[ Upstream commit
33afbfcc105a572159750f2ebee834a8a70fdd96 ]
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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
do {
if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_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));
do {
if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_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));
"health recovery flow aborted, PCI reads still not working\n");
return -EIO;
}
+ if (pci_channel_offline(dev->pdev)) {
+ mlx5_core_err(dev, "PCI channel offline, stop waiting for PCI\n");
+ return -EACCES;
+ }
msleep(100);
}
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);