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

Pull iov_iter updates from Al Viro:

 - bio_{map,copy}_user_iov() series; those are cleanups - fixes from the
   same pile went into mainline (and stable) in late September.

 - fs/iomap.c iov_iter-related fixes

 - new primitive - iov_iter_for_each_range(), which applies a function
   to kernel-mapped segments of an iov_iter.

   Usable for kvec and bvec ones, the latter does kmap()/kunmap() around
   the callback. _Not_ usable for iovec- or pipe-backed iov_iter; the
   latter is not hard to fix if the need ever appears, the former is by
   design.

   Another related primitive will have to wait for the next cycle - it
   passes page + offset + size instead of pointer + size, and that one
   will be usable for everything _except_ kvec. Unfortunately, that one
   didn't get exposure in -next yet, so...

 - a bit more lustre iov_iter work, including a use case for
   iov_iter_for_each_range() (checksum calculation)

 - vhost/scsi leak fix in failure exit

 - misc cleanups and detritectomy...

* 'work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (21 commits)
  iomap_dio_actor(): fix iov_iter bugs
  switch ksocknal_lib_recv_...() to use of iov_iter_for_each_range()
  lustre: switch struct ksock_conn to iov_iter
  vhost/scsi: switch to iov_iter_get_pages()
  fix a page leak in vhost_scsi_iov_to_sgl() error recovery
  new primitive: iov_iter_for_each_range()
  lnet_return_rx_credits_locked: don't abuse list_entry
  xen: don't open-code iov_iter_kvec()
  orangefs: remove detritus from struct orangefs_kiocb_s
  kill iov_shorten()
  bio_alloc_map_data(): do bmd->iter setup right there
  bio_copy_user_iov(): saner bio size calculation
  bio_map_user_iov(): get rid of copying iov_iter
  bio_copy_from_iter(): get rid of copying iov_iter
  move more stuff down into bio_copy_user_iov()
  blk_rq_map_user_iov(): move iov_iter_advance() down
  bio_map_user_iov(): get rid of the iov_for_each()
  bio_map_user_iov(): move alignment check into the main loop
  don't rely upon subsequent bio_add_pc_page() calls failing
  ... and with iov_iter_get_pages_alloc() it becomes even simpler
  ...

3 files changed, 15 insertions, 36 deletions

diff --git a/fs/iomap.c b/fs/iomap.c
index b9f74803e56c..47d29ccffaef 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -856,6 +856,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct bio *bio;
 	bool need_zeroout = false;
 	int nr_pages, ret;
+	size_t copied = 0;
 
 	if ((pos | length | align) & ((1 << blkbits) - 1))
 		return -EINVAL;
@@ -867,7 +868,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		/*FALLTHRU*/
 	case IOMAP_UNWRITTEN:
 		if (!(dio->flags & IOMAP_DIO_WRITE)) {
-			iov_iter_zero(length, dio->submit.iter);
+			length = iov_iter_zero(length, dio->submit.iter);
 			dio->size += length;
 			return length;
 		}
@@ -904,8 +905,11 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	}
 
 	do {
-		if (dio->error)
+		size_t n;
+		if (dio->error) {
+			iov_iter_revert(dio->submit.iter, copied);
 			return 0;
+		}
 
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 		bio_set_dev(bio, iomap->bdev);
@@ -918,20 +922,24 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		ret = bio_iov_iter_get_pages(bio, &iter);
 		if (unlikely(ret)) {
 			bio_put(bio);
-			return ret;
+			return copied ? copied : ret;
 		}
 
+		n = bio->bi_iter.bi_size;
 		if (dio->flags & IOMAP_DIO_WRITE) {
 			bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_SYNC | REQ_IDLE);
-			task_io_account_write(bio->bi_iter.bi_size);
+			task_io_account_write(n);
 		} else {
 			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 			if (dio->flags & IOMAP_DIO_DIRTY)
 				bio_set_pages_dirty(bio);
 		}
 
-		dio->size += bio->bi_iter.bi_size;
-		pos += bio->bi_iter.bi_size;
+		iov_iter_advance(dio->submit.iter, n);
+
+		dio->size += n;
+		pos += n;
+		copied += n;
 
 		nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
 
@@ -947,9 +955,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		if (pad)
 			iomap_dio_zero(dio, iomap, pos, fs_block_size - pad);
 	}
-
-	iov_iter_advance(dio->submit.iter, length);
-	return length;
+	return copied;
 }
 
 ssize_t
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 004af348fb80..f44d5eb74fcc 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -275,12 +275,6 @@ struct orangefs_kiocb_s {
 	/* orangefs kernel operation type */
 	struct orangefs_kernel_op_s *op;
 
-	/* The user space buffers from/to which I/O is being staged */
-	struct iovec *iov;
-
-	/* number of elements in the iovector */
-	unsigned long nr_segs;
-
 	/* set to indicate the type of the operation */
 	int rw;
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 0046d72efe94..f8547b82dfb3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -635,27 +635,6 @@ SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
 	return ret;
 }
 
-/*
- * Reduce an iovec's length in-place.  Return the resulting number of segments
- */
-unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
-{
-	unsigned long seg = 0;
-	size_t len = 0;
-
-	while (seg < nr_segs) {
-		seg++;
-		if (len + iov->iov_len >= to) {
-			iov->iov_len = to - len;
-			break;
-		}
-		len += iov->iov_len;
-		iov++;
-	}
-	return seg;
-}
-EXPORT_SYMBOL(iov_shorten);
-
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 		loff_t *ppos, int type, rwf_t flags)
 {