From 748e4f3d702def1a4bff191e0cf93b6a05340f01 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:41:34 +0000
Subject: [PATCH] add gpio led uart
---
kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c | 275 +++++++++++++++++++++++++++++++++++-------------------
1 files changed, 176 insertions(+), 99 deletions(-)
diff --git a/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c b/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c
index d0c35eb..35322d2 100644
--- a/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/kernel/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -52,10 +52,6 @@
#include <linux/inetdevice.h>
#include <rdma/ib_cache.h>
-#define DRV_VERSION "1.0.0"
-
-const char ipoib_driver_version[] = DRV_VERSION;
-
MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("IP-over-InfiniBand net driver");
MODULE_LICENSE("Dual BSD/GPL");
@@ -90,7 +86,7 @@
struct ib_sa_client ipoib_sa_client;
-static void ipoib_add_one(struct ib_device *device);
+static int ipoib_add_one(struct ib_device *device);
static void ipoib_remove_one(struct ib_device *device, void *client_data);
static void ipoib_neigh_reclaim(struct rcu_head *rp);
static struct net_device *ipoib_get_net_dev_by_params(
@@ -167,7 +163,7 @@
if (flags & IFF_UP)
continue;
- dev_change_flags(cpriv->dev, flags | IFF_UP);
+ dev_change_flags(cpriv->dev, flags | IFF_UP, NULL);
}
up_read(&priv->vlan_rwsem);
}
@@ -207,7 +203,7 @@
if (!(flags & IFF_UP))
continue;
- dev_change_flags(cpriv->dev, flags & ~IFF_UP);
+ dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL);
}
up_read(&priv->vlan_rwsem);
}
@@ -346,9 +342,10 @@
struct net_device *result;
};
-static int ipoib_upper_walk(struct net_device *upper, void *_data)
+static int ipoib_upper_walk(struct net_device *upper,
+ struct netdev_nested_priv *priv)
{
- struct ipoib_walk_data *data = _data;
+ struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data;
int ret = 0;
if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) {
@@ -372,10 +369,12 @@
static struct net_device *ipoib_get_net_dev_match_addr(
const struct sockaddr *addr, struct net_device *dev)
{
+ struct netdev_nested_priv priv;
struct ipoib_walk_data data = {
.addr = addr,
};
+ priv.data = (void *)&data;
rcu_read_lock();
if (ipoib_is_dev_match_addr_rcu(addr, dev)) {
dev_hold(dev);
@@ -383,7 +382,7 @@
goto out;
}
- netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &data);
+ netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv);
out:
rcu_read_unlock();
return data.result;
@@ -483,9 +482,6 @@
if (ret)
return NULL;
- if (!dev_list)
- return NULL;
-
/* See if we can find a unique device matching the L2 parameters */
matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index,
gid, NULL, &net_dev);
@@ -509,7 +505,7 @@
default:
dev_warn_ratelimited(&dev->dev,
"duplicate IP address detected\n");
- /* Fall through */
+ fallthrough;
case 1:
return net_dev;
}
@@ -533,6 +529,7 @@
"will cause multicast packet drops\n");
netdev_update_features(dev);
dev_set_mtu(dev, ipoib_cm_max_mtu(dev));
+ netif_set_real_num_tx_queues(dev, 1);
rtnl_unlock();
priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM;
@@ -544,6 +541,7 @@
clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags);
netdev_update_features(dev);
dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
+ netif_set_real_num_tx_queues(dev, dev->num_tx_queues);
rtnl_unlock();
ipoib_flush_paths(dev);
return (!rtnl_trylock()) ? -EBUSY : 0;
@@ -613,7 +611,7 @@
while ((skb = __skb_dequeue(&path->queue)))
dev_kfree_skb_irq(skb);
- ipoib_dbg(ipoib_priv(dev), "path_free\n");
+ ipoib_dbg(ipoib_priv(dev), "%s\n", __func__);
/* remove all neigh connected to this path */
ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw);
@@ -1182,7 +1180,7 @@
return NETDEV_TX_OK;
}
-static void ipoib_timeout(struct net_device *dev)
+static void ipoib_timeout(struct net_device *dev, unsigned int txqueue)
{
struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -1643,7 +1641,7 @@
{
struct ipoib_dev_priv *priv = ipoib_priv(dev);
- ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n");
+ ipoib_dbg(priv, "%s\n", __func__);
init_completion(&priv->ntbl.deleted);
cancel_delayed_work_sync(&priv->neigh_reap_task);
@@ -1825,7 +1823,7 @@
* running ensures the it will not add more work.
*/
rtnl_lock();
- dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP);
+ dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL);
rtnl_unlock();
/* ipoib_event() cannot be running once this returns */
@@ -1864,7 +1862,7 @@
priv->port);
return result;
}
- priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+ priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr);
result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
if (result) {
@@ -1897,14 +1895,22 @@
priv->max_ib_mtu = ppriv->max_ib_mtu;
set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags);
- memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
- memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid));
+ if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN))
+ memcpy(&priv->local_gid, priv->dev->dev_addr + 4,
+ sizeof(priv->local_gid));
+ else {
+ memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr,
+ INFINIBAND_ALEN);
+ memcpy(&priv->local_gid, &ppriv->local_gid,
+ sizeof(priv->local_gid));
+ }
}
static int ipoib_ndo_init(struct net_device *ndev)
{
struct ipoib_dev_priv *priv = ipoib_priv(ndev);
int rc;
+ struct rdma_netdev *rn = netdev_priv(ndev);
if (priv->parent) {
ipoib_child_init(ndev);
@@ -1917,6 +1923,7 @@
/* MTU will be reset when mcast join happens */
ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
priv->mcast_mtu = priv->admin_mtu = ndev->mtu;
+ rn->mtu = priv->mcast_mtu;
ndev->max_mtu = IPOIB_CM_MTU;
ndev->neigh_priv_len = sizeof(struct ipoib_neigh);
@@ -2023,6 +2030,15 @@
return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type);
}
+static int ipoib_get_vf_guid(struct net_device *dev, int vf,
+ struct ifla_vf_guid *node_guid,
+ struct ifla_vf_guid *port_guid)
+{
+ struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+ return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid);
+}
+
static int ipoib_get_vf_stats(struct net_device *dev, int vf,
struct ifla_vf_stats *vf_stats)
{
@@ -2049,6 +2065,7 @@
.ndo_set_vf_link_state = ipoib_set_vf_link_state,
.ndo_get_vf_config = ipoib_get_vf_config,
.ndo_get_vf_stats = ipoib_get_vf_stats,
+ .ndo_get_vf_guid = ipoib_get_vf_guid,
.ndo_set_vf_guid = ipoib_set_vf_guid,
.ndo_set_mac_address = ipoib_set_mac,
.ndo_get_stats64 = ipoib_get_stats,
@@ -2070,9 +2087,17 @@
.ndo_do_ioctl = ipoib_ioctl,
};
+static const struct net_device_ops ipoib_netdev_default_pf = {
+ .ndo_init = ipoib_dev_init_default,
+ .ndo_uninit = ipoib_dev_uninit_default,
+ .ndo_open = ipoib_ib_dev_open_default,
+ .ndo_stop = ipoib_ib_dev_stop_default,
+};
+
void ipoib_setup_common(struct net_device *dev)
{
dev->header_ops = &ipoib_header_ops;
+ dev->netdev_ops = &ipoib_netdev_default_pf;
ipoib_set_ethtool_ops(dev);
@@ -2122,89 +2147,65 @@
INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh);
}
-static const struct net_device_ops ipoib_netdev_default_pf = {
- .ndo_init = ipoib_dev_init_default,
- .ndo_uninit = ipoib_dev_uninit_default,
- .ndo_open = ipoib_ib_dev_open_default,
- .ndo_stop = ipoib_ib_dev_stop_default,
-};
-
-static struct net_device
-*ipoib_create_netdev_default(struct ib_device *hca,
- const char *name,
- unsigned char name_assign_type,
- void (*setup)(struct net_device *))
+static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u8 port,
+ const char *name)
{
struct net_device *dev;
- struct rdma_netdev *rn;
- dev = alloc_netdev((int)sizeof(struct rdma_netdev),
- name,
- name_assign_type, setup);
+ dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name,
+ NET_NAME_UNKNOWN, ipoib_setup_common);
+ if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP)
+ return dev;
+
+ dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN,
+ ipoib_setup_common);
if (!dev)
- return NULL;
-
- rn = netdev_priv(dev);
-
- rn->send = ipoib_send;
- rn->attach_mcast = ipoib_mcast_attach;
- rn->detach_mcast = ipoib_mcast_detach;
- rn->hca = hca;
- dev->netdev_ops = &ipoib_netdev_default_pf;
-
+ return ERR_PTR(-ENOMEM);
return dev;
}
-static struct net_device *ipoib_get_netdev(struct ib_device *hca, u8 port,
- const char *name)
+int ipoib_intf_init(struct ib_device *hca, u8 port, const char *name,
+ struct net_device *dev)
{
- struct net_device *dev;
-
- if (hca->alloc_rdma_netdev) {
- dev = hca->alloc_rdma_netdev(hca, port,
- RDMA_NETDEV_IPOIB, name,
- NET_NAME_UNKNOWN,
- ipoib_setup_common);
- if (IS_ERR_OR_NULL(dev) && PTR_ERR(dev) != -EOPNOTSUPP)
- return NULL;
- }
-
- if (!hca->alloc_rdma_netdev || PTR_ERR(dev) == -EOPNOTSUPP)
- dev = ipoib_create_netdev_default(hca, name, NET_NAME_UNKNOWN,
- ipoib_setup_common);
-
- return dev;
-}
-
-struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port,
- const char *name)
-{
- struct net_device *dev;
+ struct rdma_netdev *rn = netdev_priv(dev);
struct ipoib_dev_priv *priv;
- struct rdma_netdev *rn;
+ int rc;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
- return NULL;
+ return -ENOMEM;
priv->ca = hca;
priv->port = port;
- dev = ipoib_get_netdev(hca, port, name);
- if (!dev)
- goto free_priv;
+ rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name,
+ NET_NAME_UNKNOWN, ipoib_setup_common, dev);
+ if (rc) {
+ if (rc != -EOPNOTSUPP)
+ goto out;
+
+ rn->send = ipoib_send;
+ rn->attach_mcast = ipoib_mcast_attach;
+ rn->detach_mcast = ipoib_mcast_detach;
+ rn->hca = hca;
+
+ rc = netif_set_real_num_tx_queues(dev, 1);
+ if (rc)
+ goto out;
+
+ rc = netif_set_real_num_rx_queues(dev, 1);
+ if (rc)
+ goto out;
+ }
priv->rn_ops = dev->netdev_ops;
- /* fixme : should be after the query_cap */
- if (priv->hca_caps & IB_DEVICE_VIRTUAL_FUNCTION)
+ if (hca->attrs.device_cap_flags & IB_DEVICE_VIRTUAL_FUNCTION)
dev->netdev_ops = &ipoib_netdev_ops_vf;
else
dev->netdev_ops = &ipoib_netdev_ops_pf;
- rn = netdev_priv(dev);
rn->clnt_priv = priv;
-
/*
* Only the child register_netdev flows can handle priv_destructor
* being set, so we force it to NULL here and handle manually until it
@@ -2215,10 +2216,35 @@
ipoib_build_priv(dev);
- return priv;
-free_priv:
+ return 0;
+
+out:
kfree(priv);
- return NULL;
+ return rc;
+}
+
+struct net_device *ipoib_intf_alloc(struct ib_device *hca, u8 port,
+ const char *name)
+{
+ struct net_device *dev;
+ int rc;
+
+ dev = ipoib_alloc_netdev(hca, port, name);
+ if (IS_ERR(dev))
+ return dev;
+
+ rc = ipoib_intf_init(hca, port, name, dev);
+ if (rc) {
+ free_netdev(dev);
+ return ERR_PTR(rc);
+ }
+
+ /*
+ * Upon success the caller must ensure ipoib_intf_free is called or
+ * register_netdevice succeed'd and priv_destructor is set to
+ * ipoib_intf_free.
+ */
+ return dev;
}
void ipoib_intf_free(struct net_device *dev)
@@ -2398,19 +2424,62 @@
return device_create_file(&dev->dev, &dev_attr_pkey);
}
+/*
+ * We erroneously exposed the iface's port number in the dev_id
+ * sysfs field long after dev_port was introduced for that purpose[1],
+ * and we need to stop everyone from relying on that.
+ * Let's overload the shower routine for the dev_id file here
+ * to gently bring the issue up.
+ *
+ * [1] https://www.spinics.net/lists/netdev/msg272123.html
+ */
+static ssize_t dev_id_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct net_device *ndev = to_net_dev(dev);
+
+ /*
+ * ndev->dev_port will be equal to 0 in old kernel prior to commit
+ * 9b8b2a323008 ("IB/ipoib: Use dev_port to expose network interface
+ * port numbers") Zero was chosen as special case for user space
+ * applications to fallback and query dev_id to check if it has
+ * different value or not.
+ *
+ * Don't print warning in such scenario.
+ *
+ * https://github.com/systemd/systemd/blob/master/src/udev/udev-builtin-net_id.c#L358
+ */
+ if (ndev->dev_port && ndev->dev_id == ndev->dev_port)
+ netdev_info_once(ndev,
+ "\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n",
+ current->comm);
+
+ return sprintf(buf, "%#x\n", ndev->dev_id);
+}
+static DEVICE_ATTR_RO(dev_id);
+
+static int ipoib_intercept_dev_id_attr(struct net_device *dev)
+{
+ device_remove_file(&dev->dev, &dev_attr_dev_id);
+ return device_create_file(&dev->dev, &dev_attr_dev_id);
+}
+
static struct net_device *ipoib_add_port(const char *format,
struct ib_device *hca, u8 port)
{
+ struct rtnl_link_ops *ops = ipoib_get_link_ops();
+ struct rdma_netdev_alloc_params params;
struct ipoib_dev_priv *priv;
struct net_device *ndev;
int result;
- priv = ipoib_intf_alloc(hca, port, format);
- if (!priv) {
- pr_warn("%s, %d: ipoib_intf_alloc failed\n", hca->name, port);
- return ERR_PTR(-ENOMEM);
+ ndev = ipoib_intf_alloc(hca, port, format);
+ if (IS_ERR(ndev)) {
+ pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port,
+ PTR_ERR(ndev));
+ return ndev;
}
- ndev = priv->dev;
+ priv = ipoib_priv(ndev);
INIT_IB_EVENT_HANDLER(&priv->event_handler,
priv->ca, ipoib_event);
@@ -2418,6 +2487,8 @@
/* call event handler to ensure pkey in sync */
queue_work(ipoib_workqueue, &priv->flush_heavy);
+
+ ndev->rtnl_link_ops = ipoib_get_link_ops();
result = register_netdev(ndev);
if (result) {
@@ -2431,6 +2502,14 @@
return ERR_PTR(result);
}
+ if (hca->ops.rdma_netdev_get_params) {
+ int rc = hca->ops.rdma_netdev_get_params(hca, port,
+ RDMA_NETDEV_IPOIB,
+ ¶ms);
+
+ if (!rc && ops->priv_size < params.sizeof_priv)
+ ops->priv_size = params.sizeof_priv;
+ }
/*
* We cannot set priv_destructor before register_netdev because we
* need priv to be always valid during the error flow to execute
@@ -2439,6 +2518,8 @@
*/
ndev->priv_destructor = ipoib_intf_free;
+ if (ipoib_intercept_dev_id_attr(ndev))
+ goto sysfs_failed;
if (ipoib_cm_add_mode_attr(ndev))
goto sysfs_failed;
if (ipoib_add_pkey_attr(ndev))
@@ -2458,21 +2539,21 @@
return ERR_PTR(-ENOMEM);
}
-static void ipoib_add_one(struct ib_device *device)
+static int ipoib_add_one(struct ib_device *device)
{
struct list_head *dev_list;
struct net_device *dev;
struct ipoib_dev_priv *priv;
- int p;
+ unsigned int p;
int count = 0;
dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL);
if (!dev_list)
- return;
+ return -ENOMEM;
INIT_LIST_HEAD(dev_list);
- for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
+ rdma_for_each_port (device, p) {
if (!rdma_protocol_ib(device, p))
continue;
dev = ipoib_add_port("ib%d", device, p);
@@ -2485,19 +2566,17 @@
if (!count) {
kfree(dev_list);
- return;
+ return -EOPNOTSUPP;
}
ib_set_client_data(device, &ipoib_client, dev_list);
+ return 0;
}
static void ipoib_remove_one(struct ib_device *device, void *client_data)
{
struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv;
struct list_head *dev_list = client_data;
-
- if (!dev_list)
- return;
list_for_each_entry_safe(priv, tmp, dev_list, list) {
LIST_HEAD(head);
@@ -2545,9 +2624,7 @@
*/
BUILD_BUG_ON(IPOIB_CM_COPYBREAK > IPOIB_CM_HEAD_SIZE);
- ret = ipoib_register_debugfs();
- if (ret)
- return ret;
+ ipoib_register_debugfs();
/*
* We create a global workqueue here that is used for all flush
--
Gitblit v1.6.2