Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs updates from Al Viro:
 "This the bunch that sat in -next + lock_parent() fix.  This is the
  minimal set; there's more pending stuff.

  In particular, I really hope to get acct.c fixes merged this cycle -
  we need that to deal sanely with delayed-mntput stuff.  In the next
  pile, hopefully - that series is fairly short and localized
  (kernel/acct.c, fs/super.c and fs/namespace.c).  In this pile: more
  iov_iter work.  Most of prereqs for ->splice_write with sane locking
  order are there and Kent's dio rewrite would also fit nicely on top of
  this pile"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (70 commits)
  lock_parent: don't step on stale ->d_parent of all-but-freed one
  kill generic_file_splice_write()
  ceph: switch to iter_file_splice_write()
  shmem: switch to iter_file_splice_write()
  nfs: switch to iter_splice_write_file()
  fs/splice.c: remove unneeded exports
  ocfs2: switch to iter_file_splice_write()
  ->splice_write() via ->write_iter()
  bio_vec-backed iov_iter
  optimize copy_page_{to,from}_iter()
  bury generic_file_aio_{read,write}
  lustre: get rid of messing with iovecs
  ceph: switch to ->write_iter()
  ceph_sync_direct_write: stop poking into iov_iter guts
  ceph_sync_read: stop poking into iov_iter guts
  new helper: copy_page_from_iter()
  fuse: switch to ->write_iter()
  btrfs: switch to ->write_iter()
  ocfs2: switch to ->write_iter()
  xfs: switch to ->write_iter()
  ...

3 files changed, 69 insertions, 98 deletions

diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 13b691a8a7d..966ace8b243 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -94,8 +94,10 @@ static ssize_t cuse_read(struct file *file, char __user *buf, size_t count,
 	loff_t pos = 0;
 	struct iovec iov = { .iov_base = buf, .iov_len = count };
 	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct iov_iter ii;
+	iov_iter_init(&ii, READ, &iov, 1, count);
 
-	return fuse_direct_io(&io, &iov, 1, count, &pos, FUSE_DIO_CUSE);
+	return fuse_direct_io(&io, &ii, &pos, FUSE_DIO_CUSE);
 }
 
 static ssize_t cuse_write(struct file *file, const char __user *buf,
@@ -104,12 +106,14 @@ static ssize_t cuse_write(struct file *file, const char __user *buf,
 	loff_t pos = 0;
 	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count };
 	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct iov_iter ii;
+	iov_iter_init(&ii, WRITE, &iov, 1, count);
 
 	/*
 	 * No locking or generic_write_checks(), the server is
 	 * responsible for locking and sanity checks.
 	 */
-	return fuse_direct_io(&io, &iov, 1, count, &pos,
+	return fuse_direct_io(&io, &ii, &pos,
 			      FUSE_DIO_WRITE | FUSE_DIO_CUSE);
 }
 
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 903cbc9cd6b..6e16dad13e9 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -933,8 +933,7 @@ out:
 	return err;
 }
 
-static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-				  unsigned long nr_segs, loff_t pos)
+static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct fuse_conn *fc = get_fuse_conn(inode);
@@ -945,14 +944,14 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	 * i_size is up to date).
 	 */
 	if (fc->auto_inval_data ||
-	    (pos + iov_length(iov, nr_segs) > i_size_read(inode))) {
+	    (iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) {
 		int err;
 		err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL);
 		if (err)
 			return err;
 	}
 
-	return generic_file_aio_read(iocb, iov, nr_segs, pos);
+	return generic_file_read_iter(iocb, to);
 }
 
 static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff,
@@ -1181,19 +1180,17 @@ static ssize_t fuse_perform_write(struct file *file,
 	return res > 0 ? res : err;
 }
 
-static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				   unsigned long nr_segs, loff_t pos)
+static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
-	size_t count = 0;
-	size_t ocount = 0;
+	size_t count = iov_iter_count(from);
 	ssize_t written = 0;
 	ssize_t written_buffered = 0;
 	struct inode *inode = mapping->host;
 	ssize_t err;
-	struct iov_iter i;
 	loff_t endbyte = 0;
+	loff_t pos = iocb->ki_pos;
 
 	if (get_fuse_conn(inode)->writeback_cache) {
 		/* Update size (EOF optimization) and mode (SUID clearing) */
@@ -1201,17 +1198,9 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (err)
 			return err;
 
-		return generic_file_aio_write(iocb, iov, nr_segs, pos);
+		return generic_file_write_iter(iocb, from);
 	}
 
-	WARN_ON(iocb->ki_pos != pos);
-
-	ocount = 0;
-	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
-	if (err)
-		return err;
-
-	count = ocount;
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
@@ -1224,6 +1213,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (count == 0)
 		goto out;
 
+	iov_iter_truncate(from, count);
 	err = file_remove_suid(file);
 	if (err)
 		goto out;
@@ -1233,16 +1223,13 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		goto out;
 
 	if (file->f_flags & O_DIRECT) {
-		written = generic_file_direct_write(iocb, iov, &nr_segs, pos, 
-						    count, ocount);
-		if (written < 0 || written == count)
+		written = generic_file_direct_write(iocb, from, pos);
+		if (written < 0 || !iov_iter_count(from))
 			goto out;
 
 		pos += written;
-		count -= written;
 
-		iov_iter_init(&i, iov, nr_segs, count, written);
-		written_buffered = fuse_perform_write(file, mapping, &i, pos);
+		written_buffered = fuse_perform_write(file, mapping, from, pos);
 		if (written_buffered < 0) {
 			err = written_buffered;
 			goto out;
@@ -1261,8 +1248,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		written += written_buffered;
 		iocb->ki_pos = pos + written_buffered;
 	} else {
-		iov_iter_init(&i, iov, nr_segs, count, 0);
-		written = fuse_perform_write(file, mapping, &i, pos);
+		written = fuse_perform_write(file, mapping, from, pos);
 		if (written >= 0)
 			iocb->ki_pos = pos + written;
 	}
@@ -1300,7 +1286,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 	size_t nbytes = 0;  /* # bytes already packed in req */
 
 	/* Special case for kernel I/O: can copy directly into the buffer */
-	if (segment_eq(get_fs(), KERNEL_DS)) {
+	if (ii->type & ITER_KVEC) {
 		unsigned long user_addr = fuse_get_user_addr(ii);
 		size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
 
@@ -1316,35 +1302,26 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 
 	while (nbytes < *nbytesp && req->num_pages < req->max_pages) {
 		unsigned npages;
-		unsigned long user_addr = fuse_get_user_addr(ii);
-		unsigned offset = user_addr & ~PAGE_MASK;
-		size_t frag_size = fuse_get_frag_size(ii, *nbytesp - nbytes);
-		int ret;
-
+		size_t start;
 		unsigned n = req->max_pages - req->num_pages;
-		frag_size = min_t(size_t, frag_size, n << PAGE_SHIFT);
-
-		npages = (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		npages = clamp(npages, 1U, n);
-
-		ret = get_user_pages_fast(user_addr, npages, !write,
-					  &req->pages[req->num_pages]);
+		ssize_t ret = iov_iter_get_pages(ii,
+					&req->pages[req->num_pages],
+					n * PAGE_SIZE, &start);
 		if (ret < 0)
 			return ret;
 
-		npages = ret;
-		frag_size = min_t(size_t, frag_size,
-				  (npages << PAGE_SHIFT) - offset);
-		iov_iter_advance(ii, frag_size);
+		iov_iter_advance(ii, ret);
+		nbytes += ret;
+
+		ret += start;
+		npages = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
 
-		req->page_descs[req->num_pages].offset = offset;
+		req->page_descs[req->num_pages].offset = start;
 		fuse_page_descs_length_init(req, req->num_pages, npages);
 
 		req->num_pages += npages;
 		req->page_descs[req->num_pages - 1].length -=
-			(npages << PAGE_SHIFT) - offset - frag_size;
-
-		nbytes += frag_size;
+			(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
 	}
 
 	if (write)
@@ -1359,24 +1336,11 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 
 static inline int fuse_iter_npages(const struct iov_iter *ii_p)
 {
-	struct iov_iter ii = *ii_p;
-	int npages = 0;
-
-	while (iov_iter_count(&ii) && npages < FUSE_MAX_PAGES_PER_REQ) {
-		unsigned long user_addr = fuse_get_user_addr(&ii);
-		unsigned offset = user_addr & ~PAGE_MASK;
-		size_t frag_size = iov_iter_single_seg_count(&ii);
-
-		npages += (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		iov_iter_advance(&ii, frag_size);
-	}
-
-	return min(npages, FUSE_MAX_PAGES_PER_REQ);
+	return iov_iter_npages(ii_p, FUSE_MAX_PAGES_PER_REQ);
 }
 
-ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
-		       unsigned long nr_segs, size_t count, loff_t *ppos,
-		       int flags)
+ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
+		       loff_t *ppos, int flags)
 {
 	int write = flags & FUSE_DIO_WRITE;
 	int cuse = flags & FUSE_DIO_CUSE;
@@ -1386,18 +1350,16 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 	struct fuse_conn *fc = ff->fc;
 	size_t nmax = write ? fc->max_write : fc->max_read;
 	loff_t pos = *ppos;
+	size_t count = iov_iter_count(iter);
 	pgoff_t idx_from = pos >> PAGE_CACHE_SHIFT;
 	pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT;
 	ssize_t res = 0;
 	struct fuse_req *req;
-	struct iov_iter ii;
-
-	iov_iter_init(&ii, iov, nr_segs, count, 0);
 
 	if (io->async)
-		req = fuse_get_req_for_background(fc, fuse_iter_npages(&ii));
+		req = fuse_get_req_for_background(fc, fuse_iter_npages(iter));
 	else
-		req = fuse_get_req(fc, fuse_iter_npages(&ii));
+		req = fuse_get_req(fc, fuse_iter_npages(iter));
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1413,7 +1375,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 		size_t nres;
 		fl_owner_t owner = current->files;
 		size_t nbytes = min(count, nmax);
-		int err = fuse_get_user_pages(req, &ii, &nbytes, write);
+		int err = fuse_get_user_pages(req, iter, &nbytes, write);
 		if (err) {
 			res = err;
 			break;
@@ -1443,9 +1405,9 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 			fuse_put_request(fc, req);
 			if (io->async)
 				req = fuse_get_req_for_background(fc,
-					fuse_iter_npages(&ii));
+					fuse_iter_npages(iter));
 			else
-				req = fuse_get_req(fc, fuse_iter_npages(&ii));
+				req = fuse_get_req(fc, fuse_iter_npages(iter));
 			if (IS_ERR(req))
 				break;
 		}
@@ -1460,9 +1422,8 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 EXPORT_SYMBOL_GPL(fuse_direct_io);
 
 static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
-				  const struct iovec *iov,
-				  unsigned long nr_segs, loff_t *ppos,
-				  size_t count)
+				  struct iov_iter *iter,
+				  loff_t *ppos)
 {
 	ssize_t res;
 	struct file *file = io->file;
@@ -1471,7 +1432,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
 	if (is_bad_inode(inode))
 		return -EIO;
 
-	res = fuse_direct_io(io, iov, nr_segs, count, ppos, 0);
+	res = fuse_direct_io(io, iter, ppos, 0);
 
 	fuse_invalidate_attr(inode);
 
@@ -1483,22 +1444,26 @@ static ssize_t fuse_direct_read(struct file *file, char __user *buf,
 {
 	struct fuse_io_priv io = { .async = 0, .file = file };
 	struct iovec iov = { .iov_base = buf, .iov_len = count };
-	return __fuse_direct_read(&io, &iov, 1, ppos, count);
+	struct iov_iter ii;
+	iov_iter_init(&ii, READ, &iov, 1, count);
+	return __fuse_direct_read(&io, &ii, ppos);
 }
 
 static ssize_t __fuse_direct_write(struct fuse_io_priv *io,
-				   const struct iovec *iov,
-				   unsigned long nr_segs, loff_t *ppos)
+				   struct iov_iter *iter,
+				   loff_t *ppos)
 {
 	struct file *file = io->file;
 	struct inode *inode = file_inode(file);
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	ssize_t res;
 
+
 	res = generic_write_checks(file, ppos, &count, 0);
-	if (!res)
-		res = fuse_direct_io(io, iov, nr_segs, count, ppos,
-				     FUSE_DIO_WRITE);
+	if (!res) {
+		iov_iter_truncate(iter, count);
+		res = fuse_direct_io(io, iter, ppos, FUSE_DIO_WRITE);
+	}
 
 	fuse_invalidate_attr(inode);
 
@@ -1512,13 +1477,15 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
 	struct inode *inode = file_inode(file);
 	ssize_t res;
 	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct iov_iter ii;
+	iov_iter_init(&ii, WRITE, &iov, 1, count);
 
 	if (is_bad_inode(inode))
 		return -EIO;
 
 	/* Don't allow parallel writes to the same file */
 	mutex_lock(&inode->i_mutex);
-	res = __fuse_direct_write(&io, &iov, 1, ppos);
+	res = __fuse_direct_write(&io, &ii, ppos);
 	if (res > 0)
 		fuse_write_update_size(inode, *ppos);
 	mutex_unlock(&inode->i_mutex);
@@ -2372,7 +2339,7 @@ static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov,
 	if (!bytes)
 		return 0;
 
-	iov_iter_init(&ii, iov, nr_segs, bytes, 0);
+	iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes);
 
 	while (iov_iter_count(&ii)) {
 		struct page *page = pages[page_idx++];
@@ -2894,8 +2861,8 @@ static inline loff_t fuse_round_up(loff_t off)
 }
 
 static ssize_t
-fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs)
+fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+			loff_t offset)
 {
 	ssize_t ret = 0;
 	struct file *file = iocb->ki_filp;
@@ -2904,7 +2871,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	loff_t pos = 0;
 	struct inode *inode;
 	loff_t i_size;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	struct fuse_io_priv *io;
 
 	pos = offset;
@@ -2919,6 +2886,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 		if (offset >= i_size)
 			return 0;
 		count = min_t(loff_t, count, fuse_round_up(i_size - offset));
+		iov_iter_truncate(iter, count);
 	}
 
 	io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
@@ -2948,9 +2916,9 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 		io->async = false;
 
 	if (rw == WRITE)
-		ret = __fuse_direct_write(io, iov, nr_segs, &pos);
+		ret = __fuse_direct_write(io, iter, &pos);
 	else
-		ret = __fuse_direct_read(io, iov, nr_segs, &pos, count);
+		ret = __fuse_direct_read(io, iter, &pos);
 
 	if (io->async) {
 		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
@@ -3061,10 +3029,10 @@ out:
 
 static const struct file_operations fuse_file_operations = {
 	.llseek		= fuse_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= fuse_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= fuse_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= fuse_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= fuse_file_write_iter,
 	.mmap		= fuse_file_mmap,
 	.open		= fuse_open,
 	.flush		= fuse_flush,
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 7aa5c75e0de..e8e47a6ab51 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -880,9 +880,8 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 /** CUSE pass fuse_direct_io() a file which f_mapping->host is not from FUSE */
 #define FUSE_DIO_CUSE  (1 << 1)
 
-ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
-		       unsigned long nr_segs, size_t count, loff_t *ppos,
-		       int flags);
+ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
+		       loff_t *ppos, int flags);
 long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		   unsigned int flags);
 long fuse_ioctl_common(struct file *file, unsigned int cmd,