Re: [PATCH v4] misc: alcor_pci: fix null-ptr-deref when there is no PCI bridge

From: Greg Kroah-Hartman
Date: Fri May 21 2021 - 08:44:18 EST


On Tue, May 18, 2021 at 03:28:18PM -0400, Tong Zhang wrote:
> There is an issue with the ASPM(optional) capability checking function.
> A device might be attached to root complex directly, in this case,
> bus->self(bridge) will be NULL, thus priv->parent_pdev is NULL.
> Since alcor_pci_init_check_aspm(priv->parent_pdev) checks the PCI link's
> ASPM capability and populate parent_cap_off, which will be used later by
> alcor_pci_aspm_ctrl() to dynamically turn on/off device, what we can do
> here is to avoid checking the capability if we are on the root complex.
> This will make pdev_cap_off 0 and alcor_pci_aspm_ctrl() will simply
> return when bring called, effectively disable ASPM for the device.
>
> [ 1.246492] BUG: kernel NULL pointer dereference, address: 00000000000000c0
> [ 1.248731] RIP: 0010:pci_read_config_byte+0x5/0x40
> [ 1.253998] Call Trace:
> [ 1.254131] ? alcor_pci_find_cap_offset.isra.0+0x3a/0x100 [alcor_pci]
> [ 1.254476] alcor_pci_probe+0x169/0x2d5 [alcor_pci]
>
> Signed-off-by: Tong Zhang <ztong0001@xxxxxxxxx>
> Co-developed-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
> Co-developed-by: Colin Ian King <colin.king@xxxxxxxxxxxxx>
> ---
> v2: check before calling alcor_pci_find_cap_offset()
> v3: Add comment. Enable the dev_dbg() output when priv->parent_pdev is NULL.
> v4: fix inverted if statement, thanks to Colin <colin.king@xxxxxxxxxxxxx>

Please just send a fix-up patch instead, I don't want to revert and then
add this, that doesn't make any sense...

thanks,

greg k-h