@@ -580,25 +580,30 @@ static long privcmd_ioctl_mmap_batch(
static int lock_pages(
struct privcmd_dm_op_buf kbufs[], unsigned int num,
- struct page *pages[], unsigned int nr_pages)
+ struct page *pages[], unsigned int nr_pages, int *errno)
{
unsigned int i;
+ int pinned = 0, rc = 0;
for (i = 0; i < num; i++) {
unsigned int requested;
- int pinned;
+ rc += pinned;
requested = DIV_ROUND_UP(
offset_in_page(kbufs[i].uptr) + kbufs[i].size,
PAGE_SIZE);
- if (requested > nr_pages)
- return -ENOSPC;
+ if (requested > nr_pages) {
+ *errno = -ENOSPC;
+ return rc;
+ }
- pinned = get_user_pages_fast(
+ pinned = pin_user_pages_fast(
(unsigned long) kbufs[i].uptr,
requested, FOLL_WRITE, pages);
- if (pinned < 0)
- return pinned;
+ if (pinned < 0) {
+ *errno = pinned;
+ return rc;
+ }
nr_pages -= pinned;
pages += pinned;
@@ -613,11 +618,7 @@ static void unlock_pages(struct page *pages[], unsigned int nr_pages)
if (!pages)
return;
-
- for (i = 0; i < nr_pages; i++) {
- if (pages[i])
- put_page(pages[i]);
- }
+ unpin_user_pages_dirty_lock(pages, nr_pages, 1);
}
static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
@@ -630,6 +631,7 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
struct xen_dm_op_buf *xbufs = NULL;
unsigned int i;
long rc;
+ int errno = 0;
if (copy_from_user(&kdata, udata, sizeof(kdata)))
return -EFAULT;
@@ -683,9 +685,12 @@ static long privcmd_ioctl_dm_op(struct file *file, void __user *udata)
goto out;
}
- rc = lock_pages(kbufs, kdata.num, pages, nr_pages);
- if (rc)
+ rc = lock_pages(kbufs, kdata.num, pages, nr_pages, &errno);
+ if (errno < 0) {
+ nr_pages = rc;
+ rc = errno;
goto out;
+ }
for (i = 0; i < kdata.num; i++) {
set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
In 2019, we introduced pin_user_pages*() and now we are converting get_user_pages*() to the new API as appropriate. [1] & [2] could be referred for more information. This is case 5 as per document [1]. As discussed, pages need to be marked as dirty before unpinned it. Previously, if lock_pages() end up partially mapping pages, it used to return -ERRNO due to which unlock_pages() have to go through each pages[i] till *nr_pages* to validate them. This can be avoided by passing correct number partially mapped pages & -ERRNO separately while returning from lock_pages() due to error. With this fix unlock_pages() doesn't need to validate pages[i] till *nr_pages* for error scenario. [1] Documentation/core-api/pin_user_pages.rst [2] "Explicit pinning of user-space pages": https://lwn.net/Articles/807108/ Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> --- drivers/xen/privcmd.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-)