diff options
Diffstat (limited to 'drivers/infiniband/hw/mlx4')
| -rw-r--r-- | drivers/infiniband/hw/mlx4/alias_GUID.c | 7 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/cq.c | 13 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/mad.c | 105 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/main.c | 236 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/mlx4_ib.h | 37 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/qp.c | 7 |
6 files changed, 267 insertions, 138 deletions
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c index 0f00204d2..21cb41a60 100644 --- a/drivers/infiniband/hw/mlx4/alias_GUID.c +++ b/drivers/infiniband/hw/mlx4/alias_GUID.c @@ -189,7 +189,7 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, { int i; u64 guid_indexes; - int slave_id; + int slave_id, slave_port; enum slave_port_state new_state; enum slave_port_state prev_state; __be64 tmp_cur_ag, form_cache_ag; @@ -217,6 +217,11 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, slave_id = (block_num * NUM_ALIAS_GUID_IN_REC) + i ; if (slave_id >= dev->dev->persist->num_vfs + 1) return; + + slave_port = mlx4_phys_to_slave_port(dev->dev, slave_id, port_num); + if (slave_port < 0) /* this port isn't available for the VF */ + continue; + tmp_cur_ag = *(__be64 *)&p_data[i * GUID_REC_SIZE]; form_cache_ag = get_cached_alias_guid(dev, port_num, (NUM_ALIAS_GUID_IN_REC * block_num) + i); diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 0176caa57..36eb3d012 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -166,10 +166,14 @@ err_buf: return err; } -struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector, +#define CQ_CREATE_FLAGS_SUPPORTED IB_CQ_FLAGS_TIMESTAMP_COMPLETION +struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, + const struct ib_cq_init_attr *attr, struct ib_ucontext *context, struct ib_udata *udata) { + int entries = attr->cqe; + int vector = attr->comp_vector; struct mlx4_ib_dev *dev = to_mdev(ibdev); struct mlx4_ib_cq *cq; struct mlx4_uar *uar; @@ -178,6 +182,9 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector if (entries < 1 || entries > dev->dev->caps.max_cqes) return ERR_PTR(-EINVAL); + if (attr->flags & ~CQ_CREATE_FLAGS_SUPPORTED) + return ERR_PTR(-EINVAL); + cq = kmalloc(sizeof *cq, GFP_KERNEL); if (!cq) return ERR_PTR(-ENOMEM); @@ -188,6 +195,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector spin_lock_init(&cq->lock); cq->resize_buf = NULL; cq->resize_umem = NULL; + cq->create_flags = attr->flags; INIT_LIST_HEAD(&cq->send_qp_list); INIT_LIST_HEAD(&cq->recv_qp_list); @@ -231,7 +239,8 @@ 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, 0); + cq->db.dma, &cq->mcq, vector, 0, + !!(cq->create_flags & IB_CQ_FLAGS_TIMESTAMP_COMPLETION)); if (err) goto err_dbmap; diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 9cd2b002d..68b3dfa92 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -64,14 +64,6 @@ enum { #define GUID_TBL_BLK_NUM_ENTRIES 8 #define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES) -/* Counters should be saturate once they reach their maximum value */ -#define ASSIGN_32BIT_COUNTER(counter, value) do {\ - if ((value) > U32_MAX) \ - counter = cpu_to_be32(U32_MAX); \ - else \ - counter = cpu_to_be32(value); \ -} while (0) - struct mlx4_mad_rcv_buf { struct ib_grh grh; u8 payload[256]; @@ -111,8 +103,9 @@ __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx) } int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags, - int port, struct ib_wc *in_wc, struct ib_grh *in_grh, - void *in_mad, void *response_mad) + int port, const struct ib_wc *in_wc, + const struct ib_grh *in_grh, + const void *in_mad, void *response_mad) { struct mlx4_cmd_mailbox *inmailbox, *outmailbox; void *inbox; @@ -220,7 +213,7 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl) * Snoop SM MADs for port info, GUID info, and P_Key table sets, so we can * synthesize LID change, Client-Rereg, GID change, and P_Key change events. */ -static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, +static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad *mad, u16 prev_lid) { struct ib_port_info *pinfo; @@ -356,7 +349,7 @@ static void node_desc_override(struct ib_device *dev, } } -static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *mad) +static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, const struct ib_mad *mad) { int qpn = mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED; struct ib_mad_send_buf *send_buf; @@ -366,7 +359,8 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma if (agent) { send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR, - IB_MGMT_MAD_DATA, GFP_ATOMIC); + IB_MGMT_MAD_DATA, GFP_ATOMIC, + IB_MGMT_BASE_VERSION); if (IS_ERR(send_buf)) return; /* @@ -722,8 +716,8 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port, } static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, - struct ib_wc *in_wc, struct ib_grh *in_grh, - struct ib_mad *in_mad, struct ib_mad *out_mad) + const struct ib_wc *in_wc, const struct ib_grh *in_grh, + const struct ib_mad *in_mad, struct ib_mad *out_mad) { u16 slid, prev_lid = 0; int err; @@ -825,34 +819,28 @@ static void edit_counter(struct mlx4_counter *cnt, } static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, - struct ib_wc *in_wc, struct ib_grh *in_grh, - struct ib_mad *in_mad, struct ib_mad *out_mad) + const struct ib_wc *in_wc, const struct ib_grh *in_grh, + const struct ib_mad *in_mad, struct ib_mad *out_mad) { - struct mlx4_cmd_mailbox *mailbox; + struct mlx4_counter counter_stats; struct mlx4_ib_dev *dev = to_mdev(ibdev); int err; - u32 inmod = dev->counters[port_num - 1] & 0xffff; - u8 mode; if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT) return -EINVAL; - mailbox = mlx4_alloc_cmd_mailbox(dev->dev); - if (IS_ERR(mailbox)) - return IB_MAD_RESULT_FAILURE; - - err = mlx4_cmd_box(dev->dev, 0, mailbox->dma, inmod, 0, - MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C, - MLX4_CMD_WRAPPED); + memset(&counter_stats, 0, sizeof(counter_stats)); + err = mlx4_get_counter_stats(dev->dev, + dev->counters[port_num - 1].index, + &counter_stats, 0); if (err) err = IB_MAD_RESULT_FAILURE; else { memset(out_mad->data, 0, sizeof out_mad->data); - mode = ((struct mlx4_counter *)mailbox->buf)->counter_mode; - switch (mode & 0xf) { + switch (counter_stats.counter_mode & 0xf) { case 0: - edit_counter(mailbox->buf, - (void *)(out_mad->data + 40)); + edit_counter(&counter_stats, + (void *)(out_mad->data + 40)); err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; break; default: @@ -860,25 +848,43 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, } } - mlx4_free_cmd_mailbox(dev->dev, mailbox); - return err; } int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, - struct ib_wc *in_wc, struct ib_grh *in_grh, - struct ib_mad *in_mad, struct ib_mad *out_mad) + const struct ib_wc *in_wc, const struct ib_grh *in_grh, + const struct ib_mad_hdr *in, size_t in_mad_size, + struct ib_mad_hdr *out, size_t *out_mad_size, + u16 *out_mad_pkey_index) { - switch (rdma_port_get_link_layer(ibdev, port_num)) { - case IB_LINK_LAYER_INFINIBAND: + struct mlx4_ib_dev *dev = to_mdev(ibdev); + const struct ib_mad *in_mad = (const struct ib_mad *)in; + struct ib_mad *out_mad = (struct ib_mad *)out; + enum rdma_link_layer link = rdma_port_get_link_layer(ibdev, port_num); + + if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) || + *out_mad_size != sizeof(*out_mad))) + return IB_MAD_RESULT_FAILURE; + + /* iboe_process_mad() which uses the HCA flow-counters to implement IB PMA + * queries, should be called only by VFs and for that specific purpose + */ + if (link == IB_LINK_LAYER_INFINIBAND) { + if (mlx4_is_slave(dev->dev) && + in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT && + in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS) + return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, + in_grh, in_mad, out_mad); + return ib_process_mad(ibdev, mad_flags, port_num, in_wc, in_grh, in_mad, out_mad); - case IB_LINK_LAYER_ETHERNET: - return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, - in_grh, in_mad, out_mad); - default: - return -EINVAL; } + + if (link == IB_LINK_LAYER_ETHERNET) + return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, + in_grh, in_mad, out_mad); + + return -EINVAL; } static void send_handler(struct ib_mad_agent *agent, @@ -1365,14 +1371,17 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc * stadard address handle by decoding the tunnelled mlx4_ah fields */ memcpy(&ah.av, &tunnel->hdr.av, sizeof (struct mlx4_av)); ah.ibah.device = ctx->ib_dev; + + port = be32_to_cpu(ah.av.ib.port_pd) >> 24; + port = mlx4_slave_convert_port(dev->dev, slave, port); + if (port < 0) + return; + ah.av.ib.port_pd = cpu_to_be32(port << 24 | (be32_to_cpu(ah.av.ib.port_pd) & 0xffffff)); + mlx4_ib_query_ah(&ah.ibah, &ah_attr); 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 */ @@ -1773,6 +1782,7 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port, int create_tun, struct mlx4_ib_demux_pv_ctx *ctx) { int ret, cq_size; + struct ib_cq_init_attr cq_attr = {}; if (ctx->state != DEMUX_PV_STATE_DOWN) return -EEXIST; @@ -1801,8 +1811,9 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port, 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, - NULL, ctx, cq_size, 0); + NULL, ctx, &cq_attr); if (IS_ERR(ctx->cq)) { ret = PTR_ERR(ctx->cq); pr_err("Couldn't create tunnel CQ (%d)\n", ret); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index cc64400d4..8be6db816 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -132,14 +132,35 @@ static int num_ib_ports(struct mlx4_dev *dev) } static int mlx4_ib_query_device(struct ib_device *ibdev, - struct ib_device_attr *props) + struct ib_device_attr *props, + struct ib_udata *uhw) { struct mlx4_ib_dev *dev = to_mdev(ibdev); struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; int err = -ENOMEM; int have_ib_ports; + struct mlx4_uverbs_ex_query_device cmd; + struct mlx4_uverbs_ex_query_device_resp resp = {.comp_mask = 0}; + struct mlx4_clock_params clock_params; + if (uhw->inlen) { + if (uhw->inlen < sizeof(cmd)) + return -EINVAL; + + err = ib_copy_from_udata(&cmd, uhw, sizeof(cmd)); + if (err) + return err; + + if (cmd.comp_mask) + return -EINVAL; + + if (cmd.reserved) + return -EINVAL; + } + + resp.response_length = offsetof(typeof(resp), response_length) + + sizeof(resp.response_length); in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); if (!in_mad || !out_mad) @@ -229,7 +250,25 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->max_total_mcast_qp_attach = props->max_mcast_qp_attach * props->max_mcast_grp; props->max_map_per_fmr = dev->dev->caps.max_fmr_maps; + props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL; + props->timestamp_mask = 0xFFFFFFFFFFFFULL; + if (!mlx4_is_slave(dev->dev)) + err = mlx4_get_internal_clock_params(dev->dev, &clock_params); + + if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) { + resp.response_length += sizeof(resp.hca_core_clock_offset); + if (!err && !mlx4_is_slave(dev->dev)) { + resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP; + resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE; + } + } + + if (uhw->outlen) { + err = ib_copy_to_udata(uhw, &resp, resp.response_length); + if (err) + goto out; + } out: kfree(in_mad); kfree(out_mad); @@ -712,8 +751,24 @@ static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) dev->dev->caps.num_uars, PAGE_SIZE, vma->vm_page_prot)) return -EAGAIN; - } else + } else if (vma->vm_pgoff == 3) { + struct mlx4_clock_params params; + int ret = mlx4_get_internal_clock_params(dev->dev, ¶ms); + + if (ret) + return ret; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + if (io_remap_pfn_range(vma, vma->vm_start, + (pci_resource_start(dev->dev->persist->pdev, + params.bar) + + params.offset) + >> PAGE_SHIFT, + PAGE_SIZE, vma->vm_page_prot)) + return -EAGAIN; + } else { return -EINVAL; + } return 0; } @@ -758,6 +813,7 @@ static struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev, struct ib_udata *udata) { struct mlx4_ib_xrcd *xrcd; + struct ib_cq_init_attr cq_attr = {}; int err; if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC)) @@ -777,7 +833,8 @@ static struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev, goto err2; } - xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, 1, 0); + cq_attr.cqe = 1; + xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, &cq_attr); if (IS_ERR(xrcd->cq)) { err = PTR_ERR(xrcd->cq); goto err3; @@ -1090,7 +1147,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att 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); + MLX4_CMD_WRAPPED); if (ret == -ENOMEM) pr_err("mcg table is full. Fail to register network rule.\n"); else if (ret == -ENXIO) @@ -1107,7 +1164,7 @@ 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); + MLX4_CMD_WRAPPED); if (err) pr_err("Fail to detach network rule. registration id = 0x%llx\n", reg_id); @@ -1185,7 +1242,6 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, &mflow->reg_id[i].id); if (err) goto err_create_flow; - i++; if (is_bonded) { /* Application always sees one port so the mirror rule * must be on port #2 @@ -1200,6 +1256,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, j++; } + i++; } if (i < ARRAY_SIZE(type) && flow_attr->type == IB_FLOW_ATTR_NORMAL) { @@ -1207,7 +1264,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, &mflow->reg_id[i].id); if (err) goto err_create_flow; - i++; + if (is_bonded) { flow_attr->port = 2; err = mlx4_ib_tunnel_steer_add(qp, flow_attr, @@ -1218,6 +1275,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, j++; } /* function to create mirror rule */ + i++; } return &mflow->ibflow; @@ -2041,77 +2099,75 @@ 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[80]; - int eq_per_port = 0; - int added_eqs = 0; - int total_eqs = 0; - int i, j, eq; + int i, j, eq = 0, total_eqs = 0; - /* Legacy mode or comp_pool is not large enough */ - if (dev->caps.comp_pool == 0 || - dev->caps.num_ports > dev->caps.comp_pool) - return; - - eq_per_port = dev->caps.comp_pool / dev->caps.num_ports; - - /* Init eq table */ - added_eqs = 0; - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) - added_eqs += eq_per_port; - - total_eqs = dev->caps.num_comp_vectors + added_eqs; - - ibdev->eq_table = kzalloc(total_eqs * sizeof(int), GFP_KERNEL); + ibdev->eq_table = kcalloc(dev->caps.num_comp_vectors, + sizeof(ibdev->eq_table[0]), GFP_KERNEL); if (!ibdev->eq_table) return; - ibdev->eq_added = added_eqs; - - eq = 0; - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) { - for (j = 0; j < eq_per_port; j++) { - snprintf(name, sizeof(name), "mlx4-ib-%d-%d@%s", - i, j, dev->persist->pdev->bus->name); - /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(dev, name, NULL, - &ibdev->eq_table[eq])) { - /* Use legacy (same as mlx4_en driver) */ - pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq); - ibdev->eq_table[eq] = - (eq % dev->caps.num_comp_vectors); - } - eq++; + for (i = 1; i <= dev->caps.num_ports; i++) { + for (j = 0; j < mlx4_get_eqs_per_port(dev, i); + j++, total_eqs++) { + if (i > 1 && mlx4_is_eq_shared(dev, total_eqs)) + continue; + ibdev->eq_table[eq] = total_eqs; + if (!mlx4_assign_eq(dev, i, + &ibdev->eq_table[eq])) + eq++; + else + ibdev->eq_table[eq] = -1; } } - /* Fill the reset of the vector with legacy EQ */ - for (i = 0, eq = added_eqs; i < dev->caps.num_comp_vectors; i++) - ibdev->eq_table[eq++] = i; + for (i = eq; i < dev->caps.num_comp_vectors; + ibdev->eq_table[i++] = -1) + ; /* Advertise the new number of EQs to clients */ - ibdev->ib_dev.num_comp_vectors = total_eqs; + ibdev->ib_dev.num_comp_vectors = eq; } static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) { int i; + int total_eqs = ibdev->ib_dev.num_comp_vectors; - /* no additional eqs were added */ + /* no eqs were allocated */ if (!ibdev->eq_table) return; /* Reset the advertised EQ number */ - ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors; + ibdev->ib_dev.num_comp_vectors = 0; - /* Free only the added eqs */ - for (i = 0; i < ibdev->eq_added; i++) { - /* Don't free legacy eqs if used */ - if (ibdev->eq_table[i] <= dev->caps.num_comp_vectors) - continue; + for (i = 0; i < total_eqs; i++) mlx4_release_eq(dev, ibdev->eq_table[i]); - } kfree(ibdev->eq_table); + ibdev->eq_table = NULL; +} + +static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num, + struct ib_port_immutable *immutable) +{ + struct ib_port_attr attr; + int err; + + err = mlx4_ib_query_port(ibdev, port_num, &attr); + if (err) + return err; + + immutable->pkey_tbl_len = attr.pkey_tbl_len; + immutable->gid_tbl_len = attr.gid_tbl_len; + + if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND) + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB; + else + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE; + + immutable->max_mad_size = IB_MGMT_MAD_SIZE; + + return 0; } static void *mlx4_ib_add(struct mlx4_dev *dev) @@ -2123,6 +2179,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) struct mlx4_ib_iboe *iboe; int ib_num_ports = 0; int num_req_counters; + int allocated; + u32 counter_index; pr_info_once("%s", mlx4_ib_version); @@ -2241,6 +2299,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.attach_mcast = mlx4_ib_mcg_attach; ibdev->ib_dev.detach_mcast = mlx4_ib_mcg_detach; ibdev->ib_dev.process_mad = mlx4_ib_process_mad; + ibdev->ib_dev.get_port_immutable = mlx4_port_immutable; if (!mlx4_is_slave(ibdev->dev)) { ibdev->ib_dev.alloc_fmr = mlx4_ib_fmr_alloc; @@ -2278,6 +2337,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW); } + ibdev->ib_dev.uverbs_ex_cmd_mask |= + (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) | + (1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ); + mlx4_ib_alloc_eqs(dev, ibdev); spin_lock_init(&iboe->lock); @@ -2288,19 +2351,31 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) num_req_counters = mlx4_is_bonded(dev) ? 1 : ibdev->num_ports; for (i = 0; i < num_req_counters; ++i) { mutex_init(&ibdev->qp1_proxy_lock[i]); + allocated = 0; if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) == IB_LINK_LAYER_ETHERNET) { - err = mlx4_counter_alloc(ibdev->dev, &ibdev->counters[i]); + err = mlx4_counter_alloc(ibdev->dev, &counter_index); + /* if failed to allocate a new counter, use default */ if (err) - ibdev->counters[i] = -1; - } else { - ibdev->counters[i] = -1; + counter_index = + mlx4_get_default_counter_index(dev, + i + 1); + else + allocated = 1; + } else { /* IB_LINK_LAYER_INFINIBAND use the default counter */ + counter_index = mlx4_get_default_counter_index(dev, + i + 1); } + ibdev->counters[i].index = counter_index; + ibdev->counters[i].allocated = allocated; + pr_info("counter index %d for port %d allocated %d\n", + counter_index, i + 1, allocated); } if (mlx4_is_bonded(dev)) - for (i = 1; i < ibdev->num_ports ; ++i) - ibdev->counters[i] = ibdev->counters[0]; - + for (i = 1; i < ibdev->num_ports ; ++i) { + ibdev->counters[i].index = ibdev->counters[0].index; + ibdev->counters[i].allocated = 0; + } mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) ib_num_ports++; @@ -2440,10 +2515,12 @@ err_steer_qp_release: mlx4_qp_release_range(dev, ibdev->steer_qpn_base, ibdev->steer_qpn_count); err_counter: - for (; i; --i) - if (ibdev->counters[i - 1] != -1) - mlx4_counter_free(ibdev->dev, ibdev->counters[i - 1]); - + for (i = 0; i < ibdev->num_ports; ++i) { + if (ibdev->counters[i].index != -1 && + ibdev->counters[i].allocated) + mlx4_counter_free(ibdev->dev, + ibdev->counters[i].index); + } err_map: iounmap(ibdev->uar_map); @@ -2560,8 +2637,9 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) iounmap(ibdev->uar_map); for (p = 0; p < ibdev->num_ports; ++p) - if (ibdev->counters[p] != -1) - mlx4_counter_free(ibdev->dev, ibdev->counters[p]); + if (ibdev->counters[p].index != -1 && + ibdev->counters[p].allocated) + mlx4_counter_free(ibdev->dev, ibdev->counters[p].index); mlx4_foreach_port(p, dev, MLX4_PORT_TYPE_IB) mlx4_CLOSE_PORT(dev, p); @@ -2592,31 +2670,33 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init) dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC); if (!dm) { pr_err("failed to allocate memory for tunneling qp update\n"); - goto out; + return; } 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"); - for (i = 0; i < dev->caps.num_ports; i++) { - if (dm[i]) - kfree(dm[i]); - } + while (--i >= 0) + kfree(dm[i]); goto out; } - } - /* initialize or tear down tunnel QPs for the slave */ - for (i = 0; i < ports; i++) { INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work); dm[i]->port = first_port + i + 1; dm[i]->slave = slave; dm[i]->do_init = do_init; dm[i]->dev = ibdev; - spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags); - if (!ibdev->sriov.is_going_down) + } + /* initialize or tear down tunnel QPs for the slave */ + spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags); + if (!ibdev->sriov.is_going_down) { + for (i = 0; i < ports; i++) queue_work(ibdev->sriov.demux[i].ud_wq, &dm[i]->work); spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags); + } else { + spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags); + for (i = 0; i < ports; i++) + kfree(dm[i]); } out: kfree(dm); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index fce393437..334387f63 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -110,6 +110,7 @@ struct mlx4_ib_cq { struct mutex resize_mutex; struct ib_umem *umem; struct ib_umem *resize_umem; + int create_flags; /* List of qps that it serves.*/ struct list_head send_qp_list; struct list_head recv_qp_list; @@ -503,6 +504,11 @@ struct mlx4_ib_iov_port { struct mlx4_ib_iov_sysfs_attr mcg_dentry; }; +struct counter_index { + u32 index; + u8 allocated; +}; + struct mlx4_ib_dev { struct ib_device ib_dev; struct mlx4_dev *dev; @@ -521,9 +527,8 @@ struct mlx4_ib_dev { struct mutex cap_mask_mutex; bool ib_active; struct mlx4_ib_iboe iboe; - int counters[MLX4_MAX_PORTS]; + struct counter_index counters[MLX4_MAX_PORTS]; int *eq_table; - int eq_added; struct kobject *iov_parent; struct kobject *ports_parent; struct kobject *dev_ports_parent[MLX4_MFUNC_MAX]; @@ -555,6 +560,21 @@ struct mlx4_ib_qp_tunnel_init_attr { u8 port; }; +struct mlx4_uverbs_ex_query_device { + __u32 comp_mask; + __u32 reserved; +}; + +enum query_device_resp_mask { + QUERY_DEVICE_RESP_MASK_TIMESTAMP = 1UL << 0, +}; + +struct mlx4_uverbs_ex_query_device_resp { + __u32 comp_mask; + __u32 response_length; + __u64 hca_core_clock_offset; +}; + static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev) { return container_of(ibdev, struct mlx4_ib_dev, ib_dev); @@ -668,7 +688,8 @@ void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list); 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); -struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector, +struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, + const struct ib_cq_init_attr *attr, struct ib_ucontext *context, struct ib_udata *udata); int mlx4_ib_destroy_cq(struct ib_cq *cq); @@ -706,11 +727,13 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr, struct ib_recv_wr **bad_wr); int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags, - int port, struct ib_wc *in_wc, struct ib_grh *in_grh, - void *in_mad, void *response_mad); + int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh, + const void *in_mad, void *response_mad); int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, - struct ib_wc *in_wc, struct ib_grh *in_grh, - struct ib_mad *in_mad, struct ib_mad *out_mad); + const struct ib_wc *in_wc, const struct ib_grh *in_grh, + const struct ib_mad_hdr *in, size_t in_mad_size, + struct ib_mad_hdr *out, size_t *out_mad_size, + u16 *out_mad_pkey_index); int mlx4_ib_mad_init(struct mlx4_ib_dev *dev); void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 02fc91c68..c5a3a5f0d 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1539,12 +1539,13 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) { - if (dev->counters[qp->port - 1] != -1) { + if (dev->counters[qp->port - 1].index != -1) { context->pri_path.counter_index = - dev->counters[qp->port - 1]; + dev->counters[qp->port - 1].index; optpar |= MLX4_QP_OPTPAR_COUNTER_INDEX; } else - context->pri_path.counter_index = 0xff; + context->pri_path.counter_index = + MLX4_SINK_COUNTER_INDEX(dev->dev); if (qp->flags & MLX4_IB_QP_NETIF) { mlx4_ib_steer_qp_reg(dev, qp, 1); |