summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/hw/mlx5/ib_rep.c103
-rw-r--r--drivers/infiniband/hw/qib/qib_user_pages.c2
-rw-r--r--drivers/infiniband/hw/usnic/usnic_uiom.c2
-rw-r--r--drivers/infiniband/sw/rxe/rxe_verbs.c2
-rw-r--r--drivers/infiniband/sw/siw/siw_mem.c2
-rw-r--r--drivers/infiniband/sw/siw/siw_qp_tx.c16
6 files changed, 81 insertions, 46 deletions
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index ddcfc116b19a..c7a4ee896121 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -30,45 +30,65 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev,
static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev);
+static void mlx5_ib_num_ports_update(struct mlx5_core_dev *dev, u32 *num_ports)
+{
+ struct mlx5_core_dev *peer_dev;
+ int i;
+
+ mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) {
+ u32 peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev);
+
+ if (mlx5_lag_is_mpesw(peer_dev))
+ *num_ports += peer_num_ports;
+ else
+ /* Only 1 ib port is the representor for all uplinks */
+ *num_ports += peer_num_ports - 1;
+ }
+}
+
static int
mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
{
u32 num_ports = mlx5_eswitch_get_total_vports(dev);
+ struct mlx5_core_dev *lag_master = dev;
const struct mlx5_ib_profile *profile;
struct mlx5_core_dev *peer_dev;
struct mlx5_ib_dev *ibdev;
- int second_uplink = false;
- u32 peer_num_ports;
+ int new_uplink = false;
int vport_index;
int ret;
+ int i;
vport_index = rep->vport_index;
if (mlx5_lag_is_shared_fdb(dev)) {
- peer_dev = mlx5_lag_get_peer_mdev(dev);
- peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev);
if (mlx5_lag_is_master(dev)) {
- if (mlx5_lag_is_mpesw(dev))
- num_ports += peer_num_ports;
- else
- num_ports += peer_num_ports - 1;
-
+ mlx5_ib_num_ports_update(dev, &num_ports);
} else {
if (rep->vport == MLX5_VPORT_UPLINK) {
if (!mlx5_lag_is_mpesw(dev))
return 0;
- second_uplink = true;
+ new_uplink = true;
}
+ mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) {
+ u32 peer_n_ports = mlx5_eswitch_get_total_vports(peer_dev);
+
+ if (mlx5_lag_is_master(peer_dev))
+ lag_master = peer_dev;
+ else if (!mlx5_lag_is_mpesw(dev))
+ /* Only 1 ib port is the representor for all uplinks */
+ peer_n_ports--;
- vport_index += peer_num_ports;
- dev = peer_dev;
+ if (mlx5_get_dev_index(peer_dev) < mlx5_get_dev_index(dev))
+ vport_index += peer_n_ports;
+ }
}
}
- if (rep->vport == MLX5_VPORT_UPLINK && !second_uplink)
+ if (rep->vport == MLX5_VPORT_UPLINK && !new_uplink)
profile = &raw_eth_profile;
else
- return mlx5_ib_set_vport_rep(dev, rep, vport_index);
+ return mlx5_ib_set_vport_rep(lag_master, rep, vport_index);
ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev);
if (!ibdev)
@@ -85,8 +105,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
vport_index = rep->vport_index;
ibdev->port[vport_index].rep = rep;
ibdev->port[vport_index].roce.netdev =
- mlx5_ib_get_rep_netdev(dev->priv.eswitch, rep->vport);
- ibdev->mdev = dev;
+ mlx5_ib_get_rep_netdev(lag_master->priv.eswitch, rep->vport);
+ ibdev->mdev = lag_master;
ibdev->num_ports = num_ports;
ret = __mlx5_ib_add(ibdev, profile);
@@ -94,8 +114,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
goto fail_add;
rep->rep_data[REP_IB].priv = ibdev;
- if (mlx5_lag_is_shared_fdb(dev))
- mlx5_ib_register_peer_vport_reps(dev);
+ if (mlx5_lag_is_shared_fdb(lag_master))
+ mlx5_ib_register_peer_vport_reps(lag_master);
return 0;
@@ -118,23 +138,27 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
struct mlx5_ib_dev *dev = mlx5_ib_rep_to_dev(rep);
int vport_index = rep->vport_index;
struct mlx5_ib_port *port;
+ int i;
if (WARN_ON(!mdev))
return;
+ if (!dev)
+ return;
+
if (mlx5_lag_is_shared_fdb(mdev) &&
!mlx5_lag_is_master(mdev)) {
- struct mlx5_core_dev *peer_mdev;
-
- if (rep->vport == MLX5_VPORT_UPLINK)
+ if (rep->vport == MLX5_VPORT_UPLINK && !mlx5_lag_is_mpesw(mdev))
return;
- peer_mdev = mlx5_lag_get_peer_mdev(mdev);
- vport_index += mlx5_eswitch_get_total_vports(peer_mdev);
+ for (i = 0; i < dev->num_ports; i++) {
+ if (dev->port[i].rep == rep)
+ break;
+ }
+ if (WARN_ON(i == dev->num_ports))
+ return;
+ vport_index = i;
}
- if (!dev)
- return;
-
port = &dev->port[vport_index];
write_lock(&port->roce.netdev_lock);
port->roce.netdev = NULL;
@@ -143,13 +167,18 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
port->rep = NULL;
if (rep->vport == MLX5_VPORT_UPLINK) {
- struct mlx5_core_dev *peer_mdev;
- struct mlx5_eswitch *esw;
+
+ if (mlx5_lag_is_shared_fdb(mdev) && !mlx5_lag_is_master(mdev))
+ return;
if (mlx5_lag_is_shared_fdb(mdev)) {
- peer_mdev = mlx5_lag_get_peer_mdev(mdev);
- esw = peer_mdev->priv.eswitch;
- mlx5_eswitch_unregister_vport_reps(esw, REP_IB);
+ struct mlx5_core_dev *peer_mdev;
+ struct mlx5_eswitch *esw;
+
+ mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) {
+ esw = peer_mdev->priv.eswitch;
+ mlx5_eswitch_unregister_vport_reps(esw, REP_IB);
+ }
}
__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
}
@@ -163,14 +192,14 @@ static const struct mlx5_eswitch_rep_ops rep_ops = {
static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev)
{
- struct mlx5_core_dev *peer_mdev = mlx5_lag_get_peer_mdev(mdev);
+ struct mlx5_core_dev *peer_mdev;
struct mlx5_eswitch *esw;
+ int i;
- if (!peer_mdev)
- return;
-
- esw = peer_mdev->priv.eswitch;
- mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);
+ mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) {
+ esw = peer_mdev->priv.eswitch;
+ mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);
+ }
}
struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index f693bc753b6b..1bb7507325bc 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -111,7 +111,7 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
ret = pin_user_pages(start_page + got * PAGE_SIZE,
num_pages - got,
FOLL_LONGTERM | FOLL_WRITE,
- p + got, NULL);
+ p + got);
if (ret < 0) {
mmap_read_unlock(current->mm);
goto bail_release;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 2a5cac2658ec..84e0f41e7dfa 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -140,7 +140,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
ret = pin_user_pages(cur_base,
min_t(unsigned long, npages,
PAGE_SIZE / sizeof(struct page *)),
- gup_flags, page_list, NULL);
+ gup_flags, page_list);
if (ret < 0)
goto out;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index f4321a172000..903f0b71447e 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -1395,7 +1395,7 @@ static int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
if (cleanup_err)
rxe_err_mr(mr, "cleanup failed, err = %d", cleanup_err);
- kfree_rcu(mr);
+ kfree_rcu_mightsleep(mr);
return 0;
err_out:
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index f51ab2ccf151..e6e25f15567d 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -422,7 +422,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable)
umem->page_chunk[i].plist = plist;
while (nents) {
rv = pin_user_pages(first_page_va, nents, foll_flags,
- plist, NULL);
+ plist);
if (rv < 0)
goto out_sem_up;
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index 4b292e0504f1..7c7a51d36d0c 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -312,7 +312,7 @@ static int siw_tx_ctrl(struct siw_iwarp_tx *c_tx, struct socket *s,
}
/*
- * 0copy TCP transmit interface: Use do_tcp_sendpages.
+ * 0copy TCP transmit interface: Use MSG_SPLICE_PAGES.
*
* Using sendpage to push page by page appears to be less efficient
* than using sendmsg, even if data are copied.
@@ -323,20 +323,26 @@ static int siw_tx_ctrl(struct siw_iwarp_tx *c_tx, struct socket *s,
static int siw_tcp_sendpages(struct socket *s, struct page **page, int offset,
size_t size)
{
+ struct bio_vec bvec;
+ struct msghdr msg = {
+ .msg_flags = (MSG_MORE | MSG_DONTWAIT | MSG_SPLICE_PAGES),
+ };
struct sock *sk = s->sk;
- int i = 0, rv = 0, sent = 0,
- flags = MSG_MORE | MSG_DONTWAIT | MSG_SENDPAGE_NOTLAST;
+ int i = 0, rv = 0, sent = 0;
while (size) {
size_t bytes = min_t(size_t, PAGE_SIZE - offset, size);
if (size + offset <= PAGE_SIZE)
- flags = MSG_MORE | MSG_DONTWAIT;
+ msg.msg_flags &= ~MSG_MORE;
tcp_rate_check_app_limited(sk);
+ bvec_set_page(&bvec, page[i], bytes, offset);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
+
try_page_again:
lock_sock(sk);
- rv = do_tcp_sendpages(sk, page[i], offset, bytes, flags);
+ rv = tcp_sendmsg_locked(sk, &msg, size);
release_sock(sk);
if (rv > 0) {
generated by cgit v1.2.3 (git 2.25.1) at 2024-08-08 03:45:20 +0000