ priv = rte_zmalloc("mlx5 vDPA device private", sizeof(*priv) +
+ sizeof(struct mlx5_vdpa_virtq) *
+ attr->vdpa.max_num_virtio_queues,
RTE_CACHE_LINE_SIZE);
if (!priv) {
DRV_LOG(ERR, "Failed to allocate private memory.");
rte_errno = ENOMEM;
- goto error;
+ return -rte_errno;
}
- ret = mlx5_devx_cmd_query_hca_attr(ctx, &attr);
- if (ret) {
- DRV_LOG(ERR, "Unable to read HCA capabilities.");
- rte_errno = ENOTSUP;
+ priv->caps = attr->vdpa;
+ priv->log_max_rqt_size = attr->log_max_rqt_size;
+ priv->num_lag_ports = attr->num_lag_ports;
+ if (attr->num_lag_ports == 0)
+ priv->num_lag_ports = 1;
+ rte_spinlock_init(&priv->db_lock);
+ pthread_mutex_init(&priv->steer_update_lock, NULL);
+ priv->cdev = cdev;
+ mlx5_vdpa_config_get(mkvlist, priv);
+ if (priv->use_c_thread) {
+ if (conf_thread_mng.initializer_priv == priv)
+ if (mlx5_vdpa_mult_threads_create(priv->event_core))
+ goto error;
+ __atomic_fetch_add(&conf_thread_mng.refcnt, 1,
+ __ATOMIC_RELAXED);
+ }
+ if (mlx5_vdpa_create_dev_resources(priv))
goto error;
- } else {
- if (!attr.vdpa.valid || !attr.vdpa.max_num_virtio_queues) {
- DRV_LOG(ERR, "Not enough capabilities to support vdpa,"
- " maybe old FW/OFED version?");
- rte_errno = ENOTSUP;
- goto error;
- }
- priv->caps = attr.vdpa;
- priv->log_max_rqt_size = attr.log_max_rqt_size;
- }
- priv->ctx = ctx;
- priv->dev_addr.pci_addr = pci_dev->addr;
- priv->dev_addr.type = PCI_ADDR;
- priv->id = rte_vdpa_register_device(&priv->dev_addr, &mlx5_vdpa_ops);
- if (priv->id < 0) {
+ priv->vdev = rte_vdpa_register_device(cdev->dev, &mlx5_vdpa_ops);
+ if (priv->vdev == NULL) {
DRV_LOG(ERR, "Failed to register vDPA device.");
rte_errno = rte_errno ? rte_errno : EINVAL;
goto error;
}
SLIST_INIT(&priv->mr_list);
- SLIST_INIT(&priv->virtq_list);
pthread_mutex_lock(&priv_list_lock);
TAILQ_INSERT_TAIL(&priv_list, priv, next);
pthread_mutex_unlock(&priv_list_lock);
return 0;
-
error:
+ if (conf_thread_mng.initializer_priv == priv)
+ mlx5_vdpa_mult_threads_destroy(false);
if (priv)
- rte_free(priv);
- if (ctx)
- mlx5_glue->close_device(ctx);
+ mlx5_vdpa_dev_release(priv);
return -rte_errno;
}
-/**
- * DPDK callback to remove a PCI device.
- *
- * This function removes all vDPA devices belong to a given PCI device.
- *
- * @param[in] pci_dev
- * Pointer to the PCI device.
- *
- * @return
- * 0 on success, the function cannot fail.
- */
static int
-mlx5_vdpa_pci_remove(struct rte_pci_device *pci_dev)
+mlx5_vdpa_dev_remove(struct mlx5_common_device *cdev)
{
struct mlx5_vdpa_priv *priv = NULL;
int found = 0;
pthread_mutex_lock(&priv_list_lock);
TAILQ_FOREACH(priv, &priv_list, next) {
- if (memcmp(&priv->dev_addr.pci_addr, &pci_dev->addr,
- sizeof(pci_dev->addr)) == 0) {
+ if (priv->vdev->device == cdev->dev) {
found = 1;
break;
}
if (found)
TAILQ_REMOVE(&priv_list, priv, next);
pthread_mutex_unlock(&priv_list_lock);
- if (found) {
- if (priv->configured)
- mlx5_vdpa_dev_close(priv->vid);
- mlx5_glue->close_device(priv->ctx);
- rte_free(priv);
- }
+ if (found)
+ mlx5_vdpa_dev_release(priv);
return 0;
}
+static void
+mlx5_vdpa_release_dev_resources(struct mlx5_vdpa_priv *priv)
+{
+ uint32_t i;
+
+ if (priv->queues)
+ mlx5_vdpa_virtqs_cleanup(priv);
+ mlx5_vdpa_dev_cache_clean(priv);
+ for (i = 0; i < priv->caps.max_num_virtio_queues; i++) {
+ if (!priv->virtqs[i].counters)
+ continue;
+ claim_zero(mlx5_devx_cmd_destroy(priv->virtqs[i].counters));
+ }
+ mlx5_vdpa_event_qp_global_release(priv);
+ mlx5_vdpa_err_event_unset(priv);
+ if (priv->steer.tbl)
+ claim_zero(mlx5_glue->dr_destroy_flow_tbl(priv->steer.tbl));
+ if (priv->steer.domain)
+ claim_zero(mlx5_glue->dr_destroy_domain(priv->steer.domain));
+ if (priv->null_mr)
+ claim_zero(mlx5_glue->dereg_mr(priv->null_mr));
+ for (i = 0; i < priv->num_lag_ports; i++) {
+ if (priv->tiss[i])
+ claim_zero(mlx5_devx_cmd_destroy(priv->tiss[i]));
+ }
+ if (priv->td)
+ claim_zero(mlx5_devx_cmd_destroy(priv->td));
+ if (priv->virtq_db_addr)
+ /* Mask out the within page offset for munmap. */
+ claim_zero(munmap((void *)((uintptr_t)priv->virtq_db_addr &
+ ~(rte_mem_page_size() - 1)), priv->var->length));
+ if (priv->var)
+ mlx5_glue->dv_free_var(priv->var);
+}
+
+static void
+mlx5_vdpa_dev_release(struct mlx5_vdpa_priv *priv)
+{
+ if (priv->state == MLX5_VDPA_STATE_CONFIGURED)
+ mlx5_vdpa_dev_close(priv->vid);
+ mlx5_vdpa_release_dev_resources(priv);
+ if (priv->vdev)
+ rte_vdpa_unregister_device(priv->vdev);
+ if (priv->use_c_thread)
+ if (__atomic_fetch_sub(&conf_thread_mng.refcnt,
+ 1, __ATOMIC_RELAXED) == 1)
+ mlx5_vdpa_mult_threads_destroy(true);
+ rte_free(priv);
+}
+
static const struct rte_pci_id mlx5_vdpa_pci_id_map[] = {
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX5BF)
+ PCI_DEVICE_ID_MELLANOX_CONNECTX6)
},
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF)
+ PCI_DEVICE_ID_MELLANOX_CONNECTX6VF)
},
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX6)
+ PCI_DEVICE_ID_MELLANOX_CONNECTX6DX)
},
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX6VF)
+ PCI_DEVICE_ID_MELLANOX_CONNECTXVF)
},
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX6DX)
+ PCI_DEVICE_ID_MELLANOX_CONNECTX6DXBF)
},
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX6DXVF)
+ PCI_DEVICE_ID_MELLANOX_CONNECTX7)
+ },
+ {
+ RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
+ PCI_DEVICE_ID_MELLANOX_CONNECTX7BF)
},
{
.vendor_id = 0
}
};
-static struct rte_pci_driver mlx5_vdpa_driver = {
- .driver = {
- .name = "mlx5_vdpa",
- },
+static struct mlx5_class_driver mlx5_vdpa_driver = {
+ .drv_class = MLX5_CLASS_VDPA,
+ .name = RTE_STR(MLX5_VDPA_DRIVER_NAME),
.id_table = mlx5_vdpa_pci_id_map,
- .probe = mlx5_vdpa_pci_probe,
- .remove = mlx5_vdpa_pci_remove,
- .drv_flags = 0,
+ .probe = mlx5_vdpa_dev_probe,
+ .remove = mlx5_vdpa_dev_remove,
};
+RTE_LOG_REGISTER_DEFAULT(mlx5_vdpa_logtype, NOTICE)
+
/**
* Driver initialization routine.
*/
RTE_INIT(rte_mlx5_vdpa_init)
{
- /* Initialize common log type. */
- mlx5_vdpa_logtype = rte_log_register("pmd.vdpa.mlx5");
- if (mlx5_vdpa_logtype >= 0)
- rte_log_set_level(mlx5_vdpa_logtype, RTE_LOG_NOTICE);
+ mlx5_common_init();
if (mlx5_glue)
- rte_pci_register(&mlx5_vdpa_driver);
+ mlx5_class_driver_register(&mlx5_vdpa_driver);
}
-RTE_PMD_EXPORT_NAME(net_mlx5_vdpa, __COUNTER__);
-RTE_PMD_REGISTER_PCI_TABLE(net_mlx5_vdpa, mlx5_vdpa_pci_id_map);
-RTE_PMD_REGISTER_KMOD_DEP(net_mlx5_vdpa, "* ib_uverbs & mlx5_core & mlx5_ib");
+RTE_PMD_EXPORT_NAME(MLX5_VDPA_DRIVER_NAME, __COUNTER__);
+RTE_PMD_REGISTER_PCI_TABLE(MLX5_VDPA_DRIVER_NAME, mlx5_vdpa_pci_id_map);
+RTE_PMD_REGISTER_KMOD_DEP(MLX5_VDPA_DRIVER_NAME, "* ib_uverbs & mlx5_core & mlx5_ib");