sdma_v5_2_emit_copy_buffer(9)
π sdma_v5_2_emit_copy_buffer(9) π
okay so bestie, this page is from the Kernel API Manual, and it's all about sdma_v5_2_emit_copy_buffer β the copy-buffer moment for the sDMA engine. no cap, it's giving kernel API realness β¨
β¨ NAME β¨
sdma_v5_2_emit_copy_buffer β copy buffer using the sDMA engine π
π SYNOPSIS π
void sdma_v5_2_emit_copy_buffer (struct amdgpu_ib *ib , uint64_t
src_offset , uint64_t dst_offset , uint32_t byte_count , uint32_t
copy_flags );
π ARGUMENTS π
ibβ the indirect buffer to copy to. that's the destination vibe π«Άsrc_offsetβ src GPU address. literally the source GPU address, bestie πdst_offsetβ dst GPU address. yep, destination GPU address energy π¦byte_countβ number of bytes to xfer. how many bytes are gonna xfer, periodt πΈcopy_flagsβ copy flags for the buffers. the flags that come with the copy, iykyk π
π¦ DESCRIPTION π¦
So this function copies GPU buffers using the DMA engine. it's used by the amdgpu ttm implementation to move pages if it's registered as the asic copy callback. that's the whole main character job, fr fr π₯
π₯ SEE ALSO π₯
Kernel file ./drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c β the source file, iconic π
sdma_v5_2_ring_get_rptr(9)sdma_v5_2_ring_get_wptr(9)sdma_v5_2_ring_set_wptr(9)sdma_v5_2_ring_emit_ib(9)sdma_v5_2_ring_emit_mem_sync(9)sdma_v5_2_ring_emit_hdp_flush(9)sdma_v5_2_ring_emit_fence(9)sdma_v5_2_gfx_stop(9)sdma_v5_2_rlc_stop(9)sdma_v5_2_ctx_switch_enable(9)sdma_v5_2_enable(9)sdma_v5_2_gfx_resume_instance(9)sdma_v5_2_gfx_resume(9)sdma_v5_2_rlc_resume(9)sdma_v5_2_load_microcode(9)sdma_v5_2_start(9)sdma_v5_2_ring_test_ring(9)sdma_v5_2_ring_test_ib(9)sdma_v5_2_vm_copy_pte(9)sdma_v5_2_vm_write_pte(9)sdma_v5_2_vm_set_pte_pde(9)sdma_v5_2_ring_pad_ib(9)sdma_v5_2_ring_emit_pipeline_sync(9)sdma_v5_2_ring_emit_vm_flush(9)sdma_v5_2_emit_fill_buffer(9)
from ./drivers/gpu/drm/amd/amdgpu, dated October 2026 β bye bestie, mwah ππ
π¦ where this page comes from
- nixpkgs unstable: linux-manual 7.3.1
- π girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on : a language model's rewrite of the original, under its terms