cik_ih_get_wptr(9)
π cik_ih_get_wptr(9) β the Kernel API Manual, bestie edition π
okay so we're in the Kernel API Manual today and the star of the show is cik_ih_get_wptr(9). she's a little function, she fetches a pointer, she's iconic, no cap. let's get into it π¦
β¨ NAME β¨
cik_ih_get_wptr β get the IH ring buffer wptr π«
πΈ SYNOPSIS πΈ
u32 cik_ih_get_wptr (struct amdgpu_device *adev , struct amdgpu_ih_ring
*ih );
like literally that's the whole signature, copy it exactly bestie, don't be weird about the spacing π«Ά
π ARGUMENTS π
adevβ anamdgpu_devicepointer. yes she's a pointer, yes she's important πihβ the IH ring buffer we're fetching the wptr from. main character energy fr π₯
π₯ DESCRIPTION π₯
okay so what she does: she gets the IH ring buffer wptr from either the register or the writeback memory buffer (CIK). either one, she's flexible like that β¨
and the way that she ALSO checks for ring buffer overflow?? and deals with it?? because she's responsible, she's got her life together, she's not gonna let an overflow just sit there unattended π
she's used by cik_irq_process. iykyk π
and she returns the value of the wptr. that's the whole point, that's her job, she ate π
π¦ SEE ALSO π¦
- Kernel file
./drivers/gpu/drm/amd/amdgpu/cik_ih.cβ the source, go read it, it's giving lore π cik_ih_enable_interrupts(9)cik_ih_disable_interrupts(9)cik_ih_irq_init(9)cik_ih_irq_disable(9)cik_ih_set_rptr(9)
the whole friend group honestly, they all show up together π
ngl, if you're poking at the IH ring buffer and something looks off, it's probably overflow. she checks. she handles it. trust π
and that's the page!! brought to you by ./drivers/gpu/drm/amd/amdgpu, dated October 2026, filed under cik_ih_get_wptr(9) β mwah, go touch some registers bestie πππ§
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