On 19.08.2021 08:50, Kai-Heng Feng wrote:
> On Thu, Aug 19, 2021 at 2:08 PM Heiner Kallweit <hkallweit1@xxxxxxxxx> wrote:
>>
>> On 19.08.2021 07:45, Kai-Heng Feng wrote:
>>> The latest vendor driver enables ASPM for more recent r8168 NICs, so
>>> disable ASPM on older chips and enable ASPM for the rest.
>>>
>>> Rename aspm_manageable to pcie_aspm_manageable to indicate it's ASPM
>>> from PCIe, and use rtl_aspm_supported for Realtek NIC's internal ASPM
>>> function.
>>>
>>> Signed-off-by: Kai-Heng Feng <kai.heng.feng@xxxxxxxxxxxxx>
>>> ---
>>> v3:
>>> - Use pcie_aspm_supported() to retrieve ASPM support status
>>> - Use whitelist for r8169 internal ASPM status
>>>
>>> v2:
>>> - No change
>>>
>>> drivers/net/ethernet/realtek/r8169_main.c | 27 ++++++++++++++++-------
>>> 1 file changed, 19 insertions(+), 8 deletions(-)
>>>
>>> diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
>>> index 3359509c1c351..88e015d93e490 100644
>>> --- a/drivers/net/ethernet/realtek/r8169_main.c
>>> +++ b/drivers/net/ethernet/realtek/r8169_main.c
>>> @@ -623,7 +623,8 @@ struct rtl8169_private {
>>> } wk;
>>>
>>> unsigned supports_gmii:1;
>>> - unsigned aspm_manageable:1;
>>> + unsigned pcie_aspm_manageable:1;
>>> + unsigned rtl_aspm_supported:1;
>>> unsigned rtl_aspm_enabled:1;
>>> struct delayed_work aspm_toggle;
>>> atomic_t aspm_packet_count;
>>> @@ -702,6 +703,20 @@ static bool rtl_is_8168evl_up(struct rtl8169_private *tp)
>>> tp->mac_version <= RTL_GIGA_MAC_VER_53;
>>> }
>>>
>>> +static int rtl_supports_aspm(struct rtl8169_private *tp)
>>> +{
>>> + switch (tp->mac_version) {
>>> + case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_31:
>>> + case RTL_GIGA_MAC_VER_37:
>>> + case RTL_GIGA_MAC_VER_39:
>>> + case RTL_GIGA_MAC_VER_43:
>>> + case RTL_GIGA_MAC_VER_47:
>>> + return 0;
>>> + default:
>>> + return 1;
>>> + }
>>> +}
>>> +
>>> static bool rtl_supports_eee(struct rtl8169_private *tp)
>>> {
>>> return tp->mac_version >= RTL_GIGA_MAC_VER_34 &&
>>> @@ -2669,7 +2684,7 @@ static void rtl_pcie_state_l2l3_disable(struct rtl8169_private *tp)
>>>
>>> static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
>>> {
>>> - if (!tp->aspm_manageable && enable)
>>> + if (!(tp->pcie_aspm_manageable && tp->rtl_aspm_supported) && enable)
>>> return;
>>>
>>> tp->rtl_aspm_enabled = enable;
>>> @@ -5319,12 +5334,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
>>> if (rc)
>>> return rc;
>>>
>>> - /* Disable ASPM completely as that cause random device stop working
>>> - * problems as well as full system hangs for some PCIe devices users.
>>> - */
>>> - rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
>>> - PCIE_LINK_STATE_L1);
>>> - tp->aspm_manageable = !rc;
>>> + tp->pcie_aspm_manageable = pcie_aspm_supported(pdev);
>>
>> That's not what I meant, and it's also not correct.
>
> In case I make another mistake in next series, let me ask it more clearly...
> What you meant was to check both link->aspm_enabled and link->aspm_support?
>
aspm_enabled can be changed by the user at any time.
pci_disable_link_state() also considers whether BIOS forbids that OS
mess with ASPM. See aspm_disabled.
>>
>>> + tp->rtl_aspm_supported = rtl_supports_aspm(tp);
>
> Is rtl_supports_aspm() what you expect for the whitelist?
> And what else am I missing?
>
I meant use rtl_supports_aspm() to check when ASPM is relevant at all,
and in addition use a blacklist for chip versions where ASPM is
completely unusable.
> Kai-Heng
>
>>>
>>> /* enable device (incl. PCI PM wakeup and hotplug setup) */
>>> rc = pcim_enable_device(pdev);
>>>
>>
