* Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
@ 2018-12-20 14:06 Bas Vermeulen
[not found] ` <CAGtoiRiubNF5fCwGvYbC_sxzFk10Ceg79ZsK2fPLXUzFvm_QZw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
0 siblings, 1 reply; 8+ messages in thread
From: Bas Vermeulen @ 2018-12-20 14:06 UTC (permalink / raw)
To: amd-gfx list
[-- Attachment #1.1: Type: text/plain, Size: 559 bytes --]
Hi all,
I have connected an E9260 (Polaris 11 based) to a mini-PCIe slot on my NXP
LS1012ARDB.
The GPU is seen, all the BARs are correctly assigned (but there's not
enough PCIe memory space for the big BARs).
When I try to load the amdgpu module, I can't get the driver to enable the
acceleration (the scratch register check fails).
The E9260 is connected to a PCIe x1 (Gen2) slot.
Anyone have an idea on where to look or how to fix this? This is a test-bed
before we get an LS1046ARDB with quad core A72's.
Any help would be appreciated,
Bas Vermeulen
[-- Attachment #1.2: Type: text/html, Size: 747 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
[not found] ` <CAGtoiRiubNF5fCwGvYbC_sxzFk10Ceg79ZsK2fPLXUzFvm_QZw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2018-12-20 15:27 ` Alex Deucher
[not found] ` <CADnq5_MC9PLzvouWT=4J_RXkmsAy7NF1bpB-geEgxa-XV1dgQQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
0 siblings, 1 reply; 8+ messages in thread
From: Alex Deucher @ 2018-12-20 15:27 UTC (permalink / raw)
To: Bas Vermeulen; +Cc: amd-gfx list
On Thu, Dec 20, 2018 at 9:06 AM Bas Vermeulen <bas@daedalean.ai> wrote:
>
> Hi all,
>
> I have connected an E9260 (Polaris 11 based) to a mini-PCIe slot on my NXP LS1012ARDB.
> The GPU is seen, all the BARs are correctly assigned (but there's not enough PCIe memory space for the big BARs).
>
> When I try to load the amdgpu module, I can't get the driver to enable the acceleration (the scratch register check fails).
>
> The E9260 is connected to a PCIe x1 (Gen2) slot.
>
> Anyone have an idea on where to look or how to fix this? This is a test-bed before we get an LS1046ARDB with quad core A72's.
>
> Any help would be appreciated,
Something like this patch should fix it assuming this is an ARM based platform:
https://patchwork.freedesktop.org/patch/269367/
Alex
>
> Bas Vermeulen
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
[not found] ` <CADnq5_MC9PLzvouWT=4J_RXkmsAy7NF1bpB-geEgxa-XV1dgQQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2018-12-20 16:11 ` Bas Vermeulen
2019-01-10 10:55 ` Bas Vermeulen
0 siblings, 1 reply; 8+ messages in thread
From: Bas Vermeulen @ 2018-12-20 16:11 UTC (permalink / raw)
To: Alex Deucher; +Cc: amd-gfx list
[-- Attachment #1.1: Type: text/plain, Size: 1295 bytes --]
Hi Alex,
I already have a similar patch in, that doesn't fix it just yet. I'll
investigate some more.
Bas Vermeulen
On Thu, Dec 20, 2018 at 4:27 PM Alex Deucher <alexdeucher-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:
> On Thu, Dec 20, 2018 at 9:06 AM Bas Vermeulen <bas-MbI5SpmOCPBHdOctNixuYw@public.gmane.org> wrote:
> >
> > Hi all,
> >
> > I have connected an E9260 (Polaris 11 based) to a mini-PCIe slot on my
> NXP LS1012ARDB.
> > The GPU is seen, all the BARs are correctly assigned (but there's not
> enough PCIe memory space for the big BARs).
> >
> > When I try to load the amdgpu module, I can't get the driver to enable
> the acceleration (the scratch register check fails).
> >
> > The E9260 is connected to a PCIe x1 (Gen2) slot.
> >
> > Anyone have an idea on where to look or how to fix this? This is a
> test-bed before we get an LS1046ARDB with quad core A72's.
> >
> > Any help would be appreciated,
>
> Something like this patch should fix it assuming this is an ARM based
> platform:
> https://patchwork.freedesktop.org/patch/269367/
>
> Alex
>
> >
> > Bas Vermeulen
> > _______________________________________________
> > amd-gfx mailing list
> > amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
> > https://lists.freedesktop.org/mailman/listinfo/amd-gfx
>
[-- Attachment #1.2: Type: text/html, Size: 2160 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
2018-12-20 16:11 ` Bas Vermeulen
@ 2019-01-10 10:55 ` Bas Vermeulen
[not found] ` <CAGtoiRiPHW8a3afkO3ui5FtLP-OztBjVz6CgMgLifgLvnk4QOg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
0 siblings, 1 reply; 8+ messages in thread
From: Bas Vermeulen @ 2019-01-10 10:55 UTC (permalink / raw)
To: Alex Deucher; +Cc: amd-gfx list
[-- Attachment #1.1: Type: text/plain, Size: 10475 bytes --]
Hi Alex,
I've managed to get a little further. I am currently running mainline
(5.0.0-rc1) and am getting the errors below.
Looking at the datasheet for the LS1012A, it mentions in the PCI Express
section that:
The PCI Express controller as instantiated on this chip does not support
hardware coherency. All incoming PCI Express transactions are made non
IO-coherent.
Would AMDGPU still work with that PCI Express controller, or is this a
show-stopper?
[ 5.727691] [drm] initializing kernel modesetting (POLARIS11
0x1002:0x67E8 0x1DA2:0xE362 0x80).
[ 5.761767] [drm] register mmio base: 0x58000000
[ 5.777272] [drm] register mmio size: 262144
[ 5.825973] [drm] add ip block number 0 <vi_common>
[ 5.832242] [drm] add ip block number 1 <gmc_v8_0>
[ 5.837767] [drm] add ip block number 2 <tonga_ih>
[ 5.843121] [drm] add ip block number 3 <gfx_v8_0>
[ 5.848480] [drm] add ip block number 4 <sdma_v3_0>
[ 5.853969] [drm] add ip block number 5 <powerplay>
[ 5.859413] [drm] add ip block number 6 <dm>
[ 5.864238] [drm] add ip block number 7 <uvd_v6_0>
[ 5.869690] [drm] add ip block number 8 <vce_v3_0>
[ 5.875067] [drm] UVD is enabled in VM mode
[ 5.879858] [drm] UVD ENC is enabled in VM mode
[ 5.884985] [drm] VCE enabled in VM mode
[ 6.114020] ATOM BIOS: 113-C98511-U01
[ 6.117757] [drm] GPU posting now...
[ 6.238112] [drm] vm size is 64 GB, 2 levels, block size is 10-bit,
fragment size is 9-bit
[ 6.247290] amdgpu 0000:01:00.0: BAR 2: releasing [mem
0x4050000000-0x40501fffff 64bit pref]
[ 6.257354] amdgpu 0000:01:00.0: BAR 0: releasing [mem
0x4040000000-0x404fffffff 64bit pref]
[ 6.267261] pcieport 0000:00:00.0: BAR 15: releasing [mem
0x4040000000-0x4057ffffff 64bit pref]
[ 6.277288] pcieport 0000:00:00.0: BAR 15: no space for [mem size
0x300000000 64bit pref]
[ 6.286843] pcieport 0000:00:00.0: BAR 15: failed to assign [mem size
0x300000000 64bit pref]
[ 6.296708] amdgpu 0000:01:00.0: BAR 0: no space for [mem size
0x200000000 64bit pref]
[ 6.306009] amdgpu 0000:01:00.0: BAR 0: failed to assign [mem size
0x200000000 64bit pref]
[ 6.315635] amdgpu 0000:01:00.0: BAR 2: no space for [mem size
0x00200000 64bit pref]
[ 6.324804] amdgpu 0000:01:00.0: BAR 2: failed to assign [mem size
0x00200000 64bit pref]
[ 6.334366] pcieport 0000:00:00.0: PCI bridge to [bus 01-ff]
[ 6.341323] pcieport 0000:00:00.0: bridge window [io 0x1000-0x1fff]
[ 6.349158] pcieport 0000:00:00.0: bridge window [mem
0x4058000000-0x40580fffff]
[ 6.358095] pcieport 0000:00:00.0: PCI bridge to [bus 01-ff]
[ 6.365054] pcieport 0000:00:00.0: bridge window [io 0x1000-0x1fff]
[ 6.372981] pcieport 0000:00:00.0: bridge window [mem
0x4058000000-0x40580fffff]
[ 6.381917] pcieport 0000:00:00.0: bridge window [mem
0x4040000000-0x4057ffffff 64bit pref]
[ 6.391789] [drm] Not enough PCI address space for a large BAR.
[ 6.391820] amdgpu 0000:01:00.0: BAR 0: assigned [mem
0x4040000000-0x404fffffff 64bit pref]
[ 6.407776] amdgpu 0000:01:00.0: BAR 2: assigned [mem
0x4050000000-0x40501fffff 64bit pref]
[ 6.417672] amdgpu 0000:01:00.0: VRAM: 8192M 0x000000F400000000 -
0x000000F5FFFFFFFF (8192M used)
[ 6.426586] amdgpu 0000:01:00.0: GART: 256M 0x000000FF00000000 -
0x000000FF0FFFFFFF
[ 6.436171] [drm] Detected VRAM RAM=8192M, BAR=256M
[ 6.478952] [drm] GART: num cpu pages 65536, num gpu pages 65536
[ 6.487871] [drm] PCIE GART of 256M enabled (table at
0x000000F400000000).
[ 6.496316] amdgpu 0000:01:00.0: Direct firmware load for
amdgpu/polaris11_pfp_2.bin failed with error -2
[ 6.508078] amdgpu 0000:01:00.0: Direct firmware load for
amdgpu/polaris11_me_2.bin failed with error -2
[ 6.519538] amdgpu 0000:01:00.0: Direct firmware load for
amdgpu/polaris11_ce_2.bin failed with error -2
[ 6.531496] amdgpu 0000:01:00.0: Direct firmware load for
amdgpu/polaris11_mec_2.bin failed with error -2
[ 6.544214] amdgpu 0000:01:00.0: Direct firmware load for
amdgpu/polaris11_mec2_2.bin failed with error -2
[ 6.565121] [drm] Found UVD firmware Version: 1.79 Family ID: 16
[ 6.571241] [drm] UVD ENC is disabled
[ 6.580927] [drm] Found VCE firmware Version: 52.4 Binary ID: 3
[ 6.656854] amdgpu 0000:01:00.0: GPU fault detected: 147 0x00004802 for
process pid 0 thread pid 0
[ 6.666013] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR
0x0017F000
[ 6.673508] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS
0x02048002
[ 6.681006] amdgpu 0000:01:00.0: VM fault (0x02, vmid 1, pasid 0) at
page 1568768, read from 'TC0' (0x54433000) (72)
[ 6.691557] amdgpu 0000:01:00.0: GPU fault detected: 147 0x00004402 for
process pid 0 thread pid 0
[ 6.700706] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR
0x0017F000
[ 6.708200] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS
0x02048002
[ 6.715697] amdgpu 0000:01:00.0: VM fault (0x02, vmid 1, pasid 0) at
page 1568768, read from 'TC0' (0x54433000) (72)
[ 6.726246] amdgpu 0000:01:00.0: GPU fault detected: 147 0x00000402 for
process pid 0 thread pid 0
[ 6.735395] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_ADDR
0x0017F000
[ 6.742889] amdgpu 0000:01:00.0: VM_CONTEXT1_PROTECTION_FAULT_STATUS
0x02048002
[ 6.750386] amdgpu 0000:01:00.0: VM fault (0x02, vmid 1, pasid 0) at
page 1568768, read from 'TC0' (0x54433000) (72)
[ 6.984485] amdgpu 0000:01:00.0: [drm:amdgpu_ring_test_helper [amdgpu]]
*ERROR* ring gfx test failed (-110)
[ 6.994562] [drm:amdgpu_device_init [amdgpu]] *ERROR* hw_init of IP
block <gfx_v8_0> failed -110
[ 7.004942] amdgpu 0000:01:00.0: amdgpu_device_ip_init failed
[ 7.011963] amdgpu 0000:01:00.0: Fatal error during GPU init
[ 7.018890] [drm] amdgpu: finishing device.
[ 7.308898] WARNING: CPU: 0 PID: 2084 at
/home/bas/linux/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c:915
amdgpu_bo_unpin+0xe4/0x110 [amdgpu]
[ 7.321451] Modules linked in: amdgpu(+) realtek chash gpu_sched ttm
drm_kms_helper drm crct10dif_ce drm_panel_orientation_quirks pfe(C)
ip_tables x_tables ipv6
[ 7.335850] CPU: 0 PID: 2084 Comm: systemd-udevd Tainted: G C
5.0.0-rc1-00001-g3bd6e94bec12-dirty #1
[ 7.346303] Hardware name: LS1012A RDB Board (DT)
[ 7.351014] pstate: 40000005 (nZcv daif -PAN -UAO)
[ 7.356090] pc : amdgpu_bo_unpin+0xe4/0x110 [amdgpu]
[ 7.361307] lr : amdgpu_bo_free_kernel+0x7c/0x148 [amdgpu]
[ 7.366799] sp : ffff0000118c3730
[ 7.370114] x29: ffff0000118c3730 x28: ffff000008e63710
[ 7.375434] x27: ffff0000118c3df0 x26: 0000000000000100
[ 7.380754] x25: ffff80003599cb60 x24: ffff8000359927d0
[ 7.386073] x23: ffff800035994750 x22: ffff8000359927d0
[ 7.391393] x21: ffff8000358cb800 x20: ffff0000111fd000
[ 7.396713] x19: ffff8000358cb800 x18: 000000000000001e
[ 7.402033] x17: 0000000000000000 x16: 0000000000000002
[ 7.407351] x15: 0000000000000400 x14: 0000000000000400
[ 7.412670] x13: 000000000000cb72 x12: 000000000000b308
[ 7.417989] x11: ffff7e0000d02488 x10: ffff800037798030
[ 7.423308] x9 : ffff0000118c36e4 x8 : 0000000000000000
[ 7.428627] x7 : 0000000000210d00 x6 : 0000000000000000
[ 7.433946] x5 : 0000000000000001 x4 : 0000000000000001
[ 7.439265] x3 : ffff8000358cb87c x2 : 0000000000000000
[ 7.444583] x1 : 0000000000000000 x0 : ffff8000358cb800
[ 7.449903] Call trace:
[ 7.452583] amdgpu_bo_unpin+0xe4/0x110 [amdgpu]
[ 7.457437] amdgpu_bo_free_kernel+0x7c/0x148 [amdgpu]
[ 7.462812] amdgpu_gfx_rlc_fini+0x50/0x78 [amdgpu]
[ 7.467926] gfx_v8_0_sw_fini+0xfc/0x1c0 [amdgpu]
[ 7.472864] amdgpu_device_fini+0x1e0/0x480 [amdgpu]
[ 7.478058] amdgpu_driver_unload_kms+0xa0/0x150 [amdgpu]
[ 7.483686] amdgpu_driver_load_kms+0x144/0x1f8 [amdgpu]
[ 7.489110] drm_dev_register+0x14c/0x1e0 [drm]
[ 7.493906] amdgpu_pci_probe+0xcc/0x188 [amdgpu]
[ 7.498622] local_pci_probe+0x3c/0xb0
[ 7.502375] pci_device_probe+0x150/0x1b8
[ 7.506390] really_probe+0x1f0/0x298
[ 7.510055] driver_probe_device+0x58/0x100
[ 7.514242] __driver_attach+0xd4/0xd8
[ 7.517993] bus_for_each_dev+0x74/0xc8
[ 7.521832] driver_attach+0x20/0x28
[ 7.525410] bus_add_driver+0x1ac/0x218
[ 7.529250] driver_register+0x60/0x110
[ 7.533089] __pci_register_driver+0x40/0x48
[ 7.537599] amdgpu_init+0x58/0x1000 [amdgpu]
[ 7.541964] do_one_initcall+0x5c/0x178
[ 7.545804] do_init_module+0x58/0x1b0
[ 7.549556] load_module+0x1dc8/0x2178
[ 7.553308] __se_sys_finit_module+0xbc/0xd0
[ 7.557582] __arm64_sys_finit_module+0x18/0x20
[ 7.562119] el0_svc_common+0x60/0x100
[ 7.565872] el0_svc_handler+0x2c/0x80
[ 7.581715] amdgpu 0000:01:00.0: (____ptrval____) unpin not necessary
[ 7.594743] [TTM] Finalizing pool allocator
[ 7.599867] [TTM] Finalizing DMA pool allocator
[ 7.605265] [TTM] Zone kernel: Used memory at exit: 0 kiB
[ 7.611482] [drm] amdgpu: ttm finalized
[ 7.618028] amdgpu: probe of 0000:01:00.0 failed with error -110
Bas Vermeulen
On Thu, Dec 20, 2018 at 5:11 PM Bas Vermeulen <bas-MbI5SpmOCPBHdOctNixuYw@public.gmane.org> wrote:
> Hi Alex,
>
> I already have a similar patch in, that doesn't fix it just yet. I'll
> investigate some more.
>
> Bas Vermeulen
>
> On Thu, Dec 20, 2018 at 4:27 PM Alex Deucher <alexdeucher-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> wrote:
>
>> On Thu, Dec 20, 2018 at 9:06 AM Bas Vermeulen <bas-MbI5SpmOCPBHdOctNixuYw@public.gmane.org> wrote:
>> >
>> > Hi all,
>> >
>> > I have connected an E9260 (Polaris 11 based) to a mini-PCIe slot on my
>> NXP LS1012ARDB.
>> > The GPU is seen, all the BARs are correctly assigned (but there's not
>> enough PCIe memory space for the big BARs).
>> >
>> > When I try to load the amdgpu module, I can't get the driver to enable
>> the acceleration (the scratch register check fails).
>> >
>> > The E9260 is connected to a PCIe x1 (Gen2) slot.
>> >
>> > Anyone have an idea on where to look or how to fix this? This is a
>> test-bed before we get an LS1046ARDB with quad core A72's.
>> >
>> > Any help would be appreciated,
>>
>> Something like this patch should fix it assuming this is an ARM based
>> platform:
>> https://patchwork.freedesktop.org/patch/269367/
>>
>> Alex
>>
>> >
>> > Bas Vermeulen
>> > _______________________________________________
>> > amd-gfx mailing list
>> > amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
>> > https://lists.freedesktop.org/mailman/listinfo/amd-gfx
>>
>
[-- Attachment #1.2: Type: text/html, Size: 13480 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
[not found] ` <CAGtoiRiPHW8a3afkO3ui5FtLP-OztBjVz6CgMgLifgLvnk4QOg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2019-01-10 10:59 ` Christian König
[not found] ` <5ae96345-680a-221f-1b04-678cb61f7eca-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
0 siblings, 1 reply; 8+ messages in thread
From: Christian König @ 2019-01-10 10:59 UTC (permalink / raw)
To: Bas Vermeulen, Alex Deucher; +Cc: amd-gfx list
[-- Attachment #1.1: Type: text/plain, Size: 12426 bytes --]
> The PCI Express controller as instantiated on this chip does not
> support hardware coherency. All incoming PCI Express transactions are
> made non IO-coherent.
>
> Would AMDGPU still work with that PCI Express controller, or is this a
> show-stopper?
I'm really wondering what this comment in the documentation means.
As far as I know PCIe doesn't support cache coherency in the downstream
and supporting it in the up stream is a must have.
So what exactly is meant here with IO-coherent?
Regards,
Christian.
Am 10.01.19 um 11:55 schrieb Bas Vermeulen:
> Hi Alex,
>
> I've managed to get a little further. I am currently running mainline
> (5.0.0-rc1) and am getting the errors below.
> Looking at the datasheet for the LS1012A, it mentions in the PCI
> Express section that:
>
> The PCI Express controller as instantiated on this chip does not
> support hardware coherency. All incoming PCI Express transactions are
> made non IO-coherent.
>
> Would AMDGPU still work with that PCI Express controller, or is this a
> show-stopper?
>
> [ 5.727691] [drm] initializing kernel modesetting (POLARIS11
> 0x1002:0x67E8 0x1DA2:0xE362 0x80).
> [ 5.761767] [drm] register mmio base: 0x58000000
> [ 5.777272] [drm] register mmio size: 262144
> [ 5.825973] [drm] add ip block number 0 <vi_common>
> [ 5.832242] [drm] add ip block number 1 <gmc_v8_0>
> [ 5.837767] [drm] add ip block number 2 <tonga_ih>
> [ 5.843121] [drm] add ip block number 3 <gfx_v8_0>
> [ 5.848480] [drm] add ip block number 4 <sdma_v3_0>
> [ 5.853969] [drm] add ip block number 5 <powerplay>
> [ 5.859413] [drm] add ip block number 6 <dm>
> [ 5.864238] [drm] add ip block number 7 <uvd_v6_0>
> [ 5.869690] [drm] add ip block number 8 <vce_v3_0>
> [ 5.875067] [drm] UVD is enabled in VM mode
> [ 5.879858] [drm] UVD ENC is enabled in VM mode
> [ 5.884985] [drm] VCE enabled in VM mode
> [ 6.114020] ATOM BIOS: 113-C98511-U01
> [ 6.117757] [drm] GPU posting now...
> [ 6.238112] [drm] vm size is 64 GB, 2 levels, block size is 10-bit,
> fragment size is 9-bit
> [ 6.247290] amdgpu 0000:01:00.0: BAR 2: releasing [mem
> 0x4050000000-0x40501fffff 64bit pref]
> [ 6.257354] amdgpu 0000:01:00.0: BAR 0: releasing [mem
> 0x4040000000-0x404fffffff 64bit pref]
> [ 6.267261] pcieport 0000:00:00.0: BAR 15: releasing [mem
> 0x4040000000-0x4057ffffff 64bit pref]
> [ 6.277288] pcieport 0000:00:00.0: BAR 15: no space for [mem size
> 0x300000000 64bit pref]
> [ 6.286843] pcieport 0000:00:00.0: BAR 15: failed to assign [mem
> size 0x300000000 64bit pref]
> [ 6.296708] amdgpu 0000:01:00.0: BAR 0: no space for [mem size
> 0x200000000 64bit pref]
> [ 6.306009] amdgpu 0000:01:00.0: BAR 0: failed to assign [mem size
> 0x200000000 64bit pref]
> [ 6.315635] amdgpu 0000:01:00.0: BAR 2: no space for [mem size
> 0x00200000 64bit pref]
> [ 6.324804] amdgpu 0000:01:00.0: BAR 2: failed to assign [mem size
> 0x00200000 64bit pref]
> [ 6.334366] pcieport 0000:00:00.0: PCI bridge to [bus 01-ff]
> [ 6.341323] pcieport 0000:00:00.0: bridge window [io 0x1000-0x1fff]
> [ 6.349158] pcieport 0000:00:00.0: bridge window [mem
> 0x4058000000-0x40580fffff]
> [ 6.358095] pcieport 0000:00:00.0: PCI bridge to [bus 01-ff]
> [ 6.365054] pcieport 0000:00:00.0: bridge window [io 0x1000-0x1fff]
> [ 6.372981] pcieport 0000:00:00.0: bridge window [mem
> 0x4058000000-0x40580fffff]
> [ 6.381917] pcieport 0000:00:00.0: bridge window [mem
> 0x4040000000-0x4057ffffff 64bit pref]
> [ 6.391789] [drm] Not enough PCI address space for a large BAR.
> [ 6.391820] amdgpu 0000:01:00.0: BAR 0: assigned [mem
> 0x4040000000-0x404fffffff 64bit pref]
> [ 6.407776] amdgpu 0000:01:00.0: BAR 2: assigned [mem
> 0x4050000000-0x40501fffff 64bit pref]
> [ 6.417672] amdgpu 0000:01:00.0: VRAM: 8192M 0x000000F400000000 -
> 0x000000F5FFFFFFFF (8192M used)
> [ 6.426586] amdgpu 0000:01:00.0: GART: 256M 0x000000FF00000000 -
> 0x000000FF0FFFFFFF
> [ 6.436171] [drm] Detected VRAM RAM=8192M, BAR=256M
> [ 6.478952] [drm] GART: num cpu pages 65536, num gpu pages 65536
> [ 6.487871] [drm] PCIE GART of 256M enabled (table at
> 0x000000F400000000).
> [ 6.496316] amdgpu 0000:01:00.0: Direct firmware load for
> amdgpu/polaris11_pfp_2.bin failed with error -2
> [ 6.508078] amdgpu 0000:01:00.0: Direct firmware load for
> amdgpu/polaris11_me_2.bin failed with error -2
> [ 6.519538] amdgpu 0000:01:00.0: Direct firmware load for
> amdgpu/polaris11_ce_2.bin failed with error -2
> [ 6.531496] amdgpu 0000:01:00.0: Direct firmware load for
> amdgpu/polaris11_mec_2.bin failed with error -2
> [ 6.544214] amdgpu 0000:01:00.0: Direct firmware load for
> amdgpu/polaris11_mec2_2.bin failed with error -2
> [ 6.565121] [drm] Found UVD firmware Version: 1.79 Family ID: 16
> [ 6.571241] [drm] UVD ENC is disabled
> [ 6.580927] [drm] Found VCE firmware Version: 52.4 Binary ID: 3
> [ 6.656854] amdgpu 0000:01:00.0: GPU fault detected: 147 0x00004802
> for process pid 0 thread pid 0
> [ 6.666013] amdgpu 0000:01:00.0:
> VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x0017F000
> [ 6.673508] amdgpu 0000:01:00.0:
> VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x02048002
> [ 6.681006] amdgpu 0000:01:00.0: VM fault (0x02, vmid 1, pasid 0)
> at page 1568768, read from 'TC0' (0x54433000) (72)
> [ 6.691557] amdgpu 0000:01:00.0: GPU fault detected: 147 0x00004402
> for process pid 0 thread pid 0
> [ 6.700706] amdgpu 0000:01:00.0:
> VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x0017F000
> [ 6.708200] amdgpu 0000:01:00.0:
> VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x02048002
> [ 6.715697] amdgpu 0000:01:00.0: VM fault (0x02, vmid 1, pasid 0)
> at page 1568768, read from 'TC0' (0x54433000) (72)
> [ 6.726246] amdgpu 0000:01:00.0: GPU fault detected: 147 0x00000402
> for process pid 0 thread pid 0
> [ 6.735395] amdgpu 0000:01:00.0:
> VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x0017F000
> [ 6.742889] amdgpu 0000:01:00.0:
> VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x02048002
> [ 6.750386] amdgpu 0000:01:00.0: VM fault (0x02, vmid 1, pasid 0)
> at page 1568768, read from 'TC0' (0x54433000) (72)
> [ 6.984485] amdgpu 0000:01:00.0: [drm:amdgpu_ring_test_helper
> [amdgpu]] *ERROR* ring gfx test failed (-110)
> [ 6.994562] [drm:amdgpu_device_init [amdgpu]] *ERROR* hw_init of IP
> block <gfx_v8_0> failed -110
> [ 7.004942] amdgpu 0000:01:00.0: amdgpu_device_ip_init failed
> [ 7.011963] amdgpu 0000:01:00.0: Fatal error during GPU init
> [ 7.018890] [drm] amdgpu: finishing device.
> [ 7.308898] WARNING: CPU: 0 PID: 2084 at
> /home/bas/linux/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c:915
> amdgpu_bo_unpin+0xe4/0x110 [amdgpu]
> [ 7.321451] Modules linked in: amdgpu(+) realtek chash gpu_sched
> ttm drm_kms_helper drm crct10dif_ce drm_panel_orientation_quirks
> pfe(C) ip_tables x_tables ipv6
> [ 7.335850] CPU: 0 PID: 2084 Comm: systemd-udevd Tainted: G
> C 5.0.0-rc1-00001-g3bd6e94bec12-dirty #1
> [ 7.346303] Hardware name: LS1012A RDB Board (DT)
> [ 7.351014] pstate: 40000005 (nZcv daif -PAN -UAO)
> [ 7.356090] pc : amdgpu_bo_unpin+0xe4/0x110 [amdgpu]
> [ 7.361307] lr : amdgpu_bo_free_kernel+0x7c/0x148 [amdgpu]
> [ 7.366799] sp : ffff0000118c3730
> [ 7.370114] x29: ffff0000118c3730 x28: ffff000008e63710
> [ 7.375434] x27: ffff0000118c3df0 x26: 0000000000000100
> [ 7.380754] x25: ffff80003599cb60 x24: ffff8000359927d0
> [ 7.386073] x23: ffff800035994750 x22: ffff8000359927d0
> [ 7.391393] x21: ffff8000358cb800 x20: ffff0000111fd000
> [ 7.396713] x19: ffff8000358cb800 x18: 000000000000001e
> [ 7.402033] x17: 0000000000000000 x16: 0000000000000002
> [ 7.407351] x15: 0000000000000400 x14: 0000000000000400
> [ 7.412670] x13: 000000000000cb72 x12: 000000000000b308
> [ 7.417989] x11: ffff7e0000d02488 x10: ffff800037798030
> [ 7.423308] x9 : ffff0000118c36e4 x8 : 0000000000000000
> [ 7.428627] x7 : 0000000000210d00 x6 : 0000000000000000
> [ 7.433946] x5 : 0000000000000001 x4 : 0000000000000001
> [ 7.439265] x3 : ffff8000358cb87c x2 : 0000000000000000
> [ 7.444583] x1 : 0000000000000000 x0 : ffff8000358cb800
> [ 7.449903] Call trace:
> [ 7.452583] amdgpu_bo_unpin+0xe4/0x110 [amdgpu]
> [ 7.457437] amdgpu_bo_free_kernel+0x7c/0x148 [amdgpu]
> [ 7.462812] amdgpu_gfx_rlc_fini+0x50/0x78 [amdgpu]
> [ 7.467926] gfx_v8_0_sw_fini+0xfc/0x1c0 [amdgpu]
> [ 7.472864] amdgpu_device_fini+0x1e0/0x480 [amdgpu]
> [ 7.478058] amdgpu_driver_unload_kms+0xa0/0x150 [amdgpu]
> [ 7.483686] amdgpu_driver_load_kms+0x144/0x1f8 [amdgpu]
> [ 7.489110] drm_dev_register+0x14c/0x1e0 [drm]
> [ 7.493906] amdgpu_pci_probe+0xcc/0x188 [amdgpu]
> [ 7.498622] local_pci_probe+0x3c/0xb0
> [ 7.502375] pci_device_probe+0x150/0x1b8
> [ 7.506390] really_probe+0x1f0/0x298
> [ 7.510055] driver_probe_device+0x58/0x100
> [ 7.514242] __driver_attach+0xd4/0xd8
> [ 7.517993] bus_for_each_dev+0x74/0xc8
> [ 7.521832] driver_attach+0x20/0x28
> [ 7.525410] bus_add_driver+0x1ac/0x218
> [ 7.529250] driver_register+0x60/0x110
> [ 7.533089] __pci_register_driver+0x40/0x48
> [ 7.537599] amdgpu_init+0x58/0x1000 [amdgpu]
> [ 7.541964] do_one_initcall+0x5c/0x178
> [ 7.545804] do_init_module+0x58/0x1b0
> [ 7.549556] load_module+0x1dc8/0x2178
> [ 7.553308] __se_sys_finit_module+0xbc/0xd0
> [ 7.557582] __arm64_sys_finit_module+0x18/0x20
> [ 7.562119] el0_svc_common+0x60/0x100
> [ 7.565872] el0_svc_handler+0x2c/0x80
> [ 7.581715] amdgpu 0000:01:00.0: (____ptrval____) unpin not necessary
> [ 7.594743] [TTM] Finalizing pool allocator
> [ 7.599867] [TTM] Finalizing DMA pool allocator
> [ 7.605265] [TTM] Zone kernel: Used memory at exit: 0 kiB
> [ 7.611482] [drm] amdgpu: ttm finalized
> [ 7.618028] amdgpu: probe of 0000:01:00.0 failed with error -110
>
> Bas Vermeulen
>
>
> On Thu, Dec 20, 2018 at 5:11 PM Bas Vermeulen <bas-MbI5SpmOCPBHdOctNixuYw@public.gmane.org
> <mailto:bas-MbI5SpmOCPBHdOctNixuYw@public.gmane.org>> wrote:
>
> Hi Alex,
>
> I already have a similar patch in, that doesn't fix it just yet.
> I'll investigate some more.
>
> Bas Vermeulen
>
> On Thu, Dec 20, 2018 at 4:27 PM Alex Deucher
> <alexdeucher-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org <mailto:alexdeucher-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>> wrote:
>
> On Thu, Dec 20, 2018 at 9:06 AM Bas Vermeulen
> <bas-MbI5SpmOCPBHdOctNixuYw@public.gmane.org <mailto:bas-MbI5SpmOCPBHdOctNixuYw@public.gmane.org>> wrote:
> >
> > Hi all,
> >
> > I have connected an E9260 (Polaris 11 based) to a mini-PCIe
> slot on my NXP LS1012ARDB.
> > The GPU is seen, all the BARs are correctly assigned (but
> there's not enough PCIe memory space for the big BARs).
> >
> > When I try to load the amdgpu module, I can't get the driver
> to enable the acceleration (the scratch register check fails).
> >
> > The E9260 is connected to a PCIe x1 (Gen2) slot.
> >
> > Anyone have an idea on where to look or how to fix this?
> This is a test-bed before we get an LS1046ARDB with quad core
> A72's.
> >
> > Any help would be appreciated,
>
> Something like this patch should fix it assuming this is an
> ARM based platform:
> https://patchwork.freedesktop.org/patch/269367/
>
> Alex
>
> >
> > Bas Vermeulen
> > _______________________________________________
> > amd-gfx mailing list
> > amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
> <mailto:amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
> > https://lists.freedesktop.org/mailman/listinfo/amd-gfx
>
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[-- Attachment #1.2: Type: text/html, Size: 21623 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
[not found] ` <5ae96345-680a-221f-1b04-678cb61f7eca-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
@ 2019-01-10 13:31 ` Bas Vermeulen
[not found] ` <CAGtoiRiY-TK+_YHwk=f_2vMxJJ6Ucv9AQ2vuoxtufFakKp=hAA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
0 siblings, 1 reply; 8+ messages in thread
From: Bas Vermeulen @ 2019-01-10 13:31 UTC (permalink / raw)
To: Christian König; +Cc: Alex Deucher, amd-gfx list
[-- Attachment #1.1: Type: text/plain, Size: 975 bytes --]
On Thu, Jan 10, 2019 at 11:59 AM Christian König <
ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:
> The PCI Express controller as instantiated on this chip does not support
> hardware coherency. All incoming PCI Express transactions are made non
> IO-coherent.
>
> Would AMDGPU still work with that PCI Express controller, or is this a
> show-stopper?
>
>
> I'm really wondering what this comment in the documentation means.
>
> As far as I know PCIe doesn't support cache coherency in the downstream
> and supporting it in the up stream is a must have.
>
So what exactly is meant here with IO-coherent?
>
I believe IO Coherent means that when PCIe writes something to CPU memory,
the caches are flushed or updated
(or in this case they aren't). I found
https://community.arm.com/processors/b/blog/posts/extended-system-coherency---part-1---cache-coherency-fundamentals
with this explanation.
Regards,
Bas Vermeulen
[-- Attachment #1.2: Type: text/html, Size: 1979 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
[not found] ` <CAGtoiRiY-TK+_YHwk=f_2vMxJJ6Ucv9AQ2vuoxtufFakKp=hAA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
@ 2019-01-10 13:38 ` Koenig, Christian
[not found] ` <20720365-641e-ac3e-1cfb-9c16133905be-5C7GfCeVMHo@public.gmane.org>
0 siblings, 1 reply; 8+ messages in thread
From: Koenig, Christian @ 2019-01-10 13:38 UTC (permalink / raw)
To: Bas Vermeulen; +Cc: Alex Deucher, amd-gfx list
[-- Attachment #1.1: Type: text/plain, Size: 1297 bytes --]
Am 10.01.19 um 14:31 schrieb Bas Vermeulen:
On Thu, Jan 10, 2019 at 11:59 AM Christian König <ckoenig.leichtzumerken@gmail.com<mailto:ckoenig.leichtzumerken@gmail.com>> wrote:
The PCI Express controller as instantiated on this chip does not support hardware coherency. All incoming PCI Express transactions are made non IO-coherent.
Would AMDGPU still work with that PCI Express controller, or is this a show-stopper?
I'm really wondering what this comment in the documentation means.
As far as I know PCIe doesn't support cache coherency in the downstream and supporting it in the up stream is a must have.
So what exactly is meant here with IO-coherent?
I believe IO Coherent means that when PCIe writes something to CPU memory, the caches are flushed or updated
(or in this case they aren't). I found https://community.arm.com/processors/b/blog/posts/extended-system-coherency---part-1---cache-coherency-fundamentals
with this explanation.
Yeah, but as I said this upstream memory coherency is mandatory for PCIe.
When a controller doesn't have that it can't call itself a PCIe controller. The spec is pretty clear about that :)
And to answer the original question: Yes, that would be a totally show-stopper.
Regards,
Christian.
Regards,
Bas Vermeulen
[-- Attachment #1.2: Type: text/html, Size: 2902 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB
[not found] ` <20720365-641e-ac3e-1cfb-9c16133905be-5C7GfCeVMHo@public.gmane.org>
@ 2019-01-18 13:21 ` Bas Vermeulen
0 siblings, 0 replies; 8+ messages in thread
From: Bas Vermeulen @ 2019-01-18 13:21 UTC (permalink / raw)
To: Koenig, Christian; +Cc: Alex Deucher, amd-gfx list
[-- Attachment #1.1: Type: text/plain, Size: 1747 bytes --]
I've since replaced the LS1012ARDB with a LS1046ARDB, and this works out of
the box.
The LS1012ARDB does not have an SMMU, which handles hardware coherency on
ARM.
So amdgpu won't work on any ARM without an SMMU.
Bas Vermeulen
On Thu, Jan 10, 2019 at 2:38 PM Koenig, Christian <Christian.Koenig-5C7GfCeVMHo@public.gmane.org>
wrote:
> Am 10.01.19 um 14:31 schrieb Bas Vermeulen:
>
> On Thu, Jan 10, 2019 at 11:59 AM Christian König <
> ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> wrote:
>
>> The PCI Express controller as instantiated on this chip does not support
>> hardware coherency. All incoming PCI Express transactions are made non
>> IO-coherent.
>>
>> Would AMDGPU still work with that PCI Express controller, or is this a
>> show-stopper?
>>
>>
>> I'm really wondering what this comment in the documentation means.
>>
>> As far as I know PCIe doesn't support cache coherency in the downstream
>> and supporting it in the up stream is a must have.
>>
> So what exactly is meant here with IO-coherent?
>>
>
> I believe IO Coherent means that when PCIe writes something to CPU memory,
> the caches are flushed or updated
> (or in this case they aren't). I found
> https://community.arm.com/processors/b/blog/posts/extended-system-coherency---part-1---cache-coherency-fundamentals
>
> with this explanation.
>
>
> Yeah, but as I said this upstream memory coherency is mandatory for PCIe.
>
> When a controller doesn't have that it can't call itself a PCIe
> controller. The spec is pretty clear about that :)
>
> And to answer the original question: Yes, that would be a totally
> show-stopper.
>
> Regards,
> Christian.
>
>
> Regards,
>
> Bas Vermeulen
>
>
>
[-- Attachment #1.2: Type: text/html, Size: 3399 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2019-01-18 13:21 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-12-20 14:06 Trying to run AMD E9260 (Polaris 11) on NXP LS1012A-RDB Bas Vermeulen
[not found] ` <CAGtoiRiubNF5fCwGvYbC_sxzFk10Ceg79ZsK2fPLXUzFvm_QZw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-12-20 15:27 ` Alex Deucher
[not found] ` <CADnq5_MC9PLzvouWT=4J_RXkmsAy7NF1bpB-geEgxa-XV1dgQQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-12-20 16:11 ` Bas Vermeulen
2019-01-10 10:55 ` Bas Vermeulen
[not found] ` <CAGtoiRiPHW8a3afkO3ui5FtLP-OztBjVz6CgMgLifgLvnk4QOg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2019-01-10 10:59 ` Christian König
[not found] ` <5ae96345-680a-221f-1b04-678cb61f7eca-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2019-01-10 13:31 ` Bas Vermeulen
[not found] ` <CAGtoiRiY-TK+_YHwk=f_2vMxJJ6Ucv9AQ2vuoxtufFakKp=hAA-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2019-01-10 13:38 ` Koenig, Christian
[not found] ` <20720365-641e-ac3e-1cfb-9c16133905be-5C7GfCeVMHo@public.gmane.org>
2019-01-18 13:21 ` Bas Vermeulen
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.