gmc_v10_0_f...pu_tlb_pasid(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’… gmc_v10_0_flush_gpu_tlb_pasid(9) πŸ’…

okay bestie, welcome to the Kernel API Manual ✨ β€” yes this is that one function with the absolutely unhinged truncated name in the header, gmc_v10_0_f...pu_tlb_pasid(9), but the actual full name is right below and it slays πŸ’–


🌸 NAME 🌸

gmc_v10_0_flush_gpu_tlb_pasid β€” tlb flush via pasid πŸŽ€

Like, that's the whole vibe. tlb flush. via pasid. periodt.


⭐ SYNOPSIS ⭐

void gmc_v10_0_flush_gpu_tlb_pasid (struct amdgpu_device *adev ,
uint16_t pasid , uint32_t flush_type , bool all_hub , uint32_t inst );

not me showing you the exact signature character for character because we do NOT play about that πŸ™ˆ copy it exactly, bestie, iykyk.


πŸ¦‹ ARGUMENTS πŸ¦‹

  • adev β€” the amdgpu_device pointer 🫢 your main character, basically.
  • pasid β€” the pasid to be flush πŸ’… yeah that's the original wording and honestly? iconic. it's the pasid getting flushed.
  • flush_type β€” the flush type ✨ like, which kind of flush. the type, of the flush.
  • all_hub β€” used with PACKET3_INVALIDATE_TLBS_ALL_HUB 🌈 that's the literal constant, don't @ me.
  • inst β€” this one's used to select which instance of KIQ you use for the invalidation 🧚 so like, pick your instance. it matters.

πŸ’œ DESCRIPTION πŸ’œ

Flush the TLB for the requested pasid πŸ”₯ that's it. that's the whole thing. no cap, no extra lore, no secret tricks β€” it flushes the TLB for the pasid you asked for and it does it gorgeously. ate. πŸ‘‘


πŸŽ€ SEE ALSO πŸŽ€

the whole friend group πŸ’– go read them too, they're all lowkey important.


reminder bestie: everything above is literally the manpage, just with better vibes 🫢 the facts did NOT change, only the energy did. πŸ’€

and that's the page!! 🌸 brought to you by ./drivers/gpu/drm/amd/amdgpu, dated October 2026, filed under gmc_v10_0_f...pu_tlb_pasid(9) β€” mwah πŸ’‹βœ¨

πŸ“¦ where this page comes from