From edf3f301db7af7e784d06f7059dfc8a69359af13 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Mon, 10 Jul 2017 18:45:41 +0300 Subject: IB/ipoib: Fix race between light events and interface restart A potential race between light_event and interface restart may attach multicast group to an already attached QP. Scenario: light_event flow goes through ipoib_mcast_dev_flush function, if a context switch occurs before calling ipoib_mcast_remove_list, then we may face a situation where the broadcast of the priv is null and the corresponding QP is not detached yet. If an "interface restart" runs during the previous context switch, the following scenario occurs: When the device goes up, ipoib_ib_dev_up function will be called, it will send a new registration request to the broadcast group and then attach the group to the QP that was not detached before. IPOIB_FLUSH_LIGHT INTERFACE RESTART __ipoib_ib_dev_flush | | | | | | | ipoib_mcast_dev_flush | Move mcast list and broadcast to remove_list | | | | | Context Switch--> | | ipoib_ib_dev_down | | | | | ipoib_ib_dev_up | | | | | ipoib_mcast_join_task | allocate new broadcast | | | | | Attach QP to multicast group | | | | | <--Context Switch ipoib_mcast_leave Detach QP from multicast group Signed-off-by: Feras Daoud Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib.h | 1 + drivers/infiniband/ulp/ipoib/ipoib_main.c | 1 + drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 2 ++ 3 files changed, 4 insertions(+) diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index ff50a7bd66d8..7ac25059c40f 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -336,6 +336,7 @@ struct ipoib_dev_priv { unsigned long flags; struct rw_semaphore vlan_rwsem; + struct mutex mcast_mutex; struct rb_root path_tree; struct list_head path_list; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 4ce315c92b48..144187b407bd 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1877,6 +1877,7 @@ static void ipoib_build_priv(struct net_device *dev) priv->dev = dev; spin_lock_init(&priv->lock); init_rwsem(&priv->vlan_rwsem); + mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 057f58e6afca..0a0b2ce45cbc 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -838,6 +838,7 @@ void ipoib_mcast_dev_flush(struct net_device *dev) struct ipoib_mcast *mcast, *tmcast; unsigned long flags; + mutex_lock(&priv->mcast_mutex); ipoib_dbg_mcast(priv, "flushing multicast list\n"); spin_lock_irqsave(&priv->lock, flags); @@ -865,6 +866,7 @@ void ipoib_mcast_dev_flush(struct net_device *dev) wait_for_completion(&mcast->done); ipoib_mcast_remove_list(&remove_list); + mutex_unlock(&priv->mcast_mutex); } static int ipoib_mcast_addr_is_valid(const u8 *addr, const u8 *broadcast) -- cgit v1.2.3 From 6bdc8de2e86e717124a715ecc480892a2c331ff5 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Wed, 12 Jul 2017 10:40:25 +0300 Subject: IB/ipoib: Use cancel_delayed_work_sync when needed The work mcast_task can re-queue itself, so instead of doing cancel && flush_workqueue, that still can leave a queued task on the air, use cancel_delayed_work_sync. Also, no need to use lock over the cancel, the original lock was due to bit assignment setting (IPOIB_MCAST_RUN) that is not in use anymore. Signed-off-by: Erez Shitrit Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 0a0b2ce45cbc..f80bf0f5d7cf 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -684,15 +684,10 @@ void ipoib_mcast_start_thread(struct net_device *dev) int ipoib_mcast_stop_thread(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); - unsigned long flags; ipoib_dbg_mcast(priv, "stopping multicast thread\n"); - spin_lock_irqsave(&priv->lock, flags); - cancel_delayed_work(&priv->mcast_task); - spin_unlock_irqrestore(&priv->lock, flags); - - flush_workqueue(priv->wq); + cancel_delayed_work_sync(&priv->mcast_task); return 0; } -- cgit v1.2.3 From a08e1120627f72e9ed7c291e3b9f8dd29c1513ab Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Wed, 12 Jul 2017 13:11:54 +0300 Subject: IB/ipoib: Make sure no in-flight joins while leaving that mcast While cleaning neighs and there is a send-only mcast neigh, the driver should wait to finish its join process before trying to remove it. Without this patch, we will see messages like: "ipoib_mcast_leave on an in-flight join" and unexpected results in the join_complete. Signed-off-by: Erez Shitrit Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index f80bf0f5d7cf..93e149efc1f5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -743,6 +743,14 @@ void ipoib_mcast_remove_list(struct list_head *remove_list) { struct ipoib_mcast *mcast, *tmcast; + /* + * make sure the in-flight joins have finished before we attempt + * to leave + */ + list_for_each_entry_safe(mcast, tmcast, remove_list, list) + if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) + wait_for_completion(&mcast->done); + list_for_each_entry_safe(mcast, tmcast, remove_list, list) { ipoib_mcast_leave(mcast->dev, mcast); ipoib_mcast_free(mcast); @@ -852,14 +860,6 @@ void ipoib_mcast_dev_flush(struct net_device *dev) spin_unlock_irqrestore(&priv->lock, flags); - /* - * make sure the in-flight joins have finished before we attempt - * to leave - */ - list_for_each_entry_safe(mcast, tmcast, &remove_list, list) - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) - wait_for_completion(&mcast->done); - ipoib_mcast_remove_list(&remove_list); mutex_unlock(&priv->mcast_mutex); } @@ -979,14 +979,6 @@ void ipoib_mcast_restart_task(struct work_struct *work) netif_addr_unlock(dev); local_irq_restore(flags); - /* - * make sure the in-flight joins have finished before we attempt - * to leave - */ - list_for_each_entry_safe(mcast, tmcast, &remove_list, list) - if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) - wait_for_completion(&mcast->done); - ipoib_mcast_remove_list(&remove_list); /* -- cgit v1.2.3 From 11f74b40359b19f760964e71d04882a6caf530cc Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Thu, 13 Jul 2017 11:27:12 +0300 Subject: IB/ipoib: Prevent setting negative values to max_nonsrq_conn_qp Don't allow negative values to max_nonsrq_conn_qp. There is no functional impact on a negative value but it is logicically incorrect. Fixes: 68e995a29572 ("IPoIB/cm: Add connected mode support for devices without SRQs") Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 144187b407bd..8b7ec15a9d6e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2366,6 +2366,7 @@ static int __init ipoib_init_module(void) ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); + ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* -- cgit v1.2.3 From d2e46fccc3e3d73a741efe433f00960331280696 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Sun, 16 Jul 2017 11:33:01 +0300 Subject: IB/ipoib: Set IPOIB_NEIGH_TBL_FLUSH after flushed completion initialization Set IPOIB_NEIGH_TBL_FLUSH bit after initializing the neighbor flushed completion, otherwise the garbage collector may signal a completion while it is not initialized yet. Fixes: b63b70d87741 ("IPoIB: Use a private hash table for path lookup in xmit path") Signed-off-by: Feras Daoud Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 8b7ec15a9d6e..f4403c52cd67 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1560,6 +1560,7 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); + set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); @@ -1604,7 +1605,6 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev) ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n"); init_completion(&priv->ntbl.deleted); - set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); /* Stop GC if called at init fail need to cancel work */ stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags); -- cgit v1.2.3 From 4829d964dfb027558c732cfa0d13b716ab3f0838 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Mon, 10 Jul 2017 18:12:43 +0300 Subject: IB/ipoib: Add multicast packets statistics Update the multicast counter when multicast packets are received and provide this information through ethtool support. Signed-off-by: Alex Vesker Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_ethtool.c | 3 ++- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c index 7871379342f4..184a22f48027 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c @@ -52,7 +52,8 @@ static const struct ipoib_stats ipoib_gstrings_stats[] = { IPOIB_NETDEV_STAT(tx_bytes), IPOIB_NETDEV_STAT(tx_errors), IPOIB_NETDEV_STAT(rx_dropped), - IPOIB_NETDEV_STAT(tx_dropped) + IPOIB_NETDEV_STAT(tx_dropped), + IPOIB_NETDEV_STAT(multicast), }; #define IPOIB_GLOBAL_STATS_LEN ARRAY_SIZE(ipoib_gstrings_stats) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 57a9655e844d..02eda1f53a67 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -256,6 +256,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) ++dev->stats.rx_packets; dev->stats.rx_bytes += skb->len; + if (skb->pkt_type == PACKET_MULTICAST) + dev->stats.multicast++; skb->dev = dev; if ((dev->features & NETIF_F_RXCSUM) && -- cgit v1.2.3 From eb54714ddcb2462d4d4b8aa78d028b61e217a835 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Sun, 2 Jul 2017 15:05:59 +0300 Subject: IB/ipoib: Add get statistics support to SRIOV VF Add SRIOV VF support to get traffic statistics. Signed-off-by: Feras Daoud Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index f4403c52cd67..24fa87fe0952 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1847,6 +1847,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, + .ndo_get_stats64 = ipoib_get_stats, }; void ipoib_setup_common(struct net_device *dev) -- cgit v1.2.3 From dc892e17bbae670a3d7aa6ab8bd1033b15b24645 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 13 Jul 2017 13:34:19 +0300 Subject: IB/ipoib: Clean error paths in add port Refactor error paths in ipoib_add_port() function. The code flow ensures that the function terminates on every error flow and it makes redundant all "else" cases. The functions are called during the flow are returning "result < 0", in case of error, so there is no need to check it explicitly. Fixes: 58e9cc90cda7 ("IB/IPoIB: Fix bad error flow in ipoib_add_port()") Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 24fa87fe0952..6c77df34869d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2175,14 +2175,14 @@ static struct net_device *ipoib_add_port(const char *format, priv->dev->dev_id = port - 1; result = ib_query_port(hca, port, &attr); - if (!result) - priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu); - else { + if (result) { printk(KERN_WARNING "%s: ib_query_port %d failed\n", hca->name, port); goto device_init_failed; } + priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu); + /* MTU will be reset when mcast join happens */ priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = priv->dev->mtu; @@ -2213,12 +2213,14 @@ static struct net_device *ipoib_add_port(const char *format, printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n", hca->name, port, result); goto device_init_failed; - } else - memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid)); + } + + memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, + sizeof(union ib_gid)); set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); result = ipoib_dev_init(priv->dev, hca, port); - if (result < 0) { + if (result) { printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n", hca->name, port, result); goto device_init_failed; -- cgit v1.2.3 From 1b355094b308f3377c8f574ce86135ee159c6285 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sat, 15 Jul 2017 16:26:55 +0300 Subject: IB/ipoib: Remove double pointer assigning There is no need to assign "p" pointer twice. This patch fixes the following smatch warning: drivers/infiniband/ulp/ipoib/ipoib_cm.c:517 ipoib_cm_rx_handler() warn: missing break? reassigning 'p->id' Fixes: 839fcaba355a ("IPoIB: Connected mode experimental support") Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index f87d104837dc..d69410c2ed97 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -511,7 +511,6 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id, case IB_CM_REQ_RECEIVED: return ipoib_cm_req_handler(cm_id, event); case IB_CM_DREQ_RECEIVED: - p = cm_id->context; ib_send_cm_drep(cm_id, NULL, 0); /* Fall through */ case IB_CM_REJ_RECEIVED: -- cgit v1.2.3 From b287b76e89503ef1d403cc5cc8bd74b035d25bfa Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 23 Jul 2017 10:46:14 +0300 Subject: Revert "IB/core: Allow QP state transition from reset to error" The commit ebc9ca43e1d5 ("IB/core: Allow QP state transition from reset to error") allowed transition from Reset to Error state for the QPs. This behavior doesn't follow the IBTA specification 1.3, which in 10.3.1 QUEUE PAIR AND EE CONTEXT STATES section. The quote from the spec: "An error can be forced from any state, except Reset, with the Modify QP/EE Verb." Signed-off-by: Leon Romanovsky --- drivers/infiniband/core/verbs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index fb98ed67d5bc..7f8fe443df46 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -895,7 +895,6 @@ static const struct { } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = { [IB_QPS_RESET] = { [IB_QPS_RESET] = { .valid = 1 }, - [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_INIT] = { .valid = 1, .req_param = { -- cgit v1.2.3 From 5dc78ad1904db597bdb4427f3ead437aae86f54c Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Thu, 13 Jul 2017 14:29:08 +0300 Subject: IB/ipoib: Notify on modify QP failure only when relevant Modify QP can fail and it can be acceptable, like when moving from RST to ERR state, all the rest are not acceptable and a message to the log should be printed. The current code prints on all failures and many messages like: "Failed to modify QP to ERROR state" appear, even when supported by the state machine of the QP object. Signed-off-by: Erez Shitrit Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/ipoib/ipoib_ib.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 02eda1f53a67..2e075377242e 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -711,6 +711,27 @@ static int recvs_pending(struct net_device *dev) return pending; } +static void check_qp_movement_and_print(struct ipoib_dev_priv *priv, + struct ib_qp *qp, + enum ib_qp_state new_state) +{ + struct ib_qp_attr qp_attr; + struct ib_qp_init_attr query_init_attr; + int ret; + + ret = ib_query_qp(qp, &qp_attr, IB_QP_STATE, &query_init_attr); + if (ret) { + ipoib_warn(priv, "%s: Failed to query QP\n", __func__); + return; + } + /* print according to the new-state and the previous state.*/ + if (new_state == IB_QPS_ERR && qp_attr.qp_state == IB_QPS_RESET) + ipoib_dbg(priv, "Failed modify QP, IB_QPS_RESET to IB_QPS_ERR, acceptable\n"); + else + ipoib_warn(priv, "Failed to modify QP to state: %d from state: %d\n", + new_state, qp_attr.qp_state); +} + int ipoib_ib_dev_stop_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -730,7 +751,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev) */ qp_attr.qp_state = IB_QPS_ERR; if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE)) - ipoib_warn(priv, "Failed to modify QP to ERROR state\n"); + check_qp_movement_and_print(priv, priv->qp, IB_QPS_ERR); /* Wait for all sends and receives to complete */ begin = jiffies; -- cgit v1.2.3