On 19.11.2026 16:15, Marek Szyprowski wrote: > arch_dma_prep_coherent() is called by the generic DMA code on pages > which may be located in highmem: dma_direct_alloc() forces the remap > path for a highmem page returned from CMA and calls this hook on it > before creating the uncached mapping. However, the hook has never been > documented and some implementations assume that the page has a kernel > linear mapping. This issue affects MIPS, xtensa and PowerPC. It gets > fixed by patches #2-#5. > > xtensa also only invalidates the cache, which discards the zeroes > written by the dma_direct_alloc(). Patch #1 switches it to a > writeback+invalidate. > > Patch #6 documents that arch_dma_prep_coherent() must write back dirty > lines and must accept highmem pages. With that in place, patch #7 drops > the PageHighMem() check in dma_direct_alloc_no_mapping(), which so far > skipped cache maintenance for highmem CMA pages allocated with > DMA_ATTR_NO_KERNEL_MAPPING. > > Patch #8 makes dma_direct_alloc_no_mapping() always return zeroed > memory, like all other dma_alloc_* paths. Passing __GFP_ZERO is not > enough there, because CMA ignores it. > > The analysis and the patchset was prepared with the help of an LLM. The > code compiles fine, but it has not been runtime tested on any of the > affected architectures yet. Testing on real hardware would be > appreciated. I've reviewed the resulting changes. > > I plan to merge this via my dma-mapping tree, I can provide a tag if > needed for merging it also to arch code. > > Best regards > Marek Szyprowski, PhD > Samsung R&D Institute Poland
MergedĀ into dma-mapping-for-next, with Fixes tag dropped in patch #5 as requested by Ritesh. Here is a stable tag if one needs to merge this patchset also to arch tree: git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux.git tags/no_kernel_mapping_fixes Best regards -- Marek Szyprowski, PhD Samsung R&D Institute Poland
