diff mbox series

[v8,05/17] iov_iter: Introduce fault_in_iov_iter_writeable

Message ID 20211019134204.3382645-6-agruenba@redhat.com (mailing list archive)
State New, archived
Headers show
Series gfs2: Fix mmap + page fault deadlocks | expand

Commit Message

Andreas Gruenbacher Oct. 19, 2021, 1:41 p.m. UTC
Introduce a new fault_in_iov_iter_writeable helper for safely faulting
in an iterator for writing.  Uses get_user_pages() to fault in the pages
without actually writing to them, which would be destructive.

We'll use fault_in_iov_iter_writeable in gfs2 once we've determined that
the iterator passed to .read_iter isn't in memory.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 include/linux/pagemap.h |  1 +
 include/linux/uio.h     |  1 +
 lib/iov_iter.c          | 39 +++++++++++++++++++++++++
 mm/gup.c                | 63 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 104 insertions(+)

Comments

Catalin Marinas Oct. 20, 2021, 4:25 p.m. UTC | #1
On Tue, Oct 19, 2021 at 03:41:52PM +0200, Andreas Gruenbacher wrote:
> diff --git a/mm/gup.c b/mm/gup.c
> index a7efb027d6cf..614b8536b3b6 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -1691,6 +1691,69 @@ size_t fault_in_writeable(char __user *uaddr, size_t size)
>  }
>  EXPORT_SYMBOL(fault_in_writeable);
>  
> +/*
> + * fault_in_safe_writeable - fault in an address range for writing
> + * @uaddr: start of address range
> + * @size: length of address range
> + *
> + * Faults in an address range using get_user_pages, i.e., without triggering
> + * hardware page faults.  This is primarily useful when we already know that
> + * some or all of the pages in the address range aren't in memory.
> + *
> + * Other than fault_in_writeable(), this function is non-destructive.
> + *
> + * Note that we don't pin or otherwise hold the pages referenced that we fault
> + * in.  There's no guarantee that they'll stay in memory for any duration of
> + * time.
> + *
> + * Returns the number of bytes not faulted in, like copy_to_user() and
> + * copy_from_user().
> + */
> +size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
> +{
> +	unsigned long start = (unsigned long)uaddr;
> +	unsigned long end, nstart, nend;
> +	struct mm_struct *mm = current->mm;
> +	struct vm_area_struct *vma = NULL;

For arm64 tagged addresses we need the diff below, otherwise the
subsequent find_vma() will fail:

diff --git a/mm/gup.c b/mm/gup.c
index f5f362cb4640..2c51e9748a6a 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1713,7 +1713,7 @@ EXPORT_SYMBOL(fault_in_writeable);
  */
 size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
 {
-	unsigned long start = (unsigned long)uaddr;
+	unsigned long start = (unsigned long)untagged_addr(uaddr);
 	unsigned long end, nstart, nend;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma = NULL;
diff mbox series

Patch

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 9fe94f7a4f7e..2f7dd14083d9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -736,6 +736,7 @@  extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
  * Fault in userspace address range.
  */
 size_t fault_in_writeable(char __user *uaddr, size_t size);
+size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
 size_t fault_in_readable(const char __user *uaddr, size_t size);
 
 int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
diff --git a/include/linux/uio.h b/include/linux/uio.h
index d18458af6681..25d1c24fd829 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -134,6 +134,7 @@  size_t copy_page_from_iter_atomic(struct page *page, unsigned offset,
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 void iov_iter_revert(struct iov_iter *i, size_t bytes);
 size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
+size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index ce3d4f610626..ac9a87e727a3 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -467,6 +467,45 @@  size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size)
 }
 EXPORT_SYMBOL(fault_in_iov_iter_readable);
 
+/*
+ * fault_in_iov_iter_writeable - fault in iov iterator for writing
+ * @i: iterator
+ * @size: maximum length
+ *
+ * Faults in the iterator using get_user_pages(), i.e., without triggering
+ * hardware page faults.  This is primarily useful when we already know that
+ * some or all of the pages in @i aren't in memory.
+ *
+ * Returns the number of bytes not faulted in, like copy_to_user() and
+ * copy_from_user().
+ *
+ * Always returns 0 for non-user-space iterators.
+ */
+size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size)
+{
+	if (iter_is_iovec(i)) {
+		size_t count = min(size, iov_iter_count(i));
+		const struct iovec *p;
+		size_t skip;
+
+		size -= count;
+		for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) {
+			size_t len = min(count, p->iov_len - skip);
+			size_t ret;
+
+			if (unlikely(!len))
+				continue;
+			ret = fault_in_safe_writeable(p->iov_base + skip, len);
+			count -= len - ret;
+			if (ret)
+				break;
+		}
+		return count + size;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(fault_in_iov_iter_writeable);
+
 void iov_iter_init(struct iov_iter *i, unsigned int direction,
 			const struct iovec *iov, unsigned long nr_segs,
 			size_t count)
diff --git a/mm/gup.c b/mm/gup.c
index a7efb027d6cf..614b8536b3b6 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1691,6 +1691,69 @@  size_t fault_in_writeable(char __user *uaddr, size_t size)
 }
 EXPORT_SYMBOL(fault_in_writeable);
 
+/*
+ * fault_in_safe_writeable - fault in an address range for writing
+ * @uaddr: start of address range
+ * @size: length of address range
+ *
+ * Faults in an address range using get_user_pages, i.e., without triggering
+ * hardware page faults.  This is primarily useful when we already know that
+ * some or all of the pages in the address range aren't in memory.
+ *
+ * Other than fault_in_writeable(), this function is non-destructive.
+ *
+ * Note that we don't pin or otherwise hold the pages referenced that we fault
+ * in.  There's no guarantee that they'll stay in memory for any duration of
+ * time.
+ *
+ * Returns the number of bytes not faulted in, like copy_to_user() and
+ * copy_from_user().
+ */
+size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
+{
+	unsigned long start = (unsigned long)uaddr;
+	unsigned long end, nstart, nend;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma = NULL;
+	int locked = 0;
+
+	nstart = start & PAGE_MASK;
+	end = PAGE_ALIGN(start + size);
+	if (end < nstart)
+		end = 0;
+	for (; nstart != end; nstart = nend) {
+		unsigned long nr_pages;
+		long ret;
+
+		if (!locked) {
+			locked = 1;
+			mmap_read_lock(mm);
+			vma = find_vma(mm, nstart);
+		} else if (nstart >= vma->vm_end)
+			vma = vma->vm_next;
+		if (!vma || vma->vm_start >= end)
+			break;
+		nend = end ? min(end, vma->vm_end) : vma->vm_end;
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+			continue;
+		if (nstart < vma->vm_start)
+			nstart = vma->vm_start;
+		nr_pages = (nend - nstart) / PAGE_SIZE;
+		ret = __get_user_pages_locked(mm, nstart, nr_pages,
+					      NULL, NULL, &locked,
+					      FOLL_TOUCH | FOLL_WRITE);
+		if (ret <= 0)
+			break;
+		nend = nstart + ret * PAGE_SIZE;
+	}
+	if (locked)
+		mmap_read_unlock(mm);
+	if (nstart == end)
+		return 0;
+	return size - min_t(size_t, nstart - start, size);
+}
+EXPORT_SYMBOL(fault_in_safe_writeable);
+
 /**
  * fault_in_readable - fault in userspace address range for reading
  * @uaddr: start of user address range