This is used by media/videbuf2 for persistent dma mappings, not just for a single dma operation and then freed again, so needs FOLL_LONGTERM.
Unfortunately current pup_locked doesn't support FOLL_LONGTERM due to locking issues. Rework the code to pull the pup path out from the mmap_sem critical section as suggested by Jason. By relying entirely on the vma checks in pin_user_pages and follow_pfn (for vm_flags and vma_is_fsdax) we can also streamline the code a lot. Note that pin_user_pages_fast is a safe replacement despite the seeming lack of checking for vma->vm_flasg & (VM_IO | VM_PFNMAP). Such ptes are marked with pte_mkspecial (which pup_fast rejects in the fastpath), and only architectures supporting that support the pin_user_pages_fast fastpath. Signed-off-by: Daniel Vetter <daniel.vet...@intel.com> Cc: Christoph Hellwig <h...@infradead.org> Cc: Jason Gunthorpe <j...@ziepe.ca> Cc: Pawel Osciak <pa...@osciak.com> Cc: Marek Szyprowski <m.szyprow...@samsung.com> Cc: Kyungmin Park <kyungmin.p...@samsung.com> Cc: Tomasz Figa <tf...@chromium.org> Cc: Mauro Carvalho Chehab <mche...@kernel.org> Cc: Andrew Morton <a...@linux-foundation.org> Cc: John Hubbard <jhubb...@nvidia.com> Cc: Jérôme Glisse <jgli...@redhat.com> Cc: Jan Kara <j...@suse.cz> Cc: Dan Williams <dan.j.willi...@intel.com> Cc: linux...@kvack.org Cc: linux-arm-ker...@lists.infradead.org Cc: linux-samsung-...@vger.kernel.org Cc: linux-me...@vger.kernel.org Signed-off-by: Daniel Vetter <daniel.vet...@ffwll.ch> -- v2: Streamline the code and further simplify the loop checks (Jason) v5: Review from Tomasz: - fix page counting for the follow_pfn case by resetting ret - drop gup_flags paramater, now unused v6: Explain why pup_fast is safe, after discussions with John and Christoph. --- .../media/common/videobuf2/videobuf2-memops.c | 3 +- include/linux/mm.h | 2 +- mm/frame_vector.c | 53 ++++++------------- 3 files changed, 19 insertions(+), 39 deletions(-) diff --git a/drivers/media/common/videobuf2/videobuf2-memops.c b/drivers/media/common/videobuf2/videobuf2-memops.c index 6e9e05153f4e..9dd6c27162f4 100644 --- a/drivers/media/common/videobuf2/videobuf2-memops.c +++ b/drivers/media/common/videobuf2/videobuf2-memops.c @@ -40,7 +40,6 @@ struct frame_vector *vb2_create_framevec(unsigned long start, unsigned long first, last; unsigned long nr; struct frame_vector *vec; - unsigned int flags = FOLL_FORCE | FOLL_WRITE; first = start >> PAGE_SHIFT; last = (start + length - 1) >> PAGE_SHIFT; @@ -48,7 +47,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start, vec = frame_vector_create(nr); if (!vec) return ERR_PTR(-ENOMEM); - ret = get_vaddr_frames(start & PAGE_MASK, nr, flags, vec); + ret = get_vaddr_frames(start & PAGE_MASK, nr, vec); if (ret < 0) goto out_destroy; /* We accept only complete set of PFNs */ diff --git a/include/linux/mm.h b/include/linux/mm.h index db6ae4d3fb4e..efb8c39bc933 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1765,7 +1765,7 @@ struct frame_vector { struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, - unsigned int gup_flags, struct frame_vector *vec); + struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); diff --git a/mm/frame_vector.c b/mm/frame_vector.c index 10f82d5643b6..f8c34b895c76 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -32,13 +32,12 @@ * This function takes care of grabbing mmap_lock as necessary. */ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, - unsigned int gup_flags, struct frame_vector *vec) + struct frame_vector *vec) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int ret = 0; int err; - int locked; if (nr_frames == 0) return 0; @@ -48,40 +47,26 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, start = untagged_addr(start); - mmap_read_lock(mm); - locked = 1; - vma = find_vma_intersection(mm, start, start + 1); - if (!vma) { - ret = -EFAULT; - goto out; - } - - /* - * While get_vaddr_frames() could be used for transient (kernel - * controlled lifetime) pinning of memory pages all current - * users establish long term (userspace controlled lifetime) - * page pinning. Treat get_vaddr_frames() like - * get_user_pages_longterm() and disallow it for filesystem-dax - * mappings. - */ - if (vma_is_fsdax(vma)) { - ret = -EOPNOTSUPP; - goto out; - } - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { + ret = pin_user_pages_fast(start, nr_frames, + FOLL_FORCE | FOLL_WRITE | FOLL_LONGTERM, + (struct page **)(vec->ptrs)); + if (ret > 0) { vec->got_ref = true; vec->is_pfns = false; - ret = pin_user_pages_locked(start, nr_frames, - gup_flags, (struct page **)(vec->ptrs), &locked); - goto out; + goto out_unlocked; } + mmap_read_lock(mm); vec->got_ref = false; vec->is_pfns = true; + ret = 0; do { unsigned long *nums = frame_vector_pfns(vec); + vma = find_vma_intersection(mm, start, start + 1); + if (!vma) + break; + while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { err = follow_pfn(vma, start, &nums[ret]); if (err) { @@ -92,17 +77,13 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, start += PAGE_SIZE; ret++; } - /* - * We stop if we have enough pages or if VMA doesn't completely - * cover the tail page. - */ - if (ret >= nr_frames || start < vma->vm_end) + /* Bail out if VMA doesn't completely cover the tail page. */ + if (start < vma->vm_end) break; - vma = find_vma_intersection(mm, start, start + 1); - } while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP)); + } while (ret < nr_frames); out: - if (locked) - mmap_read_unlock(mm); + mmap_read_unlock(mm); +out_unlocked: if (!ret) ret = -EFAULT; if (ret > 0) -- 2.29.2