summaryrefslogtreecommitdiff
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/ah.c5
-rw-r--r--drivers/infiniband/hw/mlx4/cm.c152
-rw-r--r--drivers/infiniband/hw/mlx4/cq.c4
-rw-r--r--drivers/infiniband/hw/mlx4/mad.c158
-rw-r--r--drivers/infiniband/hw/mlx4/main.c45
-rw-r--r--drivers/infiniband/hw/mlx4/mlx4_ib.h62
-rw-r--r--drivers/infiniband/hw/mlx4/mr.c35
-rw-r--r--drivers/infiniband/hw/mlx4/qp.c345
-rw-r--r--drivers/infiniband/hw/mlx4/srq.c8
9 files changed, 464 insertions, 350 deletions
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 5f8f8d5c0ce0..7321d6ab5fe1 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -232,8 +232,3 @@ int mlx4_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)
return 0;
}
-
-void mlx4_ib_destroy_ah(struct ib_ah *ah, u32 flags)
-{
- return;
-}
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index b591861934b3..4aff1c8298b1 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -54,11 +54,20 @@ struct id_map_entry {
struct delayed_work timeout;
};
+struct rej_tmout_entry {
+ int slave;
+ u32 rem_pv_cm_id;
+ struct delayed_work timeout;
+ struct xarray *xa_rej_tmout;
+};
+
struct cm_generic_msg {
struct ib_mad_hdr hdr;
__be32 local_comm_id;
__be32 remote_comm_id;
+ unsigned char unused[2];
+ __be16 rej_reason;
};
struct cm_sidr_generic_msg {
@@ -280,11 +289,15 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id)
if (!sriov->is_going_down && !id->scheduled_delete) {
id->scheduled_delete = 1;
schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+ } else if (id->scheduled_delete) {
+ /* Adjust timeout if already scheduled */
+ mod_delayed_work(system_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
}
spin_unlock_irqrestore(&sriov->going_down_lock, flags);
spin_unlock(&sriov->id_map_lock);
}
+#define REJ_REASON(m) be16_to_cpu(((struct cm_generic_msg *)(m))->rej_reason)
int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id,
struct ib_mad *mad)
{
@@ -293,8 +306,10 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id
int pv_cm_id = -1;
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_SIDR_REQ_ATTR_ID) {
+ mad->mad_hdr.attr_id == CM_REP_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_MRA_ATTR_ID ||
+ mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID ||
+ (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID && REJ_REASON(mad) == IB_CM_REJ_TIMEOUT)) {
sl_cm_id = get_local_comm_id(mad);
id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id);
if (id)
@@ -314,8 +329,8 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id
}
if (!id) {
- pr_debug("id{slave: %d, sl_cm_id: 0x%x} is NULL!\n",
- slave_id, sl_cm_id);
+ pr_debug("id{slave: %d, sl_cm_id: 0x%x} is NULL! attr_id: 0x%x\n",
+ slave_id, sl_cm_id, be16_to_cpu(mad->mad_hdr.attr_id));
return -EINVAL;
}
@@ -327,11 +342,94 @@ cont:
return 0;
}
+static void rej_tmout_timeout(struct work_struct *work)
+{
+ struct delayed_work *delay = to_delayed_work(work);
+ struct rej_tmout_entry *item = container_of(delay, struct rej_tmout_entry, timeout);
+ struct rej_tmout_entry *deleted;
+
+ deleted = xa_cmpxchg(item->xa_rej_tmout, item->rem_pv_cm_id, item, NULL, 0);
+
+ if (deleted != item)
+ pr_debug("deleted(%p) != item(%p)\n", deleted, item);
+
+ kfree(item);
+}
+
+static int alloc_rej_tmout(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id, int slave)
+{
+ struct rej_tmout_entry *item;
+ struct rej_tmout_entry *old;
+ int ret = 0;
+
+ xa_lock(&sriov->xa_rej_tmout);
+ item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id);
+
+ if (item) {
+ if (xa_err(item))
+ ret = xa_err(item);
+ else
+ /* If a retry, adjust delayed work */
+ mod_delayed_work(system_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+ goto err_or_exists;
+ }
+ xa_unlock(&sriov->xa_rej_tmout);
+
+ item = kmalloc(sizeof(*item), GFP_KERNEL);
+ if (!item)
+ return -ENOMEM;
+
+ INIT_DELAYED_WORK(&item->timeout, rej_tmout_timeout);
+ item->slave = slave;
+ item->rem_pv_cm_id = rem_pv_cm_id;
+ item->xa_rej_tmout = &sriov->xa_rej_tmout;
+
+ old = xa_cmpxchg(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id, NULL, item, GFP_KERNEL);
+ if (old) {
+ pr_debug(
+ "Non-null old entry (%p) or error (%d) when inserting\n",
+ old, xa_err(old));
+ kfree(item);
+ return xa_err(old);
+ }
+
+ schedule_delayed_work(&item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+
+ return 0;
+
+err_or_exists:
+ xa_unlock(&sriov->xa_rej_tmout);
+ return ret;
+}
+
+static int lookup_rej_tmout_slave(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id)
+{
+ struct rej_tmout_entry *item;
+ int slave;
+
+ xa_lock(&sriov->xa_rej_tmout);
+ item = xa_load(&sriov->xa_rej_tmout, (unsigned long)rem_pv_cm_id);
+
+ if (!item || xa_err(item)) {
+ pr_debug("Could not find slave. rem_pv_cm_id 0x%x error: %d\n",
+ rem_pv_cm_id, xa_err(item));
+ slave = !item ? -ENOENT : xa_err(item);
+ } else {
+ slave = item->slave;
+ }
+ xa_unlock(&sriov->xa_rej_tmout);
+
+ return slave;
+}
+
int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
struct ib_mad *mad)
{
+ struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
+ u32 rem_pv_cm_id = get_local_comm_id(mad);
u32 pv_cm_id;
struct id_map_entry *id;
+ int sts;
if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID ||
mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) {
@@ -347,6 +445,13 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
be64_to_cpu(gid.global.interface_id));
return -ENOENT;
}
+
+ sts = alloc_rej_tmout(sriov, rem_pv_cm_id, *slave);
+ if (sts)
+ /* Even if this fails, we pass on the REQ to the slave */
+ pr_debug("Could not allocate rej_tmout entry. rem_pv_cm_id 0x%x slave %d status %d\n",
+ rem_pv_cm_id, *slave, sts);
+
return 0;
}
@@ -354,7 +459,14 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
id = id_map_get(ibdev, (int *)&pv_cm_id, -1, -1);
if (!id) {
- pr_debug("Couldn't find an entry for pv_cm_id 0x%x\n", pv_cm_id);
+ if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID &&
+ REJ_REASON(mad) == IB_CM_REJ_TIMEOUT && slave) {
+ *slave = lookup_rej_tmout_slave(sriov, rem_pv_cm_id);
+
+ return (*slave < 0) ? *slave : 0;
+ }
+ pr_debug("Couldn't find an entry for pv_cm_id 0x%x, attr_id 0x%x\n",
+ pv_cm_id, be16_to_cpu(mad->mad_hdr.attr_id));
return -ENOENT;
}
@@ -375,6 +487,34 @@ 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;
xa_init_flags(&dev->sriov.pv_id_table, XA_FLAGS_ALLOC);
+ xa_init(&dev->sriov.xa_rej_tmout);
+}
+
+static void rej_tmout_xa_cleanup(struct mlx4_ib_sriov *sriov, int slave)
+{
+ struct rej_tmout_entry *item;
+ bool flush_needed = false;
+ unsigned long id;
+ int cnt = 0;
+
+ xa_lock(&sriov->xa_rej_tmout);
+ xa_for_each(&sriov->xa_rej_tmout, id, item) {
+ if (slave < 0 || slave == item->slave) {
+ mod_delayed_work(system_wq, &item->timeout, 0);
+ flush_needed = true;
+ ++cnt;
+ }
+ }
+ xa_unlock(&sriov->xa_rej_tmout);
+
+ if (flush_needed) {
+ flush_scheduled_work();
+ pr_debug("Deleted %d entries in xarray for slave %d during cleanup\n",
+ cnt, slave);
+ }
+
+ if (slave < 0)
+ WARN_ON(!xa_empty(&sriov->xa_rej_tmout));
}
/* slave = -1 ==> all slaves */
@@ -444,4 +584,6 @@ void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave)
list_del(&map->list);
kfree(map);
}
+
+ rej_tmout_xa_cleanup(sriov, slave);
}
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 8a3436994f80..e9b5a4d57fb1 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -149,7 +149,6 @@ static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_udata *udata,
if (IS_ERR(*umem))
return PTR_ERR(*umem);
- n = ib_umem_page_count(*umem);
shift = mlx4_ib_umem_calc_optimal_mtt_size(*umem, 0, &n);
err = mlx4_mtt_init(dev->dev, n, shift, &buf->mtt);
@@ -475,7 +474,7 @@ out:
return err;
}
-void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
+int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
{
struct mlx4_ib_dev *dev = to_mdev(cq->device);
struct mlx4_ib_cq *mcq = to_mcq(cq);
@@ -495,6 +494,7 @@ void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
mlx4_db_free(dev->dev, &mcq->db);
}
ib_umem_release(mcq->umem);
+ return 0;
}
static void dump_cqe(void *cqe)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index abe68708d6d6..8bd16474708f 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -500,6 +500,13 @@ static int get_gids_from_l3_hdr(struct ib_grh *grh, union ib_gid *sgid,
sgid, dgid);
}
+static int is_proxy_qp0(struct mlx4_ib_dev *dev, int qpn, int slave)
+{
+ int proxy_start = dev->dev->phys_caps.base_proxy_sqpn + 8 * slave;
+
+ return (qpn >= proxy_start && qpn <= proxy_start + 1);
+}
+
int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
enum ib_qp_type dest_qpt, struct ib_wc *wc,
struct ib_grh *grh, struct ib_mad *mad)
@@ -520,8 +527,10 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
u16 cached_pkey;
u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
- if (dest_qpt > IB_QPT_GSI)
+ if (dest_qpt > IB_QPT_GSI) {
+ pr_debug("dest_qpt (%d) > IB_QPT_GSI\n", dest_qpt);
return -EINVAL;
+ }
tun_ctx = dev->sriov.demux[port-1].tun[slave];
@@ -538,12 +547,20 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
if (dest_qpt) {
u16 pkey_ix;
ret = ib_get_cached_pkey(&dev->ib_dev, port, wc->pkey_index, &cached_pkey);
- if (ret)
+ if (ret) {
+ pr_debug("unable to get %s cached pkey for index %d, ret %d\n",
+ is_proxy_qp0(dev, wc->src_qp, slave) ? "SMI" : "GSI",
+ wc->pkey_index, ret);
return -EINVAL;
+ }
ret = find_slave_port_pkey_ix(dev, slave, port, cached_pkey, &pkey_ix);
- if (ret)
+ if (ret) {
+ pr_debug("unable to get %s pkey ix for pkey 0x%x, ret %d\n",
+ is_proxy_qp0(dev, wc->src_qp, slave) ? "SMI" : "GSI",
+ cached_pkey, ret);
return -EINVAL;
+ }
tun_pkey_ix = pkey_ix;
} else
tun_pkey_ix = dev->pkeys.virt2phys_pkey[slave][port - 1][0];
@@ -715,7 +732,8 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
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",
+ pr_debug("failed sending %s to slave %d via tunnel qp (%d)\n",
+ is_proxy_qp0(dev, wc->src_qp, slave) ? "SMI" : "GSI",
slave, err);
return 0;
}
@@ -794,7 +812,8 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
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",
+ pr_debug("failed sending %s to slave %d via tunnel qp (%d)\n",
+ is_proxy_qp0(dev, wc->src_qp, slave) ? "SMI" : "GSI",
slave, err);
return 0;
}
@@ -807,27 +826,6 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
int err;
struct ib_port_attr pattr;
- if (in_wc && in_wc->qp) {
- pr_debug("received MAD: port:%d slid:%d sqpn:%d "
- "dlid_bits:%d dqpn:%d wc_flags:0x%x tid:%016llx cls:%x mtd:%x atr:%x\n",
- port_num,
- in_wc->slid, in_wc->src_qp,
- in_wc->dlid_path_bits,
- in_wc->qp->qp_num,
- in_wc->wc_flags,
- be64_to_cpu(in_mad->mad_hdr.tid),
- in_mad->mad_hdr.mgmt_class, in_mad->mad_hdr.method,
- be16_to_cpu(in_mad->mad_hdr.attr_id));
- if (in_wc->wc_flags & IB_WC_GRH) {
- pr_debug("sgid_hi:0x%016llx sgid_lo:0x%016llx\n",
- be64_to_cpu(in_grh->sgid.global.subnet_prefix),
- be64_to_cpu(in_grh->sgid.global.interface_id));
- pr_debug("dgid_hi:0x%016llx dgid_lo:0x%016llx\n",
- be64_to_cpu(in_grh->dgid.global.subnet_prefix),
- be64_to_cpu(in_grh->dgid.global.interface_id));
- }
- }
-
slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
@@ -1299,6 +1297,18 @@ static void mlx4_ib_tunnel_comp_handler(struct ib_cq *cq, void *arg)
spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags);
}
+static void mlx4_ib_wire_comp_handler(struct ib_cq *cq, void *arg)
+{
+ unsigned long flags;
+ struct mlx4_ib_demux_pv_ctx *ctx = cq->cq_context;
+ struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev);
+
+ spin_lock_irqsave(&dev->sriov.going_down_lock, flags);
+ if (!dev->sriov.is_going_down && ctx->state == DEMUX_PV_STATE_ACTIVE)
+ queue_work(ctx->wi_wq, &ctx->work);
+ spin_unlock_irqrestore(&dev->sriov.going_down_lock, flags);
+}
+
static int mlx4_ib_post_pv_qp_buf(struct mlx4_ib_demux_pv_ctx *ctx,
struct mlx4_ib_demux_pv_qp *tun_qp,
int index)
@@ -1341,14 +1351,6 @@ static int mlx4_ib_multiplex_sa_handler(struct ib_device *ibdev, int port,
return ret;
}
-static int is_proxy_qp0(struct mlx4_ib_dev *dev, int qpn, int slave)
-{
- int proxy_start = dev->dev->phys_caps.base_proxy_sqpn + 8 * slave;
-
- return (qpn >= proxy_start && qpn <= proxy_start + 1);
-}
-
-
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 rdma_ah_attr *attr,
@@ -1401,10 +1403,10 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
spin_lock(&sqp->tx_lock);
if (sqp->tx_ix_head - sqp->tx_ix_tail >=
- (MLX4_NUM_TUNNEL_BUFS - 1))
+ (MLX4_NUM_WIRE_BUFS - 1))
ret = -EAGAIN;
else
- wire_tx_ix = (++sqp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1);
+ wire_tx_ix = (++sqp->tx_ix_head) & (MLX4_NUM_WIRE_BUFS - 1);
spin_unlock(&sqp->tx_lock);
if (ret)
goto out;
@@ -1484,6 +1486,7 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
u16 vlan_id;
u8 qos;
u8 *dmac;
+ int sts;
/* Get slave that sent this packet */
if (wc->src_qp < dev->dev->phys_caps.base_proxy_sqpn ||
@@ -1580,13 +1583,17 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
&vlan_id, &qos))
rdma_ah_set_sl(&ah_attr, qos);
- mlx4_ib_send_to_wire(dev, slave, ctx->port,
- is_proxy_qp0(dev, wc->src_qp, slave) ?
- IB_QPT_SMI : IB_QPT_GSI,
- be16_to_cpu(tunnel->hdr.pkey_index),
- be32_to_cpu(tunnel->hdr.remote_qpn),
- be32_to_cpu(tunnel->hdr.qkey),
- &ah_attr, wc->smac, vlan_id, &tunnel->mad);
+ sts = mlx4_ib_send_to_wire(dev, slave, ctx->port,
+ is_proxy_qp0(dev, wc->src_qp, slave) ?
+ IB_QPT_SMI : IB_QPT_GSI,
+ be16_to_cpu(tunnel->hdr.pkey_index),
+ be32_to_cpu(tunnel->hdr.remote_qpn),
+ be32_to_cpu(tunnel->hdr.qkey),
+ &ah_attr, wc->smac, vlan_id, &tunnel->mad);
+ if (sts)
+ pr_debug("failed sending %s to wire on behalf of slave %d (%d)\n",
+ is_proxy_qp0(dev, wc->src_qp, slave) ? "SMI" : "GSI",
+ slave, sts);
}
static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
@@ -1595,19 +1602,20 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
int i;
struct mlx4_ib_demux_pv_qp *tun_qp;
int rx_buf_size, tx_buf_size;
+ const int nmbr_bufs = is_tun ? MLX4_NUM_TUNNEL_BUFS : MLX4_NUM_WIRE_BUFS;
if (qp_type > IB_QPT_GSI)
return -EINVAL;
tun_qp = &ctx->qp[qp_type];
- tun_qp->ring = kcalloc(MLX4_NUM_TUNNEL_BUFS,
+ tun_qp->ring = kcalloc(nmbr_bufs,
sizeof(struct mlx4_ib_buf),
GFP_KERNEL);
if (!tun_qp->ring)
return -ENOMEM;
- tun_qp->tx_ring = kcalloc(MLX4_NUM_TUNNEL_BUFS,
+ tun_qp->tx_ring = kcalloc(nmbr_bufs,
sizeof (struct mlx4_ib_tun_tx_buf),
GFP_KERNEL);
if (!tun_qp->tx_ring) {
@@ -1624,7 +1632,7 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
tx_buf_size = sizeof (struct mlx4_mad_snd_buf);
}
- for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) {
+ for (i = 0; i < nmbr_bufs; i++) {
tun_qp->ring[i].addr = kmalloc(rx_buf_size, GFP_KERNEL);
if (!tun_qp->ring[i].addr)
goto err;
@@ -1638,7 +1646,7 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
}
}
- for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) {
+ for (i = 0; i < nmbr_bufs; i++) {
tun_qp->tx_ring[i].buf.addr =
kmalloc(tx_buf_size, GFP_KERNEL);
if (!tun_qp->tx_ring[i].buf.addr)
@@ -1669,7 +1677,7 @@ tx_err:
tx_buf_size, DMA_TO_DEVICE);
kfree(tun_qp->tx_ring[i].buf.addr);
}
- i = MLX4_NUM_TUNNEL_BUFS;
+ i = nmbr_bufs;
err:
while (i > 0) {
--i;
@@ -1690,6 +1698,7 @@ static void mlx4_ib_free_pv_qp_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
int i;
struct mlx4_ib_demux_pv_qp *tun_qp;
int rx_buf_size, tx_buf_size;
+ const int nmbr_bufs = is_tun ? MLX4_NUM_TUNNEL_BUFS : MLX4_NUM_WIRE_BUFS;
if (qp_type > IB_QPT_GSI)
return;
@@ -1704,13 +1713,13 @@ static void mlx4_ib_free_pv_qp_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
}
- for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) {
+ for (i = 0; i < nmbr_bufs; i++) {
ib_dma_unmap_single(ctx->ib_dev, tun_qp->ring[i].map,
rx_buf_size, DMA_FROM_DEVICE);
kfree(tun_qp->ring[i].addr);
}
- for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) {
+ for (i = 0; i < nmbr_bufs; i++) {
ib_dma_unmap_single(ctx->ib_dev, tun_qp->tx_ring[i].buf.map,
tx_buf_size, DMA_TO_DEVICE);
kfree(tun_qp->tx_ring[i].buf.addr);
@@ -1744,9 +1753,6 @@ static void mlx4_ib_tunnel_comp_worker(struct work_struct *work)
"buf:%lld\n", wc.wr_id);
break;
case IB_WC_SEND:
- pr_debug("received tunnel send completion:"
- "wrid=0x%llx, status=0x%x\n",
- wc.wr_id, wc.status);
rdma_destroy_ah(tun_qp->tx_ring[wc.wr_id &
(MLX4_NUM_TUNNEL_BUFS - 1)].ah, 0);
tun_qp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah
@@ -1793,6 +1799,7 @@ static int create_pv_sqp(struct mlx4_ib_demux_pv_ctx *ctx,
struct mlx4_ib_qp_tunnel_init_attr qp_init_attr;
struct ib_qp_attr attr;
int qp_attr_mask_INIT;
+ const int nmbr_bufs = create_tun ? MLX4_NUM_TUNNEL_BUFS : MLX4_NUM_WIRE_BUFS;
if (qp_type > IB_QPT_GSI)
return -EINVAL;
@@ -1803,8 +1810,8 @@ static int create_pv_sqp(struct mlx4_ib_demux_pv_ctx *ctx,
qp_init_attr.init_attr.send_cq = ctx->cq;
qp_init_attr.init_attr.recv_cq = ctx->cq;
qp_init_attr.init_attr.sq_sig_type = IB_SIGNAL_ALL_WR;
- qp_init_attr.init_attr.cap.max_send_wr = MLX4_NUM_TUNNEL_BUFS;
- qp_init_attr.init_attr.cap.max_recv_wr = MLX4_NUM_TUNNEL_BUFS;
+ qp_init_attr.init_attr.cap.max_send_wr = nmbr_bufs;
+ qp_init_attr.init_attr.cap.max_recv_wr = nmbr_bufs;
qp_init_attr.init_attr.cap.max_send_sge = 1;
qp_init_attr.init_attr.cap.max_recv_sge = 1;
if (create_tun) {
@@ -1866,7 +1873,7 @@ static int create_pv_sqp(struct mlx4_ib_demux_pv_ctx *ctx,
goto err_qp;
}
- for (i = 0; i < MLX4_NUM_TUNNEL_BUFS; i++) {
+ for (i = 0; i < nmbr_bufs; i++) {
ret = mlx4_ib_post_pv_qp_buf(ctx, tun_qp, i);
if (ret) {
pr_err(" mlx4_ib_post_pv_buf error"
@@ -1902,8 +1909,8 @@ static void mlx4_ib_sqp_comp_worker(struct work_struct *work)
switch (wc.opcode) {
case IB_WC_SEND:
kfree(sqp->tx_ring[wc.wr_id &
- (MLX4_NUM_TUNNEL_BUFS - 1)].ah);
- sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah
+ (MLX4_NUM_WIRE_BUFS - 1)].ah);
+ sqp->tx_ring[wc.wr_id & (MLX4_NUM_WIRE_BUFS - 1)].ah
= NULL;
spin_lock(&sqp->tx_lock);
sqp->tx_ix_tail++;
@@ -1912,13 +1919,13 @@ static void mlx4_ib_sqp_comp_worker(struct work_struct *work)
case IB_WC_RECV:
mad = (struct ib_mad *) &(((struct mlx4_mad_rcv_buf *)
(sqp->ring[wc.wr_id &
- (MLX4_NUM_TUNNEL_BUFS - 1)].addr))->payload);
+ (MLX4_NUM_WIRE_BUFS - 1)].addr))->payload);
grh = &(((struct mlx4_mad_rcv_buf *)
(sqp->ring[wc.wr_id &
- (MLX4_NUM_TUNNEL_BUFS - 1)].addr))->grh);
+ (MLX4_NUM_WIRE_BUFS - 1)].addr))->grh);
mlx4_ib_demux_mad(ctx->ib_dev, ctx->port, &wc, grh, mad);
if (mlx4_ib_post_pv_qp_buf(ctx, sqp, wc.wr_id &
- (MLX4_NUM_TUNNEL_BUFS - 1)))
+ (MLX4_NUM_WIRE_BUFS - 1)))
pr_err("Failed reposting SQP "
"buf:%lld\n", wc.wr_id);
break;
@@ -1931,8 +1938,8 @@ static void mlx4_ib_sqp_comp_worker(struct work_struct *work)
ctx->slave, wc.status, wc.wr_id);
if (!MLX4_TUN_IS_RECV(wc.wr_id)) {
kfree(sqp->tx_ring[wc.wr_id &
- (MLX4_NUM_TUNNEL_BUFS - 1)].ah);
- sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah
+ (MLX4_NUM_WIRE_BUFS - 1)].ah);
+ sqp->tx_ring[wc.wr_id & (MLX4_NUM_WIRE_BUFS - 1)].ah
= NULL;
spin_lock(&sqp->tx_lock);
sqp->tx_ix_tail++;
@@ -1972,6 +1979,7 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
{
int ret, cq_size;
struct ib_cq_init_attr cq_attr = {};
+ const int nmbr_bufs = create_tun ? MLX4_NUM_TUNNEL_BUFS : MLX4_NUM_WIRE_BUFS;
if (ctx->state != DEMUX_PV_STATE_DOWN)
return -EEXIST;
@@ -1996,12 +2004,13 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
goto err_out_qp0;
}
- cq_size = 2 * MLX4_NUM_TUNNEL_BUFS;
+ cq_size = 2 * nmbr_bufs;
if (ctx->has_smi)
cq_size *= 2;
cq_attr.cqe = cq_size;
- ctx->cq = ib_create_cq(ctx->ib_dev, mlx4_ib_tunnel_comp_handler,
+ ctx->cq = ib_create_cq(ctx->ib_dev,
+ create_tun ? mlx4_ib_tunnel_comp_handler : mlx4_ib_wire_comp_handler,
NULL, ctx, &cq_attr);
if (IS_ERR(ctx->cq)) {
ret = PTR_ERR(ctx->cq);
@@ -2038,6 +2047,7 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
INIT_WORK(&ctx->work, mlx4_ib_sqp_comp_worker);
ctx->wq = to_mdev(ibdev)->sriov.demux[port - 1].wq;
+ ctx->wi_wq = to_mdev(ibdev)->sriov.demux[port - 1].wi_wq;
ret = ib_req_notify_cq(ctx->cq, IB_CQ_NEXT_COMP);
if (ret) {
@@ -2181,7 +2191,7 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev,
goto err_mcg;
}
- snprintf(name, sizeof name, "mlx4_ibt%d", port);
+ snprintf(name, sizeof(name), "mlx4_ibt%d", port);
ctx->wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM);
if (!ctx->wq) {
pr_err("Failed to create tunnelling WQ for port %d\n", port);
@@ -2189,7 +2199,15 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev,
goto err_wq;
}
- snprintf(name, sizeof name, "mlx4_ibud%d", port);
+ snprintf(name, sizeof(name), "mlx4_ibwi%d", port);
+ ctx->wi_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM);
+ if (!ctx->wi_wq) {
+ pr_err("Failed to create wire WQ for port %d\n", port);
+ ret = -ENOMEM;
+ goto err_wiwq;
+ }
+
+ snprintf(name, sizeof(name), "mlx4_ibud%d", port);
ctx->ud_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM);
if (!ctx->ud_wq) {
pr_err("Failed to create up/down WQ for port %d\n", port);
@@ -2200,6 +2218,10 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev,
return 0;
err_udwq:
+ destroy_workqueue(ctx->wi_wq);
+ ctx->wi_wq = NULL;
+
+err_wiwq:
destroy_workqueue(ctx->wq);
ctx->wq = NULL;
@@ -2247,12 +2269,14 @@ static void mlx4_ib_free_demux_ctx(struct mlx4_ib_demux_ctx *ctx)
ctx->tun[i]->state = DEMUX_PV_STATE_DOWNING;
}
flush_workqueue(ctx->wq);
+ flush_workqueue(ctx->wi_wq);
for (i = 0; i < dev->dev->caps.sqp_demux; i++) {
destroy_pv_resources(dev, i, ctx->port, ctx->tun[i], 0);
free_pv_object(dev, i, ctx->port);
}
kfree(ctx->tun);
destroy_workqueue(ctx->ud_wq);
+ destroy_workqueue(ctx->wi_wq);
destroy_workqueue(ctx->wq);
}
}
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index bd4f975e7f9a..cd0fba6b0964 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1215,9 +1215,10 @@ static int mlx4_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
return 0;
}
-static void mlx4_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
+static int mlx4_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
{
mlx4_pd_free(to_mdev(pd->device)->dev, to_mpd(pd)->pdn);
+ return 0;
}
static int mlx4_ib_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata)
@@ -1256,11 +1257,12 @@ err2:
return err;
}
-static void mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
+static int mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
{
ib_destroy_cq(to_mxrcd(xrcd)->cq);
ib_dealloc_pd(to_mxrcd(xrcd)->pd);
mlx4_xrcd_free(to_mdev(xrcd->device)->dev, to_mxrcd(xrcd)->xrcdn);
+ return 0;
}
static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
@@ -1533,23 +1535,11 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
struct mlx4_net_trans_rule_hw_ctrl *ctrl;
int default_flow;
- static const u16 __mlx4_domain[] = {
- [IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS,
- [IB_FLOW_DOMAIN_ETHTOOL] = MLX4_DOMAIN_ETHTOOL,
- [IB_FLOW_DOMAIN_RFS] = MLX4_DOMAIN_RFS,
- [IB_FLOW_DOMAIN_NIC] = MLX4_DOMAIN_NIC,
- };
-
if (flow_attr->priority > MLX4_IB_FLOW_MAX_PRIO) {
pr_err("Invalid priority value %d\n", flow_attr->priority);
return -EINVAL;
}
- if (domain >= IB_FLOW_DOMAIN_NUM) {
- pr_err("Invalid domain value %d\n", domain);
- return -EINVAL;
- }
-
if (mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type) < 0)
return -EINVAL;
@@ -1558,8 +1548,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
return PTR_ERR(mailbox);
ctrl = mailbox->buf;
- ctrl->prio = cpu_to_be16(__mlx4_domain[domain] |
- flow_attr->priority);
+ ctrl->prio = cpu_to_be16(domain | flow_attr->priority);
ctrl->type = mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type);
ctrl->port = flow_attr->port;
ctrl->qpn = cpu_to_be32(qp->qp_num);
@@ -1701,8 +1690,8 @@ static int mlx4_ib_add_dont_trap_rule(struct mlx4_dev *dev,
}
static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
- struct ib_flow_attr *flow_attr,
- int domain, struct ib_udata *udata)
+ struct ib_flow_attr *flow_attr,
+ struct ib_udata *udata)
{
int err = 0, i = 0, j = 0;
struct mlx4_ib_flow *mflow;
@@ -1768,8 +1757,8 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
}
while (i < ARRAY_SIZE(type) && type[i]) {
- err = __mlx4_ib_create_flow(qp, flow_attr, domain, type[i],
- &mflow->reg_id[i].id);
+ err = __mlx4_ib_create_flow(qp, flow_attr, MLX4_DOMAIN_UVERBS,
+ type[i], &mflow->reg_id[i].id);
if (err)
goto err_create_flow;
if (is_bonded) {
@@ -1778,7 +1767,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
*/
flow_attr->port = 2;
err = __mlx4_ib_create_flow(qp, flow_attr,
- domain, type[j],
+ MLX4_DOMAIN_UVERBS, type[j],
&mflow->reg_id[j].mirror);
flow_attr->port = 1;
if (err)
@@ -2589,11 +2578,16 @@ static const struct ib_device_ops mlx4_ib_dev_wq_ops = {
.destroy_rwq_ind_table = mlx4_ib_destroy_rwq_ind_table,
.destroy_wq = mlx4_ib_destroy_wq,
.modify_wq = mlx4_ib_modify_wq,
+
+ INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mlx4_ib_rwq_ind_table,
+ ib_rwq_ind_tbl),
};
static const struct ib_device_ops mlx4_ib_dev_mw_ops = {
.alloc_mw = mlx4_ib_alloc_mw,
.dealloc_mw = mlx4_ib_dealloc_mw,
+
+ INIT_RDMA_OBJ_SIZE(ib_mw, mlx4_ib_mw, ibmw),
};
static const struct ib_device_ops mlx4_ib_dev_xrc_ops = {
@@ -2847,7 +2841,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
goto err_steer_free_bitmap;
rdma_set_device_sysfs_group(&ibdev->ib_dev, &mlx4_attr_group);
- if (ib_register_device(&ibdev->ib_dev, "mlx4_%d"))
+ if (ib_register_device(&ibdev->ib_dev, "mlx4_%d",
+ &dev->persist->pdev->dev))
goto err_diag_counters;
if (mlx4_ib_mad_init(ibdev))
@@ -2989,10 +2984,8 @@ int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
/* Add an empty rule for IB L2 */
memset(&ib_spec->mask, 0, sizeof(ib_spec->mask));
- err = __mlx4_ib_create_flow(&mqp->ibqp, flow,
- IB_FLOW_DOMAIN_NIC,
- MLX4_FS_REGULAR,
- &mqp->reg_id);
+ err = __mlx4_ib_create_flow(&mqp->ibqp, flow, MLX4_DOMAIN_NIC,
+ MLX4_FS_REGULAR, &mqp->reg_id);
} else {
err = __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
}
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 38e87a700a2a..58df06492d69 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -233,7 +233,8 @@ enum mlx4_ib_mad_ifc_flags {
};
enum {
- MLX4_NUM_TUNNEL_BUFS = 256,
+ MLX4_NUM_TUNNEL_BUFS = 512,
+ MLX4_NUM_WIRE_BUFS = 2048,
};
struct mlx4_ib_tunnel_header {
@@ -298,6 +299,26 @@ struct mlx4_ib_rss {
u8 rss_key[MLX4_EN_RSS_KEY_SIZE];
};
+enum {
+ /*
+ * Largest possible UD header: send with GRH and immediate
+ * data plus 18 bytes for an Ethernet header with VLAN/802.1Q
+ * tag. (LRH would only use 8 bytes, so Ethernet is the
+ * biggest case)
+ */
+ MLX4_IB_UD_HEADER_SIZE = 82,
+ MLX4_IB_LSO_HEADER_SPARE = 128,
+};
+
+struct mlx4_ib_sqp {
+ int pkey_index;
+ u32 qkey;
+ u32 send_psn;
+ struct ib_ud_header ud_header;
+ u8 header_buf[MLX4_IB_UD_HEADER_SIZE];
+ struct ib_qp *roce_v2_gsi;
+};
+
struct mlx4_ib_qp {
union {
struct ib_qp ibqp;
@@ -343,7 +364,10 @@ struct mlx4_ib_qp {
struct mlx4_wqn_range *wqn_range;
/* Number of RSS QP parents that uses this WQ */
u32 rss_usecnt;
- struct mlx4_ib_rss *rss_ctx;
+ union {
+ struct mlx4_ib_rss *rss_ctx;
+ struct mlx4_ib_sqp *sqp;
+ };
};
struct mlx4_ib_srq {
@@ -366,6 +390,10 @@ struct mlx4_ib_ah {
union mlx4_ext_av av;
};
+struct mlx4_ib_rwq_ind_table {
+ struct ib_rwq_ind_table ib_rwq_ind_tbl;
+};
+
/****************************************/
/* alias guid support */
/****************************************/
@@ -454,6 +482,7 @@ struct mlx4_ib_demux_pv_ctx {
struct ib_pd *pd;
struct work_struct work;
struct workqueue_struct *wq;
+ struct workqueue_struct *wi_wq;
struct mlx4_ib_demux_pv_qp qp[2];
};
@@ -461,6 +490,7 @@ struct mlx4_ib_demux_ctx {
struct ib_device *ib_dev;
int port;
struct workqueue_struct *wq;
+ struct workqueue_struct *wi_wq;
struct workqueue_struct *ud_wq;
spinlock_t ud_lock;
atomic64_t subnet_prefix;
@@ -492,6 +522,7 @@ struct mlx4_ib_sriov {
spinlock_t id_map_lock;
struct rb_root sl_id_map;
struct list_head cm_list;
+ struct xarray xa_rej_tmout;
};
struct gid_cache_context {
@@ -725,8 +756,7 @@ 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_udata *udata);
-struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
- struct ib_udata *udata);
+int mlx4_ib_alloc_mw(struct ib_mw *mw, struct ib_udata *udata);
int mlx4_ib_dealloc_mw(struct ib_mw *mw);
struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
u32 max_num_sg);
@@ -736,7 +766,7 @@ int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
struct ib_udata *udata);
-void mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
+int mlx4_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata);
int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
int mlx4_ib_arm_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags);
void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq);
@@ -747,14 +777,17 @@ int mlx4_ib_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr,
int mlx4_ib_create_ah_slave(struct ib_ah *ah, struct rdma_ah_attr *ah_attr,
int slave_sgid_index, u8 *s_mac, u16 vlan_tag);
int mlx4_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr);
-void mlx4_ib_destroy_ah(struct ib_ah *ah, u32 flags);
+static inline int mlx4_ib_destroy_ah(struct ib_ah *ah, u32 flags)
+{
+ return 0;
+}
int mlx4_ib_create_srq(struct ib_srq *srq, struct ib_srq_init_attr *init_attr,
struct ib_udata *udata);
int mlx4_ib_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr,
enum ib_srq_attr_mask attr_mask, struct ib_udata *udata);
int mlx4_ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr);
-void mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
+int mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata);
void mlx4_ib_free_srq_wqe(struct mlx4_ib_srq *srq, int wqe_index);
int mlx4_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
const struct ib_recv_wr **bad_wr);
@@ -890,15 +923,18 @@ void mlx4_ib_sl2vl_update(struct mlx4_ib_dev *mdev, int port);
struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd,
struct ib_wq_init_attr *init_attr,
struct ib_udata *udata);
-void mlx4_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
+int mlx4_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata);
int mlx4_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr,
u32 wq_attr_mask, struct ib_udata *udata);
-struct ib_rwq_ind_table
-*mlx4_ib_create_rwq_ind_table(struct ib_device *device,
- struct ib_rwq_ind_table_init_attr *init_attr,
- struct ib_udata *udata);
-int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
+int mlx4_ib_create_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl,
+ struct ib_rwq_ind_table_init_attr *init_attr,
+ struct ib_udata *udata);
+static inline int
+mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table)
+{
+ return 0;
+}
int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
int *num_of_mtts);
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 1d5ef0de12c9..426fed005d53 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -271,6 +271,8 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
u64 total_len = 0;
int i;
+ *num_of_mtts = ib_umem_num_dma_blocks(umem, PAGE_SIZE);
+
for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) {
/*
* Initialization - save the first chunk start as the
@@ -421,7 +423,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
goto err_free;
}
- n = ib_umem_page_count(mr->umem);
shift = mlx4_ib_umem_calc_optimal_mtt_size(mr->umem, start, &n);
err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, virt_addr, length,
@@ -511,7 +512,7 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
mmr->umem = NULL;
goto release_mpt_entry;
}
- n = ib_umem_page_count(mmr->umem);
+ n = ib_umem_num_dma_blocks(mmr->umem, PAGE_SIZE);
shift = PAGE_SHIFT;
err = mlx4_mr_rereg_mem_write(dev->dev, &mmr->mmr,
@@ -610,37 +611,27 @@ int mlx4_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
return 0;
}
-struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type,
- struct ib_udata *udata)
+int mlx4_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)
{
- struct mlx4_ib_dev *dev = to_mdev(pd->device);
- struct mlx4_ib_mw *mw;
+ struct mlx4_ib_dev *dev = to_mdev(ibmw->device);
+ struct mlx4_ib_mw *mw = to_mmw(ibmw);
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);
+ err = mlx4_mw_alloc(dev->dev, to_mpd(ibmw->pd)->pdn,
+ to_mlx4_type(ibmw->type), &mw->mmw);
if (err)
- goto err_free;
+ return err;
err = mlx4_mw_enable(dev->dev, &mw->mmw);
if (err)
goto err_mw;
- mw->ibmw.rkey = mw->mmw.key;
-
- return &mw->ibmw;
+ ibmw->rkey = mw->mmw.key;
+ return 0;
err_mw:
mlx4_mw_free(dev->dev, &mw->mmw);
-
-err_free:
- kfree(mw);
-
- return ERR_PTR(err);
+ return err;
}
int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
@@ -648,8 +639,6 @@ 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;
}
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 2975f350b9fd..5cb8e602294c 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -68,27 +68,6 @@ enum {
};
enum {
- /*
- * Largest possible UD header: send with GRH and immediate
- * data plus 18 bytes for an Ethernet header with VLAN/802.1Q
- * tag. (LRH would only use 8 bytes, so Ethernet is the
- * biggest case)
- */
- MLX4_IB_UD_HEADER_SIZE = 82,
- MLX4_IB_LSO_HEADER_SPARE = 128,
-};
-
-struct mlx4_ib_sqp {
- struct mlx4_ib_qp qp;
- int pkey_index;
- u32 qkey;
- u32 send_psn;
- struct ib_ud_header ud_header;
- u8 header_buf[MLX4_IB_UD_HEADER_SIZE];
- struct ib_qp *roce_v2_gsi;
-};
-
-enum {
MLX4_IB_MIN_SQ_STRIDE = 6,
MLX4_IB_CACHE_LINE_SIZE = 64,
};
@@ -123,11 +102,6 @@ enum mlx4_ib_source_type {
MLX4_IB_RWQ_SRC = 1,
};
-static struct mlx4_ib_sqp *to_msqp(struct mlx4_ib_qp *mqp)
-{
- return container_of(mqp, struct mlx4_ib_sqp, qp);
-}
-
static int is_tunnel_qp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
{
if (!mlx4_is_master(dev->dev))
@@ -656,8 +630,6 @@ static int create_qp_rss(struct mlx4_ib_dev *dev,
if (err)
goto err_qpn;
- mutex_init(&qp->mutex);
-
INIT_LIST_HEAD(&qp->gid_list);
INIT_LIST_HEAD(&qp->steering_rules);
@@ -696,80 +668,72 @@ err_qpn:
return err;
}
-static struct ib_qp *_mlx4_ib_create_qp_rss(struct ib_pd *pd,
- struct ib_qp_init_attr *init_attr,
- struct ib_udata *udata)
+static int _mlx4_ib_create_qp_rss(struct ib_pd *pd, struct mlx4_ib_qp *qp,
+ struct ib_qp_init_attr *init_attr,
+ struct ib_udata *udata)
{
- struct mlx4_ib_qp *qp;
struct mlx4_ib_create_qp_rss ucmd = {};
size_t required_cmd_sz;
int err;
if (!udata) {
pr_debug("RSS QP with NULL udata\n");
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
if (udata->outlen)
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
required_cmd_sz = offsetof(typeof(ucmd), reserved1) +
sizeof(ucmd.reserved1);
if (udata->inlen < required_cmd_sz) {
pr_debug("invalid inlen\n");
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen))) {
pr_debug("copy failed\n");
- return ERR_PTR(-EFAULT);
+ return -EFAULT;
}
if (memchr_inv(ucmd.reserved, 0, sizeof(ucmd.reserved)))
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
if (ucmd.comp_mask || ucmd.reserved1)
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
if (udata->inlen > sizeof(ucmd) &&
!ib_is_udata_cleared(udata, sizeof(ucmd),
udata->inlen - sizeof(ucmd))) {
pr_debug("inlen is not supported\n");
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
}
if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
pr_debug("RSS QP with unsupported QP type %d\n",
init_attr->qp_type);
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
}
if (init_attr->create_flags) {
pr_debug("RSS QP doesn't support create flags\n");
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
}
if (init_attr->send_cq || init_attr->cap.max_send_wr) {
pr_debug("RSS QP with unsupported send attributes\n");
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
}
- qp = kzalloc(sizeof(*qp), GFP_KERNEL);
- if (!qp)
- return ERR_PTR(-ENOMEM);
-
qp->pri.vid = 0xFFFF;
qp->alt.vid = 0xFFFF;
err = create_qp_rss(to_mdev(pd->device), init_attr, &ucmd, qp);
- if (err) {
- kfree(qp);
- return ERR_PTR(err);
- }
+ if (err)
+ return err;
qp->ibqp.qp_num = qp->mqp.qpn;
-
- return &qp->ibqp;
+ return 0;
}
/*
@@ -873,7 +837,6 @@ static int create_rq(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
qp->mlx4_ib_qp_type = MLX4_IB_QPT_RAW_PACKET;
- mutex_init(&qp->mutex);
spin_lock_init(&qp->sq.lock);
spin_lock_init(&qp->rq.lock);
INIT_LIST_HEAD(&qp->gid_list);
@@ -922,7 +885,6 @@ static int create_rq(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
goto err;
}
- n = ib_umem_page_count(qp->umem);
shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n);
err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt);
@@ -989,13 +951,11 @@ err:
static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
struct ib_udata *udata, int sqpn,
- struct mlx4_ib_qp **caller_qp)
+ struct mlx4_ib_qp *qp)
{
struct mlx4_ib_dev *dev = to_mdev(pd->device);
int qpn;
int err;
- struct mlx4_ib_sqp *sqp = NULL;
- struct mlx4_ib_qp *qp;
struct mlx4_ib_ucontext *context = rdma_udata_to_drv_context(
udata, struct mlx4_ib_ucontext, ibucontext);
enum mlx4_ib_qp_type qp_type = (enum mlx4_ib_qp_type) init_attr->qp_type;
@@ -1043,27 +1003,18 @@ static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
sqpn = qpn;
}
- if (!*caller_qp) {
- 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);
- if (!sqp)
- return -ENOMEM;
- qp = &sqp->qp;
- } else {
- qp = kzalloc(sizeof(struct mlx4_ib_qp), GFP_KERNEL);
- if (!qp)
- return -ENOMEM;
- }
- qp->pri.vid = 0xFFFF;
- qp->alt.vid = 0xFFFF;
- } else
- qp = *caller_qp;
+ if (init_attr->qp_type == IB_QPT_SMI ||
+ init_attr->qp_type == IB_QPT_GSI || 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))) {
+ qp->sqp = kzalloc(sizeof(struct mlx4_ib_sqp), GFP_KERNEL);
+ if (!qp->sqp)
+ return -ENOMEM;
+ }
qp->mlx4_ib_qp_type = qp_type;
- mutex_init(&qp->mutex);
spin_lock_init(&qp->sq.lock);
spin_lock_init(&qp->rq.lock);
INIT_LIST_HEAD(&qp->gid_list);
@@ -1117,7 +1068,6 @@ static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
goto err;
}
- n = ib_umem_page_count(qp->umem);
shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n);
err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt);
@@ -1239,9 +1189,6 @@ static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
qp->mqp.event = mlx4_ib_qp_event;
- if (!*caller_qp)
- *caller_qp = qp;
-
spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
mlx4_ib_lock_cqs(to_mcq(init_attr->send_cq),
to_mcq(init_attr->recv_cq));
@@ -1293,10 +1240,7 @@ err_db:
mlx4_db_free(dev->dev, &qp->db);
err:
- if (!sqp && !*caller_qp)
- kfree(qp);
- kfree(sqp);
-
+ kfree(qp->sqp);
return err;
}
@@ -1410,7 +1354,6 @@ static void destroy_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
mlx4_qp_free(dev->dev, &qp->mqp);
mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
del_gid_entries(qp);
- kfree(qp->rss_ctx);
}
static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
@@ -1529,17 +1472,16 @@ static u32 get_sqp_num(struct mlx4_ib_dev *dev, struct ib_qp_init_attr *attr)
return dev->dev->caps.spec_qps[attr->port_num - 1].qp1_proxy;
}
-static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
- struct ib_qp_init_attr *init_attr,
- struct ib_udata *udata)
+static int _mlx4_ib_create_qp(struct ib_pd *pd, struct mlx4_ib_qp *qp,
+ struct ib_qp_init_attr *init_attr,
+ struct ib_udata *udata)
{
- struct mlx4_ib_qp *qp = NULL;
int err;
int sup_u_create_flags = MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK;
u16 xrcdn = 0;
if (init_attr->rwq_ind_tbl)
- return _mlx4_ib_create_qp_rss(pd, init_attr, udata);
+ return _mlx4_ib_create_qp_rss(pd, qp, init_attr, udata);
/*
* We only support LSO, vendor flag1, and multicast loopback blocking,
@@ -1551,16 +1493,16 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
MLX4_IB_SRIOV_SQP |
MLX4_IB_QP_NETIF |
MLX4_IB_QP_CREATE_ROCE_V2_GSI))
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
if (init_attr->qp_type != IB_QPT_UD)
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
if (init_attr->create_flags) {
if (udata && init_attr->create_flags & ~(sup_u_create_flags))
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
if ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP |
MLX4_IB_QP_CREATE_ROCE_V2_GSI |
@@ -1570,7 +1512,7 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
init_attr->qp_type > IB_QPT_GSI) ||
(init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI &&
init_attr->qp_type != IB_QPT_GSI))
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
switch (init_attr->qp_type) {
@@ -1581,53 +1523,43 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
fallthrough;
case IB_QPT_XRC_INI:
if (!(to_mdev(pd->device)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
- return ERR_PTR(-ENOSYS);
+ return -ENOSYS;
init_attr->recv_cq = init_attr->send_cq;
fallthrough;
case IB_QPT_RC:
case IB_QPT_UC:
case IB_QPT_RAW_PACKET:
- qp = kzalloc(sizeof(*qp), GFP_KERNEL);
- if (!qp)
- return ERR_PTR(-ENOMEM);
+ case IB_QPT_UD:
qp->pri.vid = 0xFFFF;
qp->alt.vid = 0xFFFF;
- fallthrough;
- case IB_QPT_UD:
- {
- err = create_qp_common(pd, init_attr, udata, 0, &qp);
- if (err) {
- kfree(qp);
- return ERR_PTR(err);
- }
+ err = create_qp_common(pd, init_attr, udata, 0, qp);
+ if (err)
+ return err;
qp->ibqp.qp_num = qp->mqp.qpn;
qp->xrcdn = xrcdn;
-
break;
- }
case IB_QPT_SMI:
case IB_QPT_GSI:
{
int sqpn;
- /* Userspace is not allowed to create special QPs: */
- if (udata)
- return ERR_PTR(-EINVAL);
if (init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI) {
int res = mlx4_qp_reserve_range(to_mdev(pd->device)->dev,
1, 1, &sqpn, 0,
MLX4_RES_USAGE_DRIVER);
if (res)
- return ERR_PTR(res);
+ return res;
} else {
sqpn = get_sqp_num(to_mdev(pd->device), init_attr);
}
- err = create_qp_common(pd, init_attr, udata, sqpn, &qp);
+ qp->pri.vid = 0xFFFF;
+ qp->alt.vid = 0xFFFF;
+ err = create_qp_common(pd, init_attr, udata, sqpn, qp);
if (err)
- return ERR_PTR(err);
+ return err;
qp->port = init_attr->port_num;
qp->ibqp.qp_num = init_attr->qp_type == IB_QPT_SMI ? 0 :
@@ -1636,25 +1568,33 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
}
default:
/* Don't support raw QPs */
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
}
-
- return &qp->ibqp;
+ return 0;
}
struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
struct ib_qp_init_attr *init_attr,
struct ib_udata *udata) {
struct ib_device *device = pd ? pd->device : init_attr->xrcd->device;
- struct ib_qp *ibqp;
struct mlx4_ib_dev *dev = to_mdev(device);
+ struct mlx4_ib_qp *qp;
+ int ret;
- ibqp = _mlx4_ib_create_qp(pd, init_attr, udata);
+ qp = kzalloc(sizeof(*qp), GFP_KERNEL);
+ if (!qp)
+ return ERR_PTR(-ENOMEM);
- if (!IS_ERR(ibqp) &&
- (init_attr->qp_type == IB_QPT_GSI) &&
+ mutex_init(&qp->mutex);
+ ret = _mlx4_ib_create_qp(pd, qp, init_attr, udata);
+ if (ret) {
+ kfree(qp);
+ return ERR_PTR(ret);
+ }
+
+ if (init_attr->qp_type == IB_QPT_GSI &&
!(init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI)) {
- struct mlx4_ib_sqp *sqp = to_msqp((to_mqp(ibqp)));
+ struct mlx4_ib_sqp *sqp = qp->sqp;
int is_eth = rdma_cap_eth_ah(&dev->ib_dev, init_attr->port_num);
if (is_eth &&
@@ -1666,14 +1606,14 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
pr_err("Failed to create GSI QP for RoCEv2 (%ld)\n", PTR_ERR(sqp->roce_v2_gsi));
sqp->roce_v2_gsi = NULL;
} else {
- sqp = to_msqp(to_mqp(sqp->roce_v2_gsi));
- sqp->qp.flags |= MLX4_IB_ROCE_V2_GSI_QP;
+ to_mqp(sqp->roce_v2_gsi)->flags |=
+ MLX4_IB_ROCE_V2_GSI_QP;
}
init_attr->create_flags &= ~MLX4_IB_QP_CREATE_ROCE_V2_GSI;
}
}
- return ibqp;
+ return &qp->ibqp;
}
static int _mlx4_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata)
@@ -1700,10 +1640,8 @@ static int _mlx4_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata)
destroy_qp_common(dev, mqp, MLX4_IB_QP_SRC, udata);
}
- if (is_sqp(dev, mqp))
- kfree(to_msqp(mqp));
- else
- kfree(mqp);
+ kfree(mqp->sqp);
+ kfree(mqp);
return 0;
}
@@ -1713,7 +1651,7 @@ int mlx4_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata)
struct mlx4_ib_qp *mqp = to_mqp(qp);
if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
- struct mlx4_ib_sqp *sqp = to_msqp(mqp);
+ struct mlx4_ib_sqp *sqp = mqp->sqp;
if (sqp->roce_v2_gsi)
ib_destroy_qp(sqp->roce_v2_gsi);
@@ -2575,7 +2513,7 @@ static int __mlx4_ib_modify_qp(void *src, enum mlx4_ib_source_type src_type,
qp->alt_port = attr->alt_port_num;
if (is_sqp(dev, qp))
- store_sqp_attrs(to_msqp(qp), attr, attr_mask);
+ store_sqp_attrs(qp->sqp, attr, attr_mask);
/*
* If we moved QP0 to RTR, bring the IB link up; if we moved
@@ -2852,7 +2790,7 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
ret = _mlx4_ib_modify_qp(ibqp, attr, attr_mask, udata);
if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
- struct mlx4_ib_sqp *sqp = to_msqp(mqp);
+ struct mlx4_ib_sqp *sqp = mqp->sqp;
int err = 0;
if (sqp->roce_v2_gsi)
@@ -2877,12 +2815,13 @@ static int vf_get_qp0_qkey(struct mlx4_dev *dev, int qpn, u32 *qkey)
return -EINVAL;
}
-static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
+static int build_sriov_qp0_header(struct mlx4_ib_qp *qp,
const struct ib_ud_wr *wr,
void *wqe, unsigned *mlx_seg_len)
{
- struct mlx4_ib_dev *mdev = to_mdev(sqp->qp.ibqp.device);
- struct ib_device *ib_dev = &mdev->ib_dev;
+ struct mlx4_ib_dev *mdev = to_mdev(qp->ibqp.device);
+ struct mlx4_ib_sqp *sqp = qp->sqp;
+ struct ib_device *ib_dev = qp->ibqp.device;
struct mlx4_wqe_mlx_seg *mlx = wqe;
struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
struct mlx4_ib_ah *ah = to_mah(wr->ah);
@@ -2904,12 +2843,12 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
/* for proxy-qp0 sends, need to add in size of tunnel header */
/* for tunnel-qp0 sends, tunnel header is already in s/g list */
- if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER)
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER)
send_size += sizeof (struct mlx4_ib_tunnel_header);
ib_ud_header_init(send_size, 1, 0, 0, 0, 0, 0, 0, &sqp->ud_header);
- if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER) {
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER) {
sqp->ud_header.lrh.service_level =
be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28;
sqp->ud_header.lrh.destination_lid =
@@ -2926,26 +2865,26 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
sqp->ud_header.lrh.virtual_lane = 0;
sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
- err = ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey);
+ err = ib_get_cached_pkey(ib_dev, qp->port, 0, &pkey);
if (err)
return err;
sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
- if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_TUN_SMI_OWNER)
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_SMI_OWNER)
sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
else
sqp->ud_header.bth.destination_qpn =
- cpu_to_be32(mdev->dev->caps.spec_qps[sqp->qp.port - 1].qp0_tunnel);
+ cpu_to_be32(mdev->dev->caps.spec_qps[qp->port - 1].qp0_tunnel);
sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
if (mlx4_is_master(mdev->dev)) {
- if (mlx4_get_parav_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
+ if (mlx4_get_parav_qkey(mdev->dev, qp->mqp.qpn, &qkey))
return -EINVAL;
} else {
- if (vf_get_qp0_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
+ if (vf_get_qp0_qkey(mdev->dev, 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);
+ sqp->ud_header.deth.source_qpn = cpu_to_be32(qp->mqp.qpn);
sqp->ud_header.bth.opcode = IB_OPCODE_UD_SEND_ONLY;
sqp->ud_header.immediate_present = 0;
@@ -3029,10 +2968,11 @@ static int fill_gid_by_hw_index(struct mlx4_ib_dev *ibdev, u8 port_num,
}
#define MLX4_ROCEV2_QP1_SPORT 0xC000
-static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
+static int build_mlx_header(struct mlx4_ib_qp *qp, const struct ib_ud_wr *wr,
void *wqe, unsigned *mlx_seg_len)
{
- struct ib_device *ib_dev = sqp->qp.ibqp.device;
+ struct mlx4_ib_sqp *sqp = qp->sqp;
+ struct ib_device *ib_dev = qp->ibqp.device;
struct mlx4_ib_dev *ibdev = to_mdev(ib_dev);
struct mlx4_wqe_mlx_seg *mlx = wqe;
struct mlx4_wqe_ctrl_seg *ctrl = wqe;
@@ -3056,7 +2996,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
for (i = 0; i < wr->wr.num_sge; ++i)
send_size += wr->wr.sg_list[i].length;
- is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET;
+ is_eth = rdma_port_get_link_layer(qp->ibqp.device, qp->port) == IB_LINK_LAYER_ETHERNET;
is_grh = mlx4_ib_ah_grh_present(ah);
if (is_eth) {
enum ib_gid_type gid_type;
@@ -3070,9 +3010,9 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
if (err)
return err;
} else {
- err = fill_gid_by_hw_index(ibdev, sqp->qp.port,
- ah->av.ib.gid_index,
- &sgid, &gid_type);
+ err = fill_gid_by_hw_index(ibdev, qp->port,
+ ah->av.ib.gid_index, &sgid,
+ &gid_type);
if (!err) {
is_udp = gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP;
if (is_udp) {
@@ -3117,13 +3057,18 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
* indexes don't necessarily match the hw ones, so
* we must use our own cache
*/
- sqp->ud_header.grh.source_gid.global.subnet_prefix =
- cpu_to_be64(atomic64_read(&(to_mdev(ib_dev)->sriov.
- demux[sqp->qp.port - 1].
- subnet_prefix)));
- sqp->ud_header.grh.source_gid.global.interface_id =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- guid_cache[ah->av.ib.gid_index];
+ sqp->ud_header.grh.source_gid.global
+ .subnet_prefix =
+ cpu_to_be64(atomic64_read(
+ &(to_mdev(ib_dev)
+ ->sriov
+ .demux[qp->port - 1]
+ .subnet_prefix)));
+ sqp->ud_header.grh.source_gid.global
+ .interface_id =
+ to_mdev(ib_dev)
+ ->sriov.demux[qp->port - 1]
+ .guid_cache[ah->av.ib.gid_index];
} else {
sqp->ud_header.grh.source_gid =
ah->ibah.sgid_attr->gid;
@@ -3155,10 +3100,13 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
mlx->flags &= cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE);
if (!is_eth) {
- mlx->flags |= cpu_to_be32((!sqp->qp.ibqp.qp_num ? MLX4_WQE_MLX_VL15 : 0) |
- (sqp->ud_header.lrh.destination_lid ==
- IB_LID_PERMISSIVE ? MLX4_WQE_MLX_SLR : 0) |
- (sqp->ud_header.lrh.service_level << 8));
+ mlx->flags |=
+ cpu_to_be32((!qp->ibqp.qp_num ? MLX4_WQE_MLX_VL15 : 0) |
+ (sqp->ud_header.lrh.destination_lid ==
+ IB_LID_PERMISSIVE ?
+ MLX4_WQE_MLX_SLR :
+ 0) |
+ (sqp->ud_header.lrh.service_level << 8));
if (ah->av.ib.port_pd & cpu_to_be32(0x80000000))
mlx->flags |= cpu_to_be32(0x1); /* force loopback */
mlx->rlid = sqp->ud_header.lrh.destination_lid;
@@ -3204,21 +3152,23 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
sqp->ud_header.vlan.tag = cpu_to_be16(vlan | pcp);
}
} else {
- sqp->ud_header.lrh.virtual_lane = !sqp->qp.ibqp.qp_num ? 15 :
- sl_to_vl(to_mdev(ib_dev),
- sqp->ud_header.lrh.service_level,
- sqp->qp.port);
- if (sqp->qp.ibqp.qp_num && sqp->ud_header.lrh.virtual_lane == 15)
+ sqp->ud_header.lrh.virtual_lane =
+ !qp->ibqp.qp_num ?
+ 15 :
+ sl_to_vl(to_mdev(ib_dev),
+ sqp->ud_header.lrh.service_level,
+ qp->port);
+ if (qp->ibqp.qp_num && sqp->ud_header.lrh.virtual_lane == 15)
return -EINVAL;
if (sqp->ud_header.lrh.destination_lid == IB_LID_PERMISSIVE)
sqp->ud_header.lrh.source_lid = IB_LID_PERMISSIVE;
}
sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
- if (!sqp->qp.ibqp.qp_num)
- err = ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index,
+ if (!qp->ibqp.qp_num)
+ err = ib_get_cached_pkey(ib_dev, qp->port, sqp->pkey_index,
&pkey);
else
- err = ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index,
+ err = ib_get_cached_pkey(ib_dev, qp->port, wr->pkey_index,
&pkey);
if (err)
return err;
@@ -3228,7 +3178,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
sqp->ud_header.deth.qkey = cpu_to_be32(wr->remote_qkey & 0x80000000 ?
sqp->qkey : wr->remote_qkey);
- sqp->ud_header.deth.source_qpn = cpu_to_be32(sqp->qp.ibqp.qp_num);
+ sqp->ud_header.deth.source_qpn = cpu_to_be32(qp->ibqp.qp_num);
header_size = ib_ud_header_pack(&sqp->ud_header, sqp->header_buf);
@@ -3551,14 +3501,14 @@ static int _mlx4_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
- struct mlx4_ib_sqp *sqp = to_msqp(qp);
+ struct mlx4_ib_sqp *sqp = qp->sqp;
if (sqp->roce_v2_gsi) {
struct mlx4_ib_ah *ah = to_mah(ud_wr(wr)->ah);
enum ib_gid_type gid_type;
union ib_gid gid;
- if (!fill_gid_by_hw_index(mdev, sqp->qp.port,
+ if (!fill_gid_by_hw_index(mdev, qp->port,
ah->av.ib.gid_index,
&gid, &gid_type))
qp = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ?
@@ -3678,8 +3628,8 @@ static int _mlx4_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
break;
case MLX4_IB_QPT_TUN_SMI_OWNER:
- err = build_sriov_qp0_header(to_msqp(qp), ud_wr(wr),
- ctrl, &seglen);
+ err = build_sriov_qp0_header(qp, ud_wr(wr), ctrl,
+ &seglen);
if (unlikely(err)) {
*bad_wr = wr;
goto out;
@@ -3715,8 +3665,8 @@ static int _mlx4_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
break;
case MLX4_IB_QPT_PROXY_SMI_OWNER:
- err = build_sriov_qp0_header(to_msqp(qp), ud_wr(wr),
- ctrl, &seglen);
+ err = build_sriov_qp0_header(qp, ud_wr(wr), ctrl,
+ &seglen);
if (unlikely(err)) {
*bad_wr = wr;
goto out;
@@ -3749,8 +3699,7 @@ static int _mlx4_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
case MLX4_IB_QPT_SMI:
case MLX4_IB_QPT_GSI:
- err = build_mlx_header(to_msqp(qp), ud_wr(wr), ctrl,
- &seglen);
+ err = build_mlx_header(qp, ud_wr(wr), ctrl, &seglen);
if (unlikely(err)) {
*bad_wr = wr;
goto out;
@@ -4172,6 +4121,7 @@ struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd,
if (!qp)
return ERR_PTR(-ENOMEM);
+ mutex_init(&qp->mutex);
qp->pri.vid = 0xFFFF;
qp->alt.vid = 0xFFFF;
@@ -4327,7 +4277,7 @@ int mlx4_ib_modify_wq(struct ib_wq *ibwq, struct ib_wq_attr *wq_attr,
return err;
}
-void mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
+int mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
{
struct mlx4_ib_dev *dev = to_mdev(ibwq->device);
struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
@@ -4338,36 +4288,35 @@ void mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
destroy_qp_common(dev, qp, MLX4_IB_RWQ_SRC, udata);
kfree(qp);
+ return 0;
}
-struct ib_rwq_ind_table
-*mlx4_ib_create_rwq_ind_table(struct ib_device *device,
- struct ib_rwq_ind_table_init_attr *init_attr,
- struct ib_udata *udata)
+int mlx4_ib_create_rwq_ind_table(struct ib_rwq_ind_table *rwq_ind_table,
+ struct ib_rwq_ind_table_init_attr *init_attr,
+ struct ib_udata *udata)
{
- struct ib_rwq_ind_table *rwq_ind_table;
struct mlx4_ib_create_rwq_ind_tbl_resp resp = {};
unsigned int ind_tbl_size = 1 << init_attr->log_ind_tbl_size;
+ struct ib_device *device = rwq_ind_table->device;
unsigned int base_wqn;
size_t min_resp_len;
- int i;
- int err;
+ int i, err = 0;
if (udata->inlen > 0 &&
!ib_is_udata_cleared(udata, 0,
udata->inlen))
- return ERR_PTR(-EOPNOTSUPP);
+ return -EOPNOTSUPP;
min_resp_len = offsetof(typeof(resp), reserved) + sizeof(resp.reserved);
if (udata->outlen && udata->outlen < min_resp_len)
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
if (ind_tbl_size >
device->attrs.rss_caps.max_rwq_indirection_table_size) {
pr_debug("log_ind_tbl_size = %d is bigger than supported = %d\n",
ind_tbl_size,
device->attrs.rss_caps.max_rwq_indirection_table_size);
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
base_wqn = init_attr->ind_tbl[0]->wq_num;
@@ -4375,39 +4324,23 @@ struct ib_rwq_ind_table
if (base_wqn % ind_tbl_size) {
pr_debug("WQN=0x%x isn't aligned with indirection table size\n",
base_wqn);
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
for (i = 1; i < ind_tbl_size; i++) {
if (++base_wqn != init_attr->ind_tbl[i]->wq_num) {
pr_debug("indirection table's WQNs aren't consecutive\n");
- return ERR_PTR(-EINVAL);
+ return -EINVAL;
}
}
- rwq_ind_table = kzalloc(sizeof(*rwq_ind_table), GFP_KERNEL);
- if (!rwq_ind_table)
- return ERR_PTR(-ENOMEM);
-
if (udata->outlen) {
resp.response_length = offsetof(typeof(resp), response_length) +
sizeof(resp.response_length);
err = ib_copy_to_udata(udata, &resp, resp.response_length);
- if (err)
- goto err;
}
- return rwq_ind_table;
-
-err:
- kfree(rwq_ind_table);
- return ERR_PTR(err);
-}
-
-int mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *ib_rwq_ind_tbl)
-{
- kfree(ib_rwq_ind_tbl);
- return 0;
+ return err;
}
struct mlx4_ib_drain_cqe {
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 8f9d5035142d..bf618529e734 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -115,8 +115,9 @@ int mlx4_ib_create_srq(struct ib_srq *ib_srq,
if (IS_ERR(srq->umem))
return PTR_ERR(srq->umem);
- err = mlx4_mtt_init(dev->dev, ib_umem_page_count(srq->umem),
- PAGE_SHIFT, &srq->mtt);
+ err = mlx4_mtt_init(
+ dev->dev, ib_umem_num_dma_blocks(srq->umem, PAGE_SIZE),
+ PAGE_SHIFT, &srq->mtt);
if (err)
goto err_buf;
@@ -260,7 +261,7 @@ int mlx4_ib_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr)
return 0;
}
-void mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
+int mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
{
struct mlx4_ib_dev *dev = to_mdev(srq->device);
struct mlx4_ib_srq *msrq = to_msrq(srq);
@@ -282,6 +283,7 @@ void mlx4_ib_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
mlx4_db_free(dev->dev, &msrq->db);
}
ib_umem_release(msrq->umem);
+ return 0;
}
void mlx4_ib_free_srq_wqe(struct mlx4_ib_srq *srq, int wqe_index)