diff options
Diffstat (limited to 'drivers/infiniband/core/device.c')
| -rw-r--r-- | drivers/infiniband/core/device.c | 252 |
1 files changed, 208 insertions, 44 deletions
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 3352a107b4a3..ea8661a00651 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -46,6 +46,7 @@ #include <rdma/rdma_netlink.h> #include <rdma/ib_addr.h> #include <rdma/ib_cache.h> +#include <rdma/rdma_counter.h> #include "core_priv.h" #include "restrack.h" @@ -93,11 +94,17 @@ static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC); static DECLARE_RWSEM(devices_rwsem); #define DEVICE_REGISTERED XA_MARK_1 -static LIST_HEAD(client_list); +static u32 highest_client_id; #define CLIENT_REGISTERED XA_MARK_1 static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC); static DECLARE_RWSEM(clients_rwsem); +static void ib_client_put(struct ib_client *client) +{ + if (refcount_dec_and_test(&client->uses)) + complete(&client->uses_zero); +} + /* * If client_data is registered then the corresponding client must also still * be registered. @@ -270,7 +277,7 @@ struct ib_port_data_rcu { struct ib_port_data pdata[]; }; -static int ib_device_check_mandatory(struct ib_device *device) +static void ib_device_check_mandatory(struct ib_device *device) { #define IB_MANDATORY_FUNC(x) { offsetof(struct ib_device_ops, x), #x } static const struct { @@ -305,8 +312,6 @@ static int ib_device_check_mandatory(struct ib_device *device) break; } } - - return 0; } /* @@ -375,7 +380,7 @@ struct ib_device *ib_device_get_by_name(const char *name, down_read(&devices_rwsem); device = __ib_device_get_by_name(name); if (device && driver_id != RDMA_DRIVER_UNKNOWN && - device->driver_id != driver_id) + device->ops.driver_id != driver_id) device = NULL; if (device) { @@ -449,6 +454,15 @@ int ib_device_rename(struct ib_device *ibdev, const char *name) return 0; } +int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim) +{ + if (use_dim > 1) + return -EINVAL; + ibdev->use_cq_dim = use_dim; + + return 0; +} + static int alloc_name(struct ib_device *ibdev, const char *name) { struct ib_device *device; @@ -494,10 +508,12 @@ static void ib_device_release(struct device *device) if (dev->port_data) { ib_cache_release_one(dev); ib_security_release_port_pkey_list(dev); + rdma_counter_release(dev); kfree_rcu(container_of(dev->port_data, struct ib_port_data_rcu, pdata[0]), rcu_head); } + xa_destroy(&dev->compat_devs); xa_destroy(&dev->client_data); kfree_rcu(dev, rcu_head); @@ -651,6 +667,14 @@ static int add_client_context(struct ib_device *device, down_write(&device->client_data_rwsem); /* + * So long as the client is registered hold both the client and device + * unregistration locks. + */ + if (!refcount_inc_not_zero(&client->uses)) + goto out_unlock; + refcount_inc(&device->refcount); + + /* * Another caller to add_client_context got here first and has already * completely initialized context. */ @@ -673,6 +697,9 @@ static int add_client_context(struct ib_device *device, return 0; out: + ib_device_put(device); + ib_client_put(client); +out_unlock: up_write(&device->client_data_rwsem); return ret; } @@ -692,7 +719,7 @@ static void remove_client_context(struct ib_device *device, client_data = xa_load(&device->client_data, client_id); xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED); client = xa_load(&clients, client_id); - downgrade_write(&device->client_data_rwsem); + up_write(&device->client_data_rwsem); /* * Notice we cannot be holding any exclusive locks when calling the @@ -702,17 +729,13 @@ static void remove_client_context(struct ib_device *device, * * For this reason clients and drivers should not call the * unregistration functions will holdling any locks. - * - * It tempting to drop the client_data_rwsem too, but this is required - * to ensure that unregister_client does not return until all clients - * are completely unregistered, which is required to avoid module - * unloading races. */ if (client->remove) client->remove(device, client_data); xa_erase(&device->client_data, client_id); - up_read(&device->client_data_rwsem); + ib_device_put(device); + ib_client_put(client); } static int alloc_port_data(struct ib_device *device) @@ -1193,10 +1216,7 @@ static int setup_device(struct ib_device *device) int ret; setup_dma_device(device); - - ret = ib_device_check_mandatory(device); - if (ret) - return ret; + ib_device_check_mandatory(device); ret = setup_port_data(device); if (ret) { @@ -1217,7 +1237,7 @@ static int setup_device(struct ib_device *device) static void disable_device(struct ib_device *device) { - struct ib_client *client; + u32 cid; WARN_ON(!refcount_read(&device->refcount)); @@ -1225,10 +1245,19 @@ static void disable_device(struct ib_device *device) xa_clear_mark(&devices, device->index, DEVICE_REGISTERED); up_write(&devices_rwsem); + /* + * Remove clients in LIFO order, see assign_client_id. This could be + * more efficient if xarray learns to reverse iterate. Since no new + * clients can be added to this ib_device past this point we only need + * the maximum possible client_id value here. + */ down_read(&clients_rwsem); - list_for_each_entry_reverse(client, &client_list, list) - remove_client_context(device, client->client_id); + cid = highest_client_id; up_read(&clients_rwsem); + while (cid) { + cid--; + remove_client_context(device, cid); + } /* Pairs with refcount_set in enable_device */ ib_device_put(device); @@ -1321,6 +1350,8 @@ int ib_register_device(struct ib_device *device, const char *name) ib_device_register_rdmacg(device); + rdma_counter_init(device); + /* * Ensure that ADD uevent is not fired because it * is too early amd device is not initialized yet. @@ -1479,7 +1510,7 @@ void ib_unregister_driver(enum rdma_driver_id driver_id) down_read(&devices_rwsem); xa_for_each (&devices, index, ib_dev) { - if (ib_dev->driver_id != driver_id) + if (ib_dev->ops.driver_id != driver_id) continue; get_device(&ib_dev->dev); @@ -1653,30 +1684,31 @@ static int assign_client_id(struct ib_client *client) /* * The add/remove callbacks must be called in FIFO/LIFO order. To * achieve this we assign client_ids so they are sorted in - * registration order, and retain a linked list we can reverse iterate - * to get the LIFO order. The extra linked list can go away if xarray - * learns to reverse iterate. + * registration order. */ - if (list_empty(&client_list)) { - client->client_id = 0; - } else { - struct ib_client *last; - - last = list_last_entry(&client_list, struct ib_client, list); - client->client_id = last->client_id + 1; - } + client->client_id = highest_client_id; ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL); if (ret) goto out; + highest_client_id++; xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED); - list_add_tail(&client->list, &client_list); out: up_write(&clients_rwsem); return ret; } +static void remove_client_id(struct ib_client *client) +{ + down_write(&clients_rwsem); + xa_erase(&clients, client->client_id); + for (; highest_client_id; highest_client_id--) + if (xa_load(&clients, highest_client_id - 1)) + break; + up_write(&clients_rwsem); +} + /** * ib_register_client - Register an IB client * @client:Client to register @@ -1696,6 +1728,8 @@ int ib_register_client(struct ib_client *client) unsigned long index; int ret; + refcount_set(&client->uses, 1); + init_completion(&client->uses_zero); ret = assign_client_id(client); if (ret) return ret; @@ -1731,24 +1765,131 @@ void ib_unregister_client(struct ib_client *client) unsigned long index; down_write(&clients_rwsem); + ib_client_put(client); xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED); up_write(&clients_rwsem); - /* - * Every device still known must be serialized to make sure we are - * done with the client callbacks before we return. - */ - down_read(&devices_rwsem); - xa_for_each (&devices, index, device) + + /* We do not want to have locks while calling client->remove() */ + rcu_read_lock(); + xa_for_each (&devices, index, device) { + if (!ib_device_try_get(device)) + continue; + rcu_read_unlock(); + remove_client_context(device, client->client_id); - up_read(&devices_rwsem); - down_write(&clients_rwsem); - list_del(&client->list); - xa_erase(&clients, client->client_id); - up_write(&clients_rwsem); + ib_device_put(device); + rcu_read_lock(); + } + rcu_read_unlock(); + + /* + * remove_client_context() is not a fence, it can return even though a + * removal is ongoing. Wait until all removals are completed. + */ + wait_for_completion(&client->uses_zero); + remove_client_id(client); } EXPORT_SYMBOL(ib_unregister_client); +static int __ib_get_global_client_nl_info(const char *client_name, + struct ib_client_nl_info *res) +{ + struct ib_client *client; + unsigned long index; + int ret = -ENOENT; + + down_read(&clients_rwsem); + xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { + if (strcmp(client->name, client_name) != 0) + continue; + if (!client->get_global_nl_info) { + ret = -EOPNOTSUPP; + break; + } + ret = client->get_global_nl_info(res); + if (WARN_ON(ret == -ENOENT)) + ret = -EINVAL; + if (!ret && res->cdev) + get_device(res->cdev); + break; + } + up_read(&clients_rwsem); + return ret; +} + +static int __ib_get_client_nl_info(struct ib_device *ibdev, + const char *client_name, + struct ib_client_nl_info *res) +{ + unsigned long index; + void *client_data; + int ret = -ENOENT; + + down_read(&ibdev->client_data_rwsem); + xan_for_each_marked (&ibdev->client_data, index, client_data, + CLIENT_DATA_REGISTERED) { + struct ib_client *client = xa_load(&clients, index); + + if (!client || strcmp(client->name, client_name) != 0) + continue; + if (!client->get_nl_info) { + ret = -EOPNOTSUPP; + break; + } + ret = client->get_nl_info(ibdev, client_data, res); + if (WARN_ON(ret == -ENOENT)) + ret = -EINVAL; + + /* + * The cdev is guaranteed valid as long as we are inside the + * client_data_rwsem as remove_one can't be called. Keep it + * valid for the caller. + */ + if (!ret && res->cdev) + get_device(res->cdev); + break; + } + up_read(&ibdev->client_data_rwsem); + + return ret; +} + +/** + * ib_get_client_nl_info - Fetch the nl_info from a client + * @device - IB device + * @client_name - Name of the client + * @res - Result of the query + */ +int ib_get_client_nl_info(struct ib_device *ibdev, const char *client_name, + struct ib_client_nl_info *res) +{ + int ret; + + if (ibdev) + ret = __ib_get_client_nl_info(ibdev, client_name, res); + else + ret = __ib_get_global_client_nl_info(client_name, res); +#ifdef CONFIG_MODULES + if (ret == -ENOENT) { + request_module("rdma-client-%s", client_name); + if (ibdev) + ret = __ib_get_client_nl_info(ibdev, client_name, res); + else + ret = __ib_get_global_client_nl_info(client_name, res); + } +#endif + if (ret) { + if (ret == -ENOENT) + return -EOPNOTSUPP; + return ret; + } + + if (WARN_ON(!res->cdev)) + return -EINVAL; + return 0; +} + /** * ib_set_client_data - Set IB client context * @device:Device to set context for @@ -2039,7 +2180,7 @@ struct ib_device *ib_device_get_by_netdev(struct net_device *ndev, (uintptr_t)ndev) { if (rcu_access_pointer(cur->netdev) == ndev && (driver_id == RDMA_DRIVER_UNKNOWN || - cur->ib_dev->driver_id == driver_id) && + cur->ib_dev->ops.driver_id == driver_id) && ib_device_try_get(cur->ib_dev)) { res = cur->ib_dev; break; @@ -2344,12 +2485,28 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) #define SET_OBJ_SIZE(ptr, name) SET_DEVICE_OP(ptr, size_##name) + if (ops->driver_id != RDMA_DRIVER_UNKNOWN) { + WARN_ON(dev_ops->driver_id != RDMA_DRIVER_UNKNOWN && + dev_ops->driver_id != ops->driver_id); + dev_ops->driver_id = ops->driver_id; + } + if (ops->owner) { + WARN_ON(dev_ops->owner && dev_ops->owner != ops->owner); + dev_ops->owner = ops->owner; + } + if (ops->uverbs_abi_ver) + dev_ops->uverbs_abi_ver = ops->uverbs_abi_ver; + + dev_ops->uverbs_no_driver_id_binding |= + ops->uverbs_no_driver_id_binding; + SET_DEVICE_OP(dev_ops, add_gid); SET_DEVICE_OP(dev_ops, advise_mr); SET_DEVICE_OP(dev_ops, alloc_dm); SET_DEVICE_OP(dev_ops, alloc_fmr); SET_DEVICE_OP(dev_ops, alloc_hw_stats); SET_DEVICE_OP(dev_ops, alloc_mr); + SET_DEVICE_OP(dev_ops, alloc_mr_integrity); SET_DEVICE_OP(dev_ops, alloc_mw); SET_DEVICE_OP(dev_ops, alloc_pd); SET_DEVICE_OP(dev_ops, alloc_rdma_netdev); @@ -2357,6 +2514,11 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, alloc_xrcd); SET_DEVICE_OP(dev_ops, attach_mcast); SET_DEVICE_OP(dev_ops, check_mr_status); + SET_DEVICE_OP(dev_ops, counter_alloc_stats); + SET_DEVICE_OP(dev_ops, counter_bind_qp); + SET_DEVICE_OP(dev_ops, counter_dealloc); + SET_DEVICE_OP(dev_ops, counter_unbind_qp); + SET_DEVICE_OP(dev_ops, counter_update_stats); SET_DEVICE_OP(dev_ops, create_ah); SET_DEVICE_OP(dev_ops, create_counters); SET_DEVICE_OP(dev_ops, create_cq); @@ -2409,6 +2571,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, iw_reject); SET_DEVICE_OP(dev_ops, iw_rem_ref); SET_DEVICE_OP(dev_ops, map_mr_sg); + SET_DEVICE_OP(dev_ops, map_mr_sg_pi); SET_DEVICE_OP(dev_ops, map_phys_fmr); SET_DEVICE_OP(dev_ops, mmap); SET_DEVICE_OP(dev_ops, modify_ah); @@ -2445,6 +2608,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, unmap_fmr); SET_OBJ_SIZE(dev_ops, ib_ah); + SET_OBJ_SIZE(dev_ops, ib_cq); SET_OBJ_SIZE(dev_ops, ib_pd); SET_OBJ_SIZE(dev_ops, ib_srq); SET_OBJ_SIZE(dev_ops, ib_ucontext); |