Re: Vfio-on-arm: the device tree does not contain the DMA device

[Alvise Rigo <a.rigo-lrHrjnjw1UfHK3s98zE1ajGjJy/sRE9J@public.gmane.org>]

Yes, that is an old guide based on VFIO v4. We will update it soon.

Regards,
alvise

Il 19/06/2014 12:18, Eric Auger ha scritto:
> On 06/19/2014 12:15 PM, Bharat.Bhushan-KZfg59tc24xl57MIdRCFDg@public.gmane.org wrote:
>>
>>
>>> -----Original Message-----
>>> From: Eric Auger [mailto:eric.auger-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org]
>>> Sent: Thursday, June 19, 2014 3:41 PM
>>> To: Shannon Zhao; Bhushan Bharat-R65777; Alvise Rigo;
>>> a.motakis-lrHrjnjw1UfHK3s98zE1ajGjJy/sRE9J@public.gmane.org; iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org;
>>> kvmarm-FPEHb7Xf0XXUo1n7N8X6UoWGPAHP3yOg@public.gmane.org
>>> Subject: Re: Vfio-on-arm: the device tree does not contain the DMA device
>>>
>>> On 06/19/2014 11:38 AM, Shannon Zhao wrote:
>>>> Hi Bharat,
>>>>
>>>> On 2014/6/19 17:19, Bharat.Bhushan-KZfg59tc24xl57MIdRCFDg@public.gmane.org wrote:
>>>>>
>>>>>
>>>>>> -----Original Message-----
>>>>>> From: kvmarm-bounces-FPEHb7Xf0XXUo1n7N8X6UoWGPAHP3yOg@public.gmane.org [mailto:kvmarm-
>>>>>> bounces-FPEHb7Xf0XXUo1n7N8X6UoWGPAHP3yOg@public.gmane.org] On Behalf Of Shannon Zhao
>>>>>> Sent: Thursday, June 19, 2014 2:45 PM
>>>>>> To: Alvise Rigo; a.motakis-lrHrjnjw1UfHK3s98zE1ajGjJy/sRE9J@public.gmane.org; iommu-cunTk1MwBs/ROKNJybVBZg@public.gmane.org
>>>>>> foundation.org; kvmarm-FPEHb7Xf0XXUo1n7N8X6UoWGPAHP3yOg@public.gmane.org
>>>>>> Subject: Re: Vfio-on-arm: the device tree does not contain the DMA device
>>>>>>
>>>>>> Hi Alvise,
>>>>>>
>>>>>> Thanks for your reply.
>>>>>> I have apply the patch and could see the DMA devices.
>>>>>> But there is no vosys_dmatest int the directory "/sys/kernel/debug/" after
>>>>>> mounting debugfs.
>>>>>> I found that the branch vfio-platform-v4 doesn't contain the module
>>>>>> vosys_dmatest.
>>>>>> Then I port it from the branch pl330_dmatest and run vosys_dmatest
>>> successfully.
>>>>>>
>>>>>> 	echo 1 > /sys/kernel/debug/vosys_dmatest/start
>>>>>>
>>>>>> 	[ 6145.343419] dmaengine: __dma_request_channel: success (dma0chan0)
>>>>>> 	[ 6145.344000] vosys dmatest: callback: transfer completed
>>>>>> 	[ 6145.344147] vosys dmatest: tx completed
>>>>>> 	[ 6145.344589] vosys dmatest: source and destination match.
>>>>>>
>>>>>> Download the qemu and use following command to start a guest:
>>>>>> 	./qemu-system-arm -enable-kvm -M vexpress-a15 -cpu cortex-a15 \
>>>>>>         	-device pl330,vfio_group="/dev/vfio/0",vfio_device="2c0a0000.dma",\
>>>>>>         	vfio_container="/dev/vfio/vfio" \
>>>>>>         	-append "earlyprintk ip=dhcp console=ttyAMA0 rootwait" \
>>>>>>         	-kernel zImage -dtb guest.dtb -initrd filesystem.cpio.gz  -
>>>>>> nographic An error reported:
>>>>>> 	qemu-system-arm: -device
>>>>>> pl330,vfio_group=/dev/vfio/0,vfio_device=2c0a0000.dma,:
>>>>>
>>>>> Why do we need to give "vfio_group=/dev/vfio/0" ?
>>>> I refer to the url
>>> "http://www.virtualopensystems.com/en/solutions/guides/vfio-on-arm/".
>>>>>
>>>>>
>>>>>> 	could not open disk image vfio_container=/dev/vfio:
>>>>>> 	Could not open 'vfio_container=/dev/vfio': No such file or directory
>>>>>
>>>>> Are you unbinding "2c0a0000.dma" from its driver and binding with "vfio-
>>> playform" driver ?
>>>> How to unbind "2c0a0000.dma" from its driver?
>>>> I have tried following cmd to bind "2c0a0000.dma" with "vfio-playform" driver.
>>>> 	echo 2c0a0000.dma > /sys/bus/platform/drivers/vfio-platform/vfio_bind
>>>> But there is no /dev/vfio/0 or /dev/vfio/vfio .
>>>
>>> Hi Shannon,
>>>
>>> you may try following cmd to unbind the native dma driver
>>> echo 2c0a0000.dma | sudo tee -a
>>> /sys/bus/platform/devices/2c0a0000.dma/driver/unbind
>>>
>>> and then the following one to bing the meta-driver to the device
>>> echo 2c0a0000.dma | sudo tee -a
>>> /sys/bus/platform/drivers/vfio-platform/vfio_bind
>>
>> Should not we use "driver-override" mechanism for binding with vfio-platform driver?
>>
>> Thanks
>> -Bharat
> 
> Hi Bharat,
> 
> I guess Shannon is using an older version of the kernel. With
> vfio-platform v4 this is the old unbind/bin mechanism that is in place,
> if I am not wrong.
> 
> Best Regards
> 
> Eric
>>
>>>
>>> Best Regards
>>>
>>> Eric
>>>
>>>>
>>>>>
>>>>> Thanks
>>>>> -Bharat
>>>>>
>>>>>>
>>>>>> Is there something I'm wrong or do I miss some steps?
>>>>>>
>>>>>> Thank you,
>>>>>> Shannon
>>>>>>
>>>>>> On 2014/6/18 21:24, Alvise Rigo wrote:
>>>>>>> Hi Shannon,
>>>>>>>
>>>>>>> Thank you for reporting this issue, the device tree file was indeed
>>> missing.
>>>>>>> To solve the problem, you can apply the following patch to the
>>>>>>> repository you mentioned
>>>>>>> (git://github.com/virtualopensystems/arm-dts.git).
>>>>>>>
>>>>>>> For your information, soon we will update the guide with a newer
>>>>>>> version of VFIO with this issue fixed.
>>>>>>>
>>>>>>> Thank you,
>>>>>>> alvise
>>>>>>>
>>>>>>> ---
>>>>>>>  fast_models/rtsm_ve-cortex_a15x4_a7x4.dts | 100
>>>>>>> +++++++++++++++++++++++++++++-
>>>>>>>  1 file changed, 97 insertions(+), 3 deletions(-)
>>>>>>>
>>>>>>> diff --git a/fast_models/rtsm_ve-cortex_a15x4_a7x4.dts
>>>>>>> b/fast_models/rtsm_ve-cortex_a15x4_a7x4.dts
>>>>>>> index ef1275b..79c6af2 100644
>>>>>>> --- a/fast_models/rtsm_ve-cortex_a15x4_a7x4.dts
>>>>>>> +++ b/fast_models/rtsm_ve-cortex_a15x4_a7x4.dts
>>>>>>> @@ -142,7 +142,7 @@
>>>>>>>  		cpu7: cpu@7 {
>>>>>>>  			device_type = "cpu";
>>>>>>>  			compatible = "arm,cortex-a7";
>>>>>>> -			reg = <0x104>;
>>>>>>> +			reg = <0x103>;
>>>>>>>  			cluster = <&cluster1>;
>>>>>>>  			core = <&core7>;
>>>>>>>  		};
>>>>>>> @@ -159,7 +159,7 @@
>>>>>>>  		#address-cells = <0>;
>>>>>>>  		interrupt-controller;
>>>>>>>  		reg = <0 0x2c001000 0 0x1000>,
>>>>>>> -		      <0 0x2c002000 0 0x2000>,
>>>>>>> +		      <0 0x2c002000 0 0x1000>,
>>>>>>>  		      <0 0x2c004000 0 0x2000>,
>>>>>>>  		      <0 0x2c006000 0 0x2000>;
>>>>>>>  		interrupts = <1 9 0xf04>;
>>>>>>> @@ -183,6 +183,101 @@
>>>>>>>  			     <1 10 0xf08>;
>>>>>>>  	};
>>>>>>>
>>>>>>> +	smmu@2c0b0000 {
>>>>>>> +                compatible = "arm,smmu-v2";
>>>>>>> +                reg = <0x0 0x2c0b0000 0x0 0x10000>;
>>>>>>> +                #global-interrupts = <2>;
>>>>>>> +                interrupts = <0 58 4>,
>>>>>>> +                             <0 59 4>,
>>>>>>> +                             <0 60 4>,
>>>>>>> +                             <0 60 4>,
>>>>>>> +                             <0 60 4>,
>>>>>>> +                             <0 60 4>,
>>>>>>> +                             <0 60 4>,
>>>>>>> +                             <0 60 4>,
>>>>>>> +                             <0 60 4>;
>>>>>>> +                mmu-masters = <&dma0 0x0 0x8>,
>>>>>>> +                              <&dma1 0x1 0x9>,
>>>>>>> +                              <&dma2 0x2 0xa>,
>>>>>>> +                              <&dma3 0x3 0xb>;
>>>>>>> +        };
>>>>>>> +
>>>>>>> +	dma0: dma@2c0a0000 {
>>>>>>> +		compatible = "arm,pl330";
>>>>>>> +		reg = <0 0x2c0a0000 0 0x1000>;
>>>>>>> +		interrupts = <0 64 4>,
>>>>>>> +			     <0 65 4>,
>>>>>>> +			     <0 66 4>,
>>>>>>> +			     <0 67 4>,
>>>>>>> +			     <0 68 4>,
>>>>>>> +			     <0 69 4>,
>>>>>>> +			     <0 70 4>,
>>>>>>> +			     <0 71 4>;
>>>>>>> +		#dma-cells = <1>;
>>>>>>> +		#stream-id-cells = <2>;
>>>>>>> +		clocks = <&oscclk6a>;
>>>>>>> +		clock-names = "apb_pclk";
>>>>>>> +	};
>>>>>>> +
>>>>>>> +	dma1: dma@2c0a1000 {
>>>>>>> +		compatible = "arm,pl330", "arm,primecell";
>>>>>>> +		reg = <0 0x2c0a1000 0 0x1000>;
>>>>>>> +		interrupts = <0 96 4>,
>>>>>>> +			     <0 97 4>,
>>>>>>> +			     <0 98 4>,
>>>>>>> +			     <0 99 4>,
>>>>>>> +			     <0 100 4>,
>>>>>>> +			     <0 101 4>,
>>>>>>> +			     <0 102 4>,
>>>>>>> +			     <0 103 4>;
>>>>>>> +		#dma-cells = <1>;
>>>>>>> +		#stream-id-cells = <2>;
>>>>>>> +		clocks = <&oscclk6a>;
>>>>>>> +		clock-names = "apb_pclk";
>>>>>>> +	};
>>>>>>> +
>>>>>>> +	dma2: dma@2c0a2000 {
>>>>>>> +		compatible = "arm,pl330", "arm,primecell";
>>>>>>> +		reg = <0 0x2c0a2000 0 0x1000>;
>>>>>>> +		interrupts = <0 128 4>,
>>>>>>> +			     <0 129 4>,
>>>>>>> +			     <0 130 4>,
>>>>>>> +			     <0 131 4>,
>>>>>>> +			     <0 132 4>,
>>>>>>> +			     <0 133 4>,
>>>>>>> +			     <0 134 4>,
>>>>>>> +			     <0 135 4>;
>>>>>>> +		#dma-cells = <1>;
>>>>>>> +		#stream-id-cells = <2>;
>>>>>>> +		clocks = <&oscclk6a>;
>>>>>>> +		clock-names = "apb_pclk";
>>>>>>> +	};
>>>>>>> +
>>>>>>> +	dma3: dma@2c0a3000 {
>>>>>>> +		compatible = "arm,pl330", "arm,primecell";
>>>>>>> +		reg = <0 0x2c0a3000 0 0x1000>;
>>>>>>> +		interrupts = <0 160 4>,
>>>>>>> +			     <0 161 4>,
>>>>>>> +			     <0 162 4>,
>>>>>>> +			     <0 163 4>,
>>>>>>> +			     <0 164 4>,
>>>>>>> +			     <0 165 4>,
>>>>>>> +			     <0 166 4>,
>>>>>>> +			     <0 167 4>;
>>>>>>> +		#dma-cells = <1>;
>>>>>>> +		#stream-id-cells = <2>;
>>>>>>> +		clocks = <&oscclk6a>;
>>>>>>> +		clock-names = "apb_pclk";
>>>>>>> +	};
>>>>>>> +
>>>>>>> +	oscclk6a: oscclk6a {
>>>>>>> +		/* Reference 24MHz clock */
>>>>>>> +		compatible = "fixed-clock";
>>>>>>> +		#clock-cells = <0>;
>>>>>>> +		clock-frequency = <24000000>;
>>>>>>> +		clock-output-names = "oscclk6a";
>>>>>>> +	};
>>>>>>> +
>>>>>>>  	smb {
>>>>>>>  		compatible = "simple-bus";
>>>>>>>
>>>>>>> @@ -244,4 +339,3 @@
>>>>>>>  		/include/ "rtsm_ve-motherboard.dtsi"
>>>>>>>  	};
>>>>>>>  };
>>>>>>> -
>>>>>>>
>>>>>>
>>>>>> --
>>>>>> Shannon
>>>>>>
>>>>>> _______________________________________________
>>>>>> kvmarm mailing list
>>>>>> kvmarm-FPEHb7Xf0XXUo1n7N8X6UoWGPAHP3yOg@public.gmane.org
>>>>>> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
>>>>>
>>>>> .
>>>>>
>>>>
>>
>