From: Saeed Mahameed <saeed@kernel.org>
To: "David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
netdev@vger.kernel.org, Tariq Toukan <tariqt@nvidia.com>,
Leon Romanovsky <leonro@nvidia.com>,
linux-rdma@vger.kernel.org, Shay Drory <shayd@nvidia.com>,
Mark Bloch <mbloch@nvidia.com>
Subject: [net-next 02/15] {net/RDMA}/mlx5: introduce lag_for_each_peer
Date: Tue, 6 Jun 2023 00:12:06 -0700 [thread overview]
Message-ID: <20230606071219.483255-3-saeed@kernel.org> (raw)
In-Reply-To: <20230606071219.483255-1-saeed@kernel.org>
From: Shay Drory <shayd@nvidia.com>
Introduce a generic APIs to iterate over all the devices which are part
of the LAG. This API replace mlx5_lag_get_peer_mdev() which retrieve
only a single peer device from the lag.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/infiniband/hw/mlx5/ib_rep.c | 98 ++++++++++++-------
.../net/ethernet/mellanox/mlx5/core/fs_cmd.c | 24 +++--
.../net/ethernet/mellanox/mlx5/core/lag/lag.c | 21 +++-
include/linux/mlx5/driver.h | 8 +-
4 files changed, 100 insertions(+), 51 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index a4db22fe1883..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 && !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;
@@ -143,16 +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);
}
@@ -166,14 +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/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 11374c3744c5..8a10ed4d8cbb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -244,16 +244,22 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
ft->type == FS_FT_FDB &&
mlx5_lag_is_shared_fdb(dev) &&
mlx5_lag_is_master(dev)) {
- err = mlx5_cmd_set_slave_root_fdb(dev,
- mlx5_lag_get_peer_mdev(dev),
- !disconnect, (!disconnect) ?
- ft->id : 0);
- if (err && !disconnect) {
- MLX5_SET(set_flow_table_root_in, in, op_mod, 0);
- MLX5_SET(set_flow_table_root_in, in, table_id,
- ns->root_ft->id);
- mlx5_cmd_exec_in(dev, set_flow_table_root, in);
+ struct mlx5_core_dev *peer_dev;
+ int i;
+
+ mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) {
+ err = mlx5_cmd_set_slave_root_fdb(dev, peer_dev, !disconnect,
+ (!disconnect) ? ft->id : 0);
+ if (err && !disconnect) {
+ MLX5_SET(set_flow_table_root_in, in, op_mod, 0);
+ MLX5_SET(set_flow_table_root_in, in, table_id,
+ ns->root_ft->id);
+ mlx5_cmd_exec_in(dev, set_flow_table_root, in);
+ }
+ if (err)
+ break;
}
+
}
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index c820f7d266de..c55e36e0571d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1519,26 +1519,37 @@ u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev)
}
EXPORT_SYMBOL(mlx5_lag_get_num_ports);
-struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
+struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int *i)
{
struct mlx5_core_dev *peer_dev = NULL;
struct mlx5_lag *ldev;
unsigned long flags;
+ int idx;
spin_lock_irqsave(&lag_lock, flags);
ldev = mlx5_lag_dev(dev);
if (!ldev)
goto unlock;
- peer_dev = ldev->pf[MLX5_LAG_P1].dev == dev ?
- ldev->pf[MLX5_LAG_P2].dev :
- ldev->pf[MLX5_LAG_P1].dev;
+ if (*i == ldev->ports)
+ goto unlock;
+ for (idx = *i; idx < ldev->ports; idx++)
+ if (ldev->pf[idx].dev != dev)
+ break;
+
+ if (idx == ldev->ports) {
+ *i = idx;
+ goto unlock;
+ }
+ *i = idx + 1;
+
+ peer_dev = ldev->pf[idx].dev;
unlock:
spin_unlock_irqrestore(&lag_lock, flags);
return peer_dev;
}
-EXPORT_SYMBOL(mlx5_lag_get_peer_mdev);
+EXPORT_SYMBOL(mlx5_lag_get_next_peer_mdev);
int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
u64 *values,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 94d2be5848ae..9a744c48eec2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1174,7 +1174,13 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
u64 *values,
int num_counters,
size_t *offsets);
-struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev);
+struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int *i);
+
+#define mlx5_lag_for_each_peer_mdev(dev, peer, i) \
+ for (i = 0, peer = mlx5_lag_get_next_peer_mdev(dev, &i); \
+ peer; \
+ peer = mlx5_lag_get_next_peer_mdev(dev, &i))
+
u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev);
struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
--
2.40.1
next prev parent reply other threads:[~2023-06-06 7:12 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-06 7:12 [pull request][net-next 00/15] mlx5 updates 2023-06-06 Saeed Mahameed
2023-06-06 7:12 ` [net-next 01/15] RDMA/mlx5: Free second uplink ib port Saeed Mahameed
2023-06-06 7:12 ` Saeed Mahameed [this message]
2023-06-06 7:12 ` [net-next 03/15] net/mlx5: LAG, check if all eswitches are paired for shared FDB Saeed Mahameed
2023-06-06 7:12 ` [net-next 04/15] net/mlx5: LAG, generalize handling of " Saeed Mahameed
2023-06-06 7:12 ` [net-next 05/15] net/mlx5: LAG, change mlx5_shared_fdb_supported() to static Saeed Mahameed
2023-06-06 7:12 ` [net-next 06/15] net/mlx5: LAG, block multipath LAG in case ldev have more than 2 ports Saeed Mahameed
2023-06-06 7:12 ` [net-next 07/15] net/mlx5: LAG, block multiport eswitch " Saeed Mahameed
2023-06-06 7:12 ` [net-next 08/15] net/mlx5: Enable 4 ports VF LAG Saeed Mahameed
2023-06-06 7:12 ` [net-next 09/15] net/mlx5e: RX, Log error when page_pool size is too large Saeed Mahameed
2023-06-07 16:24 ` Alexander Lobakin
2023-06-07 16:40 ` Dragos Tatulea
2023-06-06 7:12 ` [net-next 10/15] net/mlx5e: Expose catastrophic steering error counters Saeed Mahameed
2023-06-06 7:12 ` [net-next 11/15] net/mlx5e: Remove RX page cache leftovers Saeed Mahameed
2023-06-06 7:12 ` [net-next 12/15] net/mlx5e: TC, refactor access to hash key Saeed Mahameed
2023-06-06 7:12 ` [net-next 13/15] net/mlx5: Skip inline mode check after mlx5_eswitch_enable_locked() failure Saeed Mahameed
2023-06-07 5:01 ` Jakub Kicinski
2023-06-07 14:10 ` Jason Gunthorpe
2023-06-07 16:19 ` Jakub Kicinski
2023-06-07 23:18 ` Jason Gunthorpe
2023-06-07 15:46 ` Jiri Pirko
2023-06-07 16:22 ` Jakub Kicinski
2023-06-06 7:12 ` [net-next 14/15] mlx5/core: E-Switch, Allocate ECPF vport if it's an eswitch manager Saeed Mahameed
2023-06-06 7:12 ` [net-next 15/15] net/mlx5e: simplify condition after napi budget handling change Saeed Mahameed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230606071219.483255-3-saeed@kernel.org \
--to=saeed@kernel.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kuba@kernel.org \
--cc=leonro@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=mbloch@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=saeedm@nvidia.com \
--cc=shayd@nvidia.com \
--cc=tariqt@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).