On Mon, 2021-11-01 at 15:17 +0100, Ard Biesheuvel wrote: > On Mon, 1 Nov 2021 at 13:21, Walter Wu <walter-zh...@mediatek.com> > wrote: > > > > Hi Ard, > > > > On Mon, 2021-11-01 at 09:34 +0100, Ard Biesheuvel wrote: > > > On Mon, 1 Nov 2021 at 04:17, Walter Wu <walter-zh...@mediatek.com > > > > > > > wrote: > > > > > > > > DMA_ATTR_NO_KERNEL_MAPPING is to avoid creating a kernel > > > > mapping > > > > for the allocated buffer, but current implementation is that > > > > PTE of allocated buffer in kernel page table is valid. So we > > > > should set invalid for PTE of allocate buffer so that there are > > > > no kernel mapping for the allocated buffer. > > > > > > > > In some cases, we don't hope the allocated buffer to be read > > > > by cpu or speculative execution, so we use > > > > DMA_ATTR_NO_KERNEL_MAPPING > > > > to get no kernel mapping in order to achieve this goal. > > > > > > > > Signed-off-by: Walter Wu <walter-zh...@mediatek.com> > > > > Cc: Christoph Hellwig <h...@lst.de> > > > > Cc: Marek Szyprowski <m.szyprow...@samsung.com> > > > > Cc: Robin Murphy <robin.mur...@arm.com> > > > > Cc: Matthias Brugger <matthias....@gmail.com> > > > > Cc: Andrew Morton <a...@linux-foundation.org> > > > > --- > > > > kernel/dma/direct.c | 8 ++++++++ > > > > 1 file changed, 8 insertions(+) > > > > > > > > diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c > > > > index 4c6c5e0635e3..aa10b4c5d762 100644 > > > > --- a/kernel/dma/direct.c > > > > +++ b/kernel/dma/direct.c > > > > @@ -13,6 +13,7 @@ > > > > #include <linux/vmalloc.h> > > > > #include <linux/set_memory.h> > > > > #include <linux/slab.h> > > > > +#include <asm/cacheflush.h> > > > > #include "direct.h" > > > > > > > > /* > > > > @@ -169,6 +170,9 @@ void *dma_direct_alloc(struct device *dev, > > > > size_t size, > > > > if (!PageHighMem(page)) > > > > arch_dma_prep_coherent(page, size); > > > > *dma_handle = phys_to_dma_direct(dev, > > > > page_to_phys(page)); > > > > + /* remove kernel mapping for pages */ > > > > + set_memory_valid((unsigned > > > > long)phys_to_virt(dma_to_phys(dev, *dma_handle)), > > > > + size >> PAGE_SHIFT, 0); > > > > > > This only works if the memory is mapped at page granularity in > > > the > > > linear region, and you cannot rely on that. Many architectures > > > prefer > > > block mappings for the linear region, and arm64 will only use > > > page > > > mappings if rodata=full is set (which is set by default but can > > > be > > > overridden on the kernel command line) > > > > > > > We mainly want to solve arm64 arch. > > Solve what?
Our platform is arch64. We need a dynamic allocated buffer from CMA is not to read by CPU peculative execution, so we need to remove its kernel mapping. > > RODATA_FULL_DEFAULT_ENABLED should > > be the arm64 config. If we use CONFIG_RODATA_FULL_DEFAULT_ENABLED > > to > > check whether it call set_memory_valid(). It should avoid other > > architectures. Do you think this method is work? > > > > No. Try it with rodata=off (or rodata=on for that matter) and see > what happens. > I try with rodata=[off/on] on qemu, it looks like boot pass. see below. [ 0.000000] Kernel command line: root=/dev/ram0 rw rootfstype=ext4 rodata=off console=ttyAMA0 rdinit=qemu/ramdisk.img earlyprintk=serial I also try with rodata=off on our platform and do stress test, it looks like pass. Thanks. Walter > > Thanks for your explaination and suggestion. > > > > YW > > > > > > > > > > /* return the page pointer as the opaque cookie > > > > */ > > > > return page; > > > > } > > > > @@ -278,6 +282,10 @@ void dma_direct_free(struct device *dev, > > > > size_t size, > > > > > > > > if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && > > > > !force_dma_unencrypted(dev) && > > > > !is_swiotlb_for_alloc(dev)) { > > > > + size = PAGE_ALIGN(size); > > > > + /* create kernel mapping for pages */ > > > > + set_memory_valid((unsigned > > > > long)phys_to_virt(dma_to_phys(dev, dma_addr)), > > > > + size >> PAGE_SHIFT, 1); > > > > /* cpu_addr is a struct page cookie, not a > > > > kernel > > > > address */ > > > > dma_free_contiguous(dev, cpu_addr, size); > > > > return; > > > > -- > > > > 2.18.0 > > > > > > > > > > > > _______________________________________________ > > > > linux-arm-kernel mailing list > > > > linux-arm-ker...@lists.infradead.org > > > > > > > > https://urldefense.com/v3/__http://lists.infradead.org/mailman/listinfo/linux-arm-kernel__;!!CTRNKA9wMg0ARbw!16dLCjnvtRkaRLeCO9AQ7Fund5XL0FicZmeVaU3-WkFymr-0lbITfzwrvoJpiHlqnqIu-g$ > > > > _______________________________________________ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu