diff options
Diffstat (limited to 'drivers/infiniband/core/device.c')
| -rw-r--r-- | drivers/infiniband/core/device.c | 211 |
1 files changed, 130 insertions, 81 deletions
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index ea8661a00651..f6c255202d7f 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -39,7 +39,6 @@ #include <linux/init.h> #include <linux/netdevice.h> #include <net/net_namespace.h> -#include <net/netns/generic.h> #include <linux/security.h> #include <linux/notifier.h> #include <linux/hashtable.h> @@ -111,17 +110,7 @@ static void ib_client_put(struct ib_client *client) */ #define CLIENT_DATA_REGISTERED XA_MARK_1 -/** - * struct rdma_dev_net - rdma net namespace metadata for a net - * @net: Pointer to owner net namespace - * @id: xarray id to identify the net namespace. - */ -struct rdma_dev_net { - possible_net_t net; - u32 id; -}; - -static unsigned int rdma_dev_net_id; +unsigned int rdma_dev_net_id; /* * A list of net namespaces is maintained in an xarray. This is necessary @@ -139,17 +128,14 @@ module_param_named(netns_mode, ib_devices_shared_netns, bool, 0444); MODULE_PARM_DESC(netns_mode, "Share device among net namespaces; default=1 (shared)"); /** - * rdma_dev_access_netns() - Return whether a rdma device can be accessed + * rdma_dev_access_netns() - Return whether an rdma device can be accessed * from a specified net namespace or not. - * @device: Pointer to rdma device which needs to be checked + * @dev: Pointer to rdma device which needs to be checked * @net: Pointer to net namesapce for which access to be checked * - * rdma_dev_access_netns() - Return whether a rdma device can be accessed - * from a specified net namespace or not. When - * rdma device is in shared mode, it ignores the - * net namespace. When rdma device is exclusive - * to a net namespace, rdma device net namespace is - * checked against the specified one. + * When the rdma device is in shared mode, it ignores the net namespace. + * When the rdma device is exclusive to a net namespace, rdma device net + * namespace is checked against the specified one. */ bool rdma_dev_access_netns(const struct ib_device *dev, const struct net *net) { @@ -514,6 +500,9 @@ static void ib_device_release(struct device *device) rcu_head); } + mutex_destroy(&dev->unregistration_lock); + mutex_destroy(&dev->compat_devs_mutex); + xa_destroy(&dev->compat_devs); xa_destroy(&dev->client_data); kfree_rcu(dev, rcu_head); @@ -598,7 +587,8 @@ struct ib_device *_ib_alloc_device(size_t size) rdma_init_coredev(&device->coredev, device, &init_net); INIT_LIST_HEAD(&device->event_handler_list); - spin_lock_init(&device->event_handler_lock); + spin_lock_init(&device->qp_open_list_lock); + init_rwsem(&device->event_handler_rwsem); mutex_init(&device->unregistration_lock); /* * client_data needs to be alloc because we don't want our mark to be @@ -1060,7 +1050,7 @@ int rdma_compatdev_set(u8 enable) static void rdma_dev_exit_net(struct net *net) { - struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id); + struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); struct ib_device *dev; unsigned long index; int ret; @@ -1094,25 +1084,32 @@ static void rdma_dev_exit_net(struct net *net) } up_read(&devices_rwsem); + rdma_nl_net_exit(rnet); xa_erase(&rdma_nets, rnet->id); } static __net_init int rdma_dev_init_net(struct net *net) { - struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id); + struct rdma_dev_net *rnet = rdma_net_to_dev_net(net); unsigned long index; struct ib_device *dev; int ret; + write_pnet(&rnet->net, net); + + ret = rdma_nl_net_init(rnet); + if (ret) + return ret; + /* No need to create any compat devices in default init_net. */ if (net_eq(net, &init_net)) return 0; - write_pnet(&rnet->net, net); - ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL); - if (ret) + if (ret) { + rdma_nl_net_exit(rnet); return ret; + } down_read(&devices_rwsem); xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) { @@ -1200,9 +1197,21 @@ static void setup_dma_device(struct ib_device *device) WARN_ON_ONCE(!parent); device->dma_device = parent; } - /* Setup default max segment size for all IB devices */ - dma_set_max_seg_size(device->dma_device, SZ_2G); + if (!device->dev.dma_parms) { + if (parent) { + /* + * The caller did not provide DMA parameters, so + * 'parent' probably represents a PCI device. The PCI + * core sets the maximum segment size to 64 + * KB. Increase this parameter to 2 GB. + */ + device->dev.dma_parms = parent->dma_parms; + dma_set_max_seg_size(device->dma_device, SZ_2G); + } else { + WARN_ON_ONCE(true); + } + } } /* @@ -1318,7 +1327,9 @@ out: /** * ib_register_device - Register an IB device with IB core - * @device:Device to register + * @device: Device to register + * @name: unique string device name. This may include a '%' which will + * cause a unique index to be added to the passed device name. * * Low-level drivers use ib_register_device() to register their * devices with the IB core. All registered clients will receive a @@ -1445,7 +1456,7 @@ out: /** * ib_unregister_device - Unregister an IB device - * @device: The device to unregister + * @ib_dev: The device to unregister * * Unregister an IB device. All clients will receive a remove callback. * @@ -1467,7 +1478,7 @@ EXPORT_SYMBOL(ib_unregister_device); /** * ib_unregister_device_and_put - Unregister a device while holding a 'get' - * device: The device to unregister + * @ib_dev: The device to unregister * * This is the same as ib_unregister_device(), except it includes an internal * ib_device_put() that should match a 'get' obtained by the caller. @@ -1537,7 +1548,7 @@ static void ib_unregister_work(struct work_struct *work) /** * ib_unregister_device_queued - Unregister a device using a work queue - * device: The device to unregister + * @ib_dev: The device to unregister * * This schedules an asynchronous unregistration using a WQ for the device. A * driver should use this to avoid holding locks while doing unregistration, @@ -1921,17 +1932,15 @@ EXPORT_SYMBOL(ib_set_client_data); * * ib_register_event_handler() registers an event handler that will be * called back when asynchronous IB events occur (as defined in - * chapter 11 of the InfiniBand Architecture Specification). This - * callback may occur in interrupt context. + * chapter 11 of the InfiniBand Architecture Specification). This + * callback occurs in workqueue context. */ void ib_register_event_handler(struct ib_event_handler *event_handler) { - unsigned long flags; - - spin_lock_irqsave(&event_handler->device->event_handler_lock, flags); + down_write(&event_handler->device->event_handler_rwsem); list_add_tail(&event_handler->list, &event_handler->device->event_handler_list); - spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags); + up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_register_event_handler); @@ -1944,61 +1953,78 @@ EXPORT_SYMBOL(ib_register_event_handler); */ void ib_unregister_event_handler(struct ib_event_handler *event_handler) { - unsigned long flags; - - spin_lock_irqsave(&event_handler->device->event_handler_lock, flags); + down_write(&event_handler->device->event_handler_rwsem); list_del(&event_handler->list); - spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags); + up_write(&event_handler->device->event_handler_rwsem); } EXPORT_SYMBOL(ib_unregister_event_handler); -/** - * ib_dispatch_event - Dispatch an asynchronous event - * @event:Event to dispatch - * - * Low-level drivers must call ib_dispatch_event() to dispatch the - * event to all registered event handlers when an asynchronous event - * occurs. - */ -void ib_dispatch_event(struct ib_event *event) +void ib_dispatch_event_clients(struct ib_event *event) { - unsigned long flags; struct ib_event_handler *handler; - spin_lock_irqsave(&event->device->event_handler_lock, flags); + down_read(&event->device->event_handler_rwsem); list_for_each_entry(handler, &event->device->event_handler_list, list) handler->handler(handler, event); - spin_unlock_irqrestore(&event->device->event_handler_lock, flags); + up_read(&event->device->event_handler_rwsem); } -EXPORT_SYMBOL(ib_dispatch_event); -/** - * ib_query_port - Query IB port attributes - * @device:Device to query - * @port_num:Port number to query - * @port_attr:Port attributes - * - * ib_query_port() returns the attributes of a port through the - * @port_attr pointer. - */ -int ib_query_port(struct ib_device *device, - u8 port_num, - struct ib_port_attr *port_attr) +static int iw_query_port(struct ib_device *device, + u8 port_num, + struct ib_port_attr *port_attr) { - union ib_gid gid; - int err; + struct in_device *inetdev; + struct net_device *netdev; - if (!rdma_is_port_valid(device, port_num)) - return -EINVAL; + memset(port_attr, 0, sizeof(*port_attr)); + + netdev = ib_device_get_netdev(device, port_num); + if (!netdev) + return -ENODEV; + + port_attr->max_mtu = IB_MTU_4096; + port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu); + + if (!netif_carrier_ok(netdev)) { + port_attr->state = IB_PORT_DOWN; + port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; + } else { + rcu_read_lock(); + inetdev = __in_dev_get_rcu(netdev); + + if (inetdev && inetdev->ifa_list) { + port_attr->state = IB_PORT_ACTIVE; + port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; + } else { + port_attr->state = IB_PORT_INIT; + port_attr->phys_state = + IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING; + } + + rcu_read_unlock(); + } + + dev_put(netdev); + return device->ops.query_port(device, port_num, port_attr); +} + +static int __ib_query_port(struct ib_device *device, + u8 port_num, + struct ib_port_attr *port_attr) +{ + union ib_gid gid = {}; + int err; memset(port_attr, 0, sizeof(*port_attr)); + err = device->ops.query_port(device, port_num, port_attr); if (err || port_attr->subnet_prefix) return err; - if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND) + if (rdma_port_get_link_layer(device, port_num) != + IB_LINK_LAYER_INFINIBAND) return 0; err = device->ops.query_gid(device, port_num, 0, &gid); @@ -2008,6 +2034,28 @@ int ib_query_port(struct ib_device *device, port_attr->subnet_prefix = be64_to_cpu(gid.global.subnet_prefix); return 0; } + +/** + * ib_query_port - Query IB port attributes + * @device:Device to query + * @port_num:Port number to query + * @port_attr:Port attributes + * + * ib_query_port() returns the attributes of a port through the + * @port_attr pointer. + */ +int ib_query_port(struct ib_device *device, + u8 port_num, + struct ib_port_attr *port_attr) +{ + if (!rdma_is_port_valid(device, port_num)) + return -EINVAL; + + if (rdma_protocol_iwarp(device, port_num)) + return iw_query_port(device, port_num, port_attr); + else + return __ib_query_port(device, port_num, port_attr); +} EXPORT_SYMBOL(ib_query_port); static void add_ndev_hash(struct ib_port_data *pdata) @@ -2311,7 +2359,7 @@ int ib_modify_device(struct ib_device *device, struct ib_device_modify *device_modify) { if (!device->ops.modify_device) - return -ENOSYS; + return -EOPNOTSUPP; return device->ops.modify_device(device, device_modify_mask, device_modify); @@ -2342,8 +2390,12 @@ int ib_modify_port(struct ib_device *device, rc = device->ops.modify_port(device, port_num, port_modify_mask, port_modify); + else if (rdma_protocol_roce(device, port_num) && + ((port_modify->set_port_cap_mask & ~IB_PORT_CM_SUP) == 0 || + (port_modify->clr_port_cap_mask & ~IB_PORT_CM_SUP) == 0)) + rc = 0; else - rc = rdma_protocol_roce(device, port_num) ? 0 : -ENOSYS; + rc = -EOPNOTSUPP; return rc; } EXPORT_SYMBOL(ib_modify_port); @@ -2552,6 +2604,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, drain_sq); SET_DEVICE_OP(dev_ops, enable_driver); SET_DEVICE_OP(dev_ops, fill_res_entry); + SET_DEVICE_OP(dev_ops, fill_stat_entry); SET_DEVICE_OP(dev_ops, get_dev_fw_str); SET_DEVICE_OP(dev_ops, get_dma_mr); SET_DEVICE_OP(dev_ops, get_hw_stats); @@ -2560,6 +2613,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) SET_DEVICE_OP(dev_ops, get_port_immutable); SET_DEVICE_OP(dev_ops, get_vector_affinity); SET_DEVICE_OP(dev_ops, get_vf_config); + SET_DEVICE_OP(dev_ops, get_vf_guid); SET_DEVICE_OP(dev_ops, get_vf_stats); SET_DEVICE_OP(dev_ops, init_port); SET_DEVICE_OP(dev_ops, iw_accept); @@ -2574,6 +2628,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops) 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, mmap_free); SET_DEVICE_OP(dev_ops, modify_ah); SET_DEVICE_OP(dev_ops, modify_cq); SET_DEVICE_OP(dev_ops, modify_device); @@ -2660,11 +2715,7 @@ static int __init ib_core_init(void) goto err_comp_unbound; } - ret = rdma_nl_init(); - if (ret) { - pr_warn("Couldn't init IB netlink interface: err %d\n", ret); - goto err_sysfs; - } + rdma_nl_init(); ret = addr_init(); if (ret) { @@ -2711,8 +2762,6 @@ err_mad: err_addr: addr_cleanup(); err_ibnl: - rdma_nl_exit(); -err_sysfs: class_unregister(&ib_class); err_comp_unbound: destroy_workqueue(ib_comp_unbound_wq); |
