arm_iommu_sy...g_for_device(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

🌸 arm_iommu_sy...g_for_device(9) 🌸

okay bestie, welcome to the Kernel API Manual πŸ’– β€” yes we're reading manpages together now, this is our era, and honestly? this one's short and sweet so you're gonna slay it ✨


πŸ’… NAME πŸ’…

arm_iommu_sync_sg_for_device β€” and that's literally it, that's the whole name, no description attached πŸ™ˆ (the manpage said nothing else, so neither will I β€” no cap, I'm not out here inventing lore 🫢)


✨ SYNOPSIS ✨

void arm_iommu_sync_sg_for_device (struct device *dev , struct
scatterlist *sg , int nents , enum dma_data_direction dir );

that's the whole vibe check right there πŸ”₯ returns void, takes four things, done. iconic behavior honestly πŸ‘‘


πŸŽ€ ARGUMENTS πŸŽ€

  • dev β€” a valid struct device pointer, like, it has to actually be valid bestie, don't be out here passing garbage 🌸
  • sg β€” the list of buffers, i.e. your scatterlist situation πŸ¦‹
  • nents β€” how many buffers you're mapping β€” and listen, this is the number returned from dma_map_sg, so don't just make one up 😭
  • dir β€” the DMA transfer direction, and it's gotta be the same one you passed to dma_map_sg πŸ’€ like, matching. consistency. periodt.
fr fr, keep your nents and your dir in sync with the original dma_map_sg call β€” the manpage is very much pointing at that and I'm not gonna pretend otherwise πŸ’œ

🧚 SEE ALSO 🧚

it all lives in the kernel file ./arch/arm/mm/dma-mapping.c and the whole friend group is:

go read the whole squad, iykyk πŸ’«


and that's the page!! 🌈 sending you off with the cutest little sign-off: this one's filed under ./arch/arm/mm, dated October 2026, and it's from the Kernel API Manual β€” main character documentation energy only πŸ‘‘πŸ’– mwah, go sync those scatterlists bestie πŸŽ€πŸ«Ά

πŸ“¦ where this page comes from