@@ -2680,11 +2680,11 @@ void mlx5e_trigger_napi_sched(struct napi_struct *napi)
static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
struct mlx5e_params *params,
- struct mlx5e_channel_param *cparam,
struct xsk_buff_pool *xsk_pool,
struct mlx5e_channel **cp)
{
struct net_device *netdev = priv->netdev;
+ struct mlx5e_channel_param *cparam;
struct mlx5_core_dev *mdev;
struct mlx5e_xsk_param xsk;
struct mlx5e_channel *c;
@@ -2706,8 +2706,15 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
return err;
c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
- if (!c)
- return -ENOMEM;
+ cparam = kvzalloc(sizeof(*cparam), GFP_KERNEL);
+ if (!c || !cparam) {
+ err = -ENOMEM;
+ goto err_free;
+ }
+
+ err = mlx5e_build_channel_param(mdev, params, cparam);
+ if (err)
+ goto err_free;
c->priv = priv;
c->mdev = mdev;
@@ -2741,6 +2748,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
*cp = c;
+ kvfree(cparam);
return 0;
err_close_queues:
@@ -2749,6 +2757,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
err_napi_del:
netif_napi_del(&c->napi);
+err_free:
+ kvfree(cparam);
kvfree(c);
return err;
@@ -2807,20 +2817,14 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
int mlx5e_open_channels(struct mlx5e_priv *priv,
struct mlx5e_channels *chs)
{
- struct mlx5e_channel_param *cparam;
int err = -ENOMEM;
int i;
chs->num = chs->params.num_channels;
chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
- cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
- if (!chs->c || !cparam)
- goto err_free;
-
- err = mlx5e_build_channel_param(priv->mdev, &chs->params, cparam);
- if (err)
- goto err_free;
+ if (!chs->c)
+ goto err_out;
for (i = 0; i < chs->num; i++) {
struct xsk_buff_pool *xsk_pool = NULL;
@@ -2828,7 +2832,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
if (chs->params.xdp_prog)
xsk_pool = mlx5e_xsk_get_pool(&chs->params, chs->params.xsk, i);
- err = mlx5e_open_channel(priv, i, &chs->params, cparam, xsk_pool, &chs->c[i]);
+ err = mlx5e_open_channel(priv, i, &chs->params, xsk_pool, &chs->c[i]);
if (err)
goto err_close_channels;
}
@@ -2846,7 +2850,6 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
}
mlx5e_health_channels_update(priv);
- kvfree(cparam);
return 0;
err_close_ptp:
@@ -2857,9 +2860,8 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
for (i--; i >= 0; i--)
mlx5e_close_channel(chs->c[i]);
-err_free:
kfree(chs->c);
- kvfree(cparam);
+err_out:
chs->num = 0;
return err;
}
In a multi-PF netdev, each traffic channel creates its own resources against a specific PF. In the cited commit, where this support was added, the channel_param logic was mistakenly kept unchanged, so it always used the primary PF which is found at priv->mdev. In this patch we fix this by moving the logic to be per-channel, and passing the correct mdev instance. This bug happened to be usually harmless, as the resulting cparam structures would be the same for all channels, due to identical FW logic and decisions. However, in some use cases, like fwreset, this gets broken. This could lead to different symptoms. Example: Error cqe on cqn 0x428, ci 0x0, qn 0x10a9, opcode 0xe, syndrome 0x4, vendor syndrome 0x32 Fixes: e4f9686bdee7 ("net/mlx5e: Let channels be SD-aware") Signed-off-by: Tariq Toukan <tariqt@nvidia.com> Reviewed-by: Lama Kayal <lkayal@nvidia.com> Reviewed-by: Gal Pressman <gal@nvidia.com> --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 32 ++++++++++--------- 1 file changed, 17 insertions(+), 15 deletions(-)