iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

net/mlx5: Update log_max_qp value to be 17 at most

Browse Source 
commit 7f839965b2 upstream.

Currently, log_max_qp value is dependent on what FW reports as its max capability.
In reality, due to a bug, some FWs report a value greater than 17, even though they
don't support log_max_qp > 17.

This FW issue led the driver to exhaust memory on startup.
Thus, log_max_qp value is set to be no more than 17 regardless
of what FW reports, as it was before the cited commit.

Fixes: f79a609ea6 ("net/mlx5: Update log_max_qp value to FW max capability")
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Avihai Horon <avihaih@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Maher Sanalla
2022-02-16 11:01:04 +02:00
committed by Greg Kroah-Hartman
parent 6e94d28633
commit 2378f94c8d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
drivers/net/ethernet/mellanox/mlx5/core/main.c
View File

@ -516,7 +516,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
/* Check log_max_qp from HCA caps to set in current profile */ /* Check log_max_qp from HCA caps to set in current profile */
if (prof->log_max_qp == LOG_MAX_SUPPORTED_QPS) { if (prof->log_max_qp == LOG_MAX_SUPPORTED_QPS) {
prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); prof->log_max_qp = min_t(u8, 17, MLX5_CAP_GEN_MAX(dev, log_max_qp));
} else if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { } else if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) {
mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n",
prof->log_max_qp, prof->log_max_qp,