diff options
Diffstat (limited to 'drivers/infiniband/hw/mlx4')
| -rw-r--r-- | drivers/infiniband/hw/mlx4/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/ah.c | 16 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/alias_GUID.c | 21 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/cm.c | 171 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/cq.c | 16 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/doorbell.c | 3 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/mad.c | 207 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/main.c | 355 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/mcg.c | 84 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/mlx4_ib.h | 126 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/mr.c | 156 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/qp.c | 398 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/srq.c | 13 | ||||
| -rw-r--r-- | drivers/infiniband/hw/mlx4/sysfs.c | 70 |
14 files changed, 810 insertions, 828 deletions
diff --git a/drivers/infiniband/hw/mlx4/Kconfig b/drivers/infiniband/hw/mlx4/Kconfig index cc7c42fe6499..f30ce9dd080a 100644 --- a/drivers/infiniband/hw/mlx4/Kconfig +++ b/drivers/infiniband/hw/mlx4/Kconfig @@ -4,7 +4,7 @@ config MLX4_INFINIBAND depends on NETDEVICES && ETHERNET && PCI && INET select NET_VENDOR_MELLANOX select MLX4_CORE - ---help--- + help This driver provides low-level InfiniBand support for Mellanox ConnectX PCI Express host channel adapters (HCAs). This is required to use InfiniBand protocols such as diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c index 02a169f8027b..7321d6ab5fe1 100644 --- a/drivers/infiniband/hw/mlx4/ah.c +++ b/drivers/infiniband/hw/mlx4/ah.c @@ -141,10 +141,11 @@ static int create_iboe_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr) return 0; } -int mlx4_ib_create_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr, - u32 flags, struct ib_udata *udata) - +int mlx4_ib_create_ah(struct ib_ah *ib_ah, struct rdma_ah_init_attr *init_attr, + struct ib_udata *udata) { + struct rdma_ah_attr *ah_attr = init_attr->ah_attr; + if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) { if (!(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH)) return -EINVAL; @@ -167,12 +168,14 @@ 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) { struct rdma_ah_attr slave_attr = *ah_attr; + struct rdma_ah_init_attr init_attr = {}; struct mlx4_ib_ah *mah = to_mah(ah); int ret; slave_attr.grh.sgid_attr = NULL; slave_attr.grh.sgid_index = slave_sgid_index; - ret = mlx4_ib_create_ah(ah, &slave_attr, 0, NULL); + init_attr.ah_attr = &slave_attr; + ret = mlx4_ib_create_ah(ah, &init_attr, NULL); if (ret) return ret; @@ -229,8 +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/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c index cca414ecfcd5..111fa88a3be4 100644 --- a/drivers/infiniband/hw/mlx4/alias_GUID.c +++ b/drivers/infiniband/hw/mlx4/alias_GUID.c @@ -38,7 +38,6 @@ #include <rdma/ib_sa.h> #include <rdma/ib_pack.h> #include <linux/mlx4/cmd.h> -#include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> #include <rdma/ib_user_verbs.h> @@ -73,12 +72,12 @@ static int get_low_record_time_index(struct mlx4_ib_dev *dev, u8 port, int *resched_delay_sec); void mlx4_ib_update_cache_on_guid_change(struct mlx4_ib_dev *dev, int block_num, - u8 port_num, u8 *p_data) + u32 port_num, u8 *p_data) { int i; u64 guid_indexes; int slave_id; - int port_index = port_num - 1; + u32 port_index = port_num - 1; if (!mlx4_is_master(dev->dev)) return; @@ -86,7 +85,7 @@ void mlx4_ib_update_cache_on_guid_change(struct mlx4_ib_dev *dev, int block_num, guid_indexes = be64_to_cpu((__force __be64) dev->sriov.alias_guid. ports_guid[port_num - 1]. all_rec_per_port[block_num].guid_indexes); - pr_debug("port: %d, guid_indexes: 0x%llx\n", port_num, guid_indexes); + pr_debug("port: %u, guid_indexes: 0x%llx\n", port_num, guid_indexes); for (i = 0; i < NUM_ALIAS_GUID_IN_REC; i++) { /* The location of the specific index starts from bit number 4 @@ -184,7 +183,7 @@ unlock: * port_number - 1 or 2 */ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, - int block_num, u8 port_num, + int block_num, u32 port_num, u8 *p_data) { int i; @@ -206,7 +205,7 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, guid_indexes = be64_to_cpu((__force __be64) dev->sriov.alias_guid. ports_guid[port_num - 1]. all_rec_per_port[block_num].guid_indexes); - pr_debug("port: %d, guid_indexes: 0x%llx\n", port_num, guid_indexes); + pr_debug("port: %u, guid_indexes: 0x%llx\n", port_num, guid_indexes); /*calculate the slaves and notify them*/ for (i = 0; i < NUM_ALIAS_GUID_IN_REC; i++) { @@ -260,11 +259,11 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, new_state = set_and_calc_slave_port_state(dev->dev, slave_id, port_num, MLX4_PORT_STATE_IB_PORT_STATE_EVENT_GID_VALID, &gen_event); - pr_debug("slave: %d, port: %d prev_port_state: %d," + pr_debug("slave: %d, port: %u prev_port_state: %d," " new_port_state: %d, gen_event: %d\n", slave_id, port_num, prev_state, new_state, gen_event); if (gen_event == SLAVE_PORT_GEN_EVENT_UP) { - pr_debug("sending PORT_UP event to slave: %d, port: %d\n", + pr_debug("sending PORT_UP event to slave: %d, port: %u\n", slave_id, port_num); mlx4_gen_port_state_change_eqe(dev->dev, slave_id, port_num, MLX4_PORT_CHANGE_SUBTYPE_ACTIVE); @@ -274,7 +273,7 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, MLX4_PORT_STATE_IB_EVENT_GID_INVALID, &gen_event); if (gen_event == SLAVE_PORT_GEN_EVENT_DOWN) { - pr_debug("sending PORT DOWN event to slave: %d, port: %d\n", + pr_debug("sending PORT DOWN event to slave: %d, port: %u\n", slave_id, port_num); mlx4_gen_port_state_change_eqe(dev->dev, slave_id, @@ -822,10 +821,8 @@ void mlx4_ib_destroy_alias_guid_service(struct mlx4_ib_dev *dev) } spin_unlock_irqrestore(&sriov->alias_guid.ag_work_lock, flags); } - for (i = 0 ; i < dev->num_ports; i++) { - flush_workqueue(dev->sriov.alias_guid.ports_guid[i].wq); + for (i = 0 ; i < dev->num_ports; i++) destroy_workqueue(dev->sriov.alias_guid.ports_guid[i].wq); - } ib_sa_unregister_client(dev->sriov.alias_guid.sa_client); kfree(dev->sriov.alias_guid.sa_client); } diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c index b591861934b3..12b481d138cf 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 { @@ -71,6 +80,7 @@ struct cm_req_msg { union ib_gid primary_path_sgid; }; +static struct workqueue_struct *cm_wq; static void set_local_comm_id(struct ib_mad *mad, u32 cm_id) { @@ -279,12 +289,16 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id) /*make sure that there is no schedule inside the scheduled work.*/ if (!sriov->is_going_down && !id->scheduled_delete) { id->scheduled_delete = 1; - schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT); + queue_delayed_work(cm_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT); + } else if (id->scheduled_delete) { + /* Adjust timeout if already scheduled */ + mod_delayed_work(cm_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 +307,10 @@ 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 +330,8 @@ 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 +343,94 @@ 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(cm_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); + } + + queue_delayed_work(cm_wq, &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 +446,13 @@ 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 +460,14 @@ 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 +488,34 @@ 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(cm_wq, &item->timeout, 0); + flush_needed = true; + ++cnt; + } + } + xa_unlock(&sriov->xa_rej_tmout); + + if (flush_needed) { + flush_workqueue(cm_wq); + 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 */ @@ -400,7 +541,7 @@ void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave) spin_unlock(&sriov->id_map_lock); if (need_flush) - flush_scheduled_work(); /* make sure all timers were flushed */ + flush_workqueue(cm_wq); /* make sure all timers were flushed */ /* now, remove all leftover entries from databases*/ spin_lock(&sriov->id_map_lock); @@ -444,4 +585,20 @@ 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); +} + +int mlx4_ib_cm_init(void) +{ + cm_wq = alloc_workqueue("mlx4_ib_cm", 0, 0); + if (!cm_wq) + return -ENOMEM; + + return 0; +} + +void mlx4_ib_cm_destroy(void) +{ + destroy_workqueue(cm_wq); } diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index f8b936b76dcd..4cd738aae53c 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -135,7 +135,7 @@ static void mlx4_ib_free_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf * mlx4_buf_free(dev->dev, (cqe + 1) * buf->entry_size, &buf->buf); } -static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_udata *udata, +static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *buf, struct ib_umem **umem, u64 buf_addr, int cqe) { @@ -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); @@ -211,7 +210,7 @@ int mlx4_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, } buf_addr = (void *)(unsigned long)ucmd.buf_addr; - err = mlx4_ib_get_cq_umem(dev, udata, &cq->buf, &cq->umem, + err = mlx4_ib_get_cq_umem(dev, &cq->buf, &cq->umem, ucmd.buf_addr, entries); if (err) goto err_cq; @@ -328,8 +327,8 @@ static int mlx4_alloc_resize_umem(struct mlx4_ib_dev *dev, struct mlx4_ib_cq *cq if (!cq->resize_buf) return -ENOMEM; - err = mlx4_ib_get_cq_umem(dev, udata, &cq->resize_buf->buf, - &cq->resize_umem, ucmd.buf_addr, entries); + err = mlx4_ib_get_cq_umem(dev, &cq->resize_buf->buf, &cq->resize_umem, + ucmd.buf_addr, entries); if (err) { kfree(cq->resize_buf); cq->resize_buf = NULL; @@ -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) @@ -765,13 +765,13 @@ repoll: switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) { case MLX4_OPCODE_RDMA_WRITE_IMM: wc->wc_flags |= IB_WC_WITH_IMM; - /* fall through */ + fallthrough; case MLX4_OPCODE_RDMA_WRITE: wc->opcode = IB_WC_RDMA_WRITE; break; case MLX4_OPCODE_SEND_IMM: wc->wc_flags |= IB_WC_WITH_IMM; - /* fall through */ + fallthrough; case MLX4_OPCODE_SEND: case MLX4_OPCODE_SEND_INVAL: wc->opcode = IB_WC_SEND; diff --git a/drivers/infiniband/hw/mlx4/doorbell.c b/drivers/infiniband/hw/mlx4/doorbell.c index d41f03ccb0e1..9bbd695a9fd5 100644 --- a/drivers/infiniband/hw/mlx4/doorbell.c +++ b/drivers/infiniband/hw/mlx4/doorbell.c @@ -75,7 +75,8 @@ int mlx4_ib_db_map_user(struct ib_udata *udata, unsigned long virt, list_add(&page->list, &context->db_page_list); found: - db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK); + db->dma = sg_dma_address(page->umem->sgt_append.sgt.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 abe68708d6d6..a37cfac5e23f 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -88,15 +88,15 @@ struct mlx4_rcv_tunnel_mad { struct ib_mad mad; } __packed; -static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num); -static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num); +static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u32 port_num); +static void handle_lid_change_event(struct mlx4_ib_dev *dev, u32 port_num); static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num, int block, u32 change_bitmap); __be64 mlx4_ib_gen_node_guid(void) { #define NODE_GUID_HI ((u64) (((u64)IB_OPENIB_OUI) << 40)) - return cpu_to_be64(NODE_GUID_HI | prandom_u32()); + return cpu_to_be64(NODE_GUID_HI | get_random_u32()); } __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx) @@ -186,7 +186,7 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags, return err; } -static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl) +static void update_sm_ah(struct mlx4_ib_dev *dev, u32 port_num, u16 lid, u8 sl) { struct ib_ah *new_ah; struct rdma_ah_attr ah_attr; @@ -217,8 +217,8 @@ 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, const struct ib_mad *mad, - u16 prev_lid) +static void smp_snoop(struct ib_device *ibdev, u32 port_num, + const struct ib_mad *mad, u16 prev_lid) { struct ib_port_info *pinfo; u16 lid; @@ -274,7 +274,7 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad be16_to_cpu(base[i]); } } - pr_debug("PKEY Change event: port=%d, " + pr_debug("PKEY Change event: port=%u, " "block=0x%x, change_bitmap=0x%x\n", port_num, bn, pkey_change_bitmap); @@ -380,7 +380,8 @@ static void node_desc_override(struct ib_device *dev, } } -static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, const struct ib_mad *mad) +static void forward_trap(struct mlx4_ib_dev *dev, u32 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; @@ -429,7 +430,7 @@ static int mlx4_ib_demux_sa_handler(struct ib_device *ibdev, int port, int slave return ret; } -int mlx4_ib_find_real_gid(struct ib_device *ibdev, u8 port, __be64 guid) +int mlx4_ib_find_real_gid(struct ib_device *ibdev, u32 port, __be64 guid) { struct mlx4_ib_dev *dev = to_mdev(ibdev); int i; @@ -443,7 +444,7 @@ int mlx4_ib_find_real_gid(struct ib_device *ibdev, u8 port, __be64 guid) static int find_slave_port_pkey_ix(struct mlx4_ib_dev *dev, int slave, - u8 port, u16 pkey, u16 *ix) + u32 port, u16 pkey, u16 *ix) { int i, ret; u8 unassigned_pkey_ix, pkey_ix, partial_ix = 0xFF; @@ -500,7 +501,14 @@ static int get_gids_from_l3_hdr(struct ib_grh *grh, union ib_gid *sgid, sgid, dgid); } -int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, +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, u32 port, enum ib_qp_type dest_qpt, struct ib_wc *wc, struct ib_grh *grh, struct ib_mad *mad) { @@ -520,8 +528,10 @@ 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 +548,20 @@ 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]; @@ -661,7 +679,7 @@ end: return ret; } -static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port, +static int mlx4_ib_demux_mad(struct ib_device *ibdev, u32 port, struct ib_wc *wc, struct ib_grh *grh, struct ib_mad *mad) { @@ -715,7 +733,8 @@ 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; } @@ -794,12 +813,13 @@ 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; } -static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, +static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in_mad, struct ib_mad *out_mad) { @@ -807,27 +827,6 @@ 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) { @@ -934,9 +933,10 @@ static int iboe_process_mad_port_info(void *out_mad) return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; } -static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, - const struct ib_wc *in_wc, const struct ib_grh *in_grh, - const struct ib_mad *in_mad, struct ib_mad *out_mad) +static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, + u32 port_num, 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_counter counter_stats; struct mlx4_ib_dev *dev = to_mdev(ibdev); @@ -981,7 +981,7 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, return err; } -int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, +int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in, struct ib_mad *out, size_t *out_mad_size, u16 *out_mad_pkey_index) @@ -1075,7 +1075,7 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev) } } -static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num) +static void handle_lid_change_event(struct mlx4_ib_dev *dev, u32 port_num) { mlx4_ib_dispatch_event(dev, port_num, IB_EVENT_LID_CHANGE); @@ -1084,7 +1084,7 @@ static void handle_lid_change_event(struct mlx4_ib_dev *dev, u8 port_num) MLX4_EQ_PORT_INFO_LID_CHANGE_MASK); } -static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u8 port_num) +static void handle_client_rereg_event(struct mlx4_ib_dev *dev, u32 port_num) { /* re-configure the alias-guid and mcg's */ if (mlx4_is_master(dev->dev)) { @@ -1123,7 +1123,7 @@ static void propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num, GET_MASK_FROM_EQE(eqe)); } -static void handle_slaves_guid_change(struct mlx4_ib_dev *dev, u8 port_num, +static void handle_slaves_guid_change(struct mlx4_ib_dev *dev, u32 port_num, u32 guid_tbl_blk_num, u32 change_bitmap) { struct ib_smp *in_mad = NULL; @@ -1179,7 +1179,7 @@ void handle_port_mgmt_change_event(struct work_struct *work) struct ib_event_work *ew = container_of(work, struct ib_event_work, work); struct mlx4_ib_dev *dev = ew->ib_dev; struct mlx4_eqe *eqe = &(ew->ib_eqe); - u8 port = eqe->event.port_mgmt_change.port; + u32 port = eqe->event.port_mgmt_change.port; u32 changed_attr; u32 tbl_block; u32 change_bitmap; @@ -1276,7 +1276,7 @@ void handle_port_mgmt_change_event(struct work_struct *work) kfree(ew); } -void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num, +void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u32 port_num, enum ib_event_type type) { struct ib_event event; @@ -1299,6 +1299,18 @@ 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) @@ -1341,15 +1353,7 @@ 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, +int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u32 port, enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn, u32 qkey, struct rdma_ah_attr *attr, u8 *s_mac, u16 vlan_id, struct ib_mad *mad) @@ -1401,10 +1405,10 @@ 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 +1488,7 @@ 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 || @@ -1520,6 +1525,7 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc return; } else *slave_id = slave; + break; default: /* nothing */; } @@ -1580,13 +1586,17 @@ 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 +1605,20 @@ 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 +1635,7 @@ 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 +1649,7 @@ 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 +1680,7 @@ 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 +1701,7 @@ 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 +1716,13 @@ 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 +1756,6 @@ 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 +1802,7 @@ 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 +1813,8 @@ 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 +1876,7 @@ 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 +1912,8 @@ 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 +1922,13 @@ 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 +1941,8 @@ 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 +1982,7 @@ 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 +2007,13 @@ 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 +2050,7 @@ 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 +2194,7 @@ 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 +2202,15 @@ 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 +2221,10 @@ 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 +2272,14 @@ 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 2f5d9b181848..ba47874f90d3 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -81,18 +81,10 @@ static const char mlx4_ib_version[] = static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init); static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device, - u8 port_num); + u32 port_num); static struct workqueue_struct *wq; -static void init_query_mad(struct ib_smp *mad) -{ - mad->base_version = 1; - mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; - mad->class_version = 1; - mad->method = IB_MGMT_METHOD_GET; -} - static int check_flow_steering_support(struct mlx4_dev *dev) { int eth_num_ports = 0; @@ -129,7 +121,8 @@ static int num_ib_ports(struct mlx4_dev *dev) return ib_ports; } -static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_num) +static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, + u32 port_num) { struct mlx4_ib_dev *ibdev = to_mdev(device); struct net_device *dev; @@ -160,7 +153,7 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_n static int mlx4_ib_update_gids_v1(struct gid_entry *gids, struct mlx4_ib_dev *ibdev, - u8 port_num) + u32 port_num) { struct mlx4_cmd_mailbox *mailbox; int err; @@ -193,7 +186,7 @@ static int mlx4_ib_update_gids_v1(struct gid_entry *gids, static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids, struct mlx4_ib_dev *ibdev, - u8 port_num) + u32 port_num) { struct mlx4_cmd_mailbox *mailbox; int err; @@ -238,7 +231,7 @@ static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids, static int mlx4_ib_update_gids(struct gid_entry *gids, struct mlx4_ib_dev *ibdev, - u8 port_num) + u32 port_num) { if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2) return mlx4_ib_update_gids_v1_v2(gids, ibdev, port_num); @@ -407,7 +400,7 @@ int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev, int real_index = -EINVAL; int i; unsigned long flags; - u8 port_num = attr->port_num; + u32 port_num = attr->port_num; if (port_num > MLX4_MAX_PORTS) return -EINVAL; @@ -434,9 +427,6 @@ int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev, return real_index; } -#define field_avail(type, fld, sz) (offsetof(type, fld) + \ - sizeof(((type *)0)->fld) <= (sz)) - static int mlx4_ib_query_device(struct ib_device *ibdev, struct ib_device_attr *props, struct ib_udata *uhw) @@ -447,7 +437,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, int err; int have_ib_ports; struct mlx4_uverbs_ex_query_device cmd; - struct mlx4_uverbs_ex_query_device_resp resp = {.comp_mask = 0}; + struct mlx4_uverbs_ex_query_device_resp resp = {}; struct mlx4_clock_params clock_params; if (uhw->inlen) { @@ -473,7 +463,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, if (!in_mad || !out_mad) goto out; - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_NODE_INFO; err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS, @@ -489,8 +479,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->device_cap_flags = IB_DEVICE_CHANGE_PHY_PORT | IB_DEVICE_PORT_ACTIVE_EVENT | IB_DEVICE_SYS_IMAGE_GUID | - IB_DEVICE_RC_RNR_NAK_GEN | - IB_DEVICE_BLOCK_MULTICAST_LOOPBACK; + IB_DEVICE_RC_RNR_NAK_GEN; + props->kernel_cap_flags = IBK_BLOCK_MULTICAST_LOOPBACK; if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR) props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR; if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR) @@ -504,9 +494,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, if (dev->dev->caps.max_gso_sz && (dev->dev->rev_id != MLX4_IB_CARD_REV_A0) && (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BLH)) - props->device_cap_flags |= IB_DEVICE_UD_TSO; + props->kernel_cap_flags |= IBK_UD_TSO; if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_RESERVED_LKEY) - props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY; + props->kernel_cap_flags |= IBK_LOCAL_DMA_LKEY; if ((dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_LOCAL_INV) && (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_REMOTE_INV) && (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_FAST_REG_WR)) @@ -561,7 +551,6 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->max_mcast_qp_attach = dev->dev->caps.num_qp_per_mgm; props->max_total_mcast_qp_attach = props->max_mcast_qp_attach * props->max_mcast_grp; - props->max_map_per_fmr = dev->dev->caps.max_fmr_maps; props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL; props->timestamp_mask = 0xFFFFFFFFFFFFULL; props->max_ah = INT_MAX; @@ -584,12 +573,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT; props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD; - 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)) { + if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) { resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET; resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE; } @@ -602,7 +588,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, sizeof(struct mlx4_wqe_data_seg); } - if (field_avail(typeof(resp), rss_caps, uhw->outlen)) { + if (offsetofend(typeof(resp), rss_caps) <= uhw->outlen) { if (props->rss_caps.supported_qpts) { resp.rss_caps.rx_hash_function = MLX4_IB_RX_HASH_FUNC_TOEPLITZ; @@ -626,7 +612,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, sizeof(resp.rss_caps); } - if (field_avail(typeof(resp), tso_caps, uhw->outlen)) { + if (offsetofend(typeof(resp), tso_caps) <= uhw->outlen) { if (dev->dev->caps.max_gso_sz && ((mlx4_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET) || @@ -653,7 +639,7 @@ out: } static enum rdma_link_layer -mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num) +mlx4_ib_port_link_layer(struct ib_device *device, u32 port_num) { struct mlx4_dev *dev = to_mdev(device)->dev; @@ -661,7 +647,7 @@ mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num) IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET; } -static int ib_link_query_port(struct ib_device *ibdev, u8 port, +static int ib_link_query_port(struct ib_device *ibdev, u32 port, struct ib_port_attr *props, int netw_view) { struct ib_smp *in_mad = NULL; @@ -675,7 +661,7 @@ static int ib_link_query_port(struct ib_device *ibdev, u8 port, if (!in_mad || !out_mad) goto out; - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; in_mad->attr_mod = cpu_to_be32(port); @@ -727,7 +713,7 @@ static int ib_link_query_port(struct ib_device *ibdev, u8 port, /* If reported active speed is QDR, check if is FDR-10 */ if (props->active_speed == IB_SPEED_QDR) { - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = MLX4_ATTR_EXTENDED_PORT_INFO; in_mad->attr_mod = cpu_to_be32(port); @@ -757,7 +743,7 @@ static u8 state_to_phys_state(enum ib_port_state state) IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED; } -static int eth_link_query_port(struct ib_device *ibdev, u8 port, +static int eth_link_query_port(struct ib_device *ibdev, u32 port, struct ib_port_attr *props) { @@ -788,7 +774,8 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, props->ip_gids = true; props->gid_tbl_len = mdev->dev->caps.gid_table_len[port]; props->max_msg_sz = mdev->dev->caps.max_msg_sz; - props->pkey_tbl_len = 1; + if (mdev->dev->caps.pkey_table_len[port]) + props->pkey_tbl_len = 1; props->max_mtu = IB_MTU_4096; props->max_vl_num = 2; props->state = IB_PORT_DOWN; @@ -817,7 +804,7 @@ out: return err; } -int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port, +int __mlx4_ib_query_port(struct ib_device *ibdev, u32 port, struct ib_port_attr *props, int netw_view) { int err; @@ -831,14 +818,14 @@ int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port, return err; } -static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port, +static int mlx4_ib_query_port(struct ib_device *ibdev, u32 port, struct ib_port_attr *props) { /* returns host view */ return __mlx4_ib_query_port(ibdev, port, props, 0); } -int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, +int __mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index, union ib_gid *gid, int netw_view) { struct ib_smp *in_mad = NULL; @@ -853,7 +840,7 @@ int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, if (!in_mad || !out_mad) goto out; - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; in_mad->attr_mod = cpu_to_be32(port); @@ -875,7 +862,7 @@ int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, } } - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_GUID_INFO; in_mad->attr_mod = cpu_to_be32(index / 8); @@ -894,7 +881,7 @@ out: return err; } -static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, +static int mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index, union ib_gid *gid) { if (rdma_protocol_ib(ibdev, port)) @@ -902,7 +889,8 @@ static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, return 0; } -static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u8 port, u64 *sl2vl_tbl) +static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u32 port, + u64 *sl2vl_tbl) { union sl2vl_tbl_to_u64 sl2vl64; struct ib_smp *in_mad = NULL; @@ -921,7 +909,7 @@ static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u8 port, u64 *sl2vl_tbl) if (!in_mad || !out_mad) goto out; - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_SL_TO_VL_TABLE; in_mad->attr_mod = 0; @@ -962,7 +950,7 @@ static void mlx4_init_sl2vl_tbl(struct mlx4_ib_dev *mdev) } } -int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, +int __mlx4_ib_query_pkey(struct ib_device *ibdev, u32 port, u16 index, u16 *pkey, int netw_view) { struct ib_smp *in_mad = NULL; @@ -975,7 +963,7 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, if (!in_mad || !out_mad) goto out; - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_PKEY_TABLE; in_mad->attr_mod = cpu_to_be32(index / 32); @@ -995,7 +983,8 @@ out: return err; } -static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey) +static int mlx4_ib_query_pkey(struct ib_device *ibdev, u32 port, u16 index, + u16 *pkey) { return __mlx4_ib_query_pkey(ibdev, port, index, pkey, 0); } @@ -1036,8 +1025,8 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask, return 0; } -static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols, - u32 cap_mask) +static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u32 port, + int reset_qkey_viols, u32 cap_mask) { struct mlx4_cmd_mailbox *mailbox; int err; @@ -1062,7 +1051,7 @@ static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_vio return err; } -static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask, +static int mlx4_ib_modify_port(struct ib_device *ibdev, u32 port, int mask, struct ib_port_modify *props) { struct mlx4_ib_dev *mdev = to_mdev(ibdev); @@ -1218,51 +1207,46 @@ 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 struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev, - struct ib_udata *udata) +static int mlx4_ib_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata) { - struct mlx4_ib_xrcd *xrcd; + struct mlx4_ib_dev *dev = to_mdev(ibxrcd->device); + struct mlx4_ib_xrcd *xrcd = to_mxrcd(ibxrcd); struct ib_cq_init_attr cq_attr = {}; int err; - if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC)) - return ERR_PTR(-ENOSYS); - - xrcd = kmalloc(sizeof *xrcd, GFP_KERNEL); - if (!xrcd) - return ERR_PTR(-ENOMEM); + if (!(dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC)) + return -EOPNOTSUPP; - err = mlx4_xrcd_alloc(to_mdev(ibdev)->dev, &xrcd->xrcdn); + err = mlx4_xrcd_alloc(dev->dev, &xrcd->xrcdn); if (err) - goto err1; + return err; - xrcd->pd = ib_alloc_pd(ibdev, 0); + xrcd->pd = ib_alloc_pd(ibxrcd->device, 0); if (IS_ERR(xrcd->pd)) { err = PTR_ERR(xrcd->pd); goto err2; } cq_attr.cqe = 1; - xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, &cq_attr); + xrcd->cq = ib_create_cq(ibxrcd->device, NULL, NULL, xrcd, &cq_attr); if (IS_ERR(xrcd->cq)) { err = PTR_ERR(xrcd->cq); goto err3; } - return &xrcd->ibxrcd; + return 0; err3: ib_dealloc_pd(xrcd->pd); err2: - mlx4_xrcd_free(to_mdev(ibdev)->dev, xrcd->xrcdn); -err1: - kfree(xrcd); - return ERR_PTR(err); + mlx4_xrcd_free(dev->dev, xrcd->xrcdn); + return err; } static int mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata) @@ -1270,8 +1254,6 @@ static int mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata) ib_destroy_cq(to_mxrcd(xrcd)->cq); ib_dealloc_pd(to_mxrcd(xrcd)->pd); mlx4_xrcd_free(to_mdev(xrcd->device)->dev, to_mxrcd(xrcd)->xrcdn); - kfree(xrcd); - return 0; } @@ -1502,8 +1484,9 @@ static int __mlx4_ib_create_default_rules( int i; for (i = 0; i < ARRAY_SIZE(pdefault_rules->rules_create_list); i++) { + union ib_flow_spec ib_spec = {}; int ret; - union ib_flow_spec ib_spec; + switch (pdefault_rules->rules_create_list[i]) { case 0: /* no rule */ @@ -1544,23 +1527,11 @@ 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; @@ -1569,8 +1540,7 @@ 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); @@ -1712,8 +1682,8 @@ 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; @@ -1721,9 +1691,6 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, struct mlx4_dev *dev = (to_mdev(qp->device))->dev; int is_bonded = mlx4_is_bonded(dev); - if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt) - return ERR_PTR(-EINVAL); - if (flow_attr->flags & ~IB_FLOW_ATTR_FLAGS_DONT_TRAP) return ERR_PTR(-EOPNOTSUPP); @@ -1779,8 +1746,8 @@ 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) { @@ -1789,7 +1756,7 @@ 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) @@ -2015,7 +1982,7 @@ static int init_node_data(struct mlx4_ib_dev *dev) if (!in_mad || !out_mad) goto out; - init_query_mad(in_mad); + ib_init_query_mad(in_mad); in_mad->attr_id = IB_SMP_ATTR_NODE_DESC; if (mlx4_is_master(dev->dev)) mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW; @@ -2046,7 +2013,8 @@ static ssize_t hca_type_show(struct device *device, { struct mlx4_ib_dev *dev = rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev); - return sprintf(buf, "MT%d\n", dev->dev->persist->pdev->device); + + return sysfs_emit(buf, "MT%d\n", dev->dev->persist->pdev->device); } static DEVICE_ATTR_RO(hca_type); @@ -2055,7 +2023,8 @@ static ssize_t hw_rev_show(struct device *device, { struct mlx4_ib_dev *dev = rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev); - return sprintf(buf, "%x\n", dev->dev->rev_id); + + return sysfs_emit(buf, "%x\n", dev->dev->rev_id); } static DEVICE_ATTR_RO(hw_rev); @@ -2065,8 +2034,7 @@ static ssize_t board_id_show(struct device *device, struct mlx4_ib_dev *dev = rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev); - return sprintf(buf, "%.*s\n", MLX4_BOARD_ID_LEN, - dev->dev->board_id); + return sysfs_emit(buf, "%.*s\n", MLX4_BOARD_ID_LEN, dev->dev->board_id); } static DEVICE_ATTR_RO(board_id); @@ -2123,23 +2091,35 @@ static const struct diag_counter diag_device_only[] = { DIAG_COUNTER(rq_num_udsdprd, 0x118), }; -static struct rdma_hw_stats *mlx4_ib_alloc_hw_stats(struct ib_device *ibdev, - u8 port_num) +static struct rdma_hw_stats * +mlx4_ib_alloc_hw_device_stats(struct ib_device *ibdev) +{ + struct mlx4_ib_dev *dev = to_mdev(ibdev); + struct mlx4_ib_diag_counters *diag = dev->diag_counters; + + if (!diag[0].descs) + return NULL; + + return rdma_alloc_hw_stats_struct(diag[0].descs, diag[0].num_counters, + RDMA_HW_STATS_DEFAULT_LIFESPAN); +} + +static struct rdma_hw_stats * +mlx4_ib_alloc_hw_port_stats(struct ib_device *ibdev, u32 port_num) { struct mlx4_ib_dev *dev = to_mdev(ibdev); struct mlx4_ib_diag_counters *diag = dev->diag_counters; - if (!diag[!!port_num].name) + if (!diag[1].descs) return NULL; - return rdma_alloc_hw_stats_struct(diag[!!port_num].name, - diag[!!port_num].num_counters, + return rdma_alloc_hw_stats_struct(diag[1].descs, diag[1].num_counters, RDMA_HW_STATS_DEFAULT_LIFESPAN); } static int mlx4_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, - u8 port, int index) + u32 port, int index) { struct mlx4_ib_dev *dev = to_mdev(ibdev); struct mlx4_ib_diag_counters *diag = dev->diag_counters; @@ -2163,10 +2143,8 @@ static int mlx4_ib_get_hw_stats(struct ib_device *ibdev, } static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev, - const char ***name, - u32 **offset, - u32 *num, - bool port) + struct rdma_stat_desc **pdescs, + u32 **offset, u32 *num, bool port) { u32 num_counters; @@ -2178,53 +2156,59 @@ static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev, if (!port) num_counters += ARRAY_SIZE(diag_device_only); - *name = kcalloc(num_counters, sizeof(**name), GFP_KERNEL); - if (!*name) + *pdescs = kcalloc(num_counters, sizeof(struct rdma_stat_desc), + GFP_KERNEL); + if (!*pdescs) return -ENOMEM; *offset = kcalloc(num_counters, sizeof(**offset), GFP_KERNEL); if (!*offset) - goto err_name; + goto err; *num = num_counters; return 0; -err_name: - kfree(*name); +err: + kfree(*pdescs); return -ENOMEM; } static void mlx4_ib_fill_diag_counters(struct mlx4_ib_dev *ibdev, - const char **name, - u32 *offset, - bool port) + struct rdma_stat_desc *descs, + u32 *offset, bool port) { int i; int j; for (i = 0, j = 0; i < ARRAY_SIZE(diag_basic); i++, j++) { - name[i] = diag_basic[i].name; + descs[i].name = diag_basic[i].name; offset[i] = diag_basic[i].offset; } if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT) { for (i = 0; i < ARRAY_SIZE(diag_ext); i++, j++) { - name[j] = diag_ext[i].name; + descs[j].name = diag_ext[i].name; offset[j] = diag_ext[i].offset; } } if (!port) { for (i = 0; i < ARRAY_SIZE(diag_device_only); i++, j++) { - name[j] = diag_device_only[i].name; + descs[j].name = diag_device_only[i].name; offset[j] = diag_device_only[i].offset; } } } static const struct ib_device_ops mlx4_ib_hw_stats_ops = { - .alloc_hw_stats = mlx4_ib_alloc_hw_stats, + .alloc_hw_device_stats = mlx4_ib_alloc_hw_device_stats, + .alloc_hw_port_stats = mlx4_ib_alloc_hw_port_stats, + .get_hw_stats = mlx4_ib_get_hw_stats, +}; + +static const struct ib_device_ops mlx4_ib_hw_stats_ops1 = { + .alloc_hw_device_stats = mlx4_ib_alloc_hw_device_stats, .get_hw_stats = mlx4_ib_get_hw_stats, }; @@ -2240,17 +2224,24 @@ static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev) return 0; for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) { - /* i == 1 means we are building port counters */ - if (i && !per_port) - continue; + /* + * i == 1 means we are building port counters, set a different + * stats ops without port stats callback. + */ + if (i && !per_port) { + ib_set_device_ops(&ibdev->ib_dev, + &mlx4_ib_hw_stats_ops1); + + return 0; + } - ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].name, + ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].descs, &diag[i].offset, &diag[i].num_counters, i); if (ret) goto err_alloc; - mlx4_ib_fill_diag_counters(ibdev, diag[i].name, + mlx4_ib_fill_diag_counters(ibdev, diag[i].descs, diag[i].offset, i); } @@ -2260,7 +2251,7 @@ static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev) err_alloc: if (i) { - kfree(diag[i - 1].name); + kfree(diag[i - 1].descs); kfree(diag[i - 1].offset); } @@ -2273,7 +2264,7 @@ static void mlx4_ib_diag_cleanup(struct mlx4_ib_dev *ibdev) for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) { kfree(ibdev->diag_counters[i].offset); - kfree(ibdev->diag_counters[i].name); + kfree(ibdev->diag_counters[i].descs); } } @@ -2286,10 +2277,7 @@ static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev, u64 release_mac = MLX4_IB_INVALID_MAC; struct mlx4_ib_qp *qp; - read_lock(&dev_base_lock); - new_smac = mlx4_mac_to_u64(dev->dev_addr); - read_unlock(&dev_base_lock); - + new_smac = ether_addr_to_u64(dev->dev_addr); atomic64_set(&ibdev->iboe.mac[port - 1], new_smac); /* no need for update QP1 and mac registration in non-SRIOV */ @@ -2490,7 +2478,7 @@ static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) ibdev->eq_table = NULL; } -static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num, +static int mlx4_port_immutable(struct ib_device *ibdev, u32 port_num, struct ib_port_immutable *immutable) { struct ib_port_attr attr; @@ -2555,6 +2543,7 @@ static const struct ib_device_ops mlx4_ib_dev_ops = { .destroy_qp = mlx4_ib_destroy_qp, .destroy_srq = mlx4_ib_destroy_srq, .detach_mcast = mlx4_ib_mcg_detach, + .device_group = &mlx4_attr_group, .disassociate_ucontext = mlx4_ib_disassociate_ucontext, .drain_rq = mlx4_ib_drain_rq, .drain_sq = mlx4_ib_drain_sq, @@ -2590,6 +2579,7 @@ static const struct ib_device_ops mlx4_ib_dev_ops = { INIT_RDMA_OBJ_SIZE(ib_ah, mlx4_ib_ah, ibah), INIT_RDMA_OBJ_SIZE(ib_cq, mlx4_ib_cq, ibcq), INIT_RDMA_OBJ_SIZE(ib_pd, mlx4_ib_pd, ibpd), + INIT_RDMA_OBJ_SIZE(ib_qp, mlx4_ib_qp, ibqp), INIT_RDMA_OBJ_SIZE(ib_srq, mlx4_ib_srq, ibsrq), INIT_RDMA_OBJ_SIZE(ib_ucontext, mlx4_ib_ucontext, ibucontext), }; @@ -2600,23 +2590,23 @@ 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, -}; -static const struct ib_device_ops mlx4_ib_dev_fmr_ops = { - .alloc_fmr = mlx4_ib_fmr_alloc, - .dealloc_fmr = mlx4_ib_fmr_dealloc, - .map_phys_fmr = mlx4_ib_map_phys_fmr, - .unmap_fmr = mlx4_ib_unmap_fmr, + INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mlx4_ib_rwq_ind_table, + ib_rwq_ind_tbl), }; static const struct ib_device_ops mlx4_ib_dev_mw_ops = { .alloc_mw = mlx4_ib_alloc_mw, .dealloc_mw = mlx4_ib_dealloc_mw, + + INIT_RDMA_OBJ_SIZE(ib_mw, mlx4_ib_mw, ibmw), }; static const struct ib_device_ops mlx4_ib_dev_xrc_ops = { .alloc_xrcd = mlx4_ib_alloc_xrcd, .dealloc_xrcd = mlx4_ib_dealloc_xrcd, + + INIT_RDMA_OBJ_SIZE(ib_xrcd, mlx4_ib_xrcd, ibxrcd), }; static const struct ib_device_ops mlx4_ib_dev_fs_ops = { @@ -2679,76 +2669,25 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors; ibdev->ib_dev.dev.parent = &dev->persist->pdev->dev; - ibdev->ib_dev.uverbs_cmd_mask = - (1ull << IB_USER_VERBS_CMD_GET_CONTEXT) | - (1ull << IB_USER_VERBS_CMD_QUERY_DEVICE) | - (1ull << IB_USER_VERBS_CMD_QUERY_PORT) | - (1ull << IB_USER_VERBS_CMD_ALLOC_PD) | - (1ull << IB_USER_VERBS_CMD_DEALLOC_PD) | - (1ull << IB_USER_VERBS_CMD_REG_MR) | - (1ull << IB_USER_VERBS_CMD_REREG_MR) | - (1ull << IB_USER_VERBS_CMD_DEREG_MR) | - (1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) | - (1ull << IB_USER_VERBS_CMD_CREATE_CQ) | - (1ull << IB_USER_VERBS_CMD_RESIZE_CQ) | - (1ull << IB_USER_VERBS_CMD_DESTROY_CQ) | - (1ull << IB_USER_VERBS_CMD_CREATE_QP) | - (1ull << IB_USER_VERBS_CMD_MODIFY_QP) | - (1ull << IB_USER_VERBS_CMD_QUERY_QP) | - (1ull << IB_USER_VERBS_CMD_DESTROY_QP) | - (1ull << IB_USER_VERBS_CMD_ATTACH_MCAST) | - (1ull << IB_USER_VERBS_CMD_DETACH_MCAST) | - (1ull << IB_USER_VERBS_CMD_CREATE_SRQ) | - (1ull << IB_USER_VERBS_CMD_MODIFY_SRQ) | - (1ull << IB_USER_VERBS_CMD_QUERY_SRQ) | - (1ull << IB_USER_VERBS_CMD_DESTROY_SRQ) | - (1ull << IB_USER_VERBS_CMD_CREATE_XSRQ) | - (1ull << IB_USER_VERBS_CMD_OPEN_QP); - ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_ops); - ibdev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_CQ) | - (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) | - (1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ) | - (1ull << IB_USER_VERBS_EX_CMD_CREATE_QP); if ((dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) && ((mlx4_ib_port_link_layer(&ibdev->ib_dev, 1) == IB_LINK_LAYER_ETHERNET) || (mlx4_ib_port_link_layer(&ibdev->ib_dev, 2) == - IB_LINK_LAYER_ETHERNET))) { - ibdev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_CREATE_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_MODIFY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_WQ) | - (1ull << IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL); + IB_LINK_LAYER_ETHERNET))) ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_wq_ops); - } - - if (!mlx4_is_slave(ibdev->dev)) - ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_fmr_ops); if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || - dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) { - ibdev->ib_dev.uverbs_cmd_mask |= - (1ull << IB_USER_VERBS_CMD_ALLOC_MW) | - (1ull << IB_USER_VERBS_CMD_DEALLOC_MW); + dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_mw_ops); - } if (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) { - ibdev->ib_dev.uverbs_cmd_mask |= - (1ull << IB_USER_VERBS_CMD_OPEN_XRCD) | - (1ull << IB_USER_VERBS_CMD_CLOSE_XRCD); ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_xrc_ops); } if (check_flow_steering_support(dev)) { ibdev->steering_support = MLX4_STEERING_MODE_DEVICE_MANAGED; - ibdev->ib_dev.uverbs_ex_cmd_mask |= - (1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) | - (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW); ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_fs_ops); } @@ -2837,10 +2776,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) if (err) goto err_counter; - ibdev->ib_uc_qpns_bitmap = - kmalloc_array(BITS_TO_LONGS(ibdev->steer_qpn_count), - sizeof(long), - GFP_KERNEL); + ibdev->ib_uc_qpns_bitmap = bitmap_alloc(ibdev->steer_qpn_count, + GFP_KERNEL); if (!ibdev->ib_uc_qpns_bitmap) goto err_steer_qp_release; @@ -2865,8 +2802,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) if (mlx4_ib_alloc_diag_counters(ibdev)) 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)) @@ -2928,7 +2865,7 @@ err_diag_counters: mlx4_ib_diag_cleanup(ibdev); err_steer_free_bitmap: - kfree(ibdev->ib_uc_qpns_bitmap); + bitmap_free(ibdev->ib_uc_qpns_bitmap); err_steer_qp_release: mlx4_qp_release_range(dev, ibdev->steer_qpn_base, @@ -3008,10 +2945,8 @@ 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); } @@ -3043,7 +2978,7 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) mlx4_qp_release_range(dev, ibdev->steer_qpn_base, ibdev->steer_qpn_count); - kfree(ibdev->ib_uc_qpns_bitmap); + bitmap_free(ibdev->ib_uc_qpns_bitmap); iounmap(ibdev->uar_map); for (p = 0; p < ibdev->num_ports; ++p) @@ -3302,7 +3237,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, case MLX4_DEV_EVENT_PORT_MGMT_CHANGE: ew = kmalloc(sizeof *ew, GFP_ATOMIC); if (!ew) - break; + return; INIT_WORK(&ew->work, handle_port_mgmt_change_event); memcpy(&ew->ib_eqe, eqe, sizeof *eqe); @@ -3372,10 +3307,14 @@ static int __init mlx4_ib_init(void) if (!wq) return -ENOMEM; - err = mlx4_ib_mcg_init(); + err = mlx4_ib_cm_init(); if (err) goto clean_wq; + err = mlx4_ib_mcg_init(); + if (err) + goto clean_cm; + err = mlx4_register_interface(&mlx4_ib_interface); if (err) goto clean_mcg; @@ -3385,6 +3324,9 @@ static int __init mlx4_ib_init(void) clean_mcg: mlx4_ib_mcg_destroy(); +clean_cm: + mlx4_ib_cm_destroy(); + clean_wq: destroy_workqueue(wq); return err; @@ -3394,6 +3336,7 @@ static void __exit mlx4_ib_cleanup(void) { mlx4_unregister_interface(&mlx4_ib_interface); mlx4_ib_mcg_destroy(); + mlx4_ib_cm_destroy(); destroy_workqueue(wq); } diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c index d844831179cf..33f525b744f2 100644 --- a/drivers/infiniband/hw/mlx4/mcg.c +++ b/drivers/infiniband/hw/mlx4/mcg.c @@ -944,7 +944,7 @@ int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port, switch (sa_mad->mad_hdr.method) { case IB_MGMT_METHOD_SET: may_create = 1; - /* fall through */ + fallthrough; case IB_SA_METHOD_DELETE: req = kzalloc(sizeof *req, GFP_KERNEL); if (!req) @@ -988,53 +988,63 @@ int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port, } static ssize_t sysfs_show_group(struct device *dev, - struct device_attribute *attr, char *buf) + struct device_attribute *attr, char *buf) { struct mcast_group *group = container_of(attr, struct mcast_group, dentry); struct mcast_req *req = NULL; - char pending_str[40]; char state_str[40]; - ssize_t len = 0; - int f; + char pending_str[40]; + int len; + int i; + u32 hoplimit; if (group->state == MCAST_IDLE) - sprintf(state_str, "%s", get_state_string(group->state)); + scnprintf(state_str, sizeof(state_str), "%s", + get_state_string(group->state)); else - sprintf(state_str, "%s(TID=0x%llx)", - get_state_string(group->state), - be64_to_cpu(group->last_req_tid)); + scnprintf(state_str, sizeof(state_str), "%s(TID=0x%llx)", + get_state_string(group->state), + be64_to_cpu(group->last_req_tid)); + if (list_empty(&group->pending_list)) { - sprintf(pending_str, "No"); + scnprintf(pending_str, sizeof(pending_str), "No"); } else { - req = list_first_entry(&group->pending_list, struct mcast_req, group_list); - sprintf(pending_str, "Yes(TID=0x%llx)", - be64_to_cpu(req->sa_mad.mad_hdr.tid)); + req = list_first_entry(&group->pending_list, struct mcast_req, + group_list); + scnprintf(pending_str, sizeof(pending_str), "Yes(TID=0x%llx)", + be64_to_cpu(req->sa_mad.mad_hdr.tid)); } - len += sprintf(buf + len, "%1d [%02d,%02d,%02d] %4d %4s %5s ", - group->rec.scope_join_state & 0xf, - group->members[2], group->members[1], group->members[0], - atomic_read(&group->refcount), - pending_str, - state_str); - for (f = 0; f < MAX_VFS; ++f) - if (group->func[f].state == MCAST_MEMBER) - len += sprintf(buf + len, "%d[%1x] ", - f, group->func[f].join_state); - - len += sprintf(buf + len, "\t\t(%4hx %4x %2x %2x %2x %2x %2x " - "%4x %4x %2x %2x)\n", - be16_to_cpu(group->rec.pkey), - be32_to_cpu(group->rec.qkey), - (group->rec.mtusel_mtu & 0xc0) >> 6, - group->rec.mtusel_mtu & 0x3f, - group->rec.tclass, - (group->rec.ratesel_rate & 0xc0) >> 6, - group->rec.ratesel_rate & 0x3f, - (be32_to_cpu(group->rec.sl_flowlabel_hoplimit) & 0xf0000000) >> 28, - (be32_to_cpu(group->rec.sl_flowlabel_hoplimit) & 0x0fffff00) >> 8, - be32_to_cpu(group->rec.sl_flowlabel_hoplimit) & 0x000000ff, - group->rec.proxy_join); + + len = sysfs_emit(buf, "%1d [%02d,%02d,%02d] %4d %4s %5s ", + group->rec.scope_join_state & 0xf, + group->members[2], + group->members[1], + group->members[0], + atomic_read(&group->refcount), + pending_str, + state_str); + + for (i = 0; i < MAX_VFS; i++) { + if (group->func[i].state == MCAST_MEMBER) + len += sysfs_emit_at(buf, len, "%d[%1x] ", i, + group->func[i].join_state); + } + + hoplimit = be32_to_cpu(group->rec.sl_flowlabel_hoplimit); + len += sysfs_emit_at(buf, len, + "\t\t(%4hx %4x %2x %2x %2x %2x %2x %4x %4x %2x %2x)\n", + be16_to_cpu(group->rec.pkey), + be32_to_cpu(group->rec.qkey), + (group->rec.mtusel_mtu & 0xc0) >> 6, + (group->rec.mtusel_mtu & 0x3f), + group->rec.tclass, + (group->rec.ratesel_rate & 0xc0) >> 6, + (group->rec.ratesel_rate & 0x3f), + (hoplimit & 0xf0000000) >> 28, + (hoplimit & 0x0fffff00) >> 8, + (hoplimit & 0x000000ff), + group->rec.proxy_join); return len; } diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index d188573187fa..6a3b0f121045 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -146,11 +146,6 @@ struct mlx4_ib_mw { struct mlx4_mw mmw; }; -struct mlx4_ib_fmr { - struct ib_fmr ibfmr; - struct mlx4_fmr mfmr; -}; - #define MAX_REGS_PER_FLOW 2 struct mlx4_flow_reg_id { @@ -238,7 +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 { @@ -303,6 +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; @@ -348,7 +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 { @@ -371,6 +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 */ /****************************************/ @@ -406,7 +429,7 @@ struct mlx4_sriov_alias_guid_port_rec_det { struct mlx4_sriov_alias_guid_info_rec_det all_rec_per_port[NUM_ALIAS_GUID_REC_IN_PORT]; struct workqueue_struct *wq; struct delayed_work alias_guid_work; - u8 port; + u32 port; u32 state_flags; struct mlx4_sriov_alias_guid *parent; struct list_head cb_list; @@ -459,6 +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]; }; @@ -466,6 +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; @@ -497,6 +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 { @@ -575,7 +601,7 @@ struct mlx4_ib_counters { #define MLX4_DIAG_COUNTERS_TYPES 2 struct mlx4_ib_diag_counters { - const char **name; + struct rdma_stat_desc *descs; u32 *offset; u32 num_counters; }; @@ -631,7 +657,7 @@ struct mlx4_ib_qp_tunnel_init_attr { struct ib_qp_init_attr init_attr; int slave; enum ib_qp_type proxy_qp_type; - u8 port; + u32 port; }; struct mlx4_uverbs_ex_query_device { @@ -679,11 +705,6 @@ 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_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); @@ -735,43 +756,44 @@ 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, struct ib_udata *udata); + u32 max_num_sg); int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); 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); void mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq); -int mlx4_ib_create_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr, u32 flags, +int mlx4_ib_create_ah(struct ib_ah *ah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata); 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); -struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd, - struct ib_qp_init_attr *init_attr, - struct ib_udata *udata); +int mlx4_ib_create_qp(struct ib_qp *qp, struct ib_qp_init_attr *init_attr, + struct ib_udata *udata); int mlx4_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata); void mlx4_ib_drain_sq(struct ib_qp *qp); void mlx4_ib_drain_rq(struct ib_qp *qp); @@ -787,30 +809,24 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags, 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, +int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u32 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in, struct ib_mad *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); -struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int mr_access_flags, - struct ib_fmr_attr *fmr_attr); -int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, int npages, - u64 iova); -int mlx4_ib_unmap_fmr(struct list_head *fmr_list); -int mlx4_ib_fmr_dealloc(struct ib_fmr *fmr); -int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port, +int __mlx4_ib_query_port(struct ib_device *ibdev, u32 port, struct ib_port_attr *props, int netw_view); -int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, +int __mlx4_ib_query_pkey(struct ib_device *ibdev, u32 port, u16 index, u16 *pkey, int netw_view); -int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index, +int __mlx4_ib_query_gid(struct ib_device *ibdev, u32 port, int index, union ib_gid *gid, int netw_view); 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; + u32 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 true; @@ -824,7 +840,7 @@ void clean_vf_mcast(struct mlx4_ib_demux_ctx *ctx, int slave); int mlx4_ib_mcg_init(void); void mlx4_ib_mcg_destroy(void); -int mlx4_ib_find_real_gid(struct ib_device *ibdev, u8 port, __be64 guid); +int mlx4_ib_find_real_gid(struct ib_device *ibdev, u32 port, __be64 guid); int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port, int slave, struct ib_sa_mad *sa_mad); @@ -834,16 +850,16 @@ int mlx4_ib_mcg_demux_handler(struct ib_device *ibdev, int port, int slave, int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, union ib_gid *gid); -void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num, +void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u32 port_num, enum ib_event_type type); 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, +int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u32 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, +int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u32 port, enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn, u32 qkey, struct rdma_ah_attr *attr, u8 *s_mac, u16 vlan_id, struct ib_mad *mad); @@ -867,10 +883,10 @@ void mlx4_ib_invalidate_all_guid_record(struct mlx4_ib_dev *dev, int port); void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev, int block_num, - u8 port_num, u8 *p_data); + u32 port_num, u8 *p_data); void mlx4_ib_update_cache_on_guid_change(struct mlx4_ib_dev *dev, - int block_num, u8 port_num, + int block_num, u32 port_num, u8 *p_data); int add_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num, @@ -891,10 +907,10 @@ 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); -int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, - u64 start, u64 length, u64 virt_addr, - int mr_access_flags, struct ib_pd *pd, - struct ib_udata *udata); +struct ib_mr *mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, u64 start, + u64 length, u64 virt_addr, + int mr_access_flags, struct ib_pd *pd, + struct ib_udata *udata); int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev, const struct ib_gid_attr *attr); @@ -906,16 +922,22 @@ 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); +int mlx4_ib_cm_init(void); +void mlx4_ib_cm_destroy(void); + #endif /* MLX4_IB_H */ diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index b0121c90c561..a40bf58bcdd3 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -200,7 +200,7 @@ int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt, mtt_shift = mtt->page_shift; mtt_size = 1ULL << mtt_shift; - for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) { + for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { if (cur_start_addr + len == sg_dma_address(sg)) { /* still the same block */ len += sg_dma_len(sg); @@ -271,7 +271,9 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va, u64 total_len = 0; int i; - for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) { + *num_of_mtts = ib_umem_num_dma_blocks(umem, PAGE_SIZE); + + for_each_sgtable_dma_sg(&umem->sgt_append.sgt, sg, i) { /* * Initialization - save the first chunk start as the * current_block_start - block means contiguous pages. @@ -380,7 +382,7 @@ static struct ib_umem *mlx4_get_umem_mr(struct ib_device *device, u64 start, unsigned long untagged_start = untagged_addr(start); struct vm_area_struct *vma; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); /* * FIXME: Ideally this would iterate over all the vmas that * cover the memory, but for now it requires a single vma to @@ -395,7 +397,7 @@ static struct ib_umem *mlx4_get_umem_mr(struct ib_device *device, u64 start, access_flags |= IB_ACCESS_LOCAL_WRITE; } - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); } return ib_umem_get(device, start, length, access_flags); @@ -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, @@ -438,8 +439,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, goto err_mr; mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key; - mr->ibmr.length = length; - mr->ibmr.iova = virt_addr; mr->ibmr.page_size = 1U << shift; return &mr->ibmr; @@ -456,10 +455,10 @@ err_free: return ERR_PTR(err); } -int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, - u64 start, u64 length, u64 virt_addr, - int mr_access_flags, struct ib_pd *pd, - struct ib_udata *udata) +struct ib_mr *mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, u64 start, + u64 length, u64 virt_addr, + int mr_access_flags, struct ib_pd *pd, + struct ib_udata *udata) { struct mlx4_ib_dev *dev = to_mdev(mr->device); struct mlx4_ib_mr *mmr = to_mmr(mr); @@ -472,9 +471,8 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, * race exists. */ err = mlx4_mr_hw_get_mpt(dev->dev, &mmr->mmr, &pmpt_entry); - if (err) - return err; + return ERR_PTR(err); if (flags & IB_MR_REREG_PD) { err = mlx4_mr_hw_change_pd(dev->dev, *pmpt_entry, @@ -512,7 +510,7 @@ 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, @@ -542,8 +540,9 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, release_mpt_entry: mlx4_mr_hw_put_mpt(dev->dev, pmpt_entry); - - return err; + if (err) + return ERR_PTR(err); + return NULL; } static int @@ -611,37 +610,27 @@ 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) @@ -649,13 +638,11 @@ 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_mr(struct ib_pd *pd, enum ib_mr_type mr_type, - u32 max_num_sg, struct ib_udata *udata) + u32 max_num_sg) { struct mlx4_ib_dev *dev = to_mdev(pd->device); struct mlx4_ib_mr *mr; @@ -698,99 +685,6 @@ err_free: return ERR_PTR(err); } -struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc, - struct ib_fmr_attr *fmr_attr) -{ - struct mlx4_ib_dev *dev = to_mdev(pd->device); - struct mlx4_ib_fmr *fmr; - int err = -ENOMEM; - - fmr = kmalloc(sizeof *fmr, GFP_KERNEL); - if (!fmr) - return ERR_PTR(-ENOMEM); - - err = mlx4_fmr_alloc(dev->dev, to_mpd(pd)->pdn, convert_access(acc), - fmr_attr->max_pages, fmr_attr->max_maps, - fmr_attr->page_shift, &fmr->mfmr); - if (err) - goto err_free; - - err = mlx4_fmr_enable(to_mdev(pd->device)->dev, &fmr->mfmr); - if (err) - goto err_mr; - - fmr->ibfmr.rkey = fmr->ibfmr.lkey = fmr->mfmr.mr.key; - - return &fmr->ibfmr; - -err_mr: - (void) mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr); - -err_free: - kfree(fmr); - - return ERR_PTR(err); -} - -int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, - int npages, u64 iova) -{ - struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr); - struct mlx4_ib_dev *dev = to_mdev(ifmr->ibfmr.device); - - return mlx4_map_phys_fmr(dev->dev, &ifmr->mfmr, page_list, npages, iova, - &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey); -} - -int mlx4_ib_unmap_fmr(struct list_head *fmr_list) -{ - struct ib_fmr *ibfmr; - int err; - struct mlx4_dev *mdev = NULL; - - list_for_each_entry(ibfmr, fmr_list, list) { - if (mdev && to_mdev(ibfmr->device)->dev != mdev) - return -EINVAL; - mdev = to_mdev(ibfmr->device)->dev; - } - - if (!mdev) - return 0; - - list_for_each_entry(ibfmr, fmr_list, list) { - struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr); - - mlx4_fmr_unmap(mdev, &ifmr->mfmr, &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey); - } - - /* - * Make sure all MPT status updates are visible before issuing - * SYNC_TPT firmware command. - */ - wmb(); - - err = mlx4_SYNC_TPT(mdev); - if (err) - pr_warn("SYNC_TPT error %d when " - "unmapping FMRs\n", err); - - return 0; -} - -int mlx4_ib_fmr_dealloc(struct ib_fmr *ibfmr) -{ - struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr); - struct mlx4_ib_dev *dev = to_mdev(ibfmr->device); - int err; - - err = mlx4_fmr_free(dev->dev, &ifmr->mfmr); - - if (!err) - kfree(ifmr); - - return err; -} - static int mlx4_set_page(struct ib_mr *ibmr, u64 addr) { struct mlx4_ib_mr *mr = to_mmr(ibmr); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 26425dd2d960..b17d6ebc5b70 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); @@ -1149,8 +1099,10 @@ static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr, if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) qp->flags |= MLX4_IB_QP_NETIF; - else + else { + err = -EINVAL; goto err; + } } err = set_kernel_sq_size(dev, &init_attr->cap, qp_type, qp); @@ -1239,9 +1191,6 @@ 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 +1242,7 @@ 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 +1356,6 @@ 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 +1474,16 @@ 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 +1495,16 @@ 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 -EOPNOTSUPP; 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 +1514,7 @@ 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) { @@ -1578,56 +1522,51 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, pd = to_mxrcd(init_attr->xrcd)->pd; xrcdn = to_mxrcd(init_attr->xrcd)->xrcdn; init_attr->send_cq = to_mxrcd(init_attr->xrcd)->cq; - /* fall through */ + 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; - /* fall through */ + 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; - /* fall through */ - 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; + + if (init_attr->create_flags & + (MLX4_IB_SRIOV_SQP | MLX4_IB_SRIOV_TUNNEL_QP)) + /* Internal QP created with ib_create_qp */ + rdma_restrack_no_track(&qp->ibqp.res); qp->port = init_attr->port_num; qp->ibqp.qp_num = init_attr->qp_type == IB_QPT_SMI ? 0 : @@ -1636,25 +1575,28 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd, } default: /* Don't support raw QPs */ - return ERR_PTR(-EINVAL); + 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; +int mlx4_ib_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr, + struct ib_udata *udata) +{ + struct ib_device *device = ibqp->device; struct mlx4_ib_dev *dev = to_mdev(device); + struct mlx4_ib_qp *qp = to_mqp(ibqp); + struct ib_pd *pd = ibqp->pd; + int ret; - ibqp = _mlx4_ib_create_qp(pd, init_attr, udata); + mutex_init(&qp->mutex); + ret = _mlx4_ib_create_qp(pd, qp, init_attr, udata); + if (ret) + return ret; - if (!IS_ERR(ibqp) && - (init_attr->qp_type == IB_QPT_GSI) && + 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 +1608,14 @@ 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 0; } static int _mlx4_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata) @@ -1700,11 +1642,7 @@ 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); 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); @@ -1917,7 +1855,7 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp, u16 vlan_id, u8 *smac) { return _mlx4_set_path(dev, &qp->ah_attr, - mlx4_mac_to_u64(smac), + ether_addr_to_u64(smac), vlan_id, path, &mqp->pri, port); } @@ -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 @@ -2849,10 +2787,13 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, struct mlx4_ib_qp *mqp = to_mqp(ibqp); int ret; + if (attr_mask & ~IB_QP_ATTR_STANDARD_BITS) + return -EOPNOTSUPP; + 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 +2818,13 @@ 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); @@ -2891,6 +2833,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, int send_size; int header_size; int spc; + int err; int i; if (wr->wr.opcode != IB_WR_SEND) @@ -2903,12 +2846,12 @@ 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 = @@ -2925,24 +2868,26 @@ 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); - 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; @@ -3026,10 +2971,11 @@ 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; @@ -3053,7 +2999,7 @@ 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; @@ -3067,9 +3013,9 @@ 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) { @@ -3114,13 +3060,18 @@ 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; @@ -3152,10 +3103,13 @@ 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; @@ -3176,7 +3130,6 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr, } if (is_eth) { - struct in6_addr in6; u16 ether_type; u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13; @@ -3186,11 +3139,9 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr, mlx->sched_prio = cpu_to_be16(pcp); ether_addr_copy(sqp->ud_header.eth.smac_h, ah->av.eth.s_mac); - memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6); + ether_addr_copy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac); 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 (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6)) mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); @@ -3201,26 +3152,33 @@ 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) - ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, &pkey); + if (!qp->ibqp.qp_num) + err = ib_get_cached_pkey(ib_dev, qp->port, sqp->pkey_index, + &pkey); else - ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index, &pkey); + err = ib_get_cached_pkey(ib_dev, qp->port, wr->pkey_index, + &pkey); + if (err) + return err; + sqp->ud_header.bth.pkey = cpu_to_be16(pkey); sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn); 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); @@ -3533,24 +3491,24 @@ static int _mlx4_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, int nreq; int err = 0; unsigned ind; - int uninitialized_var(size); - unsigned uninitialized_var(seglen); + int size; + unsigned seglen; __be32 dummy; __be32 *lso_wqe; - __be32 uninitialized_var(lso_hdr_sz); + __be32 lso_hdr_sz; __be32 blh; int i; 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) ? @@ -3670,8 +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; @@ -3707,8 +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; @@ -3741,8 +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; @@ -4050,7 +4007,9 @@ int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr qp_attr->qp_access_flags = to_ib_qp_access_flags(be32_to_cpu(context.params2)); - if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) { + if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC || + qp->ibqp.qp_type == IB_QPT_XRC_INI || + qp->ibqp.qp_type == IB_QPT_XRC_TGT) { to_rdma_ah_attr(dev, &qp_attr->ah_attr, &context.pri_path); to_rdma_ah_attr(dev, &qp_attr->alt_ah_attr, &context.alt_path); qp_attr->alt_pkey_index = context.alt_path.pkey_index & 0x7f; @@ -4164,6 +4123,7 @@ 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; @@ -4286,13 +4246,8 @@ int mlx4_ib_modify_wq(struct ib_wq *ibwq, struct ib_wq_attr *wq_attr, if (wq_attr_mask & IB_WQ_FLAGS) return -EOPNOTSUPP; - cur_state = wq_attr_mask & IB_WQ_CUR_STATE ? wq_attr->curr_wq_state : - ibwq->state; - new_state = wq_attr_mask & IB_WQ_STATE ? wq_attr->wq_state : cur_state; - - if (cur_state < IB_WQS_RESET || cur_state > IB_WQS_ERR || - new_state < IB_WQS_RESET || new_state > IB_WQS_ERR) - return -EINVAL; + cur_state = wq_attr->curr_wq_state; + new_state = wq_attr->wq_state; if ((new_state == IB_WQS_RDY) && (cur_state == IB_WQS_ERR)) return -EINVAL; @@ -4319,7 +4274,7 @@ 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); @@ -4330,36 +4285,35 @@ 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; @@ -4367,39 +4321,23 @@ 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..c4cf91235eee 100644 --- a/drivers/infiniband/hw/mlx4/srq.c +++ b/drivers/infiniband/hw/mlx4/srq.c @@ -86,6 +86,10 @@ int mlx4_ib_create_srq(struct ib_srq *ib_srq, int err; int i; + if (init_attr->srq_type != IB_SRQT_BASIC && + init_attr->srq_type != IB_SRQT_XRC) + return -EOPNOTSUPP; + /* Sanity check SRQ size before proceeding */ if (init_attr->attr.max_wr >= dev->dev->caps.max_srq_wqes || init_attr->attr.max_sge > dev->dev->caps.max_srq_sge) @@ -115,8 +119,9 @@ 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 +265,7 @@ 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 +287,7 @@ 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) @@ -314,7 +320,6 @@ int mlx4_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) { err = -EIO; *bad_wr = wr; - nreq = 0; goto out; } diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c index ea1f3a081b05..24ee79aa2122 100644 --- a/drivers/infiniband/hw/mlx4/sysfs.c +++ b/drivers/infiniband/hw/mlx4/sysfs.c @@ -56,7 +56,7 @@ static ssize_t show_admin_alias_guid(struct device *dev, mlx4_ib_iov_dentry->entry_num, port->num); - return sprintf(buf, "%llx\n", be64_to_cpu(sysadmin_ag_val)); + return sysfs_emit(buf, "%llx\n", be64_to_cpu(sysadmin_ag_val)); } /* store_admin_alias_guid stores the (new) administratively assigned value of that GUID. @@ -117,22 +117,24 @@ static ssize_t show_port_gid(struct device *dev, struct mlx4_ib_iov_port *port = mlx4_ib_iov_dentry->ctx; struct mlx4_ib_dev *mdev = port->dev; union ib_gid gid; - ssize_t ret; + int ret; + __be16 *raw; ret = __mlx4_ib_query_gid(&mdev->ib_dev, port->num, mlx4_ib_iov_dentry->entry_num, &gid, 1); if (ret) return ret; - ret = sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", - be16_to_cpu(((__be16 *) gid.raw)[0]), - be16_to_cpu(((__be16 *) gid.raw)[1]), - be16_to_cpu(((__be16 *) gid.raw)[2]), - be16_to_cpu(((__be16 *) gid.raw)[3]), - be16_to_cpu(((__be16 *) gid.raw)[4]), - be16_to_cpu(((__be16 *) gid.raw)[5]), - be16_to_cpu(((__be16 *) gid.raw)[6]), - be16_to_cpu(((__be16 *) gid.raw)[7])); - return ret; + + raw = (__be16 *)gid.raw; + return sysfs_emit(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + be16_to_cpu(raw[0]), + be16_to_cpu(raw[1]), + be16_to_cpu(raw[2]), + be16_to_cpu(raw[3]), + be16_to_cpu(raw[4]), + be16_to_cpu(raw[5]), + be16_to_cpu(raw[6]), + be16_to_cpu(raw[7])); } static ssize_t show_phys_port_pkey(struct device *dev, @@ -151,7 +153,7 @@ static ssize_t show_phys_port_pkey(struct device *dev, if (ret) return ret; - return sprintf(buf, "0x%04x\n", pkey); + return sysfs_emit(buf, "0x%04x\n", pkey); } #define DENTRY_REMOVE(_dentry) \ @@ -441,16 +443,12 @@ static ssize_t show_port_pkey(struct mlx4_port *p, struct port_attribute *attr, { struct port_table_attribute *tab_attr = container_of(attr, struct port_table_attribute, attr); - ssize_t ret = -ENODEV; - - if (p->dev->pkeys.virt2phys_pkey[p->slave][p->port_num - 1][tab_attr->index] >= - (p->dev->dev->caps.pkey_table_len[p->port_num])) - ret = sprintf(buf, "none\n"); - else - ret = sprintf(buf, "%d\n", - p->dev->pkeys.virt2phys_pkey[p->slave] - [p->port_num - 1][tab_attr->index]); - return ret; + struct pkey_mgt *m = &p->dev->pkeys; + u8 key = m->virt2phys_pkey[p->slave][p->port_num - 1][tab_attr->index]; + + if (key >= p->dev->dev->caps.pkey_table_len[p->port_num]) + return sysfs_emit(buf, "none\n"); + return sysfs_emit(buf, "%d\n", key); } static ssize_t store_port_pkey(struct mlx4_port *p, struct port_attribute *attr, @@ -488,7 +486,7 @@ static ssize_t store_port_pkey(struct mlx4_port *p, struct port_attribute *attr, static ssize_t show_port_gid_idx(struct mlx4_port *p, struct port_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", p->slave); + return sysfs_emit(buf, "%d\n", p->slave); } static struct attribute ** @@ -542,14 +540,10 @@ static ssize_t sysfs_show_smi_enabled(struct device *dev, { 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; + return sysfs_emit(buf, "%d\n", + !!mlx4_vf_smi_enabled(p->dev->dev, p->slave, + p->port_num)); } static ssize_t sysfs_show_enable_smi_admin(struct device *dev, @@ -558,14 +552,10 @@ static ssize_t sysfs_show_enable_smi_admin(struct device *dev, { 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; + return sysfs_emit(buf, "%d\n", + !!mlx4_vf_get_enable_smi_admin(p->dev->dev, p->slave, + p->port_num)); } static ssize_t sysfs_store_enable_smi_admin(struct device *dev, @@ -808,7 +798,7 @@ static void unregister_pkey_tree(struct mlx4_ib_dev *device) int mlx4_ib_device_register_sysfs(struct mlx4_ib_dev *dev) { - int i; + unsigned int i; int ret = 0; if (!mlx4_is_master(dev->dev)) @@ -827,7 +817,7 @@ int mlx4_ib_device_register_sysfs(struct mlx4_ib_dev *dev) goto err_ports; } - for (i = 1; i <= dev->ib_dev.phys_port_cnt; ++i) { + rdma_for_each_port(&dev->ib_dev, i) { ret = add_port_entries(dev, i); if (ret) goto err_add_entries; |