dma_need_unmap(9)
π
dma_need_unmap β like, does this device even need dma_unmap_*?? π
okay bestie, welcome to the Kernel API Manual β¨ β this one's short and sweet, but it's important, so pay attention π«Ά
β¨ NAME β¨
dma_need_unmap β does this device need dma_unmap_* operations π
π¦ SYNOPSIS π¦
bool dma_need_unmap (struct device *dev );
π ARGUMENTS π
devβ the device to check π like, the one you're wondering about
π DESCRIPTION π
so here's the tea β β if this function returns false, drivers can skip calling dma_unmap_* after finishing an I/O. literally just don't bother, it's giving "no notes" π
β οΈ but listen β this function must be called after all mappings that might need to be unmapped have been performed. like, all of them. order matters, bestie, don't come for me π
ngl that's the whole vibe: check first, then decide whether the unmap era is even happening πΈ
π SEE ALSO π
./kernel/dma/mapping.cβ the source file, the main character π§dmam_free_coherent(9)dmam_alloc_attrs(9)dma_map_sg_attrs(9)dma_map_sgtable(9)dma_can_mmap(9)dma_mmap_attrs(9)dma_addressing_limited(9)
all of these? obsessed. go read them, iykyk π₯
and that's the whole page, bestie π this little gem lives in ./kernel/dma and the version/date stamp on it is October 2026 β so yeah, it's basically brand new, slay πβ¨
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