From df7fba66471c6bbbaebb55e1bb3658eb7ce00a9b Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Fri, 3 Aug 2012 08:26:45 +0000 Subject: IB/mlx4: Fix possible deadlock on sm_lock spinlock The sm_lock spinlock is taken in the process context by mlx4_ib_modify_device, and in the interrupt context by update_sm_ah, so we need to take that spinlock with irqsave, and release it with irqrestore. Lockdeps reports this as follows: [ INFO: inconsistent lock state ] 3.5.0+ #20 Not tainted inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. swapper/0/0 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&ibdev->sm_lock)->rlock){?.+...}, at: [] update_sm_ah+0xad/0x100 [mlx4_ib] {HARDIRQ-ON-W} state was registered at: [] mark_irqflags+0x120/0x190 [] __lock_acquire+0x307/0x4c0 [] lock_acquire+0xb1/0x150 [] _raw_spin_lock+0x41/0x50 [] mlx4_ib_modify_device+0x63/0x240 [mlx4_ib] [] ib_modify_device+0x1c/0x20 [ib_core] [] set_node_desc+0x83/0xc0 [ib_core] [] dev_attr_store+0x20/0x30 [] sysfs_write_file+0xe6/0x170 [] vfs_write+0xc8/0x190 [] sys_write+0x51/0x90 [] system_call_fastpath+0x16/0x1b ... *** DEADLOCK *** 1 lock held by swapper/0/0: stack backtrace: Pid: 0, comm: swapper/0 Not tainted 3.5.0+ #20 Call Trace: [] print_usage_bug+0x18a/0x190 [] ? print_irq_inversion_bug+0x210/0x210 [] mark_lock_irq+0xf2/0x280 [] mark_lock+0x150/0x240 [] mark_irqflags+0x16f/0x190 [] __lock_acquire+0x307/0x4c0 [] ? update_sm_ah+0xad/0x100 [mlx4_ib] [] lock_acquire+0xb1/0x150 [] ? update_sm_ah+0xad/0x100 [mlx4_ib] [] _raw_spin_lock+0x41/0x50 [] ? update_sm_ah+0xad/0x100 [mlx4_ib] [] ? ib_create_ah+0x1a/0x40 [ib_core] [] update_sm_ah+0xad/0x100 [mlx4_ib] [] ? is_module_address+0x23/0x30 [] handle_port_mgmt_change_event+0xeb/0x150 [mlx4_ib] [] mlx4_ib_event+0x117/0x160 [mlx4_ib] [] ? _raw_spin_lock_irqsave+0x61/0x70 [] mlx4_dispatch_event+0x6c/0x90 [mlx4_core] [] mlx4_eq_int+0x500/0x950 [mlx4_core] Reported by: Or Gerlitz Tested-by: Bart Van Assche Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/mad.c | 16 ++++++++++------ drivers/infiniband/hw/mlx4/main.c | 5 +++-- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'drivers/infiniband/hw') diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index c27141fef1ab..9c2ae7efd00f 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -125,6 +125,7 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl) { struct ib_ah *new_ah; struct ib_ah_attr ah_attr; + unsigned long flags; if (!dev->send_agent[port_num - 1][0]) return; @@ -139,11 +140,11 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl) if (IS_ERR(new_ah)) return; - spin_lock(&dev->sm_lock); + spin_lock_irqsave(&dev->sm_lock, flags); if (dev->sm_ah[port_num - 1]) ib_destroy_ah(dev->sm_ah[port_num - 1]); dev->sm_ah[port_num - 1] = new_ah; - spin_unlock(&dev->sm_lock); + spin_unlock_irqrestore(&dev->sm_lock, flags); } /* @@ -197,13 +198,15 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad, static void node_desc_override(struct ib_device *dev, struct ib_mad *mad) { + unsigned long flags; + if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED || mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) && mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP && mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) { - spin_lock(&to_mdev(dev)->sm_lock); + spin_lock_irqsave(&to_mdev(dev)->sm_lock, flags); memcpy(((struct ib_smp *) mad)->data, dev->node_desc, 64); - spin_unlock(&to_mdev(dev)->sm_lock); + spin_unlock_irqrestore(&to_mdev(dev)->sm_lock, flags); } } @@ -213,6 +216,7 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma struct ib_mad_send_buf *send_buf; struct ib_mad_agent *agent = dev->send_agent[port_num - 1][qpn]; int ret; + unsigned long flags; if (agent) { send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR, @@ -225,13 +229,13 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma * wrong following the IB spec strictly, but we know * it's OK for our devices). */ - spin_lock(&dev->sm_lock); + spin_lock_irqsave(&dev->sm_lock, flags); memcpy(send_buf->mad, mad, sizeof *mad); if ((send_buf->ah = dev->sm_ah[port_num - 1])) ret = ib_post_send_mad(send_buf, NULL); else ret = -EINVAL; - spin_unlock(&dev->sm_lock); + spin_unlock_irqrestore(&dev->sm_lock, flags); if (ret) ib_free_send_mad(send_buf); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index fe2088cfa6ee..cc05579ebce7 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -423,6 +423,7 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask, struct ib_device_modify *props) { struct mlx4_cmd_mailbox *mailbox; + unsigned long flags; if (mask & ~IB_DEVICE_MODIFY_NODE_DESC) return -EOPNOTSUPP; @@ -430,9 +431,9 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask, if (!(mask & IB_DEVICE_MODIFY_NODE_DESC)) return 0; - spin_lock(&to_mdev(ibdev)->sm_lock); + spin_lock_irqsave(&to_mdev(ibdev)->sm_lock, flags); memcpy(ibdev->node_desc, props->node_desc, 64); - spin_unlock(&to_mdev(ibdev)->sm_lock); + spin_unlock_irqrestore(&to_mdev(ibdev)->sm_lock, flags); /* * If possible, pass node desc to FW, so it can generate -- cgit v1.2.1 From d549f55f2e132e3d1f1288ce4231f45f12988bbf Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Fri, 10 Aug 2012 16:52:13 -0700 Subject: RDMA/ocrdma: Don't call vlan_dev_real_dev() for non-VLAN netdevs If CONFIG_VLAN_8021Q is not set, then vlan_dev_real_dev() just goes BUG(), so we shouldn't call it unless we're actually dealing with a VLAN netdev. Reported-by: Fengguang Wu Signed-off-by: Roland Dreier --- drivers/infiniband/hw/ocrdma/ocrdma_main.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'drivers/infiniband/hw') diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 5a044526e4f4..c4e0131f1b57 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -161,7 +161,7 @@ static void ocrdma_add_default_sgid(struct ocrdma_dev *dev) ocrdma_get_guid(dev, &sgid->raw[8]); } -#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) +#if IS_ENABLED(CONFIG_VLAN_8021Q) static void ocrdma_add_vlan_sgids(struct ocrdma_dev *dev) { struct net_device *netdev, *tmp; @@ -202,14 +202,13 @@ static int ocrdma_build_sgid_tbl(struct ocrdma_dev *dev) return 0; } -#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_VLAN_8021Q) +#if IS_ENABLED(CONFIG_IPV6) static int ocrdma_inet6addr_event(struct notifier_block *notifier, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr; - struct net_device *event_netdev = ifa->idev->dev; - struct net_device *netdev = NULL; + struct net_device *netdev = ifa->idev->dev; struct ib_event gid_event; struct ocrdma_dev *dev; bool found = false; @@ -217,11 +216,12 @@ static int ocrdma_inet6addr_event(struct notifier_block *notifier, bool is_vlan = false; u16 vid = 0; - netdev = vlan_dev_real_dev(event_netdev); - if (netdev != event_netdev) { - is_vlan = true; - vid = vlan_dev_vlan_id(event_netdev); + is_vlan = netdev->priv_flags & IFF_802_1Q_VLAN; + if (is_vlan) { + vid = vlan_dev_vlan_id(netdev); + netdev = vlan_dev_real_dev(netdev); } + rcu_read_lock(); list_for_each_entry_rcu(dev, &ocrdma_dev_list, entry) { if (dev->nic_info.netdev == netdev) { -- cgit v1.2.1 From 142ad5db2b29a1c392e1b14934fae5d161d6c6e7 Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Fri, 10 Aug 2012 00:07:58 +0000 Subject: IB: Fix typos in infiniband drivers Correct spelling typos in comments in drivers/infiniband. Signed-off-by: Masanari Iida Signed-off-by: Roland Dreier --- drivers/infiniband/hw/amso1100/c2_rnic.c | 2 +- drivers/infiniband/hw/cxgb3/iwch_cm.c | 2 +- drivers/infiniband/hw/qib/qib_sd7220.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/infiniband/hw') diff --git a/drivers/infiniband/hw/amso1100/c2_rnic.c b/drivers/infiniband/hw/amso1100/c2_rnic.c index 8c81992fa6db..e4a73158fc7f 100644 --- a/drivers/infiniband/hw/amso1100/c2_rnic.c +++ b/drivers/infiniband/hw/amso1100/c2_rnic.c @@ -439,7 +439,7 @@ static int c2_rnic_close(struct c2_dev *c2dev) /* * Called by c2_probe to initialize the RNIC. This principally - * involves initalizing the various limits and resouce pools that + * involves initializing the various limits and resource pools that * comprise the RNIC instance. */ int __devinit c2_rnic_init(struct c2_dev *c2dev) diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index 77b6b182778a..aaf88ef9409c 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -1680,7 +1680,7 @@ static int close_con_rpl(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) * T3A does 3 things when a TERM is received: * 1) send up a CPL_RDMA_TERMINATE message with the TERM packet * 2) generate an async event on the QP with the TERMINATE opcode - * 3) post a TERMINATE opcde cqe into the associated CQ. + * 3) post a TERMINATE opcode cqe into the associated CQ. * * For (1), we save the message in the qp for later consumer consumption. * For (2), we move the QP into TERMINATE, post a QP event and disconnect. diff --git a/drivers/infiniband/hw/qib/qib_sd7220.c b/drivers/infiniband/hw/qib/qib_sd7220.c index a322d5171a2c..50a8a0d4fe67 100644 --- a/drivers/infiniband/hw/qib/qib_sd7220.c +++ b/drivers/infiniband/hw/qib/qib_sd7220.c @@ -372,7 +372,7 @@ static void qib_sd_trimdone_monitor(struct qib_devdata *dd, /* Read CTRL reg for each channel to check TRIMDONE */ if (baduns & (1 << chn)) { qib_dev_err(dd, - "Reseting TRIMDONE on chn %d (%s)\n", + "Resetting TRIMDONE on chn %d (%s)\n", chn, where); ret = qib_sd7220_reg_mod(dd, IB_7220_SERDES, IB_CTRL2(chn), 0x10, 0x10); -- cgit v1.2.1 From 51fa3ca37e3bebb291dbe50faa3cb259af35e978 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Tue, 14 Aug 2012 12:58:35 +0000 Subject: IB/qib: Fix error return code in qib_init_7322_variables() Convert a 0 error return code to a negative one, as returned elsewhere in the function. A simplified version of the semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // @@ identifier ret; expression e,e1,e2,e3,e4,x; @@ ( if (\(ret != 0\|ret < 0\) || ...) { ... return ...; } | ret = 0 ) ... when != ret = e1 *x = \(kmalloc\|kzalloc\|kcalloc\|devm_kzalloc\|ioremap\|ioremap_nocache\|devm_ioremap\|devm_ioremap_nocache\)(...); ... when != x = e2 when != ret = e3 *if (x == NULL || ...) { ... when != ret = e4 * return ret; } // Signed-off-by: Julia Lawall Acked-by: Mike Marciniszyn Signed-off-by: Roland Dreier --- drivers/infiniband/hw/qib/qib_iba7322.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/hw') diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 0d7280af99bc..3f6b21e9dc11 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -6346,8 +6346,10 @@ static int qib_init_7322_variables(struct qib_devdata *dd) dd->piobcnt4k * dd->align4k; dd->piovl15base = ioremap_nocache(vl15off, NUM_VL15_BUFS * dd->align4k); - if (!dd->piovl15base) + if (!dd->piovl15base) { + ret = -ENOMEM; goto bail; + } } qib_7322_set_baseaddrs(dd); /* set chip access pointers now */ -- cgit v1.2.1 From a0675a386a3a68f71e831bd064082e6717b45fdc Mon Sep 17 00:00:00 2001 From: Kleber Sacilotto de Souza Date: Fri, 10 Aug 2012 18:25:34 +0000 Subject: IB/mlx4: Check iboe netdev pointer before dereferencing it Unlike other parts of the mlx4_ib code, the function build_mlx_header() doesn't check if the iboe netdev of the given port is valid before dereferencing it, which can cause a crash if the ethernet interface has already been taken down. Fix this by checking for a valid netdev pointer before using it to get the port MAC address. Signed-off-by: Kleber Sacilotto de Souza Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/qp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband/hw') diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index a6d8ea060ea8..f585eddef4b7 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1407,6 +1407,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, struct mlx4_wqe_mlx_seg *mlx = wqe; struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx; struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah); + struct net_device *ndev; union ib_gid sgid; u16 pkey; int send_size; @@ -1483,7 +1484,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6); /* FIXME: cache smac value? */ - smac = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1]->dev_addr; + ndev = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1]; + if (!ndev) + return -ENODEV; + smac = ndev->dev_addr; memcpy(sqp->ud_header.eth.smac_h, smac, 6); if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6)) mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); -- cgit v1.2.1