AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Chunming Zhou <zhoucm1-5C7GfCeVMHo@public.gmane.org>
To: "Christian König"
	<ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Subject: Re: [PATCH 21/21] drm/amdgpu: add PASID mapping for GFX v8
Date: Wed, 17 Jan 2018 14:11:21 +0800	[thread overview]
Message-ID: <bd8e530b-869f-2cf9-c5b2-8fce9afd2341@amd.com> (raw)
In-Reply-To: <20180116194017.39067-21-christian.koenig-5C7GfCeVMHo@public.gmane.org>

patch #19, #20, #21 are Reviewed-by: Chunming Zhou <david1.zhou@amd.com>


On 2018年01月17日 03:40, Christian König wrote:
> This way we can see the PASID in VM faults.
>
> Signed-off-by: Christian König <christian.koenig@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 12 +++++++++++-
>   1 file changed, 11 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index f7bcfa53eff0..2efbecf486c5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -33,6 +33,7 @@
>   #include "vega10_enum.h"
>   #include "mmhub/mmhub_1_0_offset.h"
>   #include "athub/athub_1_0_offset.h"
> +#include "oss/osssys_4_0_offset.h"
>   
>   #include "soc15.h"
>   #include "soc15_common.h"
> @@ -369,10 +370,12 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
>   					    unsigned vmid, unsigned pasid,
>   					    uint64_t pd_addr)
>   {
> -	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
> +	struct amdgpu_device *adev = ring->adev;
> +	struct amdgpu_vmhub *hub = &adev->vmhub[ring->funcs->vmhub];
>   	uint32_t req = gmc_v9_0_get_invalidate_req(vmid);
>   	uint64_t flags = AMDGPU_PTE_VALID;
>   	unsigned eng = ring->vm_inv_eng;
> +	uint32_t reg;
>   
>   	amdgpu_gmc_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
>   	pd_addr |= flags;
> @@ -383,6 +386,13 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
>   	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
>   			      upper_32_bits(pd_addr));
>   
> +	if (ring->funcs->vmhub == AMDGPU_GFXHUB)
> +		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT) + vmid;
> +	else
> +		reg = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_VMID_0_LUT_MM) + vmid;
> +
> +	amdgpu_ring_emit_wreg(ring, reg, pasid);
> +
>   	amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req);
>   
>   	return pd_addr;

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  parent reply	other threads:[~2018-01-17  6:11 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-16 19:39 [PATCH 01/21] drm/amdgpu: wire up emit_wreg for gfx v6 Christian König
     [not found] ` <20180116194017.39067-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-01-16 19:39   ` [PATCH 02/21] drm/amdgpu: wire up emit_wreg for gfx v7 Christian König
2018-01-16 19:39   ` [PATCH 03/21] drm/amdgpu: wire up emit_wreg for gfx v8 Christian König
2018-01-16 19:40   ` [PATCH 04/21] drm/amdgpu: wire up emit_wreg for gfx v9 Christian König
2018-01-16 19:40   ` [PATCH 05/21] drm/amdgpu: wire up emit_wreg for SI DMA Christian König
2018-01-16 19:40   ` [PATCH 06/21] drm/amdgpu: wire up emit_wreg for CIK SDMA Christian König
2018-01-16 19:40   ` [PATCH 07/21] drm/amdgpu: wire up emit_wreg for SDMA v2.4 Christian König
2018-01-16 19:40   ` [PATCH 08/21] drm/amdgpu: wire up emit_wreg for SDMA v3 Christian König
2018-01-16 19:40   ` [PATCH 09/21] drm/amdgpu: wire up emit_wreg for SDMA v4 Christian König
2018-01-16 19:40   ` [PATCH 10/21] drm/amdgpu: wire up emit_wreg for UVD v6 Christian König
     [not found]     ` <20180116194017.39067-10-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-01-16 20:01       ` Alex Deucher
     [not found]         ` <CADnq5_Pc2QujuEDmsb8O2E0-VGmMgSCkN2K-B4O_1y-3zrQE7A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-01-17 12:42           ` Christian König
     [not found]             ` <c33f3adf-66d4-1d37-ebc9-cf3ab7d1b967-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-01-17 14:22               ` Deucher, Alexander
     [not found]                 ` <BN6PR12MB1652DE27EE111B57EC39AA78F7E90-/b2+HYfkarQqUD6E6FAiowdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org>
2018-01-17 14:49                   ` Christian König
2018-01-16 19:40   ` [PATCH 11/21] drm/amdgpu: wire up emit_wreg for UVD v7 Christian König
     [not found]     ` <20180116194017.39067-11-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-01-16 20:05       ` Alex Deucher
     [not found]         ` <CADnq5_MaS1zp4sixq8D5ZdQ-0fheF92k+V=pBYeM1m2PAJFWVQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-01-17 12:46           ` Christian König
2018-01-16 19:40   ` [PATCH 12/21] drm/amdgpu: wire up emit_wreg for VCE v4 Christian König
2018-01-16 19:40   ` [PATCH 13/21] drm/amdgpu: wire up emit_wreg for VCN v1 Christian König
2018-01-16 19:40   ` [PATCH 14/21] drm/amdgpu: add new amdgpu_gmc_emit_flush_gpu_tlb callback Christian König
     [not found]     ` <20180116194017.39067-14-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-01-17  6:24       ` Chunming Zhou
     [not found]         ` <abf156ad-44a7-fe7f-12b0-3c1a77757fbd-5C7GfCeVMHo@public.gmane.org>
2018-01-17 12:19           ` Christian König
     [not found]             ` <2d56c566-9a4d-924e-6542-1e406ce1776a-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-01-18  7:08               ` Chunming Zhou
     [not found]                 ` <db8d7b0d-bb67-e5fe-299e-a334e483bd19-5C7GfCeVMHo@public.gmane.org>
2018-01-18  8:15                   ` Christian König
2018-01-16 19:40   ` [PATCH 15/21] drm/amdgpu: implement gmc_v6_0_emit_flush_gpu_tlb Christian König
2018-01-16 19:40   ` [PATCH 16/21] drm/amdgpu: implement gmc_v7_0_emit_flush_gpu_tlb Christian König
2018-01-16 19:40   ` [PATCH 17/21] drm/amdgpu: implement gmc_v8_0_emit_flush_gpu_tlb Christian König
2018-01-16 19:40   ` [PATCH 18/21] drm/amdgpu: implement gmc_v9_0_emit_flush_gpu_tlb Christian König
2018-01-16 19:40   ` [PATCH 19/21] drm/amdgpu: add PASID mapping for GMC v7 Christian König
2018-01-16 19:40   ` [PATCH 20/21] drm/amdgpu: add PASID mapping for GFX v8 Christian König
2018-01-16 19:40   ` [PATCH 21/21] " Christian König
     [not found]     ` <20180116194017.39067-21-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-01-17  6:11       ` Chunming Zhou [this message]
     [not found]         ` <bd8e530b-869f-2cf9-c5b2-8fce9afd2341-5C7GfCeVMHo@public.gmane.org>
2018-01-17  6:12           ` Chunming Zhou
2018-01-17  6:13           ` Chunming Zhou
     [not found]             ` <4d39da90-bbe3-d704-72b5-b5ee27a41b14-5C7GfCeVMHo@public.gmane.org>
2018-01-17  6:15               ` Chunming Zhou
2018-01-16 20:15   ` [PATCH 01/21] drm/amdgpu: wire up emit_wreg for gfx v6 Alex Deucher
     [not found]     ` <CADnq5_ObVUuxn4GxWmZfY5m6MjfDcZHR-jwGS6cGXa7MbA3NMQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-01-17 13:47       ` Christian König

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=bd8e530b-869f-2cf9-c5b2-8fce9afd2341@amd.com \
    --to=zhoucm1-5c7gfcevmho@public.gmane.org \
    --cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
    --cc=ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox