Commit 33afbfcc authored by Moshe Shemesh's avatar Moshe Shemesh Committed by David S. Miller

net/mlx5: Stop waiting for PCI if pci channel is offline

In case pci channel becomes offline the driver should not wait for PCI
reads during health dump and recovery flow. The driver has timeout for
each of these loops trying to read PCI, so it would fail anyway.
However, in case of recovery waiting till timeout may cause the pci
error_detected() callback fail to meet pci_dpc_recovered() wait timeout.

Fixes: b3bd076f ("net/mlx5: Report devlink health on FW fatal issues")
Signed-off-by: default avatarMoshe Shemesh <moshe@nvidia.com>
Reviewed-by: default avatarShay Drori <shayd@nvidia.com>
Signed-off-by: default avatarTariq Toukan <tariqt@nvidia.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent c57e5581
...@@ -373,6 +373,10 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) ...@@ -373,6 +373,10 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev)
do { do {
if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
break; break;
if (pci_channel_offline(dev->pdev)) {
mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n");
return -EACCES;
}
cond_resched(); cond_resched();
} while (!time_after(jiffies, end)); } while (!time_after(jiffies, end));
......
...@@ -248,6 +248,10 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev) ...@@ -248,6 +248,10 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
do { do {
if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
break; break;
if (pci_channel_offline(dev->pdev)) {
mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n");
goto unlock;
}
msleep(20); msleep(20);
} while (!time_after(jiffies, end)); } while (!time_after(jiffies, end));
...@@ -317,6 +321,10 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev) ...@@ -317,6 +321,10 @@ int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev)
mlx5_core_warn(dev, "device is being removed, stop waiting for PCI\n"); mlx5_core_warn(dev, "device is being removed, stop waiting for PCI\n");
return -ENODEV; return -ENODEV;
} }
if (pci_channel_offline(dev->pdev)) {
mlx5_core_err(dev, "PCI channel offline, stop waiting for PCI\n");
return -EACCES;
}
msleep(100); msleep(100);
} }
return 0; return 0;
......
...@@ -74,6 +74,10 @@ int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev) ...@@ -74,6 +74,10 @@ int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev)
ret = -EBUSY; ret = -EBUSY;
goto pci_unlock; goto pci_unlock;
} }
if (pci_channel_offline(dev->pdev)) {
ret = -EACCES;
goto pci_unlock;
}
/* Check if semaphore is already locked */ /* Check if semaphore is already locked */
ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val); ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment