On Fri, 2020-07-24 at 16:15 -0700, Jakub Kicinski wrote:
> It appears that not disabling a PCI device on .shutdown may lead to
> a Hardware Error with particular (perhaps buggy) BIOS versions:
>
> mlx4_en: eth0: Close port called
> mlx4_en 0000:04:00.0: removed PHC
> reboot: Restarting system
> {1}[Hardware Error]: Hardware error from APEI Generic Hardware
> Error Source: 1
> {1}[Hardware Error]: event severity: fatal
> {1}[Hardware Error]: Error 0, type: fatal
> {1}[Hardware Error]: section_type: PCIe error
> {1}[Hardware Error]: port_type: 4, root port
> {1}[Hardware Error]: version: 1.16
> {1}[Hardware Error]: command: 0x4010, status: 0x0143
> {1}[Hardware Error]: device_id: 0000:00:02.2
> {1}[Hardware Error]: slot: 0
> {1}[Hardware Error]: secondary_bus: 0x04
> {1}[Hardware Error]: vendor_id: 0x8086, device_id: 0x2f06
> {1}[Hardware Error]: class_code: 000604
> {1}[Hardware Error]: bridge: secondary_status: 0x2000, control:
> 0x0003
> {1}[Hardware Error]: aer_uncor_status: 0x00100000,
> aer_uncor_mask: 0x00000000
> {1}[Hardware Error]: aer_uncor_severity: 0x00062030
> {1}[Hardware Error]: TLP Header: 40000018 040000ff 791f4080
> 00000000
> [hw error repeats]
> Kernel panic - not syncing: Fatal hardware error!
> CPU: 0 PID: 2189 Comm: reboot Kdump: loaded Not tainted 5.6.x-
> blabla #1
> Hardware name: HP ProLiant DL380 Gen9/ProLiant DL380 Gen9, BIOS
> P89 05/05/2017
>
> Fix the mlx4 driver.
>
> This is a very similar problem to what had been fixed in:
> commit 0d98ba8d70b0 ("scsi: hpsa: disable device during shutdown")
> to address https://bugzilla.kernel.org/show_bug.cgi?id=199779.
>
> Fixes: 2ba5fbd62b25 ("net/mlx4_core: Handle AER flow properly")
> Reported-by: Jake Lawrence <[email protected]>
> Signed-off-by: Jakub Kicinski <[email protected]>
Reviewed-by: Saeed Mahameed <[email protected]>
> ---
> drivers/net/ethernet/mellanox/mlx4/main.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c
> b/drivers/net/ethernet/mellanox/mlx4/main.c
> index 3d9aa7da95e9..2d3e45780719 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/main.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/main.c
> @@ -4356,12 +4356,14 @@ static void mlx4_pci_resume(struct pci_dev
> *pdev)
> static void mlx4_shutdown(struct pci_dev *pdev)
> {
> struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
> + struct mlx4_dev *dev = persist->dev;
>
> mlx4_info(persist->dev, "mlx4_shutdown was called\n");
> mutex_lock(&persist->interface_state_mutex);
> if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
> mlx4_unload_one(pdev);
> mutex_unlock(&persist->interface_state_mutex);
> + mlx4_pci_disable_device(dev);
> }
>
> static const struct pci_error_handlers mlx4_err_handler = {
