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

Author: torvalds

Diff for: 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);

Diff for: drivers/staging/lustre/lustre/llite/file.c

@@ -1138,45 +1138,31 @@ ll_file_io_generic(const struct lu_env *env, struct vvp_io_args *args,
 			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,

Diff for: 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);

Diff for: 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
 	 */

Diff for: 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) {

Diff for: 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,
 };
 

Diff for: 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)