diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-09-23 16:47:34 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-09-23 16:47:34 -0700 |
commit | 452b6361c4d9baf6940adb7b1316e0f386c39799 (patch) | |
tree | 9b2ad0dac3ea58fe9c29893d0d0eb80005974344 /drivers | |
parent | ffd4341d6af49ad899144b5a02f2eba65be03f6c (diff) | |
parent | 3bdad2d13fa62bcb59ca2506e74ce467ea436586 (diff) |
Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband
Pull infiniband/rdma fixes from Roland Dreier:
"Last late set of InfiniBand/RDMA fixes for 3.17:
- fixes for the new memory region re-registration support
- iSER initiator error path fixes
- grab bag of small fixes for the qib and ocrdma hardware drivers
- larger set of fixes for mlx4, especially in RoCE mode"
* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (26 commits)
IB/mlx4: Fix VF mac handling in RoCE
IB/mlx4: Do not allow APM under RoCE
IB/mlx4: Don't update QP1 in native mode
IB/mlx4: Avoid accessing netdevice when building RoCE qp1 header
mlx4: Fix mlx4 reg/unreg mac to work properly with 0-mac addresses
IB/core: When marshaling uverbs path, clear unused fields
IB/mlx4: Avoid executing gid task when device is being removed
IB/mlx4: Fix lockdep splat for the iboe lock
IB/mlx4: Get upper dev addresses as RoCE GIDs when port comes up
IB/mlx4: Reorder steps in RoCE GID table initialization
IB/mlx4: Don't duplicate the default RoCE GID
IB/mlx4: Avoid null pointer dereference in mlx4_ib_scan_netdevs()
IB/iser: Bump version to 1.4.1
IB/iser: Allow bind only when connection state is UP
IB/iser: Fix RX/TX CQ resource leak on error flow
RDMA/ocrdma: Use right macro in query AH
RDMA/ocrdma: Resolve L2 address when creating user AH
mlx4: Correct error flows in rereg_mr
IB/qib: Correct reference counting in debugfs qp_stats
IPoIB: Remove unnecessary port query
...
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/infiniband/core/umem.c | 19 | ||||
-rw-r--r-- | drivers/infiniband/core/uverbs_marshall.c | 4 | ||||
-rw-r--r-- | drivers/infiniband/hw/ipath/ipath_user_pages.c | 6 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx4/main.c | 169 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx4/mlx4_ib.h | 1 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx4/mr.c | 7 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx4/qp.c | 60 | ||||
-rw-r--r-- | drivers/infiniband/hw/ocrdma/ocrdma_ah.c | 43 | ||||
-rw-r--r-- | drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 6 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_debugfs.c | 3 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_qp.c | 8 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_user_pages.c | 6 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 10 | ||||
-rw-r--r-- | drivers/infiniband/ulp/iser/iscsi_iser.c | 19 | ||||
-rw-r--r-- | drivers/infiniband/ulp/iser/iscsi_iser.h | 2 | ||||
-rw-r--r-- | drivers/infiniband/ulp/iser/iser_verbs.c | 24 | ||||
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/mr.c | 33 | ||||
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/port.c | 11 |
18 files changed, 276 insertions, 155 deletions
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index a3a2e9c1639b..df0c4f605a21 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -105,6 +105,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, umem->length = size; umem->offset = addr & ~PAGE_MASK; umem->page_size = PAGE_SIZE; + umem->pid = get_task_pid(current, PIDTYPE_PID); /* * We ask for writable memory if any access flags other than * "remote read" are set. "Local write" and "remote write" @@ -198,6 +199,7 @@ out: if (ret < 0) { if (need_release) __ib_umem_release(context->device, umem, 0); + put_pid(umem->pid); kfree(umem); } else current->mm->pinned_vm = locked; @@ -230,15 +232,19 @@ void ib_umem_release(struct ib_umem *umem) { struct ib_ucontext *context = umem->context; struct mm_struct *mm; + struct task_struct *task; unsigned long diff; __ib_umem_release(umem->context->device, umem, 1); - mm = get_task_mm(current); - if (!mm) { - kfree(umem); - return; - } + task = get_pid_task(umem->pid, PIDTYPE_PID); + put_pid(umem->pid); + if (!task) + goto out; + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + goto out; diff = PAGE_ALIGN(umem->length + umem->offset) >> PAGE_SHIFT; @@ -262,9 +268,10 @@ void ib_umem_release(struct ib_umem *umem) } else down_write(&mm->mmap_sem); - current->mm->pinned_vm -= diff; + mm->pinned_vm -= diff; up_write(&mm->mmap_sem); mmput(mm); +out: kfree(umem); } EXPORT_SYMBOL(ib_umem_release); diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index e7bee46868d1..abd97247443e 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -140,5 +140,9 @@ void ib_copy_path_rec_from_user(struct ib_sa_path_rec *dst, dst->packet_life_time = src->packet_life_time; dst->preference = src->preference; dst->packet_life_time_selector = src->packet_life_time_selector; + + memset(dst->smac, 0, sizeof(dst->smac)); + memset(dst->dmac, 0, sizeof(dst->dmac)); + dst->vlan_id = 0xffff; } EXPORT_SYMBOL(ib_copy_path_rec_from_user); diff --git a/drivers/infiniband/hw/ipath/ipath_user_pages.c b/drivers/infiniband/hw/ipath/ipath_user_pages.c index dc66c4506916..1da1252dcdb3 100644 --- a/drivers/infiniband/hw/ipath/ipath_user_pages.c +++ b/drivers/infiniband/hw/ipath/ipath_user_pages.c @@ -54,7 +54,7 @@ static void __ipath_release_user_pages(struct page **p, size_t num_pages, /* call with current->mm->mmap_sem held */ static int __ipath_get_user_pages(unsigned long start_page, size_t num_pages, - struct page **p, struct vm_area_struct **vma) + struct page **p) { unsigned long lock_limit; size_t got; @@ -74,7 +74,7 @@ static int __ipath_get_user_pages(unsigned long start_page, size_t num_pages, ret = get_user_pages(current, current->mm, start_page + got * PAGE_SIZE, num_pages - got, 1, 1, - p + got, vma); + p + got, NULL); if (ret < 0) goto bail_release; } @@ -165,7 +165,7 @@ int ipath_get_user_pages(unsigned long start_page, size_t num_pages, down_write(¤t->mm->mmap_sem); - ret = __ipath_get_user_pages(start_page, num_pages, p, NULL); + ret = __ipath_get_user_pages(start_page, num_pages, p); up_write(¤t->mm->mmap_sem); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 162b82c1dde4..bda5994ceb68 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -59,6 +59,7 @@ #define MLX4_IB_FLOW_MAX_PRIO 0xFFF #define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF +#define MLX4_IB_CARD_REV_A0 0xA0 MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver"); @@ -119,6 +120,17 @@ static int check_flow_steering_support(struct mlx4_dev *dev) return dmfs; } +static int num_ib_ports(struct mlx4_dev *dev) +{ + int ib_ports = 0; + int i; + + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + ib_ports++; + + return ib_ports; +} + static int mlx4_ib_query_device(struct ib_device *ibdev, struct ib_device_attr *props) { @@ -126,6 +138,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, struct ib_smp *in_mad = NULL; struct ib_smp *out_mad = NULL; int err = -ENOMEM; + int have_ib_ports; in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); @@ -142,6 +155,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, memset(props, 0, sizeof *props); + have_ib_ports = num_ib_ports(dev->dev); + props->fw_ver = dev->dev->caps.fw_ver; props->device_cap_flags = IB_DEVICE_CHANGE_PHY_PORT | IB_DEVICE_PORT_ACTIVE_EVENT | @@ -152,13 +167,15 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR; if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR) props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR; - if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_APM) + if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_APM && have_ib_ports) props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG; if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UD_AV_PORT) props->device_cap_flags |= IB_DEVICE_UD_AV_PORT_ENFORCE; if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_IPOIB_CSUM) props->device_cap_flags |= IB_DEVICE_UD_IP_CSUM; - if (dev->dev->caps.max_gso_sz && dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BLH) + if (dev->dev->caps.max_gso_sz && + (dev->dev->rev_id != MLX4_IB_CARD_REV_A0) && + (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BLH)) props->device_cap_flags |= IB_DEVICE_UD_TSO; if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_RESERVED_LKEY) props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY; @@ -357,7 +374,7 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, props->state = IB_PORT_DOWN; props->phys_state = state_to_phys_state(props->state); props->active_mtu = IB_MTU_256; - spin_lock(&iboe->lock); + spin_lock_bh(&iboe->lock); ndev = iboe->netdevs[port - 1]; if (!ndev) goto out_unlock; @@ -369,7 +386,7 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, IB_PORT_ACTIVE : IB_PORT_DOWN; props->phys_state = state_to_phys_state(props->state); out_unlock: - spin_unlock(&iboe->lock); + spin_unlock_bh(&iboe->lock); out: mlx4_free_cmd_mailbox(mdev->dev, mailbox); return err; @@ -811,11 +828,11 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, if (!mqp->port) return 0; - spin_lock(&mdev->iboe.lock); + spin_lock_bh(&mdev->iboe.lock); ndev = mdev->iboe.netdevs[mqp->port - 1]; if (ndev) dev_hold(ndev); - spin_unlock(&mdev->iboe.lock); + spin_unlock_bh(&mdev->iboe.lock); if (ndev) { ret = 1; @@ -1292,11 +1309,11 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) mutex_lock(&mqp->mutex); ge = find_gid_entry(mqp, gid->raw); if (ge) { - spin_lock(&mdev->iboe.lock); + spin_lock_bh(&mdev->iboe.lock); ndev = ge->added ? mdev->iboe.netdevs[ge->port - 1] : NULL; if (ndev) dev_hold(ndev); - spin_unlock(&mdev->iboe.lock); + spin_unlock_bh(&mdev->iboe.lock); if (ndev) dev_put(ndev); list_del(&ge->list); @@ -1417,6 +1434,9 @@ static void update_gids_task(struct work_struct *work) int err; struct mlx4_dev *dev = gw->dev->dev; + if (!gw->dev->ib_active) + return; + mailbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(mailbox)) { pr_warn("update gid table failed %ld\n", PTR_ERR(mailbox)); @@ -1447,6 +1467,9 @@ static void reset_gids_task(struct work_struct *work) int err; struct mlx4_dev *dev = gw->dev->dev; + if (!gw->dev->ib_active) + return; + mailbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(mailbox)) { pr_warn("reset gid table failed\n"); @@ -1581,7 +1604,7 @@ static int mlx4_ib_addr_event(int event, struct net_device *event_netdev, return 0; iboe = &ibdev->iboe; - spin_lock(&iboe->lock); + spin_lock_bh(&iboe->lock); for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) if ((netif_is_bond_master(real_dev) && @@ -1591,7 +1614,7 @@ static int mlx4_ib_addr_event(int event, struct net_device *event_netdev, update_gid_table(ibdev, port, gid, event == NETDEV_DOWN, 0); - spin_unlock(&iboe->lock); + spin_unlock_bh(&iboe->lock); return 0; } @@ -1664,13 +1687,21 @@ static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev, new_smac = mlx4_mac_to_u64(dev->dev_addr); read_unlock(&dev_base_lock); + atomic64_set(&ibdev->iboe.mac[port - 1], new_smac); + + /* no need for update QP1 and mac registration in non-SRIOV */ + if (!mlx4_is_mfunc(ibdev->dev)) + return; + mutex_lock(&ibdev->qp1_proxy_lock[port - 1]); qp = ibdev->qp1_proxy[port - 1]; if (qp) { int new_smac_index; - u64 old_smac = qp->pri.smac; + u64 old_smac; struct mlx4_update_qp_params update_params; + mutex_lock(&qp->mutex); + old_smac = qp->pri.smac; if (new_smac == old_smac) goto unlock; @@ -1685,17 +1716,20 @@ static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev, release_mac = new_smac; goto unlock; } - + /* if old port was zero, no mac was yet registered for this QP */ + if (qp->pri.smac_port) + release_mac = old_smac; qp->pri.smac = new_smac; + qp->pri.smac_port = port; qp->pri.smac_index = new_smac_index; - - release_mac = old_smac; } unlock: - mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]); if (release_mac != MLX4_IB_INVALID_MAC) mlx4_unregister_mac(ibdev->dev, port, release_mac); + if (qp) + mutex_unlock(&qp->mutex); + mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]); } static void mlx4_ib_get_dev_addr(struct net_device *dev, @@ -1706,6 +1740,7 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, struct inet6_dev *in6_dev; union ib_gid *pgid; struct inet6_ifaddr *ifp; + union ib_gid default_gid; #endif union ib_gid gid; @@ -1726,12 +1761,15 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) + mlx4_make_default_gid(dev, &default_gid); /* IPv6 gids */ in6_dev = in6_dev_get(dev); if (in6_dev) { read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { pgid = (union ib_gid *)&ifp->addr; + if (!memcmp(pgid, &default_gid, sizeof(*pgid))) + continue; update_gid_table(ibdev, port, pgid, 0, 0); } read_unlock_bh(&in6_dev->lock); @@ -1753,24 +1791,33 @@ static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev) struct net_device *dev; struct mlx4_ib_iboe *iboe = &ibdev->iboe; int i; + int err = 0; - for (i = 1; i <= ibdev->num_ports; ++i) - if (reset_gid_table(ibdev, i)) - return -1; + for (i = 1; i <= ibdev->num_ports; ++i) { + if (rdma_port_get_link_layer(&ibdev->ib_dev, i) == + IB_LINK_LAYER_ETHERNET) { + err = reset_gid_table(ibdev, i); + if (err) + goto out; + } + } read_lock(&dev_base_lock); - spin_lock(&iboe->lock); + spin_lock_bh(&iboe->lock); for_each_netdev(&init_net, dev) { u8 port = mlx4_ib_get_dev_port(dev, ibdev); - if (port) + /* port will be non-zero only for ETH ports */ + if (port) { + mlx4_ib_set_default_gid(ibdev, dev, port); mlx4_ib_get_dev_addr(dev, ibdev, port); + } } - spin_unlock(&iboe->lock); + spin_unlock_bh(&iboe->lock); read_unlock(&dev_base_lock); - - return 0; +out: + return err; } static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev, @@ -1784,7 +1831,7 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev, iboe = &ibdev->iboe; - spin_lock(&iboe->lock); + spin_lock_bh(&iboe->lock); mlx4_foreach_ib_transport_port(port, ibdev->dev) { enum ib_port_state port_state = IB_PORT_NOP; struct net_device *old_master = iboe->masters[port - 1]; @@ -1816,35 +1863,47 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev, port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ? IB_PORT_ACTIVE : IB_PORT_DOWN; mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } else { - reset_gid_table(ibdev, port); - } - /* if using bonding/team and a slave port is down, we don't the bond IP - * based gids in the table since flows that select port by gid may get - * the down port. - */ - if (curr_master && (port_state == IB_PORT_DOWN)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - } - /* if bonding is used it is possible that we add it to masters - * only after IP address is assigned to the net bonding - * interface. - */ - if (curr_master && (old_master != curr_master)) { - reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_master, ibdev, port); - } + if (curr_master) { + /* if using bonding/team and a slave port is down, we + * don't want the bond IP based gids in the table since + * flows that select port by gid may get the down port. + */ + if (port_state == IB_PORT_DOWN) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, + port); + } else { + /* gids from the upper dev (bond/team) + * should appear in port's gid table + */ + mlx4_ib_get_dev_addr(curr_master, + ibdev, port); + } + } + /* if bonding is used it is possible that we add it to + * masters only after IP address is assigned to the + * net bonding interface. + */ + if (curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_master, ibdev, port); + } - if (!curr_master && (old_master != curr_master)) { + if (!curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, + curr_netdev, port); + mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); + } + } else { reset_gid_table(ibdev, port); - mlx4_ib_set_default_gid(ibdev, curr_netdev, port); - mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); } } - spin_unlock(&iboe->lock); + spin_unlock_bh(&iboe->lock); if (update_qps_port > 0) mlx4_ib_update_qps(ibdev, dev, update_qps_port); @@ -2186,6 +2245,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) goto err_steer_free_bitmap; } + for (j = 1; j <= ibdev->dev->caps.num_ports; j++) + atomic64_set(&iboe->mac[j - 1], ibdev->dev->caps.def_mac[j]); + if (ib_register_device(&ibdev->ib_dev, NULL)) goto err_steer_free_bitmap; @@ -2222,12 +2284,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) } } #endif - for (i = 1 ; i <= ibdev->num_ports ; ++i) - reset_gid_table(ibdev, i); - rtnl_lock(); - mlx4_ib_scan_netdevs(ibdev, NULL, 0); - rtnl_unlock(); - mlx4_ib_init_gid_table(ibdev); + if (mlx4_ib_init_gid_table(ibdev)) + goto err_notif; } for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) { @@ -2375,6 +2433,9 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) struct mlx4_ib_dev *ibdev = ibdev_ptr; int p; + ibdev->ib_active = false; + flush_workqueue(wq); + mlx4_ib_close_sriov(ibdev); mlx4_ib_mad_cleanup(ibdev); ib_unregister_device(&ibdev->ib_dev); diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index e8cad3926bfc..6eb743f65f6f 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -451,6 +451,7 @@ struct mlx4_ib_iboe { spinlock_t lock; struct net_device *netdevs[MLX4_MAX_PORTS]; struct net_device *masters[MLX4_MAX_PORTS]; + atomic64_t mac[MLX4_MAX_PORTS]; struct notifier_block nb; struct notifier_block nb_inet; struct notifier_block nb_inet6; diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c index 9b0e80e59b08..8f9325cfc85d 100644 --- a/drivers/infiniband/hw/mlx4/mr.c +++ b/drivers/infiniband/hw/mlx4/mr.c @@ -234,14 +234,13 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, 0); if (IS_ERR(mmr->umem)) { err = PTR_ERR(mmr->umem); + /* Prevent mlx4_ib_dereg_mr from free'ing invalid pointer */ mmr->umem = NULL; goto release_mpt_entry; } n = ib_umem_page_count(mmr->umem); shift = ilog2(mmr->umem->page_size); - mmr->mmr.iova = virt_addr; - mmr->mmr.size = length; err = mlx4_mr_rereg_mem_write(dev->dev, &mmr->mmr, virt_addr, length, n, shift, *pmpt_entry); @@ -249,6 +248,8 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, ib_umem_release(mmr->umem); goto release_mpt_entry; } + mmr->mmr.iova = virt_addr; + mmr->mmr.size = length; err = mlx4_ib_umem_write_mtt(dev, &mmr->mmr.mtt, mmr->umem); if (err) { @@ -262,6 +263,8 @@ int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags, * return a failure. But dereg_mr will free the resources. */ err = mlx4_mr_hw_write_mpt(dev->dev, &mmr->mmr, pmpt_entry); + if (!err && flags & IB_MR_REREG_ACCESS) + mmr->mmr.access = mr_access_flags; release_mpt_entry: mlx4_mr_hw_put_mpt(dev->dev, pmpt_entry); diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 836503927dea..9c5150c3cb31 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -964,9 +964,10 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp)) pr_warn("modify QP %06x to RESET failed.\n", qp->mqp.qpn); - if (qp->pri.smac) { + if (qp->pri.smac || (!qp->pri.smac && qp->pri.smac_port)) { mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac); qp->pri.smac = 0; + qp->pri.smac_port = 0; } if (qp->alt.smac) { mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac); @@ -1325,7 +1326,8 @@ static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, * If one was already assigned, but the new mac differs, * unregister the old one and register the new one. */ - if (!smac_info->smac || smac_info->smac != smac) { + if ((!smac_info->smac && !smac_info->smac_port) || + smac_info->smac != smac) { /* register candidate now, unreg if needed, after success */ smac_index = mlx4_register_mac(dev->dev, port, smac); if (smac_index >= 0) { @@ -1390,21 +1392,13 @@ static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) static int handle_eth_ud_smac_index(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, u8 *smac, struct mlx4_qp_context *context) { - struct net_device *ndev; u64 u64_mac; int smac_index; - - ndev = dev->iboe.netdevs[qp->port - 1]; - if (ndev) { - smac = ndev->dev_addr; - u64_mac = mlx4_mac_to_u64(smac); - } else { - u64_mac = dev->dev->caps.def_mac[qp->port]; - } + u64_mac = atomic64_read(&dev->iboe.mac[qp->port - 1]); context->pri_path.sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | ((qp->port - 1) << 6); - if (!qp->pri.smac) { + if (!qp->pri.smac && !qp->pri.smac_port) { smac_index = mlx4_register_mac(dev->dev, qp->port, u64_mac); if (smac_index >= 0) { qp->pri.candidate_smac_index = smac_index; @@ -1432,6 +1426,12 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, int steer_qp = 0; int err = -EINVAL; + /* APM is not supported under RoCE */ + if (attr_mask & IB_QP_ALT_PATH && + rdma_port_get_link_layer(&dev->ib_dev, qp->port) == + IB_LINK_LAYER_ETHERNET) + return -ENOTSUPP; + context = kzalloc(sizeof *context, GFP_KERNEL); if (!context) return -ENOMEM; @@ -1786,9 +1786,10 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, if (qp->flags & MLX4_IB_QP_NETIF) mlx4_ib_steer_qp_reg(dev, qp, 0); } - if (qp->pri.smac) { + if (qp->pri.smac || (!qp->pri.smac && qp->pri.smac_port)) { mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac); qp->pri.smac = 0; + qp->pri.smac_port = 0; } if (qp->alt.smac) { mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac); @@ -1812,11 +1813,12 @@ out: if (err && steer_qp) mlx4_ib_steer_qp_reg(dev, qp, 0); kfree(context); - if (qp->pri.candidate_smac) { + if (qp->pri.candidate_smac || + (!qp->pri.candidate_smac && qp->pri.candidate_smac_port)) { if (err) { mlx4_unregister_mac(dev->dev, qp->pri.candidate_smac_port, qp->pri.candidate_smac); } else { - if (qp->pri.smac) + if (qp->pri.smac || (!qp->pri.smac && qp->pri.smac_port)) mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac); qp->pri.smac = qp->pri.candidate_smac; qp->pri.smac_index = qp->pri.candidate_smac_index; @@ -2089,6 +2091,16 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, return 0; } +static void mlx4_u64_to_smac(u8 *dst_mac, u64 src_mac) +{ + int i; + + for (i = ETH_ALEN; i; i--) { + dst_mac[i - 1] = src_mac & 0xff; + src_mac >>= 8; + } +} + static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, void *wqe, unsigned *mlx_seg_len) { @@ -2203,7 +2215,6 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, } if (is_eth) { - u8 *smac; struct in6_addr in6; u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13; @@ -2216,12 +2227,17 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4); memcpy(&in6, sgid.raw, sizeof(in6)); - if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev)) - smac = to_mdev(sqp->qp.ibqp.device)-> - iboe.netdevs[sqp->qp.port - 1]->dev_addr; - else /* use the src mac of the tunnel */ - smac = ah->av.eth.s_mac; - memcpy(sqp->ud_header.eth.smac_h, smac, 6); + if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev)) { + u64 mac = atomic64_read(&to_mdev(ib_dev)->iboe.mac[sqp->qp.port - 1]); + u8 smac[ETH_ALEN]; + + mlx4_u64_to_smac(smac, mac); + memcpy(sqp->ud_header.eth.smac_h, smac, ETH_ALEN); + } else { + /* use the src mac of the tunnel */ + memcpy(sqp->ud_header.eth.smac_h, ah->av.eth.s_mac, ETH_ALEN); + } + if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6)) mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); if (!is_vlan) { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c index 40f8536c10b0..ac02ce4e8040 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c @@ -38,7 +38,7 @@ #define OCRDMA_VID_PCP_SHIFT 0xD static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah, - struct ib_ah_attr *attr, int pdid) + struct ib_ah_attr *attr, union ib_gid *sgid, int pdid) { int status = 0; u16 vlan_tag; bool vlan_enabled = false; @@ -49,8 +49,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah, memset(ð, 0, sizeof(eth)); memset(&grh, 0, sizeof(grh)); - ah->sgid_index = attr->grh.sgid_index; - + /* VLAN */ vlan_tag = attr->vlan_id; if (!vlan_tag || (vlan_tag > 0xFFF)) vlan_tag = dev->pvid; @@ -65,15 +64,14 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah, eth.eth_type = cpu_to_be16(OCRDMA_ROCE_ETH_TYPE); eth_sz = sizeof(struct ocrdma_eth_basic); } + /* MAC */ memcpy(ð.smac[0], &dev->nic_info.mac_addr[0], ETH_ALEN); - memcpy(ð.dmac[0], attr->dmac, ETH_ALEN); status = ocrdma_resolve_dmac(dev, attr, ð.dmac[0]); if (status) return status; - status = ocrdma_query_gid(&dev->ibdev, 1, attr->grh.sgid_index, - (union ib_gid *)&grh.sgid[0]); - if (status) - return status; + ah->sgid_index = attr->grh.sgid_index; + memcpy(&grh.sgid[0], sgid->raw, sizeof(union ib_gid)); + memcpy(&grh.dgid[0], attr->grh.dgid.raw, sizeof(attr->grh.dgid.raw)); grh.tclass_flow = cpu_to_be32((6 << 28) | (attr->grh.traffic_class << 24) | @@ -81,8 +79,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah, /* 0x1b is next header value in GRH */ grh.pdid_hoplimit = cpu_to_be32((pdid << 16) | (0x1b << 8) | attr->grh.hop_limit); - - memcpy(&grh.dgid[0], attr->grh.dgid.raw, sizeof(attr->grh.dgid.raw)); + /* Eth HDR */ memcpy(&ah->av->eth_hdr, ð, eth_sz); memcpy((u8 *)ah->av + eth_sz, &grh, sizeof(struct ocrdma_grh)); if (vlan_enabled) @@ -98,6 +95,8 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr) struct ocrdma_ah *ah; struct ocrdma_pd *pd = get_ocrdma_pd(ibpd); struct ocrdma_dev *dev = get_ocrdma_dev(ibpd->device); + union ib_gid sgid; + u8 zmac[ETH_ALEN]; if (!(attr->ah_flags & IB_AH_GRH)) return ERR_PTR(-EINVAL); @@ -111,7 +110,27 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr) status = ocrdma_alloc_av(dev, ah); if (status) goto av_err; - status = set_av_attr(dev, ah, attr, pd->id); + + status = ocrdma_query_gid(&dev->ibdev, 1, attr->grh.sgid_index, &sgid); + if (status) { + pr_err("%s(): Failed to query sgid, status = %d\n", + __func__, status); + goto av_conf_err; + } + + memset(&zmac, 0, ETH_ALEN); + if (pd->uctx && + memcmp(attr->dmac, &zmac, ETH_ALEN)) { + status = rdma_addr_find_dmac_by_grh(&sgid, &attr->grh.dgid, + attr->dmac, &attr->vlan_id); + if (status) { + pr_err("%s(): Failed to resolve dmac from gid." + "status = %d\n", __func__, status); + goto av_conf_err; + } + } + + status = set_av_attr(dev, ah, attr, &sgid, pd->id); if (status) goto av_conf_err; @@ -145,7 +164,7 @@ int ocrdma_query_ah(struct ib_ah *ibah, struct ib_ah_attr *attr) struct ocrdma_av *av = ah->av; struct ocrdma_grh *grh; attr->ah_flags |= IB_AH_GRH; - if (ah->av->valid & Bit(1)) { + if (ah->av->valid & OCRDMA_AV_VALID) { grh = (struct ocrdma_grh *)((u8 *)ah->av + sizeof(struct ocrdma_eth_vlan)); attr->sl = be16_to_cpu(av->eth_hdr.vlan_tag) >> 13; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index acb434d16903..8f5f2577f288 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -101,7 +101,7 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr) attr->max_srq_sge = dev->attr.max_srq_sge; attr->max_srq_wr = dev->attr.max_rqe; attr->local_ca_ack_delay = dev->attr.local_ca_ack_delay; - attr->max_fast_reg_page_list_len = 0; + attr->max_fast_reg_page_list_len = dev->attr.max_pages_per_frmr; attr->max_pkeys = 1; return 0; } @@ -2846,11 +2846,9 @@ int ocrdma_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags cq_flags) if (cq->first_arm) { ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0); cq->first_arm = false; - goto skip_defer; } - cq->deferred_arm = true; -skip_defer: + cq->deferred_arm = true; cq->deferred_sol = sol_needed; spin_unlock_irqrestore(&cq->cq_lock, flags); diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 799a0c3bffc4..6abd3ed3cd51 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -193,6 +193,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) struct qib_qp_iter *iter; loff_t n = *pos; + rcu_read_lock(); iter = qib_qp_iter_init(s->private); if (!iter) return NULL; @@ -224,7 +225,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) { - /* nothing for now */ + rcu_read_unlock(); } static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr) diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 7fcc150d603c..6ddc0264aad2 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -1325,7 +1325,6 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) struct qib_qp *pqp = iter->qp; struct qib_qp *qp; - rcu_read_lock(); for (; n < dev->qp_table_size; n++) { if (pqp) qp = rcu_dereference(pqp->next); @@ -1333,18 +1332,11 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) qp = rcu_dereference(dev->qp_table[n]); pqp = qp; if (qp) { |