aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/mlx4
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/hw/mlx4')
-rw-r--r--drivers/infiniband/hw/mlx4/Kconfig2
-rw-r--r--drivers/infiniband/hw/mlx4/ah.c42
-rw-r--r--drivers/infiniband/hw/mlx4/alias_GUID.c2
-rw-r--r--drivers/infiniband/hw/mlx4/cm.c113
-rw-r--r--drivers/infiniband/hw/mlx4/cq.c75
-rw-r--r--drivers/infiniband/hw/mlx4/doorbell.c4
-rw-r--r--drivers/infiniband/hw/mlx4/mad.c181
-rw-r--r--drivers/infiniband/hw/mlx4/main.c1166
-rw-r--r--drivers/infiniband/hw/mlx4/mcg.c5
-rw-r--r--drivers/infiniband/hw/mlx4/mlx4_ib.h76
-rw-r--r--drivers/infiniband/hw/mlx4/mr.c126
-rw-r--r--drivers/infiniband/hw/mlx4/qp.c601
-rw-r--r--drivers/infiniband/hw/mlx4/srq.c7
-rw-r--r--drivers/infiniband/hw/mlx4/sysfs.c120
14 files changed, 2087 insertions, 433 deletions
diff --git a/drivers/infiniband/hw/mlx4/Kconfig b/drivers/infiniband/hw/mlx4/Kconfig
index 24ab11a9ad1..fc01deac1d3 100644
--- a/drivers/infiniband/hw/mlx4/Kconfig
+++ b/drivers/infiniband/hw/mlx4/Kconfig
@@ -1,6 +1,6 @@
config MLX4_INFINIBAND
tristate "Mellanox ConnectX HCA support"
- depends on NETDEVICES && ETHERNET && PCI
+ depends on NETDEVICES && ETHERNET && PCI && INET
select NET_VENDOR_MELLANOX
select MLX4_CORE
---help---
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index a251becdaa9..2d8c3397774 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -39,25 +39,6 @@
#include "mlx4_ib.h"
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
- u8 *mac, int *is_mcast, u8 port)
-{
- struct in6_addr in6;
-
- *is_mcast = 0;
-
- memcpy(&in6, ah_attr->grh.dgid.raw, sizeof in6);
- if (rdma_link_local_addr(&in6))
- rdma_get_ll_mac(&in6, mac);
- else if (rdma_is_multicast_addr(&in6)) {
- rdma_get_mcast_mac(&in6, mac);
- *is_mcast = 1;
- } else
- return -EINVAL;
-
- return 0;
-}
-
static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
struct mlx4_ib_ah *ah)
{
@@ -92,21 +73,18 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
{
struct mlx4_ib_dev *ibdev = to_mdev(pd->device);
struct mlx4_dev *dev = ibdev->dev;
- union ib_gid sgid;
- u8 mac[6];
- int err;
- int is_mcast;
+ int is_mcast = 0;
+ struct in6_addr in6;
u16 vlan_tag;
- err = mlx4_ib_resolve_grh(ibdev, ah_attr, mac, &is_mcast, ah_attr->port_num);
- if (err)
- return ERR_PTR(err);
-
- memcpy(ah->av.eth.mac, mac, 6);
- err = ib_get_cached_gid(pd->device, ah_attr->port_num, ah_attr->grh.sgid_index, &sgid);
- if (err)
- return ERR_PTR(err);
- vlan_tag = rdma_get_vlan_id(&sgid);
+ memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
+ if (rdma_is_multicast_addr(&in6)) {
+ is_mcast = 1;
+ rdma_get_mcast_mac(&in6, ah->av.eth.mac);
+ } else {
+ memcpy(ah->av.eth.mac, ah_attr->dmac, ETH_ALEN);
+ }
+ vlan_tag = ah_attr->vlan_id;
if (vlan_tag < 0x1000)
vlan_tag |= (ah_attr->sl & 7) << 13;
ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index 2f215b93db6..0eb141c4141 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -154,7 +154,7 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev,
continue;
slave_id = (block_num * NUM_ALIAS_GUID_IN_REC) + i ;
- if (slave_id >= dev->dev->num_slaves)
+ if (slave_id >= dev->dev->num_vfs + 1)
return;
tmp_cur_ag = *(__be64 *)&p_data[i * GUID_REC_SIZE];
form_cache_ag = get_cached_alias_guid(dev, port_num,
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index dbc99d41605..56a593e0ae5 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -61,6 +61,11 @@ struct cm_generic_msg {
__be32 remote_comm_id;
};
+struct cm_sidr_generic_msg {
+ struct ib_mad_hdr hdr;
+ __be32 request_id;
+};
+
struct cm_req_msg {
unsigned char unused[0x60];
union ib_gid primary_path_sgid;
@@ -69,28 +74,62 @@ struct cm_req_msg {
static void set_local_comm_id(struct ib_mad *mad, u32 cm_id)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
- msg->local_comm_id = cpu_to_be32(cm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ msg->request_id = cpu_to_be32(cm_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ pr_err("trying to set local_comm_id in SIDR_REP\n");
+ return;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ msg->local_comm_id = cpu_to_be32(cm_id);
+ }
}
static u32 get_local_comm_id(struct ib_mad *mad)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
-
- return be32_to_cpu(msg->local_comm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ return be32_to_cpu(msg->request_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ pr_err("trying to set local_comm_id in SIDR_REP\n");
+ return -1;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ return be32_to_cpu(msg->local_comm_id);
+ }
}
static void set_remote_comm_id(struct ib_mad *mad, u32 cm_id)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
- msg->remote_comm_id = cpu_to_be32(cm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ msg->request_id = cpu_to_be32(cm_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ pr_err("trying to set remote_comm_id in SIDR_REQ\n");
+ return;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ msg->remote_comm_id = cpu_to_be32(cm_id);
+ }
}
static u32 get_remote_comm_id(struct ib_mad *mad)
{
- struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
-
- return be32_to_cpu(msg->remote_comm_id);
+ if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
+ struct cm_sidr_generic_msg *msg =
+ (struct cm_sidr_generic_msg *)mad;
+ return be32_to_cpu(msg->request_id);
+ } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ pr_err("trying to set remote_comm_id in SIDR_REQ\n");
+ return -1;
+ } else {
+ struct cm_generic_msg *msg = (struct cm_generic_msg *)mad;
+ return be32_to_cpu(msg->remote_comm_id);
+ }
}
static union ib_gid gid_from_req_msg(struct ib_device *ibdev, struct ib_mad *mad)
@@ -203,8 +242,7 @@ static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new)
static struct id_map_entry *
id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id)
{
- int ret, id;
- static int next_id;
+ int ret;
struct id_map_entry *ent;
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
@@ -220,25 +258,22 @@ id_map_alloc(struct ib_device *ibdev, int slave_id, u32 sl_cm_id)
ent->dev = to_mdev(ibdev);
INIT_DELAYED_WORK(&ent->timeout, id_map_ent_timeout);
- do {
- spin_lock(&to_mdev(ibdev)->sriov.id_map_lock);
- ret = idr_get_new_above(&sriov->pv_id_table, ent,
- next_id, &id);
- if (!ret) {
- next_id = ((unsigned) id + 1) & MAX_IDR_MASK;
- ent->pv_cm_id = (u32)id;
- sl_id_map_add(ibdev, ent);
- }
+ idr_preload(GFP_KERNEL);
+ spin_lock(&to_mdev(ibdev)->sriov.id_map_lock);
- spin_unlock(&sriov->id_map_lock);
- } while (ret == -EAGAIN && idr_pre_get(&sriov->pv_id_table, GFP_KERNEL));
- /*the function idr_get_new_above can return -ENOSPC, so don't insert in that case.*/
- if (!ret) {
- spin_lock(&sriov->id_map_lock);
+ ret = idr_alloc_cyclic(&sriov->pv_id_table, ent, 0, 0, GFP_NOWAIT);
+ if (ret >= 0) {
+ ent->pv_cm_id = (u32)ret;
+ sl_id_map_add(ibdev, ent);
list_add_tail(&ent->list, &sriov->cm_list);
- spin_unlock(&sriov->id_map_lock);
- return ent;
}
+
+ spin_unlock(&sriov->id_map_lock);
+ idr_preload_end();
+
+ if (ret >= 0)
+ return ent;
+
/*error flow*/
kfree(ent);
mlx4_ib_warn(ibdev, "No more space in the idr (err:0x%x)\n", ret);
@@ -286,19 +321,21 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id
u32 sl_cm_id;
int pv_cm_id = -1;
- sl_cm_id = get_local_comm_id(mad);
-
if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
- mad->mad_hdr.attr_id == CM_REP_ATTR_ID) {
+ mad->mad_hdr.attr_id == CM_REP_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
+ sl_cm_id = get_local_comm_id(mad);
id = id_map_alloc(ibdev, slave_id, sl_cm_id);
if (IS_ERR(id)) {
mlx4_ib_warn(ibdev, "%s: id{slave: %d, sl_cm_id: 0x%x} Failed to id_map_alloc\n",
__func__, slave_id, sl_cm_id);
return PTR_ERR(id);
}
- } else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID) {
+ } else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) {
return 0;
} else {
+ sl_cm_id = get_local_comm_id(mad);
id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
}
@@ -319,14 +356,18 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id
}
int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
- struct ib_mad *mad)
+ struct ib_mad *mad)
{
u32 pv_cm_id;
struct id_map_entry *id;
- if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID) {
+ if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
union ib_gid gid;
+ if (!slave)
+ return 0;
+
gid = gid_from_req_msg(ibdev, mad);
*slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id);
if (*slave < 0) {
@@ -345,7 +386,8 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
return -ENOENT;
}
- *slave = id->slave_id;
+ if (slave)
+ *slave = id->slave_id;
set_remote_comm_id(mad, id->sl_cm_id);
if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
@@ -364,7 +406,6 @@ void mlx4_ib_cm_paravirt_init(struct mlx4_ib_dev *dev)
INIT_LIST_HEAD(&dev->sriov.cm_list);
dev->sriov.sl_id_map = RB_ROOT;
idr_init(&dev->sriov.pv_id_table);
- idr_pre_get(&dev->sriov.pv_id_table, GFP_KERNEL);
}
/* slave = -1 ==> all slaves */
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index ae67df35dd4..1066eec854a 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -33,6 +33,7 @@
#include <linux/mlx4/cq.h>
#include <linux/mlx4/qp.h>
+#include <linux/mlx4/srq.h>
#include <linux/slab.h>
#include "mlx4_ib.h"
@@ -101,7 +102,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
int err;
err = mlx4_buf_alloc(dev->dev, nent * dev->dev->caps.cqe_size,
- PAGE_SIZE * 2, &buf->buf);
+ PAGE_SIZE * 2, &buf->buf, GFP_KERNEL);
if (err)
goto out;
@@ -112,7 +113,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
if (err)
goto err_buf;
- err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf);
+ err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf, GFP_KERNEL);
if (err)
goto err_mtt;
@@ -208,7 +209,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
uar = &to_mucontext(context)->uar;
} else {
- err = mlx4_db_alloc(dev->dev, &cq->db, 1);
+ err = mlx4_db_alloc(dev->dev, &cq->db, 1, GFP_KERNEL);
if (err)
goto err_cq;
@@ -228,7 +229,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
vector = dev->eq_table[vector % ibdev->num_comp_vectors];
err = mlx4_cq_alloc(dev->dev, entries, &cq->buf.mtt, uar,
- cq->db.dma, &cq->mcq, vector, 0);
+ cq->db.dma, &cq->mcq, vector, 0, 0);
if (err)
goto err_dbmap;
@@ -323,7 +324,7 @@ static int mlx4_ib_get_outstanding_cqes(struct mlx4_ib_cq *cq)
u32 i;
i = cq->mcq.cons_index;
- while (get_sw_cqe(cq, i & cq->ibcq.cqe))
+ while (get_sw_cqe(cq, i))
++i;
return i - cq->mcq.cons_index;
@@ -364,7 +365,7 @@ int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
mutex_lock(&cq->resize_mutex);
- if (entries < 1 || entries > dev->dev->caps.max_cqes) {
+ if (entries < 1) {
err = -EINVAL;
goto out;
}
@@ -375,6 +376,11 @@ int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
goto out;
}
+ if (entries > dev->dev->caps.max_cqes) {
+ err = -EINVAL;
+ goto out;
+ }
+
if (ibcq->uobject) {
err = mlx4_alloc_resize_umem(dev, cq, entries, udata);
if (err)
@@ -558,7 +564,7 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum)
}
static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
- unsigned tail, struct mlx4_cqe *cqe)
+ unsigned tail, struct mlx4_cqe *cqe, int is_eth)
{
struct mlx4_ib_proxy_sqp_hdr *hdr;
@@ -568,12 +574,20 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct
DMA_FROM_DEVICE);
hdr = (struct mlx4_ib_proxy_sqp_hdr *) (qp->sqp_proxy_rcv[tail].addr);
wc->pkey_index = be16_to_cpu(hdr->tun.pkey_index);
- wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32);
- wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
wc->src_qp = be32_to_cpu(hdr->tun.flags_src_qp) & 0xFFFFFF;
wc->wc_flags |= (hdr->tun.g_ml_path & 0x80) ? (IB_WC_GRH) : 0;
wc->dlid_path_bits = 0;
+ if (is_eth) {
+ wc->vlan_id = be16_to_cpu(hdr->tun.sl_vid);
+ memcpy(&(wc->smac[0]), (char *)&hdr->tun.mac_31_0, 4);
+ memcpy(&(wc->smac[4]), (char *)&hdr->tun.slid_mac_47_32, 2);
+ wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC);
+ } else {
+ wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32);
+ wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
+ }
+
return 0;
}
@@ -585,8 +599,10 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
struct mlx4_qp *mqp;
struct mlx4_ib_wq *wq;
struct mlx4_ib_srq *srq;
+ struct mlx4_srq *msrq = NULL;
int is_send;
int is_error;
+ int is_eth;
u32 g_mlpath_rqpn;
u16 wqe_ctr;
unsigned tail = 0;
@@ -653,6 +669,20 @@ repoll:
wc->qp = &(*cur_qp)->ibqp;
+ if (wc->qp->qp_type == IB_QPT_XRC_TGT) {
+ u32 srq_num;
+ g_mlpath_rqpn = be32_to_cpu(cqe->g_mlpath_rqpn);
+ srq_num = g_mlpath_rqpn & 0xffffff;
+ /* SRQ is also in the radix tree */
+ msrq = mlx4_srq_lookup(to_mdev(cq->ibcq.device)->dev,
+ srq_num);
+ if (unlikely(!msrq)) {
+ pr_warn("CQ %06x with entry for unknown SRQN %06x\n",
+ cq->mcq.cqn, srq_num);
+ return -EINVAL;
+ }
+ }
+
if (is_send) {
wq = &(*cur_qp)->sq;
if (!(*cur_qp)->sq_signal_bits) {
@@ -666,6 +696,11 @@ repoll:
wqe_ctr = be16_to_cpu(cqe->wqe_index);
wc->wr_id = srq->wrid[wqe_ctr];
mlx4_ib_free_srq_wqe(srq, wqe_ctr);
+ } else if (msrq) {
+ srq = to_mibsrq(msrq);
+ wqe_ctr = be16_to_cpu(cqe->wqe_index);
+ wc->wr_id = srq->wrid[wqe_ctr];
+ mlx4_ib_free_srq_wqe(srq, wqe_ctr);
} else {
wq = &(*cur_qp)->rq;
tail = wq->tail & (wq->wqe_cnt - 1);
@@ -752,11 +787,15 @@ repoll:
break;
}
+ is_eth = (rdma_port_get_link_layer(wc->qp->device,
+ (*cur_qp)->port) ==
+ IB_LINK_LAYER_ETHERNET);
if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) {
if ((*cur_qp)->mlx4_ib_qp_type &
(MLX4_IB_QPT_PROXY_SMI_OWNER |
MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
- return use_tunnel_data(*cur_qp, cq, wc, tail, cqe);
+ return use_tunnel_data(*cur_qp, cq, wc, tail,
+ cqe, is_eth);
}
wc->slid = be16_to_cpu(cqe->rlid);
@@ -767,11 +806,21 @@ repoll:
wc->pkey_index = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f;
wc->wc_flags |= mlx4_ib_ipoib_csum_ok(cqe->status,
cqe->checksum) ? IB_WC_IP_CSUM_OK : 0;
- if (rdma_port_get_link_layer(wc->qp->device,
- (*cur_qp)->port) == IB_LINK_LAYER_ETHERNET)
+ if (is_eth) {
wc->sl = be16_to_cpu(cqe->sl_vid) >> 13;
- else
+ if (be32_to_cpu(cqe->vlan_my_qpn) &
+ MLX4_CQE_VLAN_PRESENT_MASK) {
+ wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
+ MLX4_CQE_VID_MASK;
+ } else {
+ wc->vlan_id = 0xffff;
+ }
+ memcpy(wc->smac, cqe->smac, ETH_ALEN);
+ wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC);
+ } else {
wc->sl = be16_to_cpu(cqe->sl_vid) >> 12;
+ wc->vlan_id = 0xffff;
+ }
}
return 0;
diff --git a/drivers/infiniband/hw/mlx4/doorbell.c b/drivers/infiniband/hw/mlx4/doorbell.c
index 8aee4233b38..c5174098636 100644
--- a/drivers/infiniband/hw/mlx4/doorbell.c
+++ b/drivers/infiniband/hw/mlx4/doorbell.c
@@ -45,7 +45,6 @@ int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
struct mlx4_db *db)
{
struct mlx4_ib_user_db_page *page;
- struct ib_umem_chunk *chunk;
int err = 0;
mutex_lock(&context->db_page_mutex);
@@ -73,8 +72,7 @@ int mlx4_ib_db_map_user(struct mlx4_ib_ucontext *context, unsigned long virt,
list_add(&page->list, &context->db_page_list);
found:
- chunk = list_entry(page->umem->chunk_list.next, struct ib_umem_chunk, list);
- db->dma = sg_dma_address(chunk->page_list) + (virt & ~PAGE_MASK);
+ db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK);
db->u.user_page = page;
++page->refcnt;
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 0a903c129f0..287ad0564ac 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -93,7 +93,7 @@ static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num,
__be64 mlx4_ib_gen_node_guid(void)
{
#define NODE_GUID_HI ((u64) (((u64)IB_OPENIB_OUI) << 40))
- return cpu_to_be64(NODE_GUID_HI | random32());
+ return cpu_to_be64(NODE_GUID_HI | prandom_u32());
}
__be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx)
@@ -467,6 +467,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
int ret = 0;
u16 tun_pkey_ix;
u16 cached_pkey;
+ u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
if (dest_qpt > IB_QPT_GSI)
return -EINVAL;
@@ -477,10 +478,6 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
if (!tun_ctx || tun_ctx->state != DEMUX_PV_STATE_ACTIVE)
return -EAGAIN;
- /* QP0 forwarding only for Dom0 */
- if (!dest_qpt && (mlx4_master_func_num(dev->dev) != slave))
- return -EINVAL;
-
if (!dest_qpt)
tun_qp = &tun_ctx->qp[0];
else
@@ -509,6 +506,10 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
* The driver will set the force loopback bit in post_send */
memset(&attr, 0, sizeof attr);
attr.port_num = port;
+ if (is_eth) {
+ memcpy(&attr.grh.dgid.raw[0], &grh->dgid.raw[0], 16);
+ attr.ah_flags = IB_AH_GRH;
+ }
ah = ib_create_ah(tun_ctx->pd, &attr);
if (IS_ERR(ah))
return -ENOMEM;
@@ -540,11 +541,36 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
/* adjust tunnel data */
tun_mad->hdr.pkey_index = cpu_to_be16(tun_pkey_ix);
- tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
- tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
tun_mad->hdr.flags_src_qp = cpu_to_be32(wc->src_qp & 0xFFFFFF);
tun_mad->hdr.g_ml_path = (grh && (wc->wc_flags & IB_WC_GRH)) ? 0x80 : 0;
+ if (is_eth) {
+ u16 vlan = 0;
+ if (mlx4_get_slave_default_vlan(dev->dev, port, slave, &vlan,
+ NULL)) {
+ /* VST mode */
+ if (vlan != wc->vlan_id)
+ /* Packet vlan is not the VST-assigned vlan.
+ * Drop the packet.
+ */
+ goto out;
+ else
+ /* Remove the vlan tag before forwarding
+ * the packet to the VF.
+ */
+ vlan = 0xffff;
+ } else {
+ vlan = wc->vlan_id;
+ }
+
+ tun_mad->hdr.sl_vid = cpu_to_be16(vlan);
+ memcpy((char *)&tun_mad->hdr.mac_31_0, &(wc->smac[0]), 4);
+ memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2);
+ } else {
+ tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
+ tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
+ }
+
ib_dma_sync_single_for_device(&dev->ib_dev,
tun_qp->tx_ring[tun_tx_ix].buf.map,
sizeof (struct mlx4_rcv_tunnel_mad),
@@ -580,6 +606,41 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
int err;
int slave;
u8 *slave_id;
+ int is_eth = 0;
+
+ if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND)
+ is_eth = 0;
+ else
+ is_eth = 1;
+
+ if (is_eth) {
+ if (!(wc->wc_flags & IB_WC_GRH)) {
+ mlx4_ib_warn(ibdev, "RoCE grh not present.\n");
+ return -EINVAL;
+ }
+ if (mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_CM) {
+ mlx4_ib_warn(ibdev, "RoCE mgmt class is not CM\n");
+ return -EINVAL;
+ }
+ if (mlx4_get_slave_from_roce_gid(dev->dev, port, grh->dgid.raw, &slave)) {
+ mlx4_ib_warn(ibdev, "failed matching grh\n");
+ return -ENOENT;
+ }
+ if (slave >= dev->dev->caps.sqp_demux) {
+ mlx4_ib_warn(ibdev, "slave id: %d is bigger than allowed:%d\n",
+ slave, dev->dev->caps.sqp_demux);
+ return -ENOENT;
+ }
+
+ if (mlx4_ib_demux_cm_handler(ibdev, port, NULL, mad))
+ return 0;
+
+ err = mlx4_ib_send_to_slave(dev, slave, port, wc->qp->qp_type, wc, grh, mad);
+ if (err)
+ pr_debug("failed sending to slave %d via tunnel qp (%d)\n",
+ slave, err);
+ return 0;
+ }
/* Initially assume that this mad is for us */
slave = mlx4_master_func_num(dev->dev);
@@ -602,6 +663,21 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
}
/* Class-specific handling */
switch (mad->mad_hdr.mgmt_class) {
+ case IB_MGMT_CLASS_SUBN_LID_ROUTED:
+ case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
+ /* 255 indicates the dom0 */
+ if (slave != 255 && slave != mlx4_master_func_num(dev->dev)) {
+ if (!mlx4_vf_smi_enabled(dev->dev, slave, port))
+ return -EPERM;
+ /* for a VF. drop unsolicited MADs */
+ if (!(mad->mad_hdr.method & IB_MGMT_METHOD_RESP)) {
+ mlx4_ib_warn(ibdev, "demux QP0. rejecting unsolicited mad for slave %d class 0x%x, method 0x%x\n",
+ slave, mad->mad_hdr.mgmt_class,
+ mad->mad_hdr.method);
+ return -EINVAL;
+ }
+ }
+ break;
case IB_MGMT_CLASS_SUBN_ADM:
if (mlx4_ib_demux_sa_handler(ibdev, port, slave,
(struct ib_sa_mad *) mad))
@@ -1076,8 +1152,9 @@ static int is_proxy_qp0(struct mlx4_ib_dev *dev, int qpn, int slave)
int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
- enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn,
- u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad)
+ enum ib_qp_type dest_qpt, u16 pkey_index,
+ u32 remote_qpn, u32 qkey, struct ib_ah_attr *attr,
+ u8 *s_mac, struct ib_mad *mad)
{
struct ib_sge list;
struct ib_send_wr wr, *bad_wr;
@@ -1099,10 +1176,6 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
if (!sqp_ctx || sqp_ctx->state != DEMUX_PV_STATE_ACTIVE)
return -EAGAIN;
- /* QP0 forwarding only for Dom0 */
- if (dest_qpt == IB_QPT_SMI && (mlx4_master_func_num(dev->dev) != slave))
- return -EINVAL;
-
if (dest_qpt == IB_QPT_SMI) {
src_qpnum = 0;
sqp = &sqp_ctx->qp[0];
@@ -1166,6 +1239,9 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
wr.num_sge = 1;
wr.opcode = IB_WR_SEND;
wr.send_flags = IB_SEND_SIGNALED;
+ if (s_mac)
+ memcpy(to_mah(ah)->av.eth.s_mac, s_mac, 6);
+
ret = ib_post_send(send_qp, &wr, &bad_wr);
out:
@@ -1174,6 +1250,22 @@ out:
return ret;
}
+static int get_slave_base_gid_ix(struct mlx4_ib_dev *dev, int slave, int port)
+{
+ if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND)
+ return slave;
+ return mlx4_get_base_gid_ix(dev->dev, slave, port);
+}
+
+static void fill_in_real_sgid_index(struct mlx4_ib_dev *dev, int slave, int port,
+ struct ib_ah_attr *ah_attr)
+{
+ if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND)
+ ah_attr->grh.sgid_index = slave;
+ else
+ ah_attr->grh.sgid_index += get_slave_base_gid_ix(dev, slave, port);
+}
+
static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc *wc)
{
struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev);
@@ -1184,6 +1276,7 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
struct ib_ah_attr ah_attr;
u8 *slave_id;
int slave;
+ int port;
/* Get slave that sent this packet */
if (wc->src_qp < dev->dev->phys_caps.base_proxy_sqpn ||
@@ -1199,11 +1292,6 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
"belongs to another slave\n", wc->src_qp);
return;
}
- if (slave != mlx4_master_func_num(dev->dev) && !(wc->src_qp & 0x2)) {
- mlx4_ib_warn(ctx->ib_dev, "can't multiplex bad sqp:%d: "
- "non-master trying to send QP0 packets\n", wc->src_qp);
- return;
- }
/* Map transaction ID */
ib_dma_sync_single_for_cpu(ctx->ib_dev, tun_qp->ring[wr_ix].map,
@@ -1231,6 +1319,12 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
/* Class-specific handling */
switch (tunnel->mad.mad_hdr.mgmt_class) {
+ case IB_MGMT_CLASS_SUBN_LID_ROUTED:
+ case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
+ if (slave != mlx4_master_func_num(dev->dev) &&
+ !mlx4_vf_smi_enabled(dev->dev, slave, ctx->port))
+ return;
+ break;
case IB_MGMT_CLASS_SUBN_ADM:
if (mlx4_ib_multiplex_sa_handler(ctx->ib_dev, ctx->port, slave,
(struct ib_sa_mad *) &tunnel->mad))
@@ -1260,12 +1354,18 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
memcpy(&ah.av, &tunnel->hdr.av, sizeof (struct mlx4_av));
ah.ibah.device = ctx->ib_dev;
mlx4_ib_query_ah(&ah.ibah, &ah_attr);
- if ((ah_attr.ah_flags & IB_AH_GRH) &&
- (ah_attr.grh.sgid_index != slave)) {
- mlx4_ib_warn(ctx->ib_dev, "slave:%d accessed invalid sgid_index:%d\n",
- slave, ah_attr.grh.sgid_index);
+ if (ah_attr.ah_flags & IB_AH_GRH)
+ fill_in_real_sgid_index(dev, slave, ctx->port, &ah_attr);
+
+ port = mlx4_slave_convert_port(dev->dev, slave, ah_attr.port_num);
+ if (port < 0)
return;
- }
+ ah_attr.port_num = port;
+ memcpy(ah_attr.dmac, tunnel->hdr.mac, 6);
+ ah_attr.vlan_id = be16_to_cpu(tunnel->hdr.vlan);
+ /* if slave have default vlan use it */
+ mlx4_get_slave_default_vlan(dev->dev, ctx->port, slave,
+ &ah_attr.vlan_id, &ah_attr.sl);
mlx4_ib_send_to_wire(dev, slave, ctx->port,
is_proxy_qp0(dev, wc->src_qp, slave) ?
@@ -1273,7 +1373,7 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
be16_to_cpu(tunnel->hdr.pkey_index),
be32_to_cpu(tunnel->hdr.remote_qpn),
be32_to_cpu(tunnel->hdr.qkey),
- &ah_attr, &tunnel->mad);
+ &ah_attr, wc->smac, &tunnel->mad);
}
static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
@@ -1511,8 +1611,14 @@ static int create_pv_sqp(struct mlx4_ib_demux_pv_ctx *ctx,
memset(&attr, 0, sizeof attr);
attr.qp_state = IB_QPS_INIT;
- attr.pkey_index =
- to_mdev(ctx->ib_dev)->pkeys.virt2phys_pkey[ctx->slave][ctx->port - 1][0];
+ ret = 0;
+ if (create_tun)
+ ret = find_slave_port_pkey_ix(to_mdev(ctx->ib_dev), ctx->slave,
+ ctx->port, IB_DEFAULT_PKEY_FULL,
+ &attr.pkey_index);
+ if (ret || !create_tun)
+ attr.pkey_index =
+ to_mdev(ctx->ib_dev)->pkeys.virt2phys_pkey[ctx->slave][ctx->port - 1][0];
attr.qkey = IB_QP1_QKEY;
attr.port_num = ctx->port;
ret = ib_modify_qp(tun_qp->qp, &attr, qp_attr_mask_INIT);
@@ -1651,9 +1757,9 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
return -EEXIST;
ctx->state = DEMUX_PV_STATE_STARTING;
- /* have QP0 only on port owner, and only if link layer is IB */
- if (ctx->slave == mlx4_master_func_num(to_mdev(ctx->ib_dev)->dev) &&
- rdma_port_get_link_layer(ibdev, ctx->port) == IB_LINK_LAYER_INFINIBAND)
+ /* have QP0 only if link layer is IB */
+ if (rdma_port_get_link_layer(ibdev, ctx->port) ==
+ IB_LINK_LAYER_INFINIBAND)
ctx->has_smi = 1;
if (ctx->has_smi) {
@@ -1844,7 +1950,15 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev,
ctx->port = port;
ctx->ib_dev = &dev->ib_dev;
- for (i = 0; i < dev->dev->caps.sqp_demux; i++) {
+ for (i = 0;
+ i < min(dev->dev->caps.sqp_demux, (u16)(dev->dev->num_vfs + 1));
+ i++) {
+ struct mlx4_active_ports actv_ports =
+ mlx4_get_active_ports(dev->dev, i);
+
+ if (!test_bit(port - 1, actv_ports.ports))
+ continue;
+
ret = alloc_pv_object(dev, i, port, &ctx->tun[i]);
if (ret) {
ret = -ENOMEM;
@@ -1999,16 +2113,17 @@ int mlx4_ib_init_sriov(struct mlx4_ib_dev *dev)
goto demux_err;
err = mlx4_ib_alloc_demux_ctx(dev, &dev->sriov.demux[i], i + 1);
if (err)
- goto demux_err;
+ goto free_pv;
}
mlx4_ib_master_tunnels(dev, 1);
return 0;
+free_pv:
+ free_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1);
demux_err:
- while (i > 0) {
+ while (--i >= 0) {
free_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1);
mlx4_ib_free_demux_ctx(&dev->sriov.demux[i]);
- --i;
}
mlx4_ib_device_unregister_sysfs(dev);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index e7d81c0d1ac..0f7027e7db1 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -39,6 +39,8 @@
#include <linux/inetdevice.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
#include <rdma/ib_smi.h>
#include <rdma/ib_user_verbs.h>
@@ -46,13 +48,17 @@
#include <linux/mlx4/driver.h>
#include <linux/mlx4/cmd.h>
+#include <linux/mlx4/qp.h>
#include "mlx4_ib.h"
#include "user.h"
#define DRV_NAME MLX4_IB_DRV_NAME
-#define DRV_VERSION "1.0"
-#define DRV_RELDATE "April 4, 2008"
+#define DRV_VERSION "2.2-1"
+#define DRV_RELDATE "Feb 2014"
+
+#define MLX4_IB_FLOW_MAX_PRIO 0xFFF
+#define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF
MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver");
@@ -88,6 +94,31 @@ static void init_query_mad(struct ib_smp *mad)
static union ib_gid zgid;
+static int check_flow_steering_support(struct mlx4_dev *dev)
+{
+ int eth_num_ports = 0;
+ int ib_num_ports = 0;
+
+ int dmfs = dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED;
+
+ if (dmfs) {
+ int i;
+ mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
+ eth_num_ports++;
+ mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+ ib_num_ports++;
+ dmfs &= (!ib_num_ports ||
+ (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB)) &&
+ (!eth_num_ports ||
+ (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN));
+ if (ib_num_ports && mlx4_is_mfunc(dev)) {
+ pr_warn("Device managed flow steering is unavailable for IB port in multifunction env.\n");
+ dmfs = 0;
+ }
+ }
+ return dmfs;
+}
+
static int mlx4_ib_query_device(struct ib_device *ibdev,
struct ib_device_attr *props)
{
@@ -137,6 +168,16 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC)
props->device_cap_flags |= IB_DEVICE_XRC;
+ if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW)
+ props->device_cap_flags |= IB_DEVICE_MEM_WINDOW;
+ if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
+ if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_WIN_TYPE_2B)
+ props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
+ else
+ props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
+ if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
+ props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
+ }
props->vendor_id = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
0xffffff;
@@ -146,18 +187,18 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->max_mr_size = ~0ull;
props->page_size_cap = dev->dev->caps.page_size_cap;
- props->max_qp = dev->dev->caps.num_qps - dev->dev->caps.reserved_qps;
+ 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_cq = dev->dev->caps.num_cqs - dev->dev->caps.reserved_cqs;
+ props->max_cq = dev->dev->quotas.cq;
props->max_cqe = dev->dev->caps.max_cqes;
- props->max_mr = dev->dev->caps.num_mpts - dev->dev->caps.reserved_mrws;
+ props->max_mr = dev->dev->quotas.mpt;
props->max_pd = dev->dev->caps.num_pds - dev->dev->caps.reserved_pds;
props->max_qp_rd_atom = dev->dev->caps.max_qp_dest_rdma;
props->max_qp_init_rd_atom = dev->dev->caps.max_qp_init_rdma;
props->max_res_rd_atom = props->max_qp_rd_atom * props->max_qp;
- props->max_srq = dev->dev->caps.num_srqs - dev->dev->caps.reserved_srqs;
+ props->max_srq = dev->dev->quotas.srq;
props->max_srq_wr = dev->dev->caps.max_srq_wqes - 1;
props->max_srq_sge = dev->dev->caps.max_srq_sge;
props->max_fast_reg_page_list_len = MLX4_MAX_FAST_REG_PAGES;
@@ -307,7 +348,7 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port,
props->active_width = (((u8 *)mailbox->buf)[5] == 0x40) ?
IB_WIDTH_4X : IB_WIDTH_1X;
props->active_speed = IB_SPEED_QDR;
- props->port_cap_flags = IB_PORT_CM_SUP;
+ props->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS;
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;
@@ -495,7 +536,6 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
if (IS_ERR(mailbox))
return 0;
- memset(mailbox->buf, 0, 256);
memcpy(mailbox->buf, props->node_desc, 64);
mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0,
MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
@@ -505,19 +545,16 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
return 0;
}
-static int mlx4_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, u8 port, int reset_qkey_viols,
+ u32 cap_mask)
{
struct mlx4_cmd_mailbox *mailbox;
int err;
- u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
mailbox = mlx4_alloc_cmd_mailbox(dev->dev);
if (IS_ERR(mailbox))
return PTR_ERR(mailbox);
- memset(mailbox->buf, 0, 256);
-
if (dev->dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
*(u8 *) mailbox->buf = !!reset_qkey_viols << 6;
((__be32 *) mailbox->buf)[2] = cpu_to_be32(cap_mask);
@@ -526,8 +563,8 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
((__be32 *) mailbox->buf)[1] = cpu_to_be32(cap_mask);
}
- err = mlx4_cmd(dev->dev, mailbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
- MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+ err = mlx4_cmd(dev->dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
mlx4_free_cmd_mailbox(dev->dev, mailbox);
return err;
@@ -536,11 +573,20 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
struct ib_port_modify *props)
{
+ struct mlx4_ib_dev *mdev = to_mdev(ibdev);
+ u8 is_eth = mdev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
struct ib_port_attr attr;
u32 cap_mask;
int err;
- mutex_lock(&to_mdev(ibdev)->cap_mask_mutex);
+ /* return OK if this is RoCE. CM calls ib_modify_port() regardless
+ * of whether port link layer is ETH or IB. For ETH ports, qkey
+ * violations and port capabilities are not meaningful.
+ */
+ if (is_eth)
+ return 0;
+
+ mutex_lock(&mdev->cap_mask_mutex);
err = mlx4_ib_query_port(ibdev, port, &attr);
if (err)
@@ -549,9 +595,9 @@ static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
cap_mask = (attr.port_cap_flags | props->set_port_cap_mask) &
~props->clr_port_cap_mask;
- err = mlx4_SET_PORT(to_mdev(ibdev), port,
- !!(mask & IB_PORT_RESET_QKEY_CNTR),
- cap_mask);
+ err = mlx4_ib_SET_PORT(mdev, port,
+ !!(mask & IB_PORT_RESET_QKEY_CNTR),
+ cap_mask);
out:
mutex_unlock(&to_mdev(ibdev)->cap_mask_mutex);
@@ -759,7 +805,6 @@ static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
union ib_gid *gid)
{
- u8 mac[6];
struct net_device *ndev;
int ret = 0;
@@ -773,11 +818,7 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
spin_unlock(&mdev->iboe.lock);
if (ndev) {
- rdma_get_mcast_mac((struct in6_addr *)gid, mac);
- rtnl_lock();
- dev_mc_add(mdev->iboe.netdevs[mqp->port - 1], mac);
ret = 1;
- rtnl_unlock();
dev_put(ndev);
}
@@ -790,6 +831,338 @@ struct mlx4_ib_steering {
union ib_gid gid;
};
+static int parse_flow_attr(struct mlx4_dev *dev,
+ u32 qp_num,
+ union ib_flow_spec *ib_spec,
+ struct _rule_hw *mlx4_spec)
+{
+ enum mlx4_net_trans_rule_id type;
+
+ switch (ib_spec->type) {
+ case IB_FLOW_SPEC_ETH:
+ type = MLX4_NET_TRANS_RULE_ID_ETH;
+ memcpy(mlx4_spec->eth.dst_mac, ib_spec->eth.val.dst_mac,
+ ETH_ALEN);
+ memcpy(mlx4_spec->eth.dst_mac_msk, ib_spec->eth.mask.dst_mac,
+ ETH_ALEN);
+ mlx4_spec->eth.vlan_tag = ib_spec->eth.val.vlan_tag;
+ mlx4_spec->eth.vlan_tag_msk = ib_spec->eth.mask.vlan_tag;
+ break;
+ case IB_FLOW_SPEC_IB:
+ type = MLX4_NET_TRANS_RULE_ID_IB;
+ mlx4_spec->ib.l3_qpn =
+ cpu_to_be32(qp_num);
+ mlx4_spec->ib.qpn_mask =
+ cpu_to_be32(MLX4_IB_FLOW_QPN_MASK);
+ break;
+
+
+ case IB_FLOW_SPEC_IPV4:
+ type = MLX4_NET_TRANS_RULE_ID_IPV4;
+ mlx4_spec->ipv4.src_ip = ib_spec->ipv4.val.src_ip;
+ mlx4_spec->ipv4.src_ip_msk = ib_spec->ipv4.mask.src_ip;
+ mlx4_spec->ipv4.dst_ip = ib_spec->ipv4.val.dst_ip;
+ mlx4_spec->ipv4.dst_ip_msk = ib_spec->ipv4.mask.dst_ip;
+ break;
+
+ case IB_FLOW_SPEC_TCP:
+ case IB_FLOW_SPEC_UDP:
+ type = ib_spec->type == IB_FLOW_SPEC_TCP ?
+ MLX4_NET_TRANS_RULE_ID_TCP :
+ MLX4_NET_TRANS_RULE_ID_UDP;
+ mlx4_spec->tcp_udp.dst_port = ib_spec->tcp_udp.val.dst_port;
+ mlx4_spec->tcp_udp.dst_port_msk = ib_spec->tcp_udp.mask.dst_port;
+ mlx4_spec->tcp_udp.src_port = ib_spec->tcp_udp.val.src_port;
+ mlx4_spec->tcp_udp.src_port_msk = ib_spec->tcp_udp.mask.src_port;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ if (mlx4_map_sw_to_hw_steering_id(dev, type) < 0 ||
+ mlx4_hw_rule_sz(dev, type) < 0)
+ return -EINVAL;
+ mlx4_spec->id = cpu_to_be16(mlx4_map_sw_to_hw_steering_id(dev, type));
+ mlx4_spec->size = mlx4_hw_rule_sz(dev, type) >> 2;
+ return mlx4_hw_rule_sz(dev, type);
+}
+
+struct default_rules {
+ __u32 mandatory_fields[IB_FLOW_SPEC_SUPPORT_LAYERS];
+ __u32 mandatory_not_fields[IB_FLOW_SPEC_SUPPORT_LAYERS];
+ __u32 rules_create_list[IB_FLOW_SPEC_SUPPORT_LAYERS];
+ __u8 link_layer;
+};
+static const struct default_rules default_table[] = {
+ {
+ .mandatory_fields = {IB_FLOW_SPEC_IPV4},
+ .mandatory_not_fields = {IB_FLOW_SPEC_ETH},
+ .rules_create_list = {IB_FLOW_SPEC_IB},
+ .link_layer = IB_LINK_LAYER_INFINIBAND
+ }
+};
+
+static int __mlx4_ib_default_rules_match(struct ib_qp *qp,
+ struct ib_flow_attr *flow_attr)
+{
+ int i, j, k;
+ void *ib_flow;
+ const struct default_rules *pdefault_rules = default_table;
+ u8 link_layer = rdma_port_get_link_layer(qp->device, flow_attr->port);
+
+ for (i = 0; i < sizeof(default_table)/sizeof(default_table[0]); i++,
+ pdefault_rules++) {
+ __u32 field_types[IB_FLOW_SPEC_SUPPORT_LAYERS];
+ memset(&field_types, 0, sizeof(field_types));
+
+ if (link_layer != pdefault_rules->link_layer)
+ continue;
+
+ ib_flow = flow_attr + 1;
+ /* we assume the specs are sorted */
+ for (j = 0, k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS &&
+ j < flow_attr->num_of_specs; k++) {
+ union ib_flow_spec *current_flow =
+ (union ib_flow_spec *)ib_flow;
+
+ /* same layer but different type */
+ if (((current_flow->type & IB_FLOW_SPEC_LAYER_MASK) ==
+ (pdefault_rules->mandatory_fields[k] &
+ IB_FLOW_SPEC_LAYER_MASK)) &&
+ (current_flow->type !=
+ pdefault_rules->mandatory_fields[k]))
+ goto out;
+
+ /* same layer, try match next one */
+ if (current_flow->type ==
+ pdefault_rules->mandatory_fields[k]) {
+ j++;
+ ib_flow +=
+ ((union ib_flow_spec *)ib_flow)->size;
+ }
+ }
+
+ ib_flow = flow_attr + 1;
+ for (j = 0; j < flow_attr->num_of_specs;
+ j++, ib_flow += ((union ib_flow_spec *)ib_flow)->size)
+ for (k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS; k++)
+ /* same layer and same type */
+ if (((union ib_flow_spec *)ib_flow)->type ==
+ pdefault_rules->mandatory_not_fields[k])
+ goto out;
+
+ return i;
+ }
+out:
+ return -1;
+}
+
+static int __mlx4_ib_create_default_rules(
+ struct mlx4_ib_dev *mdev,
+ struct ib_qp *qp,
+ const struct default_rules *pdefault_rules,
+ struct _rule_hw *mlx4_spec) {
+ int size = 0;
+ int i;
+
+ for (i = 0; i < sizeof(pdefault_rules->rules_create_list)/
+ sizeof(pdefault_rules->rules_create_list[0]); i++) {
+ int ret;
+ union ib_flow_spec ib_spec;
+ switch (pdefault_rules->rules_create_list[i]) {
+ case 0:
+ /* no rule */
+ continue;
+ case IB_FLOW_SPEC_IB:
+ ib_spec.type = IB_FLOW_SPEC_IB;
+ ib_spec.size = sizeof(struct ib_flow_spec_ib);
+
+ break;
+ default:
+ /* invalid rule */
+ return -EINVAL;
+ }
+ /* We must put empty rule, qpn is being ignored */
+ ret = parse_flow_attr(mdev->dev, 0, &ib_spec,
+ mlx4_spec);
+ if (ret < 0) {
+ pr_info("invalid parsing\n");
+ return -EINVAL;
+ }
+
+ mlx4_spec = (void *)mlx4_spec + ret;
+ size += ret;
+ }
+ return size;
+}
+
+static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr,
+ int domain,
+ enum mlx4_net_trans_promisc_mode flow_type,
+ u64 *reg_id)
+{
+ int ret, i;
+ int size = 0;
+ void *ib_flow;
+ struct mlx4_ib_dev *mdev = to_mdev(qp->device);
+ struct mlx4_cmd_mailbox *mailbox;
+ 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;
+
+ mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ ctrl = mailbox->buf;
+
+ ctrl->prio = cpu_to_be16(__mlx4_domain[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);
+
+ ib_flow = flow_attr + 1;
+ size += sizeof(struct mlx4_net_trans_rule_hw_ctrl);
+ /* Add default flows */
+ default_flow = __mlx4_ib_default_rules_match(qp, flow_attr);
+ if (default_flow >= 0) {
+ ret = __mlx4_ib_create_default_rules(
+ mdev, qp, default_table + default_flow,
+ mailbox->buf + size);
+ if (ret < 0) {
+ mlx4_free_cmd_mailbox(mdev->dev, mailbox);
+ return -EINVAL;
+ }
+ size += ret;
+ }
+ for (i = 0; i < flow_attr->num_of_specs; i++) {
+ ret = parse_flow_attr(mdev->dev, qp->qp_num, ib_flow,
+ mailbox->buf + size);
+ if (ret < 0) {
+ mlx4_free_cmd_mailbox(mdev->dev, mailbox);
+ return -EINVAL;
+ }
+ ib_flow += ((union ib_flow_spec *) ib_flow)->size;
+ size += ret;
+ }
+
+ ret = mlx4_cmd_imm(mdev->dev, mailbox->dma, reg_id, size >> 2, 0,
+ MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (ret == -ENOMEM)
+ pr_err("mcg table is full. Fail to register network rule.\n");
+ else if (ret == -ENXIO)
+ pr_err("Device managed flow steering is disabled. Fail to register network rule.\n");
+ else if (ret)
+ pr_err("Invalid argumant. Fail to register network rule.\n");
+
+ mlx4_free_cmd_mailbox(mdev->dev, mailbox);
+ return ret;
+}
+
+static int __mlx4_ib_destroy_flow(struct mlx4_dev *dev, u64 reg_id)
+{
+ int err;
+ err = mlx4_cmd(dev, reg_id, 0, 0,
+ MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (err)
+ pr_err("Fail to detach network rule. registration id = 0x%llx\n",
+ reg_id);
+ return err;
+}
+
+static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
+ struct ib_flow_attr *flow_attr,
+ int domain)
+{
+ int err = 0, i = 0;
+ struct mlx4_ib_flow *mflow;
+ enum mlx4_net_trans_promisc_mode type[2];
+
+ memset(type, 0, sizeof(type));
+
+ mflow = kzalloc(sizeof(*mflow), GFP_KERNEL);
+ if (!mflow) {
+ err = -ENOMEM;
+ goto err_free;
+ }
+
+ switch (flow_attr->type) {
+ case IB_FLOW_ATTR_NORMAL:
+ type[0] = MLX4_FS_REGULAR;
+ break;
+
+ case IB_FLOW_ATTR_ALL_DEFAULT:
+ type[0] = MLX4_FS_ALL_DEFAULT;
+ break;
+
+ case IB_FLOW_ATTR_MC_DEFAULT:
+ type[0] = MLX4_FS_MC_DEFAULT;
+ break;
+
+ case IB_FLOW_ATTR_SNIFFER:
+ type[0] = MLX4_FS_UC_SNIFFER;
+ type[1] = MLX4_FS_MC_SNIFFER;
+ break;
+
+ default:
+ err = -EINVAL;
+ goto err_free;
+ }
+
+ while (i < ARRAY_SIZE(type) && type[i]) {
+ err = __mlx4_ib_create_flow(qp, flow_attr, domain, type[i],
+ &mflow->reg_id[i]);
+ if (err)
+ goto err_free;
+ i++;
+ }
+
+ return &mflow->ibflow;
+
+err_free:
+ kfree(mflow);
+ return ERR_PTR(err);
+}
+
+static int mlx4_ib_destroy_flow(struct ib_flow *flow_id)
+{
+ int err, ret = 0;
+ int i = 0;
+ struct mlx4_ib_dev *mdev = to_mdev(flow_id->qp->device);
+ struct mlx4_ib_flow *mflow = to_mflow(flow_id);
+
+ while (i < ARRAY_SIZE(mflow->reg_id) && mflow->reg_id[i]) {
+ err = __mlx4_ib_destroy_flow(mdev->dev, mflow->reg_id[i]);
+ if (err)
+ ret = err;
+ i++;
+ }
+
+ kfree(mflow);
+ return ret;
+}
+
static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
{
int err;
@@ -797,6 +1170,8 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
struct mlx4_ib_qp *mqp = to_mqp(ibqp);
u64 reg_id;
struct mlx4_ib_steering *ib_steering = NULL;
+ enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+ MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
if (mdev->dev->caps.steering_mode ==
MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -808,7 +1183,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
!!(mqp->flags &
MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
- MLX4_PROT_IB_IPV6, &reg_id);
+ prot, &reg_id);
if (err)
goto err_malloc;
@@ -827,7 +1202,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
err_add:
mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
- MLX4_PROT_IB_IPV6, reg_id);
+ prot, reg_id);
err_malloc:
kfree(ib_steering);
@@ -855,10 +1230,11 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
int err;
struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
struct mlx4_ib_qp *mqp = to_mqp(ibqp);
- u8 mac[6];
struct net_device *ndev;
struct mlx4_ib_gid_entry *ge;
u64 reg_id = 0;
+ enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+ MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
if (mdev->dev->caps.steering_mode ==
MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -881,7 +1257,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
}
err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
- MLX4_PROT_IB_IPV6, reg_id);
+ prot, reg_id);
if (err)
return err;
@@ -893,13 +1269,8 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
if (ndev)
dev_hold(ndev);
spin_unlock(&mdev->iboe.lock);
- rdma_get_mcast_mac((struct in6_addr *)gid, mac);
- if (ndev) {
- rtnl_lock();
- dev_mc_del(mdev->iboe.netdevs[ge->port - 1], mac);
- rtnl_unlock();
+ if (ndev)
dev_put(ndev);
- }
list_del(&ge->list);
kfree(ge);
} else
@@ -995,7 +1366,8 @@ static struct device_attribute *mlx4_class_attributes[] = {
&dev_attr_board_id
};
-static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id, struct net_device *dev)
+static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id,
+ struct net_device *dev)
{
memcpy(eui, dev->dev_addr, 3);
memcpy(eui + 5, dev->dev_addr + 3, 3);
@@ -1031,162 +1403,437 @@ static void update_gids_task(struct work_struct *work)
MLX4_CMD_WRAPPED);
if (err)
pr_warn("set port command failed\n");
- else {
- memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids);
+ else
mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ kfree(gw);
+}
+
+static void reset_gids_task(struct work_struct *work)
+{
+ struct update_gid_work *gw =
+ container_of(work, struct update_gid_work, work);
+ struct mlx4_cmd_mailbox *mailbox;
+ union ib_gid *gids;
+ int err;
+ struct mlx4_dev *dev = gw->dev->dev;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox)) {
+ pr_warn("reset gid table failed\n");
+ goto free;
+ }
+
+ gids = mailbox->buf;
+ memcpy(gids, gw->gids, sizeof(gw->gids));
+
+ if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, gw->port) ==
+ IB_LINK_LAYER_ETHERNET) {
+ err = mlx4_cmd(dev, mailbox->dma,
+ MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
+ 1, MLX4_CMD_SET_PORT,
+ MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+ if (err)
+ pr_warn(KERN_WARNING
+ "set port %d command failed\n", gw->port);
}
mlx4_free_cmd_mailbox(dev, mailbox);
+free:
kfree(gw);
}
-static int update_ipv6_gids(struct mlx4_ib_dev *dev, int port, int clear)
+static int update_gid_table(struct mlx4_ib_dev *dev, int port,
+ union ib_gid *gid, int clear,
+ int default_gid)
{
- struct net_device *ndev = dev->iboe.netdevs[port - 1];
struct update_gid_work *work;
- struct net_device *tmp;
int i;
- u8 *hits;
- int ret;
- union ib_gid gid;
- int free;
- int found;
int need_update = 0;
- u16 vid;
+ int free = -1;
+ int found = -1;
+ int max_gids;
- work = kzalloc(sizeof *work, GFP_ATOMIC);
- if (!work)
- return -ENOMEM;
-
- hits = kzalloc(128, GFP_ATOMIC);
- if (!hits) {
- ret = -ENOMEM;
- goto out;
- }
-
- rcu_read_lock();
- for_each_netdev_rcu(&init_net, tmp) {
- if (ndev && (tmp == ndev || rdma_vlan_dev_real_dev(tmp) == ndev)) {
- gid.global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
- vid = rdma_vlan_dev_vlan_id(tmp);
- mlx4_addrconf_ifid_eui48(&gid.raw[8], vid, ndev);
- found = 0;
- free = -1;
- for (i = 0; i < 128; ++i) {
- if (free < 0 &&
- !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
- free = i;
- if (!memcmp(&dev->iboe.gid_table[port - 1][i], &gid, sizeof gid)) {
- hits[i] = 1;
- found = 1;
+ if (default_gid) {
+ free = 0;
+ } else {
+ max_gids = dev->dev->caps.gid_table_len[port];
+ for (i = 1; i < max_gids; ++i) {
+ if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
+ sizeof(*gid)))
+ found = i;
+
+ if (clear) {
+ if (found >= 0) {
+ need_update = 1;
+ dev->iboe.gid_table[port - 1][found] =
+ zgid;
break;
}
- }
+ } else {
+ if (found >= 0)
+ break;
- if (!found) {
- if (tmp == ndev &&
- (memcmp(&dev->iboe.gid_table[port - 1][0],
- &gid, sizeof gid) ||
- !memcmp(&dev->iboe.gid_table[port - 1][0],
- &zgid, sizeof gid))) {
- dev->iboe.gid_table[port - 1][0] = gid;
- ++need_update;
- hits[0] = 1;
- } else if (free >= 0) {
- dev->iboe.gid_table[port - 1][free] = gid;
- hits[free] = 1;
- ++need_update;
- }
+ if (free < 0 &&
+ !memcmp(&dev->iboe.gid_table[port - 1][i],
+ &zgid, sizeof(*gid)))
+ free = i;
}
}
}
- rcu_read_unlock();
- for (i = 0; i < 128; ++i)
- if (!hits[i]) {
- if (memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
- ++need_update;
- dev->iboe.gid_table[port - 1][i] = zgid;
- }
+ if (found == -1 && !clear && free >= 0) {
+ dev->iboe.gid_table[port - 1][free] = *gid;
+ need_update = 1;
+ }
- if (need_update) {
- memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof work->gids);
- INIT_WORK(&work->work, update_gids_task);
- work->port = port;
- work->dev = dev;
- queue_work(wq, &work->work);
- } else
- kfree(work);
+ if (!need_update)
+ return 0;
+
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work)
+ return -ENOMEM;
+
+ memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof(work->gids));
+ INIT_WORK(&work->work, update_gids_task);
+ work->port = port;
+ work->dev = dev;
+ queue_work(wq, &work->work);
- kfree(hits);
return 0;
+}
-out:
- kfree(work);
- return ret;
+static void mlx4_make_default_gid(struct net_device *dev, union ib_gid *gid)
+{
+ gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+ mlx4_addrconf_ifid_eui48(&gid->raw[8], 0xffff, dev);
}
-static void handle_en_event(struct mlx4_ib_dev *dev, int port, unsigned long event)
+
+static int reset_gid_table(struct mlx4_ib_dev *dev, u8 port)
{
- switch (event) {
- case NETDEV_UP:
- case NETDEV_CHANGEADDR:
- update_ipv6_gids(dev, port, 0);
- break;
+ struct update_gid_work *work;
+
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work)
+ return -ENOMEM;
+
+ memset(dev->iboe.gid_table[port - 1], 0, sizeof(work->gids));
+ memset(work->gids, 0, sizeof(work->gids));
+ INIT_WORK(&work->work, reset_gids_task);
+ work->dev = dev;
+ work->port = port;
+ queue_work(wq, &work->work);
+ return 0;
+}
+
+static int mlx4_ib_addr_event(int event, struct net_device *event_netdev,
+ struct mlx4_ib_dev *ibdev, union ib_gid *gid)
+{
+ struct mlx4_ib_iboe *iboe;
+ int port = 0;
+ struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
+ rdma_vlan_dev_real_dev(event_netdev) :
+ event_netdev;
+ union ib_gid default_gid;
+
+ mlx4_make_default_gid(real_dev, &default_gid);
+
+ if (!memcmp(gid, &default_gid, sizeof(*gid)))
+ return 0;
+
+ if (event != NETDEV_DOWN && event != NETDEV_UP)
+ return 0;
+
+ if ((real_dev != event_netdev) &&
+ (event == NETDEV_DOWN) &&
+ rdma_link_local_addr((struct in6_addr *)gid))
+ return 0;
+
+ iboe = &ibdev->iboe;
+ spin_lock(&iboe->lock);
+
+ for (port = 1; port <= ibdev->dev->caps.num_ports; ++port)
+ if ((netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->masters[port - 1])) ||
+ (!netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->netdevs[port - 1])))
+ update_gid_table(ibdev, port, gid,
+ event == NETDEV_DOWN, 0);
+
+ spin_unlock(&iboe->lock);
+ return 0;
- case NETDEV_DOWN:
- update_ipv6_gids(dev, port, 1);
- dev->iboe.netdevs[port - 1] = NULL;
- }
}
-static void netdev_added(struct mlx4_ib_dev *dev, int port)
+static u8 mlx4_ib_get_dev_port(struct net_device *dev,
+ struct mlx4_ib_dev *ibdev)
{
- update_ipv6_gids(dev, port, 0);
+ u8 port = 0;
+ struct mlx4_ib_iboe *iboe;
+ struct net_device *real_dev = rdma_vlan_dev_real_dev(dev) ?
+ rdma_vlan_dev_real_dev(dev) : dev;
+
+ iboe = &ibdev->iboe;
+
+ for (port = 1; port <= ibdev->dev->caps.num_ports; ++port)
+ if ((netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->masters[port - 1])) ||
+ (!netif_is_bond_master(real_dev) &&
+ (real_dev == iboe->netdevs[port - 1])))
+ break;
+
+ if ((port == 0) || (port > ibdev->dev->caps.num_ports))
+ return 0;
+ else
+ return port;
}
-static void netdev_removed(struct mlx4_ib_dev *dev, int port)
+static int mlx4_ib_inet_event(struct notifier_block *this, unsigned long event,
+ void *ptr)
{
- update_ipv6_gids(dev, port, 1);
+ struct mlx4_ib_dev *ibdev;
+ struct in_ifaddr *ifa = ptr;
+ union ib_gid gid;
+ struct net_device *event_netdev = ifa->ifa_dev->dev;
+
+ ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
+
+ ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet);
+
+ mlx4_ib_addr_event(event, event_netdev, ibdev, &gid);
+ return NOTIFY_DONE;
}
-static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event,
+#if IS_ENABLED(CONFIG_IPV6)
+static int mlx4_ib_inet6_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
struct mlx4_ib_dev *ibdev;
- struct net_device *oldnd;
+ struct inet6_ifaddr *ifa = ptr;
+ union ib_gid *gid = (union ib_gid *)&ifa->addr;
+ struct net_device *event_netdev = ifa->idev->dev;
+
+ ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet6);
+
+ mlx4_ib_addr_event(event, event_netdev, ibdev, gid);
+ return NOTIFY_DONE;
+}
+#endif
+
+#define MLX4_IB_INVALID_MAC ((u64)-1)
+static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
+ struct net_device *dev,
+ int port)
+{
+ u64 new_smac = 0;
+ 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);
+
+ mutex_lock(&ibdev->qp1_proxy_lock[port - 1]);
+ qp = ibdev->qp1_proxy[port - 1];
+ if (qp) {
+ int new_smac_index;
+ u64 old_smac = qp->pri.smac;
+ struct mlx4_update_qp_params update_params;
+
+ if (new_smac == old_smac)
+ goto unlock;
+
+ new_smac_index = mlx4_register_mac(ibdev->dev, port, new_smac);
+
+ if (new_smac_index < 0)
+ goto unlock;
+
+ update_params.smac_index = new_smac_index;
+ if (mlx4_update_qp(ibdev->dev, &qp->mqp, MLX4_UPDATE_QP_SMAC,
+ &update_params)) {
+ release_mac = new_smac;
+ goto unlock;
+ }
+
+ qp->pri.smac = new_smac;
+ qp->pri.smac_index = new_smac_index;
+
+ release_mac = old_smac;
+ }
+
+unlock:
+ mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]);
+ if (release_mac != MLX4_IB_INVALID_MAC)
+ mlx4_unregister_mac(ibdev->dev, port, release_mac);
+}
+
+static void mlx4_ib_get_dev_addr(struct net_device *dev,
+ struct mlx4_ib_dev *ibdev, u8 port)
+{
+ struct in_device *in_dev;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct inet6_dev *in6_dev;
+ union ib_gid *pgid;
+ struct inet6_ifaddr *ifp;
+#endif
+ union ib_gid gid;
+
+
+ if ((port == 0) || (port > ibdev->dev->caps.num_ports))
+ return;
+
+ /* IPv4 gids */
+ in_dev = in_dev_get(dev);
+ if (in_dev) {
+ for_ifa(in_dev) {
+ /*ifa->ifa_address;*/
+ ipv6_addr_set_v4mapped(ifa->ifa_address,
+ (struct in6_addr *)&gid);
+ update_gid_table(ibdev, port, &gid, 0, 0);
+ }
+ endfor_ifa(in_dev);
+ in_dev_put(in_dev);
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ /* IPv6 gids */
+ in6_dev = in6_dev_get(dev);
+ if (in6_dev) {
+ read_lock_bh(&in6_dev->lock);
+ list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
+ pgid = (union ib_gid *)&ifp->addr;
+ update_gid_table(ibdev, port, pgid, 0, 0);
+ }
+ read_unlock_bh(&in6_dev->lock);
+ in6_dev_put(in6_dev);
+ }
+#endif
+}
+
+static void mlx4_ib_set_default_gid(struct mlx4_ib_dev *ibdev,
+ struct net_device *dev, u8 port)
+{
+ union ib_gid gid;
+ mlx4_make_default_gid(dev, &gid);
+ update_gid_table(ibdev, port, &gid, 0, 1);
+}
+
+static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
+{
+ struct net_device *dev;
+ struct mlx4_ib_iboe *iboe = &ibdev->iboe;
+ int i;
+
+ for (i = 1; i <= ibdev->num_ports; ++i)
+ if (reset_gid_table(ibdev, i))
+ return -1;
+
+ read_lock(&dev_base_lock);
+ spin_lock(&iboe->lock);
+
+ for_each_netdev(&init_net, dev) {
+ u8 port = mlx4_ib_get_dev_port(dev, ibdev);
+ if (port)
+ mlx4_ib_get_dev_addr(dev, ibdev, port);
+ }
+
+ spin_unlock(&iboe->lock);
+ read_unlock(&dev_base_lock);
+
+ return 0;
+}
+
+static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
+ struct net_device *dev,
+ unsigned long event)
+
+{
struct mlx4_ib_iboe *iboe;
+ int update_qps_port = -1;
int port;
- if (!net_eq(dev_net(dev), &init_net))
- return NOTIFY_DONE;
-
- ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
iboe = &ibdev->iboe;
spin_lock(&iboe->lock);
mlx4_foreach_ib_transport_port(port, ibdev->dev) {
- oldnd = iboe->netdevs[port - 1];
+ enum ib_port_state port_state = IB_PORT_NOP;
+ struct net_device *old_master = iboe->masters[port - 1];
+ struct net_device *curr_netdev;
+ struct net_device *curr_master;
+
iboe->netdevs[port - 1] =
mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
- if (oldnd != iboe->netdevs[port - 1]) {
- if (iboe->netdevs[port - 1])
- netdev_added(ibdev, port);
- else
- netdev_removed(ibdev, port);
+ if (iboe->netdevs[port - 1])
+ mlx4_ib_set_default_gid(ibdev,
+ iboe->netdevs[port - 1], port);
+ curr_netdev = iboe->netdevs[port - 1];
+
+ if (iboe->netdevs[port - 1] &&
+ netif_is_bond_slave(iboe->netdevs[port - 1])) {
+ iboe->masters[port - 1] = netdev_master_upper_dev_get(
+ iboe->netdevs[port - 1]);
+ } else {
+ iboe->masters[port - 1] = NULL;
+ }
+ curr_master = iboe->masters[port - 1];
+
+ if (dev == iboe->netdevs[port - 1] &&
+ (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
+ event == NETDEV_UP || event == NETDEV_CHANGE))
+ update_qps_port = port;
+
+ if (curr_netdev) {
+ port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ?
+ IB_PORT_ACTIVE : IB_PORT_DOWN;
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+ } else {
+ reset_gid_table(ibdev, port);
+ }
+ /* if using bonding/team and a slave port is down, we don't the bond IP
+ * based gids in the table since flows that select port by gid may get
+ * the down port.
+ */
+ if (curr_master && (port_state == IB_PORT_DOWN)) {
+ reset_gid_table(ibdev, port);
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+ }
+ /* if bonding is used it is possible that we add it to masters
+ * only after IP address is assigned to the net bonding
+ * interface.
+ */
+ if (curr_master && (old_master != curr_master)) {
+ reset_gid_table(ibdev, port);
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+ mlx4_ib_get_dev_addr(curr_master, ibdev, port);
}
- }
- if (dev == iboe->netdevs[0] ||
- (iboe->netdevs[0] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[0]))
- handle_en_event(ibdev, 1, event);
- else if (dev == iboe->netdevs[1]
- || (iboe->netdevs[1] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[1]))
- handle_en_event(ibdev, 2, event);
+ if (!curr_master && (old_master != curr_master)) {
+ reset_gid_table(ibdev, port);
+ mlx4_ib_set_default_gid(ibdev, curr_netdev, port);
+ mlx4_ib_get_dev_addr(curr_netdev, ibdev, port);
+ }
+ }
spin_unlock(&iboe->lock);
+ if (update_qps_port > 0)
+ mlx4_ib_update_qps(ibdev, dev, update_qps_port);
+}
+
+static int mlx4_ib_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct mlx4_ib_dev *ibdev;
+
+ if (!net_eq(dev_net(dev), &init_net))
+ return NOTIFY_DONE;
+
+ ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
+ mlx4_ib_scan_netdevs(ibdev, dev, event);
+
return NOTIFY_DONE;
}
@@ -1224,7 +1871,7 @@ static void init_pkeys(struct mlx4_ib_dev *ibdev)
static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
{
- char name[32];
+ char name[80];
int eq_per_port = 0;
int added_eqs = 0;
int total_eqs = 0;
@@ -1254,8 +1901,8 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
eq = 0;
mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) {
for (j = 0; j < eq_per_port; j++) {
- sprintf(name, "mlx4-ib-%d-%d@%s",
- i, j, dev->pdev->bus->name);
+ snprintf(name, sizeof(name), "mlx4-ib-%d-%d@%s",
+ i, j, dev->pdev->bus->name);
/* Set IRQ for specific name (per ring) */
if (mlx4_assign_eq(dev, name, NULL,
&ibdev->eq_table[eq])) {
@@ -1305,17 +1952,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
int i, j;
int err;
struct mlx4_ib_iboe *iboe;
+ int ib_num_ports = 0;
pr_info_once("%s", mlx4_ib_version);
- mlx4_foreach_non_ib_transport_port(i, dev)
- num_ports++;
-
- if (mlx4_is_mfunc(dev) && num_ports) {
- dev_err(&dev->pdev->dev, "RoCE is not supported over SRIOV as yet\n");
- return NULL;
- }
-
num_ports = 0;
mlx4_foreach_ib_transport_port(i, dev)
num_ports++;
@@ -1434,6 +2074,17 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
ibdev->ib_dev.dealloc_fmr = mlx4_ib_fmr_dealloc;
}
+ 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.bind_mw = mlx4_ib_bind_mw;
+ ibdev->ib_dev.dealloc_mw = mlx4_ib_dealloc_mw;
+
+ 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_XRC) {
ibdev->ib_dev.alloc_xrcd = mlx4_ib_alloc_xrcd;
ibdev->ib_dev.dealloc_xrcd = mlx4_ib_dealloc_xrcd;
@@ -1442,6 +2093,16 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
(1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
}
+ 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);
+ }
+
mlx4_ib_alloc_eqs(dev, ibdev);
spin_lock_init(&iboe->lock);
@@ -1450,20 +2111,53 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
goto err_map;
for (i = 0; i < ibdev->num_ports; ++i) {
+ mutex_init(&ibdev->qp1_proxy_lock[i]);
if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) ==
IB_LINK_LAYER_ETHERNET) {
err = mlx4_counter_alloc(ibdev->dev, &ibdev->counters[i]);
if (err)
ibdev->counters[i] = -1;
- } else
- ibdev->counters[i] = -1;
+ } else {
+ ibdev->counters[i] = -1;
+ }
}
+ mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+ ib_num_ports++;
+
spin_lock_init(&ibdev->sm_lock);
mutex_init(&ibdev->cap_mask_mutex);
+ if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED &&
+ ib_num_ports) {
+ 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);
+ 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) {
+ dev_err(&dev->pdev->dev, "bit map alloc failed\n");
+ goto err_steer_qp_release;
+ }
+
+ bitmap_zero(ibdev->ib_uc_qpns_bitmap, ibdev->steer_qpn_count);
+
+ err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
+ dev, ibdev->steer_qpn_base,
+ ibdev->steer_qpn_base +
+ ibdev->steer_qpn_count - 1);
+ if (err)
+ goto err_steer_free_bitmap;
+ }
+
if (ib_register_device(&ibdev->ib_dev, NULL))
- goto err_counter;
+ goto err_steer_free_bitmap;
if (mlx4_ib_mad_init(ibdev))
goto err_reg;
@@ -1471,11 +2165,39 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
if (mlx4_ib_init_sriov(ibdev))
goto err_mad;
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE && !iboe->nb.notifier_call) {
- iboe->nb.notifier_call = mlx4_ib_netdev_event;
- err = register_netdevice_notifier(&iboe->nb);
- if (err)
- goto err_sriov;
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE) {
+ if (!iboe->nb.notifier_call) {
+ iboe->nb.notifier_call = mlx4_ib_netdev_event;
+ err = register_netdevice_notifier(&iboe->nb);
+ if (err) {
+ iboe->nb.notifier_call = NULL;
+ goto err_notif;
+ }
+ }
+ if (!iboe->nb_inet.notifier_call) {
+ iboe->nb_inet.notifier_call = mlx4_ib_inet_event;
+ err = register_inetaddr_notifier(&iboe->nb_inet);
+ if (err) {
+ iboe->nb_inet.notifier_call = NULL;
+ goto err_notif;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ if (!iboe->nb_inet6.notifier_call) {
+ iboe->nb_inet6.notifier_call = mlx4_ib_inet6_event;
+ err = register_inet6addr_notifier(&iboe->nb_inet6);
+ if (err) {
+ iboe->nb_inet6.notifier_call = NULL;
+ goto err_notif;
+ }
+ }
+#endif
+ for (i = 1 ; i <= ibdev->num_ports ; ++i)
+ reset_gid_table(ibdev, i);
+ rtnl_lock();
+ mlx4_ib_scan_netdevs(ibdev, NULL, 0);
+ rtnl_unlock();
+ mlx4_ib_init_gid_table(ibdev);
}
for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) {
@@ -1501,11 +2223,25 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
return ibdev;
err_notif:
- if (unregister_netdevice_notifier(&ibdev->iboe.nb))
- pr_warn("failure unregistering notifier\n");
+ 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->iboe.nb_inet.notifier_call) {
+ if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet.notifier_call = NULL;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ibdev->iboe.nb_inet6.notifier_call) {
+ if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet6.notifier_call = NULL;
+ }
+#endif
flush_workqueue(wq);
-err_sriov:
mlx4_ib_close_sriov(ibdev);
err_mad:
@@ -1514,6 +2250,13 @@ err_mad:
err_reg:
ib_unregister_device(&ibdev->ib_dev);
+err_steer_free_bitmap:
+ kfree(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);
err_counter:
for (; i; --i)
if (ibdev->counters[i - 1] != -1)
@@ -1534,6 +2277,69 @@ err_dealloc:
return NULL;
}
+int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn)
+{
+ int offset;
+
+ WARN_ON(!dev->ib_uc_qpns_bitmap);
+
+ offset = bitmap_find_free_region(dev->ib_uc_qpns_bitmap,
+ dev->steer_qpn_count,
+ get_count_order(count));
+ if (offset < 0)
+ return offset;
+
+ *qpn = dev->steer_qpn_base + offset;
+ return 0;
+}
+
+void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count)
+{
+ if (!qpn ||
+ dev->steering_support != MLX4_STEERING_MODE_DEVICE_MANAGED)
+ return;
+
+ BUG_ON(qpn < dev->steer_qpn_base);
+
+ bitmap_release_region(dev->ib_uc_qpns_bitmap,
+ qpn - dev->steer_qpn_base,
+ get_count_order(count));
+}
+
+int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
+ int is_attach)
+{
+ int err;
+ size_t flow_size;
+ struct ib_flow_attr *flow = NULL;
+ struct ib_flow_spec_ib *ib_spec;
+
+ if (is_attach) {
+ flow_size = sizeof(struct ib_flow_attr) +
+ sizeof(struct ib_flow_spec_ib);
+ flow = kzalloc(flow_size, GFP_KERNEL);
+ if (!flow)
+ return -ENOMEM;
+ flow->port = mqp->port;
+ flow->num_of_specs = 1;
+ flow->size = flow_size;
+ ib_spec = (struct ib_flow_spec_ib *)(flow + 1);
+ ib_spec->type = IB_FLOW_SPEC_IB;
+ ib_spec->size = sizeof(struct ib_flow_spec_ib);
+ /* 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);
+ }
+ kfree(flow);
+ return err;
+}
+
static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
{
struct mlx4_ib_dev *ibdev = ibdev_ptr;
@@ -1547,6 +2353,26 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
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);
+ }
+
+ if (ibdev->iboe.nb_inet.notifier_call) {
+ if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet.notifier_call = NULL;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ibdev->iboe.nb_inet6.notifier_call) {
+ if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+ pr_warn("failure unregistering notifier\n");
+ ibdev->iboe.nb_inet6.notifier_call = NULL;
+ }
+#endif
+
iounmap(ibdev->uar_map);
for (p = 0; p < ibdev->num_ports; ++p)
if (ibdev->counters[p] != -1)
@@ -1567,17 +2393,24 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
struct mlx4_dev *dev = ibdev->dev;
int i;
unsigned long flags;
+ struct mlx4_active_ports actv_ports;
+ unsigned int ports;
+ unsigned int first_port;
if (!mlx4_is_master(dev))
return;
- dm = kcalloc(dev->caps.num_ports, sizeof *dm, GFP_ATOMIC);
+ actv_ports = mlx4_get_active_ports(dev, slave);
+ ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+ first_port = find_first_bit(actv_ports.ports, dev->caps.num_ports);
+
+ dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
if (!dm) {
pr_err("failed to allocate memory for tunneling qp update\n");
goto out;
}
- for (i = 0; i < dev->caps.num_ports; i++) {
+ for (i = 0; i < ports; i++) {
dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC);
if (!dm[i]) {
pr_err("failed to allocate memory for tunneling qp update work struct\n");
@@ -1589,9 +2422,9 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
}
}
/* initialize or tear down tunnel QPs for the slave */
- for (i = 0; i < dev->caps.num_ports; i++) {
+ for (i = 0; i < ports; i++) {
INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work);
- dm[i]->port = i + 1;
+ dm[i]->port = first_port + i + 1;
dm[i]->slave = slave;
dm[i]->do_init = do_init;
dm[i]->dev = ibdev;
@@ -1601,8 +2434,7 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
}
out:
- if (dm)
- kfree(dm);
+ kfree(dm);
return;
}
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index 25b2cdff00f..ed327e6c8fd 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -215,8 +215,9 @@ static int send_mad_to_wire(struct mlx4_ib_demux_ctx *ctx, struct ib_mad *mad)
}
mlx4_ib_query_ah(dev->sm_ah[ctx->port - 1], &ah_attr);
spin_unlock(&dev->sm_lock);
- return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev), ctx->port,
- IB_QPT_GSI, 0, 1, IB_QP1_QKEY, &ah_attr, mad);
+ return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev),
+ ctx->port, IB_QPT_GSI, 0, 1, IB_QP1_QKEY,
+ &ah_attr, NULL, mad);
}
static int send_mad_to_slave(int slave, struct mlx4_ib_demux_ctx *ctx,
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index dcd845bc30f..369da3ca5d6 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -68,6 +68,8 @@ enum {
/*module param to indicate if SM assigns the alias_GUID*/
extern int mlx4_ib_sm_guid_assign;
+#define MLX4_IB_UC_STEER_QPN_ALIGN 1
+#define MLX4_IB_UC_MAX_NUM_QPS 256
struct mlx4_ib_ucontext {
struct ib_ucontext ibucontext;
struct mlx4_uar uar;
@@ -116,6 +118,11 @@ struct mlx4_ib_mr {
struct ib_umem *umem;
};
+struct mlx4_ib_mw {
+ struct ib_mw ibmw;
+ struct mlx4_mw mmw;
+};
+
struct mlx4_ib_fast_reg_page_list {
struct ib_fast_reg_page_list ibfrpl;
__be64 *mapped_page_list;
@@ -127,6 +134,12 @@ struct mlx4_ib_fmr {
struct mlx4_fmr mfmr;
};
+struct mlx4_ib_flow {
+ struct ib_flow ibflow;
+ /* translating DMFS verbs sniffer rule to FW API requires two reg IDs */
+ u64 reg_id[2];
+};
+
struct mlx4_ib_wq {
u64 *wrid;
spinlock_t lock;
@@ -142,6 +155,8 @@ struct mlx4_ib_wq {
enum mlx4_ib_qp_flags {
MLX4_IB_QP_LSO = IB_QP_CREATE_IPOIB_UD_LSO,
MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
+ MLX4_IB_QP_NETIF = IB_QP_CREATE_NETIF_QP,
+ MLX4_IB_QP_CREATE_USE_GFP_NOIO = IB_QP_CREATE_USE_GFP_NOIO,
MLX4_IB_SRIOV_TUNNEL_QP = 1 << 30,
MLX4_IB_SRIOV_SQP = 1 << 31,
};
@@ -227,6 +242,22 @@ struct mlx4_ib_proxy_sqp_hdr {
struct mlx4_rcv_tunnel_hdr tun;
} __packed;
+struct mlx4_roce_smac_vlan_info {
+ u64 smac;
+ int smac_index;
+ int smac_port;
+ u64 candidate_smac;
+ int candidate_smac_index;
+ int candidate_smac_port;
+ u16 vid;
+ int vlan_index;
+ int vlan_port;
+ u16 candidate_vid;
+ int candidate_vlan_index;
+ int candidate_vlan_port;
+ int update_vid;
+};
+
struct mlx4_ib_qp {
struct ib_qp ibqp;
struct mlx4_qp mqp;
@@ -259,7 +290,9 @@ struct mlx4_ib_qp {
struct list_head gid_list;
struct list_head steering_rules;
struct mlx4_ib_buf *sqp_proxy_rcv;
-
+ struct mlx4_roce_smac_vlan_info pri;
+ struct mlx4_roce_smac_vlan_info alt;
+ u64 reg_id;
};
struct mlx4_ib_srq {
@@ -417,7 +450,10 @@ struct mlx4_ib_sriov {
struct mlx4_ib_iboe {
spinlock_t lock;
struct net_device *netdevs[MLX4_MAX_PORTS];
+ struct net_device *masters[MLX4_MAX_PORTS];
struct notifier_block nb;
+ struct notifier_block nb_inet;
+ struct notifier_block nb_inet6;
union ib_gid gid_table[MLX4_MAX_PORTS][128];
};
@@ -483,6 +519,13 @@ struct mlx4_ib_dev {
struct kobject *dev_ports_parent[MLX4_MFUNC_MAX];
struct mlx4_ib_iov_port iov_ports[MLX4_MAX_PORTS];
struct pkey_mgt pkeys;
+ unsigned long *ib_uc_qpns_bitmap;
+ int steer_qpn_count;
+ int steer_qpn_base;
+ int steering_support;
+ struct mlx4_ib_qp *qp1_proxy[MLX4_MAX_PORTS];
+ /* lock when destroying qp1_proxy and getting netdev events */
+ struct mutex qp1_proxy_lock[MLX4_MAX_PORTS];
};
struct ib_event_work {
@@ -533,6 +576,11 @@ static inline struct mlx4_ib_mr *to_mmr(struct ib_mr *ibmr)
return container_of(ibmr, struct mlx4_ib_mr, ibmr);
}
+static inline struct mlx4_ib_mw *to_mmw(struct ib_mw *ibmw)
+{
+ return container_of(ibmw, struct mlx4_ib_mw, ibmw);
+}
+
static inline struct mlx4_ib_fast_reg_page_list *to_mfrpl(struct ib_fast_reg_page_list *ibfrpl)
{
return container_of(ibfrpl, struct mlx4_ib_fast_reg_page_list, ibfrpl);
@@ -542,6 +590,12 @@ static inline struct mlx4_ib_fmr *to_mfmr(struct ib_fmr *ibfmr)
{
return container_of(ibfmr, struct mlx4_ib_fmr, ibfmr);
}
+
+static inline struct mlx4_ib_flow *to_mflow(struct ib_flow *ibflow)
+{
+ return container_of(ibflow, struct mlx4_ib_flow, ibflow);
+}
+
static inline struct mlx4_ib_qp *to_mqp(struct ib_qp *ibqp)
{
return container_of(ibqp, struct mlx4_ib_qp, ibqp);
@@ -581,6 +635,10 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int access_flags,
struct ib_udata *udata);
int mlx4_ib_dereg_mr(struct ib_mr *mr);
+struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
+int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
+ struct ib_mw_bind *mw_bind);
+int mlx4_ib_dealloc_mw(struct ib_mw *mw);
struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
int max_page_list_len);
struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
@@ -649,15 +707,12 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
union ib_gid *gid, int netw_view);
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
- u8 *mac, int *is_mcast, u8 port);
-
-static inline int mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
+static inline bool mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
{
u8 port = be32_to_cpu(ah->av.ib.port_pd) >> 24 & 3;
if (rdma_port_get_link_layer(ah->ibah.device, port) == IB_LINK_LAYER_ETHERNET)
- return 1;
+ return true;
return !!(ah->av.ib.g_slid & 0x80);
}
@@ -686,9 +741,12 @@ void mlx4_ib_tunnels_update_work(struct work_struct *work);
int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
enum ib_qp_type qpt, struct ib_wc *wc,
struct ib_grh *grh, struct ib_mad *mad);
+
int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn,
- u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad);
+ u32 qkey, struct ib_ah_attr *attr, u8 *s_mac,
+ struct ib_mad *mad);
+
__be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx);
int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
@@ -726,5 +784,9 @@ void mlx4_ib_device_unregister_sysfs(struct mlx4_ib_dev *device);
__be64 mlx4_ib_gen_node_guid(void);
+int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn);
+void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count);
+int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
+ int is_attach);
#endif /* MLX4_IB_H */
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index bbaf6176f20..cb2a8727f3f 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -41,9 +41,19 @@ static u32 convert_access(int acc)
(acc & IB_ACCESS_REMOTE_WRITE ? MLX4_PERM_REMOTE_WRITE : 0) |
(acc & IB_ACCESS_REMOTE_READ ? MLX4_PERM_REMOTE_READ : 0) |
(acc & IB_ACCESS_LOCAL_WRITE ? MLX4_PERM_LOCAL_WRITE : 0) |
+ (acc & IB_ACCESS_MW_BIND ? MLX4_PERM_BIND_MW : 0) |
MLX4_PERM_LOCAL_READ;
}
+static enum mlx4_mw_type to_mlx4_type(enum ib_mw_type type)
+{
+ switch (type) {
+ case IB_MW_TYPE_1: return MLX4_MW_TYPE_1;
+ case IB_MW_TYPE_2: return MLX4_MW_TYPE_2;
+ default: return -1;
+ }
+}
+
struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
{
struct mlx4_ib_mr *mr;
@@ -68,7 +78,7 @@ struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
return &mr->ibmr;
err_mr:
- mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
+ (void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
err_free:
kfree(mr);
@@ -80,11 +90,11 @@ int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
struct ib_umem *umem)
{
u64 *pages;
- struct ib_umem_chunk *chunk;
- int i, j, k;
+ int i, k, entry;
int n;
int len;
int err = 0;
+ struct scatterlist *sg;
pages = (u64 *) __get_free_page(GFP_KERNEL);
if (!pages)
@@ -92,26 +102,25 @@ int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
i = n = 0;
- list_for_each_entry(chunk, &umem->chunk_list, list)
- for (j = 0; j < chunk->nmap; ++j) {
- len = sg_dma_len(&chunk->page_list[j]) >> mtt->page_shift;
- for (k = 0; k < len; ++k) {
- pages[i++] = sg_dma_address(&chunk->page_list[j]) +
- umem->page_size * k;
- /*
- * Be friendly to mlx4_write_mtt() and
- * pass it chunks of appropriate size.
- */
- if (i == PAGE_SIZE / sizeof (u64)) {
- err = mlx4_write_mtt(dev->dev, mtt, n,
- i, pages);
- if (err)
- goto out;
- n += i;
- i = 0;
- }
+ for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+ len = sg_dma_len(sg) >> mtt->page_shift;
+ for (k = 0; k < len; ++k) {
+ pages[i++] = sg_dma_address(sg) +
+ umem->page_size * k;
+ /*
+ * Be friendly to mlx4_write_mtt() and
+ * pass it chunks of appropriate size.
+ */
+ if (i == PAGE_SIZE / sizeof (u64)) {
+ err = mlx4_write_mtt(dev->dev, mtt, n,
+ i, pages);
+ if (err)
+ goto out;
+ n += i;
+ i = 0;
}
}
+ }
if (i)
err = mlx4_write_mtt(dev->dev, mtt, n, i, pages);
@@ -163,7 +172,7 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
return &mr->ibmr;
err_mr:
- mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
+ (void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);
err_umem:
ib_umem_release(mr->umem);
@@ -177,8 +186,11 @@ err_free:
int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
{
struct mlx4_ib_mr *mr = to_mmr(ibmr);
+ int ret;
- mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
+ ret = mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
+ if (ret)
+ return ret;
if (mr->umem)
ib_umem_release(mr->umem);
kfree(mr);
@@ -186,6 +198,70 @@ int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
return 0;
}
+struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
+{
+ struct mlx4_ib_dev *dev = to_mdev(pd->device);
+ struct mlx4_ib_mw *mw;
+ int err;
+
+ mw = kmalloc(sizeof(*mw), GFP_KERNEL);
+ if (!mw)
+ return ERR_PTR(-ENOMEM);
+
+ err = mlx4_mw_alloc(dev->dev, to_mpd(pd)->pdn,
+ to_mlx4_type(type), &mw->mmw);
+ if (err)
+ goto err_free;
+
+ err = mlx4_mw_enable(dev->dev, &mw->mmw);
+ if (err)
+ goto err_mw;
+
+ mw->ibmw.rkey = mw->mmw.key;
+
+ return &mw->ibmw;
+
+err_mw:
+ mlx4_mw_free(dev->dev, &mw->mmw);
+
+err_free:
+ kfree(mw);
+
+ return ERR_PTR(err);
+}
+
+int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
+ struct ib_mw_bind *mw_bind)
+{
+ struct ib_send_wr wr;
+ struct ib_send_wr *bad_wr;
+ int ret;
+
+ memset(&wr, 0, sizeof(wr));
+ wr.opcode = IB_WR_BIND_MW;
+ wr.wr_id = mw_bind->wr_id;
+ wr.send_flags = mw_bind->send_flags;
+ wr.wr.bind_mw.mw = mw;
+ wr.wr.bind_mw.bind_info = mw_bind->bind_info;
+ wr.wr.bind_mw.rkey = ib_inc_rkey(mw->rkey);
+
+ ret = mlx4_ib_post_send(qp, &wr, &bad_wr);
+ if (!ret)
+ mw->rkey = wr.wr.bind_mw.rkey;
+
+ return ret;
+}
+
+int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
+{
+ struct mlx4_ib_mw *mw = to_mmw(ibmw);
+
+ mlx4_mw_free(to_mdev(ibmw->device)->dev, &mw->mmw);
+ kfree(mw);
+
+ return 0;
+}
+
struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
int max_page_list_len)
{
@@ -212,7 +288,7 @@ struct ib_mr *mlx4_ib_alloc_fast_reg_mr(struct ib_pd *pd,
return &mr->ibmr;
err_mr:
- mlx4_mr_free(dev->dev, &mr->mmr);
+ (void) mlx4_mr_free(dev->dev, &mr->mmr);
err_free:
kfree(mr);
@@ -291,7 +367,7 @@ struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc,
return &fmr->ibfmr;
err_mr:
- mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);
+ (void) mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);
err_free:
kfree(fmr);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 19e0637220b..67780452f0c 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -90,6 +90,21 @@ enum {
MLX4_RAW_QP_MSGMAX = 31,
};
+#ifndef ETH_ALEN
+#define ETH_ALEN 6
+#endif
+static inline u64 mlx4_mac_to_u64(u8 *addr)
+{
+ u64 mac = 0;
+ int i;
+
+ for (i = 0; i < ETH_ALEN; i++) {
+ mac <<= 8;
+ mac |= addr[i];
+ }
+ return mac;
+}
+
static const __be32 mlx4_ib_opcode[] = {
[IB_WR_SEND] = cpu_to_be32(MLX4_OPCODE_SEND),
[IB_WR_LSO] = cpu_to_be32(MLX4_OPCODE_LSO),
@@ -104,6 +119,7 @@ static const __be32 mlx4_ib_opcode[] = {
[IB_WR_FAST_REG_MR] = cpu_to_be32(MLX4_OPCODE_FMR),
[IB_WR_MASKED_ATOMIC_CMP_AND_SWP] = cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_CS),
[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD] = cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA),
+ [IB_WR_BIND_MW] = cpu_to_be32(MLX4_OPCODE_BIND_MW),
};
static struct mlx4_ib_sqp *to_msqp(struct mlx4_ib_qp *mqp)
@@ -592,9 +608,20 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
return !attr->srq;
}
+static int qp0_enabled_vf(struct mlx4_dev *dev, int qpn)
+{
+ int i;
+ for (i = 0; i < dev->caps.num_ports; i++) {
+ if (qpn == dev->caps.qp0_proxy[i])
+ return !!dev->caps.qp0_qkey[i];
+ }
+ return 0;
+}
+
static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
struct ib_qp_init_attr *init_attr,
- struct ib_udata *udata, int sqpn, struct mlx4_ib_qp **caller_qp)
+ struct ib_udata *udata, int sqpn, struct mlx4_ib_qp **caller_qp,
+ gfp_t gfp)
{
int qpn;
int err;
@@ -609,10 +636,13 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
!(init_attr->create_flags & MLX4_IB_SRIOV_SQP))) {
if (init_attr->qp_type == IB_QPT_GSI)
qp_type = MLX4_IB_QPT_PROXY_GSI;
- else if (mlx4_is_master(dev->dev))
- qp_type = MLX4_IB_QPT_PROXY_SMI_OWNER;
- else
- qp_type = MLX4_IB_QPT_PROXY_SMI;
+ else {
+ if (mlx4_is_master(dev->dev) ||
+ qp0_enabled_vf(dev->dev, sqpn))
+ qp_type = MLX4_IB_QPT_PROXY_SMI_OWNER;
+ else
+ qp_type = MLX4_IB_QPT_PROXY_SMI;
+ }
}
qpn = sqpn;
/* add extra sg entry for tunneling */
@@ -627,7 +657,9 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
return -EINVAL;
if (tnl_init->proxy_qp_type == IB_QPT_GSI)
qp_type = MLX4_IB_QPT_TUN_GSI;
- else if (tnl_init->slave == mlx4_master_func_num(dev->dev))
+ else if (tnl_init->slave == mlx4_master_func_num(dev->dev) ||
+ mlx4_vf_smi_enabled(dev->dev, tnl_init->slave,
+ tnl_init->port))
qp_type = MLX4_IB_QPT_TUN_SMI_OWNER;
else
qp_type = MLX4_IB_QPT_TUN_SMI;
@@ -642,14 +674,18 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
if (qp_type == MLX4_IB_QPT_SMI || qp_type == MLX4_IB_QPT_GSI ||
(qp_type & (MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_SMI_OWNER |
MLX4_IB_QPT_PROXY_GSI | MLX4_IB_QPT_TUN_SMI_OWNER))) {
- sqp = kzalloc(sizeof (struct mlx4_ib_sqp), GFP_KERNEL);
+ sqp = kzalloc(sizeof (struct mlx4_ib_sqp), gfp);
if (!sqp)
return -ENOMEM;
qp = &sqp->qp;
+ qp->pri.vid = 0xFFFF;
+ qp->alt.vid = 0xFFFF;
} else {
- qp = kzalloc(sizeof (struct mlx4_ib_qp), GFP_KERNEL);
+ qp = kzalloc(sizeof (struct mlx4_ib_qp), gfp);
if (!qp)
return -ENOMEM;
+ qp->pri.vid = 0xFFFF;
+ qp->alt.vid = 0xFFFF;
}
} else
qp = *caller_qp;
@@ -715,19 +751,27 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
if (init_attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO)
qp->flags |= MLX4_IB_QP_LSO;
+ if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
+ if (dev->steering_support ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED)
+ qp->flags |= MLX4_IB_QP_NETIF;
+ else
+ goto err;
+ }
+
err = set_kernel_sq_size(dev, &init_attr->cap, qp_type, qp);
if (err)
goto err;
if (qp_has_rq(init_attr)) {
- err = mlx4_db_alloc(dev->dev, &qp->db, 0);
+ err = mlx4_db_alloc(dev->dev, &qp->db, 0, gfp);
if (err)
goto err;
*qp->db.db = 0;
}
- if (mlx4_buf_alloc(dev->dev, qp->buf_size, PAGE_SIZE * 2, &qp->buf)) {
+ if (mlx4_buf_alloc(dev->dev, qp->buf_size, PAGE_SIZE * 2, &qp->buf, gfp)) {
err = -ENOMEM;
goto err_db;
}
@@ -737,13 +781,12 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
if (err)
goto err_buf;
- err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf);
+ err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf, gfp);
if (err)
goto err_mtt;
- qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof (u64), GFP_KERNEL);
- qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof (u64), GFP_KERNEL);
-
+ qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof (u64), gfp);
+ qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof (u64), gfp);
if (!qp->sq.wrid || !qp->rq.wrid) {
err = -ENOMEM;
goto err_wrid;
@@ -764,12 +807,16 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
if (init_attr->qp_type == IB_QPT_RAW_PACKET)
err = mlx4_qp_reserve_range(dev->dev, 1, 1 << 8, &qpn);
else
- err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn);
+ if (qp->flags & MLX4_IB_QP_NETIF)
+ err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
+ else
+ err = mlx4_qp_reserve_range(dev->dev, 1, 1,
+ &qpn);
if (err)
goto err_proxy;
}
- err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
+ err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp, gfp);
if (err)
goto err_qpn;
@@ -789,8 +836,12 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
return 0;
err_qpn:
- if (!sqpn)
- mlx4_qp_release_range(dev->dev, qpn, 1);
+ if (!sqpn) {
+ if (qp->flags & MLX4_IB_QP_NETIF)
+ mlx4_ib_steer_qp_free(dev, qpn, 1);
+ else
+ mlx4_qp_release_range(dev->dev, qpn, 1);
+ }
err_proxy:
if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI)
free_proxy_bufs(pd->device, qp);
@@ -908,11 +959,32 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
{
struct mlx4_ib_cq *send_cq, *recv_cq;
- if (qp->state != IB_QPS_RESET)
+ if (qp->state != IB_QPS_RESET) {
if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state),
MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp))
pr_warn("modify QP %06x to RESET failed.\n",
qp->mqp.qpn);
+ if (qp->pri.smac) {
+ mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
+ qp->pri.smac = 0;
+ }
+ if (qp->alt.smac) {
+ mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
+ qp->alt.smac = 0;
+ }
+ if (qp->pri.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid);
+ qp->pri.vid = 0xFFFF;
+ qp->pri.candidate_vid = 0xFFFF;
+ qp->pri.update_vid = 0;
+ }
+ if (qp->alt.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid);
+ qp->alt.vid = 0xFFFF;
+ qp->alt.candidate_vid = 0xFFFF;
+ qp->alt.update_vid = 0;
+ }
+ }
get_cqs(qp, &send_cq, &recv_cq);
@@ -931,8 +1003,12 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
mlx4_qp_free(dev->dev, &qp->mqp);
- if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp))
- mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
+ if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp)) {
+ if (qp->flags & MLX4_IB_QP_NETIF)
+ mlx4_ib_steer_qp_free(dev, qp->mqp.qpn, 1);
+ else
+ mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
+ }
mlx4_mtt_cleanup(dev->dev, &qp->mtt);
@@ -979,19 +1055,30 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
struct mlx4_ib_qp *qp = NULL;
int err;
u16 xrcdn = 0;
+ gfp_t gfp;
+ gfp = (init_attr->create_flags & MLX4_IB_QP_CREATE_USE_GFP_NOIO) ?
+ GFP_NOIO : GFP_KERNEL;
/*
* We only support LSO, vendor flag1, and multicast loopback blocking,
* and only for kernel UD QPs.
*/
if (init_attr->create_flags & ~(MLX4_IB_QP_LSO |
MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK |
- MLX4_IB_SRIOV_TUNNEL_QP | MLX4_IB_SRIOV_SQP))
+ MLX4_IB_SRIOV_TUNNEL_QP |
+ MLX4_IB_SRIOV_SQP |
+ MLX4_IB_QP_NETIF |
+ MLX4_IB_QP_CREATE_USE_GFP_NOIO))
return ERR_PTR(-EINVAL);
+ if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
+ if (init_attr->qp_type != IB_QPT_UD)
+ return ERR_PTR(-EINVAL);
+ }
+
if (init_attr->create_flags &&
(udata ||
- ((init_attr->create_flags & ~MLX4_IB_SRIOV_SQP) &&
+ ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP | MLX4_IB_QP_CREATE_USE_GFP_NOIO)) &&
init_attr->qp_type != IB_QPT_UD) ||
((init_attr->create_flags & MLX4_IB_SRIOV_SQP) &&
init_attr->qp_type > IB_QPT_GSI)))
@@ -1011,14 +1098,16 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
case IB_QPT_RC:
case IB_QPT_UC:
case IB_QPT_RAW_PACKET:
- qp = kzalloc(sizeof *qp, GFP_KERNEL);
+ qp = kzalloc(sizeof *qp, gfp);
if (!qp)
return ERR_PTR(-ENOMEM);
+ qp->pri.vid = 0xFFFF;
+ qp->alt.vid = 0xFFFF;
/* fall through */
case IB_QPT_UD:
{
err = create_qp_common(to_mdev(pd->device), pd, init_attr,
- udata, 0, &qp);
+ udata, 0, &qp, gfp);
if (err)
return ERR_PTR(err);
@@ -1036,7 +1125,7 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata,
get_sqp_num(to_mdev(pd->device), init_attr),
- &qp);
+ &qp, gfp);
if (err)
return ERR_PTR(err);
@@ -1062,6 +1151,12 @@ int mlx4_ib_destroy_qp(struct ib_qp *qp)
if (is_qp0(dev, mqp))
mlx4_CLOSE_PORT(dev->dev, mqp->port);
+ if (dev->qp1_proxy[mqp->port - 1] == mqp) {
+ mutex_lock(&dev->qp1_proxy_lock[mqp->port - 1]);
+ dev->qp1_proxy[mqp->port - 1] = NULL;
+ mutex_unlock(&dev->qp1_proxy_lock[mqp->port - 1]);
+ }
+
pd = get_pd(mqp);
destroy_qp_common(dev, mqp, !!pd->ibpd.uobject);
@@ -1143,16 +1238,16 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port)
path->sched_queue = (path->sched_queue & 0xbf) | ((port - 1) << 6);
}
-static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
- struct mlx4_qp_path *path, u8 port)
+static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
+ u64 smac, u16 vlan_tag, struct mlx4_qp_path *path,
+ struct mlx4_roce_smac_vlan_info *smac_info, u8 port)
{
- int err;
int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) ==
IB_LINK_LAYER_ETHERNET;
- u8 mac[6];
- int is_mcast;
- u16 vlan_tag;
int vidx;
+ int smac_index;
+ int err;
+
path->grh_mylmc = ah->src_path_bits & 0x7f;
path->rlid = cpu_to_be16(ah->dlid);
@@ -1181,36 +1276,105 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
}
if (is_eth) {
- path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
- ((port - 1) << 6) | ((ah->sl & 7) << 3);
-
if (!(ah->ah_flags & IB_AH_GRH))
return -1;
- err = mlx4_ib_resolve_grh(dev, ah, mac, &is_mcast, port);
- if (err)
- return err;
-
- memcpy(path->dmac, mac, 6);
- path->ackto = MLX4_IB_LINK_TYPE_ETH;
- /* use index 0 into MAC table for IBoE */
- path->grh_mylmc &= 0x80;
+ path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
+ ((port - 1) << 6) | ((ah->sl & 7) << 3);
- vlan_tag = rdma_get_vlan_id(&dev->iboe.gid_table[port - 1][ah->grh.sgid_index]);
+ path->feup |= MLX4_FEUP_FORCE_ETH_UP;
if (vlan_tag < 0x1000) {
- if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx))
- return -ENOENT;
-
- path->vlan_index = vidx;
+ if (smac_info->vid < 0x1000) {
+ /* both valid vlan ids */
+ if (smac_info->vid != vlan_tag) {
+ /* different VIDs. unreg old and reg new */
+ err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx);
+ if (err)
+ return err;
+ smac_info->candidate_vid = vlan_tag;
+ smac_info->candidate_vlan_index = vidx;
+ smac_info->candidate_vlan_port = port;
+ smac_info->update_vid = 1;
+ path->vlan_index = vidx;
+ } else {
+ path->vlan_index = smac_info->vlan_index;
+ }
+ } else {
+ /* no current vlan tag in qp */
+ err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx);
+ if (err)
+ return err;
+ smac_info->candidate_vid = vlan_tag;
+ smac_info->candidate_vlan_index = vidx;
+ smac_info->candidate_vlan_port = port;
+ smac_info->update_vid = 1;
+ path->vlan_index = vidx;
+ }
+ path->feup |= MLX4_FVL_FORCE_ETH_VLAN;
path->fl = 1 << 6;
+ } else {
+ /* have current vlan tag. unregister it at modify-qp success */
+ if (smac_info->vid < 0x1000) {
+ smac_info->candidate_vid = 0xFFFF;
+ smac_info->update_vid = 1;
+ }
}
- } else
+
+ /* get smac_index for RoCE use.
+ * If no smac was yet assigned, register one.
+ * If one was already assigned, but the new mac differs,
+ * unregister the old one and register the new one.
+ */
+ if (!smac_info->smac || smac_info->smac != smac) {
+ /* register candidate now, unreg if needed, after success */
+ smac_index = mlx4_register_mac(dev->dev, port, smac);
+ if (smac_index >= 0) {
+ smac_info->candidate_smac_index = smac_index;
+ smac_info->candidate_smac = smac;
+ smac_info->candidate_smac_port = port;
+ } else {
+ return -EINVAL;
+ }
+ } else {
+ smac_index = smac_info->smac_index;
+ }
+
+ memcpy(path->dmac, ah->dmac, 6);
+ path->ackto = MLX4_IB_LINK_TYPE_ETH;
+ /* put MAC table smac index for IBoE */
+ path->grh_mylmc = (u8) (smac_index) | 0x80;
+ } else {
path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
((port - 1) << 6) | ((ah->sl & 0xf) << 2);
+ }
return 0;
}
+static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp,
+ enum ib_qp_attr_mask qp_attr_mask,
+ struct mlx4_ib_qp *mqp,
+ struct mlx4_qp_path *path, u8 port)
+{
+ return _mlx4_set_path(dev, &qp->ah_attr,
+ mlx4_mac_to_u64((u8 *)qp->smac),
+ (qp_attr_mask & IB_QP_VID) ? qp->vlan_id : 0xffff,
+ path, &mqp->pri, port);
+}
+
+static int mlx4_set_alt_path(struct mlx4_ib_dev *dev,
+ const struct ib_qp_attr *qp,
+ enum ib_qp_attr_mask qp_attr_mask,
+ struct mlx4_ib_qp *mqp,
+ struct mlx4_qp_path *path, u8 port)
+{
+ return _mlx4_set_path(dev, &qp->alt_ah_attr,
+ mlx4_mac_to_u64((u8 *)qp->alt_smac),
+ (qp_attr_mask & IB_QP_ALT_VID) ?
+ qp->alt_vlan_id : 0xffff,
+ path, &mqp->alt, port);
+}
+
static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
{
struct mlx4_ib_gid_entry *ge, *tmp;
@@ -1223,6 +1387,37 @@ static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
}
}
+static int handle_eth_ud_smac_index(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, u8 *smac,
+ struct mlx4_qp_context *context)
+{
+ struct net_device *ndev;
+ u64 u64_mac;
+ int smac_index;
+
+
+ ndev = dev->iboe.netdevs[qp->port - 1];
+ if (ndev) {
+ smac = ndev->dev_addr;
+ u64_mac = mlx4_mac_to_u64(smac);
+ } else {
+ u64_mac = dev->dev->caps.def_mac[qp->port];
+ }
+
+ context->pri_path.sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | ((qp->port - 1) << 6);
+ if (!qp->pri.smac) {
+ smac_index = mlx4_register_mac(dev->dev, qp->port, u64_mac);
+ if (smac_index >= 0) {
+ qp->pri.candidate_smac_index = smac_index;
+ qp->pri.candidate_smac = u64_mac;
+ qp->pri.candidate_smac_port = qp->port;
+ context->pri_path.grh_mylmc = 0x80 | (u8) smac_index;
+ } else {
+ return -ENOENT;
+ }
+ }
+ return 0;
+}
+
static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
const struct ib_qp_attr *attr, int attr_mask,
enum ib_qp_state cur_state, enum ib_qp_state new_state)
@@ -1234,6 +1429,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
struct mlx4_qp_context *context;
enum mlx4_qp_optpar optpar = 0;
int sqd_event;
+ int steer_qp = 0;
int err = -EINVAL;
context = kzalloc(sizeof *context, GFP_KERNEL);
@@ -1291,6 +1487,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
context->sq_size_stride |= !!qp->sq_no_prefetch << 7;
context->xrcd = cpu_to_be32((u32) qp->xrcdn);
+ if (ibqp->qp_type == IB_QPT_RAW_PACKET)
+ context->param3 |= cpu_to_be32(1 << 30);
}
if (qp->ibqp.uobject)
@@ -1316,6 +1514,11 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
optpar |= MLX4_QP_OPTPAR_COUNTER_INDEX;
} else
context->pri_path.counter_index = 0xff;
+
+ if (qp->flags & MLX4_IB_QP_NETIF) {
+ mlx4_ib_steer_qp_reg(dev, qp, 1);
+ steer_qp = 1;
+ }
}
if (attr_mask & IB_QP_PKEY_INDEX) {
@@ -1326,7 +1529,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
}
if (attr_mask & IB_QP_AV) {
- if (mlx4_set_path(dev, &attr->ah_attr, &context->pri_path,
+ if (mlx4_set_path(dev, attr, attr_mask, qp, &context->pri_path,
attr_mask & IB_QP_PORT ?
attr->port_num : qp->port))
goto out;
@@ -1349,8 +1552,9 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
dev->dev->caps.pkey_table_len[attr->alt_port_num])
goto out;
- if (mlx4_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
- attr->alt_port_num))
+ if (mlx4_set_alt_path(dev, attr, attr_mask, qp,
+ &context->alt_path,
+ attr->alt_port_num))
goto out;
context->alt_path.pkey_index = attr->alt_pkey_index;
@@ -1455,8 +1659,39 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
context->pri_path.fl = 0x80;
context->pri_path.sched_queue |= MLX4_IB_DEFAULT_SCHED_QUEUE;
}
+ if (rdma_port_get_link_layer(&dev->ib_dev, qp->port) ==
+ IB_LINK_LAYER_ETHERNET) {
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI ||
+ qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI)
+ context->pri_path.feup = 1 << 7; /* don't fsm */
+ /* handle smac_index */
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_UD ||
+ qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI ||
+ qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI) {
+ err = handle_eth_ud_smac_index(dev, qp, (u8 *)attr->smac, context);
+ if (err)
+ return -EINVAL;
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI)
+ dev->qp1_proxy[qp->port - 1] = qp;
+ }
+ }
}
+ if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET)
+ context->pri_path.ackto = (context->pri_path.ackto & 0xf8) |
+ MLX4_IB_LINK_TYPE_ETH;
+
+ if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
+ int is_eth = rdma_port_get_link_layer(
+ &dev->ib_dev, qp->port) ==
+ IB_LINK_LAYER_ETHERNET;
+ if (is_eth) {
+ context->pri_path.ackto = MLX4_IB_LINK_TYPE_ETH;
+ optpar |= MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH;
+ }
+ }
+
+
if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD &&
attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify)
sqd_event = 1;
@@ -1527,23 +1762,113 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
* If we moved a kernel QP to RESET, clean up all old CQ
* entries and reinitialize the QP.
*/
- if (new_state == IB_QPS_RESET && !ibqp->uobject) {
- mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
- ibqp->srq ? to_msrq(ibqp->srq): NULL);
- if (send_cq != recv_cq)
- mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
+ if (new_state == IB_QPS_RESET) {
+ if (!ibqp->uobject) {
+ mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
+ ibqp->srq ? to_msrq(ibqp->srq) : NULL);
+ if (send_cq != recv_cq)
+ mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
+
+ qp->rq.head = 0;
+ qp->rq.tail = 0;
+ qp->sq.head = 0;
+ qp->sq.tail = 0;
+ qp->sq_next_wqe = 0;
+ if (qp->rq.wqe_cnt)
+ *qp->db.db = 0;
+
+ if (qp->flags & MLX4_IB_QP_NETIF)
+ mlx4_ib_steer_qp_reg(dev, qp, 0);
+ }
+ if (qp->pri.smac) {
+ mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
+ qp->pri.smac = 0;
+ }
+ if (qp->alt.smac) {
+ mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
+ qp->alt.smac = 0;
+ }
+ if (qp->pri.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid);
+ qp->pri.vid = 0xFFFF;
+ qp->pri.candidate_vid = 0xFFFF;
+ qp->pri.update_vid = 0;
+ }
- qp->rq.head = 0;
- qp->rq.tail = 0;
- qp->sq.head = 0;
- qp->sq.tail = 0;
- qp->sq_next_wqe = 0;
- if (qp->rq.wqe_cnt)
- *qp->db.db = 0;
+ if (qp->alt.vid < 0x1000) {
+ mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid);
+ qp->alt.vid = 0xFFFF;
+ qp->alt.candidate_vid = 0xFFFF;
+ qp->alt.update_vid = 0;
+ }
}
-
out:
+ if (err && steer_qp)
+ mlx4_ib_steer_qp_reg(dev, qp, 0);
kfree(context);
+ if (qp->pri.candidate_smac) {
+ if (err) {
+ mlx4_unregister_mac(dev->dev, qp->pri.candidate_smac_port, qp->pri.candidate_smac);
+ } else {
+ if (qp->pri.smac)
+ mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
+ qp->pri.smac = qp->pri.candidate_smac;
+ qp->pri.smac_index = qp->pri.candidate_smac_index;
+ qp->pri.smac_port = qp->pri.candidate_smac_port;
+ }
+ qp->pri.candidate_smac = 0;
+ qp->pri.candidate_smac_index = 0;
+ qp->pri.candidate_smac_port = 0;
+ }
+ if (qp->alt.candidate_smac) {
+ if (err) {
+ mlx4_unregister_mac(dev->dev, qp->alt.candidate_smac_port, qp->alt.candidate_smac);
+ } else {
+ if (qp->alt.smac)
+ mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
+ qp->alt.smac = qp->alt.candidate_smac;
+ qp->alt.smac_index = qp->alt.candidate_smac_index;
+ qp->alt.smac_port = qp->alt.candidate_smac_port;
+ }
+ qp->alt.candidate_smac = 0;
+ qp->alt.candidate_smac_index = 0;
+ qp->alt.candidate_smac_port = 0;
+ }
+
+ if (qp->pri.update_vid) {
+ if (err) {
+ if (qp->pri.candidate_vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->pri.candidate_vlan_port,
+ qp->pri.candidate_vid);
+ } else {
+ if (qp->pri.vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port,
+ qp->pri.vid);
+ qp->pri.vid = qp->pri.candidate_vid;
+ qp->pri.vlan_port = qp->pri.candidate_vlan_port;
+ qp->pri.vlan_index = qp->pri.candidate_vlan_index;
+ }
+ qp->pri.candidate_vid = 0xFFFF;
+ qp->pri.update_vid = 0;
+ }
+
+ if (qp->alt.update_vid) {
+ if (err) {
+ if (qp->alt.candidate_vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->alt.candidate_vlan_port,
+ qp->alt.candidate_vid);
+ } else {
+ if (qp->alt.vid < 0x1000)
+ mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port,
+ qp->alt.vid);
+ qp->alt.vid = qp->alt.candidate_vid;
+ qp->alt.vlan_port = qp->alt.candidate_vlan_port;
+ qp->alt.vlan_index = qp->alt.candidate_vlan_index;
+ }
+ qp->alt.candidate_vid = 0xFFFF;
+ qp->alt.update_vid = 0;
+ }
+
return err;
}
@@ -1554,13 +1879,21 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
struct mlx4_ib_qp *qp = to_mqp(ibqp);
enum ib_qp_state cur_state, new_state;
int err = -EINVAL;
-
+ int ll;
mutex_lock(&qp->mutex);
cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
- if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) {
+ if (cur_state == new_state && cur_state == IB_QPS_RESET) {
+ ll = IB_LINK_LAYER_UNSPECIFIED;
+ } else {
+ int port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+ ll = rdma_port_get_link_layer(&dev->ib_dev, port);
+ }
+
+ if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
+ attr_mask, ll)) {
pr_debug("qpn 0x%x: invalid attribute mask specified "
"for transition %d to %d. qp_type %d,"
" attr_mask 0x%x\n",
@@ -1624,6 +1957,19 @@ out:
return err;
}
+static int vf_get_qp0_qkey(struct mlx4_dev *dev, int qpn, u32 *qkey)
+{
+ int i;
+ for (i = 0; i < dev->caps.num_ports; i++) {
+ if (qpn == dev->caps.qp0_proxy[i] ||
+ qpn == dev->caps.qp0_tunnel[i]) {
+ *qkey = dev->caps.qp0_qkey[i];
+ return 0;
+ }
+ }
+ return -EINVAL;
+}
+
static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
struct ib_send_wr *wr,
void *wqe, unsigned *mlx_seg_len)
@@ -1681,8 +2027,13 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
cpu_to_be32(mdev->dev->caps.qp0_tunnel[sqp->qp.port - 1]);
sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
- if (mlx4_get_parav_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
- return -EINVAL;
+ if (mlx4_is_master(mdev->dev)) {
+ if (mlx4_get_parav_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
+ return -EINVAL;
+ } else {
+ if (vf_get_qp0_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
+ return -EINVAL;
+ }
sqp->ud_header.deth.qkey = cpu_to_be32(qkey);
sqp->ud_header.deth.source_qpn = cpu_to_be32(sqp->qp.mqp.qpn);
@@ -1737,20 +2088,20 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
{
struct ib_device *ib_dev = sqp->qp.ibqp.device;
struct mlx4_wqe_mlx_seg *mlx = wqe;
+ struct mlx4_wqe_ctrl_seg *ctrl = wqe;
struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah);
- struct net_device *ndev;
union ib_gid sgid;
u16 pkey;
int send_size;
int header_size;
int spc;
int i;
- int is_eth;
- int is_vlan = 0;
- int is_grh;
- u16 vlan;
int err = 0;
+ u16 vlan = 0xffff;
+ bool is_eth;
+ bool is_vlan = false;
+ bool is_grh;
send_size = 0;
for (i = 0; i < wr->num_sge; ++i)
@@ -1763,12 +2114,11 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
/* When multi-function is enabled, the ib_core gid
* indexes don't necessarily match the hw ones, so
* we must use our own cache */
- sgid.global.subnet_prefix =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- subnet_prefix;
- sgid.global.interface_id =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- guid_cache[ah->av.ib.gid_index];
+ err = mlx4_get_roce_gid_from_slave(to_mdev(ib_dev)->dev,
+ be32_to_cpu(ah->av.ib.port_pd) >> 24,
+ ah->av.ib.gid_index, &sgid.raw[0]);
+ if (err)
+ return err;
} else {
err = ib_get_cached_gid(ib_dev,
be32_to_cpu(ah->av.ib.port_pd) >> 24,
@@ -1777,8 +2127,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
return err;
}
- vlan = rdma_get_vlan_id(&sgid);
- is_vlan = vlan < 0x1000;
+ if (ah->av.eth.vlan != cpu_to_be16(0xffff)) {
+ vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
+ is_vlan = 1;
+ }
}
ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header);
@@ -1795,6 +2147,9 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
sqp->ud_header.grh.flow_label =
ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
sqp->ud_header.grh.hop_limit = ah->av.ib.hop_limit;
+ if (is_eth)
+ memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
+ else {
if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
/* When multi-function is enabled, the ib_core gid
* indexes don't necessarily match the hw ones, so
@@ -1810,6 +2165,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
be32_to_cpu(ah->av.ib.port_pd) >> 24,
ah->av.ib.gid_index,
&sqp->ud_header.grh.source_gid);
+ }
memcpy(sqp->ud_header.grh.destination_gid.raw,
ah->av.ib.dgid, 16);
}
@@ -1842,16 +2198,23 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
if (is_eth) {
u8 *smac;
+ struct in6_addr in6;
+
u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13;
mlx->sched_prio = cpu_to_be16(pcp);
memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
/* FIXME: cache smac value? */
- ndev = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1];
- if (!ndev)
- return -ENODEV;
- smac = ndev->dev_addr;
+ memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2);
+ memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4);
+ memcpy(&in6, sgid.raw, sizeof(in6));
+
+ if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev))
+ smac = to_mdev(sqp->qp.ibqp.device)->
+ iboe.netdevs[sqp->qp.port - 1]->dev_addr;
+ else /* use the src mac of the tunnel */
+ smac = ah->av.eth.s_mac;
memcpy(sqp->ud_header.eth.smac_h, smac, 6);
if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
@@ -1953,9 +2316,12 @@ static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq
static __be32 convert_access(int acc)
{
- return (acc & IB_ACCESS_REMOTE_ATOMIC ? cpu_to_be32(MLX4_WQE_FMR_PERM_ATOMIC) : 0) |
- (acc & IB_ACCESS_REMOTE_WRITE ? cpu_to_be32(MLX4_WQE_FMR_PERM_REMOTE_WRITE) : 0) |
- (acc & IB_ACCESS_REMOTE_READ ? cpu_to_be32(MLX4_WQE_FMR_PERM_REMOTE_READ) : 0) |
+ return (acc & IB_ACCESS_REMOTE_ATOMIC ?
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC) : 0) |
+ (acc & IB_ACCESS_REMOTE_WRITE ?
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE) : 0) |
+ (acc & IB_ACCESS_REMOTE_READ ?
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ) : 0) |
(acc & IB_ACCESS_LOCAL_WRITE ? cpu_to_be32(MLX4_WQE_FMR_PERM_LOCAL_WRITE) : 0) |
cpu_to_be32(MLX4_WQE_FMR_PERM_LOCAL_READ);
}
@@ -1981,12 +2347,28 @@ static void set_fmr_seg(struct mlx4_wqe_fmr_seg *fseg, struct ib_send_wr *wr)
fseg->reserved[1] = 0;
}
+static void set_bind_seg(struct mlx4_wqe_bind_seg *bseg, struct ib_send_wr *wr)
+{
+ bseg->flags1 =
+ convert_access(wr->wr.bind_mw.bind_info.mw_access_flags) &
+ cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ |
+ MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE |
+ MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC);
+ bseg->flags2 = 0;
+ if (wr->wr.bind_mw.mw->type == IB_MW_TYPE_2)
+ bseg->flags2 |= cpu_to_be32(MLX4_WQE_BIND_TYPE_2);
+ if (wr->wr.bind_mw.bind_info.mw_access_flags & IB_ZERO_BASED)
+ bseg->flags2 |= cpu_to_be32(MLX4_WQE_BIND_ZERO_BASED);
+ bseg->new_rkey = cpu_to_be32(wr->wr.bind_mw.rkey);
+ bseg->lkey = cpu_to_be32(wr->wr.bind_mw.bind_info.mr->lkey);
+ bseg->addr = cpu_to_be64(wr->wr.bind_mw.bind_info.addr);
+ bseg->length = cpu_to_be64(wr->wr.bind_mw.bind_info.length);
+}
+
static void set_local_inv_seg(struct mlx4_wqe_local_inval_seg *iseg, u32 rkey)
{
- iseg->flags = 0;
- iseg->mem_key = cpu_to_be32(rkey);
- iseg->guest_id = 0;
- iseg->pa = 0;
+ memset(iseg, 0, sizeof(*iseg));
+ iseg->mem_key = cpu_to_be32(rkey);
}
static __always_inline void set_raddr_seg(struct mlx4_wqe_raddr_seg *rseg,
@@ -2033,7 +2415,8 @@ static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg,
static void set_tunnel_datagram_seg(struct mlx4_ib_dev *dev,
struct mlx4_wqe_datagram_seg *dseg,
- struct ib_send_wr *wr, enum ib_qp_type qpt)
+ struct ib_send_wr *wr,
+ enum mlx4_ib_qp_type qpt)
{
union mlx4_ext_av *av = &to_mah(wr->wr.ud.ah)->av;
struct mlx4_av sqp_av = {0};
@@ -2046,8 +2429,10 @@ static void set_tunnel_datagram_seg(struct mlx4_ib_dev *dev,
cpu_to_be32(0xf0000000);
memcpy(dseg->av, &sqp_av, sizeof (struct mlx4_av));
- /* This function used only for sending on QP1 proxies */
- dseg->dqpn = cpu_to_be32(dev->dev->caps.qp1_tunnel[port - 1]);
+ if (qpt == MLX4_IB_QPT_PROXY_GSI)
+ dseg->dqpn = cpu_to_be32(dev->dev->caps.qp1_tunnel[port - 1]);
+ else
+ dseg->dqpn = cpu_to_be32(dev->dev->caps.qp0_tunnel[port - 1]);
/* Use QKEY from the QP context, which is set by master */
dseg->qkey = cpu_to_be32(IB_QP_SET_QKEY);
}
@@ -2064,6 +2449,8 @@ static void build_tunnel_header(struct ib_send_wr *wr, void *wqe, unsigned *mlx_
hdr.remote_qpn = cpu_to_be32(wr->wr.ud.remote_qpn);
hdr.pkey_index = cpu_to_be16(wr->wr.ud.pkey_index);
hdr.qkey = cpu_to_be32(wr->wr.ud.remote_qkey);
+ memcpy(hdr.mac, ah->av.eth.mac, 6);
+ hdr.vlan = ah->av.eth.vlan;
spc = MLX4_INLINE_ALIGN -
((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
@@ -2291,6 +2678,13 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
size += sizeof (struct mlx4_wqe_fmr_seg) / 16;
break;
+ case IB_WR_BIND_MW:
+ ctrl->srcrb_flags |=
+ cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
+ set_bind_seg(wqe, wr);
+ wqe += sizeof(struct mlx4_wqe_bind_seg);
+ size += sizeof(struct mlx4_wqe_bind_seg) / 16;
+ break;
default:
/* No extra segments required for sends */
break;
@@ -2333,11 +2727,6 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
break;
case MLX4_IB_QPT_PROXY_SMI_OWNER:
- if (unlikely(!mlx4_is_master(to_mdev(ibqp->device)->dev))) {
- err = -ENOSYS;
- *bad_wr = wr;
- goto out;
- }
err = build_sriov_qp0_header(to_msqp(qp), wr, ctrl, &seglen);
if (unlikely(err)) {
*bad_wr = wr;
@@ -2354,16 +2743,13 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
size += seglen / 16;
break;
case MLX4_IB_QPT_PROXY_SMI:
- /* don't allow QP0 sends on guests */
- err = -ENOSYS;
- *bad_wr = wr;
- goto out;
case MLX4_IB_QPT_PROXY_GSI:
/* If we are tunneling special qps, this is a UD qp.
* In this case we first add a UD segment targeting
* the tunnel qp, and then add a header with address
* information */
- set_tunnel_datagram_seg(to_mdev(ibqp->device), wqe, wr, ibqp->qp_type);
+ set_tunnel_datagram_seg(to_mdev(ibqp->device), wqe, wr,
+ qp->mlx4_ib_qp_type);
wqe += sizeof (struct mlx4_wqe_datagram_seg);
size += sizeof (struct mlx4_wqe_datagram_seg) / 16;
build_tunnel_header(wr, wqe, &seglen);
@@ -2729,6 +3115,9 @@ done:
if (qp->flags & MLX4_IB_QP_LSO)
qp_init_attr->create_flags |= IB_QP_CREATE_IPOIB_UD_LSO;
+ if (qp->flags & MLX4_IB_QP_NETIF)
+ qp_init_attr->create_flags |= IB_QP_CREATE_NETIF_QP;
+
qp_init_attr->sq_sig_type =
qp->sq_signal_bits == cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE) ?
IB_SIGNAL_ALL_WR : IB_SIGNAL_REQ_WR;
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 60c5fb025fc..62d9285300a 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -134,13 +134,14 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
if (err)
goto err_mtt;
} else {
- err = mlx4_db_alloc(dev->dev, &srq->db, 0);
+ err = mlx4_db_alloc(dev->dev, &srq->db, 0, GFP_KERNEL);
if (err)
goto err_srq;
*srq->db.db = 0;
- if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2, &srq->buf)) {
+ if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2, &srq->buf,
+ GFP_KERNEL)) {
err = -ENOMEM;
goto err_db;
}
@@ -165,7 +166,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
if (err)
goto err_buf;
- err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf);
+ err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf, GFP_KERNEL);
if (err)
goto err_mtt;
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index 5b2a01dfb90..cb4c66e723b 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -389,8 +389,10 @@ struct mlx4_port {
struct mlx4_ib_dev *dev;
struct attribute_group pkey_group;
struct attribute_group gid_group;
- u8 port_num;
+ struct device_attribute enable_smi_admin;
+ struct device_attribute smi_enabled;
int slave;
+ u8 port_num;
};
@@ -558,6 +560,101 @@ err:
return NULL;
}
+static ssize_t sysfs_show_smi_enabled(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct mlx4_port *p =
+ container_of(attr, struct mlx4_port, smi_enabled);
+ ssize_t len = 0;
+
+ if (mlx4_vf_smi_enabled(p->dev->dev, p->slave, p->port_num))
+ len = sprintf(buf, "%d\n", 1);
+ else
+ len = sprintf(buf, "%d\n", 0);
+
+ return len;
+}
+
+static ssize_t sysfs_show_enable_smi_admin(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct mlx4_port *p =
+ container_of(attr, struct mlx4_port, enable_smi_admin);
+ ssize_t len = 0;
+
+ if (mlx4_vf_get_enable_smi_admin(p->dev->dev, p->slave, p->port_num))
+ len = sprintf(buf, "%d\n", 1);
+ else
+ len = sprintf(buf, "%d\n", 0);
+
+ return len;
+}
+
+static ssize_t sysfs_store_enable_smi_admin(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct mlx4_port *p =
+ container_of(attr, struct mlx4_port, enable_smi_admin);
+ int enable;
+
+ if (sscanf(buf, "%i", &enable) != 1 ||
+ enable < 0 || enable > 1)
+ return -EINVAL;
+
+ if (mlx4_vf_set_enable_smi_admin(p->dev->dev, p->slave, p->port_num, enable))
+ return -EINVAL;
+ return count;
+}
+
+static int add_vf_smi_entries(struct mlx4_port *p)
+{
+ int is_eth = rdma_port_get_link_layer(&p->dev->ib_dev, p->port_num) ==
+ IB_LINK_LAYER_ETHERNET;
+ int ret;
+
+ /* do not display entries if eth transport, or if master */
+ if (is_eth || p->slave == mlx4_master_func_num(p->dev->dev))
+ return 0;
+
+ sysfs_attr_init(&p->smi_enabled.attr);
+ p->smi_enabled.show = sysfs_show_smi_enabled;
+ p->smi_enabled.store = NULL;
+ p->smi_enabled.attr.name = "smi_enabled";
+ p->smi_enabled.attr.mode = 0444;
+ ret = sysfs_create_file(&p->kobj, &p->smi_enabled.attr);
+ if (ret) {
+ pr_err("failed to create smi_enabled\n");
+ return ret;
+ }
+
+ sysfs_attr_init(&p->enable_smi_admin.attr);
+ p->enable_smi_admin.show = sysfs_show_enable_smi_admin;
+ p->enable_smi_admin.store = sysfs_store_enable_smi_admin;
+ p->enable_smi_admin.attr.name = "enable_smi_admin";
+ p->enable_smi_admin.attr.mode = 0644;
+ ret = sysfs_create_file(&p->kobj, &p->enable_smi_admin.attr);
+ if (ret) {
+ pr_err("failed to create enable_smi_admin\n");
+ sysfs_remove_file(&p->kobj, &p->smi_enabled.attr);
+ return ret;
+ }
+ return 0;
+}
+
+static void remove_vf_smi_entries(struct mlx4_port *p)
+{
+ int is_eth = rdma_port_get_link_layer(&p->dev->ib_dev, p->port_num) ==
+ IB_LINK_LAYER_ETHERNET;
+
+ if (is_eth || p->slave == mlx4_master_func_num(p->dev->dev))
+ return;
+
+ sysfs_remove_file(&p->kobj, &p->smi_enabled.attr);
+ sysfs_remove_file(&p->kobj, &p->enable_smi_admin.attr);
+}
+
static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
{
struct mlx4_port *p;
@@ -582,8 +679,10 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
p->pkey_group.attrs =
alloc_group_attrs(show_port_pkey, store_port_pkey,
dev->dev->caps.pkey_table_len[port_num]);
- if (!p->pkey_group.attrs)
+ if (!p->pkey_group.attrs) {
+ ret = -ENOMEM;
goto err_alloc;
+ }
ret = sysfs_create_group(&p->kobj, &p->pkey_group);
if (ret)
@@ -591,13 +690,19 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
p->gid_group.name = "gid_idx";
p->gid_group.attrs = alloc_group_attrs(show_port_gid_idx, NULL, 1);
- if (!p->gid_group.attrs)
+ if (!p->gid_group.attrs) {
+ ret = -ENOMEM;
goto err_free_pkey;
+ }
ret = sysfs_create_group(&p->kobj, &p->gid_group);
if (ret)
goto err_free_gid;
+ ret = add_vf_smi_entries(p);
+ if (ret)
+ goto err_free_gid;
+
list_add_tail(&p->kobj.entry, &dev->pkeys.pkey_port_list[slave]);
return 0;
@@ -623,6 +728,7 @@ static int register_one_pkey_tree(struct mlx4_ib_dev *dev, int slave)
int port;
struct kobject *p, *t;
struct mlx4_port *mport;
+ struct mlx4_active_ports actv_ports;
get_name(dev, name, slave, sizeof name);
@@ -645,7 +751,11 @@ static int register_one_pkey_tree(struct mlx4_ib_dev *dev, int slave)
goto err_ports;
}
+ actv_ports = mlx4_get_active_ports(dev->dev, slave);
+
for (port = 1; port <= dev->dev->caps.num_ports; ++port) {
+ if (!test_bit(port - 1, actv_ports.ports))
+ continue;
err = add_port(dev, port, slave);
if (err)
goto err_add;
@@ -660,6 +770,7 @@ err_add:
mport = container_of(p, struct mlx4_port, kobj);
sysfs_remove_group(p, &mport->pkey_group);
sysfs_remove_group(p, &mport->gid_group);
+ remove_vf_smi_entries(mport);
kobject_put(p);
}
kobject_put(dev->dev_ports_parent[slave]);
@@ -704,6 +815,7 @@ static void unregister_pkey_tree(struct mlx4_ib_dev *device)
port = container_of(p, struct mlx4_port, kobj);
sysfs_remove_group(p, &port->pkey_group);
sysfs_remove_group(p, &port->gid_group);
+ remove_vf_smi_entries(port);
kobject_put(p);
kobject_put(device->dev_ports_parent[slave]);
}
@@ -732,7 +844,7 @@ int mlx4_ib_device_register_sysfs(struct mlx4_ib_dev *dev)
dev->ports_parent =
kobject_create_and_add("ports",
kobject_get(dev->iov_parent));
- if (!dev->iov_parent) {
+ if (!dev->ports_parent) {
ret = -ENOMEM;
goto err_ports;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 19:30:44 +0000