On Thu, Sep 24, 2020 at 03:39:53PM -0300, Jason Gunthorpe wrote: > On Thu, Sep 24, 2020 at 02:34:18PM -0400, Peter Xu wrote: > > > > > // RDONLY gup > > > > pin_user_pages(buf, !WRITE); > > > > // pte of buf duplicated on both sides > > > > fork(); > > > > mprotect(buf, WRITE); > > > > *buf = 1; > > > > // buf page replaced as cow triggered > > > > > > > > Currently when fork() we'll happily share a pinned read-only page with the > > > > child by copying the pte directly. > > > > > > Why? This series prevents that, the page will be maybe_dma_pinned, so > > > fork() will copy it. > > > > With the extra mprotect(!WRITE), I think we'll see a !pte_write() entry. Then > > it'll not go into maybe_dma_pinned() at all since cow==false. > > Hum that seems like a problem in this patch, we still need to do the > DMA pinned logic even if the pte is already write protected. Yes I agree. I'll take care of that in the next version too. -- Peter Xu
