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, 43 insertions, 3 deletions

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index b173c36bcab3..91a194596552 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2558,7 +2558,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	 *
 	 * Take and drop the meta data lock to update inode fields
 	 * like i_size. This allows the checks down below
-	 * generic_file_read_iter() a chance of actually working.
+	 * copy_splice_read() a chance of actually working.
 	 */
 	ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level,
 				     !nowait);
@@ -2587,6 +2587,43 @@ bail:
 	return ret;
 }
 
+static ssize_t ocfs2_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);
+	ssize_t ret = 0;
+	int lock_level = 0;
+
+	trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry,
+				     (unsigned long long)OCFS2_I(inode)->ip_blkno,
+				     in->f_path.dentry->d_name.len,
+				     in->f_path.dentry->d_name.name,
+				     flags);
+
+	/*
+	 * We're fine letting folks race truncates and extending writes with
+	 * read across the cluster, just like they can locally.  Hence no
+	 * rw_lock during read.
+	 *
+	 * Take and drop the meta data lock to update inode fields like i_size.
+	 * This allows the checks down below filemap_splice_read() a chance of
+	 * actually working.
+	 */
+	ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level, 1);
+	if (ret < 0) {
+		if (ret != -EAGAIN)
+			mlog_errno(ret);
+		goto bail;
+	}
+	ocfs2_inode_unlock(inode, lock_level);
+
+	ret = filemap_splice_read(in, ppos, pipe, len, flags);
+	trace_filemap_splice_read_ret(ret);
+bail:
+	return ret;
+}
+
 /* Refer generic_file_llseek_unlocked() */
 static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
 {
@@ -2750,7 +2787,7 @@ const struct file_operations ocfs2_fops = {
 #endif
 	.lock		= ocfs2_lock,
 	.flock		= ocfs2_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= ocfs2_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 	.remap_file_range = ocfs2_remap_file_range,
@@ -2796,7 +2833,7 @@ const struct file_operations ocfs2_fops_no_plocks = {
 	.compat_ioctl   = ocfs2_compat_ioctl,
 #endif
 	.flock		= ocfs2_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= filemap_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 	.remap_file_range = ocfs2_remap_file_range,
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index dc4bce1649c1..b8c3d1702076 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1319,6 +1319,8 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter);
 
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_read);
+
 DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file);
 
 DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_truncate_file_error);
@@ -1470,6 +1472,7 @@ TRACE_EVENT(ocfs2_prepare_inode_for_write,
 );
 
 DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret);
+DEFINE_OCFS2_INT_EVENT(filemap_splice_read_ret);
 
 /* End of trace events for fs/ocfs2/file.c. */