diff options
Diffstat (limited to 'drivers/infiniband')
29 files changed, 396 insertions, 244 deletions
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 0bee1f4b914e..3208ad6ad540 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -338,6 +338,39 @@ static int add_roce_gid(struct ib_gid_table_entry *entry) } /** + * del_gid - Delete GID table entry + * + * @ib_dev: IB device whose GID entry to be deleted + * @port: Port number of the IB device + * @table: GID table of the IB device for a port + * @ix: GID entry index to delete + * + */ +static void del_gid(struct ib_device *ib_dev, u8 port, + struct ib_gid_table *table, int ix) +{ + struct ib_gid_table_entry *entry; + + lockdep_assert_held(&table->lock); + + pr_debug("%s device=%s port=%d index=%d gid %pI6\n", __func__, + ib_dev->name, port, ix, + table->data_vec[ix]->attr.gid.raw); + + write_lock_irq(&table->rwlock); + entry = table->data_vec[ix]; + entry->state = GID_TABLE_ENTRY_PENDING_DEL; + /* + * For non RoCE protocol, GID entry slot is ready to use. + */ + if (!rdma_protocol_roce(ib_dev, port)) + table->data_vec[ix] = NULL; + write_unlock_irq(&table->rwlock); + + put_gid_entry_locked(entry); +} + +/** * add_modify_gid - Add or modify GID table entry * * @table: GID table in which GID to be added or modified @@ -358,7 +391,7 @@ static int add_modify_gid(struct ib_gid_table *table, * this index. */ if (is_gid_entry_valid(table->data_vec[attr->index])) - put_gid_entry(table->data_vec[attr->index]); + del_gid(attr->device, attr->port_num, table, attr->index); /* * Some HCA's report multiple GID entries with only one valid GID, and @@ -386,39 +419,6 @@ done: return ret; } -/** - * del_gid - Delete GID table entry - * - * @ib_dev: IB device whose GID entry to be deleted - * @port: Port number of the IB device - * @table: GID table of the IB device for a port - * @ix: GID entry index to delete - * - */ -static void del_gid(struct ib_device *ib_dev, u8 port, - struct ib_gid_table *table, int ix) -{ - struct ib_gid_table_entry *entry; - - lockdep_assert_held(&table->lock); - - pr_debug("%s device=%s port=%d index=%d gid %pI6\n", __func__, - ib_dev->name, port, ix, - table->data_vec[ix]->attr.gid.raw); - - write_lock_irq(&table->rwlock); - entry = table->data_vec[ix]; - entry->state = GID_TABLE_ENTRY_PENDING_DEL; - /* - * For non RoCE protocol, GID entry slot is ready to use. - */ - if (!rdma_protocol_roce(ib_dev, port)) - table->data_vec[ix] = NULL; - write_unlock_irq(&table->rwlock); - - put_gid_entry_locked(entry); -} - /* rwlock should be read locked, or lock should be held */ static int find_gid(struct ib_gid_table *table, const union ib_gid *gid, const struct ib_gid_attr *val, bool default_gid, diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index f72677291b69..a36c94930c31 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -724,6 +724,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); + mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { if (!rdma_cap_af_ib(cur_dev->device, p)) @@ -750,18 +751,19 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; + goto found; } } } } - - if (!cma_dev) - return -ENODEV; + mutex_unlock(&lock); + return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); - addr = (struct sockaddr_ib *) cma_src_addr(id_priv); - memcpy(&addr->sib_addr, &sgid, sizeof sgid); + mutex_unlock(&lock); + addr = (struct sockaddr_ib *)cma_src_addr(id_priv); + memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 6eb64c6f0802..c4118bcd5103 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -882,6 +882,8 @@ static int __uverbs_cleanup_ufile(struct ib_uverbs_file *ufile, WARN_ON(uverbs_try_lock_object(obj, UVERBS_LOOKUP_WRITE)); if (!uverbs_destroy_uobject(obj, reason)) ret = 0; + else + atomic_set(&obj->usecnt, 0); } return ret; } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ec8fb289621f..21863ddde63e 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -124,6 +124,8 @@ static DEFINE_MUTEX(mut); static DEFINE_IDR(ctx_idr); static DEFINE_IDR(multicast_idr); +static const struct file_operations ucma_fops; + static inline struct ucma_context *_ucma_find_context(int id, struct ucma_file *file) { @@ -1581,6 +1583,10 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file, f = fdget(cmd.fd); if (!f.file) return -ENOENT; + if (f.file->f_op != &ucma_fops) { + ret = -EINVAL; + goto file_put; + } /* Validate current fd and prevent destruction of id. */ ctx = ucma_get_ctx(f.file->private_data, cmd.id); @@ -1753,6 +1759,8 @@ static int ucma_close(struct inode *inode, struct file *filp) mutex_lock(&mut); if (!ctx->closing) { mutex_unlock(&mut); + ucma_put_ctx(ctx); + wait_for_completion(&ctx->comp); /* rdma_destroy_id ensures that no event handlers are * inflight for that id before releasing it. */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index a21d5214afc3..e012ca80f9d1 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2027,33 +2027,55 @@ static int modify_qp(struct ib_uverbs_file *file, if ((cmd->base.attr_mask & IB_QP_CUR_STATE && cmd->base.cur_qp_state > IB_QPS_ERR) || - cmd->base.qp_state > IB_QPS_ERR) { + (cmd->base.attr_mask & IB_QP_STATE && + cmd->base.qp_state > IB_QPS_ERR)) { ret = -EINVAL; goto release_qp; } - attr->qp_state = cmd->base.qp_state; - attr->cur_qp_state = cmd->base.cur_qp_state; - attr->path_mtu = cmd->base.path_mtu; - attr->path_mig_state = cmd->base.path_mig_state; - attr->qkey = cmd->base.qkey; - attr->rq_psn = cmd->base.rq_psn; - attr->sq_psn = cmd->base.sq_psn; - attr->dest_qp_num = cmd->base.dest_qp_num; - attr->qp_access_flags = cmd->base.qp_access_flags; - attr->pkey_index = cmd->base.pkey_index; - attr->alt_pkey_index = cmd->base.alt_pkey_index; - attr->en_sqd_async_notify = cmd->base.en_sqd_async_notify; - attr->max_rd_atomic = cmd->base.max_rd_atomic; - attr->max_dest_rd_atomic = cmd->base.max_dest_rd_atomic; - attr->min_rnr_timer = cmd->base.min_rnr_timer; - attr->port_num = cmd->base.port_num; - attr->timeout = cmd->base.timeout; - attr->retry_cnt = cmd->base.retry_cnt; - attr->rnr_retry = cmd->base.rnr_retry; - attr->alt_port_num = cmd->base.alt_port_num; - attr->alt_timeout = cmd->base.alt_timeout; - attr->rate_limit = cmd->rate_limit; + if (cmd->base.attr_mask & IB_QP_STATE) + attr->qp_state = cmd->base.qp_state; + if (cmd->base.attr_mask & IB_QP_CUR_STATE) + attr->cur_qp_state = cmd->base.cur_qp_state; + if (cmd->base.attr_mask & IB_QP_PATH_MTU) + attr->path_mtu = cmd->base.path_mtu; + if (cmd->base.attr_mask & IB_QP_PATH_MIG_STATE) + attr->path_mig_state = cmd->base.path_mig_state; + if (cmd->base.attr_mask & IB_QP_QKEY) + attr->qkey = cmd->base.qkey; + if (cmd->base.attr_mask & IB_QP_RQ_PSN) + attr->rq_psn = cmd->base.rq_psn; + if (cmd->base.attr_mask & IB_QP_SQ_PSN) + attr->sq_psn = cmd->base.sq_psn; + if (cmd->base.attr_mask & IB_QP_DEST_QPN) + attr->dest_qp_num = cmd->base.dest_qp_num; + if (cmd->base.attr_mask & IB_QP_ACCESS_FLAGS) + attr->qp_access_flags = cmd->base.qp_access_flags; + if (cmd->base.attr_mask & IB_QP_PKEY_INDEX) + attr->pkey_index = cmd->base.pkey_index; + if (cmd->base.attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) + attr->en_sqd_async_notify = cmd->base.en_sqd_async_notify; + if (cmd->base.attr_mask & IB_QP_MAX_QP_RD_ATOMIC) + attr->max_rd_atomic = cmd->base.max_rd_atomic; + if (cmd->base.attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) + attr->max_dest_rd_atomic = cmd->base.max_dest_rd_atomic; + if (cmd->base.attr_mask & IB_QP_MIN_RNR_TIMER) + attr->min_rnr_timer = cmd->base.min_rnr_timer; + if (cmd->base.attr_mask & IB_QP_PORT) + attr->port_num = cmd->base.port_num; + if (cmd->base.attr_mask & IB_QP_TIMEOUT) + attr->timeout = cmd->base.timeout; + if (cmd->base.attr_mask & IB_QP_RETRY_CNT) + attr->retry_cnt = cmd->base.retry_cnt; + if (cmd->base.attr_mask & IB_QP_RNR_RETRY) + attr->rnr_retry = cmd->base.rnr_retry; + if (cmd->base.attr_mask & IB_QP_ALT_PATH) { + attr->alt_port_num = cmd->base.alt_port_num; + attr->alt_timeout = cmd->base.alt_timeout; + attr->alt_pkey_index = cmd->base.alt_pkey_index; + } + if (cmd->base.attr_mask & IB_QP_RATE_LIMIT) + attr->rate_limit = cmd->rate_limit; if (cmd->base.attr_mask & IB_QP_AV) copy_ah_attr_from_uverbs(qp->device, &attr->ah_attr, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 823beca448e1..50152c1b1004 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -440,6 +440,7 @@ static int ib_uverbs_comp_event_close(struct inode *inode, struct file *filp) list_del(&entry->obj_list); kfree(entry); } + file->ev_queue.is_closed = 1; spin_unlock_irq(&file->ev_queue.lock); uverbs_close_fd(filp); @@ -1050,7 +1051,7 @@ static void ib_uverbs_add_one(struct ib_device *device) uverbs_dev->num_comp_vectors = device->num_comp_vectors; if (ib_uverbs_create_uapi(device, uverbs_dev)) - goto err; + goto err_uapi; cdev_init(&uverbs_dev->cdev, NULL); uverbs_dev->cdev.owner = THIS_MODULE; @@ -1077,11 +1078,10 @@ static void ib_uverbs_add_one(struct ib_device *device) err_class: device_destroy(uverbs_class, uverbs_dev->cdev.dev); - err_cdev: cdev_del(&uverbs_dev->cdev); +err_uapi: clear_bit(devnum, dev_map); - err: if (atomic_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); diff --git a/drivers/infiniband/core/uverbs_uapi.c b/drivers/infiniband/core/uverbs_uapi.c index 73ea6f0db88f..be854628a7c6 100644 --- a/drivers/infiniband/core/uverbs_uapi.c +++ b/drivers/infiniband/core/uverbs_uapi.c @@ -248,6 +248,7 @@ void uverbs_destroy_api(struct uverbs_api *uapi) kfree(rcu_dereference_protected(*slot, true)); radix_tree_iter_delete(&uapi->radix, &iter, slot); } + kfree(uapi); } struct uverbs_api *uverbs_alloc_api( diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 6ee03d6089eb..8ec7418e99f0 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2621,3 +2621,49 @@ void ib_drain_qp(struct ib_qp *qp) ib_drain_rq(qp); } EXPORT_SYMBOL(ib_drain_qp); + +struct net_device *rdma_alloc_netdev(struct ib_device *device, u8 port_num, + enum rdma_netdev_t type, const char *name, + unsigned char name_assign_type, + void (*setup)(struct net_device *)) +{ + struct rdma_netdev_alloc_params params; + struct net_device *netdev; + int rc; + + if (!device->rdma_netdev_get_params) + return ERR_PTR(-EOPNOTSUPP); + + rc = device->rdma_netdev_get_params(device, port_num, type, ¶ms); + if (rc) + return ERR_PTR(rc); + + netdev = alloc_netdev_mqs(params.sizeof_priv, name, name_assign_type, + setup, params.txqs, params.rxqs); + if (!netdev) + return ERR_PTR(-ENOMEM); + + return netdev; +} +EXPORT_SYMBOL(rdma_alloc_netdev); + +int rdma_init_netdev(struct ib_device *device, u8 port_num, + enum rdma_netdev_t type, const char *name, + unsigned char name_assign_type, + void (*setup)(struct net_device *), + struct net_device *netdev) +{ + struct rdma_netdev_alloc_params params; + int rc; + + if (!device->rdma_netdev_get_params) + return -EOPNOTSUPP; + + rc = device->rdma_netdev_get_params(device, port_num, type, ¶ms); + if (rc) + return rc; + + return params.initialize_rdma_netdev(device, port_num, + netdev, params.param); +} +EXPORT_SYMBOL(rdma_init_netdev); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index bbfb86eb2d24..bc2b9e038439 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -833,6 +833,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) "Failed to destroy Shadow QP"); return rc; } + bnxt_qplib_free_qp_res(&rdev->qplib_res, + &rdev->qp1_sqp->qplib_qp); mutex_lock(&rdev->qp_lock); list_del(&rdev->qp1_sqp->list); atomic_dec(&rdev->qp_count); diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 20b9f31052bf..85cd1a3593d6 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -78,7 +78,7 @@ static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list); /* Mutex to protect the list of bnxt_re devices added */ static DEFINE_MUTEX(bnxt_re_dev_lock); static struct workqueue_struct *bnxt_re_wq; -static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait); +static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev); /* SR-IOV helper functions */ @@ -182,7 +182,7 @@ static void bnxt_re_shutdown(void *p) if (!rdev) return; - bnxt_re_ib_unreg(rdev, false); + bnxt_re_ib_unreg(rdev); } static void bnxt_re_stop_irq(void *handle) @@ -251,7 +251,7 @@ static struct bnxt_ulp_ops bnxt_re_ulp_ops = { /* Driver registration routines used to let the networking driver (bnxt_en) * to know that the RoCE driver is now installed */ -static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev, bool lock_wait) +static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev) { struct bnxt_en_dev *en_dev; int rc; @@ -260,14 +260,9 @@ static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev, bool lock_wait) return -EINVAL; en_dev = rdev->en_dev; - /* Acquire rtnl lock if it is not invokded from netdev event */ - if (lock_wait) - rtnl_lock(); rc = en_dev->en_ops->bnxt_unregister_device(rdev->en_dev, BNXT_ROCE_ULP); - if (lock_wait) - rtnl_unlock(); return rc; } @@ -281,14 +276,12 @@ static int bnxt_re_register_netdev(struct bnxt_re_dev *rdev) en_dev = rdev->en_dev; - rtnl_lock(); rc = en_dev->en_ops->bnxt_register_device(en_dev, BNXT_ROCE_ULP, &bnxt_re_ulp_ops, rdev); - rtnl_unlock(); return rc; } -static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait) +static int bnxt_re_free_msix(struct bnxt_re_dev *rdev) { struct bnxt_en_dev *en_dev; int rc; @@ -298,13 +291,9 @@ static int bnxt_re_free_msix(struct bnxt_re_dev *rdev, bool lock_wait) en_dev = rdev->en_dev; - if (lock_wait) - rtnl_lock(); rc = en_dev->en_ops->bnxt_free_msix(rdev->en_dev, BNXT_ROCE_ULP); - if (lock_wait) - rtnl_unlock(); return rc; } @@ -320,7 +309,6 @@ static int bnxt_re_request_msix(struct bnxt_re_dev *rdev) num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus()); - rtnl_lock(); num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP, rdev->msix_entries, num_msix_want); @@ -335,7 +323,6 @@ static int bnxt_re_request_msix(struct bnxt_re_dev *rdev) } rdev->num_msix = num_msix_got; done: - rtnl_unlock(); return rc; } @@ -358,24 +345,18 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg, fw_msg->timeout = timeout; } -static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id, - bool lock_wait) +static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id) { struct bnxt_en_dev *en_dev = rdev->en_dev; struct hwrm_ring_free_input req = {0}; struct hwrm_ring_free_output resp; struct bnxt_fw_msg fw_msg; - bool do_unlock = false; int rc = -EINVAL; if (!en_dev) return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - if (lock_wait) { - rtnl_lock(); - do_unlock = true; - } bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_FREE, -1, -1); req.ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL; @@ -386,8 +367,6 @@ static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id, if (rc) dev_err(rdev_to_dev(rdev), "Failed to free HW ring:%d :%#x", req.ring_id, rc); - if (do_unlock) - rtnl_unlock(); return rc; } @@ -405,7 +384,6 @@ static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, dma_addr_t *dma_arr, return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - rtnl_lock(); bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_ALLOC, -1, -1); req.enables = 0; req.page_tbl_addr = cpu_to_le64(dma_arr[0]); @@ -426,27 +404,21 @@ static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, dma_addr_t *dma_arr, if (!rc) *fw_ring_id = le16_to_cpu(resp.ring_id); - rtnl_unlock(); return rc; } static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev, - u32 fw_stats_ctx_id, bool lock_wait) + u32 fw_stats_ctx_id) { struct bnxt_en_dev *en_dev = rdev->en_dev; struct hwrm_stat_ctx_free_input req = {0}; struct bnxt_fw_msg fw_msg; - bool do_unlock = false; int rc = -EINVAL; if (!en_dev) return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - if (lock_wait) { - rtnl_lock(); - do_unlock = true; - } bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_FREE, -1, -1); req.stat_ctx_id = cpu_to_le32(fw_stats_ctx_id); @@ -457,8 +429,6 @@ static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev, dev_err(rdev_to_dev(rdev), "Failed to free HW stats context %#x", rc); - if (do_unlock) - rtnl_unlock(); return rc; } @@ -478,7 +448,6 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, return rc; memset(&fw_msg, 0, sizeof(fw_msg)); - rtnl_lock(); bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1); req.update_period_ms = cpu_to_le32(1000); @@ -490,7 +459,6 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, if (!rc) *fw_stats_ctx_id = le32_to_cpu(resp.stat_ctx_id); - rtnl_unlock(); return rc; } @@ -929,19 +897,19 @@ fail: return rc; } -static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev, bool lock_wait) +static void bnxt_re_free_nq_res(struct bnxt_re_dev *rdev) { int i; for (i = 0; i < rdev->num_msix - 1; i++) { - bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id, lock_wait); + bnxt_re_net_ring_free(rdev, rdev->nq[i].ring_id); bnxt_qplib_free_nq(&rdev->nq[i]); } } -static void bnxt_re_free_res(struct bnxt_re_dev *rdev, bool lock_wait) +static void bnxt_re_free_res(struct bnxt_re_dev *rdev) { - bnxt_re_free_nq_res(rdev, lock_wait); + bnxt_re_free_nq_res(rdev); if (rdev->qplib_res.dpi_tbl.max) { bnxt_qplib_dealloc_dpi(&rdev->qplib_res, @@ -1219,7 +1187,7 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev) return 0; } -static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait) +static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev) { int i, rc; @@ -1234,28 +1202,27 @@ static void bnxt_re_ib_unreg(struct bnxt_re_dev *rdev, bool lock_wait) cancel_delayed_work(&rdev->worker); bnxt_re_cleanup_res(rdev); - bnxt_re_free_res(rdev, lock_wait); + bnxt_re_free_res(rdev); if (test_and_clear_bit(BNXT_RE_FLAG_RCFW_CHANNEL_EN, &rdev->flags)) { rc = bnxt_qplib_deinit_rcfw(&rdev->rcfw); if (rc) dev_warn(rdev_to_dev(rdev), "Failed to deinitialize RCFW: %#x", rc); - bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id, - lock_wait); + bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id); bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx); bnxt_qplib_disable_rcfw_channel(&rdev->rcfw); - bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, lock_wait); + bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id); bnxt_qplib_free_rcfw_channel(&rdev->rcfw); } if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) { - rc = bnxt_re_free_msix(rdev, lock_wait); + rc = bnxt_re_free_msix(rdev); if (rc) dev_warn(rdev_to_dev(rdev), "Failed to free MSI-X vectors: %#x", rc); } if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) { - rc = bnxt_re_unregister_netdev(rdev, lock_wait); + rc = bnxt_re_unregister_netdev(rdev); if (rc) dev_warn(rdev_to_dev(rdev), "Failed to unregister with netdev: %#x", rc); @@ -1276,6 +1243,12 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) { int i, j, rc; + bool locked; + + /* Acquire rtnl lock through out this function */ + rtnl_lock(); + locked = true; + /* Registered a new RoCE device instance to netdev */ rc = bnxt_re_register_netdev(rdev); if (rc) { @@ -1374,12 +1347,16 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000)); } + rtnl_unlock(); + locked = false; + /* Register ib dev */ rc = bnxt_re_register_ib(rdev); if (rc) { pr_err("Failed to register with IB: %#x\n", rc); goto fail; } + set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags); dev_info(rdev_to_dev(rdev), "Device registered successfully"); for (i = 0; i < ARRAY_SIZE(bnxt_re_attributes); i++) { rc = device_create_file(&rdev->ibdev.dev, @@ -1395,7 +1372,6 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) goto fail; } } - set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags); ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, &rdev->active_width); set_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags); @@ -1404,17 +1380,21 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) return 0; free_sctx: - bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id, true); + bnxt_re_net_stats_ctx_free(rdev, rdev->qplib_ctx.stats.fw_id); free_ctx: bnxt_qplib_free_ctx(rdev->en_dev->pdev, &rdev->qplib_ctx); disable_rcfw: bnxt_qplib_disable_rcfw_channel(&rdev->rcfw); free_ring: - bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id, true); + bnxt_re_net_ring_free(rdev, rdev->rcfw.creq_ring_id); free_rcfw: bnxt_qplib_free_rcfw_channel(&rdev->rcfw); fail: - bnxt_re_ib_unreg(rdev, true); + if (!locked) + rtnl_lock(); + bnxt_re_ib_unreg(rdev); + rtnl_unlock(); + return rc; } @@ -1567,7 +1547,7 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, */ if (atomic_read(&rdev->sched_count) > 0) goto exit; - bnxt_re_ib_unreg(rdev, false); + bnxt_re_ib_unreg(rdev); bnxt_re_remove_one(rdev); bnxt_re_dev_unreg(rdev); break; @@ -1646,7 +1626,10 @@ static void __exit bnxt_re_mod_exit(void) */ flush_workqueue(bnxt_re_wq); bnxt_re_dev_stop(rdev); - bnxt_re_ib_unreg(rdev, true); + /* Acquire the rtnl_lock as the L2 resources are freed here */ + rtnl_lock(); + bnxt_re_ib_unreg(rdev); + rtnl_unlock(); bnxt_re_remove_one(rdev); bnxt_re_dev_unreg(rdev); } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e426b990c1dd..6ad0d46ab879 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -196,7 +196,7 @@ static int bnxt_qplib_alloc_qp_hdr_buf(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_q *rq = &qp->rq; - struct bnxt_qplib_q *sq = &qp->rq; + struct bnxt_qplib_q *sq = &qp->sq; int rc = 0; if (qp->sq_hdr_buf_size && sq->hwq.max_elements) { diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index b3203afa3b1d..347fe18b1a41 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1685,6 +1685,12 @@ static void flush_qp(struct c4iw_qp *qhp) schp = to_c4iw_cq(qhp->ibqp.send_cq); if (qhp->ibqp.uobject) { + + /* for user qps, qhp->wq.flushed is protected by qhp->mutex */ + if (qhp->wq.flushed) + return; + + qhp->wq.flushed = 1; t4_set_wq_in_error(&qhp->wq, 0); t4_set_cq_in_error(&rchp->cq); spin_lock_irqsave(&rchp->comp_handler_lock, flag); diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 2c19bf772451..e1668bcc2d13 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -6733,6 +6733,7 @@ void start_freeze_handling(struct hfi1_pportdata *ppd, int flags) struct hfi1_devdata *dd = ppd->dd; struct send_context *sc; int i; + int sc_flags; if (flags & FREEZE_SELF) write_csr(dd, CCE_CTRL, CCE_CTRL_SPC_FREEZE_SMASK); @@ -6743,11 +6744,13 @@ void start_freeze_handling(struct hfi1_pportdata *ppd, int flags) /* notify all SDMA engines that they are going into a freeze */ sdma_freeze_notify(dd, !!(flags & FREEZE_LINK_DOWN)); + sc_flags = SCF_FROZEN | SCF_HALTED | (flags & FREEZE_LINK_DOWN ? + SCF_LINK_DOWN : 0); /* do halt pre-handling on all enabled send contexts */ for (i = 0; i < dd->num_send_contexts; i++) { sc = dd->send_contexts[i].sc; if (sc && (sc->flags & SCF_ENABLED)) - sc_stop(sc, SCF_FROZEN | SCF_HALTED); + sc_stop(sc, sc_flags); } /* Send context are frozen. Notify user space */ @@ -10674,6 +10677,7 @@ int set_link_state(struct hfi1_pportdata *ppd, u32 state) add_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK); handle_linkup_change(dd, 1); + pio_kernel_linkup(dd); /* * After link up, a new link width will have been set. diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index eec83757d55f..6c967dde58e7 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -893,14 +893,11 @@ static int trigger_sbr(struct hfi1_devdata *dd) } /* - * A secondary bus reset (SBR) issues a hot reset to our device. - * The following routine does a 1s wait after the reset is dropped - * per PCI Trhfa (recovery time). PCIe 3.0 section 6.6.1 - - * Conventional Reset, paragraph 3, line 35 also says that a 1s - * delay after a reset is required. Per spec requirements, - * the link is either working or not after that point. + * This is an end around to do an SBR during probe time. A new API needs + * to be implemented to have cleaner interface but this fixes the + * current brokenness */ - return pci_reset_bus(dev); + return pci_bridge_secondary_bus_reset(dev->bus->self); } /* diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index c2c1cba5b23b..752057647f09 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -86,6 +86,7 @@ void pio_send_control(struct hfi1_devdata *dd, int op) unsigned long flags; int write = 1; /* write sendctrl back */ int flush = 0; /* re-read sendctrl to make sure it is flushed */ + int i; spin_lock_irqsave(&dd->sendctrl_lock, flags); @@ -95,9 +96,13 @@ void pio_send_control(struct hfi1_devdata *dd, int op) reg |= SEND_CTRL_SEND_ENABLE_SMASK; /* Fall through */ case PSC_DATA_VL_ENABLE: + mask = 0; + for (i = 0; i < ARRAY_SIZE(dd->vld); i++) + if (!dd->vld[i].mtu) + mask |= BIT_ULL(i); /* Disallow sending on VLs not enabled */ - mask = (((~0ull) << num_vls) & SEND_CTRL_UNSUPPORTED_VL_MASK) << - SEND_CTRL_UNSUPPORTED_VL_SHIFT; + mask = (mask & SEND_CTRL_UNSUPPORTED_VL_MASK) << + SEND_CTRL_UNSUPPORTED_VL_SHIFT; reg = (reg & ~SEND_CTRL_UNSUPPORTED_VL_SMASK) | mask; break; case PSC_GLOBAL_DISABLE: @@ -921,20 +926,18 @@ void sc_free(struct send_context *sc) void sc_disable(struct send_context *sc) { u64 reg; - unsigned long flags; struct pio_buf *pbuf; if (!sc) return; /* do all steps, even if already disabled */ - spin_lock_irqsave(&sc->alloc_lock, flags); + spin_lock_irq(&sc->alloc_lock); reg = read_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL)); reg &= ~SC(CTRL_CTXT_ENABLE_SMASK); sc->flags &= ~SCF_ENABLED; sc_wait_for_packet_egress(sc, 1); write_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL), reg); - spin_unlock_irqrestore(&sc->alloc_lock, flags); /* * Flush any waiters. Once the context is disabled, @@ -944,7 +947,7 @@ void sc_disable(struct send_context *sc) * proceed with the flush. */ udelay(1); - spin_lock_irqsave(&sc->release_lock, flags); + spin_lock(&sc->release_lock); if (sc->sr) { /* this context has a shadow ring */ while (sc->sr_tail != sc->sr_head) { pbuf = &sc->sr[sc->sr_tail].pbuf; @@ -955,7 +958,8 @@ void sc_disable(struct send_context *sc) sc->sr_tail = 0; } } - spin_unlock_irqrestore(&sc->release_lock, flags); + spin_unlock(&sc->release_lock); + spin_unlock_irq(&sc->alloc_lock); } /* return SendEgressCtxtStatus.PacketOccupancy */ @@ -1178,11 +1182,39 @@ void pio_kernel_unfreeze(struct hfi1_devdata *dd) sc = dd->send_contexts[i].sc; if (!sc || !(sc->flags & SCF_FROZEN) || sc->type == SC_USER) continue; + if (sc->flags & SCF_LINK_DOWN) + continue; sc_enable(sc); /* will clear the sc frozen flag */ } } +/** + * pio_kernel_linkup() - Re-enable send contexts after linkup event + * @dd: valid devive data + * + * When the link goes down, the freeze path is taken. However, a link down + * event is different from a freeze because if the send context is re-enabled + * whowever is sending data will start sending data again, which will hang + * any QP that is sending data. + * + * The freeze path now looks at the type of event that occurs and takes this + * path for link down event. + */ +void pio_kernel_linkup(struct hfi1_devdata *dd) +{ + struct send_context *sc; + int i; + + for (i = 0; i < dd->num_send_contexts; i++) { + sc = dd->send_contexts[i].sc; + if (!sc || !(sc->flags & SCF_LINK_DOWN) || sc->type == SC_USER) + continue; + + sc_enable(sc); /* will clear the sc link down flag */ + } +} + /* * Wait for the SendPioInitCtxt.PioInitInProgress bit to clear. * Returns: @@ -1382,11 +1414,10 @@ void sc_stop(struct send_context *sc, int flag) { unsigned long flags; - /* mark the context */ - sc->flags |= flag; - /* stop buffer allocations */ spin_lock_irqsave(&sc->alloc_lock, flags); + /* mark the context */ + sc->flags |= flag; sc->flags &= ~SCF_ENABLED; spin_unlock_irqrestore(&sc->alloc_lock, flags); wake_up(&sc->halt_wait); diff --git a/drivers/infiniband/hw/hfi1/pio.h b/drivers/infiniband/hw/hfi1/pio.h index 058b08f459ab..aaf372c3e5d6 100644 --- a/drivers/infiniband/hw/hfi1/pio.h +++ b/drivers/infiniband/hw/hfi1/pio.h @@ -139,6 +139,7 @@ struct send_context { #define SCF_IN_FREE 0x02 #define SCF_HALTED 0x04 #define SCF_FROZEN 0x08 +#define SCF_LINK_DOWN 0x10 struct send_context_info { struct send_context *sc; /* allocated working context */ @@ -306,6 +307,7 @@ void set_pio_integrity(struct send_context *sc); void pio_reset_all(struct hfi1_devdata *dd); void pio_freeze(struct hfi1_devdata *dd); void pio_kernel_unfreeze(struct hfi1_devdata *dd); +void pio_kernel_linkup(struct hfi1_devdata *dd); /* global PIO send control operations */ #define PSC_GLOBAL_ENABLE 0 diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index a3a7b33196d6..5c88706121c1 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -828,7 +828,7 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) if (READ_ONCE(iovec->offset) == iovec->iov.iov_len) { if (++req->iov_idx == req->data_iovs) { ret = -EFAULT; - goto free_txreq; + goto free_tx; } iovec = &req->iovs[req->iov_idx]; WARN_ON(iovec->offset); diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 13374c727b14..a7c586a5589d 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1582,6 +1582,7 @@ static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr) struct hfi1_pportdata *ppd; struct hfi1_devdata *dd; u8 sc5; + u8 sl; if (hfi1_check_mcast(rdma_ah_get_dlid(ah_attr)) && !(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH)) @@ -1590,8 +1591,13 @@ static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr) /* test the mapping for validity */ ibp = to_iport(ibdev, rdma_ah_get_port_num(ah_attr)); ppd = ppd_from_ibp(ibp); - sc5 = ibp->sl_to_sc[rdma_ah_get_sl(ah_attr)]; dd = dd_from_ppd(ppd); + + sl = rdma_ah_get_sl(ah_attr); + if (sl >= ARRAY_SIZE(ibp->sl_to_sc)) + return -EINVAL; + + sc5 = ibp->sl_to_sc[sl]; if (sc_to_vlt(dd, sc5) > num_vls && sc_to_vlt(dd, sc5) != 0xf) return -EINVAL; return 0; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index ca0f1ee26091..0bbeaaae47e0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -517,9 +517,11 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->page_size_cap = dev->dev->caps.page_size_cap; props->max_qp = dev->dev->quotas.qp; props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE; - props->max_send_sge = dev->dev->caps.max_sq_sg; - props->max_recv_sge = dev->dev->caps.max_rq_sg; - props->max_sge_rd = MLX4_MAX_SGE_RD; + props->max_send_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_recv_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_sge_rd = MLX4_MAX_SGE_RD; props->max_cq = dev->dev->quotas.cq; props->max_cqe = dev->dev->caps.max_cqes; props->max_mr = dev->dev->quotas.mpt; diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 25dafa4ff6ca..66dc337e49a7 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -723,6 +723,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_HANDLE); struct mlx5_ib_ucontext *c = to_mucontext(uobj->context); struct mlx5_ib_dev *dev = to_mdev(c->ibucontext.device); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; struct devx_obj *obj; int err; @@ -754,10 +755,12 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( err = uverbs_copy_to(attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_CMD_OUT, cmd_out, cmd_out_len); if (err) - goto obj_free; + goto obj_destroy; return 0; +obj_destroy: + mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out)); obj_free: kfree(obj); return err; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c414f3809e5c..5d9b7f62a0ba 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -5163,22 +5163,14 @@ done: return num_counters; } -static struct net_device* -mlx5_ib_alloc_rdma_netdev(struct ib_device *hca, - u8 port_num, - enum rdma_netdev_t type, - const char *name, - unsigned char name_assign_type, - void (*setup)(struct net_device *)) +static int mlx5_ib_rn_get_params(struct ib_device *device, u8 port_num, + enum rdma_netdev_t type, + struct rdma_netdev_alloc_params *params) { - struct net_device *netdev; - if (type != RDMA_NETDEV_IPOIB) - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; - netdev = mlx5_rdma_netdev_alloc(to_mdev(hca)->mdev, hca, - name, setup); - return netdev; + return mlx5_rdma_rn_get_params(to_mdev(device)->mdev, device, params); } static void delay_drop_debugfs_cleanup(struct mlx5_ib_dev *dev) @@ -5824,8 +5816,9 @@ int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) dev->ib_dev.check_mr_status = mlx5_ib_check_mr_status; dev->ib_dev.get_dev_fw_str = get_dev_fw_str; dev->ib_dev.get_vector_affinity = mlx5_ib_get_vector_affinity; - if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads)) - dev->ib_dev.alloc_rdma_netdev = mlx5_ib_alloc_rdma_netdev; + if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads) && + IS_ENABLED(CONFIG_MLX5_CORE_IPOIB)) + dev->ib_dev.rdma_netdev_get_params = mlx5_ib_rn_get_params; if (mlx5_core_is_pf(mdev)) { dev->ib_dev.get_vf_config = mlx5_ib_get_vf_config; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 9fb1d9cb9401..e22314837645 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -544,6 +544,9 @@ void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) int shrink = 0; int c; + if (!mr->allocated_from_cache) + return; + c = order2idx(dev, mr->order); if (c < 0 || c >= MAX_MR_CACHE_ENTRIES) { mlx5_ib_warn(dev, "order %d, cache index %d\n", mr->order, c); @@ -1647,18 +1650,19 @@ static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) umem = NULL; } #endif - clean_mr(dev, mr); + /* + * We should unregister the DMA address from the HCA before + * remove the DMA mapping. + */ + mlx5_mr_cache_free(dev, mr); if (umem) { ib_umem_release(umem); atomic_sub(npages, &dev->mdev->priv.reg_pages); } - if (!mr->allocated_from_cache) kfree(mr); - else - mlx5_mr_cache_free(dev, mr); } int mlx5_ib_dereg_mr(struct ib_mr *ibmr) diff --git a/drivers/infiniband/hw/nes/nes_mgt.c b/drivers/infiniband/hw/nes/nes_mgt.c index 9bdb84dc225c..e96ffff61c3a 100644 --- a/drivers/infiniband/hw/nes/nes_mgt.c +++ b/drivers/infiniband/hw/nes/nes_mgt.c @@ -198,9 +198,9 @@ static struct sk_buff *nes_get_next_skb(struct nes_device *nesdev, struct nes_qp if (skb) { /* Continue processing fpdu */ - if (skb->next == (struct sk_buff *)&nesqp->pau_list) + skb = skb_peek_next(skb, &nesqp->pau_list); + if (!skb) goto out; - skb = skb->next; processacks = false; } else { /* Starting a new one */ @@ -553,12 +553,10 @@ static void queue_fpdus(struct sk_buff *skb, struct nes_vnic *nesvnic, struct ne if (skb_queue_len(&nesqp->pau_list) == 0) { skb_queue_head(&nesqp->pau_list, skb); } else { - tmpskb = nesqp->pau_list.next; - while (tmpskb != (struct sk_buff *)&nesqp->pau_list) { + skb_queue_walk(&nesqp->pau_list, tmpskb) { cb = (struct nes_rskb_cb *)&tmpskb->cb[0]; if (before(seqnum, cb->seqnum)) break; - tmpskb = tmpskb->next; } skb_insert(tmpskb, skb, &nesqp->pau_list); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 1abe3c62f106..1da119d901a9 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -499,8 +499,10 @@ void ipoib_reap_ah(struct work_struct *work); struct ipoib_path *__path_find(struct net_device *dev, void *gid); void ipoib_mark_paths_invalid(struct net_device *dev); void ipoib_flush_paths(struct net_device *dev); -struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, - const char *format); +struct net_device *ipoib_intf_alloc(struct ib_device *hca, u8 port, + const char *format); +int ipoib_intf_init(struct ib_device *hca, u8 port, const char *format, + struct net_device *dev); void ipoib_ib_tx_timer_func(struct timer_list *t); void ipoib_ib_dev_flush_light(struct work_struct *work); void ipoib_ib_dev_flush_normal(struct work_struct *work); @@ -531,6 +533,8 @@ int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req); void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv, struct ipoib_tx_buf *tx_req); +struct rtnl_link_ops *ipoib_get_link_ops(void); + static inline void ipoib_build_sge(struct ipoib_dev_priv *priv, struct ipoib_tx_buf *tx_req) { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index ea01b8dd2be6..3d5424f335cb 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1027,12 +1027,14 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, skb_queue_head_init(&skqueue); + netif_tx_lock_bh(p->dev); spin_lock_irq(&priv->lock); set_bit(IPOIB_FLAG_OPER_UP, &p->flags); if (p->neigh) while ((skb = __skb_dequeue(&p->neigh->queue))) __skb_queue_tail(&skqueue, skb); spin_unlock_irq(&priv->lock); + netif_tx_unlock_bh(p->dev); while ((skb = __skb_dequeue(&skqueue))) { skb->dev = p->dev; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index e3d28f9ad9c0..8baa75a705c5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2115,82 +2115,58 @@ static const struct net_device_ops ipoib_netdev_default_pf = { .ndo_stop = ipoib_ib_dev_stop_default, }; -static struct net_device -*ipoib_create_netdev_default(struct ib_device *hca, - const char *name, - unsigned char name_assign_type, - void (*setup)(struct net_device *)) +static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u8 port, + const char *name) { struct net_device *dev; - struct rdma_netdev *rn; - dev = alloc_netdev((int)sizeof(struct rdma_netdev), - name, - name_assign_type, setup); - if (!dev) - return NULL; - - rn = netdev_priv(dev); - - rn->send = ipoib_send; - rn->attach_mcast = ipoib_mcast_attach; - rn->detach_mcast = ipoib_mcast_detach; - rn->hca = hca; - dev->netdev_ops = &ipoib_netdev_default_pf; - - return dev; -} - -static struct net_device *ipoib_get_netdev(struct ib_device *hca, u8 port, - const char *name) -{ - struct net_device *dev; - - if (hca->alloc_rdma_netdev) { - dev = hca->alloc_rdma_netdev(hca, port, - RDMA_NETDEV_IPOIB, name, - NET_NAME_UNKNOWN, - ipoib_setup_common); - if (IS_ERR_OR_NULL(dev) && PTR_ERR(dev) != -EOPNOTSUPP) - return NULL; - } - - if (!hca->alloc_rdma_netdev || PTR_ERR(dev) == -EOPNOTSUPP) - dev = ipoib_create_netdev_default(hca, name, NET_NAME_UNKNOWN, - ipoib_setup_common); + dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, + NET_NAME_UNKNOWN, ipoib_setup_common); + if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP) + return dev; + dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN, + ipoib_setup_common); + if (!dev) + return ERR_PTR(-ENOMEM); return dev; } -struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, - const char *name) +int ipoib_intf_init(struct ib_device *hca, u8 port, const char *name, + struct net_device *dev) { - struct net_device *dev; + struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_dev_priv *priv; - struct rdma_netdev *rn; + int rc; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) - return NULL; + return -ENOMEM; priv->ca = hca; priv->port = port; - dev = ipoib_get_netdev(hca, port, name); - if (!dev) - goto free_priv; + rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name, + NET_NAME_UNKNOWN, ipoib_setup_common, dev); + if (rc) { + if (rc != -EOPNOTSUPP) + goto out; + + dev->netdev_ops = &ipoib_netdev_default_pf; + rn->send = ipoib_send; + rn->attach_mcast = ipoib_mcast_attach; + rn->detach_mcast = ipoib_mcast_detach; + rn->hca = hca; + } priv->rn_ops = dev->netdev_ops; - /* fixme : should be after the query_cap */ - if (priv->hca_caps & IB_DEVICE_VIRTUAL_FUNCTION) + if (hca->attrs.device_cap_flags & IB_DEVICE_VIRTUAL_FUNCTION) dev->netdev_ops = &ipoib_netdev_ops_vf; else dev->netdev_ops = &ipoib_netdev_ops_pf; - rn = netdev_priv(dev); rn->clnt_priv = priv; - /* * Only the child register_netdev flows can handle priv_destructor * being set, so we force it to NULL here and handle manually until it @@ -2201,10 +2177,35 @@ struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, ipoib_build_priv(dev); - return priv; -free_priv: + return 0; + +out: kfree(priv); - return NULL; + return rc; +} + +struct net_device *ipoib_intf_alloc(struct ib_device *hca, u8 port, + const char *name) +{ + struct net_device *dev; + int rc; + + dev = ipoib_alloc_netdev(hca, port, name); + if (IS_ERR(dev)) + return dev; + + rc = ipoib_intf_init(hca, port, name, dev); + if (rc) { + free_netdev(dev); + return ERR_PTR(rc); + } + + /* + * Upon success the caller must ensure ipoib_intf_free is called or + * register_netdevice succeed'd and priv_destructor is set to + * ipoib_intf_free. + */ + return dev; } void ipoib_intf_free(struct net_device *dev) @@ -2387,16 +2388,19 @@ int ipoib_add_pkey_attr(struct net_device *dev) static struct net_device *ipoib_add_port(const char *format, struct ib_device *hca, u8 port) { + struct rtnl_link_ops *ops = ipoib_get_link_ops(); + struct rdma_netdev_alloc_params params; struct ipoib_dev_priv *priv; struct net_device *ndev; int result; - priv = ipoib_intf_alloc(hca, port, format); - if (!priv) { - pr_warn("%s, %d: ipoib_intf_alloc failed\n", hca->name, port); - return ERR_PTR(-ENOMEM); + ndev = ipoib_intf_alloc(hca, port, format); + if (IS_ERR(ndev)) { + pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port, + PTR_ERR(ndev)); + return ndev; } - ndev = priv->dev; + priv = ipoib_priv(ndev); INIT_IB_EVENT_HANDLER(&priv->event_handler, priv->ca, ipoib_event); @@ -2417,6 +2421,14 @@ static struct net_device *ipoib_add_port(const char *format, return ERR_PTR(result); } + if (hca->rdma_netdev_get_params) { + int rc = hca->rdma_netdev_get_params(hca, port, + RDMA_NETDEV_IPOIB, + ¶ms); + + if (!rc && ops->priv_size < params.sizeof_priv) + ops->priv_size = params.sizeof_priv; + } /* * We cannot set priv_destructor before register_netdev because we * need priv to be always valid during the error flow to execute diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index d4d553a51fa9..38c984d16996 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -122,12 +122,26 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, } else child_pkey = nla_get_u16(data[IFLA_IPOIB_PKEY]); + err = ipoib_intf_init(ppriv->ca, ppriv->port, dev->name, dev); + if (err) { + ipoib_warn(ppriv, "failed to initialize pkey device\n"); + return err; + } + err = __ipoib_vlan_add(ppriv, ipoib_priv(dev), child_pkey, IPOIB_RTNL_CHILD); + if (err) + return err; - if (!err && data) + if (data) { err = ipoib_changelink(dev, tb, data, extack); - return err; + if (err) { + unregister_netdevice(dev); + return err; + } + } + + return 0; } static size_t ipoib_get_size(const struct net_device *dev) @@ -149,6 +163,11 @@ static struct rtnl_link_ops ipoib_link_ops __read_mostly = { .fill_info = ipoib_fill_info, }; +struct rtnl_link_ops *ipoib_get_link_ops(void) +{ + return &ipoib_link_ops; +} + int __init ipoib_netlink_init(void) { return rtnl_link_register(&ipoib_link_ops); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 341753fbda54..8ac8e18fbe0c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -85,7 +85,7 @@ static bool is_child_unique(struct ipoib_dev_priv *ppriv, /* * NOTE: If this function fails then the priv->dev will remain valid, however - * priv can have been freed and must not be touched by caller in the error + * priv will have been freed and must not be touched by caller in the error * case. * * If (ndev->reg_state == NETREG_UNINITIALIZED) then it is up to the caller to @@ -101,6 +101,12 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, ASSERT_RTNL(); /* + * We do not need to touch priv if register_netdevice fails, so just + * always use this flow. + */ + ndev->priv_destructor = ipoib_intf_free; + + /* * Racing with unregister of the parent must be prevented by the * caller. */ @@ -120,9 +126,6 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, goto out_early; } - /* We do not need to touch priv if register_netdevice fails */ - ndev->priv_destructor = ipoib_intf_free; - result = register_netdevice(ndev); if (result) { ipoib_warn(priv, "failed to initialize; error %i", result); @@ -182,12 +185,12 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) snprintf(intf_name, sizeof(intf_name), "%s.%04x", ppriv->dev->name, pkey); - priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); - if (!priv) { - result = -ENOMEM; + ndev = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name); + if (IS_ERR(ndev)) { + result = PTR_ERR(ndev); goto out; } - ndev = priv->dev; + priv = ipoib_priv(ndev); result = __ipoib_vlan_add(ppriv, priv, pkey, IPOIB_LEGACY_CHILD); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 444d16520506..0b34e909505f 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -2951,7 +2951,7 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) { struct srp_target_port *target = host_to_target(scmnd->device->host); struct srp_rdma_ch *ch; - int i; + int i, j; u8 status; shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n"); @@ -2965,8 +2965,8 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) for (i = 0; i < target->ch_count; i++) { ch = &target->ch[i]; - for (i = 0; i < target->req_ring_size; ++i) { - struct srp_request *req = &ch->req_ring[i]; + for (j = 0; j < target->req_ring_size; ++j) { + struct srp_request *req = &ch->req_ring[j]; srp_finish_req(ch, req, scmnd->device, DID_RESET << 16); } |