Re: [PATCH] PCI: Add cavium acs pci quirk
From: David Daney
Date: Mon Feb 27 2017 - 15:40:11 EST
On 02/27/2017 11:13 AM, Chalamarla, Tirumalesh wrote:
On 2/27/17, 11:02 AM, "David Daney" <ddaney.cavm@xxxxxxxxx> wrote:
On 02/14/2017 07:07 AM, Bjorn Helgaas wrote:
> On Mon, Feb 13, 2017 at 09:44:57PM -0700, Alex Williamson wrote:
>> On Sat, 30 Jan 2016 01:33:58 +0530
>> Manish Jaggi <mjaggi@xxxxxxxxxxxxxxxxxx> wrote:
>>
>>> Cavium devices matching this quirk do not perform
>>> peer-to-peer with other functions, allowing masking out
>>> these bits as if they were unimplemented in the ACS capability.
>>>
>>> Acked-by: Tirumalesh Chalamarla <tchalamarla@xxxxxxxxxx>
>>> Signed-off-by: Manish Jaggi <mjaggi@xxxxxxxxxxxxxxxxxx>
>>> ---
>>> drivers/pci/quirks.c | 15 +++++++++++++++
>>> 1 file changed, 15 insertions(+)
>>>
>>> diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
>>> index 7e32730..a300fa6 100644
>>> --- a/drivers/pci/quirks.c
>>> +++ b/drivers/pci/quirks.c
>>> @@ -3814,6 +3814,19 @@ static int pci_quirk_amd_sb_acs(struct pci_dev *dev, u16 acs_flags)
>>> #endif
>>> }
>>>
>>> +static int pci_quirk_cavium_acs(struct pci_dev *dev, u16 acs_flags)
>>> +{
Perhaps add a check here for dev->device and/or dev->subsystem_device to
see if we need the workaround. There may be many that match, so ...
>>> + /*
>>> + * Cavium devices matching this quirk do not perform
>>> + * peer-to-peer with other functions, allowing masking out
>>> + * these bits as if they were unimplemented in the ACS capability.
>>> + */
>>> + acs_flags &= ~(PCI_ACS_SV | PCI_ACS_TB | PCI_ACS_RR |
>>> + PCI_ACS_CR | PCI_ACS_UF | PCI_ACS_DT);
>>> +
>>> + return acs_flags ? 0 : 1;
>>> +}
>>> +
>>> /*
>>> * Many Intel PCH root ports do provide ACS-like features to disable peer
>>> * transactions and validate bus numbers in requests, but do not provide an
>>> @@ -3966,6 +3979,8 @@ static const struct pci_dev_acs_enabled {
>>> { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_intel_pch_acs },
>>> { 0x19a2, 0x710, pci_quirk_mf_endpoint_acs }, /* Emulex BE3-R */
>>> { 0x10df, 0x720, pci_quirk_mf_endpoint_acs }, /* Emulex Skyhawk-R */
>>> + /* Cavium ThunderX */
>>> + { PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs },
.. Leaving PCI_ANY_ID here may keep the table more manageable.
>>> { 0 }
>>> };
>>>
>>
>> Apologies for not catching this, but what sort of crystal ball do you
>> have that can predict not only current devices, but future devices will
>> not support peer-to-peer features? Is there an internal design
>> guidelines reference specification for Cavium that we can realistically
>> expect this to remain consistent, or is this just an attempt to never
>> think about ACS again at the customer's peril? What about the existing
>> non-ThunderX products with Cavium vendor ID, does this really apply to
>> those? I would strongly suggest taking the device ID into account.
>> See examples like the pci_quirk_intel_pch_acs quirk where the initial
>> filter is PCI_ANY_ID, but specific device types and ranges of device
>> IDs are identified by the function for evaluation. This seems reckless
>> to me and I'd advise that it be reverted. Thanks,
>
> I'd be happy to revert this, but it would be easier if somebody sent a
> patch and a changelog.
>
I agree that it should be reverted.
I was hoping that Manish or Tirumalesh would fix this properly by only
activating the quirk on the faulty hardware, but such a fix has never
appeared.
This was supposed to be true for all Cavium chips. We got such answer from Hardware architects, but it might change in the future.
I will be happy to replace this with DEVICE_ID.
Manish,
Could you please take this u, if not I will send a patch to do this.
I think several device ids or subsystem_device may be involved.
See above.
Tirumalesh.
David Daney