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()
  ...

3 files changed, 25 insertions, 2 deletions

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index f0edf5a36237..3855f3ce8d2d 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -178,6 +178,27 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 }
 EXPORT_SYMBOL_GPL(nfs_file_read);
 
+ssize_t
+nfs_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 result;
+
+	dprintk("NFS: splice_read(%pD2, %zu@%llu)\n", in, len, *ppos);
+
+	nfs_start_io_read(inode);
+	result = nfs_revalidate_mapping(inode, in->f_mapping);
+	if (!result) {
+		result = filemap_splice_read(in, ppos, pipe, len, flags);
+		if (result > 0)
+			nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
+	}
+	nfs_end_io_read(inode);
+	return result;
+}
+EXPORT_SYMBOL_GPL(nfs_file_splice_read);
+
 int
 nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 {
@@ -879,7 +900,7 @@ const struct file_operations nfs_file_operations = {
 	.fsync		= nfs_file_fsync,
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 3cc027d3bd58..b5f21d35d30e 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -416,6 +416,8 @@ static inline __u32 nfs_access_xattr_mask(const struct nfs_server *server)
 int nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync);
 loff_t nfs_file_llseek(struct file *, loff_t, int);
 ssize_t nfs_file_read(struct kiocb *, struct iov_iter *);
+ssize_t nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe,
+			     size_t len, unsigned int flags);
 int nfs_file_mmap(struct file *, struct vm_area_struct *);
 ssize_t nfs_file_write(struct kiocb *, struct iov_iter *);
 int nfs_file_release(struct inode *, struct file *);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 2563ed8580f3..4aeadd6e1a6d 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -454,7 +454,7 @@ const struct file_operations nfs4_file_operations = {
 	.fsync		= nfs_file_fsync,
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= nfs_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= nfs4_setlease,