* Copyright 2019 Mellanox Technologies, Ltd
*/
#include <unistd.h>
+#include <net/if.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <fcntl.h>
+#include <netinet/in.h>
#include <rte_malloc.h>
#include <rte_log.h>
#include <rte_errno.h>
#include <rte_bus_pci.h>
#include <rte_pci.h>
+#include <rte_string_fns.h>
#include <mlx5_glue.h>
#include <mlx5_common.h>
(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))
+
+#define MLX5_VDPA_MAX_RETRIES 20
+#define MLX5_VDPA_USEC 1000
TAILQ_HEAD(mlx5_vdpa_privs, mlx5_vdpa_priv) priv_list =
TAILQ_HEAD_INITIALIZER(priv_list);
{
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;
if (priv == NULL) {
DRV_LOG(ERR, "Invalid device id: %d.", did);
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 * 2) {
+ DRV_LOG(ERR, "Too big vring id: %d.", vring);
+ return -E2BIG;
+ }
+ return mlx5_vdpa_virtq_enable(priv, vring, state);
+}
+
+static int
+mlx5_vdpa_direct_db_prepare(struct mlx5_vdpa_priv *priv)
+{
+ int ret;
+
+ if (priv->direct_notifier) {
+ ret = rte_vhost_host_notifier_ctrl(priv->vid, false);
+ if (ret != 0) {
+ DRV_LOG(INFO, "Direct HW notifier FD cannot be "
+ "destroyed for device %d: %d.", priv->vid, ret);
+ return -1;
+ }
+ priv->direct_notifier = 0;
}
- return mlx5_vdpa_virtq_enable(virtq, state);
+ ret = rte_vhost_host_notifier_ctrl(priv->vid, true);
+ if (ret != 0)
+ DRV_LOG(INFO, "Direct HW notifier FD cannot be configured for"
+ " device %d: %d.", priv->vid, ret);
+ else
+ priv->direct_notifier = 1;
+ return 0;
}
static int
return 0;
}
+static int
+mlx5_vdpa_pd_create(struct mlx5_vdpa_priv *priv)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ priv->pd = mlx5_glue->alloc_pd(priv->ctx);
+ if (priv->pd == NULL) {
+ DRV_LOG(ERR, "Failed to allocate PD.");
+ return errno ? -errno : -ENOMEM;
+ }
+ struct mlx5dv_obj obj;
+ struct mlx5dv_pd pd_info;
+ int ret = 0;
+
+ obj.pd.in = priv->pd;
+ obj.pd.out = &pd_info;
+ ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_PD);
+ if (ret) {
+ DRV_LOG(ERR, "Fail to get PD object info.");
+ mlx5_glue->dealloc_pd(priv->pd);
+ priv->pd = NULL;
+ return -errno;
+ }
+ priv->pdn = pd_info.pdn;
+ return 0;
+#else
+ (void)priv;
+ DRV_LOG(ERR, "Cannot get pdn - no DV support.");
+ return -ENOTSUP;
+#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
+}
+
+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(priv->ctx->device->ibdev_path,
+ 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 int
mlx5_vdpa_dev_close(int vid)
{
if (priv->configured)
ret |= mlx5_vdpa_lm_log(priv);
mlx5_vdpa_cqe_event_unset(priv);
- ret |= mlx5_vdpa_steer_unset(priv);
+ mlx5_vdpa_steer_unset(priv);
mlx5_vdpa_virtqs_release(priv);
mlx5_vdpa_event_qp_global_release(priv);
mlx5_vdpa_mem_dereg(priv);
+ if (priv->pd) {
+ claim_zero(mlx5_glue->dealloc_pd(priv->pd));
+ priv->pd = NULL;
+ }
priv->configured = 0;
priv->vid = 0;
+ DRV_LOG(INFO, "vDPA device %d was closed.", vid);
return ret;
}
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)) {
+ if (mlx5_vdpa_mtu_set(priv))
+ DRV_LOG(WARNING, "MTU cannot be set on device %d.", did);
+ if (mlx5_vdpa_pd_create(priv) || mlx5_vdpa_mem_register(priv) ||
+ mlx5_vdpa_direct_db_prepare(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;
+ DRV_LOG(INFO, "vDPA device %d was configured.", vid);
return 0;
}
+static int
+mlx5_vdpa_get_device_fd(int vid)
+{
+ int did = rte_vhost_get_vdpa_device_id(vid);
+ struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device id: %d.", did);
+ return -EINVAL;
+ }
+ return priv->ctx->cmd_fd;
+}
+
+static int
+mlx5_vdpa_get_notify_area(int vid, int qid, uint64_t *offset, uint64_t *size)
+{
+ int did = rte_vhost_get_vdpa_device_id(vid);
+ struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+
+ RTE_SET_USED(qid);
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device id: %d.", did);
+ return -EINVAL;
+ }
+ if (!priv->var) {
+ DRV_LOG(ERR, "VAR was not created for device %d, is the device"
+ " configured?.", did);
+ return -EINVAL;
+ }
+ *offset = priv->var->mmap_off;
+ *size = priv->var->length;
+ return 0;
+}
+
+static int
+mlx5_vdpa_get_stats_names(int did, struct rte_vdpa_stat_name *stats_names,
+ unsigned int size)
+{
+ 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_did(did);
+ unsigned int i;
+
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device id: %d.", did);
+ 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;
+}
+
+static int
+mlx5_vdpa_get_stats(int did, int qid, struct rte_vdpa_stat *stats,
+ unsigned int n)
+{
+ struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device id: %d.", did);
+ return -ENODEV;
+ }
+ if (!priv->configured) {
+ DRV_LOG(ERR, "Device %d was not configured.", did);
+ return -ENODATA;
+ }
+ if (qid >= (int)priv->nr_virtqs) {
+ DRV_LOG(ERR, "Too big vring id: %d.", qid);
+ return -E2BIG;
+ }
+ if (!priv->caps.queue_counters_valid) {
+ DRV_LOG(ERR, "Virtq statistics is not supported for device %d.",
+ did);
+ return -ENOTSUP;
+ }
+ return mlx5_vdpa_virtq_stats_get(priv, qid, stats, n);
+}
+
+static int
+mlx5_vdpa_reset_stats(int did, int qid)
+{
+ struct mlx5_vdpa_priv *priv = mlx5_vdpa_find_priv_resource_by_did(did);
+
+ if (priv == NULL) {
+ DRV_LOG(ERR, "Invalid device id: %d.", did);
+ return -ENODEV;
+ }
+ if (!priv->configured) {
+ DRV_LOG(ERR, "Device %d was not configured.", did);
+ return -ENODATA;
+ }
+ if (qid >= (int)priv->nr_virtqs) {
+ DRV_LOG(ERR, "Too big vring id: %d.", qid);
+ return -E2BIG;
+ }
+ if (!priv->caps.queue_counters_valid) {
+ DRV_LOG(ERR, "Virtq statistics is not supported for device %d.",
+ did);
+ return -ENOTSUP;
+ }
+ return mlx5_vdpa_virtq_stats_reset(priv, qid);
+}
+
static struct rte_vdpa_dev_ops mlx5_vdpa_ops = {
.get_queue_num = mlx5_vdpa_get_queue_num,
.get_features = mlx5_vdpa_get_vdpa_features,
.set_features = mlx5_vdpa_features_set,
.migration_done = NULL,
.get_vfio_group_fd = NULL,
- .get_vfio_device_fd = NULL,
- .get_notify_area = 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 struct ibv_device *
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)))
+ if (rte_pci_addr_cmp(addr, &pci_addr))
continue;
ibv_match = ibv_list[n];
break;
return ret;
}
-#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)
{
rte_errno = ENODEV;
return -rte_errno;
}
- priv = rte_zmalloc("mlx5 vDPA device private", sizeof(*priv),
- RTE_CACHE_LINE_SIZE);
- if (!priv) {
- DRV_LOG(ERR, "Failed to allocate private memory.");
- rte_errno = ENOMEM;
- goto error;
- }
ret = mlx5_devx_cmd_query_hca_attr(ctx, &attr);
if (ret) {
DRV_LOG(ERR, "Unable to read HCA capabilities.");
rte_errno = ENOTSUP;
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;
+ } 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;
}
+ 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 * 2,
+ RTE_CACHE_LINE_SIZE);
+ if (!priv) {
+ DRV_LOG(ERR, "Failed to allocate private memory.");
+ rte_errno = ENOMEM;
+ 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 = VDPA_ADDR_PCI;
+ priv->pci_dev = pci_dev;
priv->var = mlx5_glue->dv_alloc_var(ctx, 0);
if (!priv->var) {
DRV_LOG(ERR, "Failed to allocate VAR %u.\n", errno);
goto error;
}
- priv->id = rte_vdpa_register_device(&priv->dev_addr, &mlx5_vdpa_ops);
+ priv->id = rte_vdpa_register_device(&pci_dev->device, &mlx5_vdpa_ops);
if (priv->id < 0) {
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);
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 (!rte_pci_addr_cmp(&priv->pci_dev->addr, &pci_dev->addr)) {
found = 1;
break;
}
}
static const struct rte_pci_id mlx5_vdpa_pci_id_map[] = {
- {
- RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX5BF)
- },
- {
- RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
- PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF)
- },
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
PCI_DEVICE_ID_MELLANOX_CONNECTX6)
git.droids-corp.org / dpdk.git / blobdiff