summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/mlx4/main.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/hw/mlx4/main.c')
-rw-r--r--drivers/infiniband/hw/mlx4/main.c1308
1 files changed, 652 insertions, 656 deletions
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index d1b43cbbfea7..dd35e03402ab 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -70,7 +70,6 @@
MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver");
MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION(DRV_VERSION);
int mlx4_ib_sm_guid_assign = 0;
module_param_named(sm_guid_assign, mlx4_ib_sm_guid_assign, int, 0444);
@@ -81,17 +80,13 @@ static const char mlx4_ib_version[] =
DRV_VERSION "\n";
static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init);
+static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device,
+ u32 port_num);
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+ void *param);
static struct workqueue_struct *wq;
-static void init_query_mad(struct ib_smp *mad)
-{
- mad->base_version = 1;
- mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED;
- mad->class_version = 1;
- mad->method = IB_MGMT_METHOD_GET;
-}
-
static int check_flow_steering_support(struct mlx4_dev *dev)
{
int eth_num_ports = 0;
@@ -128,17 +123,20 @@ static int num_ib_ports(struct mlx4_dev *dev)
return ib_ports;
}
-static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_num)
+static struct net_device *mlx4_ib_get_netdev(struct ib_device *device,
+ u32 port_num)
{
struct mlx4_ib_dev *ibdev = to_mdev(device);
- struct net_device *dev;
+ struct net_device *dev, *ret = NULL;
rcu_read_lock();
- dev = mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port_num);
+ for_each_netdev_rcu(&init_net, dev) {
+ if (dev->dev.parent != ibdev->ib_dev.dev.parent ||
+ dev->dev_port + 1 != port_num)
+ continue;
- if (dev) {
if (mlx4_is_bonded(ibdev->dev)) {
- struct net_device *upper = NULL;
+ struct net_device *upper;
upper = netdev_master_upper_dev_get_rcu(dev);
if (upper) {
@@ -149,17 +147,19 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_n
dev = active;
}
}
- }
- if (dev)
+
dev_hold(dev);
+ ret = dev;
+ break;
+ }
rcu_read_unlock();
- return dev;
+ return ret;
}
static int mlx4_ib_update_gids_v1(struct gid_entry *gids,
struct mlx4_ib_dev *ibdev,
- u8 port_num)
+ u32 port_num)
{
struct mlx4_cmd_mailbox *mailbox;
int err;
@@ -192,7 +192,7 @@ static int mlx4_ib_update_gids_v1(struct gid_entry *gids,
static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids,
struct mlx4_ib_dev *ibdev,
- u8 port_num)
+ u32 port_num)
{
struct mlx4_cmd_mailbox *mailbox;
int err;
@@ -218,8 +218,6 @@ static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids,
gid_tbl[i].version = 2;
if (!ipv6_addr_v4mapped((struct in6_addr *)&gids[i].gid))
gid_tbl[i].type = 1;
- else
- memset(&gid_tbl[i].gid, 0, 12);
}
}
@@ -239,7 +237,7 @@ static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids,
static int mlx4_ib_update_gids(struct gid_entry *gids,
struct mlx4_ib_dev *ibdev,
- u8 port_num)
+ u32 port_num)
{
if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2)
return mlx4_ib_update_gids_v1_v2(gids, ibdev, port_num);
@@ -247,40 +245,49 @@ static int mlx4_ib_update_gids(struct gid_entry *gids,
return mlx4_ib_update_gids_v1(gids, ibdev, port_num);
}
-static int mlx4_ib_add_gid(struct ib_device *device,
- u8 port_num,
- unsigned int index,
- const union ib_gid *gid,
- const struct ib_gid_attr *attr,
- void **context)
+static void free_gid_entry(struct gid_entry *entry)
{
- struct mlx4_ib_dev *ibdev = to_mdev(device);
+ memset(&entry->gid, 0, sizeof(entry->gid));
+ kfree(entry->ctx);
+ entry->ctx = NULL;
+}
+
+static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
+{
+ struct mlx4_ib_dev *ibdev = to_mdev(attr->device);
struct mlx4_ib_iboe *iboe = &ibdev->iboe;
struct mlx4_port_gid_table *port_gid_table;
int free = -1, found = -1;
int ret = 0;
int hw_update = 0;
int i;
- struct gid_entry *gids = NULL;
+ struct gid_entry *gids;
+ u16 vlan_id = 0xffff;
+ u8 mac[ETH_ALEN];
- if (!rdma_cap_roce_gid_table(device, port_num))
+ if (!rdma_cap_roce_gid_table(attr->device, attr->port_num))
return -EINVAL;
- if (port_num > MLX4_MAX_PORTS)
+ if (attr->port_num > MLX4_MAX_PORTS)
return -EINVAL;
if (!context)
return -EINVAL;
- port_gid_table = &iboe->gids[port_num - 1];
+ ret = rdma_read_gid_l2_fields(attr, &vlan_id, &mac[0]);
+ if (ret)
+ return ret;
+ port_gid_table = &iboe->gids[attr->port_num - 1];
spin_lock_bh(&iboe->lock);
for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i) {
- if (!memcmp(&port_gid_table->gids[i].gid, gid, sizeof(*gid)) &&
- (port_gid_table->gids[i].gid_type == attr->gid_type)) {
+ if (!memcmp(&port_gid_table->gids[i].gid,
+ &attr->gid, sizeof(attr->gid)) &&
+ port_gid_table->gids[i].gid_type == attr->gid_type &&
+ port_gid_table->gids[i].vlan_id == vlan_id) {
found = i;
break;
}
- if (free < 0 && !memcmp(&port_gid_table->gids[i].gid, &zgid, sizeof(*gid)))
+ if (free < 0 && rdma_is_zero_gid(&port_gid_table->gids[i].gid))
free = i; /* HW has space */
}
@@ -293,8 +300,9 @@ static int mlx4_ib_add_gid(struct ib_device *device,
ret = -ENOMEM;
} else {
*context = port_gid_table->gids[free].ctx;
- memcpy(&port_gid_table->gids[free].gid, gid, sizeof(*gid));
+ port_gid_table->gids[free].gid = attr->gid;
port_gid_table->gids[free].gid_type = attr->gid_type;
+ port_gid_table->gids[free].vlan_id = vlan_id;
port_gid_table->gids[free].ctx->real_index = free;
port_gid_table->gids[free].ctx->refcount = 1;
hw_update = 1;
@@ -306,9 +314,12 @@ static int mlx4_ib_add_gid(struct ib_device *device,
ctx->refcount++;
}
if (!ret && hw_update) {
- gids = kmalloc(sizeof(*gids) * MLX4_MAX_PORT_GIDS, GFP_ATOMIC);
+ gids = kmalloc_array(MLX4_MAX_PORT_GIDS, sizeof(*gids),
+ GFP_ATOMIC);
if (!gids) {
ret = -ENOMEM;
+ *context = NULL;
+ free_gid_entry(&port_gid_table->gids[free]);
} else {
for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) {
memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
@@ -319,77 +330,82 @@ static int mlx4_ib_add_gid(struct ib_device *device,
spin_unlock_bh(&iboe->lock);
if (!ret && hw_update) {
- ret = mlx4_ib_update_gids(gids, ibdev, port_num);
+ ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
+ if (ret) {
+ spin_lock_bh(&iboe->lock);
+ *context = NULL;
+ free_gid_entry(&port_gid_table->gids[free]);
+ spin_unlock_bh(&iboe->lock);
+ }
kfree(gids);
}
return ret;
}
-static int mlx4_ib_del_gid(struct ib_device *device,
- u8 port_num,
- unsigned int index,
- void **context)
+static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context)
{
struct gid_cache_context *ctx = *context;
- struct mlx4_ib_dev *ibdev = to_mdev(device);
+ struct mlx4_ib_dev *ibdev = to_mdev(attr->device);
struct mlx4_ib_iboe *iboe = &ibdev->iboe;
struct mlx4_port_gid_table *port_gid_table;
int ret = 0;
int hw_update = 0;
struct gid_entry *gids = NULL;
- if (!rdma_cap_roce_gid_table(device, port_num))
+ if (!rdma_cap_roce_gid_table(attr->device, attr->port_num))
return -EINVAL;
- if (port_num > MLX4_MAX_PORTS)
+ if (attr->port_num > MLX4_MAX_PORTS)
return -EINVAL;
- port_gid_table = &iboe->gids[port_num - 1];
+ port_gid_table = &iboe->gids[attr->port_num - 1];
spin_lock_bh(&iboe->lock);
if (ctx) {
ctx->refcount--;
if (!ctx->refcount) {
unsigned int real_index = ctx->real_index;
- memcpy(&port_gid_table->gids[real_index].gid, &zgid, sizeof(zgid));
- kfree(port_gid_table->gids[real_index].ctx);
- port_gid_table->gids[real_index].ctx = NULL;
+ free_gid_entry(&port_gid_table->gids[real_index]);
hw_update = 1;
}
}
if (!ret && hw_update) {
int i;
- gids = kmalloc(sizeof(*gids) * MLX4_MAX_PORT_GIDS, GFP_ATOMIC);
+ gids = kmalloc_array(MLX4_MAX_PORT_GIDS, sizeof(*gids),
+ GFP_ATOMIC);
if (!gids) {
ret = -ENOMEM;
} else {
- for (i = 0; i < MLX4_MAX_PORT_GIDS; i++)
- memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
+ for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) {
+ memcpy(&gids[i].gid,
+ &port_gid_table->gids[i].gid,
+ sizeof(union ib_gid));
+ gids[i].gid_type =
+ port_gid_table->gids[i].gid_type;
+ }
}
}
spin_unlock_bh(&iboe->lock);
- if (!ret && hw_update) {
- ret = mlx4_ib_update_gids(gids, ibdev, port_num);
- kfree(gids);
- }
+ if (gids)
+ ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
+
+ kfree(gids);
return ret;
}
int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
- u8 port_num, int index)
+ const struct ib_gid_attr *attr)
{
struct mlx4_ib_iboe *iboe = &ibdev->iboe;
struct gid_cache_context *ctx = NULL;
- union ib_gid gid;
struct mlx4_port_gid_table *port_gid_table;
int real_index = -EINVAL;
int i;
- int ret;
unsigned long flags;
- struct ib_gid_attr attr;
+ u32 port_num = attr->port_num;
if (port_num > MLX4_MAX_PORTS)
return -EINVAL;
@@ -398,24 +414,15 @@ int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
port_num = 1;
if (!rdma_cap_roce_gid_table(&ibdev->ib_dev, port_num))
- return index;
-
- ret = ib_get_cached_gid(&ibdev->ib_dev, port_num, index, &gid, &attr);
- if (ret)
- return ret;
-
- if (attr.ndev)
- dev_put(attr.ndev);
-
- if (!memcmp(&gid, &zgid, sizeof(gid)))
- return -EINVAL;
+ return attr->index;
spin_lock_irqsave(&iboe->lock, flags);
port_gid_table = &iboe->gids[port_num - 1];
for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i)
- if (!memcmp(&port_gid_table->gids[i].gid, &gid, sizeof(gid)) &&
- attr.gid_type == port_gid_table->gids[i].gid_type) {
+ if (!memcmp(&port_gid_table->gids[i].gid,
+ &attr->gid, sizeof(attr->gid)) &&
+ attr->gid_type == port_gid_table->gids[i].gid_type) {
ctx = port_gid_table->gids[i].ctx;
break;
}
@@ -430,12 +437,12 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
struct ib_udata *uhw)
{
struct mlx4_ib_dev *dev = to_mdev(ibdev);
- struct ib_smp *in_mad = NULL;
- struct ib_smp *out_mad = NULL;
+ struct ib_smp *in_mad;
+ struct ib_smp *out_mad;
int err;
int have_ib_ports;
struct mlx4_uverbs_ex_query_device cmd;
- struct mlx4_uverbs_ex_query_device_resp resp = {.comp_mask = 0};
+ struct mlx4_uverbs_ex_query_device_resp resp = {};
struct mlx4_clock_params clock_params;
if (uhw->inlen) {
@@ -461,7 +468,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
if (!in_mad || !out_mad)
goto out;
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS,
@@ -477,8 +484,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->device_cap_flags = IB_DEVICE_CHANGE_PHY_PORT |
IB_DEVICE_PORT_ACTIVE_EVENT |
IB_DEVICE_SYS_IMAGE_GUID |
- IB_DEVICE_RC_RNR_NAK_GEN |
- IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
+ IB_DEVICE_RC_RNR_NAK_GEN;
+ props->kernel_cap_flags = IBK_BLOCK_MULTICAST_LOOPBACK;
if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR)
props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR)
@@ -492,9 +499,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
if (dev->dev->caps.max_gso_sz &&
(dev->dev->rev_id != MLX4_IB_CARD_REV_A0) &&
(dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BLH))
- props->device_cap_flags |= IB_DEVICE_UD_TSO;
+ props->kernel_cap_flags |= IBK_UD_TSO;
if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_RESERVED_LKEY)
- props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
+ props->kernel_cap_flags |= IBK_LOCAL_DMA_LKEY;
if ((dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_LOCAL_INV) &&
(dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_REMOTE_INV) &&
(dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_FAST_REG_WR))
@@ -524,9 +531,11 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->page_size_cap = dev->dev->caps.page_size_cap;
props->max_qp = dev->dev->quotas.qp;
props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
- props->max_sge = min(dev->dev->caps.max_sq_sg,
- dev->dev->caps.max_rq_sg);
- props->max_sge_rd = MLX4_MAX_SGE_RD;
+ props->max_send_sge =
+ min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg);
+ props->max_recv_sge =
+ min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg);
+ props->max_sge_rd = MLX4_MAX_SGE_RD;
props->max_cq = dev->dev->quotas.cq;
props->max_cqe = dev->dev->caps.max_cqes;
props->max_mr = dev->dev->quotas.mpt;
@@ -547,22 +556,81 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->max_mcast_qp_attach = dev->dev->caps.num_qp_per_mgm;
props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
props->max_mcast_grp;
- props->max_map_per_fmr = dev->dev->caps.max_fmr_maps;
props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
props->timestamp_mask = 0xFFFFFFFFFFFFULL;
props->max_ah = INT_MAX;
- if (!mlx4_is_slave(dev->dev))
- err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
+ if (mlx4_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET ||
+ mlx4_ib_port_link_layer(ibdev, 2) == IB_LINK_LAYER_ETHERNET) {
+ if (dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) {
+ props->rss_caps.max_rwq_indirection_tables =
+ props->max_qp;
+ props->rss_caps.max_rwq_indirection_table_size =
+ dev->dev->caps.max_rss_tbl_sz;
+ props->rss_caps.supported_qpts = 1 << IB_QPT_RAW_PACKET;
+ props->max_wq_type_rq = props->max_qp;
+ }
+
+ if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP)
+ props->raw_packet_caps |= IB_RAW_PACKET_CAP_SCATTER_FCS;
+ }
+
+ props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT;
+ props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD;
if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
resp.response_length += sizeof(resp.hca_core_clock_offset);
- if (!err && !mlx4_is_slave(dev->dev)) {
- resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+ if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) {
+ resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET;
resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
}
}
+ if (uhw->outlen >= resp.response_length +
+ sizeof(resp.max_inl_recv_sz)) {
+ resp.response_length += sizeof(resp.max_inl_recv_sz);
+ resp.max_inl_recv_sz = dev->dev->caps.max_rq_sg *
+ sizeof(struct mlx4_wqe_data_seg);
+ }
+
+ if (offsetofend(typeof(resp), rss_caps) <= uhw->outlen) {
+ if (props->rss_caps.supported_qpts) {
+ resp.rss_caps.rx_hash_function =
+ MLX4_IB_RX_HASH_FUNC_TOEPLITZ;
+
+ resp.rss_caps.rx_hash_fields_mask =
+ MLX4_IB_RX_HASH_SRC_IPV4 |
+ MLX4_IB_RX_HASH_DST_IPV4 |
+ MLX4_IB_RX_HASH_SRC_IPV6 |
+ MLX4_IB_RX_HASH_DST_IPV6 |
+ MLX4_IB_RX_HASH_SRC_PORT_TCP |
+ MLX4_IB_RX_HASH_DST_PORT_TCP |
+ MLX4_IB_RX_HASH_SRC_PORT_UDP |
+ MLX4_IB_RX_HASH_DST_PORT_UDP;
+
+ if (dev->dev->caps.tunnel_offload_mode ==
+ MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+ resp.rss_caps.rx_hash_fields_mask |=
+ MLX4_IB_RX_HASH_INNER;
+ }
+ resp.response_length = offsetof(typeof(resp), rss_caps) +
+ sizeof(resp.rss_caps);
+ }
+
+ if (offsetofend(typeof(resp), tso_caps) <= uhw->outlen) {
+ if (dev->dev->caps.max_gso_sz &&
+ ((mlx4_ib_port_link_layer(ibdev, 1) ==
+ IB_LINK_LAYER_ETHERNET) ||
+ (mlx4_ib_port_link_layer(ibdev, 2) ==
+ IB_LINK_LAYER_ETHERNET))) {
+ resp.tso_caps.max_tso = dev->dev->caps.max_gso_sz;
+ resp.tso_caps.supported_qpts |=
+ 1 << IB_QPT_RAW_PACKET;
+ }
+ resp.response_length = offsetof(typeof(resp), tso_caps) +
+ sizeof(resp.tso_caps);
+ }
+
if (uhw->outlen) {
err = ib_copy_to_udata(uhw, &resp, resp.response_length);
if (err)
@@ -576,7 +644,7 @@ out:
}
static enum rdma_link_layer
-mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num)
+mlx4_ib_port_link_layer(struct ib_device *device, u32 port_num)
{
struct mlx4_dev *dev = to_mdev(device)->dev;
@@ -584,11 +652,11 @@ mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num)
IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
}
-static int ib_link_query_port(struct ib_device *ibdev, u8 port,
+static int ib_link_query_port(struct ib_device *ibdev, u32 port,
struct ib_port_attr *props, int netw_view)
{
- struct ib_smp *in_mad = NULL;
- struct ib_smp *out_mad = NULL;
+ struct ib_smp *in_mad;
+ struct ib_smp *out_mad;
int ext_active_speed;
int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
int err = -ENOMEM;
@@ -598,7 +666,7 @@ static int ib_link_query_port(struct ib_device *ibdev, u8 port,
if (!in_mad || !out_mad)
goto out;
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = IB_SMP_ATTR_PORT_INFO;
in_mad->attr_mod = cpu_to_be32(port);
@@ -650,7 +718,7 @@ static int ib_link_query_port(struct ib_device *ibdev, u8 port,
/* If reported active speed is QDR, check if is FDR-10 */
if (props->active_speed == IB_SPEED_QDR) {
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = MLX4_ATTR_EXTENDED_PORT_INFO;
in_mad->attr_mod = cpu_to_be32(port);
@@ -676,10 +744,11 @@ out:
static u8 state_to_phys_state(enum ib_port_state state)
{
- return state == IB_PORT_ACTIVE ? 5 : 3;
+ return state == IB_PORT_ACTIVE ?
+ IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED;
}
-static int eth_link_query_port(struct ib_device *ibdev, u8 port,
+static int eth_link_query_port(struct ib_device *ibdev, u32 port,
struct ib_port_attr *props)
{
@@ -706,10 +775,12 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
IB_WIDTH_4X : IB_WIDTH_1X;
props->active_speed = (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
IB_SPEED_FDR : IB_SPEED_QDR;
- props->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
+ props->port_cap_flags = IB_PORT_CM_SUP;
+ props->ip_gids = true;
props->gid_tbl_len = mdev->dev->caps.gid_table_len[port];
props->max_msg_sz = mdev->dev->caps.max_msg_sz;
- props->pkey_tbl_len = 1;
+ if (mdev->dev->caps.pkey_table_len[port])
+ props->pkey_tbl_len = 1;
props->max_mtu = IB_MTU_4096;
props->max_vl_num = 2;
props->state = IB_PORT_DOWN;
@@ -738,7 +809,7 @@ out:
return err;
}
-int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
+int __mlx4_ib_query_port(struct ib_device *ibdev, u32 port,
struct ib_port_attr *props, int netw_view)
{
int err;
@@ -752,18 +823,18 @@ int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
return err;
}
-static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
+static int mlx4_ib_query_port(struct ib_device *ibdev, u32 port,
struct ib_port_attr *props)
{
/* returns host view */
return __mlx4_ib_query_port(ibdev, port, props, 0);
}
-int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
+int __mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
union ib_gid *gid, int netw_view)
{
- struct ib_smp *in_mad = NULL;
- struct ib_smp *out_mad = NULL;
+ struct ib_smp *in_mad;
+ struct ib_smp *out_mad;
int err = -ENOMEM;
struct mlx4_ib_dev *dev = to_mdev(ibdev);
int clear = 0;
@@ -774,7 +845,7 @@ int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
if (!in_mad || !out_mad)
goto out;
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = IB_SMP_ATTR_PORT_INFO;
in_mad->attr_mod = cpu_to_be32(port);
@@ -796,7 +867,7 @@ int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
}
}
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = IB_SMP_ATTR_GUID_INFO;
in_mad->attr_mod = cpu_to_be32(index / 8);
@@ -815,34 +886,20 @@ out:
return err;
}
-static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
+static int mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index,
union ib_gid *gid)
{
- int ret;
-
if (rdma_protocol_ib(ibdev, port))
return __mlx4_ib_query_gid(ibdev, port, index, gid, 0);
-
- if (!rdma_protocol_roce(ibdev, port))
- return -ENODEV;
-
- if (!rdma_cap_roce_gid_table(ibdev, port))
- return -ENODEV;
-
- ret = ib_get_cached_gid(ibdev, port, index, gid, NULL);
- if (ret == -EAGAIN) {
- memcpy(gid, &zgid, sizeof(*gid));
- return 0;
- }
-
- return ret;
+ return 0;
}
-static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u8 port, u64 *sl2vl_tbl)
+static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u32 port,
+ u64 *sl2vl_tbl)
{
union sl2vl_tbl_to_u64 sl2vl64;
- struct ib_smp *in_mad = NULL;
- struct ib_smp *out_mad = NULL;
+ struct ib_smp *in_mad;
+ struct ib_smp *out_mad;
int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
int err = -ENOMEM;
int jj;
@@ -857,7 +914,7 @@ static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u8 port, u64 *sl2vl_tbl)
if (!in_mad || !out_mad)
goto out;
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = IB_SMP_ATTR_SL_TO_VL_TABLE;
in_mad->attr_mod = 0;
@@ -898,11 +955,11 @@ static void mlx4_init_sl2vl_tbl(struct mlx4_ib_dev *mdev)
}
}
-int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
+int __mlx4_ib_query_pkey(struct ib_device *ibdev, u32 port, u16 index,
u16 *pkey, int netw_view)
{
- struct ib_smp *in_mad = NULL;
- struct ib_smp *out_mad = NULL;
+ struct ib_smp *in_mad;
+ struct ib_smp *out_mad;
int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
int err = -ENOMEM;
@@ -911,7 +968,7 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
if (!in_mad || !out_mad)
goto out;
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = IB_SMP_ATTR_PKEY_TABLE;
in_mad->attr_mod = cpu_to_be32(index / 32);
@@ -931,7 +988,8 @@ out:
return err;
}
-static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey)
+static int mlx4_ib_query_pkey(struct ib_device *ibdev, u32 port, u16 index,
+ u16 *pkey)
{
return __mlx4_ib_query_pkey(ibdev, port, index, pkey, 0);
}
@@ -972,8 +1030,8 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
return 0;
}
-static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
- u32 cap_mask)
+static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u32 port,
+ int reset_qkey_viols, u32 cap_mask)
{
struct mlx4_cmd_mailbox *mailbox;
int err;
@@ -998,7 +1056,7 @@ static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_vio
return err;
}
-static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
+static int mlx4_ib_modify_port(struct ib_device *ibdev, u32 port, int mask,
struct ib_port_modify *props)
{
struct mlx4_ib_dev *mdev = to_mdev(ibdev);
@@ -1032,19 +1090,21 @@ out:
return err;
}
-static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
- struct ib_udata *udata)
+static int mlx4_ib_alloc_ucontext(struct ib_ucontext *uctx,
+ struct ib_udata *udata)
{
+ struct ib_device *ibdev = uctx->device;
struct mlx4_ib_dev *dev = to_mdev(ibdev);
- struct mlx4_ib_ucontext *context;
+ struct mlx4_ib_ucontext *context = to_mucontext(uctx);
struct mlx4_ib_alloc_ucontext_resp_v3 resp_v3;
struct mlx4_ib_alloc_ucontext_resp resp;
int err;
if (!dev->ib_active)
- return ERR_PTR(-EAGAIN);
+ return -EAGAIN;
- if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) {
+ if (ibdev->ops.uverbs_abi_ver ==
+ MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) {
resp_v3.qp_tab_size = dev->dev->caps.num_qps;
resp_v3.bf_reg_size = dev->dev->caps.bf_reg_size;
resp_v3.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
@@ -1056,308 +1116,149 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
resp.cqe_size = dev->dev->caps.cqe_size;
}
- context = kzalloc(sizeof(*context), GFP_KERNEL);
- if (!context)
- return ERR_PTR(-ENOMEM);
-
err = mlx4_uar_alloc(to_mdev(ibdev)->dev, &context->uar);
- if (err) {
- kfree(context);
- return ERR_PTR(err);
- }
+ if (err)
+ return err;
INIT_LIST_HEAD(&context->db_page_list);
mutex_init(&context->db_page_mutex);
- if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
+ INIT_LIST_HEAD(&context->wqn_ranges_list);
+ mutex_init(&context->wqn_ranges_mutex);
+
+ if (ibdev->ops.uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
err = ib_copy_to_udata(udata, &resp_v3, sizeof(resp_v3));
else
err = ib_copy_to_udata(udata, &resp, sizeof(resp));
if (err) {
mlx4_uar_free(to_mdev(ibdev)->dev, &context->uar);
- kfree(context);
- return ERR_PTR(-EFAULT);
+ return -EFAULT;
}
- return &context->ibucontext;
+ return err;
}
-static int mlx4_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
+static void mlx4_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
{
struct mlx4_ib_ucontext *context = to_mucontext(ibcontext);
mlx4_uar_free(to_mdev(ibcontext->device)->dev, &context->uar);
- kfree(context);
-
- return 0;
-}
-
-static void mlx4_ib_vma_open(struct vm_area_struct *area)
-{
- /* vma_open is called when a new VMA is created on top of our VMA.
- * This is done through either mremap flow or split_vma (usually due
- * to mlock, madvise, munmap, etc.). We do not support a clone of the
- * vma, as this VMA is strongly hardware related. Therefore we set the
- * vm_ops of the newly created/cloned VMA to NULL, to prevent it from
- * calling us again and trying to do incorrect actions. We assume that
- * the original vma size is exactly a single page that there will be no
- * "splitting" operations on.
- */
- area->vm_ops = NULL;
-}
-
-static void mlx4_ib_vma_close(struct vm_area_struct *area)
-{
- struct mlx4_ib_vma_private_data *mlx4_ib_vma_priv_data;
-
- /* It's guaranteed that all VMAs opened on a FD are closed before the
- * file itself is closed, therefore no sync is needed with the regular
- * closing flow. (e.g. mlx4_ib_dealloc_ucontext) However need a sync
- * with accessing the vma as part of mlx4_ib_disassociate_ucontext.
- * The close operation is usually called under mm->mmap_sem except when
- * process is exiting. The exiting case is handled explicitly as part
- * of mlx4_ib_disassociate_ucontext.
- */
- mlx4_ib_vma_priv_data = (struct mlx4_ib_vma_private_data *)
- area->vm_private_data;
-
- /* set the vma context pointer to null in the mlx4_ib driver's private
- * data to protect against a race condition in mlx4_ib_dissassociate_ucontext().
- */
- mlx4_ib_vma_priv_data->vma = NULL;
}
-static const struct vm_operations_struct mlx4_ib_vm_ops = {
- .open = mlx4_ib_vma_open,
- .close = mlx4_ib_vma_close
-};
-
static void mlx4_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
{
- int i;
- int ret = 0;
- struct vm_area_struct *vma;
- struct mlx4_ib_ucontext *context = to_mucontext(ibcontext);
- struct task_struct *owning_process = NULL;
- struct mm_struct *owning_mm = NULL;
-
- owning_process = get_pid_task(ibcontext->tgid, PIDTYPE_PID);
- if (!owning_process)
- return;
-
- owning_mm = get_task_mm(owning_process);
- if (!owning_mm) {
- pr_info("no mm, disassociate ucontext is pending task termination\n");
- while (1) {
- /* make sure that task is dead before returning, it may
- * prevent a rare case of module down in parallel to a
- * call to mlx4_ib_vma_close.
- */
- put_task_struct(owning_process);
- usleep_range(1000, 2000);
- owning_process = get_pid_task(ibcontext->tgid,
- PIDTYPE_PID);
- if (!owning_process ||
- owning_process->state == TASK_DEAD) {
- pr_info("disassociate ucontext done, task was terminated\n");
- /* in case task was dead need to release the task struct */
- if (owning_process)
- put_task_struct(owning_process);
- return;
- }
- }
- }
-
- /* need to protect from a race on closing the vma as part of
- * mlx4_ib_vma_close().
- */
- down_write(&owning_mm->mmap_sem);
- for (i = 0; i < HW_BAR_COUNT; i++) {
- vma = context->hw_bar_info[i].vma;
- if (!vma)
- continue;
-
- ret = zap_vma_ptes(context->hw_bar_info[i].vma,
- context->hw_bar_info[i].vma->vm_start,
- PAGE_SIZE);
- if (ret) {
- pr_err("Error: zap_vma_ptes failed for index=%d, ret=%d\n", i, ret);
- BUG_ON(1);
- }
-
- context->hw_bar_info[i].vma->vm_flags &=
- ~(VM_SHARED | VM_MAYSHARE);
- /* context going to be destroyed, should not access ops any more */
- context->hw_bar_info[i].vma->vm_ops = NULL;
- }
-
- up_write(&owning_mm->mmap_sem);
- mmput(owning_mm);
- put_task_struct(owning_process);
-}
-
-static void mlx4_ib_set_vma_data(struct vm_area_struct *vma,
- struct mlx4_ib_vma_private_data *vma_private_data)
-{
- vma_private_data->vma = vma;
- vma->vm_private_data = vma_private_data;
- vma->vm_ops = &mlx4_ib_vm_ops;
}
static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
{
struct mlx4_ib_dev *dev = to_mdev(context->device);
- struct mlx4_ib_ucontext *mucontext = to_mucontext(context);
- if (vma->vm_end - vma->vm_start != PAGE_SIZE)
- return -EINVAL;
+ switch (vma->vm_pgoff) {
+ case 0:
+ return rdma_user_mmap_io(context, vma,
+ to_mucontext(context)->uar.pfn,
+ PAGE_SIZE,
+ pgprot_noncached(vma->vm_page_prot),
+ NULL);
- if (vma->vm_pgoff == 0) {
- /* We prevent double mmaping on same context */
- if (mucontext->hw_bar_info[HW_BAR_DB].vma)
+ case 1:
+ if (dev->dev->caps.bf_reg_size == 0)
return -EINVAL;
-
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
- if (io_remap_pfn_range(vma, vma->vm_start,
- to_mucontext(context)->uar.pfn,
- PAGE_SIZE, vma->vm_page_prot))
- return -EAGAIN;
-
- mlx4_ib_set_vma_data(vma, &mucontext->hw_bar_info[HW_BAR_DB]);
-
- } else if (vma->vm_pgoff == 1 && dev->dev->caps.bf_reg_size != 0) {
- /* We prevent double mmaping on same context */
- if (mucontext->hw_bar_info[HW_BAR_BF].vma)
- return -EINVAL;
-
- vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
- if (io_remap_pfn_range(vma, vma->vm_start,
- to_mucontext(context)->uar.pfn +
- dev->dev->caps.num_uars,
- PAGE_SIZE, vma->vm_page_prot))
- return -EAGAIN;
-
- mlx4_ib_set_vma_data(vma, &mucontext->hw_bar_info[HW_BAR_BF]);
-
- } else if (vma->vm_pgoff == 3) {
+ return rdma_user_mmap_io(
+ context, vma,
+ to_mucontext(context)->uar.pfn +
+ dev->dev->caps.num_uars,
+ PAGE_SIZE, pgprot_writecombine(vma->vm_page_prot),
+ NULL);
+
+ case 3: {
struct mlx4_clock_params params;
int ret;
- /* We prevent double mmaping on same context */
- if (mucontext->hw_bar_info[HW_BAR_CLOCK].vma)
- return -EINVAL;
-
ret = mlx4_get_internal_clock_params(dev->dev, &params);
-
if (ret)
return ret;
- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
- if (io_remap_pfn_range(vma, vma->vm_start,
- (pci_resource_start(dev->dev->persist->pdev,
- params.bar) +
- params.offset)
- >> PAGE_SHIFT,
- PAGE_SIZE, vma->vm_page_prot))
- return -EAGAIN;
-
- mlx4_ib_set_vma_data(vma,
- &mucontext->hw_bar_info[HW_BAR_CLOCK]);
- } else {
- return -EINVAL;
+ return rdma_user_mmap_io(
+ context, vma,
+ (pci_resource_start(dev->dev->persist->pdev,
+ params.bar) +
+ params.offset) >>
+ PAGE_SHIFT,
+ PAGE_SIZE, pgprot_noncached(vma->vm_page_prot),
+ NULL);
}
- return 0;
+ default:
+ return -EINVAL;
+ }
}
-static struct ib_pd *mlx4_ib_alloc_pd(struct ib_device *ibdev,
- struct ib_ucontext *context,
- struct ib_udata *udata)
+static int mlx4_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
{
- struct mlx4_ib_pd *pd;
+ struct mlx4_ib_pd *pd = to_mpd(ibpd);
+ struct ib_device *ibdev = ibpd->device;
int err;
- pd = kmalloc(sizeof *pd, GFP_KERNEL);
- if (!pd)
- return ERR_PTR(-ENOMEM);
-
err = mlx4_pd_alloc(to_mdev(ibdev)->dev, &pd->pdn);
- if (err) {
- kfree(pd);
- return ERR_PTR(err);
- }
-
- if (context)
- if (ib_copy_to_udata(udata, &pd->pdn, sizeof (__u32))) {
- mlx4_pd_free(to_mdev(ibdev)->dev, pd->pdn);
- kfree(pd);
- return ERR_PTR(-EFAULT);
- }
+ if (err)
+ return err;
- return &pd->ibpd;
+ if (udata && ib_copy_to_udata(udata, &pd->pdn, sizeof(__u32))) {
+ mlx4_pd_free(to_mdev(ibdev)->dev, pd->pdn);
+ return -EFAULT;
+ }
+ return 0;
}
-static int mlx4_ib_dealloc_pd(struct ib_pd *pd)
+static int mlx4_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
{
mlx4_pd_free(to_mdev(pd->device)->dev, to_mpd(pd)->pdn);
- kfree(pd);
-
return 0;
}
-static struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev,
- struct ib_ucontext *context,
- struct ib_udata *udata)
+static int mlx4_ib_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata)
{
- struct mlx4_ib_xrcd *xrcd;
+ struct mlx4_ib_dev *dev = to_mdev(ibxrcd->device);
+ struct mlx4_ib_xrcd *xrcd = to_mxrcd(ibxrcd);
struct ib_cq_init_attr cq_attr = {};
int err;
- if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
- return ERR_PTR(-ENOSYS);
-
- xrcd = kmalloc(sizeof *xrcd, GFP_KERNEL);
- if (!xrcd)
- return ERR_PTR(-ENOMEM);
+ if (!(dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
+ return -EOPNOTSUPP;
- err = mlx4_xrcd_alloc(to_mdev(ibdev)->dev, &xrcd->xrcdn);
+ err = mlx4_xrcd_alloc(dev->dev, &xrcd->xrcdn);
if (err)
- goto err1;
+ return err;
- xrcd->pd = ib_alloc_pd(ibdev, 0);
+ xrcd->pd = ib_alloc_pd(ibxrcd->device, 0);
if (IS_ERR(xrcd->pd)) {
err = PTR_ERR(xrcd->pd);
goto err2;
}
cq_attr.cqe = 1;
- xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, &cq_attr);
+ xrcd->cq = ib_create_cq(ibxrcd->device, NULL, NULL, xrcd, &cq_attr);
if (IS_ERR(xrcd->cq)) {
err = PTR_ERR(xrcd->cq);
goto err3;
}
- return &xrcd->ibxrcd;
+ return 0;
err3:
ib_dealloc_pd(xrcd->pd);
err2:
- mlx4_xrcd_free(to_mdev(ibdev)->dev, xrcd->xrcdn);
-err1:
- kfree(xrcd);
- return ERR_PTR(err);
+ mlx4_xrcd_free(dev->dev, xrcd->xrcdn);
+ return err;
}
-static int mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd)
+static int mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
{
ib_destroy_cq(to_mxrcd(xrcd)->cq);
ib_dealloc_pd(to_mxrcd(xrcd)->pd);
mlx4_xrcd_free(to_mdev(xrcd->device)->dev, to_mxrcd(xrcd)->xrcdn);
- kfree(xrcd);
-
return 0;
}
@@ -1411,8 +1312,7 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
spin_lock_bh(&mdev->iboe.lock);
ndev = mdev->iboe.netdevs[mqp->port - 1];
- if (ndev)
- dev_hold(ndev);
+ dev_hold(ndev);
spin_unlock_bh(&mdev->iboe.lock);
if (ndev) {
@@ -1588,8 +1488,9 @@ static int __mlx4_ib_create_default_rules(
int i;
for (i = 0; i < ARRAY_SIZE(pdefault_rules->rules_create_list); i++) {
+ union ib_flow_spec ib_spec = {};
int ret;
- union ib_flow_spec ib_spec;
+
switch (pdefault_rules->rules_create_list[i]) {
case 0:
/* no rule */
@@ -1630,23 +1531,11 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
struct mlx4_net_trans_rule_hw_ctrl *ctrl;
int default_flow;
- static const u16 __mlx4_domain[] = {
- [IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS,
- [IB_FLOW_DOMAIN_ETHTOOL] = MLX4_DOMAIN_ETHTOOL,
- [IB_FLOW_DOMAIN_RFS] = MLX4_DOMAIN_RFS,
- [IB_FLOW_DOMAIN_NIC] = MLX4_DOMAIN_NIC,
- };
-
if (flow_attr->priority > MLX4_IB_FLOW_MAX_PRIO) {
pr_err("Invalid priority value %d\n", flow_attr->priority);
return -EINVAL;
}
- if (domain >= IB_FLOW_DOMAIN_NUM) {
- pr_err("Invalid domain value %d\n", domain);
- return -EINVAL;
- }
-
if (mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type) < 0)
return -EINVAL;
@@ -1655,8 +1544,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
return PTR_ERR(mailbox);
ctrl = mailbox->buf;
- ctrl->prio = cpu_to_be16(__mlx4_domain[domain] |
- flow_attr->priority);
+ ctrl->prio = cpu_to_be16(domain | flow_attr->priority);
ctrl->type = mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type);
ctrl->port = flow_attr->port;
ctrl->qpn = cpu_to_be32(qp->qp_num);
@@ -1798,8 +1686,8 @@ static int mlx4_ib_add_dont_trap_rule(struct mlx4_dev *dev,
}
static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
- struct ib_flow_attr *flow_attr,
- int domain)
+ struct ib_flow_attr *flow_attr,
+ struct ib_udata *udata)
{
int err = 0, i = 0, j = 0;
struct mlx4_ib_flow *mflow;
@@ -1807,13 +1695,17 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
int is_bonded = mlx4_is_bonded(dev);
- if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt)
- return ERR_PTR(-EINVAL);
+ if (flow_attr->flags & ~IB_FLOW_ATTR_FLAGS_DONT_TRAP)
+ return ERR_PTR(-EOPNOTSUPP);
if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) &&
(flow_attr->type != IB_FLOW_ATTR_NORMAL))
return ERR_PTR(-EOPNOTSUPP);
+ if (udata &&
+ udata->inlen && !ib_is_udata_cleared(udata, 0, udata->inlen))
+ return ERR_PTR(-EOPNOTSUPP);
+
memset(type, 0, sizeof(type));
mflow = kzalloc(sizeof(*mflow), GFP_KERNEL);
@@ -1858,8 +1750,8 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
}
while (i < ARRAY_SIZE(type) && type[i]) {
- err = __mlx4_ib_create_flow(qp, flow_attr, domain, type[i],
- &mflow->reg_id[i].id);
+ err = __mlx4_ib_create_flow(qp, flow_attr, MLX4_DOMAIN_UVERBS,
+ type[i], &mflow->reg_id[i].id);
if (err)
goto err_create_flow;
if (is_bonded) {
@@ -1868,7 +1760,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
*/
flow_attr->port = 2;
err = __mlx4_ib_create_flow(qp, flow_attr,
- domain, type[j],
+ MLX4_DOMAIN_UVERBS, type[j],
&mflow->reg_id[j].mirror);
flow_attr->port = 1;
if (err)
@@ -2067,11 +1959,9 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
if (ge) {
spin_lock_bh(&mdev->iboe.lock);
ndev = ge->added ? mdev->iboe.netdevs[ge->port - 1] : NULL;
- if (ndev)
- dev_hold(ndev);
+ dev_hold(ndev);
spin_unlock_bh(&mdev->iboe.lock);
- if (ndev)
- dev_put(ndev);
+ dev_put(ndev);
list_del(&ge->list);
kfree(ge);
} else
@@ -2084,8 +1974,8 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
static int init_node_data(struct mlx4_ib_dev *dev)
{
- struct ib_smp *in_mad = NULL;
- struct ib_smp *out_mad = NULL;
+ struct ib_smp *in_mad;
+ struct ib_smp *out_mad;
int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
int err = -ENOMEM;
@@ -2094,7 +1984,7 @@ static int init_node_data(struct mlx4_ib_dev *dev)
if (!in_mad || !out_mad)
goto out;
- init_query_mad(in_mad);
+ ib_init_query_mad(in_mad);
in_mad->attr_id = IB_SMP_ATTR_NODE_DESC;
if (mlx4_is_master(dev->dev))
mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW;
@@ -2120,39 +2010,45 @@ out:
return err;
}
-static ssize_t show_hca(struct device *device, struct device_attribute *attr,
- char *buf)
+static ssize_t hca_type_show(struct device *device,
+ struct device_attribute *attr, char *buf)
{
struct mlx4_ib_dev *dev =
- container_of(device, struct mlx4_ib_dev, ib_dev.dev);
- return sprintf(buf, "MT%d\n", dev->dev->persist->pdev->device);
+ rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev);
+
+ return sysfs_emit(buf, "MT%d\n", dev->dev->persist->pdev->device);
}
+static DEVICE_ATTR_RO(hca_type);
-static ssize_t show_rev(struct device *device, struct device_attribute *attr,
- char *buf)
+static ssize_t hw_rev_show(struct device *device,
+ struct device_attribute *attr, char *buf)
{
struct mlx4_ib_dev *dev =
- container_of(device, struct mlx4_ib_dev, ib_dev.dev);
- return sprintf(buf, "%x\n", dev->dev->rev_id);
+ rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev);
+
+ return sysfs_emit(buf, "%x\n", dev->dev->rev_id);
}
+static DEVICE_ATTR_RO(hw_rev);
-static ssize_t show_board(struct device *device, struct device_attribute *attr,
- char *buf)
+static ssize_t board_id_show(struct device *device,
+ struct device_attribute *attr, char *buf)
{
struct mlx4_ib_dev *dev =
- container_of(device, struct mlx4_ib_dev, ib_dev.dev);
- return sprintf(buf, "%.*s\n", MLX4_BOARD_ID_LEN,
- dev->dev->board_id);
+ rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev);
+
+ return sysfs_emit(buf, "%.*s\n", MLX4_BOARD_ID_LEN, dev->dev->board_id);
}
+static DEVICE_ATTR_RO(board_id);
-static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
-static DEVICE_ATTR(hca_type, S_IRUGO, show_hca, NULL);
-static DEVICE_ATTR(board_id, S_IRUGO, show_board, NULL);
+static struct attribute *mlx4_class_attributes[] = {
+ &dev_attr_hw_rev.attr,
+ &dev_attr_hca_type.attr,
+ &dev_attr_board_id.attr,
+ NULL
+};
-static struct device_attribute *mlx4_class_attributes[] = {
- &dev_attr_hw_rev,
- &dev_attr_hca_type,
- &dev_attr_board_id
+static const struct attribute_group mlx4_attr_group = {
+ .attrs = mlx4_class_attributes,
};
struct diag_counter {
@@ -2197,23 +2093,35 @@ static const struct diag_counter diag_device_only[] = {
DIAG_COUNTER(rq_num_udsdprd, 0x118),
};
-static struct rdma_hw_stats *mlx4_ib_alloc_hw_stats(struct ib_device *ibdev,
- u8 port_num)
+static struct rdma_hw_stats *
+mlx4_ib_alloc_hw_device_stats(struct ib_device *ibdev)
+{
+ struct mlx4_ib_dev *dev = to_mdev(ibdev);
+ struct mlx4_ib_diag_counters *diag = dev->diag_counters;
+
+ if (!diag[0].descs)
+ return NULL;
+
+ return rdma_alloc_hw_stats_struct(diag[0].descs, diag[0].num_counters,
+ RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
+static struct rdma_hw_stats *
+mlx4_ib_alloc_hw_port_stats(struct ib_device *ibdev, u32 port_num)
{
struct mlx4_ib_dev *dev = to_mdev(ibdev);
struct mlx4_ib_diag_counters *diag = dev->diag_counters;
- if (!diag[!!port_num].name)
+ if (!diag[1].descs)
return NULL;
- return rdma_alloc_hw_stats_struct(diag[!!port_num].name,
- diag[!!port_num].num_counters,
+ return rdma_alloc_hw_stats_struct(diag[1].descs, diag[1].num_counters,
RDMA_HW_STATS_DEFAULT_LIFESPAN);
}
static int mlx4_ib_get_hw_stats(struct ib_device *ibdev,
struct rdma_hw_stats *stats,
- u8 port, int index)
+ u32 port, int index)
{
struct mlx4_ib_dev *dev = to_mdev(ibdev);
struct mlx4_ib_diag_counters *diag = dev->diag_counters;
@@ -2237,10 +2145,8 @@ static int mlx4_ib_get_hw_stats(struct ib_device *ibdev,
}
static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev,
- const char ***name,
- u32 **offset,
- u32 *num,
- bool port)
+ struct rdma_stat_desc **pdescs,
+ u32 **offset, u32 *num, bool port)
{
u32 num_counters;
@@ -2252,51 +2158,62 @@ static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev,
if (!port)
num_counters += ARRAY_SIZE(diag_device_only);
- *name = kcalloc(num_counters, sizeof(**name), GFP_KERNEL);
- if (!*name)
+ *pdescs = kcalloc(num_counters, sizeof(struct rdma_stat_desc),
+ GFP_KERNEL);
+ if (!*pdescs)
return -ENOMEM;
*offset = kcalloc(num_counters, sizeof(**offset), GFP_KERNEL);
if (!*offset)
- goto err_name;
+ goto err;
*num = num_counters;
return 0;
-err_name:
- kfree(*name);
+err:
+ kfree(*pdescs);
return -ENOMEM;
}
static void mlx4_ib_fill_diag_counters(struct mlx4_ib_dev *ibdev,
- const char **name,
- u32 *offset,
- bool port)
+ struct rdma_stat_desc *descs,
+ u32 *offset, bool port)
{
int i;
int j;
for (i = 0, j = 0; i < ARRAY_SIZE(diag_basic); i++, j++) {
- name[i] = diag_basic[i].name;
+ descs[i].name = diag_basic[i].name;
offset[i] = diag_basic[i].offset;
}
if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT) {
for (i = 0; i < ARRAY_SIZE(diag_ext); i++, j++) {
- name[j] = diag_ext[i].name;
+ descs[j].name = diag_ext[i].name;
offset[j] = diag_ext[i].offset;
}
}
if (!port) {
for (i = 0; i < ARRAY_SIZE(diag_device_only); i++, j++) {
- name[j] = diag_device_only[i].name;
+ descs[j].name = diag_device_only[i].name;
offset[j] = diag_device_only[i].offset;
}
}
}
+static const struct ib_device_ops mlx4_ib_hw_stats_ops = {
+ .alloc_hw_device_stats = mlx4_ib_alloc_hw_device_stats,
+ .alloc_hw_port_stats = mlx4_ib_alloc_hw_port_stats,
+ .get_hw_stats = mlx4_ib_get_hw_stats,
+};
+
+static const struct ib_device_ops mlx4_ib_hw_stats_ops1 = {
+ .alloc_hw_device_stats = mlx4_ib_alloc_hw_device_stats,
+ .get_hw_stats = mlx4_ib_get_hw_stats,
+};
+
static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
{
struct mlx4_ib_diag_counters *diag = ibdev->diag_counters;
@@ -2309,28 +2226,34 @@ static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
return 0;
for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
- /* i == 1 means we are building port counters */
- if (i && !per_port)
- continue;
+ /*
+ * i == 1 means we are building port counters, set a different
+ * stats ops without port stats callback.
+ */
+ if (i && !per_port) {
+ ib_set_device_ops(&ibdev->ib_dev,
+ &mlx4_ib_hw_stats_ops1);
+
+ return 0;
+ }
- ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].name,
+ ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].descs,
&diag[i].offset,
&diag[i].num_counters, i);
if (ret)
goto err_alloc;
- mlx4_ib_fill_diag_counters(ibdev, diag[i].name,
+ mlx4_ib_fill_diag_counters(ibdev, diag[i].descs,
diag[i].offset, i);
}
- ibdev->ib_dev.get_hw_stats = mlx4_ib_get_hw_stats;
- ibdev->ib_dev.alloc_hw_stats = mlx4_ib_alloc_hw_stats;
+ ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_hw_stats_ops);
return 0;
err_alloc:
if (i) {
- kfree(diag[i - 1].name);
+ kfree(diag[i - 1].descs);
kfree(diag[i - 1].offset);
}
@@ -2343,7 +2266,7 @@ static void mlx4_ib_diag_cleanup(struct mlx4_ib_dev *ibdev)
for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
kfree(ibdev->diag_counters[i].offset);
- kfree(ibdev->diag_counters[i].name);
+ kfree(ibdev->diag_counters[i].descs);
}
}
@@ -2356,10 +2279,7 @@ static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
u64 release_mac = MLX4_IB_INVALID_MAC;
struct mlx4_ib_qp *qp;
- read_lock(&dev_base_lock);
- new_smac = mlx4_mac_to_u64(dev->dev_addr);
- read_unlock(&dev_base_lock);
-
+ new_smac = ether_addr_to_u64(dev->dev_addr);
atomic64_set(&ibdev->iboe.mac[port - 1], new_smac);
/* no need for update QP1 and mac registration in non-SRIOV */
@@ -2405,35 +2325,54 @@ unlock:
mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]);
}
-static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
- struct net_device *dev,
- unsigned long event)
+static void mlx4_ib_scan_netdev(struct mlx4_ib_dev *ibdev,
+ struct net_device *dev,
+ unsigned long event)
{
- struct mlx4_ib_iboe *iboe;
- int update_qps_port = -1;
- int port;
+ struct mlx4_ib_iboe *iboe = &ibdev->iboe;
ASSERT_RTNL();
- iboe = &ibdev->iboe;
+ if (dev->dev.parent != ibdev->ib_dev.dev.parent)
+ return;
spin_lock_bh(&iboe->lock);
- mlx4_foreach_ib_transport_port(port, ibdev->dev) {
- iboe->netdevs[port - 1] =
- mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
+ iboe->netdevs[dev->dev_port] = event != NETDEV_UNREGISTER ? dev : NULL;
- if (dev == iboe->netdevs[port - 1] &&
- (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
- event == NETDEV_UP || event == NETDEV_CHANGE))
- update_qps_port = port;
+ spin_unlock_bh(&iboe->lock);
+
+ if (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER)
+ mlx4_ib_update_qps(ibdev, dev, dev->dev_port + 1);
+}
+
+static void mlx4_ib_port_event(struct ib_device *ibdev, struct net_device *ndev,
+ unsigned long event)
+{
+ struct mlx4_ib_dev *mlx4_ibdev =
+ container_of(ibdev, struct mlx4_ib_dev, ib_dev);
+ struct mlx4_ib_iboe *iboe = &mlx4_ibdev->iboe;
+
+ if (!net_eq(dev_net(ndev), &init_net))
+ return;
+
+ ASSERT_RTNL();
+
+ if (ndev->dev.parent != mlx4_ibdev->ib_dev.dev.parent)
+ return;
+
+ spin_lock_bh(&iboe->lock);
+
+ iboe->netdevs[ndev->dev_port] = event != NETDEV_UNREGISTER ? ndev : NULL;
+
+ if (event == NETDEV_UP || event == NETDEV_DOWN)
+ ib_dispatch_port_state_event(&mlx4_ibdev->ib_dev, ndev);
- }
spin_unlock_bh(&iboe->lock);
- if (update_qps_port > 0)
- mlx4_ib_update_qps(ibdev, dev, update_qps_port);
+ if (event == NETDEV_UP || event == NETDEV_CHANGE)
+ mlx4_ib_update_qps(mlx4_ibdev, ndev, ndev->dev_port + 1);
}
static int mlx4_ib_netdev_event(struct notifier_block *this,
@@ -2446,7 +2385,7 @@ static int mlx4_ib_netdev_event(struct notifier_block *this,
return NOTIFY_DONE;
ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
- mlx4_ib_scan_netdevs(ibdev, dev, event);
+ mlx4_ib_scan_netdev(ibdev, dev, event);
return NOTIFY_DONE;
}
@@ -2534,7 +2473,7 @@ static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
ibdev->eq_table = NULL;
}
-static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
+static int mlx4_port_immutable(struct ib_device *ibdev, u32 port_num,
struct ib_port_immutable *immutable)
{
struct ib_port_attr attr;
@@ -2566,19 +2505,116 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
return 0;
}
-static void get_fw_ver_str(struct ib_device *device, char *str,
- size_t str_len)
+static void get_fw_ver_str(struct ib_device *device, char *str)
{
struct mlx4_ib_dev *dev =
container_of(device, struct mlx4_ib_dev, ib_dev);
- snprintf(str, str_len, "%d.%d.%d",
+ snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
(int) (dev->dev->caps.fw_ver >> 32),
(int) (dev->dev->caps.fw_ver >> 16) & 0xffff,
(int) dev->dev->caps.fw_ver & 0xffff);
}
-static void *mlx4_ib_add(struct mlx4_dev *dev)
+static const struct ib_device_ops mlx4_ib_dev_ops = {
+ .owner = THIS_MODULE,
+ .driver_id = RDMA_DRIVER_MLX4,
+ .uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION,
+
+ .add_gid = mlx4_ib_add_gid,
+ .alloc_mr = mlx4_ib_alloc_mr,
+ .alloc_pd = mlx4_ib_alloc_pd,
+ .alloc_ucontext = mlx4_ib_alloc_ucontext,
+ .attach_mcast = mlx4_ib_mcg_attach,
+ .create_ah = mlx4_ib_create_ah,
+ .create_cq = mlx4_ib_create_cq,
+ .create_qp = mlx4_ib_create_qp,
+ .create_srq = mlx4_ib_create_srq,
+ .dealloc_pd = mlx4_ib_dealloc_pd,
+ .dealloc_ucontext = mlx4_ib_dealloc_ucontext,
+ .del_gid = mlx4_ib_del_gid,
+ .dereg_mr = mlx4_ib_dereg_mr,
+ .destroy_ah = mlx4_ib_destroy_ah,
+ .destroy_cq = mlx4_ib_destroy_cq,
+ .destroy_qp = mlx4_ib_destroy_qp,
+ .destroy_srq = mlx4_ib_destroy_srq,
+ .detach_mcast = mlx4_ib_mcg_detach,
+ .device_group = &mlx4_attr_group,
+ .disassociate_ucontext = mlx4_ib_disassociate_ucontext,
+ .drain_rq = mlx4_ib_drain_rq,
+ .drain_sq = mlx4_ib_drain_sq,
+ .get_dev_fw_str = get_fw_ver_str,
+ .get_dma_mr = mlx4_ib_get_dma_mr,
+ .get_link_layer = mlx4_ib_port_link_layer,
+ .get_netdev = mlx4_ib_get_netdev,
+ .get_port_immutable = mlx4_port_immutable,
+ .map_mr_sg = mlx4_ib_map_mr_sg,
+ .mmap = mlx4_ib_mmap,
+ .modify_cq = mlx4_ib_modify_cq,
+ .modify_device = mlx4_ib_modify_device,
+ .modify_port = mlx4_ib_modify_port,
+ .modify_qp = mlx4_ib_modify_qp,
+ .modify_srq = mlx4_ib_modify_srq,
+ .poll_cq = mlx4_ib_poll_cq,
+ .post_recv = mlx4_ib_post_recv,
+ .post_send = mlx4_ib_post_send,
+ .post_srq_recv = mlx4_ib_post_srq_recv,
+ .process_mad = mlx4_ib_process_mad,
+ .query_ah = mlx4_ib_query_ah,
+ .query_device = mlx4_ib_query_device,
+ .query_gid = mlx4_ib_query_gid,
+ .query_pkey = mlx4_ib_query_pkey,
+ .query_port = mlx4_ib_query_port,
+ .query_qp = mlx4_ib_query_qp,
+ .query_srq = mlx4_ib_query_srq,
+ .reg_user_mr = mlx4_ib_reg_user_mr,
+ .req_notify_cq = mlx4_ib_arm_cq,
+ .rereg_user_mr = mlx4_ib_rereg_user_mr,
+ .resize_cq = mlx4_ib_resize_cq,
+ .report_port_event = mlx4_ib_port_event,
+
+ INIT_RDMA_OBJ_SIZE(ib_ah, mlx4_ib_ah, ibah),
+ INIT_RDMA_OBJ_SIZE(ib_cq, mlx4_ib_cq, ibcq),
+ INIT_RDMA_OBJ_SIZE(ib_pd, mlx4_ib_pd, ibpd),
+ INIT_RDMA_OBJ_SIZE(ib_qp, mlx4_ib_qp, ibqp),
+ INIT_RDMA_OBJ_SIZE(ib_srq, mlx4_ib_srq, ibsrq),
+ INIT_RDMA_OBJ_SIZE(ib_ucontext, mlx4_ib_ucontext, ibucontext),
+};
+
+static const struct ib_device_ops mlx4_ib_dev_wq_ops = {
+ .create_rwq_ind_table = mlx4_ib_create_rwq_ind_table,
+ .create_wq = mlx4_ib_create_wq,
+ .destroy_rwq_ind_table = mlx4_ib_destroy_rwq_ind_table,
+ .destroy_wq = mlx4_ib_destroy_wq,
+ .modify_wq = mlx4_ib_modify_wq,
+
+ INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mlx4_ib_rwq_ind_table,
+ ib_rwq_ind_tbl),
+};
+
+static const struct ib_device_ops mlx4_ib_dev_mw_ops = {
+ .alloc_mw = mlx4_ib_alloc_mw,
+ .dealloc_mw = mlx4_ib_dealloc_mw,
+
+ INIT_RDMA_OBJ_SIZE(ib_mw, mlx4_ib_mw, ibmw),
+};
+
+static const struct ib_device_ops mlx4_ib_dev_xrc_ops = {
+ .alloc_xrcd = mlx4_ib_alloc_xrcd,
+ .dealloc_xrcd = mlx4_ib_dealloc_xrcd,
+
+ INIT_RDMA_OBJ_SIZE(ib_xrcd, mlx4_ib_xrcd, ibxrcd),
+};
+
+static const struct ib_device_ops mlx4_ib_dev_fs_ops = {
+ .create_flow = mlx4_ib_create_flow,
+ .destroy_flow = mlx4_ib_destroy_flow,
+};
+
+static int mlx4_ib_probe(struct auxiliary_device *adev,
+ const struct auxiliary_device_id *id)
{
+ struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+ struct mlx4_dev *dev = madev->mdev;
struct mlx4_ib_dev *ibdev;
int num_ports = 0;
int i, j;
@@ -2588,7 +2624,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
int num_req_counters;
int allocated;
u32 counter_index;
- struct counter_index *new_counter_index = NULL;
+ struct counter_index *new_counter_index;
pr_info_once("%s", mlx4_ib_version);
@@ -2598,34 +2634,36 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
/* No point in registering a device with no ports... */
if (num_ports == 0)
- return NULL;
+ return -ENODEV;
- ibdev = (struct mlx4_ib_dev *) ib_alloc_device(sizeof *ibdev);
+ ibdev = ib_alloc_device(mlx4_ib_dev, ib_dev);
if (!ibdev) {
dev_err(&dev->persist->pdev->dev,
"Device struct alloc failed\n");
- return NULL;
+ return -ENOMEM;
}
iboe = &ibdev->iboe;
- if (mlx4_pd_alloc(dev, &ibdev->priv_pdn))
+ err = mlx4_pd_alloc(dev, &ibdev->priv_pdn);
+ if (err)
goto err_dealloc;
- if (mlx4_uar_alloc(dev, &ibdev->priv_uar))
+ err = mlx4_uar_alloc(dev, &ibdev->priv_uar);
+ if (err)
goto err_pd;
ibdev->uar_map = ioremap((phys_addr_t) ibdev->priv_uar.pfn << PAGE_SHIFT,
PAGE_SIZE);
- if (!ibdev->uar_map)
+ if (!ibdev->uar_map) {
+ err = -ENOMEM;
goto err_uar;
+ }
MLX4_INIT_DOORBELL_LOCK(&ibdev->uar_lock);
ibdev->dev = dev;
ibdev->bond_next_port = 0;
- strlcpy(ibdev->ib_dev.name, "mlx4_%d", IB_DEVICE_NAME_MAX);
- ibdev->ib_dev.owner = THIS_MODULE;
ibdev->ib_dev.node_type = RDMA_NODE_IB_CA;
ibdev->ib_dev.local_dma_lkey = dev->caps.reserved_lkey;
ibdev->num_ports = num_ports;
@@ -2633,137 +2671,46 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
1 : ibdev->num_ports;
ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors;
ibdev->ib_dev.dev.parent = &dev->persist->pdev->dev;
- ibdev->ib_dev.get_netdev = mlx4_ib_get_netdev;
- ibdev->ib_dev.add_gid = mlx4_ib_add_gid;
- ibdev->ib_dev.del_gid = mlx4_ib_del_gid;
- if (dev->caps.userspace_caps)
- ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION;
- else
- ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION;
-
- ibdev->ib_dev.uverbs_cmd_mask =
- (1ull << IB_USER_VERBS_CMD_GET_CONTEXT) |
- (1ull << IB_USER_VERBS_CMD_QUERY_DEVICE) |
- (1ull << IB_USER_VERBS_CMD_QUERY_PORT) |
- (1ull << IB_USER_VERBS_CMD_ALLOC_PD) |
- (1ull << IB_USER_VERBS_CMD_DEALLOC_PD) |
- (1ull << IB_USER_VERBS_CMD_REG_MR) |
- (1ull << IB_USER_VERBS_CMD_REREG_MR) |
- (1ull << IB_USER_VERBS_CMD_DEREG_MR) |
- (1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) |
- (1ull << IB_USER_VERBS_CMD_CREATE_CQ) |
- (1ull << IB_USER_VERBS_CMD_RESIZE_CQ) |
- (1ull << IB_USER_VERBS_CMD_DESTROY_CQ) |
- (1ull << IB_USER_VERBS_CMD_CREATE_QP) |
- (1ull << IB_USER_VERBS_CMD_MODIFY_QP) |
- (1ull << IB_USER_VERBS_CMD_QUERY_QP) |
- (1ull << IB_USER_VERBS_CMD_DESTROY_QP) |
- (1ull << IB_USER_VERBS_CMD_ATTACH_MCAST) |
- (1ull << IB_USER_VERBS_CMD_DETACH_MCAST) |
- (1ull << IB_USER_VERBS_CMD_CREATE_SRQ) |
- (1ull << IB_USER_VERBS_CMD_MODIFY_SRQ) |
- (1ull << IB_USER_VERBS_CMD_QUERY_SRQ) |
- (1ull << IB_USER_VERBS_CMD_DESTROY_SRQ) |
- (1ull << IB_USER_VERBS_CMD_CREATE_XSRQ) |
- (1ull << IB_USER_VERBS_CMD_OPEN_QP);
-
- ibdev->ib_dev.query_device = mlx4_ib_query_device;
- ibdev->ib_dev.query_port = mlx4_ib_query_port;
- ibdev->ib_dev.get_link_layer = mlx4_ib_port_link_layer;
- ibdev->ib_dev.query_gid = mlx4_ib_query_gid;
- ibdev->ib_dev.query_pkey = mlx4_ib_query_pkey;
- ibdev->ib_dev.modify_device = mlx4_ib_modify_device;
- ibdev->ib_dev.modify_port = mlx4_ib_modify_port;
- ibdev->ib_dev.alloc_ucontext = mlx4_ib_alloc_ucontext;
- ibdev->ib_dev.dealloc_ucontext = mlx4_ib_dealloc_ucontext;
- ibdev->ib_dev.mmap = mlx4_ib_mmap;
- ibdev->ib_dev.alloc_pd = mlx4_ib_alloc_pd;
- ibdev->ib_dev.dealloc_pd = mlx4_ib_dealloc_pd;
- ibdev->ib_dev.create_ah = mlx4_ib_create_ah;
- ibdev->ib_dev.query_ah = mlx4_ib_query_ah;
- ibdev->ib_dev.destroy_ah = mlx4_ib_destroy_ah;
- ibdev->ib_dev.create_srq = mlx4_ib_create_srq;
- ibdev->ib_dev.modify_srq = mlx4_ib_modify_srq;
- ibdev->ib_dev.query_srq = mlx4_ib_query_srq;
- ibdev->ib_dev.destroy_srq = mlx4_ib_destroy_srq;
- ibdev->ib_dev.post_srq_recv = mlx4_ib_post_srq_recv;
- ibdev->ib_dev.create_qp = mlx4_ib_create_qp;
- ibdev->ib_dev.modify_qp = mlx4_ib_modify_qp;
- ibdev->ib_dev.query_qp = mlx4_ib_query_qp;
- ibdev->ib_dev.destroy_qp = mlx4_ib_destroy_qp;
- ibdev->ib_dev.post_send = mlx4_ib_post_send;
- ibdev->ib_dev.post_recv = mlx4_ib_post_recv;
- ibdev->ib_dev.create_cq = mlx4_ib_create_cq;
- ibdev->ib_dev.modify_cq = mlx4_ib_modify_cq;
- ibdev->ib_dev.resize_cq = mlx4_ib_resize_cq;
- ibdev->ib_dev.destroy_cq = mlx4_ib_destroy_cq;
- ibdev->ib_dev.poll_cq = mlx4_ib_poll_cq;
- ibdev->ib_dev.req_notify_cq = mlx4_ib_arm_cq;
- ibdev->ib_dev.get_dma_mr = mlx4_ib_get_dma_mr;
- ibdev->ib_dev.reg_user_mr = mlx4_ib_reg_user_mr;
- ibdev->ib_dev.rereg_user_mr = mlx4_ib_rereg_user_mr;
- ibdev->ib_dev.dereg_mr = mlx4_ib_dereg_mr;
- ibdev->ib_dev.alloc_mr = mlx4_ib_alloc_mr;
- ibdev->ib_dev.map_mr_sg = mlx4_ib_map_mr_sg;
- ibdev->ib_dev.attach_mcast = mlx4_ib_mcg_attach;
- ibdev->ib_dev.detach_mcast = mlx4_ib_mcg_detach;
- ibdev->ib_dev.process_mad = mlx4_ib_process_mad;
- ibdev->ib_dev.get_port_immutable = mlx4_port_immutable;
- ibdev->ib_dev.get_dev_fw_str = get_fw_ver_str;
- ibdev->ib_dev.disassociate_ucontext = mlx4_ib_disassociate_ucontext;
-
- if (!mlx4_is_slave(ibdev->dev)) {
- ibdev->ib_dev.alloc_fmr = mlx4_ib_fmr_alloc;
- ibdev->ib_dev.map_phys_fmr = mlx4_ib_map_phys_fmr;
- ibdev->ib_dev.unmap_fmr = mlx4_ib_unmap_fmr;
- ibdev->ib_dev.dealloc_fmr = mlx4_ib_fmr_dealloc;
- }
+ ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_ops);
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
- dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
- ibdev->ib_dev.alloc_mw = mlx4_ib_alloc_mw;
- ibdev->ib_dev.dealloc_mw = mlx4_ib_dealloc_mw;
+ if ((dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) &&
+ ((mlx4_ib_port_link_layer(&ibdev->ib_dev, 1) ==
+ IB_LINK_LAYER_ETHERNET) ||
+ (mlx4_ib_port_link_layer(&ibdev->ib_dev, 2) ==
+ IB_LINK_LAYER_ETHERNET)))
+ ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_wq_ops);
- ibdev->ib_dev.uverbs_cmd_mask |=
- (1ull << IB_USER_VERBS_CMD_ALLOC_MW) |
- (1ull << IB_USER_VERBS_CMD_DEALLOC_MW);
- }
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
+ dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)
+ ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_mw_ops);
if (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) {
- ibdev->ib_dev.alloc_xrcd = mlx4_ib_alloc_xrcd;
- ibdev->ib_dev.dealloc_xrcd = mlx4_ib_dealloc_xrcd;
- ibdev->ib_dev.uverbs_cmd_mask |=
- (1ull << IB_USER_VERBS_CMD_OPEN_XRCD) |
- (1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
+ ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_xrc_ops);
}
if (check_flow_steering_support(dev)) {
ibdev->steering_support = MLX4_STEERING_MODE_DEVICE_MANAGED;
- ibdev->ib_dev.create_flow = mlx4_ib_create_flow;
- ibdev->ib_dev.destroy_flow = mlx4_ib_destroy_flow;
-
- ibdev->ib_dev.uverbs_ex_cmd_mask |=
- (1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) |
- (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW);
+ ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_fs_ops);
}
- ibdev->ib_dev.uverbs_ex_cmd_mask |=
- (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) |
- (1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ) |
- (1ull << IB_USER_VERBS_EX_CMD_CREATE_QP);
+ if (!dev->caps.userspace_caps)
+ ibdev->ib_dev.ops.uverbs_abi_ver =
+ MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION;
mlx4_ib_alloc_eqs(dev, ibdev);
spin_lock_init(&iboe->lock);
- if (init_node_data(ibdev))
+ err = init_node_data(ibdev);
+ if (err)
goto err_map;
mlx4_init_sl2vl_tbl(ibdev);
for (i = 0; i < ibdev->num_ports; ++i) {
mutex_init(&ibdev->counters_table[i].mutex);
INIT_LIST_HEAD(&ibdev->counters_table[i].counters_list);
+ iboe->last_port_state[i] = IB_PORT_DOWN;
}
num_req_counters = mlx4_is_bonded(dev) ? 1 : ibdev->num_ports;
@@ -2772,7 +2719,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
allocated = 0;
if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) ==
IB_LINK_LAYER_ETHERNET) {
- err = mlx4_counter_alloc(ibdev->dev, &counter_index);
+ err = mlx4_counter_alloc(ibdev->dev, &counter_index,
+ MLX4_RES_USAGE_DRIVER);
/* if failed to allocate a new counter, use default */
if (err)
counter_index =
@@ -2787,6 +2735,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
new_counter_index = kmalloc(sizeof(*new_counter_index),
GFP_KERNEL);
if (!new_counter_index) {
+ err = -ENOMEM;
if (allocated)
mlx4_counter_free(ibdev->dev, counter_index);
goto err_counter;
@@ -2804,8 +2753,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
new_counter_index =
kmalloc(sizeof(struct counter_index),
GFP_KERNEL);
- if (!new_counter_index)
+ if (!new_counter_index) {
+ err = -ENOMEM;
goto err_counter;
+ }
new_counter_index->index = counter_index;
new_counter_index->allocated = 0;
list_add_tail(&new_counter_index->list,
@@ -2827,16 +2778,17 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
MLX4_IB_UC_STEER_QPN_ALIGN,
- &ibdev->steer_qpn_base, 0);
+ &ibdev->steer_qpn_base, 0,
+ MLX4_RES_USAGE_DRIVER);
if (err)
goto err_counter;
- ibdev->ib_uc_qpns_bitmap =
- kmalloc(BITS_TO_LONGS(ibdev->steer_qpn_count) *
- sizeof(long),
- GFP_KERNEL);
- if (!ibdev->ib_uc_qpns_bitmap)
+ ibdev->ib_uc_qpns_bitmap = bitmap_alloc(ibdev->steer_qpn_count,
+ GFP_KERNEL);
+ if (!ibdev->ib_uc_qpns_bitmap) {
+ err = -ENOMEM;
goto err_steer_qp_release;
+ }
if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB) {
bitmap_zero(ibdev->ib_uc_qpns_bitmap,
@@ -2856,16 +2808,21 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
for (j = 1; j <= ibdev->dev->caps.num_ports; j++)
atomic64_set(&iboe->mac[j - 1], ibdev->dev->caps.def_mac[j]);
- if (mlx4_ib_alloc_diag_counters(ibdev))
+ err = mlx4_ib_alloc_diag_counters(ibdev);
+ if (err)
goto err_steer_free_bitmap;
- if (ib_register_device(&ibdev->ib_dev, NULL))
+ err = ib_register_device(&ibdev->ib_dev, "mlx4_%d",
+ &dev->persist->pdev->dev);
+ if (err)
goto err_diag_counters;
- if (mlx4_ib_mad_init(ibdev))
+ err = mlx4_ib_mad_init(ibdev);
+ if (err)
goto err_reg;
- if (mlx4_ib_init_sriov(ibdev))
+ err = mlx4_ib_init_sriov(ibdev);
+ if (err)
goto err_mad;
if (!iboe->nb.notifier_call) {
@@ -2882,12 +2839,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
goto err_notif;
}
- for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) {
- if (device_create_file(&ibdev->ib_dev.dev,
- mlx4_class_attributes[j]))
- goto err_notif;
- }
-
ibdev->ib_active = true;
mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
devlink_port_type_ib_set(mlx4_get_devlink_port(dev, i),
@@ -2905,7 +2856,14 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
do_slave_init(ibdev, j, 1);
}
}
- return ibdev;
+
+ /* register mlx4 core notifier */
+ ibdev->mlx_nb.notifier_call = mlx4_ib_event;
+ err = mlx4_register_event_notifier(dev, &ibdev->mlx_nb);
+ WARN(err, "failed to register mlx4 event notifier (%d)", err);
+
+ auxiliary_set_drvdata(adev, ibdev);
+ return 0;
err_notif:
if (ibdev->iboe.nb.notifier_call) {
@@ -2927,12 +2885,11 @@ err_diag_counters:
mlx4_ib_diag_cleanup(ibdev);
err_steer_free_bitmap:
- kfree(ibdev->ib_uc_qpns_bitmap);
+ bitmap_free(ibdev->ib_uc_qpns_bitmap);
err_steer_qp_release:
- if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
- mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
- ibdev->steer_qpn_count);
+ mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
+ ibdev->steer_qpn_count);
err_counter:
for (i = 0; i < ibdev->num_ports; ++i)
mlx4_ib_delete_counters_table(ibdev, &ibdev->counters_table[i]);
@@ -2950,7 +2907,7 @@ err_pd:
err_dealloc:
ib_dealloc_device(&ibdev->ib_dev);
- return NULL;
+ return err;
}
int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn)
@@ -2975,7 +2932,10 @@ void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count)
dev->steering_support != MLX4_STEERING_MODE_DEVICE_MANAGED)
return;
- BUG_ON(qpn < dev->steer_qpn_base);
+ if (WARN(qpn < dev->steer_qpn_base, "qpn = %u, steer_qpn_base = %u\n",
+ qpn, dev->steer_qpn_base))
+ /* not supposed to be here */
+ return;
bitmap_release_region(dev->ib_uc_qpns_bitmap,
qpn - dev->steer_qpn_base,
@@ -2987,7 +2947,7 @@ int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
{
int err;
size_t flow_size;
- struct ib_flow_attr *flow = NULL;
+ struct ib_flow_attr *flow;
struct ib_flow_spec_ib *ib_spec;
if (is_attach) {
@@ -3005,43 +2965,44 @@ int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
/* Add an empty rule for IB L2 */
memset(&ib_spec->mask, 0, sizeof(ib_spec->mask));
- err = __mlx4_ib_create_flow(&mqp->ibqp, flow,
- IB_FLOW_DOMAIN_NIC,
- MLX4_FS_REGULAR,
- &mqp->reg_id);
- } else {
- err = __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
+ err = __mlx4_ib_create_flow(&mqp->ibqp, flow, MLX4_DOMAIN_NIC,
+ MLX4_FS_REGULAR, &mqp->reg_id);
+ kfree(flow);
+ return err;
}
- kfree(flow);
- return err;
+
+ return __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
}
-static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
+static void mlx4_ib_remove(struct auxiliary_device *adev)
{
- struct mlx4_ib_dev *ibdev = ibdev_ptr;
+ struct mlx4_adev *madev = container_of(adev, struct mlx4_adev, adev);
+ struct mlx4_dev *dev = madev->mdev;
+ struct mlx4_ib_dev *ibdev = auxiliary_get_drvdata(adev);
int p;
int i;
+ mlx4_unregister_event_notifier(dev, &ibdev->mlx_nb);
+
mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
devlink_port_type_clear(mlx4_get_devlink_port(dev, i));
ibdev->ib_active = false;
flush_workqueue(wq);
- mlx4_ib_close_sriov(ibdev);
- mlx4_ib_mad_cleanup(ibdev);
- ib_unregister_device(&ibdev->ib_dev);
- mlx4_ib_diag_cleanup(ibdev);
if (ibdev->iboe.nb.notifier_call) {
if (unregister_netdevice_notifier(&ibdev->iboe.nb))
pr_warn("failure unregistering notifier\n");
ibdev->iboe.nb.notifier_call = NULL;
}
- if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) {
- mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
- ibdev->steer_qpn_count);
- kfree(ibdev->ib_uc_qpns_bitmap);
- }
+ mlx4_ib_close_sriov(ibdev);
+ mlx4_ib_mad_cleanup(ibdev);
+ ib_unregister_device(&ibdev->ib_dev);
+ mlx4_ib_diag_cleanup(ibdev);
+
+ mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
+ ibdev->steer_qpn_count);
+ bitmap_free(ibdev->ib_uc_qpns_bitmap);
iounmap(ibdev->uar_map);
for (p = 0; p < ibdev->num_ports; ++p)
@@ -3059,7 +3020,7 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
{
- struct mlx4_ib_demux_work **dm = NULL;
+ struct mlx4_ib_demux_work **dm;
struct mlx4_dev *dev = ibdev->dev;
int i;
unsigned long flags;
@@ -3243,11 +3204,13 @@ void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
}
}
-static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
- enum mlx4_dev_event event, unsigned long param)
+static int mlx4_ib_event(struct notifier_block *this, unsigned long event,
+ void *param)
{
+ struct mlx4_ib_dev *ibdev =
+ container_of(this, struct mlx4_ib_dev, mlx_nb);
+ struct mlx4_dev *dev = ibdev->dev;
struct ib_event ibev;
- struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
struct mlx4_eqe *eqe = NULL;
struct ib_event_work *ew;
int p = 0;
@@ -3257,22 +3220,28 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
(event == MLX4_DEV_EVENT_PORT_DOWN))) {
ew = kmalloc(sizeof(*ew), GFP_ATOMIC);
if (!ew)
- return;
+ return NOTIFY_DONE;
INIT_WORK(&ew->work, handle_bonded_port_state_event);
ew->ib_dev = ibdev;
queue_work(wq, &ew->work);
- return;
+ return NOTIFY_DONE;
}
- if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE)
+ switch (event) {
+ case MLX4_DEV_EVENT_CATASTROPHIC_ERROR:
+ break;
+ case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
eqe = (struct mlx4_eqe *)param;
- else
- p = (int) param;
+ break;
+ default:
+ p = *(int *)param;
+ break;
+ }
switch (event) {
case MLX4_DEV_EVENT_PORT_UP:
if (p > ibdev->num_ports)
- return;
+ return NOTIFY_DONE;
if (!mlx4_is_slave(dev) &&
rdma_port_get_link_layer(&ibdev->ib_dev, p) ==
IB_LINK_LAYER_INFINIBAND) {
@@ -3287,7 +3256,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
case MLX4_DEV_EVENT_PORT_DOWN:
if (p > ibdev->num_ports)
- return;
+ return NOTIFY_DONE;
ibev.event = IB_EVENT_PORT_ERR;
break;
@@ -3300,7 +3269,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
ew = kmalloc(sizeof *ew, GFP_ATOMIC);
if (!ew)
- break;
+ return NOTIFY_DONE;
INIT_WORK(&ew->work, handle_port_mgmt_change_event);
memcpy(&ew->ib_eqe, eqe, sizeof *eqe);
@@ -3310,7 +3279,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
queue_work(wq, &ew->work);
else
handle_port_mgmt_change_event(&ew->work);
- return;
+ return NOTIFY_DONE;
case MLX4_DEV_EVENT_SLAVE_INIT:
/* here, p is the slave id */
@@ -3326,7 +3295,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
1);
}
}
- return;
+ return NOTIFY_DONE;
case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
if (mlx4_is_master(dev)) {
@@ -3342,22 +3311,33 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
}
/* here, p is the slave id */
do_slave_init(ibdev, p, 0);
- return;
+ return NOTIFY_DONE;
default:
- return;
+ return NOTIFY_DONE;
}
- ibev.device = ibdev_ptr;
+ ibev.device = &ibdev->ib_dev;
ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p;
ib_dispatch_event(&ibev);
+ return NOTIFY_DONE;
}
-static struct mlx4_interface mlx4_ib_interface = {
- .add = mlx4_ib_add,
- .remove = mlx4_ib_remove,
- .event = mlx4_ib_event,
+static const struct auxiliary_device_id mlx4_ib_id_table[] = {
+ { .name = MLX4_ADEV_NAME ".ib" },
+ {},
+};
+
+MODULE_DEVICE_TABLE(auxiliary, mlx4_ib_id_table);
+
+static struct mlx4_adrv mlx4_ib_adrv = {
+ .adrv = {
+ .name = "ib",
+ .probe = mlx4_ib_probe,
+ .remove = mlx4_ib_remove,
+ .id_table = mlx4_ib_id_table,
+ },
.protocol = MLX4_PROT_IB_IPV6,
.flags = MLX4_INTFF_BONDING
};
@@ -3370,11 +3350,19 @@ static int __init mlx4_ib_init(void)
if (!wq)
return -ENOMEM;
- err = mlx4_ib_mcg_init();
+ err = mlx4_ib_qp_event_init();
+ if (err)
+ goto clean_qp_event;
+
+ err = mlx4_ib_cm_init();
if (err)
goto clean_wq;
- err = mlx4_register_interface(&mlx4_ib_interface);
+ err = mlx4_ib_mcg_init();
+ if (err)
+ goto clean_cm;
+
+ err = mlx4_register_auxiliary_driver(&mlx4_ib_adrv);
if (err)
goto clean_mcg;
@@ -3383,15 +3371,23 @@ static int __init mlx4_ib_init(void)
clean_mcg:
mlx4_ib_mcg_destroy();
+clean_cm:
+ mlx4_ib_cm_destroy();
+
clean_wq:
+ mlx4_ib_qp_event_cleanup();
+
+clean_qp_event:
destroy_workqueue(wq);
return err;
}
static void __exit mlx4_ib_cleanup(void)
{
- mlx4_unregister_interface(&mlx4_ib_interface);
+ mlx4_unregister_auxiliary_driver(&mlx4_ib_adrv);
mlx4_ib_mcg_destroy();
+ mlx4_ib_cm_destroy();
+ mlx4_ib_qp_event_cleanup();
destroy_workqueue(wq);
}
generated by cgit (git 2.34.1) at 2025-12-25 08:52:41 +0000