iov_iter: Introduce nofault flag to disable page faults

Introduce a new nofault flag to indicate to iov_iter_get_pages not to
fault in user pages.

This is implemented by passing the FOLL_NOFAULT flag to get_user_pages,
which causes get_user_pages to fail when it would otherwise fault in a
page. We'll use the ->nofault flag to prevent iomap_dio_rw from faulting
in pages when page faults are not allowed.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

diff --git a/include/linux/uio.h b/include/linux/uio.h
index 25d1c24fd829a4f578370a3d1ec8d7f87fba86f7..6350354f97e90f08b0d64f66c349f9224bc1a2f9 100644 (file)
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -35,6 +35,7 @@ struct iov_iter_state {
 
 struct iov_iter {
        u8 iter_type;
+       bool nofault;
        bool data_source;
        size_t iov_offset;
        size_t count;

diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index ac9a87e727a3224e8431c18123b5fb9d62c02d92..66a740e6e153c4846abef78d54dfcff97e96219c 100644 (file)
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -513,6 +513,7 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction,
        WARN_ON(direction & ~(READ | WRITE));
        *i = (struct iov_iter) {
                .iter_type = ITER_IOVEC,
+               .nofault = false,
                .data_source = direction,
                .iov = iov,
                .nr_segs = nr_segs,
@@ -1527,13 +1528,17 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
                return 0;
 
        if (likely(iter_is_iovec(i))) {
+               unsigned int gup_flags = 0;
                unsigned long addr;
 
+               if (iov_iter_rw(i) != WRITE)
+                       gup_flags |= FOLL_WRITE;
+               if (i->nofault)
+                       gup_flags |= FOLL_NOFAULT;
+
                addr = first_iovec_segment(i, &len, start, maxsize, maxpages);
                n = DIV_ROUND_UP(len, PAGE_SIZE);
-               res = get_user_pages_fast(addr, n,
-                               iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0,
-                               pages);
+               res = get_user_pages_fast(addr, n, gup_flags, pages);
                if (unlikely(res <= 0))
                        return res;
                return (res == n ? len : res * PAGE_SIZE) - *start;
@@ -1649,15 +1654,20 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
                return 0;
 
        if (likely(iter_is_iovec(i))) {
+               unsigned int gup_flags = 0;
                unsigned long addr;
 
+               if (iov_iter_rw(i) != WRITE)
+                       gup_flags |= FOLL_WRITE;
+               if (i->nofault)
+                       gup_flags |= FOLL_NOFAULT;
+
                addr = first_iovec_segment(i, &len, start, maxsize, ~0U);
                n = DIV_ROUND_UP(len, PAGE_SIZE);
                p = get_pages_array(n);
                if (!p)
                        return -ENOMEM;
-               res = get_user_pages_fast(addr, n,
-                               iov_iter_rw(i) != WRITE ?  FOLL_WRITE : 0, p);
+               res = get_user_pages_fast(addr, n, gup_flags, p);
                if (unlikely(res <= 0)) {
                        kvfree(p);
                        *pages = NULL;