diff options
Diffstat (limited to 'drivers/infiniband/core/cma.c')
| -rw-r--r-- | drivers/infiniband/core/cma.c | 2127 |
1 files changed, 1395 insertions, 732 deletions
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index cc9b5940fa9..d570030d899 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -40,12 +40,17 @@ #include <linux/random.h> #include <linux/idr.h> #include <linux/inetdevice.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <net/route.h> #include <net/tcp.h> #include <net/ipv6.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> +#include <rdma/rdma_netlink.h> +#include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> @@ -58,6 +63,7 @@ MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24) +#define CMA_IBOE_PACKET_LIFETIME 18 static void cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device); @@ -74,11 +80,10 @@ static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct workqueue_struct *cma_wq; -static DEFINE_IDR(sdp_ps); static DEFINE_IDR(tcp_ps); static DEFINE_IDR(udp_ps); static DEFINE_IDR(ipoib_ps); -static int next_port; +static DEFINE_IDR(ib_ps); struct cma_device { struct list_head list; @@ -88,26 +93,16 @@ struct cma_device { struct list_head id_list; }; -enum cma_state { - CMA_IDLE, - CMA_ADDR_QUERY, - CMA_ADDR_RESOLVED, - CMA_ROUTE_QUERY, - CMA_ROUTE_RESOLVED, - CMA_CONNECT, - CMA_DISCONNECT, - CMA_ADDR_BOUND, - CMA_LISTEN, - CMA_DEVICE_REMOVAL, - CMA_DESTROYING -}; - struct rdma_bind_list { struct idr *ps; struct hlist_head owners; unsigned short port; }; +enum { + CMA_OPTION_AFONLY, +}; + /* * Device removal can occur at anytime, so we need extra handling to * serialize notifying the user of device removal with other callbacks. @@ -125,7 +120,7 @@ struct rdma_id_private { struct list_head mc_list; int internal_id; - enum cma_state state; + enum rdma_cm_state state; spinlock_t lock; struct mutex qp_mutex; @@ -145,8 +140,12 @@ struct rdma_id_private { u32 seq_num; u32 qkey; u32 qp_num; + pid_t owner; + u32 options; u8 srq; u8 tos; + u8 reuseaddr; + u8 afonly; }; struct cma_multicast { @@ -157,13 +156,14 @@ struct cma_multicast { struct list_head list; void *context; struct sockaddr_storage addr; + struct kref mcref; }; struct cma_work { struct work_struct work; struct rdma_id_private *id; - enum cma_state old_state; - enum cma_state new_state; + enum rdma_cm_state old_state; + enum rdma_cm_state new_state; struct rdma_cm_event event; }; @@ -173,6 +173,12 @@ struct cma_ndev_work { struct rdma_cm_event event; }; +struct iboe_mcast_work { + struct work_struct work; + struct rdma_id_private *id; + struct cma_multicast *mc; +}; + union cma_ip_addr { struct in6_addr ip6; struct { @@ -189,26 +195,9 @@ struct cma_hdr { union cma_ip_addr dst_addr; }; -struct sdp_hh { - u8 bsdh[16]; - u8 sdp_version; /* Major version: 7:4 */ - u8 ip_version; /* IP version: 7:4 */ - u8 sdp_specific1[10]; - __be16 port; - __be16 sdp_specific2; - union cma_ip_addr src_addr; - union cma_ip_addr dst_addr; -}; - -struct sdp_hah { - u8 bsdh[16]; - u8 sdp_version; -}; - #define CMA_VERSION 0x00 -#define SDP_MAJ_VERSION 0x2 -static int cma_comp(struct rdma_id_private *id_priv, enum cma_state comp) +static int cma_comp(struct rdma_id_private *id_priv, enum rdma_cm_state comp) { unsigned long flags; int ret; @@ -220,7 +209,7 @@ static int cma_comp(struct rdma_id_private *id_priv, enum cma_state comp) } static int cma_comp_exch(struct rdma_id_private *id_priv, - enum cma_state comp, enum cma_state exch) + enum rdma_cm_state comp, enum rdma_cm_state exch) { unsigned long flags; int ret; @@ -232,11 +221,11 @@ static int cma_comp_exch(struct rdma_id_private *id_priv, return ret; } -static enum cma_state cma_exch(struct rdma_id_private *id_priv, - enum cma_state exch) +static enum rdma_cm_state cma_exch(struct rdma_id_private *id_priv, + enum rdma_cm_state exch) { unsigned long flags; - enum cma_state old; + enum rdma_cm_state old; spin_lock_irqsave(&id_priv->lock, flags); old = id_priv->state; @@ -255,32 +244,14 @@ static inline void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } -static inline u8 sdp_get_majv(u8 sdp_version) -{ - return sdp_version >> 4; -} - -static inline u8 sdp_get_ip_ver(struct sdp_hh *hh) -{ - return hh->ip_version >> 4; -} - -static inline void sdp_set_ip_ver(struct sdp_hh *hh, u8 ip_ver) -{ - hh->ip_version = (ip_ver << 4) | (hh->ip_version & 0xF); -} - -static inline int cma_is_ud_ps(enum rdma_port_space ps) -{ - return (ps == RDMA_PS_UDP || ps == RDMA_PS_IPOIB); -} - static void cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { atomic_inc(&cma_dev->refcount); id_priv->cma_dev = cma_dev; id_priv->id.device = cma_dev->device; + id_priv->id.route.addr.dev_addr.transport = + rdma_node_get_transport(cma_dev->device->node_type); list_add_tail(&id_priv->list, &cma_dev->id_list); } @@ -290,23 +261,57 @@ static inline void cma_deref_dev(struct cma_device *cma_dev) complete(&cma_dev->comp); } -static void cma_detach_from_dev(struct rdma_id_private *id_priv) +static inline void release_mc(struct kref *kref) +{ + struct cma_multicast *mc = container_of(kref, struct cma_multicast, mcref); + + kfree(mc->multicast.ib); + kfree(mc); +} + +static void cma_release_dev(struct rdma_id_private *id_priv) { + mutex_lock(&lock); list_del(&id_priv->list); cma_deref_dev(id_priv->cma_dev); id_priv->cma_dev = NULL; + mutex_unlock(&lock); +} + +static inline struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) +{ + return (struct sockaddr *) &id_priv->id.route.addr.src_addr; } -static int cma_set_qkey(struct rdma_id_private *id_priv) +static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) +{ + return (struct sockaddr *) &id_priv->id.route.addr.dst_addr; +} + +static inline unsigned short cma_family(struct rdma_id_private *id_priv) +{ + return id_priv->id.route.addr.src_addr.ss_family; +} + +static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) { struct ib_sa_mcmember_rec rec; int ret = 0; - if (id_priv->qkey) + if (id_priv->qkey) { + if (qkey && id_priv->qkey != qkey) + return -EINVAL; return 0; + } + + if (qkey) { + id_priv->qkey = qkey; + return 0; + } switch (id_priv->id.ps) { case RDMA_PS_UDP: + case RDMA_PS_IB: id_priv->qkey = RDMA_UDP_QKEY; break; case RDMA_PS_IPOIB: @@ -323,25 +328,149 @@ static int cma_set_qkey(struct rdma_id_private *id_priv) return ret; } -static int cma_acquire_dev(struct rdma_id_private *id_priv) +static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) +{ + dev_addr->dev_type = ARPHRD_INFINIBAND; + rdma_addr_set_sgid(dev_addr, (union ib_gid *) &sib->sib_addr); + ib_addr_set_pkey(dev_addr, ntohs(sib->sib_pkey)); +} + +static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) +{ + int ret; + + if (addr->sa_family != AF_IB) { + ret = rdma_translate_ip(addr, dev_addr, NULL); + } else { + cma_translate_ib((struct sockaddr_ib *) addr, dev_addr); + ret = 0; + } + + return ret; +} + +static int cma_acquire_dev(struct rdma_id_private *id_priv, + struct rdma_id_private *listen_id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct cma_device *cma_dev; - union ib_gid gid; + union ib_gid gid, iboe_gid; int ret = -ENODEV; + u8 port, found_port; + enum rdma_link_layer dev_ll = dev_addr->dev_type == ARPHRD_INFINIBAND ? + IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET; + + if (dev_ll != IB_LINK_LAYER_INFINIBAND && + id_priv->id.ps == RDMA_PS_IPOIB) + return -EINVAL; + + mutex_lock(&lock); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, + &iboe_gid); + + memcpy(&gid, dev_addr->src_dev_addr + + rdma_addr_gid_offset(dev_addr), sizeof gid); + if (listen_id_priv && + rdma_port_get_link_layer(listen_id_priv->id.device, + listen_id_priv->id.port_num) == dev_ll) { + cma_dev = listen_id_priv->cma_dev; + port = listen_id_priv->id.port_num; + if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB && + rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET) + ret = ib_find_cached_gid(cma_dev->device, &iboe_gid, + &found_port, NULL); + else + ret = ib_find_cached_gid(cma_dev->device, &gid, + &found_port, NULL); - rdma_addr_get_sgid(dev_addr, &gid); + if (!ret && (port == found_port)) { + id_priv->id.port_num = found_port; + goto out; + } + } list_for_each_entry(cma_dev, &dev_list, list) { - ret = ib_find_cached_gid(cma_dev->device, &gid, - &id_priv->id.port_num, NULL); - if (!ret) { - cma_attach_to_dev(id_priv, cma_dev); - break; + for (port = 1; port <= cma_dev->device->phys_port_cnt; ++port) { + if (listen_id_priv && + listen_id_priv->cma_dev == cma_dev && + listen_id_priv->id.port_num == port) + continue; + if (rdma_port_get_link_layer(cma_dev->device, port) == dev_ll) { + if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB && + rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET) + ret = ib_find_cached_gid(cma_dev->device, &iboe_gid, &found_port, NULL); + else + ret = ib_find_cached_gid(cma_dev->device, &gid, &found_port, NULL); + + if (!ret && (port == found_port)) { + id_priv->id.port_num = found_port; + goto out; + } + } } } + +out: + if (!ret) + cma_attach_to_dev(id_priv, cma_dev); + + mutex_unlock(&lock); return ret; } +/* + * Select the source IB device and address to reach the destination IB address. + */ +static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) +{ + struct cma_device *cma_dev, *cur_dev; + struct sockaddr_ib *addr; + union ib_gid gid, sgid, *dgid; + u16 pkey, index; + u8 p; + int i; + + cma_dev = NULL; + addr = (struct sockaddr_ib *) cma_dst_addr(id_priv); + dgid = (union ib_gid *) &addr->sib_addr; + pkey = ntohs(addr->sib_pkey); + + list_for_each_entry(cur_dev, &dev_list, list) { + if (rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB) + continue; + + for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { + if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) + continue; + + for (i = 0; !ib_get_cached_gid(cur_dev->device, p, i, &gid); i++) { + if (!memcmp(&gid, dgid, sizeof(gid))) { + cma_dev = cur_dev; + sgid = gid; + id_priv->id.port_num = p; + goto found; + } + + if (!cma_dev && (gid.global.subnet_prefix == + dgid->global.subnet_prefix)) { + cma_dev = cur_dev; + sgid = gid; + id_priv->id.port_num = p; + } + } + } + } + + if (!cma_dev) + return -ENODEV; + +found: + cma_attach_to_dev(id_priv, cma_dev); + addr = (struct sockaddr_ib *) cma_src_addr(id_priv); + memcpy(&addr->sib_addr, &sgid, sizeof sgid); + cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); + return 0; +} + static void cma_deref_id(struct rdma_id_private *id_priv) { if (atomic_dec_and_test(&id_priv->refcount)) @@ -349,7 +478,7 @@ static void cma_deref_id(struct rdma_id_private *id_priv) } static int cma_disable_callback(struct rdma_id_private *id_priv, - enum cma_state state) + enum rdma_cm_state state) { mutex_lock(&id_priv->handler_mutex); if (id_priv->state != state) { @@ -359,13 +488,9 @@ static int cma_disable_callback(struct rdma_id_private *id_priv, return 0; } -static int cma_has_cm_dev(struct rdma_id_private *id_priv) -{ - return (id_priv->id.device && id_priv->cm_id.ib); -} - struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler, - void *context, enum rdma_port_space ps) + void *context, enum rdma_port_space ps, + enum ib_qp_type qp_type) { struct rdma_id_private *id_priv; @@ -373,10 +498,12 @@ struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler, if (!id_priv) return ERR_PTR(-ENOMEM); - id_priv->state = CMA_IDLE; + id_priv->owner = task_pid_nr(current); + id_priv->state = RDMA_CM_IDLE; id_priv->id.context = context; id_priv->id.event_handler = event_handler; id_priv->id.ps = ps; + id_priv->id.qp_type = qp_type; spin_lock_init(&id_priv->lock); mutex_init(&id_priv->qp_mutex); init_completion(&id_priv->comp); @@ -444,7 +571,7 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, if (IS_ERR(qp)) return PTR_ERR(qp); - if (cma_is_ud_ps(id_priv->id.ps)) + if (id->qp_type == IB_QPT_UD) ret = cma_init_ud_qp(id_priv, qp); else ret = cma_init_conn_qp(id_priv, qp); @@ -478,6 +605,7 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; + union ib_gid sgid; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { @@ -500,6 +628,20 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, if (ret) goto out; + ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num, + qp_attr.ah_attr.grh.sgid_index, &sgid); + if (ret) + goto out; + + if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) + == RDMA_TRANSPORT_IB && + rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) + == IB_LINK_LAYER_ETHERNET) { + ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL); + + if (ret) + goto out; + } if (conn_param) qp_attr.max_dest_rd_atomic = conn_param->responder_resources; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); @@ -556,18 +698,24 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int ret; + u16 pkey; + + if (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) == + IB_LINK_LAYER_INFINIBAND) + pkey = ib_addr_get_pkey(dev_addr); + else + pkey = 0xffff; ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, - ib_addr_get_pkey(dev_addr), - &qp_attr->pkey_index); + pkey, &qp_attr->pkey_index); if (ret) return ret; qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; - if (cma_is_ud_ps(id_priv->id.ps)) { - ret = cma_set_qkey(id_priv); + if (id_priv->id.qp_type == IB_QPT_UD) { + ret = cma_set_qkey(id_priv, 0); if (ret) return ret; @@ -589,11 +737,12 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, id_priv = container_of(id, struct rdma_id_private, id); switch (rdma_node_get_transport(id_priv->id.device->node_type)) { case RDMA_TRANSPORT_IB: - if (!id_priv->cm_id.ib || cma_is_ud_ps(id_priv->id.ps)) + if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD)) ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask); else ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr, qp_attr_mask); + if (qp_attr->qp_state == IB_QPS_RTR) qp_attr->rq_psn = id_priv->seq_num; break; @@ -616,26 +765,30 @@ EXPORT_SYMBOL(rdma_init_qp_attr); static inline int cma_zero_addr(struct sockaddr *addr) { - struct in6_addr *ip6; - - if (addr->sa_family == AF_INET) - return ipv4_is_zeronet( - ((struct sockaddr_in *)addr)->sin_addr.s_addr); - else { - ip6 = &((struct sockaddr_in6 *) addr)->sin6_addr; - return (ip6->s6_addr32[0] | ip6->s6_addr32[1] | - ip6->s6_addr32[2] | ip6->s6_addr32[3]) == 0; + switch (addr->sa_family) { + case AF_INET: + return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr); + case AF_INET6: + return ipv6_addr_any(&((struct sockaddr_in6 *) addr)->sin6_addr); + case AF_IB: + return ib_addr_any(&((struct sockaddr_ib *) addr)->sib_addr); + default: + return 0; } } static inline int cma_loopback_addr(struct sockaddr *addr) { - if (addr->sa_family == AF_INET) - return ipv4_is_loopback( - ((struct sockaddr_in *) addr)->sin_addr.s_addr); - else - return ipv6_addr_loopback( - &((struct sockaddr_in6 *) addr)->sin6_addr); + switch (addr->sa_family) { + case AF_INET: + return ipv4_is_loopback(((struct sockaddr_in *) addr)->sin_addr.s_addr); + case AF_INET6: + return ipv6_addr_loopback(&((struct sockaddr_in6 *) addr)->sin6_addr); + case AF_IB: + return ib_addr_loopback(&((struct sockaddr_ib *) addr)->sib_addr); + default: + return 0; + } } static inline int cma_any_addr(struct sockaddr *addr) @@ -643,12 +796,40 @@ static inline int cma_any_addr(struct sockaddr *addr) return cma_zero_addr(addr) || cma_loopback_addr(addr); } -static inline __be16 cma_port(struct sockaddr *addr) +static int cma_addr_cmp(struct sockaddr *src, struct sockaddr *dst) { - if (addr->sa_family == AF_INET) + if (src->sa_family != dst->sa_family) + return -1; + + switch (src->sa_family) { + case AF_INET: + return ((struct sockaddr_in *) src)->sin_addr.s_addr != + ((struct sockaddr_in *) dst)->sin_addr.s_addr; + case AF_INET6: + return ipv6_addr_cmp(&((struct sockaddr_in6 *) src)->sin6_addr, + &((struct sockaddr_in6 *) dst)->sin6_addr); + default: + return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, + &((struct sockaddr_ib *) dst)->sib_addr); + } +} + +static __be16 cma_port(struct sockaddr *addr) +{ + struct sockaddr_ib *sib; + + switch (addr->sa_family) { + case AF_INET: return ((struct sockaddr_in *) addr)->sin_port; - else + case AF_INET6: return ((struct sockaddr_in6 *) addr)->sin6_port; + case AF_IB: + sib = (struct sockaddr_ib *) addr; + return htons((u16) (be64_to_cpu(sib->sib_sid) & + be64_to_cpu(sib->sib_sid_mask))); + default: + return 0; + } } static inline int cma_any_port(struct sockaddr *addr) @@ -656,89 +837,99 @@ static inline int cma_any_port(struct sockaddr *addr) return !cma_port(addr); } -static int cma_get_net_info(void *hdr, enum rdma_port_space ps, - u8 *ip_ver, __be16 *port, - union cma_ip_addr **src, union cma_ip_addr **dst) +static void cma_save_ib_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, + struct ib_sa_path_rec *path) { - switch (ps) { - case RDMA_PS_SDP: - if (sdp_get_majv(((struct sdp_hh *) hdr)->sdp_version) != - SDP_MAJ_VERSION) - return -EINVAL; + struct sockaddr_ib *listen_ib, *ib; - *ip_ver = sdp_get_ip_ver(hdr); - *port = ((struct sdp_hh *) hdr)->port; - *src = &((struct sdp_hh *) hdr)->src_addr; - *dst = &((struct sdp_hh *) hdr)->dst_addr; - break; - default: - if (((struct cma_hdr *) hdr)->cma_version != CMA_VERSION) - return -EINVAL; + listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr; + ib = (struct sockaddr_ib *) &id->route.addr.src_addr; + ib->sib_family = listen_ib->sib_family; + ib->sib_pkey = path->pkey; + ib->sib_flowinfo = path->flow_label; + memcpy(&ib->sib_addr, &path->sgid, 16); + ib->sib_sid = listen_ib->sib_sid; + ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL); + ib->sib_scope_id = listen_ib->sib_scope_id; - *ip_ver = cma_get_ip_ver(hdr); - *port = ((struct cma_hdr *) hdr)->port; - *src = &((struct cma_hdr *) hdr)->src_addr; - *dst = &((struct cma_hdr *) hdr)->dst_addr; - break; - } - - if (*ip_ver != 4 && *ip_ver != 6) - return -EINVAL; - return 0; + ib = (struct sockaddr_ib *) &id->route.addr.dst_addr; + ib->sib_family = listen_ib->sib_family; + ib->sib_pkey = path->pkey; + ib->sib_flowinfo = path->flow_label; + memcpy(&ib->sib_addr, &path->dgid, 16); } -static void cma_save_net_info(struct rdma_addr *addr, - struct rdma_addr *listen_addr, - u8 ip_ver, __be16 port, - union cma_ip_addr *src, union cma_ip_addr *dst) +static void cma_save_ip4_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, + struct cma_hdr *hdr) { struct sockaddr_in *listen4, *ip4; + + listen4 = (struct sockaddr_in *) &listen_id->route.addr.src_addr; + ip4 = (struct sockaddr_in *) &id->route.addr.src_addr; + ip4->sin_family = listen4->sin_family; + ip4->sin_addr.s_addr = hdr->dst_addr.ip4.addr; + ip4->sin_port = listen4->sin_port; + + ip4 = (struct sockaddr_in *) &id->route.addr.dst_addr; + ip4->sin_family = listen4->sin_family; + ip4->sin_addr.s_addr = hdr->src_addr.ip4.addr; + ip4->sin_port = hdr->port; +} + +static void cma_save_ip6_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, + struct cma_hdr *hdr) +{ struct sockaddr_in6 *listen6, *ip6; - switch (ip_ver) { + listen6 = (struct sockaddr_in6 *) &listen_id->route.addr.src_addr; + ip6 = (struct sockaddr_in6 *) &id->route.addr.src_addr; + ip6->sin6_family = listen6->sin6_family; + ip6->sin6_addr = hdr->dst_addr.ip6; + ip6->sin6_port = listen6->sin6_port; + + ip6 = (struct sockaddr_in6 *) &id->route.addr.dst_addr; + ip6->sin6_family = listen6->sin6_family; + ip6->sin6_addr = hdr->src_addr.ip6; + ip6->sin6_port = hdr->port; +} + +static int cma_save_net_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id, + struct ib_cm_event *ib_event) +{ + struct cma_hdr *hdr; + + if ((listen_id->route.addr.src_addr.ss_family == AF_IB) && + (ib_event->event == IB_CM_REQ_RECEIVED)) { + cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path); + return 0; + } + + hdr = ib_event->private_data; + if (hdr->cma_version != CMA_VERSION) + return -EINVAL; + + switch (cma_get_ip_ver(hdr)) { case 4: - listen4 = (struct sockaddr_in *) &listen_addr->src_addr; - ip4 = (struct sockaddr_in *) &addr->src_addr; - ip4->sin_family = listen4->sin_family; - ip4->sin_addr.s_addr = dst->ip4.addr; - ip4->sin_port = listen4->sin_port; - - ip4 = (struct sockaddr_in *) &addr->dst_addr; - ip4->sin_family = listen4->sin_family; - ip4->sin_addr.s_addr = src->ip4.addr; - ip4->sin_port = port; + cma_save_ip4_info(id, listen_id, hdr); break; case 6: - listen6 = (struct sockaddr_in6 *) &listen_addr->src_addr; - ip6 = (struct sockaddr_in6 *) &addr->src_addr; - ip6->sin6_family = listen6->sin6_family; - ip6->sin6_addr = dst->ip6; - ip6->sin6_port = listen6->sin6_port; - - ip6 = (struct sockaddr_in6 *) &addr->dst_addr; - ip6->sin6_family = listen6->sin6_family; - ip6->sin6_addr = src->ip6; - ip6->sin6_port = port; + cma_save_ip6_info(id, listen_id, hdr); break; default: - break; + return -EINVAL; } + return 0; } -static inline int cma_user_data_offset(enum rdma_port_space ps) +static inline int cma_user_data_offset(struct rdma_id_private *id_priv) { - switch (ps) { - case RDMA_PS_SDP: - return 0; - default: - return sizeof(struct cma_hdr); - } + return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } static void cma_cancel_route(struct rdma_id_private *id_priv) { - switch (rdma_node_get_transport(id_priv->id.device->node_type)) { - case RDMA_TRANSPORT_IB: + switch (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)) { + case IB_LINK_LAYER_INFINIBAND: if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); break; @@ -773,18 +964,17 @@ static void cma_cancel_listens(struct rdma_id_private *id_priv) } static void cma_cancel_operation(struct rdma_id_private *id_priv, - enum cma_state state) + enum rdma_cm_state state) { switch (state) { - case CMA_ADDR_QUERY: + case RDMA_CM_ADDR_QUERY: rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; - case CMA_ROUTE_QUERY: + case RDMA_CM_ROUTE_QUERY: cma_cancel_route(id_priv); break; - case CMA_LISTEN: - if (cma_any_addr((struct sockaddr *) &id_priv->id.route.addr.src_addr) - && !id_priv->cma_dev) + case RDMA_CM_LISTEN: + if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) cma_cancel_listens(id_priv); break; default: @@ -816,40 +1006,52 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv) mc = container_of(id_priv->mc_list.next, struct cma_multicast, list); list_del(&mc->list); - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); + switch (rdma_port_get_link_layer(id_priv->cma_dev->device, id_priv->id.port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ib_sa_free_multicast(mc->multicast.ib); + kfree(mc); + break; + case IB_LINK_LAYER_ETHERNET: + kref_put(&mc->mcref, release_mc); + break; + default: + break; + } } } void rdma_destroy_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; - enum cma_state state; + enum rdma_cm_state state; id_priv = container_of(id, struct rdma_id_private, id); - state = cma_exch(id_priv, CMA_DESTROYING); + state = cma_exch(id_priv, RDMA_CM_DESTROYING); cma_cancel_operation(id_priv, state); - mutex_lock(&lock); + /* + * Wait for any active callback to finish. New callbacks will find + * the id_priv state set to destroying and abort. + */ + mutex_lock(&id_priv->handler_mutex); + mutex_unlock(&id_priv->handler_mutex); + if (id_priv->cma_dev) { - mutex_unlock(&lock); - switch (rdma_node_get_transport(id->device->node_type)) { + switch (rdma_node_get_transport(id_priv->id.device->node_type)) { case RDMA_TRANSPORT_IB: - if (id_priv->cm_id.ib && !IS_ERR(id_priv->cm_id.ib)) + if (id_priv->cm_id.ib) ib_destroy_cm_id(id_priv->cm_id.ib); break; case RDMA_TRANSPORT_IWARP: - if (id_priv->cm_id.iw && !IS_ERR(id_priv->cm_id.iw)) + if (id_priv->cm_id.iw) iw_destroy_cm_id(id_priv->cm_id.iw); break; default: break; } cma_leave_mc_groups(id_priv); - mutex_lock(&lock); - cma_detach_from_dev(id_priv); + cma_release_dev(id_priv); } - mutex_unlock(&lock); cma_release_port(id_priv); cma_deref_id(id_priv); @@ -887,16 +1089,6 @@ reject: return ret; } -static int cma_verify_rep(struct rdma_id_private *id_priv, void *data) -{ - if (id_priv->id.ps == RDMA_PS_SDP && - sdp_get_majv(((struct sdp_hah *) data)->sdp_version) != - SDP_MAJ_VERSION) - return -EINVAL; - - return 0; -} - static void cma_set_rep_event_data(struct rdma_cm_event *event, struct ib_cm_rep_event_param *rep_data, void *private_data) @@ -918,9 +1110,9 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) int ret = 0; if ((ib_event->event != IB_CM_TIMEWAIT_EXIT && - cma_disable_callback(id_priv, CMA_CONNECT)) || + cma_disable_callback(id_priv, RDMA_CM_CONNECT)) || (ib_event->event == IB_CM_TIMEWAIT_EXIT && - cma_disable_callback(id_priv, CMA_DISCONNECT))) + cma_disable_callback(id_priv, RDMA_CM_DISCONNECT))) return 0; memset(&event, 0, sizeof event); @@ -931,15 +1123,13 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) event.status = -ETIMEDOUT; break; case IB_CM_REP_RECEIVED: - event.status = cma_verify_rep(id_priv, ib_event->private_data); - if (event.status) - event.event = RDMA_CM_EVENT_CONNECT_ERROR; - else if (id_priv->id.qp && id_priv->id.ps != RDMA_PS_SDP) { + if (id_priv->id.qp) { event.status = cma_rep_recv(id_priv); event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR : RDMA_CM_EVENT_ESTABLISHED; - } else + } else { event.event = RDMA_CM_EVENT_CONNECT_RESPONSE; + } cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd, ib_event->private_data); break; @@ -951,7 +1141,8 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) event.status = -ETIMEDOUT; /* fall through */ case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: - if (!cma_comp_exch(id_priv, CMA_CONNECT, CMA_DISCONNECT)) + if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT, + RDMA_CM_DISCONNECT)) goto out; event.event = RDMA_CM_EVENT_DISCONNECTED; break; @@ -978,7 +1169,7 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; - cma_exch(id_priv, CMA_DESTROYING); + cma_exch(id_priv, RDMA_CM_DESTROYING); mutex_unlock(&id_priv->handler_mutex); rdma_destroy_id(&id_priv->id); return ret; @@ -994,53 +1185,44 @@ static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id, struct rdma_id_private *id_priv; struct rdma_cm_id *id; struct rdma_route *rt; - union cma_ip_addr *src, *dst; - __be16 port; - u8 ip_ver; int ret; - if (cma_get_net_info(ib_event->private_data, listen_id->ps, - &ip_ver, &port, &src, &dst)) - goto err; - id = rdma_create_id(listen_id->event_handler, listen_id->context, - listen_id->ps); + listen_id->ps, ib_event->param.req_rcvd.qp_type); if (IS_ERR(id)) - goto err; + return NULL; - cma_save_net_info(&id->route.addr, &listen_id->route.addr, - ip_ver, port, src, dst); + id_priv = container_of(id, struct rdma_id_private, id); + if (cma_save_net_info(id, listen_id, ib_event)) + goto err; rt = &id->route; rt->num_paths = ib_event->param.req_rcvd.alternate_path ? 2 : 1; rt->path_rec = kmalloc(sizeof *rt->path_rec * rt->num_paths, GFP_KERNEL); if (!rt->path_rec) - goto destroy_id; + goto err; rt->path_rec[0] = *ib_event->param.req_rcvd.primary_path; if (rt->num_paths == 2) rt->path_rec[1] = *ib_event->param.req_rcvd.alternate_path; - if (cma_any_addr((struct sockaddr *) &rt->addr.src_addr)) { + if (cma_any_addr(cma_src_addr(id_priv))) { rt->addr.dev_addr.dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(&rt->addr.dev_addr, &rt->path_rec[0].sgid); - ib_addr_set_pkey(&rt->addr.dev_addr, rt->path_rec[0].pkey); + ib_addr_set_pkey(&rt->addr.dev_addr, be16_to_cpu(rt->path_rec[0].pkey)); } else { - ret = rdma_translate_ip((struct sockaddr *) &rt->addr.src_addr, - &rt->addr.dev_addr); + ret = cma_translate_addr(cma_src_addr(id_priv), &rt->addr.dev_addr); if (ret) - goto destroy_id; + goto err; } rdma_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid); - id_priv = container_of(id, struct rdma_id_private, id); - id_priv->state = CMA_CONNECT; + id_priv->state = RDMA_CM_CONNECT; return id_priv; -destroy_id: - rdma_destroy_id(id); err: + rdma_destroy_id(id); return NULL; } @@ -1049,33 +1231,24 @@ static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id, { struct rdma_id_private *id_priv; struct rdma_cm_id *id; - union cma_ip_addr *src, *dst; - __be16 port; - u8 ip_ver; int ret; id = rdma_create_id(listen_id->event_handler, listen_id->context, - listen_id->ps); + listen_id->ps, IB_QPT_UD); if (IS_ERR(id)) return NULL; - - if (cma_get_net_info(ib_event->private_data, listen_id->ps, - &ip_ver, &port, &src, &dst)) + id_priv = container_of(id, struct rdma_id_private, id); + if (cma_save_net_info(id, listen_id, ib_event)) goto err; - cma_save_net_info(&id->route.addr, &listen_id->route.addr, - ip_ver, port, src, dst); - if (!cma_any_addr((struct sockaddr *) &id->route.addr.src_addr)) { - ret = rdma_translate_ip((struct sockaddr *) &id->route.addr.src_addr, - &id->route.addr.dev_addr); + ret = cma_translate_addr(cma_src_addr(id_priv), &id->route.addr.dev_addr); if (ret) goto err; } - id_priv = container_of(id, struct rdma_id_private, id); - id_priv->state = CMA_CONNECT; + id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); @@ -1097,6 +1270,15 @@ static void cma_set_req_event_data(struct rdma_cm_event *event, event->param.conn.qp_num = req_data->remote_qpn; } +static int cma_check_req_qp_type(struct rdma_cm_id *id, struct ib_cm_event *ib_event) +{ + return (((ib_event->event == IB_CM_REQ_RECEIVED) && + (ib_event->param.req_rcvd.qp_type == id->qp_type)) || + ((ib_event->event == IB_CM_SIDR_REQ_RECEIVED) && + (id->qp_type == IB_QPT_UD)) || + (!id->qp_type)); +} + static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) { struct rdma_id_private *listen_id, *conn_id; @@ -1104,13 +1286,16 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) int offset, ret; listen_id = cm_id->context; - if (cma_disable_callback(listen_id, CMA_LISTEN)) + if (!cma_check_req_qp_type(&listen_id->id, ib_event)) + return -EINVAL; + + if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) return -ECONNABORTED; memset(&event, 0, sizeof event); - offset = cma_user_data_offset(listen_id->id.ps); + offset = cma_user_data_offset(listen_id); event.event = RDMA_CM_EVENT_CONNECT_REQUEST; - if (cma_is_ud_ps(listen_id->id.ps)) { + if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) { conn_id = cma_new_udp_id(&listen_id->id, ib_event); event.param.ud.private_data = ib_event->private_data + offset; event.param.ud.private_data_len = @@ -1122,93 +1307,89 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) } if (!conn_id) { ret = -ENOMEM; - goto out; + goto err1; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); - mutex_lock(&lock); - ret = cma_acquire_dev(conn_id); - mutex_unlock(&lock); + ret = cma_acquire_dev(conn_id, listen_id); if (ret) - goto release_conn_id; + goto err2; conn_id->cm_id.ib = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_ib_handler; + /* + * Protect against the user destroying conn_id from another thread + * until we're done accessing it. + */ + atomic_inc(&conn_id->refcount); ret = conn_id->id.event_handler(&conn_id->id, &event); - if (!ret) { - /* - * Acquire mutex to prevent user executing rdma_destroy_id() - * while we're accessing the cm_id. - */ - mutex_lock(&lock); - if (cma_comp(conn_id, CMA_CONNECT) && - !cma_is_ud_ps(conn_id->id.ps)) - ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); - mutex_unlock(&lock); - mutex_unlock(&conn_id->handler_mutex); - goto out; - } + if (ret) + goto err3; + /* + * Acquire mutex to prevent user executing rdma_destroy_id() + * while we're accessing the cm_id. + */ + mutex_lock(&lock); + if (cma_comp(conn_id, RDMA_CM_CONNECT) && + (conn_id->id.qp_type != IB_QPT_UD)) + ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0); + mutex_unlock(&lock); + mutex_unlock(&conn_id->handler_mutex); + mutex_unlock(&listen_id->handler_mutex); + cma_deref_id(conn_id); + return 0; +err3: + cma_deref_id(conn_id); /* Destroy the CM ID by returning a non-zero value. */ conn_id->cm_id.ib = NULL; - -release_conn_id: - cma_exch(conn_id, CMA_DESTROYING); +err2: + cma_exch(conn_id, RDMA_CM_DESTROYING); mutex_unlock(&conn_id->handler_mutex); - rdma_destroy_id(&conn_id->id); - -out: +err1: mutex_unlock(&listen_id->handler_mutex); + if (conn_id) + rdma_destroy_id(&conn_id->id); return ret; } -static __be64 cma_get_service_id(enum rdma_port_space ps, struct sockaddr *addr) +__be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr) { - return cpu_to_be64(((u64)ps << 16) + be16_to_cpu(cma_port(addr))); + if (addr->sa_family == AF_IB) + return ((struct sockaddr_ib *) addr)->sib_sid; + + return cpu_to_be64(((u64)id->ps << 16) + be16_to_cpu(cma_port(addr))); } +EXPORT_SYMBOL(rdma_get_service_id); static void cma_set_compare_data(enum rdma_port_space ps, struct sockaddr *addr, struct ib_cm_compare_data *compare) { struct cma_hdr *cma_data, *cma_mask; - struct sdp_hh *sdp_data, *sdp_mask; __be32 ip4_addr; struct in6_addr ip6_addr; memset(compare, 0, sizeof *compare); cma_data = (void *) compare->data; cma_mask = (void *) compare->mask; - sdp_data = (void *) compare->data; - sdp_mask = (void *) compare->mask; switch (addr->sa_family) { case AF_INET: ip4_addr = ((struct sockaddr_in *) addr)->sin_addr.s_addr; - if (ps == RDMA_PS_SDP) { - sdp_set_ip_ver(sdp_data, 4); - sdp_set_ip_ver(sdp_mask, 0xF); - sdp_data->dst_addr.ip4.addr = ip4_addr; - sdp_mask->dst_addr.ip4.addr = htonl(~0); - } else { - cma_set_ip_ver(cma_data, 4); - cma_set_ip_ver(cma_mask, 0xF); + cma_set_ip_ver(cma_data, 4); + cma_set_ip_ver(cma_mask, 0xF); + if (!cma_any_addr(addr)) { cma_data->dst_addr.ip4.addr = ip4_addr; cma_mask->dst_addr.ip4.addr = htonl(~0); } break; case AF_INET6: ip6_addr = ((struct sockaddr_in6 *) addr)->sin6_addr; - if (ps == RDMA_PS_SDP) { - sdp_set_ip_ver(sdp_data, 6); - sdp_set_ip_ver(sdp_mask, 0xF); - sdp_data->dst_addr.ip6 = ip6_addr; - memset(&sdp_mask->dst_addr.ip6, 0xFF, - sizeof sdp_mask->dst_addr.ip6); - } else { - cma_set_ip_ver(cma_data, 6); - cma_set_ip_ver(cma_mask, 0xF); + cma_set_ip_ver(cma_data, 6); + cma_set_ip_ver(cma_mask, 0xF); + if (!cma_any_addr(addr)) { cma_data->dst_addr.ip6 = ip6_addr; memset(&cma_mask->dst_addr.ip6, 0xFF, sizeof cma_mask->dst_addr.ip6); @@ -1223,10 +1404,11 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; struct rdma_cm_event event; - struct sockaddr_in *sin; int ret = 0; + struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; + struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; - if (cma_disable_callback(id_priv, CMA_CONNECT)) + if (cma_disable_callback(id_priv, RDMA_CM_CONNECT)) return 0; memset(&event, 0, sizeof event); @@ -1235,13 +1417,15 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IW_CM_EVENT_CONNECT_REPLY: - sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr; - *sin = iw_event->local_addr; - sin = (struct sockaddr_in *) &id_priv->id.route.addr.dst_addr; - *sin = iw_event->remote_addr; + memcpy(cma_src_addr(id_priv), laddr, + rdma_addr_size(laddr)); + memcpy(cma_dst_addr(id_priv), raddr, + rdma_addr_size(raddr)); switch (iw_event->status) { case 0: event.event = RDMA_CM_EVENT_ESTABLISHED; + event.param.conn.initiator_depth = iw_event->ird; + event.param.conn.responder_resources = iw_event->ord; break; case -ECONNRESET: case -ECONNREFUSED: @@ -1257,6 +1441,8 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) break; case IW_CM_EVENT_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; + event.param.conn.initiator_depth = iw_event->ird; + event.param.conn.responder_resources = iw_event->ord; break; default: BUG_ON(1); @@ -1269,7 +1455,7 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.iw = NULL; - cma_exch(id_priv, CMA_DESTROYING); + cma_exch(id_priv, RDMA_CM_DESTROYING); mutex_unlock(&id_priv->handler_mutex); rdma_destroy_id(&id_priv->id); return ret; @@ -1284,45 +1470,36 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, { struct rdma_cm_id *new_cm_id; struct rdma_id_private *listen_id, *conn_id; - struct sockaddr_in *sin; - struct net_device *dev = NULL; struct rdma_cm_event event; int ret; struct ib_device_attr attr; + struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; + struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; listen_id = cm_id->context; - if (cma_disable_callback(listen_id, CMA_LISTEN)) + if (cma_disable_callback(listen_id, RDMA_CM_LISTEN)) return -ECONNABORTED; /* Create a new RDMA id for the new IW CM ID */ new_cm_id = rdma_create_id(listen_id->id.event_handler, listen_id->id.context, - RDMA_PS_TCP); + RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(new_cm_id)) { ret = -ENOMEM; goto out; } conn_id = container_of(new_cm_id, struct rdma_id_private, id); mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); - conn_id->state = CMA_CONNECT; + conn_id->state = RDMA_CM_CONNECT; - dev = ip_dev_find(&init_net, iw_event->local_addr.sin_addr.s_addr); - if (!dev) { - ret = -EADDRNOTAVAIL; - mutex_unlock(&conn_id->handler_mutex); - rdma_destroy_id(new_cm_id); - goto out; - } - ret = rdma_copy_addr(&conn_id->id.route.addr.dev_addr, dev, NULL); + ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr, NULL); if (ret) { mutex_unlock(&conn_id->handler_mutex); rdma_destroy_id(new_cm_id); goto out; } - mutex_lock(&lock); - ret = cma_acquire_dev(conn_id); - mutex_unlock(&lock); + ret = cma_acquire_dev(conn_id, listen_id); if (ret) { mutex_unlock(&conn_id->handler_mutex); rdma_destroy_id(new_cm_id); @@ -1333,10 +1510,8 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; - sin = (struct sockaddr_in *) &new_cm_id->route.addr.src_addr; - *sin = iw_event->local_addr; - sin = (struct sockaddr_in *) &new_cm_id->route.addr.dst_addr; - *sin = iw_event->remote_addr; + memcpy(cma_src_addr(conn_id), laddr, rdma_addr_size(laddr)); + memcpy(cma_dst_addr(conn_id), raddr, rdma_addr_size(raddr)); ret = ib_query_device(conn_id->id.device, &attr); if (ret) { @@ -1349,23 +1524,29 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, event.event = RDMA_CM_EVENT_CONNECT_REQUEST; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; - event.param.conn.initiator_depth = attr.max_qp_init_rd_atom; - event.param.conn.responder_resources = attr.max_qp_rd_atom; + event.param.conn.initiator_depth = iw_event->ird; + event.param.conn.responder_resources = iw_event->ord; + + /* + * Protect against the user destroying conn_id from another thread + * until we're done accessing it. + */ + atomic_inc(&conn_id->refcount); ret = conn_id->id.event_handler(&conn_id->id, &event); if (ret) { /* User wants to destroy the CM ID */ conn_id->cm_id.iw = NULL; - cma_exch(conn_id, CMA_DESTROYING); + cma_exch(conn_id, RDMA_CM_DESTROYING); mutex_unlock(&conn_id->handler_mutex); + cma_deref_id(conn_id); rdma_destroy_id(&conn_id->id); goto out; } mutex_unlock(&conn_id->handler_mutex); + cma_deref_id(conn_id); out: - if (dev) - dev_put(dev); mutex_unlock(&listen_id->handler_mutex); return ret; } @@ -1374,17 +1555,19 @@ static int cma_ib_listen(struct rdma_id_private *id_priv) { struct ib_cm_compare_data compare_data; struct sockaddr *addr; + struct ib_cm_id *id; __be64 svc_id; int ret; - id_priv->cm_id.ib = ib_create_cm_id(id_priv->id.device, cma_req_handler, - id_priv); - if (IS_ERR(id_priv->cm_id.ib)) - return PTR_ERR(id_priv->cm_id.ib); + id = ib_create_cm_id(id_priv->id.device, cma_req_handler, id_priv); + if (IS_ERR(id)) + return PTR_ERR(id); + + id_priv->cm_id.ib = id; - addr = (struct sockaddr *) &id_priv->id.route.addr.src_addr; - svc_id = cma_get_service_id(id_priv->id.ps, addr); - if (cma_any_addr(addr)) + addr = cma_src_addr(id_priv); + svc_id = rdma_get_service_id(&id_priv->id, addr); + if (cma_any_addr(addr) && !id_priv->afonly) ret = ib_cm_listen(id_priv->cm_id.ib, svc_id, 0, NULL); else { cma_set_compare_data(id_priv->id.ps, addr, &compare_data); @@ -1402,16 +1585,18 @@ static int cma_ib_listen(struct rdma_id_private *id_priv) static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog) { int ret; - struct sockaddr_in *sin; + struct iw_cm_id *id; + + id = iw_create_cm_id(id_priv->id.device, + iw_conn_req_handler, + id_priv); + if (IS_ERR(id)) + return PTR_ERR(id); - id_priv->cm_id.iw = iw_create_cm_id(id_priv->id.device, - iw_conn_req_handler, - id_priv); - if (IS_ERR(id_priv->cm_id.iw)) - return PTR_ERR(id_priv->cm_id.iw); + id_priv->cm_id.iw = id; - sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr; - id_priv->cm_id.iw->local_addr = *sin; + memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv), + rdma_addr_size(cma_src_addr(id_priv))); ret = iw_cm_listen(id_priv->cm_id.iw, backlog); @@ -1440,20 +1625,26 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv, struct rdma_cm_id *id; int ret; - id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps); + if (cma_family(id_priv) == AF_IB && + rdma_node_get_transport(cma_dev->device->node_type) != RDMA_TRANSPORT_IB) + return; + + id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps, + id_priv->id.qp_type); if (IS_ERR(id)) return; dev_id_priv = container_of(id, struct rdma_id_private, id); - dev_id_priv->state = CMA_ADDR_BOUND; - memcpy(&id->route.addr.src_addr, &id_priv->id.route.addr.src_addr, - ip_addr_size((struct sockaddr *) &id_priv->id.route.addr.src_addr)); + dev_id_priv->state = RDMA_CM_ADDR_BOUND; + memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv), + rdma_addr_size(cma_src_addr(id_priv))); cma_attach_to_dev(dev_id_priv, cma_dev); list_add_tail(&dev_id_priv->listen_list, &id_priv->listen_list); atomic_inc(&id_priv->refcount); dev_id_priv->internal_id = 1; + dev_id_priv->afonly = id_priv->afonly; ret = rdma_listen(id, id_priv->backlog); if (ret) @@ -1472,50 +1663,6 @@ static void cma_listen_on_all(struct rdma_id_private *id_priv) mutex_unlock(&lock); } -int rdma_listen(struct rdma_cm_id *id, int backlog) -{ - struct rdma_id_private *id_priv; - int ret; - - id_priv = container_of(id, struct rdma_id_private, id); - if (id_priv->state == CMA_IDLE) { - ((struct sockaddr *) &id->route.addr.src_addr)->sa_family = AF_INET; - ret = rdma_bind_addr(id, (struct sockaddr *) &id->route.addr.src_addr); - if (ret) - return ret; - } - - if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_LISTEN)) - return -EINVAL; - - id_priv->backlog = backlog; - if (id->device) { - switch (rdma_node_get_transport(id->device->node_type)) { - case RDMA_TRANSPORT_IB: - ret = cma_ib_listen(id_priv); - if (ret) - goto err; - break; - case RDMA_TRANSPORT_IWARP: - ret = cma_iw_listen(id_priv, backlog); - if (ret) - goto err; - break; - default: - ret = -ENOSYS; - goto err; - } - } else - cma_listen_on_all(id_priv); - - return 0; -err: - id_priv->backlog = 0; - cma_comp_exch(id_priv, CMA_LISTEN, CMA_ADDR_BOUND); - return ret; -} -EXPORT_SYMBOL(rdma_listen); - void rdma_set_service_type(struct rdma_cm_id *id, int tos) { struct rdma_id_private *id_priv; @@ -1537,8 +1684,8 @@ static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec, route->num_paths = 1; *route->path_rec = *path_rec; } else { - work->old_state = CMA_ROUTE_QUERY; - work->new_state = CMA_ADDR_RESOLVED; + work->old_state = RDMA_CM_ROUTE_QUERY; + work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_ERROR; work->event.status = status; } @@ -1549,31 +1696,39 @@ static void cma_query_handler(int status, struct ib_sa_path_rec *path_rec, static int cma_query_ib_route(struct rdma_id_private *id_priv, int timeout_ms, struct cma_work *work) { - struct rdma_addr *addr = &id_priv->id.route.addr; + struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct ib_sa_path_rec path_rec; ib_sa_comp_mask comp_mask; struct sockaddr_in6 *sin6; + struct sockaddr_ib *sib; memset(&path_rec, 0, sizeof path_rec); - rdma_addr_get_sgid(&addr->dev_addr, &path_rec.sgid); - rdma_addr_get_dgid(&addr->dev_addr, &path_rec.dgid); - path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(&addr->dev_addr)); + rdma_addr_get_sgid(dev_addr, &path_rec.sgid); + rdma_addr_get_dgid(dev_addr, &path_rec.dgid); + path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); path_rec.numb_path = 1; path_rec.reversible = 1; - path_rec.service_id = cma_get_service_id(id_priv->id.ps, - (struct sockaddr *) &addr->dst_addr); + path_rec.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID; - if (addr->src_addr.ss_family == AF_INET) { + switch (cma_family(id_priv)) { + case AF_INET: path_rec.qos_class = cpu_to_be16((u16) id_priv->tos); comp_mask |= IB_SA_PATH_REC_QOS_CLASS; - } else { - sin6 = (struct sockaddr_in6 *) &addr->src_addr; + break; + case AF_INET6: + sin6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; + break; + case AF_IB: + sib = (struct sockaddr_ib *) cma_src_addr(id_priv); + path_rec.traffic_class = (u8) (be32_to_cpu(sib->sib_flowinfo) >> 20); + comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; + break; } id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device, @@ -1596,7 +1751,7 @@ static void cma_work_handler(struct work_struct *_work) goto out; if (id_priv->id.event_handler(&id_priv->id, &work->event)) { - cma_exch(id_priv, CMA_DESTROYING); + cma_exch(id_priv, RDMA_CM_DESTROYING); destroy = 1; } out: @@ -1614,12 +1769,12 @@ static void cma_ndev_work_handler(struct work_struct *_work) int destroy = 0; mutex_lock(&id_priv->handler_mutex); - if (id_priv->state == CMA_DESTROYING || - id_priv->state == CMA_DEVICE_REMOVAL) + if (id_priv->state == RDMA_CM_DESTROYING || + id_priv->state == RDMA_CM_DEVICE_REMOVAL) goto out; if (id_priv->id.event_handler(&id_priv->id, &work->event)) { - cma_exch(id_priv, CMA_DESTROYING); + cma_exch(id_priv, RDMA_CM_DESTROYING); destroy = 1; } @@ -1643,8 +1798,8 @@ static int cma_resolve_ib_route(struct rdma_id_private *id_priv, int timeout_ms) work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); - work->old_state = CMA_ROUTE_QUERY; - work->new_state = CMA_ROUTE_RESOLVED; + work->old_state = RDMA_CM_ROUTE_QUERY; + work->new_state = RDMA_CM_ROUTE_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; route->path_rec = kmalloc(sizeof *route->path_rec, GFP_KERNEL); @@ -1673,19 +1828,21 @@ int rdma_set_ib_paths(struct rdma_cm_id *id, int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_comp_exch(id_priv, CMA_ADDR_RESOLVED, CMA_ROUTE_RESOLVED)) + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, + RDMA_CM_ROUTE_RESOLVED)) return -EINVAL; - id->route.path_rec = kmalloc(sizeof *path_rec * num_paths, GFP_KERNEL); + id->route.path_rec = kmemdup(path_rec, sizeof *path_rec * num_paths, + GFP_KERNEL); if (!id->route.path_rec) { ret = -ENOMEM; goto err; } - memcpy(id->route.path_rec, path_rec, sizeof *path_rec * num_paths); + id->route.num_paths = num_paths; return 0; err: - cma_comp_exch(id_priv, CMA_ROUTE_RESOLVED, CMA_ADDR_RESOLVED); + cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_set_ib_paths); @@ -1700,26 +1857,128 @@ static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms) work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); - work->old_state = CMA_ROUTE_QUERY; - work->new_state = CMA_ROUTE_RESOLVED; + work->old_state = RDMA_CM_ROUTE_QUERY; + work->new_state = RDMA_CM_ROUTE_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; queue_work(cma_wq, &work->work); return 0; } +static int iboe_tos_to_sl(struct net_device *ndev, int tos) +{ + int prio; + struct net_device *dev; + + prio = rt_tos2priority(tos); + dev = ndev->priv_flags & IFF_802_1Q_VLAN ? + vlan_dev_real_dev(ndev) : ndev; + + if (dev->num_tc) + return netdev_get_prio_tc_map(dev, prio); + +#if IS_ENABLED(CONFIG_VLAN_8021Q) + if (ndev->priv_flags & IFF_802_1Q_VLAN) + return (vlan_dev_get_egress_qos_mask(ndev, prio) & + VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; +#endif + return 0; +} + +static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) +{ + struct rdma_route *route = &id_priv->id.route; + struct rdma_addr *addr = &route->addr; + struct cma_work *work; + int ret; + struct net_device *ndev = NULL; + + + work = kzalloc(sizeof *work, GFP_KERNEL); + if (!work) + return -ENOMEM; + + work->id = id_priv; + INIT_WORK(&work->work, cma_work_handler); + + route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL); + if (!route->path_rec) { + ret = -ENOMEM; + goto err1; + } + + route->num_paths = 1; + + if (addr->dev_addr.bound_dev_if) + ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); + if (!ndev) { + ret = -ENODEV; + goto err2; + } + + route->path_rec->vlan_id = rdma_vlan_dev_vlan_id(ndev); + memcpy(route->path_rec->dmac, addr->dev_addr.dst_dev_addr, ETH_ALEN); + memcpy(route->path_rec->smac, ndev->dev_addr, ndev->addr_len); + + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, + &route->path_rec->sgid); + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr, + &route->path_rec->dgid); + + route->path_rec->hop_limit = 1; + route->path_rec->reversible = 1; + route->path_rec->pkey = cpu_to_be16(0xffff); + route->path_rec->mtu_selector = IB_SA_EQ; + route->path_rec->sl = iboe_tos_to_sl(ndev, id_priv->tos); + route->path_rec->mtu = iboe_get_mtu(ndev->mtu); + route->path_rec->rate_selector = IB_SA_EQ; + route->path_rec->rate = iboe_get_rate(ndev); + dev_put(ndev); + route->path_rec->packet_life_time_selector = IB_SA_EQ; + route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; + if (!route->path_rec->mtu) { + ret = -EINVAL; + goto err2; + } + + work->old_state = RDMA_CM_ROUTE_QUERY; + work->new_state = RDMA_CM_ROUTE_RESOLVED; + work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; + work->event.status = 0; + + queue_work(cma_wq, &work->work); + + return 0; + +err2: + kfree(route->path_rec); + route->path_rec = NULL; +err1: + kfree(work); + return ret; +} + int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_comp_exch(id_priv, CMA_ADDR_RESOLVED, CMA_ROUTE_QUERY)) + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_QUERY)) return -EINVAL; atomic_inc(&id_priv->refcount); switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - ret = cma_resolve_ib_route(id_priv, timeout_ms); + switch (rdma_port_get_link_layer(id->device, id->port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ret = cma_resolve_ib_route(id_priv, timeout_ms); + break; + case IB_LINK_LAYER_ETHERNET: + ret = cma_resolve_iboe_route(id_priv); + break; + default: + ret = -ENOSYS; + } break; case RDMA_TRANSPORT_IWARP: ret = cma_resolve_iw_route(id_priv, timeout_ms); @@ -1733,34 +1992,63 @@ int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms) return 0; err: - cma_comp_exch(id_priv, CMA_ROUTE_QUERY, CMA_ADDR_RESOLVED); + cma_comp_exch(id_priv, RDMA_CM_ROUTE_QUERY, RDMA_CM_ADDR_RESOLVED); cma_deref_id(id_priv); return ret; } EXPORT_SYMBOL(rdma_resolve_route); +static void cma_set_loopback(struct sockaddr *addr) +{ + switch (addr->sa_family) { + case AF_INET: + ((struct sockaddr_in *) addr)->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + break; + case AF_INET6: + ipv6_addr_set(&((struct sockaddr_in6 *) addr)->sin6_addr, + 0, 0, 0, htonl(1)); + break; + default: + ib_addr_set(&((struct sockaddr_ib *) addr)->sib_addr, + 0, 0, 0, htonl(1)); + break; + } +} + static int cma_bind_loopback(struct rdma_id_private *id_priv) { - struct cma_device *cma_dev; + struct cma_device *cma_dev, *cur_dev; struct ib_port_attr port_attr; union ib_gid gid; u16 pkey; int ret; u8 p; + cma_dev = NULL; mutex_lock(&lock); - if (list_empty(&dev_list)) { + list_for_each_entry(cur_dev, &dev_list, list) { + if (cma_family(id_priv) == AF_IB && + rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB) + continue; + + if (!cma_dev) + cma_dev = cur_dev; + + for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { + if (!ib_query_port(cur_dev->device, p, &port_attr) && + port_attr.state == IB_PORT_ACTIVE) { + cma_dev = cur_dev; + goto port_found; + } + } + } + + if (!cma_dev) { ret = -ENODEV; goto out; } - list_for_each_entry(cma_dev, &dev_list, list) - for (p = 1; p <= cma_dev->device->phys_port_cnt; ++p) - if (!ib_query_port(cma_dev->device, p, &port_attr) && - port_attr.state == IB_PORT_ACTIVE) - goto port_found; p = 1; - cma_dev = list_entry(dev_list.next, struct cma_device, list); port_found: ret = ib_get_cached_gid(cma_dev->device, p, 0, &gid); @@ -1772,13 +2060,14 @@ port_found: goto out; id_priv->id.route.addr.dev_addr.dev_type = - (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB) ? + (rdma_port_get_link_layer(cma_dev->device, p) == IB_LINK_LAYER_INFINIBAND) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey); id_priv->id.port_num = p; cma_attach_to_dev(id_priv, cma_dev); + cma_set_loopback(cma_src_addr(id_priv)); out: mutex_unlock(&lock); return ret; @@ -1792,34 +2081,25 @@ static void addr_handler(int status, struct sockaddr *src_addr, memset(&event, 0, sizeof event); mutex_lock(&id_priv->handler_mutex); - - /* - * Grab mutex to block rdma_destroy_id() from removing the device while - * we're trying to acquire it. - */ - mutex_lock(&lock); - if (!cma_comp_exch(id_priv, CMA_ADDR_QUERY, CMA_ADDR_RESOLVED)) { - mutex_unlock(&lock); + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, + RDMA_CM_ADDR_RESOLVED)) goto out; - } + memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr)); if (!status && !id_priv->cma_dev) - status = cma_acquire_dev(id_priv); - mutex_unlock(&lock); + status = cma_acquire_dev(id_priv, NULL); if (status) { - if (!cma_comp_exch(id_priv, CMA_ADDR_RESOLVED, CMA_ADDR_BOUND)) + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, + RDMA_CM_ADDR_BOUND)) goto out; event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = status; - } else { - memcpy(&id_priv->id.route.addr.src_addr, src_addr, - ip_addr_size(src_addr)); + } else event.event = RDMA_CM_EVENT_ADDR_RESOLVED; - } if (id_priv->id.event_handler(&id_priv->id, &event)) { - cma_exch(id_priv, CMA_DESTROYING); + cma_exch(id_priv, RDMA_CM_DESTROYING); mutex_unlock(&id_priv->handler_mutex); cma_deref_id(id_priv); rdma_destroy_id(&id_priv->id); @@ -1833,7 +2113,6 @@ out: static int cma_resolve_loopback(struct rdma_id_private *id_priv) { struct cma_work *work; - struct sockaddr *src, *dst; union ib_gid gid; int ret; @@ -1850,22 +2129,40 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv) rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid); rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid); - src = (struct sockaddr *) &id_priv->id.route.addr.src_addr; - if (cma_zero_addr(src)) { - dst = (struct sockaddr *) &id_priv->id.route.addr.dst_addr; - if ((src->sa_family = dst->sa_family) == AF_INET) { - ((struct sockaddr_in *) src)->sin_addr.s_addr = - ((struct sockaddr_in *) dst)->sin_addr.s_addr; - } else { - ipv6_addr_copy(&((struct sockaddr_in6 *) src)->sin6_addr, - &((struct sockaddr_in6 *) dst)->sin6_addr); - } + work->id = id_priv; + INIT_WORK(&work->work, cma_work_handler); + work->old_state = RDMA_CM_ADDR_QUERY; + work->new_state = RDMA_CM_ADDR_RESOLVED; + work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; + queue_work(cma_wq, &work->work); + return 0; +err: + kfree(work); + return ret; +} + +static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) +{ + struct cma_work *work; + int ret; + + work = kzalloc(sizeof *work, GFP_KERNEL); + if (!work) + return -ENOMEM; + + if (!id_priv->cma_dev) { + ret = cma_resolve_ib_dev(id_priv); + if (ret) + goto err; } + rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *) + &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr)); + work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); - work->old_state = CMA_ADDR_QUERY; - work->new_state = CMA_ADDR_RESOLVED; + work->old_state = RDMA_CM_ADDR_QUERY; + work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; queue_work(cma_wq, &work->work); return 0; @@ -1879,9 +2176,13 @@ static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, { if (!src_addr || !src_addr->sa_family) { src_addr = (struct sockaddr *) &id->route.addr.src_addr; - if ((src_addr->sa_family = dst_addr->sa_family) == AF_INET6) { + src_addr->sa_family = dst_addr->sa_family; + if (dst_addr->sa_family == AF_INET6) { ((struct sockaddr_in6 *) src_addr)->sin6_scope_id = ((struct sockaddr_in6 *) dst_addr)->sin6_scope_id; + } else if (dst_addr->sa_family == AF_IB) { + ((struct sockaddr_ib *) src_addr)->sib_pkey = + ((struct sockaddr_ib *) dst_addr)->sib_pkey; } } return rdma_bind_addr(id, src_addr); @@ -1894,41 +2195,107 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (id_priv->state == CMA_IDLE) { + if (id_priv->state == RDMA_CM_IDLE) { ret = cma_bind_addr(id, src_addr, dst_addr); if (ret) return ret; } - if (!cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_ADDR_QUERY)) + if (cma_family(id_priv) != dst_addr->sa_family) + return -EINVAL; + + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) return -EINVAL; atomic_inc(&id_priv->refcount); - memcpy(&id->route.addr.dst_addr, dst_addr, ip_addr_size(dst_addr)); - if (cma_any_addr(dst_addr)) + memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); + if (cma_any_addr(dst_addr)) { ret = cma_resolve_loopback(id_priv); - else - ret = rdma_resolve_ip(&addr_client, (struct sockaddr *) &id->route.addr.src_addr, - dst_addr, &id->route.addr.dev_addr, - timeout_ms, addr_handler, id_priv); + } else { + if (dst_addr->sa_family == AF_IB) { + ret = cma_resolve_ib_addr(id_priv); + } else { + ret = rdma_resolve_ip(&addr_client, cma_src_addr(id_priv), + dst_addr, &id->route.addr.dev_addr, + timeout_ms, addr_handler, id_priv); + } + } if (ret) goto err; return 0; err: - cma_comp_exch(id_priv, CMA_ADDR_QUERY, CMA_ADDR_BOUND); + cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); cma_deref_id(id_priv); return ret; } EXPORT_SYMBOL(rdma_resolve_addr); +int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) +{ + struct rdma_id_private *id_priv; + unsigned long flags; + int ret; + + id_priv = container_of(id, struct rdma_id_private, id); + spin_lock_irqsave(&id_priv->lock, flags); + if (reuse || id_priv->state == RDMA_CM_IDLE) { + id_priv->reuseaddr = reuse; + ret = 0; + } else { + ret = -EINVAL; + } + spin_unlock_irqrestore(&id_priv->lock, flags); + return ret; +} +EXPORT_SYMBOL(rdma_set_reuseaddr); + +int rdma_set_afonly(struct rdma_cm_id *id, int afonly) +{ + struct rdma_id_private *id_priv; + unsigned long flags; + int ret; + + id_priv = container_of(id, struct rdma_id_private, id); + spin_lock_irqsave(&id_priv->lock, flags); + if (id_priv->state == RDMA_CM_IDLE || id_priv->state == RDMA_CM_ADDR_BOUND) { + id_priv->options |= (1 << CMA_OPTION_AFONLY); + id_priv->afonly = afonly; + ret = 0; + } else { + ret = -EINVAL; + } + spin_unlock_irqrestore(&id_priv->lock, flags); + return ret; +} +EXPORT_SYMBOL(rdma_set_afonly); + static void cma_bind_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { - struct sockaddr_in *sin; + struct sockaddr *addr; + struct sockaddr_ib *sib; + u64 sid, mask; + __be16 port; + + addr = cma_src_addr(id_priv); + port = htons(bind_list->port); - sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr; - sin->sin_port = htons(bind_list->port); + switch (addr->sa_family) { + case AF_INET: + ((struct sockaddr_in *) addr)->sin_port = port; + break; + case AF_INET6: + ((struct sockaddr_in6 *) addr)->sin6_port = port; + break; + case AF_IB: + sib = (struct sockaddr_ib *) addr; + sid = be64_to_cpu(sib->sib_sid); + mask = be64_to_cpu(sib->sib_sid_mask); + sib->sib_sid = cpu_to_be64((sid & mask) | (u64) ntohs(port)); + sib->sib_sid_mask = cpu_to_be64(~0ULL); + break; + } id_priv->bind_list = bind_list; hlist_add_head(&id_priv->node, &bind_list->owners); } @@ -1937,115 +2304,169 @@ static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv, unsigned short snum) { struct rdma_bind_list *bind_list; - int port, ret; + int ret; bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; - do { - ret = idr_get_new_above(ps, bind_list, snum, &port); - } while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL)); - - if (ret) - goto err1; - - if (port != snum) { - ret = -EADDRNOTAVAIL; - goto err2; - } + ret = idr_alloc(ps, bind_list, snum, snum + 1, GFP_KERNEL); + if (ret < 0) + goto err; bind_list->ps = ps; - bind_list->port = (unsigned short) port; + bind_list->port = (unsigned short)ret; cma_bind_port(bind_list, id_priv); return 0; -err2: - idr_remove(ps, port); -err1: +err: kfree(bind_list); - return ret; + return ret == -ENOSPC ? -EADDRNOTAVAIL : ret; } static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv) { - struct rdma_bind_list *bind_list; - int port, ret, low, high; - - bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); - if (!bind_list) - return -ENOMEM; + static unsigned int last_used_port; + int low, high, remaining; + unsigned int rover; + inet_get_local_port_range(&init_net, &low, &high); + remaining = (high - low) + 1; + rover = prandom_u32() % remaining + low; retry: - /* FIXME: add proper port randomization per like inet_csk_get_port */ - do { - ret = idr_get_new_above(ps, bind_list, next_port, &port); - } while ((ret == -EAGAIN) && idr_pre_get(ps, GFP_KERNEL)); + if (last_used_port != rover && + !idr_find(ps, (unsigned short) rover)) { + int ret = cma_alloc_port(ps, id_priv, rover); + /* + * Remember previously used port number in order to avoid + * re-using same port immediately after it is closed. + */ + if (!ret) + last_used_port = rover; + if (ret != -EADDRNOTAVAIL) + return ret; + } + if (--remaining) { + rover++; + if ((rover < low) || (rover > high)) + rover = low; + goto retry; + } + return -EADDRNOTAVAIL; +} - if (ret) - goto err1; +/* + * Check that the requested port is available. This is called when trying to + * bind to a specific port, or when trying to listen on a bound port. In + * the latter case, the provided id_priv may already be on the bind_list, but + * we still need to check that it's okay to start listening. + */ +static int cma_check_port(struct rdma_bind_list *bind_list, + struct rdma_id_private *id_priv, uint8_t reuseaddr) +{ + struct rdma_id_private *cur_id; + struct sockaddr *addr, *cur_addr; - inet_get_local_port_range(&low, &high); - if (port > high) { - if (next_port != low) { - idr_remove(ps, port); - next_port = low; - goto retry; - } - ret = -EADDRNOTAVAIL; - goto err2; - } + addr = cma_src_addr(id_priv); + hlist_for_each_entry(cur_id, &bind_list->owners, node) { + if (id_priv == cur_id) + continue; - if (port == high) - next_port = low; - else - next_port = port + 1; + if ((cur_id->state != RDMA_CM_LISTEN) && reuseaddr && + cur_id->reuseaddr) + continue; - bind_list->ps = ps; - bind_list->port = (unsigned short) port; - cma_bind_port(bind_list, id_priv); + cur_addr = cma_src_addr(cur_id); + if (id_priv->afonly && cur_id->afonly && + (addr->sa_family != cur_addr->sa_family)) + continue; + + if (cma_any_addr(addr) || cma_any_addr(cur_addr)) + return -EADDRNOTAVAIL; + + if (!cma_addr_cmp(addr, cur_addr)) + return -EADDRINUSE; + } return 0; -err2: - idr_remove(ps, port); -err1: - kfree(bind_list); - return ret; } static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv) { - struct rdma_id_private *cur_id; - struct sockaddr_in *sin, *cur_sin; struct rdma_bind_list *bind_list; - struct hlist_node *node; unsigned short snum; + int ret; - sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr; - snum = ntohs(sin->sin_port); + snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; bind_list = idr_find(ps, snum); - if (!bind_list) - return cma_alloc_port(ps, id_priv, snum); + if (!bind_list) { + ret = cma_alloc_port(ps, id_priv, snum); + } else { + ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr); + if (!ret) + cma_bind_port(bind_list, id_priv); + } + return ret; +} - /* - * We don't support binding to any address if anyone is bound to - * a specific address on the same port. - */ - if (cma_any_addr((struct sockaddr *) &id_priv->id.route.addr.src_addr)) - return -EADDRNOTAVAIL; +static int cma_bind_listen(struct rdma_id_private *id_priv) +{ + struct rdma_bind_list *bind_list = id_priv->bind_list; + int ret = 0; - hlist_for_each_entry(cur_id, node, &bind_list->owners, node) { - if (cma_any_addr((struct sockaddr *) &cur_id->id.route.addr.src_addr)) - return -EADDRNOTAVAIL; + mutex_lock(&lock); + if (bind_list->owners.first->next) + ret = cma_check_port(bind_list, id_priv, 0); + mutex_unlock(&lock); + return ret; +} - cur_sin = (struct sockaddr_in *) &cur_id->id.route.addr.src_addr; - if (sin->sin_addr.s_addr == cur_sin->sin_addr.s_addr) - return -EADDRINUSE; +static struct idr *cma_select_inet_ps(struct rdma_id_private *id_priv) +{ + switch (id_priv->id.ps) { + case RDMA_PS_TCP: + return &tcp_ps; + case RDMA_PS_UDP: + return &udp_ps; + case RDMA_PS_IPOIB: + return &ipoib_ps; + case RDMA_PS_IB: + return &ib_ps; + default: + return NULL; } +} - cma_bind_port(bind_list, id_priv); - return 0; +static struct idr *cma_select_ib_ps(struct rdma_id_private *id_priv) +{ + struct idr *ps = NULL; + struct sockaddr_ib *sib; + u64 sid_ps, mask, sid; + + sib = (struct sockaddr_ib *) cma_src_addr(id_priv); + mask = be64_to_cpu(sib->sib_sid_mask) & RDMA_IB_IP_PS_MASK; + sid = be64_to_cpu(sib->sib_sid) & mask; + + if ((id_priv->id.ps == RDMA_PS_IB) && (sid == (RDMA_IB_IP_PS_IB & mask))) { + sid_ps = RDMA_IB_IP_PS_IB; + ps = &ib_ps; + } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_TCP)) && + (sid == (RDMA_IB_IP_PS_TCP & mask))) { + sid_ps = RDMA_IB_IP_PS_TCP; + ps = &tcp_ps; + } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_UDP)) && + (sid == (RDMA_IB_IP_PS_UDP & mask))) { + sid_ps = RDMA_IB_IP_PS_UDP; + ps = &udp_ps; + } + + if (ps) { + sib->sib_sid = cpu_to_be64(sid_ps | ntohs(cma_port((struct sockaddr *) sib))); + sib->sib_sid_mask = cpu_to_be64(RDMA_IB_IP_PS_MASK | + be64_to_cpu(sib->sib_sid_mask)); + } + return ps; } static int cma_get_port(struct rdma_id_private *id_priv) @@ -2053,25 +2474,15 @@ static int cma_get_port(struct rdma_id_private *id_priv) struct idr *ps; int ret; - switch (id_priv->id.ps) { - case RDMA_PS_SDP: - ps = &sdp_ps; - break; - case RDMA_PS_TCP: - ps = &tcp_ps; - break; - case RDMA_PS_UDP: - ps = &udp_ps; - break; - case RDMA_PS_IPOIB: - ps = &ipoib_ps; - break; - default: + if (cma_family(id_priv) != AF_IB) + ps = cma_select_inet_ps(id_priv); + else + ps = cma_select_ib_ps(id_priv); + if (!ps) return -EPROTONOSUPPORT; - } mutex_lock(&lock); - if (cma_any_port((struct sockaddr *) &id_priv->id.route.addr.src_addr)) + if (cma_any_port(cma_src_addr(id_priv))) ret = cma_alloc_any_port(ps, id_priv); else ret = cma_use_port(ps, id_priv); @@ -2083,15 +2494,18 @@ static int cma_get_port(struct rdma_id_private *id_priv) static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, struct sockaddr *addr) { -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 *sin6; if (addr->sa_family != AF_INET6) return 0; sin6 = (struct sockaddr_in6 *) addr; - if ((ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) && - !sin6->sin6_scope_id) + + if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) + return 0; + + if (!sin6->sin6_scope_id) return -EINVAL; dev_addr->bound_dev_if = sin6->sin6_scope_id; @@ -2099,110 +2513,132 @@ static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, return 0; } +int rdma_listen(struct rdma_cm_id *id, int backlog) +{ + struct rdma_id_private *id_priv; + int ret; + + id_priv = container_of(id, struct rdma_id_private, id); + if (id_priv->state == RDMA_CM_IDLE) { + id->route.addr.src_addr.ss_family = AF_INET; + ret = rdma_bind_addr(id, cma_src_addr(id_priv)); + if (ret) + return ret; + } + + if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) + return -EINVAL; + + if (id_priv->reuseaddr) { + ret = cma_bind_listen(id_priv); + if (ret) + goto err; + } + + id_priv->backlog = backlog; + if (id->device) { + switch (rdma_node_get_transport(id->device->node_type)) { + case RDMA_TRANSPORT_IB: + ret = cma_ib_listen(id_priv); + if (ret) + goto err; + break; + case RDMA_TRANSPORT_IWARP: + ret = cma_iw_listen(id_priv, backlog); + if (ret) + goto err; + break; + default: + ret = -ENOSYS; + goto err; + } + } else + cma_listen_on_all(id_priv); + + return 0; +err: + id_priv->backlog = 0; + cma_comp_exch(id_priv, RDMA_CM_LISTEN, RDMA_CM_ADDR_BOUND); + return ret; +} +EXPORT_SYMBOL(rdma_listen); + int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; int ret; - if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6) + if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && + addr->sa_family != AF_IB) return -EAFNOSUPPORT; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_comp_exch(id_priv, CMA_IDLE, CMA_ADDR_BOUND)) + if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL; ret = cma_check_linklocal(&id->route.addr.dev_addr, addr); if (ret) goto err1; - if (cma_loopback_addr(addr)) { - ret = cma_bind_loopback(id_priv); - } else if (!cma_zero_addr(addr)) { - ret = rdma_translate_ip(addr, &id->route.addr.dev_addr); + memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); + if (!cma_any_addr(addr)) { + ret = cma_translate_addr(addr, &id->route.addr.dev_addr); if (ret) goto err1; - mutex_lock(&lock); - ret = cma_acquire_dev(id_priv); - mutex_unlock(&lock); + ret = cma_acquire_dev(id_priv, NULL); if (ret) goto err1; } - memcpy(&id->route.addr.src_addr, addr, ip_addr_size(addr)); + if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) { + if (addr->sa_family == AF_INET) + id_priv->afonly = 1; +#if IS_ENABLED(CONFIG_IPV6) + else if (addr->sa_family == AF_INET6) + id_priv->afonly = init_net.ipv6.sysctl.bindv6only; +#endif + } ret = cma_get_port(id_priv); if (ret) goto err2; return 0; err2: - if (id_priv->cma_dev) { - mutex_lock(&lock); - cma_detach_from_dev(id_priv); - mutex_unlock(&lock); - } + if (id_priv->cma_dev) + cma_release_dev(id_priv); err1: - cma_comp_exch(id_priv, CMA_ADDR_BOUND, CMA_IDLE); + cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } EXPORT_SYMBOL(rdma_bind_addr); -static int cma_format_hdr(void *hdr, enum rdma_port_space ps, - struct rdma_route *route) +static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) { struct cma_hdr *cma_hdr; - struct sdp_hh *sdp_hdr; - if (route->addr.src_addr.ss_family == AF_INET) { + cma_hdr = hdr; + cma_hdr->cma_version = CMA_VERSION; + if (cma_family(id_priv) == AF_INET) { struct sockaddr_in *src4, *dst4; - src4 = (struct sockaddr_in *) &route->addr.src_addr; - dst4 = (struct sockaddr_in *) &route->addr.dst_addr; - - switch (ps) { - case RDMA_PS_SDP: - sdp_hdr = hdr; - if (sdp_get_majv(sdp_hdr->sdp_version) != SDP_MAJ_VERSION) - return -EINVAL; - sdp_set_ip_ver(sdp_hdr, 4); - sdp_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; - sdp_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; - sdp_hdr->port = src4->sin_port; - break; - default: - cma_hdr = hdr; - cma_hdr->cma_version = CMA_VERSION; - cma_set_ip_ver(cma_hdr, 4); - cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; - cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; - cma_hdr->port = src4->sin_port; - break; - } - } else { + src4 = (struct sockaddr_in *) cma_src_addr(id_priv); + dst4 = (struct sockaddr_in *) cma_dst_addr(id_priv); + + cma_set_ip_ver(cma_hdr, 4); + cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; + cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; + cma_hdr->port = src4->sin_port; + } else if (cma_family(id_priv) == AF_INET6) { struct sockaddr_in6 *src6, *dst6; - src6 = (struct sockaddr_in6 *) &route->addr.src_addr; - dst6 = (struct sockaddr_in6 *) &route->addr.dst_addr; - - switch (ps) { - case RDMA_PS_SDP: - sdp_hdr = hdr; - if (sdp_get_majv(sdp_hdr->sdp_version) != SDP_MAJ_VERSION) - return -EINVAL; - sdp_set_ip_ver(sdp_hdr, 6); - sdp_hdr->src_addr.ip6 = src6->sin6_addr; - sdp_hdr->dst_addr.ip6 = dst6->sin6_addr; - sdp_hdr->port = src6->sin6_port; - break; - default: - cma_hdr = hdr; - cma_hdr->cma_version = CMA_VERSION; - cma_set_ip_ver(cma_hdr, 6); - cma_hdr->src_addr.ip6 = src6->sin6_addr; - cma_hdr->dst_addr.ip6 = dst6->sin6_addr; - cma_hdr->port = src6->sin6_port; - break; - } + src6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); + dst6 = (struct sockaddr_in6 *) cma_dst_addr(id_priv); + + cma_set_ip_ver(cma_hdr, 6); + cma_hdr->src_addr.ip6 = src6->sin6_addr; + cma_hdr->dst_addr.ip6 = dst6->sin6_addr; + cma_hdr->port = src6->sin6_port; } return 0; } @@ -2215,7 +2651,7 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; int ret = 0; - if (cma_disable_callback(id_priv, CMA_CONNECT)) + if (cma_disable_callback(id_priv, RDMA_CM_CONNECT)) return 0; memset(&event, 0, sizeof event); @@ -2232,15 +2668,10 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, event.status = ib_event->param.sidr_rep_rcvd.status; break; } - ret = cma_set_qkey(id_priv); + ret = cma_set_qkey(id_priv, rep->qkey); if (ret) { event.event = RDMA_CM_EVENT_ADDR_ERROR; - event.status = -EINVAL; - break; - } - if (id_priv->qkey != rep->qkey) { - event.event = RDMA_CM_EVENT_UNREACHABLE; - event.status = -EINVAL; + event.status = ret; break; } ib_init_ah_from_path(id_priv->id.device, id_priv->id.port_num, @@ -2261,7 +2692,7 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; - cma_exch(id_priv, CMA_DESTROYING); + cma_exch(id_priv, RDMA_CM_DESTROYING); mutex_unlock(&id_priv->handler_mutex); rdma_destroy_id(&id_priv->id); return ret; @@ -2275,34 +2706,45 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_sidr_req_param req; - struct rdma_route *route; - int ret; + struct ib_cm_id *id; + void *private_data; + int offset, ret; - req.private_data_len = sizeof(struct cma_hdr) + - conn_param->private_data_len; - req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC); - if (!req.private_data) - return -ENOMEM; + memset(&req, 0, sizeof req); + offset = cma_user_data_offset(id_priv); + req.private_data_len = offset + conn_param->private_data_len; + if (req.private_data_len < conn_param->private_data_len) + return -EINVAL; + + if (req.private_data_len) { + private_data = kzalloc(req.private_data_len, GFP_ATOMIC); + if (!private_data) + return -ENOMEM; + } else { + private_data = NULL; + } if (conn_param->private_data && conn_param->private_data_len) - memcpy((void *) req.private_data + sizeof(struct cma_hdr), - conn_param->private_data, conn_param->private_data_len); + memcpy(private_data + offset, conn_param->private_data, + conn_param->private_data_len); - route = &id_priv->id.route; - ret = cma_format_hdr((void *) req.private_data, id_priv->id.ps, route); - if (ret) - goto out; + if (private_data) { + ret = cma_format_hdr(private_data, id_priv); + if (ret) + goto out; + req.private_data = private_data; + } - id_priv->cm_id.ib = ib_create_cm_id(id_priv->id.device, - cma_sidr_rep_handler, id_priv); - if (IS_ERR(id_priv->cm_id.ib)) { - ret = PTR_ERR(id_priv->cm_id.ib); + id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler, + id_priv); + if (IS_ERR(id)) { + ret = PTR_ERR(id); goto out; } + id_priv->cm_id.ib = id; - req.path = route->path_rec; - req.service_id = cma_get_service_id(id_priv->id.ps, - (struct sockaddr *) &route->addr.dst_addr); + req.path = id_priv->id.route.path_rec; + req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8); req.max_cm_retries = CMA_MAX_CM_RETRIES; @@ -2312,7 +2754,7 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, id_priv->cm_id.ib = NULL; } out: - kfree(req.private_data); + kfree(private_data); return ret; } @@ -2322,46 +2764,55 @@ static int cma_connect_ib(struct rdma_id_private *id_priv, struct ib_cm_req_param req; struct rdma_route *route; void *private_data; + struct ib_cm_id *id; int offset, ret; memset(&req, 0, sizeof req); - offset = cma_user_data_offset(id_priv->id.ps); + offset = cma_user_data_offset(id_priv); req.private_data_len = offset + conn_param->private_data_len; - private_data = kzalloc(req.private_data_len, GFP_ATOMIC); - if (!private_data) - return -ENOMEM; + if (req.private_data_len < conn_param->private_data_len) + return -EINVAL; + + if (req.private_data_len) { + private_data = kzalloc(req.private_data_len, GFP_ATOMIC); + if (!private_data) + return -ENOMEM; + } else { + private_data = NULL; + } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); - id_priv->cm_id.ib = ib_create_cm_id(id_priv->id.device, cma_ib_handler, - id_priv); - if (IS_ERR(id_priv->cm_id.ib)) { - ret = PTR_ERR(id_priv->cm_id.ib); + id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv); + if (IS_ERR(id)) { + ret = PTR_ERR(id); goto out; } + id_priv->cm_id.ib = id; route = &id_priv->id.route; - ret = cma_format_hdr(private_data, id_priv->id.ps, route); - if (ret) - goto out; - req.private_data = private_data; + if (private_data) { + ret = cma_format_hdr(private_data, id_priv); + if (ret) + goto out; + req.private_data = private_data; + } req.primary_path = &route->path_rec[0]; if (route->num_paths == 2) req.alternate_path = &route->path_rec[1]; - req.service_id = cma_get_service_id(id_priv->id.ps, - (struct sockaddr *) &route->addr.dst_addr); + req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.qp_num = id_priv->qp_num; - req.qp_type = IB_QPT_RC; + req.qp_type = id_priv->id.qp_type; req.starting_psn = id_priv->seq_num; req.responder_resources = conn_param->responder_resources; req.initiator_depth = conn_param->initiator_depth; req.flow_control = conn_param->flow_control; - req.retry_count = conn_param->retry_count; - req.rnr_retry_count = conn_param->rnr_retry_count; + req.retry_count = min_t(u8, 7, conn_param->retry_count); + req.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.max_cm_retries = CMA_MAX_CM_RETRIES; @@ -2369,8 +2820,8 @@ static int cma_connect_ib(struct rdma_id_private *id_priv, ret = ib_send_cm_req(id_priv->cm_id.ib, &req); out: - if (ret && !IS_ERR(id_priv->cm_id.ib)) { - ib_destroy_cm_id(id_priv->cm_id.ib); + if (ret && !IS_ERR(id)) { + ib_destroy_cm_id(id); id_priv->cm_id.ib = NULL; } @@ -2382,39 +2833,37 @@ static int cma_connect_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_id *cm_id; - struct sockaddr_in* sin; int ret; struct iw_cm_conn_param iw_param; cm_id = iw_create_cm_id(id_priv->id.device, cma_iw_handler, id_priv); - if (IS_ERR(cm_id)) { - ret = PTR_ERR(cm_id); - goto out; - } + if (IS_ERR(cm_id)) + return PTR_ERR(cm_id); id_priv->cm_id.iw = cm_id; - sin = (struct sockaddr_in*) &id_priv->id.route.addr.src_addr; - cm_id->local_addr = *sin; - - sin = (struct sockaddr_in*) &id_priv->id.route.addr.dst_addr; - cm_id->remote_addr = *sin; + memcpy(&cm_id->local_addr, cma_src_addr(id_priv), + rdma_addr_size(cma_src_addr(id_priv))); + memcpy(&cm_id->remote_addr, cma_dst_addr(id_priv), + rdma_addr_size(cma_dst_addr(id_priv))); ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; - iw_param.ord = conn_param->initiator_depth; - iw_param.ird = conn_param->responder_resources; - iw_param.private_data = conn_param->private_data; - iw_param.private_data_len = conn_param->private_data_len; - if (id_priv->id.qp) + if (conn_param) { + iw_param.ord = conn_param->initiator_depth; + iw_param.ird = conn_param->responder_resources; + iw_param.private_data = conn_param->private_data; + iw_param.private_data_len = conn_param->private_data_len; + iw_param.qpn = id_priv->id.qp ? id_priv->qp_num : conn_param->qp_num; + } else { + memset(&iw_param, 0, sizeof iw_param); iw_param.qpn = id_priv->qp_num; - else - iw_param.qpn = conn_param->qp_num; + } ret = iw_cm_connect(cm_id, &iw_param); out: - if (ret && !IS_ERR(cm_id)) { + if (ret) { iw_destroy_cm_id(cm_id); id_priv->cm_id.iw = NULL; } @@ -2427,7 +2876,7 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_comp_exch(id_priv, CMA_ROUTE_RESOLVED, CMA_CONNECT)) + if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) return -EINVAL; if (!id->qp) { @@ -2437,7 +2886,7 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - if (cma_is_ud_ps(id->ps)) + if (id->qp_type == IB_QPT_UD) ret = cma_resolve_ib_udp(id_priv, conn_param); else ret = cma_connect_ib(id_priv, conn_param); @@ -2454,7 +2903,7 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) return 0; err: - cma_comp_exch(id_priv, CMA_CONNECT, CMA_ROUTE_RESOLVED); + cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_connect); @@ -2482,7 +2931,7 @@ static int cma_accept_ib(struct rdma_id_private *id_priv, rep.initiator_depth = conn_param->initiator_depth; rep.failover_accepted = 0; rep.flow_control = conn_param->flow_control; - rep.rnr_retry_count = conn_param->rnr_retry_count; + rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); rep.srq = id_priv->srq ? 1 : 0; ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep); @@ -2513,7 +2962,7 @@ static int cma_accept_iw(struct rdma_id_private *id_priv, } static int cma_send_sidr_rep(struct rdma_id_private *id_priv, - enum ib_cm_sidr_status status, + enum ib_cm_sidr_status status, u32 qkey, const void *private_data, int private_data_len) { struct ib_cm_sidr_rep_param rep; @@ -2522,7 +2971,7 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv, memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { - ret = cma_set_qkey(id_priv); + ret = cma_set_qkey(id_priv, qkey); if (ret) return ret; rep.qp_num = id_priv->qp_num; @@ -2540,7 +2989,10 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_comp(id_priv, CMA_CONNECT)) + + id_priv->owner = task_pid_nr(current); + + if (!cma_comp(id_priv, RDMA_CM_CONNECT)) return -EINVAL; if (!id->qp && conn_param) { @@ -2550,14 +3002,21 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - if (cma_is_ud_ps(id->ps)) - ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, - conn_param->private_data, - conn_param->private_data_len); - else if (conn_param) - ret = cma_accept_ib(id_priv, conn_param); - else - ret = cma_rep_recv(id_priv); + if (id->qp_type == IB_QPT_UD) { + if (conn_param) + ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, + conn_param->qkey, + conn_param->private_data, + conn_param->private_data_len); + else + ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, + 0, NULL, 0); + } else { + if (conn_param) + ret = cma_accept_ib(id_priv, conn_param); + else + ret = cma_rep_recv(id_priv); + } break; case RDMA_TRANSPORT_IWARP: ret = cma_accept_iw(id_priv, conn_param); @@ -2584,7 +3043,7 @@ int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_has_cm_dev(id_priv)) + if (!id_priv->cm_id.ib) return -EINVAL; switch (id->device->node_type) { @@ -2606,13 +3065,13 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data, int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_has_cm_dev(id_priv)) + if (!id_priv->cm_id.ib) return -EINVAL; switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - if (cma_is_ud_ps(id->ps)) - ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, + if (id->qp_type == IB_QPT_UD) + ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0, private_data, private_data_len); else ret = ib_send_cm_rej(id_priv->cm_id.ib, @@ -2637,7 +3096,7 @@ int rdma_disconnect(struct rdma_cm_id *id) int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_has_cm_dev(id_priv)) + if (!id_priv->cm_id.ib) return -EINVAL; switch (rdma_node_get_transport(id->device->node_type)) { @@ -2669,14 +3128,16 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) int ret; id_priv = mc->id_priv; - if (cma_disable_callback(id_priv, CMA_ADDR_BOUND) && - cma_disable_callback(id_priv, CMA_ADDR_RESOLVED)) + if (cma_disable_callback(id_priv, RDMA_CM_ADDR_BOUND) && + cma_disable_callback(id_priv, RDMA_CM_ADDR_RESOLVED)) return 0; + if (!status) + status = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); mutex_lock(&id_priv->qp_mutex); if (!status && id_priv->id.qp) status = ib_attach_mcast(id_priv->id.qp, &multicast->rec.mgid, - multicast->rec.mlid); + be16_to_cpu(multicast->rec.mlid)); mutex_unlock(&id_priv->qp_mutex); memset(&event, 0, sizeof event); @@ -2694,7 +3155,7 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) ret = id_priv->id.event_handler(&id_priv->id, &event); if (ret) { - cma_exch(id_priv, CMA_DESTROYING); + cma_exch(id_priv, RDMA_CM_DESTROYING); mutex_unlock(&id_priv->handler_mutex); rdma_destroy_id(&id_priv->id); return 0; @@ -2719,6 +3180,8 @@ static void cma_set_mgid(struct rdma_id_private *id_priv, 0xFF10A01B)) { /* IPv6 address is an SA assigned MGID. */ memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); + } else if (addr->sa_family == AF_IB) { + memcpy(mgid, &((struct sockaddr_ib *) addr)->sib_addr, sizeof *mgid); } else if ((addr->sa_family == AF_INET6)) { ipv6_ib_mc_map(&sin6->sin6_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) @@ -2746,9 +3209,12 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, if (ret) return ret; + ret = cma_set_qkey(id_priv, 0); + if (ret) + return ret; + cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); - if (id_priv->id.ps == RDMA_PS_UDP) - rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); + rec.qkey = cpu_to_be32(id_priv->qkey); rdma_addr_get_sgid(dev_addr, &rec.port_gid); rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); rec.join_state = 1; @@ -2761,16 +3227,113 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv, if (id_priv->id.ps == RDMA_PS_IPOIB) comp_mask |= IB_SA_MCMEMBER_REC_RATE | - IB_SA_MCMEMBER_REC_RATE_SELECTOR; + IB_SA_MCMEMBER_REC_RATE_SELECTOR | + IB_SA_MCMEMBER_REC_MTU_SELECTOR | + IB_SA_MCMEMBER_REC_MTU | + IB_SA_MCMEMBER_REC_HOP_LIMIT; mc->multicast.ib = ib_sa_join_multicast(&sa_client, id_priv->id.device, id_priv->id.port_num, &rec, comp_mask, GFP_KERNEL, cma_ib_mc_handler, mc); - if (IS_ERR(mc->multicast.ib)) - return PTR_ERR(mc->multicast.ib); + return PTR_ERR_OR_ZERO(mc->multicast.ib); +} + +static void iboe_mcast_work_handler(struct work_struct *work) +{ + struct iboe_mcast_work *mw = container_of(work, struct iboe_mcast_work, work); + struct cma_multicast *mc = mw->mc; + struct ib_sa_multicast *m = mc->multicast.ib; + + mc->multicast.ib->context = mc; + cma_ib_mc_handler(0, m); + kref_put(&mc->mcref, release_mc); + kfree(mw); +} + +static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid) +{ + struct sockaddr_in *sin = (struct sockaddr_in *)addr; + struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; + + if (cma_any_addr(addr)) { + memset(mgid, 0, sizeof *mgid); + } else if (addr->sa_family == AF_INET6) { + memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); + } else { + mgid->raw[0] = 0xff; + mgid->raw[1] = 0x0e; + mgid->raw[2] = 0; + mgid->raw[3] = 0; + mgid->raw[4] = 0; + mgid->raw[5] = 0; + mgid->raw[6] = 0; + mgid->raw[7] = 0; + mgid->raw[8] = 0; + mgid->raw[9] = 0; + mgid->raw[10] = 0xff; + mgid->raw[11] = 0xff; + *(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr; + } +} + +static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, + struct cma_multicast *mc) +{ + struct iboe_mcast_work *work; + struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; + int err; + struct sockaddr *addr = (struct sockaddr *)&mc->addr; + struct net_device *ndev = NULL; + + if (cma_zero_addr((struct sockaddr *)&mc->addr)) + return -EINVAL; + + work = kzalloc(sizeof *work, GFP_KERNEL); + if (!work) + return -ENOMEM; + + mc->multicast.ib = kzalloc(sizeof(struct ib_sa_multicast), GFP_KERNEL); + if (!mc->multicast.ib) { + err = -ENOMEM; + goto out1; + } + + cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid); + + mc->multicast.ib->rec.pkey = cpu_to_be16(0xffff); + if (id_priv->id.ps == RDMA_PS_UDP) + mc->multicast.ib->rec.qkey = cpu_to_be32(RDMA_UDP_QKEY); + + if (dev_addr->bound_dev_if) + ndev = dev_get_by_index(&init_net, dev_addr->bound_dev_if); + if (!ndev) { + err = -ENODEV; + goto out2; + } + mc->multicast.ib->rec.rate = iboe_get_rate(ndev); + mc->multicast.ib->rec.hop_limit = 1; + mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu); + dev_put(ndev); + if (!mc->multicast.ib->rec.mtu) { + err = -EINVAL; + goto out2; + } + rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, + &mc->multicast.ib->rec.port_gid); + work->id = id_priv; + work->mc = mc; + INIT_WORK(&work->work, iboe_mcast_work_handler); + kref_get(&mc->mcref); + queue_work(cma_wq, &work->work); return 0; + +out2: + kfree(mc->multicast.ib); +out1: + kfree(work); + return err; } int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, @@ -2781,15 +3344,15 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, int ret; id_priv = container_of(id, struct rdma_id_private, id); - if (!cma_comp(id_priv, CMA_ADDR_BOUND) && - !cma_comp(id_priv, CMA_ADDR_RESOLVED)) + if (!cma_comp(id_priv, RDMA_CM_ADDR_BOUND) && + !cma_comp(id_priv, RDMA_CM_ADDR_RESOLVED)) return -EINVAL; mc = kmalloc(sizeof *mc, GFP_KERNEL); if (!mc) return -ENOMEM; - memcpy(&mc->addr, addr, ip_addr_size(addr)); + memcpy(&mc->addr, addr, rdma_addr_size(addr)); mc->context = context; mc->id_priv = id_priv; @@ -2799,7 +3362,17 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - ret = cma_join_ib_multicast(id_priv, mc); + switch (rdma_port_get_link_layer(id->device, id->port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ret = cma_join_ib_multicast(id_priv, mc); + break; + case IB_LINK_LAYER_ETHERNET: + kref_init(&mc->mcref); + ret = cma_iboe_join_multicast(id_priv, mc); + break; + default: + ret = -EINVAL; + } break; default: ret = -ENOSYS; @@ -2824,16 +3397,27 @@ 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, ip_addr_size(addr))) { + 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, - mc->multicast.ib->rec.mlid); - ib_sa_free_multicast(mc->multicast.ib); - kfree(mc); + be16_to_cpu(mc->multicast.ib->rec.mlid)); + if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) == RDMA_TRANSPORT_IB) { + switch (rdma_port_get_link_layer(id->device, id->port_num)) { + case IB_LINK_LAYER_INFINIBAND: + ib_sa_free_multicast(mc->multicast.ib); + kfree(mc); + break; + case IB_LINK_LAYER_ETHERNET: + kref_put(&mc->mcref, release_mc); + break; + default: + break; + } + } return; } } @@ -2867,9 +3451,9 @@ static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id } static int cma_netdev_callback(struct notifier_block *self, unsigned long event, - void *ctx) + void *ptr) { - struct net_device *ndev = (struct net_device *)ctx; + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct cma_device *cma_dev; struct rdma_id_private *id_priv; int ret = NOTIFY_DONE; @@ -2926,19 +3510,19 @@ static void cma_add_one(struct ib_device *device) static int cma_remove_id_dev(struct rdma_id_private *id_priv) { struct rdma_cm_event event; - enum cma_state state; + enum rdma_cm_state state; int ret = 0; /* Record that we want to remove the device */ - state = cma_exch(id_priv, CMA_DEVICE_REMOVAL); - if (state == CMA_DESTROYING) + state = cma_exch(id_priv, RDMA_CM_DEVICE_REMOVAL); + if (state == RDMA_CM_DESTROYING) return 0; cma_cancel_operation(id_priv, state); mutex_lock(&id_priv->handler_mutex); /* Check for destruction from another callback. */ - if (!cma_comp(id_priv, CMA_DEVICE_REMOVAL)) + if (!cma_comp(id_priv, RDMA_CM_DEVICE_REMOVAL)) goto out; memset(&event, 0, sizeof event); @@ -2993,14 +3577,88 @@ static void cma_remove_one(struct ib_device *device) kfree(cma_dev); } -static int __init cma_init(void) +static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb) { - int ret, low, high, remaining; + struct nlmsghdr *nlh; + struct rdma_cm_id_stats *id_stats; + struct rdma_id_private *id_priv; + struct rdma_cm_id *id = NULL; + struct cma_device *cma_dev; + int i_dev = 0, i_id = 0; - get_random_bytes(&next_port, sizeof next_port); - inet_get_local_port_range(&low, &high); - remaining = (high - low) + 1; - next_port = ((unsigned int) next_port % remaining) + low; + /* + * We export all of the IDs as a sequence of messages. Each + * ID gets its own netlink message. + */ + mutex_lock(&lock); + + list_for_each_entry(cma_dev, &dev_list, list) { + if (i_dev < cb->args[0]) { + i_dev++; + continue; + } + + i_id = 0; + list_for_each_entry(id_priv, &cma_dev->id_list, list) { + if (i_id < cb->args[1]) { + i_id++; + continue; + } + + id_stats = ibnl_put_msg(skb, &nlh, cb->nlh->nlmsg_seq, + sizeof *id_stats, RDMA_NL_RDMA_CM, + RDMA_NL_RDMA_CM_ID_STATS, + NLM_F_MULTI); + if (!id_stats) + goto out; + + memset(id_stats, 0, sizeof *id_stats); + id = &id_priv->id; + id_stats->node_type = id->route.addr.dev_addr.dev_type; + id_stats->port_num = id->port_num; + id_stats->bound_dev_if = + id->route.addr.dev_addr.bound_dev_if; + + if (ibnl_put_attr(skb, nlh, + rdma_addr_size(cma_src_addr(id_priv)), + cma_src_addr(id_priv), + RDMA_NL_RDMA_CM_ATTR_SRC_ADDR)) + goto out; + if (ibnl_put_attr(skb, nlh, + rdma_addr_size(cma_src_addr(id_priv)), + cma_dst_addr(id_priv), + RDMA_NL_RDMA_CM_ATTR_DST_ADDR)) + goto out; + + id_stats->pid = id_priv->owner; + id_stats->port_space = id->ps; + id_stats->cm_state = id_priv->state; + id_stats->qp_num = id_priv->qp_num; + id_stats->qp_type = id->qp_type; + + i_id++; + } + + cb->args[1] = 0; + i_dev++; + } + +out: + mutex_unlock(&lock); + cb->args[0] = i_dev; + cb->args[1] = i_id; + + return skb->len; +} + +static const struct ibnl_client_cbs cma_cb_table[] = { + [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats, + .module = THIS_MODULE }, +}; + +static int __init cma_init(void) +{ + int ret; cma_wq = create_singlethread_workqueue("rdma_cm"); if (!cma_wq) @@ -3013,6 +3671,10 @@ static int __init cma_init(void) ret = ib_register_client(&cma_client); if (ret) goto err; + + if (ibnl_add_client(RDMA_NL_RDMA_CM, RDMA_NL_RDMA_CM_NUM_OPS, cma_cb_table)) + printk(KERN_WARNING "RDMA CMA: failed to add netlink callback\n"); + return 0; err: @@ -3025,15 +3687,16 @@ err: static void __exit cma_cleanup(void) { + ibnl_remove_client(RDMA_NL_RDMA_CM); ib_unregister_client(&cma_client); unregister_netdevice_notifier(&cma_nb); rdma_addr_unregister_client(&addr_client); ib_sa_unregister_client(&sa_client); destroy_workqueue(cma_wq); - idr_destroy(&sdp_ps); idr_destroy(&tcp_ps); idr_destroy(&udp_ps); idr_destroy(&ipoib_ps); + idr_destroy(&ib_ps); } module_init(cma_init); |