[lkml]   [2018]   [Sep]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 00/21] SMMU enablement for NXP LS1043A and LS1046A

On 20.09.2018 14:49, Robin Murphy wrote:
> On 20/09/18 11:38, Laurentiu Tudor wrote:
>> On 19.09.2018 17:37, Robin Murphy wrote:
>>> On 19/09/18 15:18, Laurentiu Tudor wrote:
>>>> Hi Robin,
>>>> On 19.09.2018 16:25, Robin Murphy wrote:
>>>>> Hi Laurentiu,
>>>>> On 19/09/18 13:35, wrote:
>>>>>> From: Laurentiu Tudor <>
>>>>>> This patch series adds SMMU support for NXP LS1043A and LS1046A chips
>>>>>> and consists mostly in important driver fixes and the required device
>>>>>> tree updates. It touches several subsystems and consists of three
>>>>>> main
>>>>>> parts:
>>>>>>     - changes in soc/drivers/fsl/qbman drivers adding iommu
>>>>>> mapping of
>>>>>>       reserved memory areas, fixes and defered probe support
>>>>>>     - changes in drivers/net/ethernet/freescale/dpaa_eth drivers
>>>>>>       consisting in misc dma mapping related fixes and probe ordering
>>>>>>     - addition of the actual arm smmu device tree node together with
>>>>>>       various adjustments to the device trees
>>>>>> Performance impact
>>>>>>        Running iperf benchmarks in a back-to-back setup (both sides
>>>>>>        having smmu enabled) on a 10GBps port show an important
>>>>>>        networking performance degradation of around %40 (9.48Gbps
>>>>>>        linerate vs 5.45Gbps). If you need performance but without
>>>>>>        SMMU support you can use "iommu.passthrough=1" to disable
>>>>>>        SMMU.
> I should have said before - thanks for the numbers there as well. Always
> good to add another datapoint to my collection. If you're interested
> I've added SMMUv2 support to the "non-strict mode" series (of which I
> should be posting v8 soon), so it might be fun to see how well that
> works on MMU-500 in the real world.

Hmm, I think I gave those a try some weeks ago and vaguely remember that
I did see improvements. Can't remember the numbers off the top of my
head but I'll re-test with the latest spin and update the numbers.

>>>>>> USB issue and workaround
>>>>>>        There's a problem with the usb controllers in these chips
>>>>>>        generating smaller, 40-bit wide dma addresses instead of the
>>>>>> 48-bit
>>>>>>        supported at the smmu input. So you end up in a situation
>>>>>> where the
>>>>>>        smmu is mapped with 48-bit address translations, but the
>>>>>> device
>>>>>>        generates transactions with clipped 40-bit addresses, thus
>>>>>> smmu
>>>>>>        context faults are triggered. I encountered a similar
>>>>>> situation for
>>>>>>        mmc that I  managed to fix in software [1] however for USB I
>>>>>> did not
>>>>>>        find a proper place in the code to add a similar fix. The only
>>>>>>        workaround I found was to add this kernel parameter which
>>>>>> limits the
>>>>>>        usb dma to 32-bit size: "xhci-hcd.quirks=0x800000".
>>>>>>        This workaround if far from ideal, so any suggestions for a
>>>>>> code
>>>>>>        based workaround in this area would be greatly appreciated.
>>>>> If you have a nominally-64-bit device with a
>>>>> narrower-than-the-main-interconnect link in front of it, that should
>>>>> already be fixed in 4.19-rc by bus_dma_mask picking up DT dma-ranges,
>>>>> provided the interconnect hierarchy can be described appropriately (or
>>>>> at least massaged sufficiently to satisfy the binding), e.g.:
>>>>> / {
>>>>>        ...
>>>>>        soc {
>>>>>            ranges;
>>>>>            dma-ranges = <0 0 10000 0>;
>>>>>            dev_48bit { ... };
>>>>>            periph_bus {
>>>>>                ranges;
>>>>>                dma-ranges = <0 0 100 0>;
>>>>>                dev_40bit { ... };
>>>>>            };
>>>>>        };
>>>>> };
>>>>> and if that fails to work as expected (except for PCI hosts where
>>>>> handling dma-ranges properly still needs sorting out), please do
>>>>> let us
>>>>> know ;)
>>>> Just to confirm, Is this [1] the change I was supposed to test?
>>> Not quite - dma-ranges is only valid for nodes representing a bus, so
>>> putting it directly in the USB device nodes doesn't work (FWIW that's
>>> why PCI is broken, because the parser doesn't expect the
>>> bus-as-leaf-node case). That's teh point of that intermediate simple-bus
>>> node represented by "periph_bus" in my example (sorry, I should have put
>>> compatibles in to make it clearer) - often that's actually true to life
>>> (i.e. "soc" is something like a CCI and "periph_bus" is something like
>>> an AXI NIC gluing a bunch of lower-bandwidth DMA masters to one of the
>>> CCI ports) but at worst it's just a necessary evil to make the binding
>>> happy (if it literally only represents the point-to-point link between
>>> the device master port and interconnect slave port).
>> Quick update: so I adjusted to device tree according to your example and
>> it works so now I can get rid of that nasty kernel arg based workaround,
>> yey! :-)
> Cool! In fact, judging by the block diagrams on the website, the "basic
> peripherals and interconnect" section hanging off the side of the CCI
> implies that probably is true to the real topology as I imagined, so it
> doesn't even count as a horrible hack :)

Indeed, on this chip there's a NoC lumping behind it several low-speed
devices such as usb, sata, esdhc.

>> Thanks a lot, that was really helpful.
> No problem. FWIW if you ever come to doing ACPI support for these SoCs,
> the equivalent is merely a case of setting the device memory address
> size limit field appropriately for all the named components.

Thanks, I'll keep this in mind. If i remember correctly, there are
people over here working on UEFI + ACPI support for some LS chips but
progress appears to be slow.

Best Regards, Laurentiu
 \ /
  Last update: 2018-09-20 16:34    [W:0.077 / U:4.928 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site