Merge branch 'work.splice_read' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull VFS splice updates from Al Viro:
 "There's a bunch of branches this cycle, both mine and from other folks
  and I'd rather send pull requests separately.

  This one is the conversion of ->splice_read() to ITER_PIPE iov_iter
  (and introduction of such). Gets rid of a lot of code in fs/splice.c
  and elsewhere; there will be followups, but these are for the next
  cycle...  Some pipe/splice-related cleanups from Miklos in the same
  branch as well"

* 'work.splice_read' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  pipe: fix comment in pipe_buf_operations
  pipe: add pipe_buf_steal() helper
  pipe: add pipe_buf_confirm() helper
  pipe: add pipe_buf_release() helper
  pipe: add pipe_buf_get() helper
  relay: simplify relay_file_read()
  switch default_file_splice_read() to use of pipe-backed iov_iter
  switch generic_file_splice_read() to use of ->read_iter()
  new iov_iter flavour: pipe-backed
  fuse_dev_splice_read(): switch to add_to_pipe()
  skb_splice_bits(): get rid of callback
  new helper: add_to_pipe()
  splice: lift pipe_lock out of splice_to_pipe()
  splice: switch get_iovec_page_array() to iov_iter
  splice_to_pipe(): don't open-code wakeup_pipe_readers()
  consistent treatment of EFAULT on O_DIRECT read/write

drivers/char/virtio_console.c

@@ -889,7 +889,7 @@ static int pipe_to_sg(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		return 0;
 
 	/* Try lock this page */
-	if (buf->ops->steal(pipe, buf) == 0) {
+	if (pipe_buf_steal(pipe, buf) == 0) {
 		/* Get reference and unlock page for moving */
 		get_page(buf->page);
 		unlock_page(buf->page);

drivers/staging/lustre/lustre/llite/file.c

@@ -1138,45 +1138,31 @@ restart:
 			range_lock_init(&range, *ppos, *ppos + count - 1);
 
 		vio->vui_fd  = LUSTRE_FPRIVATE(file);
-		vio->vui_io_subtype = args->via_io_subtype;
+		vio->vui_iter = args->u.normal.via_iter;
+		vio->vui_iocb = args->u.normal.via_iocb;
+		/*
+		 * Direct IO reads must also take range lock,
+		 * or multiple reads will try to work on the same pages
+		 * See LU-6227 for details.
+		 */
+		if (((iot == CIT_WRITE) ||
+		     (iot == CIT_READ && (file->f_flags & O_DIRECT))) &&
+		    !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
+			CDEBUG(D_VFSTRACE, "Range lock [%llu, %llu]\n",
+			       range.rl_node.in_extent.start,
+			       range.rl_node.in_extent.end);
+			result = range_lock(&lli->lli_write_tree,
+					    &range);
+			if (result < 0)
+				goto out;
 
-		switch (vio->vui_io_subtype) {
-		case IO_NORMAL:
-			vio->vui_iter = args->u.normal.via_iter;
-			vio->vui_iocb = args->u.normal.via_iocb;
-			/*
-			 * Direct IO reads must also take range lock,
-			 * or multiple reads will try to work on the same pages
-			 * See LU-6227 for details.
-			 */
-			if (((iot == CIT_WRITE) ||
-			     (iot == CIT_READ && (file->f_flags & O_DIRECT))) &&
-			    !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
-				CDEBUG(D_VFSTRACE, "Range lock [%llu, %llu]\n",
-				       range.rl_node.in_extent.start,
-				       range.rl_node.in_extent.end);
-				result = range_lock(&lli->lli_write_tree,
-						    &range);
-				if (result < 0)
-					goto out;
-
-				range_locked = true;
-			}
-			down_read(&lli->lli_trunc_sem);
-			break;
-		case IO_SPLICE:
-			vio->u.splice.vui_pipe = args->u.splice.via_pipe;
-			vio->u.splice.vui_flags = args->u.splice.via_flags;
-			break;
-		default:
-			CERROR("Unknown IO type - %u\n", vio->vui_io_subtype);
-			LBUG();
+			range_locked = true;
 		}
+		down_read(&lli->lli_trunc_sem);
 		ll_cl_add(file, env, io);
 		result = cl_io_loop(env, io);
 		ll_cl_remove(file, env);
-		if (args->via_io_subtype == IO_NORMAL)
-			up_read(&lli->lli_trunc_sem);
+		up_read(&lli->lli_trunc_sem);
 		if (range_locked) {
 			CDEBUG(D_VFSTRACE, "Range unlock [%llu, %llu]\n",
 			       range.rl_node.in_extent.start,
@@ -1235,7 +1221,7 @@ static ssize_t ll_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
-	args = ll_env_args(env, IO_NORMAL);
+	args = ll_env_args(env);
 	args->u.normal.via_iter = to;
 	args->u.normal.via_iocb = iocb;
 
@@ -1259,7 +1245,7 @@ static ssize_t ll_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
-	args = ll_env_args(env, IO_NORMAL);
+	args = ll_env_args(env);
 	args->u.normal.via_iter = from;
 	args->u.normal.via_iocb = iocb;
 
@@ -1269,31 +1255,6 @@ static ssize_t ll_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	return result;
 }
 
-/*
- * Send file content (through pagecache) somewhere with helper
- */
-static ssize_t ll_file_splice_read(struct file *in_file, loff_t *ppos,
-				   struct pipe_inode_info *pipe, size_t count,
-				   unsigned int flags)
-{
-	struct lu_env      *env;
-	struct vvp_io_args *args;
-	ssize_t	     result;
-	int		 refcheck;
-
-	env = cl_env_get(&refcheck);
-	if (IS_ERR(env))
-		return PTR_ERR(env);
-
-	args = ll_env_args(env, IO_SPLICE);
-	args->u.splice.via_pipe = pipe;
-	args->u.splice.via_flags = flags;
-
-	result = ll_file_io_generic(env, args, in_file, CIT_READ, ppos, count);
-	cl_env_put(env, &refcheck);
-	return result;
-}
-
 int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry,
 			     __u64 flags, struct lov_user_md *lum,
 			     int lum_size)
@@ -3267,7 +3228,7 @@ struct file_operations ll_file_operations = {
 	.release	= ll_file_release,
 	.mmap	   = ll_file_mmap,
 	.llseek	 = ll_file_seek,
-	.splice_read    = ll_file_splice_read,
+	.splice_read    = generic_file_splice_read,
 	.fsync	  = ll_fsync,
 	.flush	  = ll_flush
 };
@@ -3280,7 +3241,7 @@ struct file_operations ll_file_operations_flock = {
 	.release	= ll_file_release,
 	.mmap	   = ll_file_mmap,
 	.llseek	 = ll_file_seek,
-	.splice_read    = ll_file_splice_read,
+	.splice_read    = generic_file_splice_read,
 	.fsync	  = ll_fsync,
 	.flush	  = ll_flush,
 	.flock	  = ll_file_flock,
@@ -3296,7 +3257,7 @@ struct file_operations ll_file_operations_noflock = {
 	.release	= ll_file_release,
 	.mmap	   = ll_file_mmap,
 	.llseek	 = ll_file_seek,
-	.splice_read    = ll_file_splice_read,
+	.splice_read    = generic_file_splice_read,
 	.fsync	  = ll_fsync,
 	.flush	  = ll_flush,
 	.flock	  = ll_file_noflock,

drivers/staging/lustre/lustre/llite/llite_internal.h

@@ -908,17 +908,11 @@ void vvp_write_complete(struct vvp_object *club, struct vvp_page *page);
  */
 struct vvp_io_args {
 	/** normal/splice */
-	enum vvp_io_subtype via_io_subtype;
-
 	union {
 		struct {
 			struct kiocb      *via_iocb;
 			struct iov_iter   *via_iter;
 		} normal;
-		struct {
-			struct pipe_inode_info  *via_pipe;
-			unsigned int       via_flags;
-		} splice;
 	} u;
 };
 
@@ -946,14 +940,9 @@ static inline struct ll_thread_info *ll_env_info(const struct lu_env *env)
 	return lti;
 }
 
-static inline struct vvp_io_args *ll_env_args(const struct lu_env *env,
-					      enum vvp_io_subtype type)
+static inline struct vvp_io_args *ll_env_args(const struct lu_env *env)
 {
-	struct vvp_io_args *via = &ll_env_info(env)->lti_args;
-
-	via->via_io_subtype = type;
-
-	return via;
+	return &ll_env_info(env)->lti_args;
 }
 
 void ll_queue_done_writing(struct inode *inode, unsigned long flags);

drivers/staging/lustre/lustre/llite/vvp_internal.h

@@ -49,14 +49,6 @@ struct obd_device;
 struct obd_export;
 struct page;
 
-/* specific architecture can implement only part of this list */
-enum vvp_io_subtype {
-	/** normal IO */
-	IO_NORMAL,
-	/** io started from splice_{read|write} */
-	IO_SPLICE
-};
-
 /**
  * IO state private to IO state private to VVP layer.
  */
@@ -98,10 +90,6 @@ struct vvp_io {
 			 */
 			bool		ft_flags_valid;
 		} fault;
-		struct {
-			struct pipe_inode_info	*vui_pipe;
-			unsigned int		 vui_flags;
-		} splice;
 		struct {
 			struct cl_page_list vui_queue;
 			unsigned long vui_written;
@@ -110,8 +98,6 @@ struct vvp_io {
 		} write;
 	} u;
 
-	enum vvp_io_subtype	vui_io_subtype;
-
 	/**
 	 * Layout version when this IO is initialized
 	 */

drivers/staging/lustre/lustre/llite/vvp_io.c

@@ -53,18 +53,6 @@ static struct vvp_io *cl2vvp_io(const struct lu_env *env,
 	return vio;
 }
 
-/**
- * True, if \a io is a normal io, False for splice_{read,write}
- */
-static int cl_is_normalio(const struct lu_env *env, const struct cl_io *io)
-{
-	struct vvp_io *vio = vvp_env_io(env);
-
-	LASSERT(io->ci_type == CIT_READ || io->ci_type == CIT_WRITE);
-
-	return vio->vui_io_subtype == IO_NORMAL;
-}
-
 /**
  * For swapping layout. The file's layout may have changed.
  * To avoid populating pages to a wrong stripe, we have to verify the
@@ -390,9 +378,6 @@ static int vvp_mmap_locks(const struct lu_env *env,
 
 	LASSERT(io->ci_type == CIT_READ || io->ci_type == CIT_WRITE);
 
-	if (!cl_is_normalio(env, io))
-		return 0;
-
 	if (!vio->vui_iter) /* nfs or loop back device write */
 		return 0;
 
@@ -461,15 +446,10 @@ static void vvp_io_advance(const struct lu_env *env,
 			   const struct cl_io_slice *ios,
 			   size_t nob)
 {
-	struct vvp_io    *vio = cl2vvp_io(env, ios);
-	struct cl_io     *io  = ios->cis_io;
 	struct cl_object *obj = ios->cis_io->ci_obj;
-
+	struct vvp_io	 *vio = cl2vvp_io(env, ios);
 	CLOBINVRNT(env, obj, vvp_object_invariant(obj));
 
-	if (!cl_is_normalio(env, io))
-		return;
-
 	iov_iter_reexpand(vio->vui_iter, vio->vui_tot_count  -= nob);
 }
 
@@ -478,7 +458,7 @@ static void vvp_io_update_iov(const struct lu_env *env,
 {
 	size_t size = io->u.ci_rw.crw_count;
 
-	if (!cl_is_normalio(env, io) || !vio->vui_iter)
+	if (!vio->vui_iter)
 		return;
 
 	iov_iter_truncate(vio->vui_iter, size);
@@ -715,25 +695,8 @@ static int vvp_io_read_start(const struct lu_env *env,
 
 	/* BUG: 5972 */
 	file_accessed(file);
-	switch (vio->vui_io_subtype) {
-	case IO_NORMAL:
-		LASSERT(vio->vui_iocb->ki_pos == pos);
-		result = generic_file_read_iter(vio->vui_iocb, vio->vui_iter);
-		break;
-	case IO_SPLICE:
-		result = generic_file_splice_read(file, &pos,
-						  vio->u.splice.vui_pipe, cnt,
-						  vio->u.splice.vui_flags);
-		/* LU-1109: do splice read stripe by stripe otherwise if it
-		 * may make nfsd stuck if this read occupied all internal pipe
-		 * buffers.
-		 */
-		io->ci_continue = 0;
-		break;
-	default:
-		CERROR("Wrong IO type %u\n", vio->vui_io_subtype);
-		LBUG();
-	}
+	LASSERT(vio->vui_iocb->ki_pos == pos);
+	result = generic_file_read_iter(vio->vui_iocb, vio->vui_iter);
 
 out:
 	if (result >= 0) {

fs/coda/file.c

@@ -37,27 +37,6 @@ coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos);
 }
 
-static ssize_t
-coda_file_splice_read(struct file *coda_file, loff_t *ppos,
-		      struct pipe_inode_info *pipe, size_t count,
-		      unsigned int flags)
-{
-	ssize_t (*splice_read)(struct file *, loff_t *,
-			       struct pipe_inode_info *, size_t, unsigned int);
-	struct coda_file_info *cfi;
-	struct file *host_file;
-
-	cfi = CODA_FTOC(coda_file);
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
-	host_file = cfi->cfi_container;
-
-	splice_read = host_file->f_op->splice_read;
-	if (!splice_read)
-		splice_read = default_file_splice_read;
-
-	return splice_read(host_file, ppos, pipe, count, flags);
-}
-
 static ssize_t
 coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -225,6 +204,6 @@ const struct file_operations coda_file_operations = {
 	.open		= coda_open,
 	.release	= coda_release,
 	.fsync		= coda_fsync,
-	.splice_read	= coda_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 };
 

fs/direct-io.c

@@ -246,6 +246,9 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
 		if ((dio->op == REQ_OP_READ) &&
 		    ((offset + transferred) > dio->i_size))
 			transferred = dio->i_size - offset;
+		/* ignore EFAULT if some IO has been done */
+		if (unlikely(ret == -EFAULT) && transferred)
+			ret = 0;
 	}
 
 	if (ret == 0)

fs/fuse/dev.c

@@ -728,7 +728,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 		struct pipe_buffer *buf = cs->pipebufs;
 
 		if (!cs->write) {
-			err = buf->ops->confirm(cs->pipe, buf);
+			err = pipe_buf_confirm(cs->pipe, buf);
 			if (err)
 				return err;
 
@@ -827,7 +827,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 
 	fuse_copy_finish(cs);
 
-	err = buf->ops->confirm(cs->pipe, buf);
+	err = pipe_buf_confirm(cs->pipe, buf);
 	if (err)
 		return err;
 
@@ -840,7 +840,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 	if (cs->len != PAGE_SIZE)
 		goto out_fallback;
 
-	if (buf->ops->steal(cs->pipe, buf) != 0)
+	if (pipe_buf_steal(cs->pipe, buf) != 0)
 		goto out_fallback;
 
 	newpage = buf->page;
@@ -1341,9 +1341,8 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 				    struct pipe_inode_info *pipe,
 				    size_t len, unsigned int flags)
 {
-	int ret;
+	int total, ret;
 	int page_nr = 0;
-	int do_wakeup = 0;
 	struct pipe_buffer *bufs;
 	struct fuse_copy_state cs;
 	struct fuse_dev *fud = fuse_get_dev(in);
@@ -1362,52 +1361,23 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 	if (ret < 0)
 		goto out;
 
-	ret = 0;
-	pipe_lock(pipe);
-
-	if (!pipe->readers) {
-		send_sig(SIGPIPE, current, 0);
-		if (!ret)
-			ret = -EPIPE;
-		goto out_unlock;
-	}
-
 	if (pipe->nrbufs + cs.nr_segs > pipe->buffers) {
 		ret = -EIO;
-		goto out_unlock;
+		goto out;
 	}
 
-	while (page_nr < cs.nr_segs) {
-		int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
-		struct pipe_buffer *buf = pipe->bufs + newbuf;
-
-		buf->page = bufs[page_nr].page;
-		buf->offset = bufs[page_nr].offset;
-		buf->len = bufs[page_nr].len;
+	for (ret = total = 0; page_nr < cs.nr_segs; total += ret) {
 		/*
 		 * Need to be careful about this.  Having buf->ops in module
 		 * code can Oops if the buffer persists after module unload.
 		 */
-		buf->ops = &nosteal_pipe_buf_ops;
-
-		pipe->nrbufs++;
-		page_nr++;
-		ret += buf->len;
-
-		if (pipe->files)
-			do_wakeup = 1;
+		bufs[page_nr].ops = &nosteal_pipe_buf_ops;
+		ret = add_to_pipe(pipe, &bufs[page_nr++]);
+		if (unlikely(ret < 0))
+			break;
 	}
-
-out_unlock:
-	pipe_unlock(pipe);
-
-	if (do_wakeup) {
-		smp_mb();
-		if (waitqueue_active(&pipe->wait))
-			wake_up_interruptible(&pipe->wait);
-		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
-	}
-
+	if (total)
+		ret = total;
 out:
 	for (; page_nr < cs.nr_segs; page_nr++)
 		put_page(bufs[page_nr].page);
@@ -1992,7 +1962,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 			pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
 			pipe->nrbufs--;
 		} else {
-			ibuf->ops->get(pipe, ibuf);
+			pipe_buf_get(pipe, ibuf);
 			*obuf = *ibuf;
 			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
 			obuf->len = rem;
@@ -2014,10 +1984,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	ret = fuse_dev_do_write(fud, &cs, len);
 
-	for (idx = 0; idx < nbuf; idx++) {
-		struct pipe_buffer *buf = &bufs[idx];
-		buf->ops->release(pipe, buf);
-	}
+	for (idx = 0; idx < nbuf; idx++)
+		pipe_buf_release(pipe, &bufs[idx]);
+
 out:
 	kfree(bufs);
 	return ret;

fs/gfs2/file.c

@@ -954,30 +954,6 @@ out_uninit:
 	return ret;
 }
 
-static ssize_t gfs2_file_splice_read(struct file *in, loff_t *ppos,
-				     struct pipe_inode_info *pipe, size_t len,
-				     unsigned int flags)
-{
-	struct inode *inode = in->f_mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_holder gh;
-	int ret;
-
-	inode_lock(inode);
-
-	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
-	if (ret) {
-		inode_unlock(inode);
-		return ret;
-	}
-
-	gfs2_glock_dq_uninit(&gh);
-	inode_unlock(inode);
-
-	return generic_file_splice_read(in, ppos, pipe, len, flags);
-}
-
-
 static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
 				      struct file *out, loff_t *ppos,
 				      size_t len, unsigned int flags)
@@ -1140,7 +1116,7 @@ const struct file_operations gfs2_file_fops = {
 	.fsync		= gfs2_fsync,
 	.lock		= gfs2_lock,
 	.flock		= gfs2_flock,
-	.splice_read	= gfs2_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 	.splice_write	= gfs2_file_splice_write,
 	.setlease	= simple_nosetlease,
 	.fallocate	= gfs2_fallocate,
@@ -1168,7 +1144,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 	.open		= gfs2_open,
 	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
-	.splice_read	= gfs2_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 	.splice_write	= gfs2_file_splice_write,
 	.setlease	= generic_setlease,
 	.fallocate	= gfs2_fallocate,

fs/nfs/file.c

@@ -182,29 +182,6 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 }
 EXPORT_SYMBOL_GPL(nfs_file_read);
 
-ssize_t
-nfs_file_splice_read(struct file *filp, loff_t *ppos,
-		     struct pipe_inode_info *pipe, size_t count,
-		     unsigned int flags)
-{
-	struct inode *inode = file_inode(filp);
-	ssize_t res;
-
-	dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n",
-		filp, (unsigned long) count, (unsigned long long) *ppos);
-
-	nfs_start_io_read(inode);
-	res = nfs_revalidate_mapping(inode, filp->f_mapping);
-	if (!res) {
-		res = generic_file_splice_read(filp, ppos, pipe, count, flags);
-		if (res > 0)
-			nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, res);
-	}
-	nfs_end_io_read(inode);
-	return res;
-}
-EXPORT_SYMBOL_GPL(nfs_file_splice_read);
-
 int
 nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 {
@@ -871,7 +848,7 @@ const struct file_operations nfs_file_operations = {
 	.fsync		= nfs_file_fsync,
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
-	.splice_read	= nfs_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,

fs/nfs/internal.h

@@ -365,8 +365,6 @@ int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *)
 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 *, loff_t *, struct pipe_inode_info *,
-			     size_t, unsigned int);
 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 *);

fs/nfs/nfs4file.c

@@ -248,7 +248,7 @@ const struct file_operations nfs4_file_operations = {
 	.fsync		= nfs_file_fsync,
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
-	.splice_read	= nfs_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,

fs/ocfs2/file.c

@@ -2321,36 +2321,6 @@ out_mutex:
 	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)
-{
-	int ret = 0, lock_level = 0;
-	struct inode *inode = file_inode(in);
-
-	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, len);
-
-	/*
-	 * See the comment in ocfs2_file_read_iter()
-	 */
-	ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
-	if (ret < 0) {
-		mlog_errno(ret);
-		goto bail;
-	}
-	ocfs2_inode_unlock(inode, lock_level);
-
-	ret = generic_file_splice_read(in, ppos, pipe, len, flags);
-
-bail:
-	return ret;
-}
-
 static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 				   struct iov_iter *to)
 {
@@ -2509,7 +2479,7 @@ const struct file_operations ocfs2_fops = {
 #endif
 	.lock		= ocfs2_lock,
 	.flock		= ocfs2_flock,
-	.splice_read	= ocfs2_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 };
@@ -2554,7 +2524,7 @@ const struct file_operations ocfs2_fops_no_plocks = {
 	.compat_ioctl   = ocfs2_compat_ioctl,
 #endif
 	.flock		= ocfs2_flock,
-	.splice_read	= ocfs2_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 };

fs/ocfs2/ocfs2_trace.h

@@ -1314,8 +1314,6 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_write);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write);
 
-DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_read);
-
 DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_read);
 
 DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file);

fs/pipe.c

@@ -267,7 +267,6 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 		if (bufs) {
 			int curbuf = pipe->curbuf;
 			struct pipe_buffer *buf = pipe->bufs + curbuf;
-			const struct pipe_buf_operations *ops = buf->ops;
 			size_t chars = buf->len;
 			size_t written;
 			int error;
@@ -275,7 +274,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 			if (chars > total_len)
 				chars = total_len;
 
-			error = ops->confirm(pipe, buf);
+			error = pipe_buf_confirm(pipe, buf);
 			if (error) {
 				if (!ret)
 					ret = error;
@@ -299,8 +298,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 			}
 
 			if (!buf->len) {
-				buf->ops = NULL;
-				ops->release(pipe, buf);
+				pipe_buf_release(pipe, buf);
 				curbuf = (curbuf + 1) & (pipe->buffers - 1);
 				pipe->curbuf = curbuf;
 				pipe->nrbufs = --bufs;
@@ -383,11 +381,10 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) &
 							(pipe->buffers - 1);
 		struct pipe_buffer *buf = pipe->bufs + lastbuf;
-		const struct pipe_buf_operations *ops = buf->ops;
 		int offset = buf->offset + buf->len;
 
-		if (ops->can_merge && offset + chars <= PAGE_SIZE) {
-			ret = ops->confirm(pipe, buf);
+		if (buf->ops->can_merge && offset + chars <= PAGE_SIZE) {
+			ret = pipe_buf_confirm(pipe, buf);
 			if (ret)
 				goto out;
 
@@ -664,7 +661,7 @@ void free_pipe_info(struct pipe_inode_info *pipe)
 	for (i = 0; i < pipe->buffers; i++) {
 		struct pipe_buffer *buf = pipe->bufs + i;
 		if (buf->ops)
-			buf->ops->release(pipe, buf);
+			pipe_buf_release(pipe, buf);
 	}
 	if (pipe->tmp_page)
 		__free_page(pipe->tmp_page);

fs/xfs/xfs_file.c

@@ -393,45 +393,6 @@ xfs_file_read_iter(
 	return ret;
 }
 
-STATIC ssize_t
-xfs_file_splice_read(
-	struct file		*infilp,
-	loff_t			*ppos,
-	struct pipe_inode_info	*pipe,
-	size_t			count,
-	unsigned int		flags)
-{
-	struct xfs_inode	*ip = XFS_I(infilp->f_mapping->host);
-	ssize_t			ret;
-
-	XFS_STATS_INC(ip->i_mount, xs_read_calls);
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
-
-	trace_xfs_file_splice_read(ip, count, *ppos);
-
-	/*
-	 * DAX inodes cannot ues the page cache for splice, so we have to push
-	 * them through the VFS IO path. This means it goes through
-	 * ->read_iter, which for us takes the XFS_IOLOCK_SHARED. Hence we
-	 * cannot lock the splice operation at this level for DAX inodes.
-	 */
-	if (IS_DAX(VFS_I(ip))) {
-		ret = default_file_splice_read(infilp, ppos, pipe, count,
-					       flags);
-		goto out;
-	}
-
-	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-out:
-	if (ret > 0)
-		XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
-	return ret;
-}
-
 /*
  * Zero any on disk space between the current EOF and the new, larger EOF.
  *
@@ -1608,7 +1569,7 @@ const struct file_operations xfs_file_operations = {
 	.llseek		= xfs_file_llseek,
 	.read_iter	= xfs_file_read_iter,
 	.write_iter	= xfs_file_write_iter,
-	.splice_read	= xfs_file_splice_read,
+	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.unlocked_ioctl	= xfs_file_ioctl,
 #ifdef CONFIG_COMPAT

fs/xfs/xfs_trace.h

@@ -1170,7 +1170,6 @@ DEFINE_RW_EVENT(xfs_file_dax_read);
 DEFINE_RW_EVENT(xfs_file_buffered_write);
 DEFINE_RW_EVENT(xfs_file_direct_write);
 DEFINE_RW_EVENT(xfs_file_dax_write);
-DEFINE_RW_EVENT(xfs_file_splice_read);
 
 DECLARE_EVENT_CLASS(xfs_page_class,
 	TP_PROTO(struct inode *inode, struct page *page, unsigned long off,

include/linux/fs.h

@@ -2794,8 +2794,6 @@ extern void block_sync_page(struct page *page);
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
-extern ssize_t default_file_splice_read(struct file *, loff_t *,
-		struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,

include/linux/pipe_fs_i.h

@@ -66,15 +66,10 @@ struct pipe_inode_info {
  *
  * ->confirm()
  *	->steal()
- *	...
- *	->map()
- *	...
- *	->unmap()
  *
- * That is, ->map() must be called on a confirmed buffer,
- * same goes for ->steal(). See below for the meaning of each
- * operation. Also see kerneldoc in fs/pipe.c for the pipe
- * and generic variants of these hooks.
+ * That is, ->steal() must be called on a confirmed buffer.
+ * See below for the meaning of each operation. Also see kerneldoc
+ * in fs/pipe.c for the pipe and generic variants of these hooks.
  */
 struct pipe_buf_operations {
 	/*
@@ -115,6 +110,53 @@ struct pipe_buf_operations {
 	void (*get)(struct pipe_inode_info *, struct pipe_buffer *);
 };
 
+/**
+ * pipe_buf_get - get a reference to a pipe_buffer
+ * @pipe:	the pipe that the buffer belongs to
+ * @buf:	the buffer to get a reference to
+ */
+static inline void pipe_buf_get(struct pipe_inode_info *pipe,
+				struct pipe_buffer *buf)
+{
+	buf->ops->get(pipe, buf);
+}
+
+/**
+ * pipe_buf_release - put a reference to a pipe_buffer
+ * @pipe:	the pipe that the buffer belongs to
+ * @buf:	the buffer to put a reference to
+ */
+static inline void pipe_buf_release(struct pipe_inode_info *pipe,
+				    struct pipe_buffer *buf)
+{
+	const struct pipe_buf_operations *ops = buf->ops;
+
+	buf->ops = NULL;
+	ops->release(pipe, buf);
+}
+
+/**
+ * pipe_buf_confirm - verify contents of the pipe buffer
+ * @pipe:	the pipe that the buffer belongs to
+ * @buf:	the buffer to confirm
+ */
+static inline int pipe_buf_confirm(struct pipe_inode_info *pipe,
+				   struct pipe_buffer *buf)
+{
+	return buf->ops->confirm(pipe, buf);
+}
+
+/**
+ * pipe_buf_steal - attempt to take ownership of a pipe_buffer
+ * @pipe:	the pipe that the buffer belongs to
+ * @buf:	the buffer to attempt to steal
+ */
+static inline int pipe_buf_steal(struct pipe_inode_info *pipe,
+				 struct pipe_buffer *buf)
+{
+	return buf->ops->steal(pipe, buf);
+}
+
 /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual
    memory allocation, whereas PIPE_BUF makes atomicity guarantees.  */
 #define PIPE_SIZE		PAGE_SIZE
@@ -129,7 +171,6 @@ extern unsigned long pipe_user_pages_hard;
 extern unsigned long pipe_user_pages_soft;
 int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 
-
 /* Drop the inode semaphore and wait for a pipe event, atomically */
 void pipe_wait(struct pipe_inode_info *pipe);