GIT e23e865e5b7ce22b5d14f2b5a2e478dc15610f01 git+ssh://master.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git#for-mm commit Author: Sean Hefty Date: Wed Oct 4 11:37:25 2006 -0700 IB/cm: Send DREP in response to unmatched DREQ Currently a DREP is only sent in response to a DREQ if a connection has been found matching the DREQ, and it is in the proper state. Once a DREP is sent, the local connection moves into timewait. Duplicate DREQs received while in this state result in re-sending the DREP. However, it's likely that the local connection will enter and exit timewait before the remote side times out a lost DREP and resends a DREQ. To handle this, we send a DREP in response to a DREQ, even if a local connection is not found. This avoids maintaining disconnected id's in timewait states for excessively long times, just to handle a lost DREP. Signed-off-by: Sean Hefty Signed-off-by: Roland Dreier commit 2dc5a620ebdf804d0b97008c16c47e92d93d3348 Author: Sean Hefty Date: Wed Oct 4 11:29:59 2006 -0700 IB/cm: Fix timewait crash after module unload If the ib_cm module is unloaded while id's are still in timewait, the CM will destroy the work queue used to process timewait. Once the id's exit timewait, their timers will fire, leading to a crash trying to access the destroyed work queue. We need to track id's that are in timewait, and cancel their deferred work on module unload. Signed-off-by: Sean Hefty Signed-off-by: Roland Dreier commit d4f62f67fa8122cf103c50b5a5e4dfc4b7dde83d Author: Jack Morgenstein Date: Wed Oct 4 13:56:34 2006 +0200 IB/mthca: query port fix Fill in "max_vl_num" (encoded according to VLCap field in the PortInfo MAD), and "init_type_reply" values in the ib_query_port verb. Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier commit 2d3e46fb802de94900e2966d82785ed14d6c9a03 Author: Ishai Rabinovitz Date: Wed Oct 4 15:28:56 2006 +0200 IB/srp: enable multiple connections to the same target Enable multiple concurrent connections to the same SRP target: 1) Use port GUID instead of node GUID in the initiator port identifier. This allows connections to be made from multiple HCA ports at the same time. 2) Let the user specify the identifier extention when adding the device. This allows userspace to make multiple connections even from the same port, if it wants too. Without this, only one connection can be made from any given HCA, even if it has multiple ports, because we don't use multi-channel mode, so targets will only allow one connection from a given initiator port ID. Signed-off-by: Ishai Rabinovitz Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier commit 9cb454f4203628ac10aefce0d98cdb9c65f9a6a7 Author: Ishai Rabinovitz Date: Wed Oct 4 15:24:32 2006 -0700 IB/srp: Remove redundant memset() scsi_host_alloc() already allocates with kzalloc(), so the struct Scsi_Host is zeroed out, including the private data portion. Remove the redundant memset that zeros this out again in the SRP initiator. Signed-off-by: Ishai Rabinovitz Signed-off-by: Roland Dreier commit c039f264d4b024518966e179f03a2c8a85c1ae54 Author: Tom Tucker Date: Tue Oct 3 09:46:41 2006 -0500 RDMA/amso1100: Add spinlocks to serialize ib_post_send/ib_post_recv The AMSO driver was not thread-safe in the post WR code and had code that would sleep if the WR post FIFO was full. Since these functions can be called on interrupt level I changed the sleep to a udelay. Signed-off-by: Tom Tucker Signed-off-by: Roland Dreier drivers/infiniband/core/cm.c | 84 ++++++++++++++++++++------ drivers/infiniband/hw/amso1100/c2_qp.c | 16 ++++- drivers/infiniband/hw/mthca/mthca_provider.c | 2 + drivers/infiniband/ulp/srp/ib_srp.c | 20 ++++-- drivers/infiniband/ulp/srp/ib_srp.h | 2 - 5 files changed, 93 insertions(+), 31 deletions(-) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index f35fcc4..25b1018 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -75,6 +75,7 @@ static struct ib_cm { struct rb_root remote_sidr_table; struct idr local_id_table; __be32 random_id_operand; + struct list_head timewait_list; struct workqueue_struct *wq; } cm; @@ -112,6 +113,7 @@ struct cm_work { struct cm_timewait_info { struct cm_work work; /* Must be first. */ + struct list_head list; struct rb_node remote_qp_node; struct rb_node remote_id_node; __be64 remote_ca_guid; @@ -647,13 +649,6 @@ static inline int cm_convert_to_ms(int i static void cm_cleanup_timewait(struct cm_timewait_info *timewait_info) { - unsigned long flags; - - if (!timewait_info->inserted_remote_id && - !timewait_info->inserted_remote_qp) - return; - - spin_lock_irqsave(&cm.lock, flags); if (timewait_info->inserted_remote_id) { rb_erase(&timewait_info->remote_id_node, &cm.remote_id_table); timewait_info->inserted_remote_id = 0; @@ -663,7 +658,6 @@ static void cm_cleanup_timewait(struct c rb_erase(&timewait_info->remote_qp_node, &cm.remote_qp_table); timewait_info->inserted_remote_qp = 0; } - spin_unlock_irqrestore(&cm.lock, flags); } static struct cm_timewait_info * cm_create_timewait_info(__be32 local_id) @@ -684,8 +678,12 @@ static struct cm_timewait_info * cm_crea static void cm_enter_timewait(struct cm_id_private *cm_id_priv) { int wait_time; + unsigned long flags; + spin_lock_irqsave(&cm.lock, flags); cm_cleanup_timewait(cm_id_priv->timewait_info); + list_add_tail(&cm_id_priv->timewait_info->list, &cm.timewait_list); + spin_unlock_irqrestore(&cm.lock, flags); /* * The cm_id could be destroyed by the user before we exit timewait. @@ -701,9 +699,13 @@ static void cm_enter_timewait(struct cm_ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv) { + unsigned long flags; + cm_id_priv->id.state = IB_CM_IDLE; if (cm_id_priv->timewait_info) { + spin_lock_irqsave(&cm.lock, flags); cm_cleanup_timewait(cm_id_priv->timewait_info); + spin_unlock_irqrestore(&cm.lock, flags); kfree(cm_id_priv->timewait_info); cm_id_priv->timewait_info = NULL; } @@ -1307,6 +1309,7 @@ static struct cm_id_private * cm_match_r if (timewait_info) { cur_cm_id_priv = cm_get_id(timewait_info->work.local_id, timewait_info->work.remote_id); + cm_cleanup_timewait(cm_id_priv->timewait_info); spin_unlock_irqrestore(&cm.lock, flags); if (cur_cm_id_priv) { cm_dup_req_handler(work, cur_cm_id_priv); @@ -1315,7 +1318,8 @@ static struct cm_id_private * cm_match_r cm_issue_rej(work->port, work->mad_recv_wc, IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REQ, NULL, 0); - goto error; + listen_cm_id_priv = NULL; + goto out; } /* Find matching listen request. */ @@ -1323,21 +1327,20 @@ static struct cm_id_private * cm_match_r req_msg->service_id, req_msg->private_data); if (!listen_cm_id_priv) { + cm_cleanup_timewait(cm_id_priv->timewait_info); spin_unlock_irqrestore(&cm.lock, flags); cm_issue_rej(work->port, work->mad_recv_wc, IB_CM_REJ_INVALID_SERVICE_ID, CM_MSG_RESPONSE_REQ, NULL, 0); - goto error; + goto out; } atomic_inc(&listen_cm_id_priv->refcount); atomic_inc(&cm_id_priv->refcount); cm_id_priv->id.state = IB_CM_REQ_RCVD; atomic_inc(&cm_id_priv->work_count); spin_unlock_irqrestore(&cm.lock, flags); +out: return listen_cm_id_priv; - -error: cm_cleanup_timewait(cm_id_priv->timewait_info); - return NULL; } static int cm_req_handler(struct cm_work *work) @@ -1899,6 +1902,32 @@ out: spin_unlock_irqrestore(&cm_id_priv- } EXPORT_SYMBOL(ib_send_cm_drep); +static int cm_issue_drep(struct cm_port *port, + struct ib_mad_recv_wc *mad_recv_wc) +{ + struct ib_mad_send_buf *msg = NULL; + struct cm_dreq_msg *dreq_msg; + struct cm_drep_msg *drep_msg; + int ret; + + ret = cm_alloc_response_msg(port, mad_recv_wc, &msg); + if (ret) + return ret; + + dreq_msg = (struct cm_dreq_msg *) mad_recv_wc->recv_buf.mad; + drep_msg = (struct cm_drep_msg *) msg->mad; + + cm_format_mad_hdr(&drep_msg->hdr, CM_DREP_ATTR_ID, dreq_msg->hdr.tid); + drep_msg->remote_comm_id = dreq_msg->local_comm_id; + drep_msg->local_comm_id = dreq_msg->remote_comm_id; + + ret = ib_post_send_mad(msg, NULL); + if (ret) + cm_free_msg(msg); + + return ret; +} + static int cm_dreq_handler(struct cm_work *work) { struct cm_id_private *cm_id_priv; @@ -1910,8 +1939,10 @@ static int cm_dreq_handler(struct cm_wor dreq_msg = (struct cm_dreq_msg *)work->mad_recv_wc->recv_buf.mad; cm_id_priv = cm_acquire_id(dreq_msg->remote_comm_id, dreq_msg->local_comm_id); - if (!cm_id_priv) + if (!cm_id_priv) { + cm_issue_drep(work->port, work->mad_recv_wc); return -EINVAL; + } work->cm_event.private_data = &dreq_msg->private_data; @@ -2601,28 +2632,29 @@ static int cm_timewait_handler(struct cm { struct cm_timewait_info *timewait_info; struct cm_id_private *cm_id_priv; - unsigned long flags; int ret; timewait_info = (struct cm_timewait_info *)work; - cm_cleanup_timewait(timewait_info); + spin_lock_irq(&cm.lock); + list_del(&timewait_info->list); + spin_unlock_irq(&cm.lock); cm_id_priv = cm_acquire_id(timewait_info->work.local_id, timewait_info->work.remote_id); if (!cm_id_priv) return -EINVAL; - spin_lock_irqsave(&cm_id_priv->lock, flags); + spin_lock_irq(&cm_id_priv->lock); if (cm_id_priv->id.state != IB_CM_TIMEWAIT || cm_id_priv->remote_qpn != timewait_info->remote_qpn) { - spin_unlock_irqrestore(&cm_id_priv->lock, flags); + spin_unlock_irq(&cm_id_priv->lock); goto out; } cm_id_priv->id.state = IB_CM_IDLE; ret = atomic_inc_and_test(&cm_id_priv->work_count); if (!ret) list_add_tail(&work->list, &cm_id_priv->work_list); - spin_unlock_irqrestore(&cm_id_priv->lock, flags); + spin_unlock_irq(&cm_id_priv->lock); if (ret) cm_process_work(cm_id_priv, work); @@ -3374,6 +3406,7 @@ static int __init ib_cm_init(void) idr_init(&cm.local_id_table); get_random_bytes(&cm.random_id_operand, sizeof cm.random_id_operand); idr_pre_get(&cm.local_id_table, GFP_KERNEL); + INIT_LIST_HEAD(&cm.timewait_list); cm.wq = create_workqueue("ib_cm"); if (!cm.wq) @@ -3391,7 +3424,20 @@ error: static void __exit ib_cm_cleanup(void) { + struct cm_timewait_info *timewait_info, *tmp; + + spin_lock_irq(&cm.lock); + list_for_each_entry(timewait_info, &cm.timewait_list, list) + cancel_delayed_work(&timewait_info->work.work); + spin_unlock_irq(&cm.lock); + destroy_workqueue(cm.wq); + + list_for_each_entry_safe(timewait_info, tmp, &cm.timewait_list, list) { + list_del(&timewait_info->list); + kfree(timewait_info); + } + ib_unregister_client(&cm_client); idr_destroy(&cm.local_id_table); } diff --git a/drivers/infiniband/hw/amso1100/c2_qp.c b/drivers/infiniband/hw/amso1100/c2_qp.c index 1226113..5bcf697 100644 --- a/drivers/infiniband/hw/amso1100/c2_qp.c +++ b/drivers/infiniband/hw/amso1100/c2_qp.c @@ -35,6 +35,8 @@ * */ +#include + #include "c2.h" #include "c2_vq.h" #include "c2_status.h" @@ -705,10 +707,8 @@ static inline void c2_activity(struct c2 * cannot get on the bus and the card and system hang in a * deadlock -- thus the need for this code. [TOT] */ - while (readl(c2dev->regs + PCI_BAR0_ADAPTER_HINT) & 0x80000000) { - set_current_state(TASK_UNINTERRUPTIBLE); - schedule_timeout(0); - } + while (readl(c2dev->regs + PCI_BAR0_ADAPTER_HINT) & 0x80000000) + udelay(10); __raw_writel(C2_HINT_MAKE(mq_index, shared), c2dev->regs + PCI_BAR0_ADAPTER_HINT); @@ -766,6 +766,7 @@ int c2_post_send(struct ib_qp *ibqp, str struct c2_dev *c2dev = to_c2dev(ibqp->device); struct c2_qp *qp = to_c2qp(ibqp); union c2wr wr; + unsigned long lock_flags; int err = 0; u32 flags; @@ -881,8 +882,10 @@ int c2_post_send(struct ib_qp *ibqp, str /* * Post the puppy! */ + spin_lock_irqsave(&qp->lock, lock_flags); err = qp_wr_post(&qp->sq_mq, &wr, qp, msg_size); if (err) { + spin_unlock_irqrestore(&qp->lock, lock_flags); break; } @@ -890,6 +893,7 @@ int c2_post_send(struct ib_qp *ibqp, str * Enqueue mq index to activity FIFO. */ c2_activity(c2dev, qp->sq_mq.index, qp->sq_mq.hint_count); + spin_unlock_irqrestore(&qp->lock, lock_flags); ib_wr = ib_wr->next; } @@ -905,6 +909,7 @@ int c2_post_receive(struct ib_qp *ibqp, struct c2_dev *c2dev = to_c2dev(ibqp->device); struct c2_qp *qp = to_c2qp(ibqp); union c2wr wr; + unsigned long lock_flags; int err = 0; if (qp->state > IB_QPS_RTS) @@ -945,8 +950,10 @@ int c2_post_receive(struct ib_qp *ibqp, break; } + spin_lock_irqsave(&qp->lock, lock_flags); err = qp_wr_post(&qp->rq_mq, &wr, qp, qp->rq_mq.msg_size); if (err) { + spin_unlock_irqrestore(&qp->lock, lock_flags); break; } @@ -954,6 +961,7 @@ int c2_post_receive(struct ib_qp *ibqp, * Enqueue mq index to activity FIFO */ c2_activity(c2dev, qp->rq_mq.index, qp->rq_mq.hint_count); + spin_unlock_irqrestore(&qp->lock, lock_flags); ib_wr = ib_wr->next; } diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 981fe2e..fc67f78 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -179,6 +179,8 @@ static int mthca_query_port(struct ib_de props->max_mtu = out_mad->data[41] & 0xf; props->active_mtu = out_mad->data[36] >> 4; props->subnet_timeout = out_mad->data[51] & 0x1f; + props->max_vl_num = out_mad->data[37] >> 4; + props->init_type_reply = out_mad->data[41] >> 4; out: kfree(in_mad); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 44b9e5b..3bf0c5b 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -343,14 +343,16 @@ static int srp_send_req(struct srp_targe */ if (target->io_class == SRP_REV10_IB_IO_CLASS) { memcpy(req->priv.initiator_port_id, - target->srp_host->initiator_port_id + 8, 8); + &target->path.sgid.global.interface_id, 8); memcpy(req->priv.initiator_port_id + 8, - target->srp_host->initiator_port_id, 8); + &target->initiator_ext, 8); memcpy(req->priv.target_port_id, &target->ioc_guid, 8); memcpy(req->priv.target_port_id + 8, &target->id_ext, 8); } else { memcpy(req->priv.initiator_port_id, - target->srp_host->initiator_port_id, 16); + &target->initiator_ext, 8); + memcpy(req->priv.initiator_port_id + 8, + &target->path.sgid.global.interface_id, 8); memcpy(req->priv.target_port_id, &target->id_ext, 8); memcpy(req->priv.target_port_id + 8, &target->ioc_guid, 8); } @@ -1553,6 +1555,7 @@ enum { SRP_OPT_MAX_SECT = 1 << 5, SRP_OPT_MAX_CMD_PER_LUN = 1 << 6, SRP_OPT_IO_CLASS = 1 << 7, + SRP_OPT_INITIATOR_EXT = 1 << 8, SRP_OPT_ALL = (SRP_OPT_ID_EXT | SRP_OPT_IOC_GUID | SRP_OPT_DGID | @@ -1569,6 +1572,7 @@ static match_table_t srp_opt_tokens = { { SRP_OPT_MAX_SECT, "max_sect=%d" }, { SRP_OPT_MAX_CMD_PER_LUN, "max_cmd_per_lun=%d" }, { SRP_OPT_IO_CLASS, "io_class=%x" }, + { SRP_OPT_INITIATOR_EXT, "initiator_ext=%s" }, { SRP_OPT_ERR, NULL } }; @@ -1668,6 +1672,12 @@ static int srp_parse_options(const char target->io_class = token; break; + case SRP_OPT_INITIATOR_EXT: + p = match_strdup(args); + target->initiator_ext = cpu_to_be64(simple_strtoull(p, NULL, 16)); + kfree(p); + break; + default: printk(KERN_WARNING PFX "unknown parameter or missing value " "'%s' in target creation request\n", p); @@ -1708,7 +1718,6 @@ static ssize_t srp_create_target(struct target_host->max_lun = SRP_MAX_LUN; target = host_to_target(target_host); - memset(target, 0, sizeof *target); target->io_class = SRP_REV16A_IB_IO_CLASS; target->scsi_host = target_host; @@ -1815,9 +1824,6 @@ static struct srp_host *srp_add_port(str host->dev = device; host->port = port; - host->initiator_port_id[7] = port; - memcpy(host->initiator_port_id + 8, &device->dev->node_guid, 8); - host->class_dev.class = &srp_class; host->class_dev.dev = device->dev->dma_device; snprintf(host->class_dev.class_id, BUS_ID_SIZE, "srp-%s-%d", diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index 5b581fb..d4e35ef 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -91,7 +91,6 @@ struct srp_device { }; struct srp_host { - u8 initiator_port_id[16]; struct srp_device *dev; u8 port; struct class_device class_dev; @@ -122,6 +121,7 @@ struct srp_target_port { __be64 id_ext; __be64 ioc_guid; __be64 service_id; + __be64 initiator_ext; u16 io_class; struct srp_host *srp_host; struct Scsi_Host *scsi_host;