sdma_v6_0_gfx_stop(9)

📦 version 7.3.1, in nixpkgs unstable

💖 sdma_v6_0_gfx_stop(9) — the kernel API manual, but make it make sense 💖

okay so bestie, welcome to the sdma_v6_0_gfx_stop(9) page from the Kernel API Manual ✨ this is the one that stops the gfx async dma engines — like, the whole entire point. and yes, we're getting into it. no cap.

🌸 NAME 🌸

sdma_v6_0_gfx_stop — stop the gfx async dma engines 🛑

like. that's it. that's the job. it stops them. slay.

✨ SYNOPSIS ✨

void sdma_v6_0_gfx_stop (struct amdgpu_device *adev );

(it returns void, so don't come looking for a return value, she gives you nothing back and she's iconic for it 💅)

🎀 ARGUMENTS 🎀

  • adev — an amdgpu_device pointer 🫶 that's the one and only thing you hand her. one (1) argument, very low maintenance, we love a low-effort queen.

🦋 DESCRIPTION 🦋

so what does she actually do? she stops the gfx async dma ring buffers 💀 that's the whole description. straightforward. to the point. no filler, no fluff, no three-paragraph lore drop. she stops the ring buffers and she moves on. periodt.

ngl this is one of those "does exactly what it says on the tin" functions — and honestly? respect. 🫡

🔥 SEE ALSO 🔥

the kernel file where all the magic lives, no cap:

  • ./drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c ⭐

and the whole entire friend group — every single one of these, not skipping a single bestie 😭:

note the gfx_stop / gfx_resume situation — she's got a counterpart and they're giving main character energy from opposite ends of the lifecycle 💀 don't @ me.

and that's the page, bestie!! 🎀✨ this lil masterpiece lives in ./drivers/gpu/drm/amd/amdgpu, dated October 2026, and it's literally sdma_v6_0_gfx_stop(9) through and through 💖 go stop some async dma engines, you absolute icon 👑🦋

📦 where this page comes from