arm_iommu_sy...g_for_device(9)
πΈ arm_iommu_sy...g_for_device(9) πΈ
okay bestie, welcome to the Kernel API Manual π 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 β¨
π NAME π
arm_iommu_sync_sg_for_device β and that's literally it, that's the whole name, no description attached π (the manpage said nothing else, so neither will I β no cap, I'm not out here inventing lore π«Ά)
β¨ SYNOPSIS β¨
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 π₯ returns void, takes four things, done. iconic behavior honestly π
π ARGUMENTS π
devβ a validstruct devicepointer, like, it has to actually be valid bestie, don't be out here passing garbage πΈsgβ the list of buffers, i.e. yourscatterlistsituation π¦nentsβ how many buffers you're mapping β and listen, this is the number returned fromdma_map_sg, so don't just make one up πdirβ the DMA transfer direction, and it's gotta be the same one you passed todma_map_sgπ like, matching. consistency. periodt.
fr fr, keep yournentsand yourdirin sync with the originaldma_map_sgcall β the manpage is very much pointing at that and I'm not gonna pretend otherwise π
π§ SEE ALSO π§
it all lives in the kernel file ./arch/arm/mm/dma-mapping.c and the whole friend group is:
arm_iommu_map_sg(9)arm_iommu_unmap_sg(9)arm_iommu_sync_sg_for_cpu(9)arm_iommu_map_phys(9)arm_iommu_create_mapping(9)arm_iommu_attach_device(9)arm_iommu_detach_device(9)
go read the whole squad, iykyk π«
and that's the page!! π 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 ππ mwah, go sync those scatterlists bestie ππ«Ά
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