Re: [PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content

2024-06-17 Thread Icenowy Zheng
在 2024-06-17星期一的 15:59 +0200,Christian König写道: > Am 17.06.24 um 15:43 schrieb Icenowy Zheng: > > 在 2024-06-17星期一的 15:09 +0200,Christian König写道: > > > Am 17.06.24 um 15:03 schrieb Icenowy Zheng: > > > > 在 2024-06-17星期一的 14:35 +0200,Christian König写道: > > > &

Re: [PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content

2024-06-17 Thread Icenowy Zheng
在 2024-06-17星期一的 16:42 +0200,Christian König写道: > Am 17.06.24 um 16:30 schrieb Icenowy Zheng: > > 在 2024-06-17星期一的 15:59 +0200,Christian König写道: > > > Am 17.06.24 um 15:43 schrieb Icenowy Zheng: > > > > 在 2024-06-17星期一的 15:09 +0200,Christian König写道: > > > &

Re: [PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content

2024-06-17 Thread Icenowy Zheng
在 2024-06-17星期一的 15:59 +0200,Christian König写道: > Am 17.06.24 um 15:43 schrieb Icenowy Zheng: > > 在 2024-06-17星期一的 15:09 +0200,Christian König写道: > > > Am 17.06.24 um 15:03 schrieb Icenowy Zheng: > > > > 在 2024-06-17星期一的 14:35 +0200,Christian König写道: > > > &

Re: [PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content

2024-06-17 Thread Icenowy Zheng
在 2024-06-17星期一的 15:09 +0200,Christian König写道: > Am 17.06.24 um 15:03 schrieb Icenowy Zheng: > > 在 2024-06-17星期一的 14:35 +0200,Christian König写道: > > > Am 17.06.24 um 12:58 schrieb Icenowy Zheng: > > > > The duplication of EOP packets for GFX7/8, with the former

Re: [PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content

2024-06-17 Thread Icenowy Zheng
在 2024-06-17星期一的 14:35 +0200,Christian König写道: > Am 17.06.24 um 12:58 schrieb Icenowy Zheng: > > The duplication of EOP packets for GFX7/8, with the former one have > > seq-1 written and the latter one have seq written, seems to confuse > > some > > hardware platform (e

[PATCH 2/2] drm/radeon: repeat the same EOP packet for EOP workaround on CIK

2024-06-17 Thread Icenowy Zheng
Ths first EOP packet with a sequence number as seq-1 seems to confuse some PCIe hardware (e.g. Loongson 7A PCHs). Use the real sequence number instead. Fixes: a9c73a0e022c ("drm/radeon: workaround for CP HW bug on CIK") Signed-off-by: Icenowy Zheng --- drivers/gpu/drm/radeon

[PATCH 1/2] drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content

2024-06-17 Thread Icenowy Zheng
possible interrupts. Fixes: bf26da927a1c ("drm/amdgpu: add cache flush workaround to gfx8 emit_fence") Fixes: a2e73f56fa62 ("drm/amdgpu: Add support for CIK parts") Signed-off-by: Icenowy Zheng --- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 12 +--- drivers/gpu/drm/amd/am

[PATCH 0/2] Fixes of AMD GFX7/8 hang on Loongson platforms

2024-06-17 Thread Icenowy Zheng
This patchset tries to fix some workaround code in amdgpu/radeon driver, that makes Loongson 3A+7A platform suffering from GPU crashes. Icenowy Zheng (2): drm/amdgpu: make duplicated EOP packet for GFX7/8 have real content drm/radeon: repeat the same EOP packet for EOP workaround on CIK

[PATCH] drm/amdgpu: fix SI failure due to doorbells allocation

2023-10-08 Thread Icenowy Zheng
t;) Signed-off-by: Icenowy Zheng --- drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c | 4 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c index d0249ada91d30..599aece42017a 100644 --- a/drive