linux/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c, branch v6.3

Merge tag 'drm-misc-next-2022-11-10-1' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

2022-11-15T21:17:32Z

drm-misc-next for 6.2: UAPI Changes: Cross-subsystem Changes: Core Changes: - atomic-helper: Add begin_fb_access and end_fb_access hooks - fb-helper: Rework to move fb emulation into helpers - scheduler: rework entity flush, kill and fini - ttm: Optimize pool allocations Driver Changes: - amdgpu: scheduler rework - hdlcd: Switch to DRM-managed resources - ingenic: Fix registration error path - lcdif: FIFO threshold tuning - meson: Fix return type of cvbs' mode_valid - ofdrm: multiple fixes (kconfig, types, endianness) - sun4i: A100 and D1 support - panel: - New Panel: Jadard JD9365DA-H3 Signed-off-by: Dave Airlie From: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20221110083612.g63eaocoaa554soh@houat

Merge drm/drm-next into drm-misc-next

2022-11-05T15:08:36Z

Backmerging drm/drm-next to get the latest changes in the xlnx driver. Signed-off-by: Thomas Zimmermann

drm/amdgpu: cleanup scheduler job initialization v2

2022-11-03T11:45:20Z

Init the DRM scheduler base class while allocating the job. This makes the whole handling much more cleaner. v2: fix coding style Signed-off-by: Christian König Reviewed-by: Luben Tuikov Link: https://patchwork.freedesktop.org/patch/msgid/20221014084641.128280-7-christian.koenig@amd.com

drm/amdkfd: Cleanup kfd_dev struct

2022-10-27T19:12:09Z

Cleanup kfd_dev struct by removing ddev and pdev as both drm_device and pci_dev can be fetched from amdgpu_device. Signed-off-by: Mukul Joshi Tested-by: Amber Lin Reviewed-by: Felix Kuehling Acked-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: disable GFXOFF during compute for GFX11

2022-10-27T19:12:09Z

Temporary workaround to fix issues observed in some compute applications when GFXOFF is enabled on GFX11. Signed-off-by: Graham Sider Acked-by: Alex Deucher Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher

drm/amdgpu: remove ras_error_status parameter for UMC poison handler

2022-10-27T19:12:08Z

Make the code simpler. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher

Revert "drm/amdgpu: let mode2 reset fallback to default when failure"

2022-10-19T02:08:33Z

This reverts commit dac6b80818ac2353631c5a33d140d8d5508e2957. This commit reverted the AMDGPU_SKIP_MODE2_RESET as it conflicts with the original design of reset handler. Will redesign it. Fixes: dac6b80818ac23 ("drm/amdgpu: let mode2 reset fallback to default when failure") Signed-off-by: Victor Zhao Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher

Revert "drm/amdgpu: let mode2 reset fallback to default when failure"

2022-10-17T21:41:20Z

drm/amdgpu: Correct amdgpu_amdkfd_total_mem_size calculation

2022-10-06T16:08:18Z

amdkfd_total_mem_size is the size of total GPUs vram plus system memory to estimate page tables memory usage and leave enough VRAM room for page tables allocation. Calculate amdkfd_total_mem_size in amdgpu_amdkfd_device_probe is incorrect because adev->gmc.real_vram_size is still 0 called from amdgpu_device_ip_early_init. Move the calculation to amdgpu_amdkfd_device_init to get the correct VRAM size. Do reverse calculation in amdgpu_amdkfd_device_fini_sw to support hot-unplugging GPUs. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdgpu: add page retirement handling for CPU RAS

2022-09-29T13:42:36Z

Do RAS page retirement in poison consumption handler unconditionally. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher