[PATCH v2 5/7] io_uring: rsrc: use FOLL_SAME_FILE on pin_user_pages()

From: Lorenzo Stoakes
Date: Sat Apr 15 2023 - 05:09:13 EST


Commit edd478269640 ("io_uring/rsrc: disallow multi-source reg buffers")
prevents io_pin_pages() from pinning pages spanning multiple VMAs with
permitted characteristics (anon/huge), requiring that all VMAs share the
same vm_file.

The newly introduced FOLL_SAME_FILE flag permits this to be expressed as a
GUP flag rather than having to retrieve VMAs to perform the check.

We then only need to perform a VMA lookup for the first VMA to assert the
anon/hugepage requirement as we know the rest of the VMAs will possess the
same characteristics.

Doing this eliminates the one instance of vmas being used by
pin_user_pages().

Signed-off-by: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Suggested-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
io_uring/rsrc.c | 39 ++++++++++++++++-----------------------
1 file changed, 16 insertions(+), 23 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 7a43aed8e395..adc860bcbd4f 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1141,9 +1141,8 @@ static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages,
struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages)
{
unsigned long start, end, nr_pages;
- struct vm_area_struct **vmas = NULL;
struct page **pages = NULL;
- int i, pret, ret = -ENOMEM;
+ int pret, ret = -ENOMEM;

end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
start = ubuf >> PAGE_SHIFT;
@@ -1153,31 +1152,26 @@ struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages)
if (!pages)
goto done;

- vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!vmas)
- goto done;
-
ret = 0;
mmap_read_lock(current->mm);
- pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
- pages, vmas);
+
+ pret = pin_user_pages(ubuf, nr_pages,
+ FOLL_WRITE | FOLL_LONGTERM | FOLL_SAME_FILE,
+ pages, NULL);
if (pret == nr_pages) {
- struct file *file = vmas[0]->vm_file;
+ /*
+ * lookup the first VMA, we require that all VMAs in range
+ * maintain the same file characteristics, as enforced by
+ * FOLL_SAME_FILE
+ */
+ struct vm_area_struct *vma = vma_lookup(current->mm, ubuf);
+ struct file *file;

/* don't support file backed memory */
- for (i = 0; i < nr_pages; i++) {
- if (vmas[i]->vm_file != file) {
- ret = -EINVAL;
- break;
- }
- if (!file)
- continue;
- if (!vma_is_shmem(vmas[i]) && !is_file_hugepages(file)) {
- ret = -EOPNOTSUPP;
- break;
- }
- }
+ file = vma->vm_file;
+ if (file && !vma_is_shmem(vma) && !is_file_hugepages(file))
+ ret = -EOPNOTSUPP;
+
*npages = nr_pages;
} else {
ret = pret < 0 ? pret : -EFAULT;
@@ -1194,7 +1188,6 @@ struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages)
}
ret = 0;
done:
- kvfree(vmas);
if (ret < 0) {
kvfree(pages);
pages = ERR_PTR(ret);
--
2.40.0