Merge tag 'for-6.5/splice-2023-06-23' of git://git.kernel.dk/linux

Pull splice updates from Jens Axboe:
 "This kills off ITER_PIPE to avoid a race between truncate,
  iov_iter_revert() on the pipe and an as-yet incomplete DMA to a bio
  with unpinned/unref'ed pages from an O_DIRECT splice read. This causes
  memory corruption.

  Instead, we either use (a) filemap_splice_read(), which invokes the
  buffered file reading code and splices from the pagecache into the
  pipe; (b) copy_splice_read(), which bulk-allocates a buffer, reads
  into it and then pushes the filled pages into the pipe; or (c) handle
  it in filesystem-specific code.

  Summary:

   - Rename direct_splice_read() to copy_splice_read()

   - Simplify the calculations for the number of pages to be reclaimed
     in copy_splice_read()

   - Turn do_splice_to() into a helper, vfs_splice_read(), so that it
     can be used by overlayfs and coda to perform the checks on the
     lower fs

   - Make vfs_splice_read() jump to copy_splice_read() to handle
     direct-I/O and DAX

   - Provide shmem with its own splice_read to handle non-existent pages
     in the pagecache. We don't want a ->read_folio() as we don't want
     to populate holes, but filemap_get_pages() requires it

   - Provide overlayfs with its own splice_read to call down to a lower
     layer as overlayfs doesn't provide ->read_folio()

   - Provide coda with its own splice_read to call down to a lower layer
     as coda doesn't provide ->read_folio()

   - Direct ->splice_read to copy_splice_read() in tty, procfs, kernfs
     and random files as they just copy to the output buffer and don't
     splice pages

   - Provide wrappers for afs, ceph, ecryptfs, ext4, f2fs, nfs, ntfs3,
     ocfs2, orangefs, xfs and zonefs to do locking and/or revalidation

   - Make cifs use filemap_splice_read()

   - Replace pointers to generic_file_splice_read() with pointers to
     filemap_splice_read() as DIO and DAX are handled in the caller;
     filesystems can still provide their own alternate ->splice_read()
     op

   - Remove generic_file_splice_read()

   - Remove ITER_PIPE and its paraphernalia as generic_file_splice_read
     was the only user"

* tag 'for-6.5/splice-2023-06-23' of git://git.kernel.dk/linux: (31 commits)
  splice: kdoc for filemap_splice_read() and copy_splice_read()
  iov_iter: Kill ITER_PIPE
  splice: Remove generic_file_splice_read()
  splice: Use filemap_splice_read() instead of generic_file_splice_read()
  cifs: Use filemap_splice_read()
  trace: Convert trace/seq to use copy_splice_read()
  zonefs: Provide a splice-read wrapper
  xfs: Provide a splice-read wrapper
  orangefs: Provide a splice-read wrapper
  ocfs2: Provide a splice-read wrapper
  ntfs3: Provide a splice-read wrapper
  nfs: Provide a splice-read wrapper
  f2fs: Provide a splice-read wrapper
  ext4: Provide a splice-read wrapper
  ecryptfs: Provide a splice-read wrapper
  ceph: Provide a splice-read wrapper
  afs: Provide a splice-read wrapper
  9p: Add splice_read wrapper
  net: Make sock_splice_read() use copy_splice_read() by default
  tty, proc, kernfs, random: Use copy_splice_read()
  ...

2 files changed, 157 insertions, 8 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 83dda76d1fc3..00f01d8ead47 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2693,8 +2693,7 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 		if (unlikely(iocb->ki_pos >= i_size_read(inode)))
 			break;
 
-		error = filemap_get_pages(iocb, iter->count, &fbatch,
-					  iov_iter_is_pipe(iter));
+		error = filemap_get_pages(iocb, iter->count, &fbatch, false);
 		if (error < 0)
 			break;
 
@@ -2878,9 +2877,24 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
 	return spliced;
 }
 
-/*
- * Splice folios from the pagecache of a buffered (ie. non-O_DIRECT) file into
- * a pipe.
+/**
+ * filemap_splice_read -  Splice data from a file's pagecache into a pipe
+ * @in: The file to read from
+ * @ppos: Pointer to the file position to read from
+ * @pipe: The pipe to splice into
+ * @len: The amount to splice
+ * @flags: The SPLICE_F_* flags
+ *
+ * This function gets folios from a file's pagecache and splices them into the
+ * pipe.  Readahead will be called as necessary to fill more folios.  This may
+ * be used for blockdevs also.
+ *
+ * Return: On success, the number of bytes read will be returned and *@ppos
+ * will be updated if appropriate; 0 will be returned if there is no more data
+ * to be read; -EAGAIN will be returned if the pipe had no space, and some
+ * other negative error code will be returned on error.  A short read may occur
+ * if the pipe has insufficient space, we reach the end of the data or we hit a
+ * hole.
  */
 ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 			    struct pipe_inode_info *pipe,
@@ -2893,6 +2907,9 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 	bool writably_mapped;
 	int i, error = 0;
 
+	if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes))
+		return 0;
+
 	init_sync_kiocb(&iocb, in);
 	iocb.ki_pos = *ppos;
 
@@ -2906,7 +2923,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 	do {
 		cond_resched();
 
-		if (*ppos >= i_size_read(file_inode(in)))
+		if (*ppos >= i_size_read(in->f_mapping->host))
 			break;
 
 		iocb.ki_pos = *ppos;
@@ -2922,7 +2939,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 		 * part of the page is not copied back to userspace (unless
 		 * another truncate extends the file - this is desired though).
 		 */
-		isize = i_size_read(file_inode(in));
+		isize = i_size_read(in->f_mapping->host);
 		if (unlikely(*ppos >= isize))
 			break;
 		end_offset = min_t(loff_t, isize, *ppos + len);
diff --git a/mm/shmem.c b/mm/shmem.c
index e40a08c5c6d7..1f504ed982cf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2731,6 +2731,138 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return retval ? retval : error;
 }
 
+static bool zero_pipe_buf_get(struct pipe_inode_info *pipe,
+			      struct pipe_buffer *buf)
+{
+	return true;
+}
+
+static void zero_pipe_buf_release(struct pipe_inode_info *pipe,
+				  struct pipe_buffer *buf)
+{
+}
+
+static bool zero_pipe_buf_try_steal(struct pipe_inode_info *pipe,
+				    struct pipe_buffer *buf)
+{
+	return false;
+}
+
+static const struct pipe_buf_operations zero_pipe_buf_ops = {
+	.release	= zero_pipe_buf_release,
+	.try_steal	= zero_pipe_buf_try_steal,
+	.get		= zero_pipe_buf_get,
+};
+
+static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe,
+					loff_t fpos, size_t size)
+{
+	size_t offset = fpos & ~PAGE_MASK;
+
+	size = min_t(size_t, size, PAGE_SIZE - offset);
+
+	if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+		struct pipe_buffer *buf = pipe_head_buf(pipe);
+
+		*buf = (struct pipe_buffer) {
+			.ops	= &zero_pipe_buf_ops,
+			.page	= ZERO_PAGE(0),
+			.offset	= offset,
+			.len	= size,
+		};
+		pipe->head++;
+	}
+
+	return size;
+}
+
+static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
+				      struct pipe_inode_info *pipe,
+				      size_t len, unsigned int flags)
+{
+	struct inode *inode = file_inode(in);
+	struct address_space *mapping = inode->i_mapping;
+	struct folio *folio = NULL;
+	size_t total_spliced = 0, used, npages, n, part;
+	loff_t isize;
+	int error = 0;
+
+	/* Work out how much data we can actually add into the pipe */
+	used = pipe_occupancy(pipe->head, pipe->tail);
+	npages = max_t(ssize_t, pipe->max_usage - used, 0);
+	len = min_t(size_t, len, npages * PAGE_SIZE);
+
+	do {
+		if (*ppos >= i_size_read(inode))
+			break;
+
+		error = shmem_get_folio(inode, *ppos / PAGE_SIZE, &folio, SGP_READ);
+		if (error) {
+			if (error == -EINVAL)
+				error = 0;
+			break;
+		}
+		if (folio) {
+			folio_unlock(folio);
+
+			if (folio_test_hwpoison(folio)) {
+				error = -EIO;
+				break;
+			}
+		}
+
+		/*
+		 * i_size must be checked after we know the pages are Uptodate.
+		 *
+		 * Checking i_size after the check allows us to calculate
+		 * the correct value for "nr", which means the zero-filled
+		 * part of the page is not copied back to userspace (unless
+		 * another truncate extends the file - this is desired though).
+		 */
+		isize = i_size_read(inode);
+		if (unlikely(*ppos >= isize))
+			break;
+		part = min_t(loff_t, isize - *ppos, len);
+
+		if (folio) {
+			/*
+			 * If users can be writing to this page using arbitrary
+			 * virtual addresses, take care about potential aliasing
+			 * before reading the page on the kernel side.
+			 */
+			if (mapping_writably_mapped(mapping))
+				flush_dcache_folio(folio);
+			folio_mark_accessed(folio);
+			/*
+			 * Ok, we have the page, and it's up-to-date, so we can
+			 * now splice it into the pipe.
+			 */
+			n = splice_folio_into_pipe(pipe, folio, *ppos, part);
+			folio_put(folio);
+			folio = NULL;
+		} else {
+			n = splice_zeropage_into_pipe(pipe, *ppos, len);
+		}
+
+		if (!n)
+			break;
+		len -= n;
+		total_spliced += n;
+		*ppos += n;
+		in->f_ra.prev_pos = *ppos;
+		if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+			break;
+
+		cond_resched();
+	} while (len);
+
+	if (folio)
+		folio_put(folio);
+
+	file_accessed(in);
+	return total_spliced ? total_spliced : error;
+}
+
 static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct address_space *mapping = file->f_mapping;
@@ -3971,7 +4103,7 @@ static const struct file_operations shmem_file_operations = {
 	.read_iter	= shmem_file_read_iter,
 	.write_iter	= generic_file_write_iter,
 	.fsync		= noop_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= shmem_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= shmem_fallocate,
 #endif