@@ -3175,6 +3175,20 @@ static inline bool vma_is_dax(struct vm_area_struct *vma)
return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}
+static inline bool vma_is_fsdax(struct vm_area_struct *vma)
+{
+ struct inode *inode;
+
+ if (!vma->vm_file)
+ return false;
+ if (!vma_is_dax(vma))
+ return false;
+ inode = file_inode(vma->vm_file);
+ if (inode->i_mode == S_IFCHR)
+ return false; /* device-dax */
+ return true;
+}
+
static inline int iocb_flags(struct file *file)
{
int res = 0;
@@ -1369,6 +1369,19 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
unsigned int gup_flags, struct page **pages, int *locked);
long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
struct page **pages, unsigned int gup_flags);
+#ifdef CONFIG_FS_DAX
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas);
+#else
+static inline long get_user_pages_longterm(unsigned long start,
+ unsigned long nr_pages, unsigned int gup_flags,
+ struct page **pages, struct vm_area_struct **vmas)
+{
+ return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+}
+#endif /* CONFIG_FS_DAX */
+
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
@@ -1095,6 +1095,70 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
}
EXPORT_SYMBOL(get_user_pages);
+#ifdef CONFIG_FS_DAX
+/*
+ * This is the same as get_user_pages() in that it assumes we are
+ * operating on the current task's mm, but it goes further to validate
+ * that the vmas associated with the address range are suitable for
+ * longterm elevated page reference counts. For example, filesystem-dax
+ * mappings are subject to the lifetime enforced by the filesystem and
+ * we need guarantees that longterm users like RDMA and V4L2 only
+ * establish mappings that have a kernel enforced revocation mechanism.
+ *
+ * "longterm" == userspace controlled elevated page count lifetime.
+ * Contrast this to iov_iter_get_pages() usages which are transient.
+ */
+long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ struct vm_area_struct **vmas_arg)
+{
+ struct vm_area_struct **vmas = vmas_arg;
+ struct vm_area_struct *vma_prev = NULL;
+ long rc, i;
+
+ if (!pages)
+ return -EINVAL;
+
+ if (!vmas) {
+ vmas = kzalloc(sizeof(struct vm_area_struct *) * nr_pages,
+ GFP_KERNEL);
+ if (!vmas)
+ return -ENOMEM;
+ }
+
+ rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+
+ for (i = 0; i < rc; i++) {
+ struct vm_area_struct *vma = vmas[i];
+
+ if (vma == vma_prev)
+ continue;
+
+ vma_prev = vma;
+
+ if (vma_is_fsdax(vma))
+ break;
+ }
+
+ /*
+ * Either get_user_pages() failed, or the vma validation
+ * succeeded, in either case we don't need to put_page() before
+ * returning.
+ */
+ if (i >= rc)
+ goto out;
+
+ for (i = 0; i < rc; i++)
+ put_page(pages[i]);
+ rc = -EOPNOTSUPP;
+out:
+ if (vmas != vmas_arg)
+ kfree(vmas);
+ return rc;
+}
+EXPORT_SYMBOL(get_user_pages_longterm);
+#endif /* CONFIG_FS_DAX */
+
/**
* populate_vma_page_range() - populate a range of pages in the vma.
* @vma: target vma
Until there is a solution to the dma-to-dax vs truncate problem it is not safe to allow long standing memory registrations against filesytem-dax vmas. Device-dax vmas do not have this problem and are explicitly allowed. This is temporary until a "memory registration with layout-lease" mechanism can be implemented for the affected sub-systems (RDMA and V4L2). Cc: <stable@vger.kernel.org> Fixes: 3565fce3a659 ("mm, x86: get_user_pages() for dax mappings") Suggested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com> --- include/linux/fs.h | 14 +++++++++++ include/linux/mm.h | 13 +++++++++++ mm/gup.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 91 insertions(+)