diff options
| author | Igor Opaniuk <igor.opaniuk@toradex.com> | 2020-11-13 14:11:10 +0200 |
|---|---|---|
| committer | Igor Opaniuk <igor.opaniuk@toradex.com> | 2020-11-13 14:17:32 +0200 |
| commit | 3b59d4725be760cd276094079b4fbe7bd44e1464 (patch) | |
| tree | 37a4892c12efe64a69453ecdb694866dd18dc4f5 /drivers/infiniband | |
| parent | 4d47b797d6bb1db34ddf702f2cf78104be135a8f (diff) | |
| parent | 70d1232fdbe28e4c765c4cfc3cc5c7580959d5e0 (diff) | |
Merge commit '70d1232fdbe28e4c765c4cfc3cc5c7580959d5e0' into toradex_5.4-2.1.x-imx
Update 5.4-2.1.x-imx to v5.4.74 from [1].
[1] https://github.com/Freescale/linux-fslc
Diffstat (limited to 'drivers/infiniband')
69 files changed, 573 insertions, 423 deletions
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 1753a9801b70..8beed4197e73 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -645,13 +645,12 @@ static void process_one_req(struct work_struct *_work) req->callback = NULL; spin_lock_bh(&lock); + /* + * Although the work will normally have been canceled by the workqueue, + * it can still be requeued as long as it is on the req_list. + */ + cancel_delayed_work(&req->work); if (!list_empty(&req->list)) { - /* - * Although the work will normally have been canceled by the - * workqueue, it can still be requeued as long as it is on the - * req_list. - */ - cancel_delayed_work(&req->work); list_del_init(&req->list); kfree(req); } diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 09af96ec41dd..c1d6a068f50f 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1092,14 +1092,22 @@ retest: break; } - spin_lock_irq(&cm.lock); + spin_lock_irq(&cm_id_priv->lock); + spin_lock(&cm.lock); + /* Required for cleanup paths related cm_req_handler() */ + if (cm_id_priv->timewait_info) { + cm_cleanup_timewait(cm_id_priv->timewait_info); + kfree(cm_id_priv->timewait_info); + cm_id_priv->timewait_info = NULL; + } if (!list_empty(&cm_id_priv->altr_list) && (!cm_id_priv->altr_send_port_not_ready)) list_del(&cm_id_priv->altr_list); if (!list_empty(&cm_id_priv->prim_list) && (!cm_id_priv->prim_send_port_not_ready)) list_del(&cm_id_priv->prim_list); - spin_unlock_irq(&cm.lock); + spin_unlock(&cm.lock); + spin_unlock_irq(&cm_id_priv->lock); cm_free_id(cm_id->local_id); cm_deref_id(cm_id_priv); @@ -1416,7 +1424,7 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, /* Verify that we're not in timewait. */ cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irqsave(&cm_id_priv->lock, flags); - if (cm_id->state != IB_CM_IDLE) { + if (cm_id->state != IB_CM_IDLE || WARN_ON(cm_id_priv->timewait_info)) { spin_unlock_irqrestore(&cm_id_priv->lock, flags); ret = -EINVAL; goto out; @@ -1434,12 +1442,12 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, param->ppath_sgid_attr, &cm_id_priv->av, cm_id_priv); if (ret) - goto error1; + goto out; if (param->alternate_path) { ret = cm_init_av_by_path(param->alternate_path, NULL, &cm_id_priv->alt_av, cm_id_priv); if (ret) - goto error1; + goto out; } cm_id->service_id = param->service_id; cm_id->service_mask = ~cpu_to_be64(0); @@ -1457,7 +1465,7 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, ret = cm_alloc_msg(cm_id_priv, &cm_id_priv->msg); if (ret) - goto error1; + goto out; req_msg = (struct cm_req_msg *) cm_id_priv->msg->mad; cm_format_req(req_msg, cm_id_priv, param); @@ -1480,7 +1488,6 @@ int ib_send_cm_req(struct ib_cm_id *cm_id, return 0; error2: cm_free_msg(cm_id_priv->msg); -error1: kfree(cm_id_priv->timewait_info); out: return ret; } EXPORT_SYMBOL(ib_send_cm_req); @@ -1965,7 +1972,7 @@ static int cm_req_handler(struct cm_work *work) pr_debug("%s: local_id %d, no listen_cm_id_priv\n", __func__, be32_to_cpu(cm_id->local_id)); ret = -EINVAL; - goto free_timeinfo; + goto destroy; } cm_id_priv->id.cm_handler = listen_cm_id_priv->id.cm_handler; @@ -2050,8 +2057,6 @@ static int cm_req_handler(struct cm_work *work) rejected: atomic_dec(&cm_id_priv->refcount); cm_deref_id(listen_cm_id_priv); -free_timeinfo: - kfree(cm_id_priv->timewait_info); destroy: ib_destroy_cm_id(cm_id); return ret; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 8f776b7de45e..98d2d74b96f7 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1631,6 +1631,8 @@ static struct rdma_id_private *cma_find_listener( { struct rdma_id_private *id_priv, *id_priv_dev; + lockdep_assert_held(&lock); + if (!bind_list) return ERR_PTR(-EINVAL); @@ -1677,6 +1679,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, } } + mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice @@ -1718,6 +1721,7 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); + mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; @@ -1799,19 +1803,30 @@ static void cma_release_port(struct rdma_id_private *id_priv) mutex_unlock(&lock); } -static void cma_leave_roce_mc_group(struct rdma_id_private *id_priv, - struct cma_multicast *mc) +static void destroy_mc(struct rdma_id_private *id_priv, + struct cma_multicast *mc) { - struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; - struct net_device *ndev = NULL; + if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) { + ib_sa_free_multicast(mc->multicast.ib); + kfree(mc); + return; + } - if (dev_addr->bound_dev_if) - ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); - if (ndev) { - cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid, false); - dev_put(ndev); + if (rdma_protocol_roce(id_priv->id.device, + id_priv->id.port_num)) { + struct rdma_dev_addr *dev_addr = + &id_priv->id.route.addr.dev_addr; + struct net_device *ndev = NULL; + + if (dev_addr->bound_dev_if) + ndev = dev_get_by_index(dev_addr->net, + dev_addr->bound_dev_if); + if (ndev) { + cma_igmp_send(ndev, &mc->multicast.ib->rec.mgid, false); + dev_put(ndev); + } + kref_put(&mc->mcref, release_mc); } - kref_put(&mc->mcref, release_mc); } static void cma_leave_mc_groups(struct rdma_id_private *id_priv) @@ -1819,16 +1834,10 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv) struct cma_multicast *mc; while (!list_empty(&id_priv->mc_list)) { - mc = container_of(id_priv->mc_list.next, - struct cma_multicast, list); + mc = list_first_entry(&id_priv->mc_list, struct cma_multicast, + list); list_del(&mc->list); - if (rdma_cap_ib_mcast(id_priv->cma_dev->device, - id_priv->id.port_num)) { - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); - } else { - cma_leave_roce_mc_group(id_priv, mc); - } + destroy_mc(id_priv, mc); } } @@ -2473,6 +2482,8 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv, struct net *net = id_priv->id.route.addr.dev_addr.net; int ret; + lockdep_assert_held(&lock); + if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return; @@ -3245,6 +3256,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list, u64 sid, mask; __be16 port; + lockdep_assert_held(&lock); + addr = cma_src_addr(id_priv); port = htons(bind_list->port); @@ -3273,6 +3286,8 @@ static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list; int ret; + lockdep_assert_held(&lock); + bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; @@ -3299,6 +3314,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr); + lockdep_assert_held(&lock); + hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); @@ -3338,6 +3355,8 @@ static int cma_alloc_any_port(enum rdma_ucm_port_space ps, unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net; + lockdep_assert_held(&lock); + inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = prandom_u32() % remaining + low; @@ -3385,6 +3404,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; + lockdep_assert_held(&lock); + addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) @@ -3415,6 +3436,8 @@ static int cma_use_port(enum rdma_ucm_port_space ps, unsigned short snum; int ret; + lockdep_assert_held(&lock); + snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; @@ -4164,16 +4187,6 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) else pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); - mutex_lock(&id_priv->qp_mutex); - if (!status && id_priv->id.qp) { - status = ib_attach_mcast(id_priv->id.qp, &multicast->rec.mgid, - be16_to_cpu(multicast->rec.mlid)); - if (status) - pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to attach QP. status %d\n", - status); - } - mutex_unlock(&id_priv->qp_mutex); - event.status = status; event.param.ud.private_data = mc->context; if (!status) { @@ -4428,6 +4441,10 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, struct cma_multicast *mc; int ret; + /* Not supported for kernel QPs */ + if (WARN_ON(id->qp)) + return -EINVAL; + if (!id->device) return -EINVAL; @@ -4478,25 +4495,14 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irq(&id_priv->lock); list_for_each_entry(mc, &id_priv->mc_list, list) { - if (!memcmp(&mc->addr, addr, rdma_addr_size(addr))) { - list_del(&mc->list); - spin_unlock_irq(&id_priv->lock); - - if (id->qp) - ib_detach_mcast(id->qp, - &mc->multicast.ib->rec.mgid, - be16_to_cpu(mc->multicast.ib->rec.mlid)); - - BUG_ON(id_priv->cma_dev->device != id->device); - - if (rdma_cap_ib_mcast(id->device, id->port_num)) { - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); - } else if (rdma_protocol_roce(id->device, id->port_num)) { - cma_leave_roce_mc_group(id_priv, mc); - } - return; - } + if (memcmp(&mc->addr, addr, rdma_addr_size(addr)) != 0) + continue; + list_del(&mc->list); + spin_unlock_irq(&id_priv->lock); + + WARN_ON(id_priv->cma_dev->device != id->device); + destroy_mc(id_priv, mc); + return; } spin_unlock_irq(&id_priv->lock); } diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c index 8b0b5ae22e4c..726e70b68249 100644 --- a/drivers/infiniband/core/cma_configfs.c +++ b/drivers/infiniband/core/cma_configfs.c @@ -322,8 +322,21 @@ fail: return ERR_PTR(err); } +static void drop_cma_dev(struct config_group *cgroup, struct config_item *item) +{ + struct config_group *group = + container_of(item, struct config_group, cg_item); + struct cma_dev_group *cma_dev_group = + container_of(group, struct cma_dev_group, device_group); + + configfs_remove_default_groups(&cma_dev_group->ports_group); + configfs_remove_default_groups(&cma_dev_group->device_group); + config_item_put(item); +} + static struct configfs_group_operations cma_subsys_group_ops = { .make_group = make_cma_dev, + .drop_item = drop_cma_dev, }; static const struct config_item_type cma_subsys_type = { diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c index 46dd50ff7c85..f454d63008d6 100644 --- a/drivers/infiniband/core/counters.c +++ b/drivers/infiniband/core/counters.c @@ -195,7 +195,7 @@ static int __rdma_counter_unbind_qp(struct ib_qp *qp) return ret; } -static void counter_history_stat_update(const struct rdma_counter *counter) +static void counter_history_stat_update(struct rdma_counter *counter) { struct ib_device *dev = counter->device; struct rdma_port_counter *port_counter; @@ -205,6 +205,8 @@ static void counter_history_stat_update(const struct rdma_counter *counter) if (!port_counter->hstats) return; + rdma_counter_query_stats(counter); + for (i = 0; i < counter->stats->num_counters; i++) port_counter->hstats->value[i] += counter->stats->value[i]; } @@ -282,7 +284,7 @@ int rdma_counter_bind_qp_auto(struct ib_qp *qp, u8 port) struct rdma_counter *counter; int ret; - if (!qp->res.valid) + if (!qp->res.valid || rdma_is_kernel_res(&qp->res)) return 0; if (!rdma_is_port_valid(dev, port)) @@ -485,7 +487,7 @@ int rdma_counter_bind_qpn(struct ib_device *dev, u8 port, goto err; } - if (counter->res.task != qp->res.task) { + if (rdma_is_kernel_res(&counter->res) != rdma_is_kernel_res(&qp->res)) { ret = -EINVAL; goto err_task; } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 10ae6c6eab0a..59dc9f3cfb37 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1330,6 +1330,10 @@ out: return ret; } +static void prevent_dealloc_device(struct ib_device *ib_dev) +{ +} + /** * ib_register_device - Register an IB device with IB core * @device:Device to register @@ -1397,11 +1401,11 @@ int ib_register_device(struct ib_device *device, const char *name) * possibility for a parallel unregistration along with this * error flow. Since we have a refcount here we know any * parallel flow is stopped in disable_device and will see the - * NULL pointers, causing the responsibility to + * special dealloc_driver pointer, causing the responsibility to * ib_dealloc_device() to revert back to this thread. */ dealloc_fn = device->ops.dealloc_driver; - device->ops.dealloc_driver = NULL; + device->ops.dealloc_driver = prevent_dealloc_device; ib_device_put(device); __ib_unregister_device(device); device->ops.dealloc_driver = dealloc_fn; @@ -1449,7 +1453,8 @@ static void __ib_unregister_device(struct ib_device *ib_dev) * Drivers using the new flow may not call ib_dealloc_device except * in error unwind prior to registration success. */ - if (ib_dev->ops.dealloc_driver) { + if (ib_dev->ops.dealloc_driver && + ib_dev->ops.dealloc_driver != prevent_dealloc_device) { WARN_ON(kref_read(&ib_dev->dev.kobj.kref) <= 1); ib_dealloc_device(ib_dev); } diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 9947d16edef2..2284930b5f91 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -639,10 +639,10 @@ static void unregister_mad_agent(struct ib_mad_agent_private *mad_agent_priv) xa_erase(&ib_mad_clients, mad_agent_priv->agent.hi_tid); flush_workqueue(port_priv->wq); - ib_cancel_rmpp_recvs(mad_agent_priv); deref_mad_agent(mad_agent_priv); wait_for_completion(&mad_agent_priv->comp); + ib_cancel_rmpp_recvs(mad_agent_priv); ib_mad_agent_security_cleanup(&mad_agent_priv->agent); @@ -2960,6 +2960,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info, DMA_FROM_DEVICE); if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device, sg_list.addr))) { + kfree(mad_priv); ret = -ENOMEM; break; } diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 244ebf285fc3..e4905d9fecb0 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -702,9 +702,6 @@ static int fill_stat_counter_qps(struct sk_buff *msg, continue; qp = container_of(res, struct ib_qp, res); - if (qp->qp_type == IB_QPT_RAW_PACKET && !capable(CAP_NET_RAW)) - continue; - if (!qp->counter || (qp->counter->id != counter->id)) continue; diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index bddb5434fbed..d2d70c89193f 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -829,13 +829,20 @@ static int ib_nl_get_path_rec_attrs_len(ib_sa_comp_mask comp_mask) return len; } -static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask) +static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask) { struct sk_buff *skb = NULL; struct nlmsghdr *nlh; void *data; struct ib_sa_mad *mad; int len; + unsigned long flags; + unsigned long delay; + gfp_t gfp_flag; + int ret; + + INIT_LIST_HEAD(&query->list); + query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq); mad = query->mad_buf->mad; len = ib_nl_get_path_rec_attrs_len(mad->sa_hdr.comp_mask); @@ -860,36 +867,25 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask) /* Repair the nlmsg header length */ nlmsg_end(skb, nlh); - return rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_mask); -} + gfp_flag = ((gfp_mask & GFP_ATOMIC) == GFP_ATOMIC) ? GFP_ATOMIC : + GFP_NOWAIT; -static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask) -{ - unsigned long flags; - unsigned long delay; - int ret; + spin_lock_irqsave(&ib_nl_request_lock, flags); + ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_flag); - INIT_LIST_HEAD(&query->list); - query->seq = (u32)atomic_inc_return(&ib_nl_sa_request_seq); + if (ret) + goto out; - /* Put the request on the list first.*/ - spin_lock_irqsave(&ib_nl_request_lock, flags); + /* Put the request on the list.*/ delay = msecs_to_jiffies(sa_local_svc_timeout_ms); query->timeout = delay + jiffies; list_add_tail(&query->list, &ib_nl_request_list); /* Start the timeout if this is the only request */ if (ib_nl_request_list.next == &query->list) queue_delayed_work(ib_nl_wq, &ib_nl_timed_work, delay); - spin_unlock_irqrestore(&ib_nl_request_lock, flags); - ret = ib_nl_send_msg(query, gfp_mask); - if (ret) { - ret = -EIO; - /* Remove the request */ - spin_lock_irqsave(&ib_nl_request_lock, flags); - list_del(&query->list); - spin_unlock_irqrestore(&ib_nl_request_lock, flags); - } +out: + spin_unlock_irqrestore(&ib_nl_request_lock, flags); return ret; } diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 7a50cedcef1f..091cca9d88ed 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -1060,8 +1060,7 @@ static int add_port(struct ib_core_device *coredev, int port_num) coredev->ports_kobj, "%d", port_num); if (ret) { - kfree(p); - return ret; + goto err_put; } p->gid_attr_group = kzalloc(sizeof(*p->gid_attr_group), GFP_KERNEL); @@ -1074,8 +1073,7 @@ static int add_port(struct ib_core_device *coredev, int port_num) ret = kobject_init_and_add(&p->gid_attr_group->kobj, &gid_attr_type, &p->kobj, "gid_attrs"); if (ret) { - kfree(p->gid_attr_group); - goto err_put; + goto err_put_gid_attrs; } if (device->ops.process_mad && is_full_dev) { @@ -1406,8 +1404,10 @@ int ib_port_register_module_stat(struct ib_device *device, u8 port_num, ret = kobject_init_and_add(kobj, ktype, &port->kobj, "%s", name); - if (ret) + if (ret) { + kobject_put(kobj); return ret; + } } return 0; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index f4f79f1292b9..ef4be14af3bb 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -581,6 +581,7 @@ static int ucma_free_ctx(struct ucma_context *ctx) list_move_tail(&uevent->list, &list); } list_del(&ctx->list); + events_reported = ctx->events_reported; mutex_unlock(&ctx->file->mut); list_for_each_entry_safe(uevent, tmp, &list, list) { @@ -590,7 +591,6 @@ static int ucma_free_ctx(struct ucma_context *ctx) kfree(uevent); } - events_reported = ctx->events_reported; mutex_destroy(&ctx->mutex); kfree(ctx); return events_reported; @@ -1473,7 +1473,9 @@ static ssize_t ucma_process_join(struct ucma_file *file, return 0; err3: + mutex_lock(&ctx->mutex); rdma_leave_multicast(ctx->cm_id, (struct sockaddr *) &mc->addr); + mutex_unlock(&ctx->mutex); ucma_cleanup_mc_events(mc); err2: xa_erase(&multicast_table, mc->id); @@ -1639,7 +1641,9 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file, cur_file = ctx->file; if (cur_file == new_file) { + mutex_lock(&cur_file->mut); resp.events_reported = ctx->events_reported; + mutex_unlock(&cur_file->mut); goto response; } diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 0d42ba8c0b69..650f71dd4ab9 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -151,13 +151,24 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, dma_addr_t mask; int i; + /* rdma_for_each_block() has a bug if the page size is smaller than the + * page size used to build the umem. For now prevent smaller page sizes + * from being returned. + */ + pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT); + /* At minimum, drivers must support PAGE_SIZE or smaller */ if (WARN_ON(!(pgsz_bitmap & GENMASK(PAGE_SHIFT, 0)))) return 0; va = virt; - /* max page size not to exceed MR length */ - mask = roundup_pow_of_two(umem->length); + /* The best result is the smallest page size that results in the minimum + * number of required pages. Compute the largest page size that could + * work based on VA address bits that don't change. + */ + mask = pgsz_bitmap & + GENMASK(BITS_PER_LONG - 1, + bits_per((umem->length - 1 + virt) ^ virt)); /* offset into first SGL */ pgoff = umem->address & ~PAGE_MASK; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index e2ddcb0dc4ee..c398d1a64614 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -757,6 +757,7 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs) mr->uobject = uobj; atomic_inc(&pd->usecnt); mr->res.type = RDMA_RESTRACK_MR; + mr->iova = cmd.hca_va; rdma_restrack_uadd(&mr->res); uobj->object = mr; @@ -847,6 +848,9 @@ static int ib_uverbs_rereg_mr(struct uverbs_attr_bundle *attrs) atomic_dec(&old_pd->usecnt); } + if (cmd.flags & IB_MR_REREG_TRANS) + mr->iova = cmd.hca_va; + memset(&resp, 0, sizeof(resp)); resp.lkey = mr->lkey; resp.rkey = mr->rkey; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 6c4093d0a91d..5d896f6b2b61 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1648,7 +1648,7 @@ static int _ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *attr, if (!(rdma_protocol_ib(qp->device, attr->alt_ah_attr.port_num) && rdma_protocol_ib(qp->device, port))) { - ret = EINVAL; + ret = -EINVAL; goto out; } } @@ -1749,7 +1749,7 @@ int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width) dev_put(netdev); - if (!rc) { + if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) { netdev_speed = lksettings.base.speed; } else { netdev_speed = SPEED_1000; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index ebc3e3d4a6e2..3b05c0640338 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -2973,6 +2973,19 @@ static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc, wc->wc_flags |= IB_WC_GRH; } +static bool bnxt_re_check_if_vlan_valid(struct bnxt_re_dev *rdev, + u16 vlan_id) +{ + /* + * Check if the vlan is configured in the host. If not configured, it + * can be a transparent VLAN. So dont report the vlan id. + */ + if (!__vlan_find_dev_deep_rcu(rdev->netdev, + htons(ETH_P_8021Q), vlan_id)) + return false; + return true; +} + static bool bnxt_re_is_vlan_pkt(struct bnxt_qplib_cqe *orig_cqe, u16 *vid, u8 *sl) { @@ -3041,9 +3054,11 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *qp, wc->src_qp = orig_cqe->src_qp; memcpy(wc->smac, orig_cqe->smac, ETH_ALEN); if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) { - wc->vlan_id = vlan_id; - wc->sl = sl; - wc->wc_flags |= IB_WC_WITH_VLAN; + if (bnxt_re_check_if_vlan_valid(rdev, vlan_id)) { + wc->vlan_id = vlan_id; + wc->sl = sl; + wc->wc_flags |= IB_WC_WITH_VLAN; + } } wc->port_num = 1; wc->vendor_err = orig_cqe->status; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 27e2df44d043..cfe5f47d9890 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -789,7 +789,8 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event, struct ib_event event; unsigned int flags; - if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR && + rdma_is_kernel_res(&qp->ib_qp.res)) { flags = bnxt_re_lock_cqs(qp); bnxt_qplib_add_flush_qp(&qp->qplib_qp); bnxt_re_unlock_cqs(qp, flags); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 40296b97d21e..079aaaaffec7 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -152,7 +152,7 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_inline_data = le32_to_cpu(sb->max_inline_data); attr->l2_db_size = (sb->l2_db_space_size + 1) * (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); - attr->max_sgid = le32_to_cpu(sb->max_gid); + attr->max_sgid = BNXT_QPLIB_NUM_GIDS_SUPPORTED; bnxt_qplib_query_version(rcfw, attr->fw_ver); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 13d9432d5ce2..194f5ef45ca6 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -47,6 +47,7 @@ struct bnxt_qplib_dev_attr { #define FW_VER_ARR_LEN 4 u8 fw_ver[FW_VER_ARR_LEN]; +#define BNXT_QPLIB_NUM_GIDS_SUPPORTED 256 u16 max_sgid; u16 max_mrw; u32 max_qp; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 6b4e7235d2f5..30e08bcc9afb 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3382,7 +3382,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (raddr->sin_addr.s_addr == htonl(INADDR_ANY)) { err = pick_local_ipaddrs(dev, cm_id); if (err) - goto fail2; + goto fail3; } /* find a route */ @@ -3404,7 +3404,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (ipv6_addr_type(&raddr6->sin6_addr) == IPV6_ADDR_ANY) { err = pick_local_ip6addrs(dev, cm_id); if (err) - goto fail2; + goto fail3; } /* find a route */ diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index 599340c1f0b8..541dbcf22d0e 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -953,6 +953,7 @@ void c4iw_dealloc(struct uld_ctx *ctx) static void c4iw_remove(struct uld_ctx *ctx) { pr_debug("c4iw_dev %p\n", ctx->dev); + debugfs_remove_recursive(ctx->dev->debugfs_root); c4iw_unregister_device(ctx->dev); c4iw_dealloc(ctx); } diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 35c284af574d..dcb58cef336d 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -399,7 +399,6 @@ static int finish_mem_reg(struct c4iw_mr *mhp, u32 stag) mmid = stag >> 8; mhp->ibmr.rkey = mhp->ibmr.lkey = stag; mhp->ibmr.length = mhp->attr.len; - mhp->ibmr.iova = mhp->attr.va_fbo; mhp->ibmr.page_size = 1U << (mhp->attr.page_size + 12); pr_debug("mmid 0x%x mhp %p\n", mmid, mhp); return xa_insert_irq(&mhp->rhp->mrs, mmid, mhp, GFP_KERNEL); diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index d268bf9c42ee..c29da2f4e339 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -985,15 +985,10 @@ static ssize_t qsfp2_debugfs_read(struct file *file, char __user *buf, static int __i2c_debugfs_open(struct inode *in, struct file *fp, u32 target) { struct hfi1_pportdata *ppd; - int ret; ppd = private2ppd(fp); - ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0); - if (ret) /* failed - release the module */ - module_put(THIS_MODULE); - - return ret; + return acquire_chip_resource(ppd->dd, i2c_target(target), 0); } static int i2c1_debugfs_open(struct inode *in, struct file *fp) @@ -1013,7 +1008,6 @@ static int __i2c_debugfs_release(struct inode *in, struct file *fp, u32 target) ppd = private2ppd(fp); release_chip_resource(ppd->dd, i2c_target(target)); - module_put(THIS_MODULE); return 0; } @@ -1031,18 +1025,10 @@ static int i2c2_debugfs_release(struct inode *in, struct file *fp) static int __qsfp_debugfs_open(struct inode *in, struct file *fp, u32 target) { struct hfi1_pportdata *ppd; - int ret; - - if (!try_module_get(THIS_MODULE)) - return -ENODEV; ppd = private2ppd(fp); - ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0); - if (ret) /* failed - release the module */ - module_put(THIS_MODULE); - - return ret; + return acquire_chip_resource(ppd->dd, i2c_target(target), 0); } static int qsfp1_debugfs_open(struct inode *in, struct file *fp) @@ -1062,7 +1048,6 @@ static int __qsfp_debugfs_release(struct inode *in, struct file *fp, u32 target) ppd = private2ppd(fp); release_chip_resource(ppd->dd, i2c_target(target)); - module_put(THIS_MODULE); return 0; } diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 26b792bb1027..fbff6b2f00e7 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -845,6 +845,29 @@ wq_error: } /** + * destroy_workqueues - destroy per port workqueues + * @dd: the hfi1_ib device + */ +static void destroy_workqueues(struct hfi1_devdata *dd) +{ + int pidx; + struct hfi1_pportdata *ppd; + + for (pidx = 0; pidx < dd->num_pports; ++pidx) { + ppd = dd->pport + pidx; + + if (ppd->hfi1_wq) { + destroy_workqueue(ppd->hfi1_wq); + ppd->hfi1_wq = NULL; + } + if (ppd->link_wq) { + destroy_workqueue(ppd->link_wq); + ppd->link_wq = NULL; + } + } +} + +/** * enable_general_intr() - Enable the IRQs that will be handled by the * general interrupt handler. * @dd: valid devdata @@ -1117,15 +1140,10 @@ static void shutdown_device(struct hfi1_devdata *dd) * We can't count on interrupts since we are stopping. */ hfi1_quiet_serdes(ppd); - - if (ppd->hfi1_wq) { - destroy_workqueue(ppd->hfi1_wq); - ppd->hfi1_wq = NULL; - } - if (ppd->link_wq) { - destroy_workqueue(ppd->link_wq); - ppd->link_wq = NULL; - } + if (ppd->hfi1_wq) + flush_workqueue(ppd->hfi1_wq); + if (ppd->link_wq) + flush_workqueue(ppd->link_wq); } sdma_exit(dd); } @@ -1814,6 +1832,7 @@ static void remove_one(struct pci_dev *pdev) * clear dma engines, etc. */ shutdown_device(dd); + destroy_workqueues(dd); stop_timers(dd); diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index f8e733aa3bb8..acd4400b0092 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -381,7 +381,10 @@ bool _hfi1_schedule_send(struct rvt_qp *qp) struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device); + struct hfi1_devdata *dd = ppd->dd; + + if (dd->flags & HFI1_SHUTDOWN) + return true; return iowait_schedule(&priv->s_iowait, ppd->hfi1_wq, priv->s_sde ? diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 8a2e0d9351e9..c018fc633cca 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -3215,6 +3215,7 @@ bool hfi1_tid_rdma_wqe_interlock(struct rvt_qp *qp, struct rvt_swqe *wqe) case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: case IB_WR_RDMA_WRITE: + case IB_WR_RDMA_WRITE_WITH_IMM: switch (prev->wr.opcode) { case IB_WR_TID_RDMA_WRITE: req = wqe_to_tid_req(prev); @@ -5406,7 +5407,10 @@ static bool _hfi1_schedule_tid_send(struct rvt_qp *qp) struct hfi1_ibport *ibp = to_iport(qp->ibqp.device, qp->port_num); struct hfi1_pportdata *ppd = ppd_from_ibp(ibp); - struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device); + struct hfi1_devdata *dd = ppd->dd; + + if ((dd->flags & HFI1_SHUTDOWN)) + return true; return iowait_tid_schedule(&priv->s_iowait, ppd->hfi1_wq, priv->s_sde ? diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index a79fa67df871..a405c64d2a82 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -271,7 +271,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp, ps_opcode = HNS_ROCE_WQE_OPCODE_SEND; break; case IB_WR_LOCAL_INV: - break; case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: case IB_WR_LSO: diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 4540b00ccee9..bb7532819395 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1349,34 +1349,26 @@ static int hns_roce_query_pf_resource(struct hns_roce_dev *hr_dev) static int hns_roce_query_pf_timer_resource(struct hns_roce_dev *hr_dev) { struct hns_roce_pf_timer_res_a *req_a; - struct hns_roce_cmq_desc desc[2]; - int ret, i; + struct hns_roce_cmq_desc desc; + int ret; - for (i = 0; i < 2; i++) { - hns_roce_cmq_setup_basic_desc(&desc[i], - HNS_ROCE_OPC_QUERY_PF_TIMER_RES, - true); + hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_QUERY_PF_TIMER_RES, + true); - if (i == 0) - desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); - else - desc[i].flag &= ~cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); - } - - ret = hns_roce_cmq_send(hr_dev, desc, 2); + ret = hns_roce_cmq_send(hr_dev, &desc, 1); if (ret) return ret; - req_a = (struct hns_roce_pf_timer_res_a *)desc[0].data; + req_a = (struct hns_roce_pf_timer_res_a *)desc.data; hr_dev->caps.qpc_timer_bt_num = - roce_get_field(req_a->qpc_timer_bt_idx_num, - PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_M, - PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_S); + roce_get_field(req_a->qpc_timer_bt_idx_num, + PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_M, + PF_RES_DATA_1_PF_QPC_TIMER_BT_NUM_S); hr_dev->caps.cqc_timer_bt_num = - roce_get_field(req_a->cqc_timer_bt_idx_num, - PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_M, - PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_S); + roce_get_field(req_a->cqc_timer_bt_idx_num, + PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_M, + PF_RES_DATA_2_PF_CQC_TIMER_BT_NUM_S); return 0; } @@ -4564,7 +4556,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->path_mig_state = IB_MIG_ARMED; qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; if (hr_qp->ibqp.qp_type == IB_QPT_UD) - qp_attr->qkey = V2_QKEY_VAL; + qp_attr->qkey = le32_to_cpu(context.qkey_xrcd); qp_attr->rq_psn = roce_get_field(context.byte_108_rx_reqepsn, V2_QPC_BYTE_108_RX_REQ_EPSN_M, @@ -4624,7 +4616,9 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->retry_cnt = roce_get_field(context.byte_212_lsn, V2_QPC_BYTE_212_RETRY_CNT_M, V2_QPC_BYTE_212_RETRY_CNT_S); - qp_attr->rnr_retry = le32_to_cpu(context.rq_rnr_timer); + qp_attr->rnr_retry = roce_get_field(context.byte_244_rnr_rxack, + V2_QPC_BYTE_244_RNR_CNT_M, + V2_QPC_BYTE_244_RNR_CNT_S); done: qp_attr->cur_qp_state = qp_attr->qp_state; @@ -4640,6 +4634,7 @@ done: } qp_init_attr->cap = qp_attr->cap; + qp_init_attr->sq_sig_type = hr_qp->sq_signal_bits; out: mutex_unlock(&hr_qp->mutex); diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 8dd2d666f687..730e50c87a76 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -1181,8 +1181,10 @@ int hns_roce_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, mutex_lock(&hr_qp->mutex); - cur_state = attr_mask & IB_QP_CUR_STATE ? - attr->cur_qp_state : (enum ib_qp_state)hr_qp->state; + if (attr_mask & IB_QP_CUR_STATE && attr->cur_qp_state != hr_qp->state) + goto out; + + cur_state = hr_qp->state; new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state; if (ibqp->uobject && diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index 8feec35f95a7..6d6719fa7e46 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -398,8 +398,8 @@ static inline struct i40iw_qp *to_iwqp(struct ib_qp *ibqp) } /* i40iw.c */ -void i40iw_add_ref(struct ib_qp *); -void i40iw_rem_ref(struct ib_qp *); +void i40iw_qp_add_ref(struct ib_qp *ibqp); +void i40iw_qp_rem_ref(struct ib_qp *ibqp); struct ib_qp *i40iw_get_qp(struct ib_device *, int); void i40iw_flush_wqes(struct i40iw_device *iwdev, @@ -543,9 +543,8 @@ enum i40iw_status_code i40iw_manage_qhash(struct i40iw_device *iwdev, bool wait); void i40iw_receive_ilq(struct i40iw_sc_vsi *vsi, struct i40iw_puda_buf *rbuf); void i40iw_free_sqbuf(struct i40iw_sc_vsi *vsi, void *bufp); -void i40iw_free_qp_resources(struct i40iw_device *iwdev, - struct i40iw_qp *iwqp, - u32 qp_num); +void i40iw_free_qp_resources(struct i40iw_qp *iwqp); + enum i40iw_status_code i40iw_obj_aligned_mem(struct i40iw_device *iwdev, struct i40iw_dma_mem *memptr, u32 size, u32 mask); diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index b1df93b69df4..56c1e9abc52d 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -2074,9 +2074,9 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, dst = i40iw_get_dst_ipv6(&src_addr, &dst_addr); if (!dst || dst->error) { if (dst) { - dst_release(dst); i40iw_pr_err("ip6_route_output returned dst->error = %d\n", dst->error); + dst_release(dst); } return rc; } @@ -2322,7 +2322,7 @@ static void i40iw_rem_ref_cm_node(struct i40iw_cm_node *cm_node) iwqp = cm_node->iwqp; if (iwqp) { iwqp->cm_node = NULL; - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); cm_node->iwqp = NULL; } else if (cm_node->qhash_set) { i40iw_get_addr_info(cm_node, &nfo); @@ -3452,7 +3452,7 @@ void i40iw_cm_disconn(struct i40iw_qp *iwqp) kfree(work); return; } - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); spin_unlock_irqrestore(&iwdev->qptable_lock, flags); work->iwqp = iwqp; @@ -3623,7 +3623,7 @@ static void i40iw_disconnect_worker(struct work_struct *work) kfree(dwork); i40iw_cm_disconn_true(iwqp); - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } /** @@ -3745,7 +3745,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) cm_node->lsmm_size = accept.size + conn_param->private_data_len; i40iw_cm_init_tsa_conn(iwqp, cm_node); cm_id->add_ref(cm_id); - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); attr.qp_state = IB_QPS_RTS; cm_node->qhash_set = false; @@ -3908,7 +3908,7 @@ int i40iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) iwqp->cm_node = cm_node; cm_node->iwqp = iwqp; iwqp->cm_id = cm_id; - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); if (cm_node->state != I40IW_CM_STATE_OFFLOADED) { cm_node->state = I40IW_CM_STATE_SYN_SENT; diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c index ae8b97c30665..a7512508f7e6 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_hw.c +++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c @@ -313,7 +313,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev) __func__, info->qp_cq_id); continue; } - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); spin_unlock_irqrestore(&iwdev->qptable_lock, flags); qp = &iwqp->sc_qp; spin_lock_irqsave(&iwqp->lock, flags); @@ -427,7 +427,7 @@ void i40iw_process_aeq(struct i40iw_device *iwdev) break; } if (info->qp) - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } while (1); if (aeqcnt) diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 016524683e17..72db7c1dc299 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -480,25 +480,6 @@ void i40iw_cleanup_pending_cqp_op(struct i40iw_device *iwdev) } /** - * i40iw_free_qp - callback after destroy cqp completes - * @cqp_request: cqp request for destroy qp - * @num: not used - */ -static void i40iw_free_qp(struct i40iw_cqp_request *cqp_request, u32 num) -{ - struct i40iw_sc_qp *qp = (struct i40iw_sc_qp *)cqp_request->param; - struct i40iw_qp *iwqp = (struct i40iw_qp *)qp->back_qp; - struct i40iw_device *iwdev; - u32 qp_num = iwqp->ibqp.qp_num; - - iwdev = iwqp->iwdev; - - i40iw_rem_pdusecount(iwqp->iwpd, iwdev); - i40iw_free_qp_resources(iwdev, iwqp, qp_num); - i40iw_rem_devusecount(iwdev); -} - -/** * i40iw_wait_event - wait for completion * @iwdev: iwarp device * @cqp_request: cqp request to wait @@ -618,26 +599,23 @@ void i40iw_rem_pdusecount(struct i40iw_pd *iwpd, struct i40iw_device *iwdev) } /** - * i40iw_add_ref - add refcount for qp + * i40iw_qp_add_ref - add refcount for qp * @ibqp: iqarp qp */ -void i40iw_add_ref(struct ib_qp *ibqp) +void i40iw_qp_add_ref(struct ib_qp *ibqp) { struct i40iw_qp *iwqp = (struct i40iw_qp *)ibqp; - atomic_inc(&iwqp->refcount); + refcount_inc(&iwqp->refcount); } /** - * i40iw_rem_ref - rem refcount for qp and free if 0 + * i40iw_qp_rem_ref - rem refcount for qp and free if 0 * @ibqp: iqarp qp */ -void i40iw_rem_ref(struct ib_qp *ibqp) +void i40iw_qp_rem_ref(struct ib_qp *ibqp) { struct i40iw_qp *iwqp; - enum i40iw_status_code status; - struct i40iw_cqp_request *cqp_request; - struct cqp_commands_info *cqp_info; struct i40iw_device *iwdev; u32 qp_num; unsigned long flags; @@ -645,7 +623,7 @@ void i40iw_rem_ref(struct ib_qp *ibqp) iwqp = to_iwqp(ibqp); iwdev = iwqp->iwdev; spin_lock_irqsave(&iwdev->qptable_lock, flags); - if (!atomic_dec_and_test(&iwqp->refcount)) { + if (!refcount_dec_and_test(&iwqp->refcount)) { spin_unlock_irqrestore(&iwdev->qptable_lock, flags); return; } @@ -653,25 +631,8 @@ void i40iw_rem_ref(struct ib_qp *ibqp) qp_num = iwqp->ibqp.qp_num; iwdev->qp_table[qp_num] = NULL; spin_unlock_irqrestore(&iwdev->qptable_lock, flags); - cqp_request = i40iw_get_cqp_request(&iwdev->cqp, false); - if (!cqp_request) - return; - - cqp_request->callback_fcn = i40iw_free_qp; - cqp_request->param = (void *)&iwqp->sc_qp; - cqp_info = &cqp_request->info; - cqp_info->cqp_cmd = OP_QP_DESTROY; - cqp_info->post_sq = 1; - cqp_info->in.u.qp_destroy.qp = &iwqp->sc_qp; - cqp_info->in.u.qp_destroy.scratch = (uintptr_t)cqp_request; - cqp_info->in.u.qp_destroy.remove_hash_idx = true; - status = i40iw_handle_cqp_op(iwdev, cqp_request); - if (!status) - return; + complete(&iwqp->free_qp); - i40iw_rem_pdusecount(iwqp->iwpd, iwdev); - i40iw_free_qp_resources(iwdev, iwqp, qp_num); - i40iw_rem_devusecount(iwdev); } /** @@ -938,7 +899,7 @@ static void i40iw_terminate_timeout(struct timer_list *t) struct i40iw_sc_qp *qp = (struct i40iw_sc_qp *)&iwqp->sc_qp; i40iw_terminate_done(qp, 1); - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } /** @@ -950,7 +911,7 @@ void i40iw_terminate_start_timer(struct i40iw_sc_qp *qp) struct i40iw_qp *iwqp; iwqp = (struct i40iw_qp *)qp->back_qp; - i40iw_add_ref(&iwqp->ibqp); + i40iw_qp_add_ref(&iwqp->ibqp); timer_setup(&iwqp->terminate_timer, i40iw_terminate_timeout, 0); iwqp->terminate_timer.expires = jiffies + HZ; add_timer(&iwqp->terminate_timer); @@ -966,7 +927,7 @@ void i40iw_terminate_del_timer(struct i40iw_sc_qp *qp) iwqp = (struct i40iw_qp *)qp->back_qp; if (del_timer(&iwqp->terminate_timer)) - i40iw_rem_ref(&iwqp->ibqp); + i40iw_qp_rem_ref(&iwqp->ibqp); } /** diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index cd9ee1664a69..22bf4f09c064 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -366,11 +366,11 @@ static struct i40iw_pbl *i40iw_get_pbl(unsigned long va, * @iwqp: qp ptr (user or kernel) * @qp_num: qp number assigned */ -void i40iw_free_qp_resources(struct i40iw_device *iwdev, - struct i40iw_qp *iwqp, - u32 qp_num) +void i40iw_free_qp_resources(struct i40iw_qp *iwqp) { struct i40iw_pbl *iwpbl = &iwqp->iwpbl; + struct i40iw_device *iwdev = iwqp->iwdev; + u32 qp_num = iwqp->ibqp.qp_num; i40iw_ieq_cleanup_qp(iwdev->vsi.ieq, &iwqp->sc_qp); i40iw_dealloc_push_page(iwdev, &iwqp->sc_qp); @@ -404,6 +404,10 @@ static void i40iw_clean_cqes(struct i40iw_qp *iwqp, struct i40iw_cq *iwcq) static int i40iw_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) { struct i40iw_qp *iwqp = to_iwqp(ibqp); + struct ib_qp_attr attr; + struct i40iw_device *iwdev = iwqp->iwdev; + + memset(&attr, 0, sizeof(attr)); iwqp->destroyed = 1; @@ -418,7 +422,15 @@ static int i40iw_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) } } - i40iw_rem_ref(&iwqp->ibqp); + attr.qp_state = IB_QPS_ERR; + i40iw_modify_qp(&iwqp->ibqp, &attr, IB_QP_STATE, NULL); + i40iw_qp_rem_ref(&iwqp->ibqp); + wait_for_completion(&iwqp->free_qp); + i40iw_cqp_qp_destroy_cmd(&iwdev->sc_dev, &iwqp->sc_qp); + i40iw_rem_pdusecount(iwqp->iwpd, iwdev); + i40iw_free_qp_resources(iwqp); + i40iw_rem_devusecount(iwdev); + return 0; } @@ -579,6 +591,7 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, qp->back_qp = (void *)iwqp; qp->push_idx = I40IW_INVALID_PUSH_PAGE_INDEX; + iwqp->iwdev = iwdev; iwqp->ctx_info.iwarp_info = &iwqp->iwarp_info; if (i40iw_allocate_dma_mem(dev->hw, @@ -603,7 +616,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, goto error; } - iwqp->iwdev = iwdev; iwqp->iwpd = iwpd; iwqp->ibqp.qp_num = qp_num; qp = &iwqp->sc_qp; @@ -717,7 +729,7 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, goto error; } - i40iw_add_ref(&iwqp->ibqp); + refcount_set(&iwqp->refcount, 1); spin_lock_init(&iwqp->lock); iwqp->sig_all = (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) ? 1 : 0; iwdev->qp_table[qp_num] = iwqp; @@ -739,10 +751,11 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, } init_completion(&iwqp->sq_drained); init_completion(&iwqp->rq_drained); + init_completion(&iwqp->free_qp); return &iwqp->ibqp; error: - i40iw_free_qp_resources(iwdev, iwqp, qp_num); + i40iw_free_qp_resources(iwqp); return ERR_PTR(err_code); } @@ -2654,13 +2667,13 @@ static const struct ib_device_ops i40iw_dev_ops = { .get_hw_stats = i40iw_get_hw_stats, .get_port_immutable = i40iw_port_immutable, .iw_accept = i40iw_accept, - .iw_add_ref = i40iw_add_ref, + .iw_add_ref = i40iw_qp_add_ref, .iw_connect = i40iw_connect, .iw_create_listen = i40iw_create_listen, .iw_destroy_listen = i40iw_destroy_listen, .iw_get_qp = i40iw_get_qp, .iw_reject = i40iw_reject, - .iw_rem_ref = i40iw_rem_ref, + .iw_rem_ref = i40iw_qp_rem_ref, .map_mr_sg = i40iw_map_mr_sg, .mmap = i40iw_mmap, .modify_qp = i40iw_modify_qp, diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.h b/drivers/infiniband/hw/i40iw/i40iw_verbs.h index 3a413752ccc3..ad7d81041bc9 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.h +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.h @@ -140,7 +140,7 @@ struct i40iw_qp { struct i40iw_qp_host_ctx_info ctx_info; struct i40iwarp_offload_info iwarp_info; void *allocated_buffer; - atomic_t refcount; + refcount_t refcount; struct iw_cm_id *cm_id; void *cm_node; struct ib_mr *lsmm_mr; @@ -175,5 +175,6 @@ struct i40iw_qp { struct i40iw_dma_mem ietf_mem; struct completion sq_drained; struct completion rq_drained; + struct completion free_qp; }; #endif diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c index b591861934b3..81d6a3460b55 100644 --- a/drivers/infiniband/hw/mlx4/cm.c +++ b/drivers/infiniband/hw/mlx4/cm.c @@ -280,6 +280,9 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id) if (!sriov->is_going_down && !id->scheduled_delete) { id->scheduled_delete = 1; schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT); + } else if (id->scheduled_delete) { + /* Adjust timeout if already scheduled */ + mod_delayed_work(system_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT); } spin_unlock_irqrestore(&sriov->going_down_lock, flags); spin_unlock(&sriov->id_map_lock); diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 57079110af9b..08eccf2b6967 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -1307,6 +1307,18 @@ 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) @@ -2009,7 +2021,8 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port, 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); @@ -2046,6 +2059,7 @@ 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) { @@ -2189,7 +2203,7 @@ 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); @@ -2197,7 +2211,15 @@ 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); @@ -2208,6 +2230,10 @@ 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; @@ -2255,12 +2281,14 @@ 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 61a1b0bdede0..b8274c6fc43e 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -781,7 +781,8 @@ 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; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index eb53bb4c0c91..0173e3931cc7 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -459,6 +459,7 @@ 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 +467,7 @@ 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; diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 6ae503cfc526..9114cb730769 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -439,7 +439,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, 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; diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index ff664355de55..73d5b8dc74d8 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -167,7 +167,7 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, { enum rdma_link_layer ll = rdma_port_get_link_layer(qp->ibqp.device, 1); struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.device); - struct mlx5_ib_srq *srq; + struct mlx5_ib_srq *srq = NULL; struct mlx5_ib_wq *wq; u16 wqe_ctr; u8 roce_packet_type; @@ -179,7 +179,8 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, if (qp->ibqp.xrcd) { msrq = mlx5_cmd_get_srq(dev, be32_to_cpu(cqe->srqn)); - srq = to_mibsrq(msrq); + if (msrq) + srq = to_mibsrq(msrq); } else { srq = to_msrq(qp->ibqp.srq); } diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index d609f4659afb..fd75a9043bf1 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -489,6 +489,10 @@ static u64 devx_get_obj_id(const void *in) obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_QP, MLX5_GET(rst2init_qp_in, in, qpn)); break; + case MLX5_CMD_OP_INIT2INIT_QP: + obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_QP, + MLX5_GET(init2init_qp_in, in, qpn)); + break; case MLX5_CMD_OP_INIT2RTR_QP: obj_id = get_enc_obj_id(MLX5_CMD_OP_CREATE_QP, MLX5_GET(init2rtr_qp_in, in, qpn)); @@ -814,6 +818,7 @@ static bool devx_is_obj_modify_cmd(const void *in) case MLX5_CMD_OP_SET_L2_TABLE_ENTRY: case MLX5_CMD_OP_RST2INIT_QP: case MLX5_CMD_OP_INIT2RTR_QP: + case MLX5_CMD_OP_INIT2INIT_QP: case MLX5_CMD_OP_RTR2RTS_QP: case MLX5_CMD_OP_RTS2RTS_QP: case MLX5_CMD_OP_SQERR2RTS_QP: diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 4f44a731a48e..40c1a05c2445 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -517,7 +517,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, mdev_port_num); if (err) goto out; - ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet); + ext = !!MLX5_GET_ETH_PROTO(ptys_reg, out, true, eth_proto_capability); eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); props->active_width = IB_WIDTH_4X; @@ -888,7 +888,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, /* We support 'Gappy' memory registration too */ props->device_cap_flags |= IB_DEVICE_SG_GAPS_REG; } - props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; + /* IB_WR_REG_MR always requires changing the entity size with UMR */ + if (!MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled)) + props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; if (MLX5_CAP_GEN(mdev, sho)) { props->device_cap_flags |= IB_DEVICE_INTEGRITY_HANDOVER; /* At this stage no support for signature handover */ diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 96edc5c30204..09e29c6cb66d 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1463,6 +1463,8 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, u16 uid = to_mpd(pd)->uid; u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {}; + if (!qp->sq.wqe_cnt && !qp->rq.wqe_cnt) + return -EINVAL; if (qp->sq.wqe_cnt) { err = create_raw_packet_qp_tis(dev, qp, sq, tdn, pd); if (err) diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 4e7fde86c96b..c29c1f7da4a1 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -310,12 +310,18 @@ int mlx5_ib_create_srq(struct ib_srq *ib_srq, srq->msrq.event = mlx5_ib_srq_event; srq->ibsrq.ext.xrc.srq_num = srq->msrq.srqn; - if (udata) - if (ib_copy_to_udata(udata, &srq->msrq.srqn, sizeof(__u32))) { + if (udata) { + struct mlx5_ib_create_srq_resp resp = { + .srqn = srq->msrq.srqn, + }; + + if (ib_copy_to_udata(udata, &resp, min(udata->outlen, + sizeof(resp)))) { mlx5_ib_dbg(dev, "copy to user failed\n"); err = -EFAULT; goto err_core; } + } init_attr->attr.max_wr = srq->msrq.max - 1; diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c index 8fc3630a9d4c..0224231a2e6f 100644 --- a/drivers/infiniband/hw/mlx5/srq_cmd.c +++ b/drivers/infiniband/hw/mlx5/srq_cmd.c @@ -83,11 +83,11 @@ struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn) struct mlx5_srq_table *table = &dev->srq_table; struct mlx5_core_srq *srq; - xa_lock(&table->array); + xa_lock_irq(&table->array); srq = xa_load(&table->array, srqn); if (srq) refcount_inc(&srq->common.refcount); - xa_unlock(&table->array); + xa_unlock_irq(&table->array); return srq; } diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 4494dab8c3d8..93040c994e2e 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -601,7 +601,7 @@ static int qedr_set_device_attr(struct qedr_dev *dev) qed_attr = dev->ops->rdma_query_device(dev->rdma_ctx); /* Part 2 - check capabilities */ - page_size = ~dev->attr.page_size_caps + 1; + page_size = ~qed_attr->page_size_caps + 1; if (page_size > PAGE_SIZE) { DP_ERR(dev, "Kernel PAGE_SIZE is %ld which is smaller than minimum page size (%d) required by qedr\n", diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h index 8e927f6c1520..ed56df319d2d 100644 --- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -349,10 +349,10 @@ struct qedr_srq_hwq_info { u32 wqe_prod; u32 sge_prod; u32 wr_prod_cnt; - u32 wr_cons_cnt; + atomic_t wr_cons_cnt; u32 num_elems; - u32 *virt_prod_pair_addr; + struct rdma_srq_producers *virt_prod_pair_addr; dma_addr_t phy_prod_pair_addr; }; diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 5e9732990be5..e521f3c3dbbf 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -150,8 +150,17 @@ qedr_iw_issue_event(void *context, if (params->cm_info) { event.ird = params->cm_info->ird; event.ord = params->cm_info->ord; - event.private_data_len = params->cm_info->private_data_len; - event.private_data = (void *)params->cm_info->private_data; + /* Only connect_request and reply have valid private data + * the rest of the events this may be left overs from + * connection establishment. CONNECT_REQUEST is issued via + * qedr_iw_mpa_request + */ + if (event_type == IW_CM_EVENT_CONNECT_REPLY) { + event.private_data_len = + params->cm_info->private_data_len; + event.private_data = + (void *)params->cm_info->private_data; + } } if (ep->cm_id) @@ -481,10 +490,10 @@ qedr_addr6_resolve(struct qedr_dev *dev, if ((!dst) || dst->error) { if (dst) { - dst_release(dst); DP_ERR(dev, "ip6_route_output returned dst->error = %d\n", dst->error); + dst_release(dst); } return -EINVAL; } @@ -727,7 +736,7 @@ int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) struct qedr_dev *dev = ep->dev; struct qedr_qp *qp; struct qed_iwarp_accept_in params; - int rc = 0; + int rc; DP_DEBUG(dev, QEDR_MSG_IWARP, "Accept on qpid=%d\n", conn_param->qpn); @@ -750,8 +759,10 @@ int qedr_iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) params.ord = conn_param->ord; if (test_and_set_bit(QEDR_IWARP_CM_WAIT_FOR_CONNECT, - &qp->iwarp_cm_flags)) + &qp->iwarp_cm_flags)) { + rc = -EINVAL; goto err; /* QP already destroyed */ + } rc = dev->ops->iwarp_accept(dev->rdma_ctx, ¶ms); if (rc) { diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 8b4240c1cc76..4408d3364664 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -2405,7 +2405,7 @@ int qedr_query_qp(struct ib_qp *ibqp, qp_attr->cap.max_recv_wr = qp->rq.max_wr; qp_attr->cap.max_send_sge = qp->sq.max_sges; qp_attr->cap.max_recv_sge = qp->rq.max_sges; - qp_attr->cap.max_inline_data = ROCE_REQ_MAX_INLINE_DATA_SIZE; + qp_attr->cap.max_inline_data = dev->attr.max_inline; qp_init_attr->cap = qp_attr->cap; qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; @@ -2518,6 +2518,8 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) if (rdma_protocol_iwarp(&dev->ibdev, 1)) qedr_iw_qp_rem_ref(&qp->ibqp); + else + kfree(qp); return 0; } @@ -3460,7 +3462,7 @@ static u32 qedr_srq_elem_left(struct qedr_srq_hwq_info *hw_srq) * count and consumer count and subtract it from max * work request supported so that we get elements left. */ - used = hw_srq->wr_prod_cnt - hw_srq->wr_cons_cnt; + used = hw_srq->wr_prod_cnt - (u32)atomic_read(&hw_srq->wr_cons_cnt); return hw_srq->max_wr - used; } @@ -3475,7 +3477,6 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, unsigned long flags; int status = 0; u32 num_sge; - u32 offset; spin_lock_irqsave(&srq->lock, flags); @@ -3488,7 +3489,8 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, if (!qedr_srq_elem_left(hw_srq) || wr->num_sge > srq->hw_srq.max_sges) { DP_ERR(dev, "Can't post WR (%d,%d) || (%d > %d)\n", - hw_srq->wr_prod_cnt, hw_srq->wr_cons_cnt, + hw_srq->wr_prod_cnt, + atomic_read(&hw_srq->wr_cons_cnt), wr->num_sge, srq->hw_srq.max_sges); status = -ENOMEM; *bad_wr = wr; @@ -3522,22 +3524,20 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, hw_srq->sge_prod++; } - /* Flush WQE and SGE information before + /* Update WQE and SGE information before * updating producer. */ - wmb(); + dma_wmb(); /* SRQ producer is 8 bytes. Need to update SGE producer index * in first 4 bytes and need to update WQE producer in * next 4 bytes. */ - *srq->hw_srq.virt_prod_pair_addr = hw_srq->sge_prod; - offset = offsetof(struct rdma_srq_producers, wqe_prod); - *((u8 *)srq->hw_srq.virt_prod_pair_addr + offset) = - hw_srq->wqe_prod; + srq->hw_srq.virt_prod_pair_addr->sge_prod = hw_srq->sge_prod; + /* Make sure sge producer is updated first */ + dma_wmb(); + srq->hw_srq.virt_prod_pair_addr->wqe_prod = hw_srq->wqe_prod; - /* Flush producer after updating it. */ - wmb(); wr = wr->next; } @@ -3956,7 +3956,7 @@ static int process_resp_one_srq(struct qedr_dev *dev, struct qedr_qp *qp, } else { __process_resp_one(dev, qp, cq, wc, resp, wr_id); } - srq->hw_srq.wr_cons_cnt++; + atomic_inc(&srq->hw_srq.wr_cons_cnt); return 1; } diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index d35465389357..d14ad523f96c 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -898,8 +898,6 @@ static void rvt_init_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp, qp->s_tail_ack_queue = 0; qp->s_acked_ack_queue = 0; qp->s_num_rd_atomic = 0; - if (qp->r_rq.kwq) - qp->r_rq.kwq->count = qp->r_rq.size; qp->r_sge.num_sge = 0; atomic_set(&qp->s_reserved_used, 0); } @@ -1196,7 +1194,7 @@ struct ib_qp *rvt_create_qp(struct ib_pd *ibpd, err = alloc_ud_wq_attr(qp, rdi->dparms.node); if (err) { ret = (ERR_PTR(err)); - goto bail_driver_priv; + goto bail_rq_rvt; } err = alloc_qpn(rdi, &rdi->qp_dev->qpn_table, @@ -1300,9 +1298,11 @@ bail_qpn: rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); bail_rq_wq: - rvt_free_rq(&qp->r_rq); free_ud_wq_attr(qp); +bail_rq_rvt: + rvt_free_rq(&qp->r_rq); + bail_driver_priv: rdi->driver_f.qp_priv_free(rdi, qp); @@ -2351,31 +2351,6 @@ bad_lkey: } /** - * get_count - count numbers of request work queue entries - * in circular buffer - * @rq: data structure for request queue entry - * @tail: tail indices of the circular buffer - * @head: head indices of the circular buffer - * - * Return - total number of entries in the circular buffer - */ -static u32 get_count(struct rvt_rq *rq, u32 tail, u32 head) -{ - u32 count; - - count = head; - - if (count >= rq->size) - count = 0; - if (count < tail) - count += rq->size - tail; - else - count -= tail; - - return count; -} - -/** * get_rvt_head - get head indices of the circular buffer * @rq: data structure for request queue entry * @ip: the QP @@ -2449,7 +2424,7 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) if (kwq->count < RVT_RWQ_COUNT_THRESHOLD) { head = get_rvt_head(rq, ip); - kwq->count = get_count(rq, tail, head); + kwq->count = rvt_get_rq_count(rq, head, tail); } if (unlikely(kwq->count == 0)) { ret = 0; @@ -2484,7 +2459,9 @@ int rvt_get_rwqe(struct rvt_qp *qp, bool wr_id_only) * the number of remaining WQEs. */ if (kwq->count < srq->limit) { - kwq->count = get_count(rq, tail, get_rvt_head(rq, ip)); + kwq->count = + rvt_get_rq_count(rq, + get_rvt_head(rq, ip), tail); if (kwq->count < srq->limit) { struct ib_event ev; diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c index 890d7b760d2e..27415185d862 100644 --- a/drivers/infiniband/sw/rdmavt/rc.c +++ b/drivers/infiniband/sw/rdmavt/rc.c @@ -127,9 +127,7 @@ __be32 rvt_compute_aeth(struct rvt_qp *qp) * not atomic, which is OK, since the fuzziness is * resolved as further ACKs go out. */ - credits = head - tail; - if ((int)credits < 0) - credits += qp->r_rq.size; + credits = rvt_get_rq_count(&qp->r_rq, head, tail); } /* * Binary search the credit table to find the code to diff --git a/drivers/infiniband/sw/rdmavt/vt.c b/drivers/infiniband/sw/rdmavt/vt.c index 18da1e1ea979..833f3f1b87f5 100644 --- a/drivers/infiniband/sw/rdmavt/vt.c +++ b/drivers/infiniband/sw/rdmavt/vt.c @@ -95,9 +95,7 @@ struct rvt_dev_info *rvt_alloc_device(size_t size, int nports) if (!rdi) return rdi; - rdi->ports = kcalloc(nports, - sizeof(struct rvt_ibport **), - GFP_KERNEL); + rdi->ports = kcalloc(nports, sizeof(*rdi->ports), GFP_KERNEL); if (!rdi->ports) ib_dealloc_device(&rdi->ibdev); diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index a8c11b5e1e94..de5f3efe9fcb 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -48,6 +48,8 @@ static void rxe_cleanup_ports(struct rxe_dev *rxe) } +bool rxe_initialized; + /* free resources for a rxe device all objects created for this device must * have been destroyed */ @@ -116,6 +118,8 @@ static void rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN; rxe->attr.max_pkeys = RXE_MAX_PKEYS; rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY; + addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid, + rxe->ndev->dev_addr); rxe->max_ucontext = RXE_MAX_UCONTEXT; } @@ -157,9 +161,6 @@ static int rxe_init_ports(struct rxe_dev *rxe) rxe_init_port_param(port); - if (!port->attr.pkey_tbl_len || !port->attr.gid_tbl_len) - return -EINVAL; - port->pkey_tbl = kcalloc(port->attr.pkey_tbl_len, sizeof(*port->pkey_tbl), GFP_KERNEL); @@ -358,6 +359,7 @@ static int __init rxe_module_init(void) return err; rdma_link_register(&rxe_link_ops); + rxe_initialized = true; pr_info("loaded\n"); return 0; } @@ -369,6 +371,7 @@ static void __exit rxe_module_exit(void) rxe_net_exit(); rxe_cache_exit(); + rxe_initialized = false; pr_info("unloaded\n"); } diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index fb07eed9e402..cae1b0a24c85 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -67,6 +67,8 @@ #define RXE_ROCE_V2_SPORT (0xc000) +extern bool rxe_initialized; + static inline u32 rxe_crc32(struct rxe_dev *rxe, u32 crc, void *next, size_t len) { diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index ea6a819b7167..ffbc50341a55 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -207,6 +207,7 @@ int rxe_mem_init_user(struct rxe_pd *pd, u64 start, vaddr = page_address(sg_page_iter_page(&sg_iter)); if (!vaddr) { pr_warn("null vaddr\n"); + ib_umem_release(umem); err = -ENOMEM; goto err1; } diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index e2c6d1cedf41..f85273883794 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -592,15 +592,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, int err; if (mask & IB_QP_MAX_QP_RD_ATOMIC) { - int max_rd_atomic = __roundup_pow_of_two(attr->max_rd_atomic); + int max_rd_atomic = attr->max_rd_atomic ? + roundup_pow_of_two(attr->max_rd_atomic) : 0; qp->attr.max_rd_atomic = max_rd_atomic; atomic_set(&qp->req.rd_atomic, max_rd_atomic); } if (mask & IB_QP_MAX_DEST_RD_ATOMIC) { - int max_dest_rd_atomic = - __roundup_pow_of_two(attr->max_dest_rd_atomic); + int max_dest_rd_atomic = attr->max_dest_rd_atomic ? + roundup_pow_of_two(attr->max_dest_rd_atomic) : 0; qp->attr.max_dest_rd_atomic = max_dest_rd_atomic; diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 831ad578a7b2..9bfb98056fc2 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -281,6 +281,8 @@ static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb) struct rxe_mc_elem *mce; struct rxe_qp *qp; union ib_gid dgid; + struct sk_buff *per_qp_skb; + struct rxe_pkt_info *per_qp_pkt; int err; if (skb->protocol == htons(ETH_P_IP)) @@ -309,31 +311,43 @@ static void rxe_rcv_mcast_pkt(struct rxe_dev *rxe, struct sk_buff *skb) if (err) continue; - /* if *not* the last qp in the list - * increase the users of the skb then post to the next qp + /* for all but the last qp create a new clone of the + * skb and pass to the qp. */ if (mce->qp_list.next != &mcg->qp_list) - skb_get(skb); + per_qp_skb = skb_clone(skb, GFP_ATOMIC); + else + per_qp_skb = skb; + + if (unlikely(!per_qp_skb)) + continue; - pkt->qp = qp; + per_qp_pkt = SKB_TO_PKT(per_qp_skb); + per_qp_pkt->qp = qp; rxe_add_ref(qp); - rxe_rcv_pkt(pkt, skb); + rxe_rcv_pkt(per_qp_pkt, per_qp_skb); } spin_unlock_bh(&mcg->mcg_lock); rxe_drop_ref(mcg); /* drop ref from rxe_pool_get_key. */ + return; + err1: kfree_skb(skb); } static int rxe_match_dgid(struct rxe_dev *rxe, struct sk_buff *skb) { + struct rxe_pkt_info *pkt = SKB_TO_PKT(skb); const struct ib_gid_attr *gid_attr; union ib_gid dgid; union ib_gid *pdgid; + if (pkt->mask & RXE_LOOPBACK_MASK) + return 0; + if (skb->protocol == htons(ETH_P_IP)) { ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, (struct in6_addr *)&dgid); @@ -366,7 +380,7 @@ void rxe_rcv(struct sk_buff *skb) if (unlikely(skb->len < pkt->offset + RXE_BTH_BYTES)) goto drop; - if (unlikely(rxe_match_dgid(rxe, skb) < 0)) { + if (rxe_match_dgid(rxe, skb) < 0) { pr_warn_ratelimited("failed matching dgid\n"); goto drop; } diff --git a/drivers/infiniband/sw/rxe/rxe_sysfs.c b/drivers/infiniband/sw/rxe/rxe_sysfs.c index ccda5f5a3bc0..2af31d421bfc 100644 --- a/drivers/infiniband/sw/rxe/rxe_sysfs.c +++ b/drivers/infiniband/sw/rxe/rxe_sysfs.c @@ -61,6 +61,11 @@ static int rxe_param_set_add(const char *val, const struct kernel_param *kp) struct net_device *ndev; struct rxe_dev *exists; + if (!rxe_initialized) { + pr_err("Module parameters are not supported, use rdma link add or rxe_cfg\n"); + return -EAGAIN; + } + len = sanitize_arg(val, intf, sizeof(intf)); if (!len) { pr_err("add: invalid interface name\n"); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 623129f27f5a..d1fe57ac87f5 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -679,6 +679,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, unsigned int mask; unsigned int length = 0; int i; + struct ib_send_wr *next; while (wr) { mask = wr_opcode_mask(wr->opcode, qp); @@ -695,6 +696,8 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, break; } + next = wr->next; + length = 0; for (i = 0; i < wr->num_sge; i++) length += wr->sg_list[i].length; @@ -705,7 +708,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, *bad_wr = wr; break; } - wr = wr->next; + wr = next; } rxe_run_task(&qp->req.task, 1); @@ -1075,7 +1078,7 @@ static ssize_t parent_show(struct device *device, struct rxe_dev *rxe = rdma_device_to_drv_device(device, struct rxe_dev, ib_dev); - return snprintf(buf, 16, "%s\n", rxe_parent_name(rxe, 1)); + return scnprintf(buf, PAGE_SIZE, "%s\n", rxe_parent_name(rxe, 1)); } static DEVICE_ATTR_RO(parent); diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 130b1e31b978..fb66d6757278 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -66,12 +66,13 @@ static int siw_device_register(struct siw_device *sdev, const char *name) static int dev_id = 1; int rv; + sdev->vendor_part_id = dev_id++; + rv = ib_register_device(base_dev, name); if (rv) { pr_warn("siw: device registration error %d\n", rv); return rv; } - sdev->vendor_part_id = dev_id++; siw_dbg(base_dev, "HWaddr=%pM\n", sdev->netdev->dev_addr); diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index c0a887240325..0520e70084f9 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -139,7 +139,8 @@ static int siw_rx_pbl(struct siw_rx_stream *srx, int *pbl_idx, break; bytes = min(bytes, len); - if (siw_rx_kva(srx, (void *)buf_addr, bytes) == bytes) { + if (siw_rx_kva(srx, (void *)(uintptr_t)buf_addr, bytes) == + bytes) { copied += bytes; offset += bytes; len -= bytes; diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 0e5f27caf2b2..50a355738609 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -515,7 +515,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev); int ipoib_ib_dev_open_default(struct net_device *dev); int ipoib_ib_dev_open(struct net_device *dev); -int ipoib_ib_dev_stop(struct net_device *dev); +void ipoib_ib_dev_stop(struct net_device *dev); void ipoib_ib_dev_up(struct net_device *dev); void ipoib_ib_dev_down(struct net_device *dev); int ipoib_ib_dev_stop_default(struct net_device *dev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index da3c5315bbb5..494f413dc3c6 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -670,13 +670,12 @@ int ipoib_send(struct net_device *dev, struct sk_buff *skb, return rc; } -static void __ipoib_reap_ah(struct net_device *dev) +static void ipoib_reap_dead_ahs(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah, *tah; unsigned long flags; - netif_tx_lock_bh(dev); + netif_tx_lock_bh(priv->dev); spin_lock_irqsave(&priv->lock, flags); list_for_each_entry_safe(ah, tah, &priv->dead_ahs, list) @@ -687,37 +686,37 @@ static void __ipoib_reap_ah(struct net_device *dev) } spin_unlock_irqrestore(&priv->lock, flags); - netif_tx_unlock_bh(dev); + netif_tx_unlock_bh(priv->dev); } void ipoib_reap_ah(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, ah_reap_task.work); - struct net_device *dev = priv->dev; - __ipoib_reap_ah(dev); + ipoib_reap_dead_ahs(priv); if (!test_bit(IPOIB_STOP_REAPER, &priv->flags)) queue_delayed_work(priv->wq, &priv->ah_reap_task, round_jiffies_relative(HZ)); } -static void ipoib_flush_ah(struct net_device *dev) +static void ipoib_start_ah_reaper(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); - - cancel_delayed_work(&priv->ah_reap_task); - flush_workqueue(priv->wq); - ipoib_reap_ah(&priv->ah_reap_task.work); + clear_bit(IPOIB_STOP_REAPER, &priv->flags); + queue_delayed_work(priv->wq, &priv->ah_reap_task, + round_jiffies_relative(HZ)); } -static void ipoib_stop_ah(struct net_device *dev) +static void ipoib_stop_ah_reaper(struct ipoib_dev_priv *priv) { - struct ipoib_dev_priv *priv = ipoib_priv(dev); - set_bit(IPOIB_STOP_REAPER, &priv->flags); - ipoib_flush_ah(dev); + cancel_delayed_work(&priv->ah_reap_task); + /* + * After ipoib_stop_ah_reaper() we always go through + * ipoib_reap_dead_ahs() which ensures the work is really stopped and + * does a final flush out of the dead_ah's list + */ } static int recvs_pending(struct net_device *dev) @@ -846,18 +845,6 @@ timeout: return 0; } -int ipoib_ib_dev_stop(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = ipoib_priv(dev); - - priv->rn_ops->ndo_stop(dev); - - clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); - ipoib_flush_ah(dev); - - return 0; -} - int ipoib_ib_dev_open_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -901,10 +888,7 @@ int ipoib_ib_dev_open(struct net_device *dev) return -1; } - clear_bit(IPOIB_STOP_REAPER, &priv->flags); - queue_delayed_work(priv->wq, &priv->ah_reap_task, - round_jiffies_relative(HZ)); - + ipoib_start_ah_reaper(priv); if (priv->rn_ops->ndo_open(dev)) { pr_warn("%s: Failed to open dev\n", dev->name); goto dev_stop; @@ -915,13 +899,20 @@ int ipoib_ib_dev_open(struct net_device *dev) return 0; dev_stop: - set_bit(IPOIB_STOP_REAPER, &priv->flags); - cancel_delayed_work(&priv->ah_reap_task); - set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); - ipoib_ib_dev_stop(dev); + ipoib_stop_ah_reaper(priv); return -1; } +void ipoib_ib_dev_stop(struct net_device *dev) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + priv->rn_ops->ndo_stop(dev); + + clear_bit(IPOIB_FLAG_INITIALIZED, &priv->flags); + ipoib_stop_ah_reaper(priv); +} + void ipoib_pkey_dev_check_presence(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -1232,7 +1223,7 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_mcast_dev_flush(dev); if (oper_up) set_bit(IPOIB_FLAG_OPER_UP, &priv->flags); - ipoib_flush_ah(dev); + ipoib_reap_dead_ahs(priv); } if (level >= IPOIB_FLUSH_NORMAL) @@ -1307,7 +1298,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) * the neighbor garbage collection is stopped and reaped. * That should all be done now, so make a final ah flush. */ - ipoib_stop_ah(dev); + ipoib_reap_dead_ahs(priv); clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 4fd095fd63b6..69ecf37053a8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1979,6 +1979,8 @@ static void ipoib_ndo_uninit(struct net_device *dev) /* no more works over the priv->wq */ if (priv->wq) { + /* See ipoib_mcast_carrier_on_task() */ + WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); flush_workqueue(priv->wq); destroy_workqueue(priv->wq); priv->wq = NULL; @@ -2461,6 +2463,8 @@ static struct net_device *ipoib_add_port(const char *format, /* call event handler to ensure pkey in sync */ queue_work(ipoib_workqueue, &priv->flush_heavy); + ndev->rtnl_link_ops = ipoib_get_link_ops(); + result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index 38c984d16996..d5a90a66b45c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -144,6 +144,16 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, return 0; } +static void ipoib_del_child_link(struct net_device *dev, struct list_head *head) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + if (!priv->parent) + return; + + unregister_netdevice_queue(dev, head); +} + static size_t ipoib_get_size(const struct net_device *dev) { return nla_total_size(2) + /* IFLA_IPOIB_PKEY */ @@ -158,6 +168,7 @@ static struct rtnl_link_ops ipoib_link_ops __read_mostly = { .priv_size = sizeof(struct ipoib_dev_priv), .setup = ipoib_setup_common, .newlink = ipoib_new_child_link, + .dellink = ipoib_del_child_link, .changelink = ipoib_changelink, .get_size = ipoib_get_size, .fill_info = ipoib_fill_info, diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index 8ac8e18fbe0c..58ca5e9c6079 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -192,6 +192,8 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) } priv = ipoib_priv(ndev); + ndev->rtnl_link_ops = ipoib_get_link_ops(); + result = __ipoib_vlan_add(ppriv, priv, pkey, IPOIB_LEGACY_CHILD); if (result && ndev->reg_state == NETREG_UNINITIALIZED) diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 2cc89a9b9e9b..ea8e611397a3 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -292,12 +292,27 @@ void iser_unreg_mem_fastreg(struct iscsi_iser_task *iser_task, { struct iser_device *device = iser_task->iser_conn->ib_conn.device; struct iser_mem_reg *reg = &iser_task->rdma_reg[cmd_dir]; + struct iser_fr_desc *desc; + struct ib_mr_status mr_status; - if (!reg->mem_h) + desc = reg->mem_h; + if (!desc) return; - device->reg_ops->reg_desc_put(&iser_task->iser_conn->ib_conn, - reg->mem_h); + /* + * The signature MR cannot be invalidated and reused without checking. + * libiscsi calls the check_protection transport handler only if + * SCSI-Response is received. And the signature MR is not checked if + * the task is completed for some other reason like a timeout or error + * handling. That's why we must check the signature MR here before + * putting it to the free pool. + */ + if (unlikely(desc->sig_protected)) { + desc->sig_protected = false; + ib_check_mr_status(desc->rsc.sig_mr, IB_MR_CHECK_SIG_STATUS, + &mr_status); + } + device->reg_ops->reg_desc_put(&iser_task->iser_conn->ib_conn, desc); reg->mem_h = NULL; } diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index a1a035270cab..71268d61d2b8 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -182,15 +182,15 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn) rx_desc = isert_conn->rx_descs; for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { - dma_addr = ib_dma_map_single(ib_dev, (void *)rx_desc, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + dma_addr = ib_dma_map_single(ib_dev, rx_desc->buf, + ISER_RX_SIZE, DMA_FROM_DEVICE); if (ib_dma_mapping_error(ib_dev, dma_addr)) goto dma_map_fail; rx_desc->dma_addr = dma_addr; rx_sg = &rx_desc->rx_sg; - rx_sg->addr = rx_desc->dma_addr; + rx_sg->addr = rx_desc->dma_addr + isert_get_hdr_offset(rx_desc); rx_sg->length = ISER_RX_PAYLOAD_SIZE; rx_sg->lkey = device->pd->local_dma_lkey; rx_desc->rx_cqe.done = isert_recv_done; @@ -202,7 +202,7 @@ dma_map_fail: rx_desc = isert_conn->rx_descs; for (j = 0; j < i; j++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); } kfree(isert_conn->rx_descs); isert_conn->rx_descs = NULL; @@ -223,7 +223,7 @@ isert_free_rx_descriptors(struct isert_conn *isert_conn) rx_desc = isert_conn->rx_descs; for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); } kfree(isert_conn->rx_descs); @@ -408,10 +408,9 @@ isert_free_login_buf(struct isert_conn *isert_conn) ISER_RX_PAYLOAD_SIZE, DMA_TO_DEVICE); kfree(isert_conn->login_rsp_buf); - ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, - DMA_FROM_DEVICE); - kfree(isert_conn->login_req_buf); + ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); + kfree(isert_conn->login_desc); } static int @@ -420,25 +419,25 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, { int ret; - isert_conn->login_req_buf = kzalloc(sizeof(*isert_conn->login_req_buf), + isert_conn->login_desc = kzalloc(sizeof(*isert_conn->login_desc), GFP_KERNEL); - if (!isert_conn->login_req_buf) + if (!isert_conn->login_desc) return -ENOMEM; - isert_conn->login_req_dma = ib_dma_map_single(ib_dev, - isert_conn->login_req_buf, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); - ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma); + isert_conn->login_desc->dma_addr = ib_dma_map_single(ib_dev, + isert_conn->login_desc->buf, + ISER_RX_SIZE, DMA_FROM_DEVICE); + ret = ib_dma_mapping_error(ib_dev, isert_conn->login_desc->dma_addr); if (ret) { - isert_err("login_req_dma mapping error: %d\n", ret); - isert_conn->login_req_dma = 0; - goto out_free_login_req_buf; + isert_err("login_desc dma mapping error: %d\n", ret); + isert_conn->login_desc->dma_addr = 0; + goto out_free_login_desc; } isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL); if (!isert_conn->login_rsp_buf) { ret = -ENOMEM; - goto out_unmap_login_req_buf; + goto out_unmap_login_desc; } isert_conn->login_rsp_dma = ib_dma_map_single(ib_dev, @@ -455,11 +454,11 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, out_free_login_rsp_buf: kfree(isert_conn->login_rsp_buf); -out_unmap_login_req_buf: - ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); -out_free_login_req_buf: - kfree(isert_conn->login_req_buf); +out_unmap_login_desc: + ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); +out_free_login_desc: + kfree(isert_conn->login_desc); return ret; } @@ -578,7 +577,7 @@ isert_connect_release(struct isert_conn *isert_conn) ib_destroy_qp(isert_conn->qp); } - if (isert_conn->login_req_buf) + if (isert_conn->login_desc) isert_free_login_buf(isert_conn); isert_device_put(device); @@ -964,17 +963,18 @@ isert_login_post_recv(struct isert_conn *isert_conn) int ret; memset(&sge, 0, sizeof(struct ib_sge)); - sge.addr = isert_conn->login_req_dma; + sge.addr = isert_conn->login_desc->dma_addr + + isert_get_hdr_offset(isert_conn->login_desc); sge.length = ISER_RX_PAYLOAD_SIZE; sge.lkey = isert_conn->device->pd->local_dma_lkey; isert_dbg("Setup sge: addr: %llx length: %d 0x%08x\n", sge.addr, sge.length, sge.lkey); - isert_conn->login_req_buf->rx_cqe.done = isert_login_recv_done; + isert_conn->login_desc->rx_cqe.done = isert_login_recv_done; memset(&rx_wr, 0, sizeof(struct ib_recv_wr)); - rx_wr.wr_cqe = &isert_conn->login_req_buf->rx_cqe; + rx_wr.wr_cqe = &isert_conn->login_desc->rx_cqe; rx_wr.sg_list = &sge; rx_wr.num_sge = 1; @@ -1051,7 +1051,7 @@ post_send: static void isert_rx_login_req(struct isert_conn *isert_conn) { - struct iser_rx_desc *rx_desc = isert_conn->login_req_buf; + struct iser_rx_desc *rx_desc = isert_conn->login_desc; int rx_buflen = isert_conn->login_req_len; struct iscsi_conn *conn = isert_conn->conn; struct iscsi_login *login = conn->conn_login; @@ -1063,7 +1063,7 @@ isert_rx_login_req(struct isert_conn *isert_conn) if (login->first_request) { struct iscsi_login_req *login_req = - (struct iscsi_login_req *)&rx_desc->iscsi_header; + (struct iscsi_login_req *)isert_get_iscsi_hdr(rx_desc); /* * Setup the initial iscsi_login values from the leading * login request PDU. @@ -1082,13 +1082,13 @@ isert_rx_login_req(struct isert_conn *isert_conn) login->tsih = be16_to_cpu(login_req->tsih); } - memcpy(&login->req[0], (void *)&rx_desc->iscsi_header, ISCSI_HDR_LEN); + memcpy(&login->req[0], isert_get_iscsi_hdr(rx_desc), ISCSI_HDR_LEN); size = min(rx_buflen, MAX_KEY_VALUE_PAIRS); isert_dbg("Using login payload size: %d, rx_buflen: %d " "MAX_KEY_VALUE_PAIRS: %d\n", size, rx_buflen, MAX_KEY_VALUE_PAIRS); - memcpy(login->req_buf, &rx_desc->data[0], size); + memcpy(login->req_buf, isert_get_data(rx_desc), size); if (login->first_request) { complete(&isert_conn->login_comp); @@ -1153,14 +1153,15 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn, if (imm_data_len != data_len) { sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE)); sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents, - &rx_desc->data[0], imm_data_len); + isert_get_data(rx_desc), imm_data_len); isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n", sg_nents, imm_data_len); } else { sg_init_table(&isert_cmd->sg, 1); cmd->se_cmd.t_data_sg = &isert_cmd->sg; cmd->se_cmd.t_data_nents = 1; - sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len); + sg_set_buf(&isert_cmd->sg, isert_get_data(rx_desc), + imm_data_len); isert_dbg("Transfer Immediate imm_data_len: %d\n", imm_data_len); } @@ -1229,9 +1230,9 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn, } isert_dbg("Copying DataOut: sg_start: %p, sg_off: %u " "sg_nents: %u from %p %u\n", sg_start, sg_off, - sg_nents, &rx_desc->data[0], unsol_data_len); + sg_nents, isert_get_data(rx_desc), unsol_data_len); - sg_copy_from_buffer(sg_start, sg_nents, &rx_desc->data[0], + sg_copy_from_buffer(sg_start, sg_nents, isert_get_data(rx_desc), unsol_data_len); rc = iscsit_check_dataout_payload(cmd, hdr, false); @@ -1290,7 +1291,7 @@ isert_handle_text_cmd(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd } cmd->text_in_ptr = text_in; - memcpy(cmd->text_in_ptr, &rx_desc->data[0], payload_length); + memcpy(cmd->text_in_ptr, isert_get_data(rx_desc), payload_length); return iscsit_process_text_cmd(conn, cmd, hdr); } @@ -1300,7 +1301,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc, uint32_t read_stag, uint64_t read_va, uint32_t write_stag, uint64_t write_va) { - struct iscsi_hdr *hdr = &rx_desc->iscsi_header; + struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc); struct iscsi_conn *conn = isert_conn->conn; struct iscsi_cmd *cmd; struct isert_cmd *isert_cmd; @@ -1398,8 +1399,8 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc) struct isert_conn *isert_conn = wc->qp->qp_context; struct ib_device *ib_dev = isert_conn->cm_id->device; struct iser_rx_desc *rx_desc = cqe_to_rx_desc(wc->wr_cqe); - struct iscsi_hdr *hdr = &rx_desc->iscsi_header; - struct iser_ctrl *iser_ctrl = &rx_desc->iser_header; + struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc); + struct iser_ctrl *iser_ctrl = isert_get_iser_hdr(rx_desc); uint64_t read_va = 0, write_va = 0; uint32_t read_stag = 0, write_stag = 0; @@ -1413,7 +1414,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc) rx_desc->in_use = true; ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); isert_dbg("DMA: 0x%llx, iSCSI opcode: 0x%02x, ITT: 0x%08x, flags: 0x%02x dlen: %d\n", rx_desc->dma_addr, hdr->opcode, hdr->itt, hdr->flags, @@ -1448,7 +1449,7 @@ isert_recv_done(struct ib_cq *cq, struct ib_wc *wc) read_stag, read_va, write_stag, write_va); ib_dma_sync_single_for_device(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); } static void @@ -1462,8 +1463,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } - ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); isert_conn->login_req_len = wc->byte_len - ISER_HEADERS_LEN; @@ -1478,8 +1479,8 @@ isert_login_recv_done(struct ib_cq *cq, struct ib_wc *wc) complete(&isert_conn->login_req_comp); mutex_unlock(&isert_conn->mutex); - ib_dma_sync_single_for_device(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ib_dma_sync_single_for_device(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); } static void diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 3b296bac4f60..d267a6d60d87 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -59,9 +59,11 @@ ISERT_MAX_TX_MISC_PDUS + \ ISERT_MAX_RX_MISC_PDUS) -#define ISER_RX_PAD_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \ - (ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \ - sizeof(struct ib_cqe) + sizeof(bool))) +/* + * RX size is default of 8k plus headers, but data needs to align to + * 512 boundary, so use 1024 to have the extra space for alignment. + */ +#define ISER_RX_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 1024) #define ISCSI_ISER_SG_TABLESIZE 256 @@ -80,21 +82,41 @@ enum iser_conn_state { }; struct iser_rx_desc { - struct iser_ctrl iser_header; - struct iscsi_hdr iscsi_header; - char data[ISCSI_DEF_MAX_RECV_SEG_LEN]; + char buf[ISER_RX_SIZE]; u64 dma_addr; struct ib_sge rx_sg; struct ib_cqe rx_cqe; bool in_use; - char pad[ISER_RX_PAD_SIZE]; -} __packed; +}; static inline struct iser_rx_desc *cqe_to_rx_desc(struct ib_cqe *cqe) { return container_of(cqe, struct iser_rx_desc, rx_cqe); } +static void *isert_get_iser_hdr(struct iser_rx_desc *desc) +{ + return PTR_ALIGN(desc->buf + ISER_HEADERS_LEN, 512) - ISER_HEADERS_LEN; +} + +static size_t isert_get_hdr_offset(struct iser_rx_desc *desc) +{ + return isert_get_iser_hdr(desc) - (void *)desc->buf; +} + +static void *isert_get_iscsi_hdr(struct iser_rx_desc *desc) +{ + return isert_get_iser_hdr(desc) + sizeof(struct iser_ctrl); +} + +static void *isert_get_data(struct iser_rx_desc *desc) +{ + void *data = isert_get_iser_hdr(desc) + ISER_HEADERS_LEN; + + WARN_ON((uintptr_t)data & 511); + return data; +} + struct iser_tx_desc { struct iser_ctrl iser_header; struct iscsi_hdr iscsi_header; @@ -141,9 +163,8 @@ struct isert_conn { u32 responder_resources; u32 initiator_depth; bool pi_support; - struct iser_rx_desc *login_req_buf; + struct iser_rx_desc *login_desc; char *login_rsp_buf; - u64 login_req_dma; int login_req_len; u64 login_rsp_dma; struct iser_rx_desc *rx_descs; |