diff options
Diffstat (limited to 'drivers/infiniband')
-rw-r--r-- | drivers/infiniband/core/multicast.c | 23 | ||||
-rw-r--r-- | drivers/infiniband/core/sa_query.c | 173 | ||||
-rw-r--r-- | drivers/infiniband/hw/cxgb3/cxio_hal.c | 2 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_mad.c | 6 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib.h | 4 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_ib.c | 109 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_main.c | 140 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 48 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 3 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 2 | ||||
-rw-r--r-- | drivers/infiniband/ulp/srpt/ib_srpt.c | 2 |
11 files changed, 484 insertions, 28 deletions
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c index 250937c..a83ec28 100644 --- a/drivers/infiniband/core/multicast.c +++ b/drivers/infiniband/core/multicast.c @@ -93,6 +93,18 @@ enum { struct mcast_member; +/* +* There are 4 types of join states: +* FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember. +*/ +enum { + FULLMEMBER_JOIN, + NONMEMBER_JOIN, + SENDONLY_NONMEBER_JOIN, + SENDONLY_FULLMEMBER_JOIN, + NUM_JOIN_MEMBERSHIP_TYPES, +}; + struct mcast_group { struct ib_sa_mcmember_rec rec; struct rb_node node; @@ -102,7 +114,7 @@ struct mcast_group { struct list_head pending_list; struct list_head active_list; struct mcast_member *last_join; - int members[3]; + int members[NUM_JOIN_MEMBERSHIP_TYPES]; atomic_t refcount; enum mcast_group_state state; struct ib_sa_query *query; @@ -220,8 +232,9 @@ static void queue_join(struct mcast_member *member) } /* - * A multicast group has three types of members: full member, non member, and - * send only member. We need to keep track of the number of members of each + * A multicast group has four types of members: full member, non member, + * sendonly non member and sendonly full member. + * We need to keep track of the number of members of each * type based on their join state. Adjust the number of members the belong to * the specified join states. */ @@ -229,7 +242,7 @@ static void adjust_membership(struct mcast_group *group, u8 join_state, int inc) { int i; - for (i = 0; i < 3; i++, join_state >>= 1) + for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++, join_state >>= 1) if (join_state & 0x1) group->members[i] += inc; } @@ -245,7 +258,7 @@ static u8 get_leave_state(struct mcast_group *group) u8 leave_state = 0; int i; - for (i = 0; i < 3; i++) + for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++) if (!group->members[i]) leave_state |= (0x1 << i); diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 8bd61a61..e955386 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -115,6 +115,12 @@ struct ib_sa_guidinfo_query { struct ib_sa_query sa_query; }; +struct ib_sa_classport_info_query { + void (*callback)(int, struct ib_class_port_info *, void *); + void *context; + struct ib_sa_query sa_query; +}; + struct ib_sa_mcmember_query { void (*callback)(int, struct ib_sa_mcmember_rec *, void *); void *context; @@ -388,6 +394,82 @@ static const struct ib_field service_rec_table[] = { .size_bits = 2*64 }, }; +#define CLASSPORTINFO_REC_FIELD(field) \ + .struct_offset_bytes = offsetof(struct ib_class_port_info, field), \ + .struct_size_bytes = sizeof((struct ib_class_port_info *)0)->field, \ + .field_name = "ib_class_port_info:" #field + +static const struct ib_field classport_info_rec_table[] = { + { CLASSPORTINFO_REC_FIELD(base_version), + .offset_words = 0, + .offset_bits = 0, + .size_bits = 8 }, + { CLASSPORTINFO_REC_FIELD(class_version), + .offset_words = 0, + .offset_bits = 8, + .size_bits = 8 }, + { CLASSPORTINFO_REC_FIELD(capability_mask), + .offset_words = 0, + .offset_bits = 16, + .size_bits = 16 }, + { CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time), + .offset_words = 1, + .offset_bits = 0, + .size_bits = 32 }, + { CLASSPORTINFO_REC_FIELD(redirect_gid), + .offset_words = 2, + .offset_bits = 0, + .size_bits = 128 }, + { CLASSPORTINFO_REC_FIELD(redirect_tcslfl), + .offset_words = 6, + .offset_bits = 0, + .size_bits = 32 }, + { CLASSPORTINFO_REC_FIELD(redirect_lid), + .offset_words = 7, + .offset_bits = 0, + .size_bits = 16 }, + { CLASSPORTINFO_REC_FIELD(redirect_pkey), + .offset_words = 7, + .offset_bits = 16, + .size_bits = 16 }, + + { CLASSPORTINFO_REC_FIELD(redirect_qp), + .offset_words = 8, + .offset_bits = 0, + .size_bits = 32 }, + { CLASSPORTINFO_REC_FIELD(redirect_qkey), + .offset_words = 9, + .offset_bits = 0, + .size_bits = 32 }, + + { CLASSPORTINFO_REC_FIELD(trap_gid), + .offset_words = 10, + .offset_bits = 0, + .size_bits = 128 }, + { CLASSPORTINFO_REC_FIELD(trap_tcslfl), + .offset_words = 14, + .offset_bits = 0, + .size_bits = 32 }, + + { CLASSPORTINFO_REC_FIELD(trap_lid), + .offset_words = 15, + .offset_bits = 0, + .size_bits = 16 }, + { CLASSPORTINFO_REC_FIELD(trap_pkey), + .offset_words = 15, + .offset_bits = 16, + .size_bits = 16 }, + + { CLASSPORTINFO_REC_FIELD(trap_hlqp), + .offset_words = 16, + .offset_bits = 0, + .size_bits = 32 }, + { CLASSPORTINFO_REC_FIELD(trap_qkey), + .offset_words = 17, + .offset_bits = 0, + .size_bits = 32 }, +}; + #define GUIDINFO_REC_FIELD(field) \ .struct_offset_bytes = offsetof(struct ib_sa_guidinfo_rec, field), \ .struct_size_bytes = sizeof((struct ib_sa_guidinfo_rec *) 0)->field, \ @@ -1632,6 +1714,97 @@ err1: } EXPORT_SYMBOL(ib_sa_guid_info_rec_query); +/* Support get SA ClassPortInfo */ +static void ib_sa_classport_info_rec_callback(struct ib_sa_query *sa_query, + int status, + struct ib_sa_mad *mad) +{ + struct ib_sa_classport_info_query *query = + container_of(sa_query, struct ib_sa_classport_info_query, sa_query); + + if (mad) { + struct ib_class_port_info rec; + + ib_unpack(classport_info_rec_table, + ARRAY_SIZE(classport_info_rec_table), + mad->data, &rec); + query->callback(status, &rec, query->context); + } else { + query->callback(status, NULL, query->context); + } +} + +static void ib_sa_portclass_info_rec_release(struct ib_sa_query *sa_query) +{ + kfree(container_of(sa_query, struct ib_sa_classport_info_query, + sa_query)); +} + +int ib_sa_classport_info_rec_query(struct ib_sa_client *client, + struct ib_device *device, u8 port_num, + int timeout_ms, gfp_t gfp_mask, + void (*callback)(int status, + struct ib_class_port_info *resp, + void *context), + void *context, + struct ib_sa_query **sa_query) +{ + struct ib_sa_classport_info_query *query; + struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client); + struct ib_sa_port *port; + struct ib_mad_agent *agent; + struct ib_sa_mad *mad; + int ret; + + if (!sa_dev) + return -ENODEV; + + port = &sa_dev->port[port_num - sa_dev->start_port]; + agent = port->agent; + + query = kzalloc(sizeof(*query), gfp_mask); + if (!query) + return -ENOMEM; + + query->sa_query.port = port; + ret = alloc_mad(&query->sa_query, gfp_mask); + if (ret) + goto err1; + + ib_sa_client_get(client); + query->sa_query.client = client; + query->callback = callback; + query->context = context; + + mad = query->sa_query.mad_buf->mad; + init_mad(mad, agent); + + query->sa_query.callback = callback ? ib_sa_classport_info_rec_callback : NULL; + + query->sa_query.release = ib_sa_portclass_info_rec_release; + /* support GET only */ + mad->mad_hdr.method = IB_MGMT_METHOD_GET; + mad->mad_hdr.attr_id = cpu_to_be16(IB_SA_ATTR_CLASS_PORTINFO); + mad->sa_hdr.comp_mask = 0; + *sa_query = &query->sa_query; + + ret = send_mad(&query->sa_query, timeout_ms, gfp_mask); + if (ret < 0) + goto err2; + + return ret; + +err2: + *sa_query = NULL; + ib_sa_client_put(query->sa_query.client); + free_mad(&query->sa_query); + +err1: + kfree(query); + return ret; +} +EXPORT_SYMBOL(ib_sa_classport_info_rec_query); + static void send_handler(struct ib_mad_agent *agent, struct ib_mad_send_wc *mad_send_wc) { diff --git a/drivers/infiniband/hw/cxgb3/cxio_hal.c b/drivers/infiniband/hw/cxgb3/cxio_hal.c index de1c61b4..ada2e50 100644 --- a/drivers/infiniband/hw/cxgb3/cxio_hal.c +++ b/drivers/infiniband/hw/cxgb3/cxio_hal.c @@ -327,7 +327,7 @@ int cxio_destroy_cq(struct cxio_rdev *rdev_p, struct t3_cq *cq) kfree(cq->sw_queue); dma_free_coherent(&(rdev_p->rnic_info.pdev->dev), (1UL << (cq->size_log2)) - * sizeof(struct t3_cqe), cq->queue, + * sizeof(struct t3_cqe) + 1, cq->queue, dma_unmap_addr(cq, mapping)); cxio_hal_put_cqid(rdev_p->rscp, cq->cqid); return err; diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index 0bd1837..d2ac298 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -1172,11 +1172,13 @@ static int pma_get_classportinfo(struct ib_pma_mad *pmp, * Set the most significant bit of CM2 to indicate support for * congestion statistics */ - p->reserved[0] = dd->psxmitwait_supported << 7; + ib_set_cpi_capmask2(p, + dd->psxmitwait_supported << + (31 - IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE)); /* * Expected response time is 4.096 usec. * 2^18 == 1.073741824 sec. */ - p->resp_time_value = 18; + ib_set_cpi_resp_time(p, 18); return reply((struct ib_smp *) pmp); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index caec8e9..bab7db6 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -92,6 +92,8 @@ enum { IPOIB_FLAG_UMCAST = 10, IPOIB_STOP_NEIGH_GC = 11, IPOIB_NEIGH_TBL_FLUSH = 12, + IPOIB_FLAG_DEV_ADDR_SET = 13, + IPOIB_FLAG_DEV_ADDR_CTRL = 14, IPOIB_MAX_BACKOFF_SECONDS = 16, @@ -392,6 +394,7 @@ struct ipoib_dev_priv { struct ipoib_ethtool_st ethtool; struct timer_list poll_timer; unsigned max_send_sge; + bool sm_fullmember_sendonly_support; }; struct ipoib_ah { @@ -476,6 +479,7 @@ void ipoib_reap_ah(struct work_struct *work); void ipoib_mark_paths_invalid(struct net_device *dev); void ipoib_flush_paths(struct net_device *dev); +int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv); struct ipoib_dev_priv *ipoib_intf_alloc(const char *format); int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index da5f28c..7e9a770 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -997,6 +997,106 @@ static inline int update_child_pkey(struct ipoib_dev_priv *priv) return 0; } +/* + * returns true if the device address of the ipoib interface has changed and the + * new address is a valid one (i.e in the gid table), return false otherwise. + */ +static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv) +{ + union ib_gid search_gid; + union ib_gid gid0; + union ib_gid *netdev_gid; + int err; + u16 index; + u8 port; + bool ret = false; + + netdev_gid = (union ib_gid *)(priv->dev->dev_addr + 4); + if (ib_query_gid(priv->ca, priv->port, 0, &gid0, NULL)) + return false; + + netif_addr_lock(priv->dev); + + /* The subnet prefix may have changed, update it now so we won't have + * to do it later + */ + priv->local_gid.global.subnet_prefix = gid0.global.subnet_prefix; + netdev_gid->global.subnet_prefix = gid0.global.subnet_prefix; + search_gid.global.subnet_prefix = gid0.global.subnet_prefix; + + search_gid.global.interface_id = priv->local_gid.global.interface_id; + + netif_addr_unlock(priv->dev); + + err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB, + priv->dev, &port, &index); + + netif_addr_lock(priv->dev); + + if (search_gid.global.interface_id != + priv->local_gid.global.interface_id) + /* There was a change while we were looking up the gid, bail + * here and let the next work sort this out + */ + goto out; + + /* The next section of code needs some background: + * Per IB spec the port GUID can't change if the HCA is powered on. + * port GUID is the basis for GID at index 0 which is the basis for + * the default device address of a ipoib interface. + * + * so it seems the flow should be: + * if user_changed_dev_addr && gid in gid tbl + * set bit dev_addr_set + * return true + * else + * return false + * + * The issue is that there are devices that don't follow the spec, + * they change the port GUID when the HCA is powered, so in order + * not to break userspace applications, We need to check if the + * user wanted to control the device address and we assume that + * if he sets the device address back to be based on GID index 0, + * he no longer wishs to control it. + * + * If the user doesn't control the the device address, + * IPOIB_FLAG_DEV_ADDR_SET is set and ib_find_gid failed it means + * the port GUID has changed and GID at index 0 has changed + * so we need to change priv->local_gid and priv->dev->dev_addr + * to reflect the new GID. + */ + if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) { + if (!err && port == priv->port) { + set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); + if (index == 0) + clear_bit(IPOIB_FLAG_DEV_ADDR_CTRL, + &priv->flags); + else + set_bit(IPOIB_FLAG_DEV_ADDR_CTRL, &priv->flags); + ret = true; + } else { + ret = false; + } + } else { + if (!err && port == priv->port) { + ret = true; + } else { + if (!test_bit(IPOIB_FLAG_DEV_ADDR_CTRL, &priv->flags)) { + memcpy(&priv->local_gid, &gid0, + sizeof(priv->local_gid)); + memcpy(priv->dev->dev_addr + 4, &gid0, + sizeof(priv->local_gid)); + ret = true; + } + } + } + +out: + netif_addr_unlock(priv->dev); + + return ret; +} + static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, enum ipoib_flush_level level, int nesting) @@ -1018,6 +1118,9 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags) && level != IPOIB_FLUSH_HEAVY) { + /* Make sure the dev_addr is set even if not flushing */ + if (level == IPOIB_FLUSH_LIGHT) + ipoib_dev_addr_changed_valid(priv); ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n"); return; } @@ -1029,7 +1132,8 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, update_parent_pkey(priv); else update_child_pkey(priv); - } + } else if (level == IPOIB_FLUSH_LIGHT) + ipoib_dev_addr_changed_valid(priv); ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_ADMIN_UP not set.\n"); return; } @@ -1081,7 +1185,8 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) { if (level >= IPOIB_FLUSH_NORMAL) ipoib_ib_dev_up(dev); - ipoib_mcast_restart_task(&priv->restart_task); + if (ipoib_dev_addr_changed_valid(priv)) + ipoib_mcast_restart_task(&priv->restart_task); } } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 80807d6..2c3fb53 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -99,6 +99,7 @@ static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u8 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); +static int ipoib_set_mac(struct net_device *dev, void *addr); static struct ib_client ipoib_client = { .name = "ipoib", @@ -117,6 +118,8 @@ int ipoib_open(struct net_device *dev) set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); + priv->sm_fullmember_sendonly_support = false; + if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; @@ -629,6 +632,77 @@ void ipoib_mark_paths_invalid(struct net_device *dev) spin_unlock_irq(&priv->lock); } +struct classport_info_context { + struct ipoib_dev_priv *priv; + struct completion done; + struct ib_sa_query *sa_query; +}; + +static void classport_info_query_cb(int status, struct ib_class_port_info *rec, + void *context) +{ + struct classport_info_context *cb_ctx = context; + struct ipoib_dev_priv *priv; + + WARN_ON(!context); + + priv = cb_ctx->priv; + + if (status || !rec) { + pr_debug("device: %s failed query classport_info status: %d\n", + priv->dev->name, status); + /* keeps the default, will try next mcast_restart */ + priv->sm_fullmember_sendonly_support = false; + goto out; + } + + if (ib_get_cpi_capmask2(rec) & + IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT) { + pr_debug("device: %s enabled fullmember-sendonly for sendonly MCG\n", + priv->dev->name); + priv->sm_fullmember_sendonly_support = true; + } else { + pr_debug("device: %s disabled fullmember-sendonly for sendonly MCG\n", + priv->dev->name); + priv->sm_fullmember_sendonly_support = false; + } + +out: + complete(&cb_ctx->done); +} + +int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv) +{ + struct classport_info_context *callback_context; + int ret; + + callback_context = kmalloc(sizeof(*callback_context), GFP_KERNEL); + if (!callback_context) + return -ENOMEM; + + callback_context->priv = priv; + init_completion(&callback_context->done); + + ret = ib_sa_classport_info_rec_query(&ipoib_sa_client, + priv->ca, priv->port, 3000, + GFP_KERNEL, + classport_info_query_cb, + callback_context, + &callback_context->sa_query); + if (ret < 0) { + pr_info("%s failed to send ib_sa_classport_info query, ret: %d\n", + priv->dev->name, ret); + kfree(callback_context); + return ret; + } + + /* waiting for the callback to finish before returnning */ + wait_for_completion(&callback_context->done); + kfree(callback_context); + + return ret; +} + void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); @@ -1649,6 +1723,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_get_vf_config = ipoib_get_vf_config, .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_set_vf_guid = ipoib_set_vf_guid, + .ndo_set_mac_address = ipoib_set_mac, }; static const struct net_device_ops ipoib_netdev_ops_vf = { @@ -1771,6 +1846,70 @@ int ipoib_add_umcast_attr(struct net_device *dev) return device_create_file(&dev->dev, &dev_attr_umcast); } +static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) +{ + struct ipoib_dev_priv *child_priv; + struct net_device *netdev = priv->dev; + + netif_addr_lock(netdev); + + memcpy(&priv->local_gid.global.interface_id, + &gid->global.interface_id, + sizeof(gid->global.interface_id)); + memcpy(netdev->dev_addr + 4, &priv->local_gid, sizeof(priv->local_gid)); + clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); + + netif_addr_unlock(netdev); + + if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { + down_read(&priv->vlan_rwsem); + list_for_each_entry(child_priv, &priv->child_intfs, list) + set_base_guid(child_priv, gid); + up_read(&priv->vlan_rwsem); + } +} + +static int ipoib_check_lladdr(struct net_device *dev, + struct sockaddr_storage *ss) +{ + union ib_gid *gid = (union ib_gid *)(ss->__data + 4); + int ret = 0; + + netif_addr_lock(dev); + + /* Make sure the QPN, reserved and subnet prefix match the current + * lladdr, it also makes sure the lladdr is unicast. + */ + if (memcmp(dev->dev_addr, ss->__data, + 4 + sizeof(gid->global.subnet_prefix)) || + gid->global.interface_id == 0) + ret = -EINVAL; + + netif_addr_unlock(dev); + + return ret; +} + +static int ipoib_set_mac(struct net_device *dev, void *addr) +{ + struct ipoib_dev_priv *priv = netdev_priv(dev); + struct sockaddr_storage *ss = addr; + int ret; + + if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) + return -EBUSY; + + ret = ipoib_check_lladdr(dev, ss); + if (ret) + return ret; + + set_base_guid(priv, (union ib_gid *)(ss->__data + 4)); + + queue_work(ipoib_workqueue, &priv->flush_light); + + return 0; +} + static ssize_t create_child(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -1894,6 +2033,7 @@ static struct net_device *ipoib_add_port(const char *format, goto device_init_failed; } else 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) { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 2588931..82fbc94 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -64,6 +64,9 @@ struct ipoib_mcast_iter { unsigned int send_only; }; +/* join state that allows creating mcg with sendonly member request */ +#define SENDONLY_FULLMEMBER_JOIN 8 + /* * This should be called with the priv->lock held */ @@ -326,12 +329,23 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, carrier_on_task); struct ib_port_attr attr; + int ret; if (ib_query_port(priv->ca, priv->port, &attr) || attr.state != IB_PORT_ACTIVE) { ipoib_dbg(priv, "Keeping carrier off until IB port is active\n"); return; } + /* + * Check if can send sendonly MCG's with sendonly-fullmember join state. + * It done here after the successfully join to the broadcast group, + * because the broadcast group must always be joined first and is always + * re-joined if the SM changes substantially. + */ + ret = ipoib_check_sm_sendonly_fullmember_support(priv); + if (ret < 0) + pr_debug("%s failed query sm support for sendonly-fullmember (ret: %d)\n", + priv->dev->name, ret); /* * Take rtnl_lock to avoid racing with ipoib_stop() and @@ -515,22 +529,20 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) rec.hop_limit = priv->broadcast->mcmember.hop_limit; /* - * Send-only IB Multicast joins do not work at the core - * IB layer yet, so we can't use them here. However, - * we are emulating an Ethernet multicast send, which - * does not require a multicast subscription and will - * still send properly. The most appropriate thing to + * Send-only IB Multicast joins work at the core IB layer but + * require specific SM support. + * We can use such joins here only if the current SM supports that feature. + * However, if not, we emulate an Ethernet multicast send, + * which does not require a multicast subscription and will + * still send properly. The most appropriate thing to * do is to create the group if it doesn't exist as that * most closely emulates the behavior, from a user space - * application perspecitive, of Ethernet multicast - * operation. For now, we do a full join, maybe later - * when the core IB layers support send only joins we - * will use them. + * application perspective, of Ethernet multicast operation. */ -#if 0 - if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) - rec.join_state = 4; -#endif + if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) && + priv->sm_fullmember_sendonly_support) + /* SM supports sendonly-fullmember, otherwise fallback to full-member */ + rec.join_state = SENDONLY_FULLMEMBER_JOIN; } spin_unlock_irq(&priv->lock); @@ -570,11 +582,13 @@ void ipoib_mcast_join_task(struct work_struct *work) return; } priv->local_lid = port_attr.lid; + netif_addr_lock(dev); - if (ib_query_gid(priv->ca, priv->port, 0, &priv->local_gid, NULL)) - ipoib_warn(priv, "ib_query_gid() failed\n"); - else - memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid)); + if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) { + netif_addr_unlock(dev); + return; + } + netif_addr_unlock(dev); spin_lock_irq(&priv->lock); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index b809c37..1e7cbba 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -307,5 +307,8 @@ void ipoib_event(struct ib_event_handler *handler, queue_work(ipoib_workqueue, &priv->flush_normal); } else if (record->event == IB_EVENT_PKEY_CHANGE) { queue_work(ipoib_workqueue, &priv->flush_heavy); + } else if (record->event == IB_EVENT_GID_CHANGE && + !test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) { + queue_work(ipoib_workqueue, &priv->flush_light); } } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index fca1a88..64a3559 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -68,6 +68,8 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, priv->pkey = pkey; memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN); + memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); + set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); priv->dev->broadcast[8] = pkey >> 8; priv->dev->broadcast[9] = pkey & 0xff; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 2843f1a..887ebad 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -254,8 +254,8 @@ static void srpt_get_class_port_info(struct ib_dm_mad *mad) memset(cif, 0, sizeof(*cif)); cif->base_version = 1; cif->class_version = 1; - cif->resp_time_value = 20; + ib_set_cpi_resp_time(cif, 20); mad->mad_hdr.status = 0; } |