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: b3bd076f7501 ("net/mlx5: Report devlink health on FW fatal issues")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 2d95a9b..b61b7d9 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -373,6 +373,10 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev)
        do {
                if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
                        break;
+               if (pci_channel_offline(dev->pdev)) {
+                       mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n");
+                       return -EACCES;
+               }
 
                cond_resched();
        } while (!time_after(jiffies, end));

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index ad38e31..a6329ca 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -248,6 +248,10 @@ recover_from_sw_reset:
        do {
                if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
                        break;
+               if (pci_channel_offline(dev->pdev)) {
+                       mlx5_core_err(dev, "PCI channel offline, stop waiting for NIC IFC\n");
+                       goto unlock;
+               }
 
                msleep(20);
        } while (!time_after(jiffies, end));
@@ -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");
                        return -ENODEV;
                }
+               if (pci_channel_offline(dev->pdev)) {
+                       mlx5_core_err(dev, "PCI channel offline, stop waiting for PCI\n");
+                       return -EACCES;
+               }
                msleep(100);
        }
        return 0;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
index 6b774e0..d0b595b 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/pci_vsc.c
@@ -74,6 +74,10 @@ int mlx5_vsc_gw_lock(struct mlx5_core_dev *dev)
                        ret = -EBUSY;
                        goto pci_unlock;
                }
+               if (pci_channel_offline(dev->pdev)) {
+                       ret = -EACCES;
+                       goto pci_unlock;
+               }
 
                /* Check if semaphore is already locked */
                ret = vsc_read(dev, VSC_SEMAPHORE_OFFSET, &lock_val);