after an error on the PCI link, the driver does not need to wait
for the link to become functional again as a reset is required. Stop
the wait loop in this case to accelerate the recovery flow.
Co-developed-by: Alexander Schmidt <alexs@xxxxxxxxxxxxx>
Signed-off-by: Alexander Schmidt <alexs@xxxxxxxxxxxxx>
Signed-off-by: Niklas Schnelle <schnelle@xxxxxxxxxxxxx>
---
drivers/net/ethernet/mellanox/mlx5/core/health.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index f9438d4e43ca..81ca44e0705a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -325,6 +325,8 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)
while (sensor_pci_not_working(dev)) {
if (time_after(jiffies, end))
return -ETIMEDOUT;
+ if (pci_channel_offline(dev->pdev))
+ return -EIO;
msleep(100);
}
return 0;
@@ -332,10 +334,16 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)
static int mlx5_health_try_recover(struct mlx5_core_dev *dev)
{
+ int rc;
+
mlx5_core_warn(dev, "handling bad device here\n");
mlx5_handle_bad_state(dev);
- if (mlx5_health_wait_pci_up(dev)) {
- mlx5_core_err(dev, "health recovery flow aborted, PCI reads still not working\n");
+ rc = mlx5_health_wait_pci_up(dev);
+ if (rc) {
+ if (rc == -ETIMEDOUT)
+ mlx5_core_err(dev, "health recovery flow aborted, PCI reads still not working\n");
+ else
+ mlx5_core_err(dev, "health recovery flow aborted, PCI channel offline\n");
return -EIO;
}
mlx5_core_err(dev, "starting health recovery flow\n");
base-commit: 7e364e56293bb98cae1b55fd835f5991c4e96e7d
--
2.37.2
