1 files changed, 222 insertions, 328 deletions

diff --git a/fs/splice.c b/fs/splice.c
index d671936d0aad..0878b852b355 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -33,7 +33,6 @@
 #include <linux/security.h>
 #include <linux/gfp.h>
 #include <linux/socket.h>
-#include <linux/compat.h>
 #include <linux/sched/signal.h>
 
 #include "internal.h"
@@ -44,49 +43,49 @@
  * addition of remove_mapping(). If success is returned, the caller may
  * attempt to reuse this page for another destination.
  */
-static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
-				     struct pipe_buffer *buf)
+static bool page_cache_pipe_buf_try_steal(struct pipe_inode_info *pipe,
+		struct pipe_buffer *buf)
 {
-	struct page *page = buf->page;
+	struct folio *folio = page_folio(buf->page);
 	struct address_space *mapping;
 
-	lock_page(page);
+	folio_lock(folio);
 
-	mapping = page_mapping(page);
+	mapping = folio_mapping(folio);
 	if (mapping) {
-		WARN_ON(!PageUptodate(page));
+		WARN_ON(!folio_test_uptodate(folio));
 
 		/*
 		 * At least for ext2 with nobh option, we need to wait on
-		 * writeback completing on this page, since we'll remove it
+		 * writeback completing on this folio, since we'll remove it
 		 * from the pagecache.  Otherwise truncate wont wait on the
-		 * page, allowing the disk blocks to be reused by someone else
+		 * folio, allowing the disk blocks to be reused by someone else
 		 * before we actually wrote our data to them. fs corruption
 		 * ensues.
 		 */
-		wait_on_page_writeback(page);
+		folio_wait_writeback(folio);
 
-		if (page_has_private(page) &&
-		    !try_to_release_page(page, GFP_KERNEL))
+		if (folio_has_private(folio) &&
+		    !filemap_release_folio(folio, GFP_KERNEL))
 			goto out_unlock;
 
 		/*
 		 * If we succeeded in removing the mapping, set LRU flag
 		 * and return good.
 		 */
-		if (remove_mapping(mapping, page)) {
+		if (remove_mapping(mapping, folio)) {
 			buf->flags |= PIPE_BUF_FLAG_LRU;
-			return 0;
+			return true;
 		}
 	}
 
 	/*
-	 * Raced with truncate or failed to remove page from current
+	 * Raced with truncate or failed to remove folio from current
 	 * address space, unlock and return failure.
 	 */
 out_unlock:
-	unlock_page(page);
-	return 1;
+	folio_unlock(folio);
+	return false;
 }
 
 static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe,
@@ -139,27 +138,26 @@ error:
 }
 
 const struct pipe_buf_operations page_cache_pipe_buf_ops = {
-	.confirm = page_cache_pipe_buf_confirm,
-	.release = page_cache_pipe_buf_release,
-	.steal = page_cache_pipe_buf_steal,
-	.get = generic_pipe_buf_get,
+	.confirm	= page_cache_pipe_buf_confirm,
+	.release	= page_cache_pipe_buf_release,
+	.try_steal	= page_cache_pipe_buf_try_steal,
+	.get		= generic_pipe_buf_get,
 };
 
-static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
-				    struct pipe_buffer *buf)
+static bool user_page_pipe_buf_try_steal(struct pipe_inode_info *pipe,
+		struct pipe_buffer *buf)
 {
 	if (!(buf->flags & PIPE_BUF_FLAG_GIFT))
-		return 1;
+		return false;
 
 	buf->flags |= PIPE_BUF_FLAG_LRU;
-	return generic_pipe_buf_steal(pipe, buf);
+	return generic_pipe_buf_try_steal(pipe, buf);
 }
 
 static const struct pipe_buf_operations user_page_pipe_buf_ops = {
-	.confirm = generic_pipe_buf_confirm,
-	.release = page_cache_pipe_buf_release,
-	.steal = user_page_pipe_buf_steal,
-	.get = generic_pipe_buf_get,
+	.release	= page_cache_pipe_buf_release,
+	.try_steal	= user_page_pipe_buf_try_steal,
+	.get		= generic_pipe_buf_get,
 };
 
 static void wakeup_pipe_readers(struct pipe_inode_info *pipe)
@@ -303,11 +301,9 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 {
 	struct iov_iter to;
 	struct kiocb kiocb;
-	unsigned int i_head;
 	int ret;
 
 	iov_iter_pipe(&to, READ, pipe, len);
-	i_head = to.head;
 	init_sync_kiocb(&kiocb, in);
 	kiocb.ki_pos = *ppos;
 	ret = call_read_iter(in, &kiocb, &to);
@@ -315,9 +311,8 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 		*ppos = kiocb.ki_pos;
 		file_accessed(in);
 	} else if (ret < 0) {
-		to.head = i_head;
-		to.iov_offset = 0;
-		iov_iter_advance(&to, 0); /* to free what was emitted */
+		/* free what was emitted */
+		pipe_discard_from(pipe, to.start_head);
 		/*
 		 * callers of ->splice_read() expect -EAGAIN on
 		 * "can't put anything in there", rather than -EFAULT.
@@ -331,110 +326,18 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 EXPORT_SYMBOL(generic_file_splice_read);
 
 const struct pipe_buf_operations default_pipe_buf_ops = {
-	.confirm = generic_pipe_buf_confirm,
-	.release = generic_pipe_buf_release,
-	.steal = generic_pipe_buf_steal,
-	.get = generic_pipe_buf_get,
+	.release	= generic_pipe_buf_release,
+	.try_steal	= generic_pipe_buf_try_steal,
+	.get		= generic_pipe_buf_get,
 };
 
-int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
-			     struct pipe_buffer *buf)
-{
-	return 1;
-}
-
 /* Pipe buffer operations for a socket and similar. */
 const struct pipe_buf_operations nosteal_pipe_buf_ops = {
-	.confirm = generic_pipe_buf_confirm,
-	.release = generic_pipe_buf_release,
-	.steal = generic_pipe_buf_nosteal,
-	.get = generic_pipe_buf_get,
+	.release	= generic_pipe_buf_release,
+	.get		= generic_pipe_buf_get,
 };
 EXPORT_SYMBOL(nosteal_pipe_buf_ops);
 
-static ssize_t kernel_readv(struct file *file, const struct kvec *vec,
-			    unsigned long vlen, loff_t offset)
-{
-	mm_segment_t old_fs;
-	loff_t pos = offset;
-	ssize_t res;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
-	set_fs(old_fs);
-
-	return res;
-}
-
-static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
-				 struct pipe_inode_info *pipe, size_t len,
-				 unsigned int flags)
-{
-	struct kvec *vec, __vec[PIPE_DEF_BUFFERS];
-	struct iov_iter to;
-	struct page **pages;
-	unsigned int nr_pages;
-	unsigned int mask;
-	size_t offset, base, copied = 0;
-	ssize_t res;
-	int i;
-
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
-		return -EAGAIN;
-
-	/*
-	 * Try to keep page boundaries matching to source pagecache ones -
-	 * it probably won't be much help, but...
-	 */
-	offset = *ppos & ~PAGE_MASK;
-
-	iov_iter_pipe(&to, READ, pipe, len + offset);
-
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
-	if (res <= 0)
-		return -ENOMEM;
-
-	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
-
-	vec = __vec;
-	if (nr_pages > PIPE_DEF_BUFFERS) {
-		vec = kmalloc_array(nr_pages, sizeof(struct kvec), GFP_KERNEL);
-		if (unlikely(!vec)) {
-			res = -ENOMEM;
-			goto out;
-		}
-	}
-
-	mask = pipe->ring_size - 1;
-	pipe->bufs[to.head & mask].offset = offset;
-	pipe->bufs[to.head & mask].len -= offset;
-
-	for (i = 0; i < nr_pages; i++) {
-		size_t this_len = min_t(size_t, len, PAGE_SIZE - offset);
-		vec[i].iov_base = page_address(pages[i]) + offset;
-		vec[i].iov_len = this_len;
-		len -= this_len;
-		offset = 0;
-	}
-
-	res = kernel_readv(in, vec, nr_pages, *ppos);
-	if (res > 0) {
-		copied = res;
-		*ppos += res;
-	}
-
-	if (vec != __vec)
-		kfree(vec);
-out:
-	for (i = 0; i < nr_pages; i++)
-		put_page(pages[i]);
-	kvfree(pages);
-	iov_iter_advance(&to, copied);	/* truncates and discards */
-	return res;
-}
-
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -536,6 +439,22 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des
 	return 1;
 }
 
+/* We know we have a pipe buffer, but maybe it's empty? */
+static inline bool eat_empty_buffer(struct pipe_inode_info *pipe)
+{
+	unsigned int tail = pipe->tail;
+	unsigned int mask = pipe->ring_size - 1;
+	struct pipe_buffer *buf = &pipe->bufs[tail & mask];
+
+	if (unlikely(!buf->len)) {
+		pipe_buf_release(pipe, buf);
+		pipe->tail = tail+1;
+		return true;
+	}
+
+	return false;
+}
+
 /**
  * splice_from_pipe_next - wait for some data to splice from
  * @pipe:	pipe to splice from
@@ -555,6 +474,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des
 	if (signal_pending(current))
 		return -ERESTARTSYS;
 
+repeat:
 	while (pipe_empty(pipe->head, pipe->tail)) {
 		if (!pipe->writers)
 			return 0;
@@ -573,9 +493,12 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des
 			sd->need_wakeup = false;
 		}
 
-		pipe_wait(pipe);
+		pipe_wait_readable(pipe);
 	}
 
+	if (eat_empty_buffer(pipe))
+		goto repeat;
+
 	return 1;
 }
 
@@ -736,12 +659,14 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 		/* build the vector */
 		left = sd.total_len;
-		for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++, n++) {
+		for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++) {
 			struct pipe_buffer *buf = &pipe->bufs[tail & mask];
 			size_t this_len = buf->len;
 
-			if (this_len > left)
-				this_len = left;
+			/* zero-length bvecs are not supported, skip them */
+			if (!this_len)
+				continue;
+			this_len = min(this_len, left);
 
 			ret = pipe_buf_confirm(pipe, buf);
 			if (unlikely(ret)) {
@@ -754,6 +679,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 			array[n].bv_len = this_len;
 			array[n].bv_offset = buf->offset;
 			left -= this_len;
+			n++;
 		}
 
 		iov_iter_bvec(&from, WRITE, array, n, sd.total_len - left);
@@ -798,33 +724,6 @@ done:
 
 EXPORT_SYMBOL(iter_file_splice_write);
 
-static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-			  struct splice_desc *sd)
-{
-	int ret;
-	void *data;
-	loff_t tmp = sd->pos;
-
-	data = kmap(buf->page);
-	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	kunmap(buf->page);
-
-	return ret;
-}
-
-static ssize_t default_file_splice_write(struct pipe_inode_info *pipe,
-					 struct file *out, loff_t *ppos,
-					 size_t len, unsigned int flags)
-{
-	ssize_t ret;
-
-	ret = splice_from_pipe(pipe, out, ppos, len, flags, write_pipe_buf);
-	if (ret > 0)
-		*ppos += ret;
-
-	return ret;
-}
-
 /**
  * generic_splice_sendpage - splice data from a pipe to a socket
  * @pipe:	pipe to splice from
@@ -846,21 +745,23 @@ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out,
 
 EXPORT_SYMBOL(generic_splice_sendpage);
 
+static int warn_unsupported(struct file *file, const char *op)
+{
+	pr_debug_ratelimited(
+		"splice %s not supported for file %pD4 (pid: %d comm: %.20s)\n",
+		op, file, current->pid, current->comm);
+	return -EINVAL;
+}
+
 /*
  * Attempt to initiate a splice from pipe to file.
  */
 static long do_splice_from(struct pipe_inode_info *pipe, struct file *out,
 			   loff_t *ppos, size_t len, unsigned int flags)
 {
-	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *,
-				loff_t *, size_t, unsigned int);
-
-	if (out->f_op->splice_write)
-		splice_write = out->f_op->splice_write;
-	else
-		splice_write = default_file_splice_write;
-
-	return splice_write(pipe, out, ppos, len, flags);
+	if (unlikely(!out->f_op->splice_write))
+		return warn_unsupported(out, "write");
+	return out->f_op->splice_write(pipe, out, ppos, len, flags);
 }
 
 /*
@@ -870,13 +771,16 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 			 struct pipe_inode_info *pipe, size_t len,
 			 unsigned int flags)
 {
-	ssize_t (*splice_read)(struct file *, loff_t *,
-			       struct pipe_inode_info *, size_t, unsigned int);
+	unsigned int p_space;
 	int ret;
 
 	if (unlikely(!(in->f_mode & FMODE_READ)))
 		return -EBADF;
 
+	/* Don't try to read more the pipe has space for. */
+	p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail);
+	len = min_t(size_t, len, p_space << PAGE_SHIFT);
+
 	ret = rw_verify_area(READ, in, ppos, len);
 	if (unlikely(ret < 0))
 		return ret;
@@ -884,12 +788,9 @@ static long do_splice_to(struct file *in, loff_t *ppos,
 	if (unlikely(len > MAX_RW_COUNT))
 		len = MAX_RW_COUNT;
 
-	if (in->f_op->splice_read)
-		splice_read = in->f_op->splice_read;
-	else
-		splice_read = default_file_splice_read;
-
-	return splice_read(in, ppos, pipe, len, flags);
+	if (unlikely(!in->f_op->splice_read))
+		return warn_unsupported(in, "read");
+	return in->f_op->splice_read(in, ppos, pipe, len, flags);
 }
 
 /**
@@ -910,17 +811,15 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 {
 	struct pipe_inode_info *pipe;
 	long ret, bytes;
-	umode_t i_mode;
 	size_t len;
 	int i, flags, more;
 
 	/*
-	 * We require the input being a regular file, as we don't want to
-	 * randomly drop data for eg socket -> socket splicing. Use the
-	 * piped splicing for that!
+	 * We require the input to be seekable, as we don't want to randomly
+	 * drop data for eg socket -> socket splicing. Use the piped splicing
+	 * for that!
 	 */
-	i_mode = file_inode(in)->i_mode;
-	if (unlikely(!S_ISREG(i_mode) && !S_ISBLK(i_mode)))
+	if (unlikely(!(in->f_mode & FMODE_LSEEK)))
 		return -EINVAL;
 
 	/*
@@ -960,15 +859,10 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 	WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail));
 
 	while (len) {
-		unsigned int p_space;
 		size_t read_len;
 		loff_t pos = sd->pos, prev_pos = pos;
 
-		/* Don't try to read more the pipe has space for. */
-		p_space = pipe->max_usage -
-			pipe_occupancy(pipe->head, pipe->tail);
-		read_len = min_t(size_t, len, p_space << PAGE_SHIFT);
-		ret = do_splice_to(in, &pos, pipe, read_len, flags);
+		ret = do_splice_to(in, &pos, pipe, len, flags);
 		if (unlikely(ret <= 0))
 			goto out_release;
 
@@ -1098,7 +992,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
 			return -EAGAIN;
 		if (signal_pending(current))
 			return -ERESTARTSYS;
-		pipe_wait(pipe);
+		pipe_wait_writable(pipe);
 	}
 }
 
@@ -1106,31 +1000,45 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
 			       struct pipe_inode_info *opipe,
 			       size_t len, unsigned int flags);
 
+long splice_file_to_pipe(struct file *in,
+			 struct pipe_inode_info *opipe,
+			 loff_t *offset,
+			 size_t len, unsigned int flags)
+{
+	long ret;
+
+	pipe_lock(opipe);
+	ret = wait_for_space(opipe, flags);
+	if (!ret)
+		ret = do_splice_to(in, offset, opipe, len, flags);
+	pipe_unlock(opipe);
+	if (ret > 0)
+		wakeup_pipe_readers(opipe);
+	return ret;
+}
+
 /*
  * Determine where to splice to/from.
  */
-static long do_splice(struct file *in, loff_t __user *off_in,
-		      struct file *out, loff_t __user *off_out,
-		      size_t len, unsigned int flags)
+long do_splice(struct file *in, loff_t *off_in, struct file *out,
+	       loff_t *off_out, size_t len, unsigned int flags)
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
 	loff_t offset;
 	long ret;
 
-	ipipe = get_pipe_info(in);
-	opipe = get_pipe_info(out);
+	if (unlikely(!(in->f_mode & FMODE_READ) ||
+		     !(out->f_mode & FMODE_WRITE)))
+		return -EBADF;
+
+	ipipe = get_pipe_info(in, true);
+	opipe = get_pipe_info(out, true);
 
 	if (ipipe && opipe) {
 		if (off_in || off_out)
 			return -ESPIPE;
 
-		if (!(in->f_mode & FMODE_READ))
-			return -EBADF;
-
-		if (!(out->f_mode & FMODE_WRITE))
-			return -EBADF;
-
 		/* Splicing to self would be fun, but... */
 		if (ipipe == opipe)
 			return -EINVAL;
@@ -1147,15 +1055,11 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_out) {
 			if (!(out->f_mode & FMODE_PWRITE))
 				return -EINVAL;
-			if (copy_from_user(&offset, off_out, sizeof(loff_t)))
-				return -EFAULT;
+			offset = *off_out;
 		} else {
 			offset = out->f_pos;
 		}
 
-		if (unlikely(!(out->f_mode & FMODE_WRITE)))
-			return -EBADF;
-
 		if (unlikely(out->f_flags & O_APPEND))
 			return -EINVAL;
 
@@ -1172,8 +1076,8 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 
 		if (!off_out)
 			out->f_pos = offset;
-		else if (copy_to_user(off_out, &offset, sizeof(loff_t)))
-			ret = -EFAULT;
+		else
+			*off_out = offset;
 
 		return ret;
 	}
@@ -1184,8 +1088,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		if (off_in) {
 			if (!(in->f_mode & FMODE_PREAD))
 				return -EINVAL;
-			if (copy_from_user(&offset, off_in, sizeof(loff_t)))
-				return -EFAULT;
+			offset = *off_in;
 		} else {
 			offset = in->f_pos;
 		}
@@ -1193,24 +1096,11 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 		if (out->f_flags & O_NONBLOCK)
 			flags |= SPLICE_F_NONBLOCK;
 
-		pipe_lock(opipe);
-		ret = wait_for_space(opipe, flags);
-		if (!ret) {
-			unsigned int p_space;
-
-			/* Don't try to read more the pipe has space for. */
-			p_space = opipe->max_usage - pipe_occupancy(opipe->head, opipe->tail);
-			len = min_t(size_t, len, p_space << PAGE_SHIFT);
-
-			ret = do_splice_to(in, &offset, opipe, len, flags);
-		}
-		pipe_unlock(opipe);
-		if (ret > 0)
-			wakeup_pipe_readers(opipe);
+		ret = splice_file_to_pipe(in, opipe, &offset, len, flags);
 		if (!off_in)
 			in->f_pos = offset;
-		else if (copy_to_user(off_in, &offset, sizeof(loff_t)))
-			ret = -EFAULT;
+		else
+			*off_in = offset;
 
 		return ret;
 	}
@@ -1218,6 +1108,46 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 	return -EINVAL;
 }
 
+static long __do_splice(struct file *in, loff_t __user *off_in,
+			struct file *out, loff_t __user *off_out,
+			size_t len, unsigned int flags)
+{
+	struct pipe_inode_info *ipipe;
+	struct pipe_inode_info *opipe;
+	loff_t offset, *__off_in = NULL, *__off_out = NULL;
+	long ret;
+
+	ipipe = get_pipe_info(in, true);
+	opipe = get_pipe_info(out, true);
+
+	if (ipipe && off_in)
+		return -ESPIPE;
+	if (opipe && off_out)
+		return -ESPIPE;
+
+	if (off_out) {
+		if (copy_from_user(&offset, off_out, sizeof(loff_t)))
+			return -EFAULT;
+		__off_out = &offset;
+	}
+	if (off_in) {
+		if (copy_from_user(&offset, off_in, sizeof(loff_t)))
+			return -EFAULT;
+		__off_in = &offset;
+	}
+
+	ret = do_splice(in, __off_in, out, __off_out, len, flags);
+	if (ret < 0)
+		return ret;
+
+	if (__off_out && copy_to_user(off_out, __off_out, sizeof(loff_t)))
+		return -EFAULT;
+	if (__off_in && copy_to_user(off_in, __off_in, sizeof(loff_t)))
+		return -EFAULT;
+
+	return ret;
+}
+
 static int iter_to_pipe(struct iov_iter *from,
 			struct pipe_inode_info *pipe,
 			unsigned flags)
@@ -1228,39 +1158,40 @@ static int iter_to_pipe(struct iov_iter *from,
 	};
 	size_t total = 0;
 	int ret = 0;
-	bool failed = false;
 
-	while (iov_iter_count(from) && !failed) {
+	while (iov_iter_count(from)) {
 		struct page *pages[16];
-		ssize_t copied;
+		ssize_t left;
 		size_t start;
-		int n;
+		int i, n;
 
-		copied = iov_iter_get_pages(from, pages, ~0UL, 16, &start);
-		if (copied <= 0) {
-			ret = copied;
+		left = iov_iter_get_pages2(from, pages, ~0UL, 16, &start);
+		if (left <= 0) {
+			ret = left;
 			break;
 		}
 
-		for (n = 0; copied; n++, start = 0) {
-			int size = min_t(int, copied, PAGE_SIZE - start);
-			if (!failed) {
-				buf.page = pages[n];
-				buf.offset = start;
-				buf.len = size;
-				ret = add_to_pipe(pipe, &buf);
-				if (unlikely(ret < 0)) {
-					failed = true;
-				} else {
-					iov_iter_advance(from, ret);
-					total += ret;
-				}
-			} else {
-				put_page(pages[n]);
+		n = DIV_ROUND_UP(left + start, PAGE_SIZE);
+		for (i = 0; i < n; i++) {
+			int size = min_t(int, left, PAGE_SIZE - start);
+
+			buf.page = pages[i];
+			buf.offset = start;
+			buf.len = size;
+			ret = add_to_pipe(pipe, &buf);
+			if (unlikely(ret < 0)) {
+				iov_iter_revert(from, left);
+				// this one got dropped by add_to_pipe()
+				while (++i < n)
+					put_page(pages[i]);
+				goto out;
 			}
-			copied -= size;
+			total += ret;
+			left -= size;
+			start = 0;
 		}
 	}
+out:
 	return total ? total : ret;
 }
 
@@ -1278,7 +1209,7 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
 			     unsigned int flags)
 {
-	struct pipe_inode_info *pipe = get_pipe_info(file);
+	struct pipe_inode_info *pipe = get_pipe_info(file, true);
 	struct splice_desc sd = {
 		.total_len = iov_iter_count(iter),
 		.flags = flags,
@@ -1313,7 +1244,7 @@ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
 	if (flags & SPLICE_F_GIFT)
 		buf_flag = PIPE_BUF_FLAG_GIFT;
 
-	pipe = get_pipe_info(file);
+	pipe = get_pipe_info(file, true);
 	if (!pipe)
 		return -EBADF;
 
@@ -1358,20 +1289,6 @@ static int vmsplice_type(struct fd f, int *type)
  * Currently we punt and implement it as a normal copy, see pipe_to_user().
  *
  */
-static long do_vmsplice(struct file *f, struct iov_iter *iter, unsigned int flags)
-{
-	if (unlikely(flags & ~SPLICE_F_ALL))
-		return -EINVAL;
-
-	if (!iov_iter_count(iter))
-		return 0;
-
-	if (iov_iter_rw(iter) == WRITE)
-		return vmsplice_to_pipe(f, iter, flags);
-	else
-		return vmsplice_to_user(f, iter, flags);
-}
-
 SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 		unsigned long, nr_segs, unsigned int, flags)
 {
@@ -1382,6 +1299,9 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 	struct fd f;
 	int type;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	f = fdget(fd);
 	error = vmsplice_type(f, &type);
 	if (error)
@@ -1389,40 +1309,21 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
 
 	error = import_iovec(type, uiov, nr_segs,
 			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
-	fdput(f);
-	return error;
-}
+	if (error < 0)
+		goto out_fdput;
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(vmsplice, int, fd, const struct compat_iovec __user *, iov32,
-		    unsigned int, nr_segs, unsigned int, flags)
-{
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t error;
-	struct fd f;
-	int type;
-
-	f = fdget(fd);
-	error = vmsplice_type(f, &type);
-	if (error)
-		return error;
+	if (!iov_iter_count(&iter))
+		error = 0;
+	else if (iov_iter_rw(&iter) == WRITE)
+		error = vmsplice_to_pipe(f.file, &iter, flags);
+	else
+		error = vmsplice_to_user(f.file, &iter, flags);
 
-	error = compat_import_iovec(type, iov32, nr_segs,
-			     ARRAY_SIZE(iovstack), &iov, &iter);
-	if (error >= 0) {
-		error = do_vmsplice(f.file, &iter, flags);
-		kfree(iov);
-	}
+	kfree(iov);
+out_fdput:
 	fdput(f);
 	return error;
 }
-#endif
 
 SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 		int, fd_out, loff_t __user *, off_out,
@@ -1440,15 +1341,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 	error = -EBADF;
 	in = fdget(fd_in);
 	if (in.file) {
-		if (in.file->f_mode & FMODE_READ) {
-			out = fdget(fd_out);
-			if (out.file) {
-				if (out.file->f_mode & FMODE_WRITE)
-					error = do_splice(in.file, off_in,
-							  out.file, off_out,
-							  len, flags);
-				fdput(out);
-			}
+		out = fdget(fd_out);
+		if (out.file) {
+			error = __do_splice(in.file, off_in, out.file, off_out,
+						len, flags);
+			fdput(out);
 		}
 		fdput(in);
 	}
@@ -1484,7 +1381,7 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 			ret = -EAGAIN;
 			break;
 		}
-		pipe_wait(pipe);
+		pipe_wait_readable(pipe);
 	}
 
 	pipe_unlock(pipe);
@@ -1503,7 +1400,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 	 * Check pipe occupancy without the inode lock first. This function
 	 * is speculative anyways, so missing one is ok.
 	 */
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+	if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage))
 		return 0;
 
 	ret = 0;
@@ -1523,7 +1420,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 			ret = -ERESTARTSYS;
 			break;
 		}
-		pipe_wait(pipe);
+		pipe_wait_writable(pipe);
 	}
 
 	pipe_unlock(pipe);
@@ -1635,12 +1532,11 @@ retry:
 			*obuf = *ibuf;
 
 			/*
-			 * Don't inherit the gift flag, we need to
+			 * Don't inherit the gift and merge flags, we need to
 			 * prevent multiple steals of this page.
 			 */
 			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
-
-			pipe_buf_mark_unmergeable(obuf);
+			obuf->flags &= ~PIPE_BUF_FLAG_CAN_MERGE;
 
 			obuf->len = len;
 			ibuf->offset += len;
@@ -1728,12 +1624,11 @@ static int link_pipe(struct pipe_inode_info *ipipe,
 		*obuf = *ibuf;
 
 		/*
-		 * Don't inherit the gift flag, we need to
-		 * prevent multiple steals of this page.
+		 * Don't inherit the gift and merge flag, we need to prevent
+		 * multiple steals of this page.
 		 */
 		obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
-
-		pipe_buf_mark_unmergeable(obuf);
+		obuf->flags &= ~PIPE_BUF_FLAG_CAN_MERGE;
 
 		if (obuf->len > len)
 			obuf->len = len;
@@ -1763,13 +1658,16 @@ static int link_pipe(struct pipe_inode_info *ipipe,
  * The 'flags' used are the SPLICE_F_* variants, currently the only
  * applicable one is SPLICE_F_NONBLOCK.
  */
-static long do_tee(struct file *in, struct file *out, size_t len,
-		   unsigned int flags)
+long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags)
 {
-	struct pipe_inode_info *ipipe = get_pipe_info(in);
-	struct pipe_inode_info *opipe = get_pipe_info(out);
+	struct pipe_inode_info *ipipe = get_pipe_info(in, true);
+	struct pipe_inode_info *opipe = get_pipe_info(out, true);
 	int ret = -EINVAL;
 
+	if (unlikely(!(in->f_mode & FMODE_READ) ||
+		     !(out->f_mode & FMODE_WRITE)))
+		return -EBADF;
+
 	/*
 	 * Duplicate the contents of ipipe to opipe without actually
 	 * copying the data.
@@ -1795,7 +1693,7 @@ static long do_tee(struct file *in, struct file *out, size_t len,
 
 SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 {
-	struct fd in;
+	struct fd in, out;
 	int error;
 
 	if (unlikely(flags & ~SPLICE_F_ALL))
@@ -1807,14 +1705,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 	error = -EBADF;
 	in = fdget(fdin);
 	if (in.file) {
-		if (in.file->f_mode & FMODE_READ) {
-			struct fd out = fdget(fdout);
-			if (out.file) {
-				if (out.file->f_mode & FMODE_WRITE)
-					error = do_tee(in.file, out.file,
-							len, flags);
-				fdput(out);
-			}
+		out = fdget(fdout);
+		if (out.file) {
+			error = do_tee(in.file, out.file, len, flags);
+			fdput(out);
 		}
  		fdput(in);
  	}