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()
  ...

Documentation/filesystems/Locking

@@ -196,8 +196,7 @@ prototypes:
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs);
+	int (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
 	int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
 				unsigned long *);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
@@ -431,6 +430,8 @@ prototypes:
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
+	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
+	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);

Documentation/filesystems/vfs.txt

@@ -589,8 +589,7 @@ struct address_space_operations {
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs);
+	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
 	struct page* (*get_xip_page)(struct address_space *, sector_t,
 			int);
 	/* migrate the contents of a page to the specified target */
@@ -807,6 +806,8 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
+	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
+	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
@@ -837,11 +838,15 @@ otherwise noted.
 
   read: called by read(2) and related system calls
 
-  aio_read: called by io_submit(2) and other asynchronous I/O operations
+  aio_read: vectored, possibly asynchronous read
+
+  read_iter: possibly asynchronous read with iov_iter as destination
 
   write: called by write(2) and related system calls
 
-  aio_write: called by io_submit(2) and other asynchronous I/O operations
+  aio_write: vectored, possibly asynchronous write
+
+  write_iter: possibly asynchronous write with iov_iter as source
 
   iterate: called when the VFS needs to read the directory contents
 

drivers/char/raw.c

@@ -284,10 +284,10 @@ static long raw_ctl_compat_ioctl(struct file *file, unsigned int cmd,
 #endif
 
 static const struct file_operations raw_fops = {
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= blkdev_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= blkdev_write_iter,
 	.fsync		= blkdev_fsync,
 	.open		= raw_open,
 	.release	= raw_release,

drivers/mtd/nand/nandsim.c

@@ -575,12 +575,12 @@ static int alloc_device(struct nandsim *ns)
 		cfile = filp_open(cache_file, O_CREAT | O_RDWR | O_LARGEFILE, 0600);
 		if (IS_ERR(cfile))
 			return PTR_ERR(cfile);
-		if (!cfile->f_op->read && !cfile->f_op->aio_read) {
+		if (!(cfile->f_mode & FMODE_CAN_READ)) {
 			NS_ERR("alloc_device: cache file not readable\n");
 			err = -EINVAL;
 			goto err_close;
 		}
-		if (!cfile->f_op->write && !cfile->f_op->aio_write) {
+		if (!(cfile->f_mode & FMODE_CAN_WRITE)) {
 			NS_ERR("alloc_device: cache file not writeable\n");
 			err = -EINVAL;
 			goto err_close;

drivers/staging/lustre/lustre/include/lclient.h

@@ -82,16 +82,7 @@ struct ccc_io {
 	/**
 	 * I/O vector information to or from which read/write is going.
 	 */
-	struct iovec *cui_iov;
-	unsigned long cui_nrsegs;
-	/**
-	 * Total iov count for left IO.
-	 */
-	unsigned long cui_tot_nrsegs;
-	/**
-	 * Old length for iov that was truncated partially.
-	 */
-	size_t cui_iov_olen;
+	struct iov_iter *cui_iter;
 	/**
 	 * Total size for the left IO.
 	 */

drivers/staging/lustre/lustre/lclient/lcommon_cl.c

@@ -720,31 +720,12 @@ int ccc_io_one_lock_index(const struct lu_env *env, struct cl_io *io,
 void ccc_io_update_iov(const struct lu_env *env,
 		       struct ccc_io *cio, struct cl_io *io)
 {
-	int i;
 	size_t size = io->u.ci_rw.crw_count;
 
-	cio->cui_iov_olen = 0;
-	if (!cl_is_normalio(env, io) || cio->cui_tot_nrsegs == 0)
+	if (!cl_is_normalio(env, io) || cio->cui_iter == NULL)
 		return;
 
-	for (i = 0; i < cio->cui_tot_nrsegs; i++) {
-		struct iovec *iv = &cio->cui_iov[i];
-
-		if (iv->iov_len < size)
-			size -= iv->iov_len;
-		else {
-			if (iv->iov_len > size) {
-				cio->cui_iov_olen = iv->iov_len;
-				iv->iov_len = size;
-			}
-			break;
-		}
-	}
-
-	cio->cui_nrsegs = i + 1;
-	LASSERTF(cio->cui_tot_nrsegs >= cio->cui_nrsegs,
-		 "tot_nrsegs: %lu, nrsegs: %lu\n",
-		 cio->cui_tot_nrsegs, cio->cui_nrsegs);
+	iov_iter_truncate(cio->cui_iter, size);
 }
 
 int ccc_io_one_lock(const struct lu_env *env, struct cl_io *io,
@@ -775,30 +756,7 @@ void ccc_io_advance(const struct lu_env *env,
 	if (!cl_is_normalio(env, io))
 		return;
 
-	LASSERT(cio->cui_tot_nrsegs >= cio->cui_nrsegs);
-	LASSERT(cio->cui_tot_count  >= nob);
-
-	cio->cui_iov	+= cio->cui_nrsegs;
-	cio->cui_tot_nrsegs -= cio->cui_nrsegs;
-	cio->cui_tot_count  -= nob;
-
-	/* update the iov */
-	if (cio->cui_iov_olen > 0) {
-		struct iovec *iv;
-
-		cio->cui_iov--;
-		cio->cui_tot_nrsegs++;
-		iv = &cio->cui_iov[0];
-		if (io->ci_continue) {
-			iv->iov_base += iv->iov_len;
-			LASSERT(cio->cui_iov_olen > iv->iov_len);
-			iv->iov_len = cio->cui_iov_olen - iv->iov_len;
-		} else {
-			/* restore the iov_len, in case of restart io. */
-			iv->iov_len = cio->cui_iov_olen;
-		}
-		cio->cui_iov_olen = 0;
-	}
+	iov_iter_reexpand(cio->cui_iter, cio->cui_tot_count  -= nob);
 }
 
 /**

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

@@ -1114,9 +1114,7 @@ restart:
 
 		switch (vio->cui_io_subtype) {
 		case IO_NORMAL:
-			cio->cui_iov = args->u.normal.via_iov;
-			cio->cui_nrsegs = args->u.normal.via_nrsegs;
-			cio->cui_tot_nrsegs = cio->cui_nrsegs;
+			cio->cui_iter = args->u.normal.via_iter;
 			cio->cui_iocb = args->u.normal.via_iocb;
 			if ((iot == CIT_WRITE) &&
 			    !(cio->cui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
@@ -1180,58 +1178,23 @@ out:
 	return result;
 }
 
-static ssize_t ll_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+static ssize_t ll_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct lu_env      *env;
 	struct vvp_io_args *args;
-	size_t	      count = 0;
 	ssize_t	     result;
 	int		 refcheck;
 
-	result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
-	if (result)
-		return result;
-
 	env = cl_env_get(&refcheck);
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
 	args = vvp_env_args(env, IO_NORMAL);
-	args->u.normal.via_iov = (struct iovec *)iov;
-	args->u.normal.via_nrsegs = nr_segs;
+	args->u.normal.via_iter = to;
 	args->u.normal.via_iocb = iocb;
 
 	result = ll_file_io_generic(env, args, iocb->ki_filp, CIT_READ,
-				    &iocb->ki_pos, count);
-	cl_env_put(env, &refcheck);
-	return result;
-}
-
-static ssize_t ll_file_read(struct file *file, char *buf, size_t count,
-			    loff_t *ppos)
-{
-	struct lu_env *env;
-	struct iovec  *local_iov;
-	struct kiocb  *kiocb;
-	ssize_t	result;
-	int	    refcheck;
-
-	env = cl_env_get(&refcheck);
-	if (IS_ERR(env))
-		return PTR_ERR(env);
-
-	local_iov = &vvp_env_info(env)->vti_local_iov;
-	kiocb = &vvp_env_info(env)->vti_kiocb;
-	local_iov->iov_base = (void __user *)buf;
-	local_iov->iov_len = count;
-	init_sync_kiocb(kiocb, file);
-	kiocb->ki_pos = *ppos;
-	kiocb->ki_nbytes = count;
-
-	result = ll_file_aio_read(kiocb, local_iov, 1, kiocb->ki_pos);
-	*ppos = kiocb->ki_pos;
-
+				    &iocb->ki_pos, iov_iter_count(to));
 	cl_env_put(env, &refcheck);
 	return result;
 }
@@ -1239,64 +1202,27 @@ static ssize_t ll_file_read(struct file *file, char *buf, size_t count,
 /*
  * Write to a file (through the page cache).
  */
-static ssize_t ll_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs, loff_t pos)
+static ssize_t ll_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct lu_env      *env;
 	struct vvp_io_args *args;
-	size_t	      count = 0;
 	ssize_t	     result;
 	int		 refcheck;
 
-	result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
-	if (result)
-		return result;
-
 	env = cl_env_get(&refcheck);
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
 	args = vvp_env_args(env, IO_NORMAL);
-	args->u.normal.via_iov = (struct iovec *)iov;
-	args->u.normal.via_nrsegs = nr_segs;
+	args->u.normal.via_iter = from;
 	args->u.normal.via_iocb = iocb;
 
 	result = ll_file_io_generic(env, args, iocb->ki_filp, CIT_WRITE,
-				  &iocb->ki_pos, count);
+				  &iocb->ki_pos, iov_iter_count(from));
 	cl_env_put(env, &refcheck);
 	return result;
 }
 
-static ssize_t ll_file_write(struct file *file, const char *buf, size_t count,
-			     loff_t *ppos)
-{
-	struct lu_env *env;
-	struct iovec  *local_iov;
-	struct kiocb  *kiocb;
-	ssize_t	result;
-	int	    refcheck;
-
-	env = cl_env_get(&refcheck);
-	if (IS_ERR(env))
-		return PTR_ERR(env);
-
-	local_iov = &vvp_env_info(env)->vti_local_iov;
-	kiocb = &vvp_env_info(env)->vti_kiocb;
-	local_iov->iov_base = (void __user *)buf;
-	local_iov->iov_len = count;
-	init_sync_kiocb(kiocb, file);
-	kiocb->ki_pos = *ppos;
-	kiocb->ki_nbytes = count;
-
-	result = ll_file_aio_write(kiocb, local_iov, 1, kiocb->ki_pos);
-	*ppos = kiocb->ki_pos;
-
-	cl_env_put(env, &refcheck);
-	return result;
-}
-
-
-
 /*
  * Send file content (through pagecache) somewhere with helper
  */
@@ -3143,10 +3069,10 @@ int ll_inode_permission(struct inode *inode, int mask)
 
 /* -o localflock - only provides locally consistent flock locks */
 struct file_operations ll_file_operations = {
-	.read	   = ll_file_read,
-	.aio_read = ll_file_aio_read,
-	.write	  = ll_file_write,
-	.aio_write = ll_file_aio_write,
+	.read	   = new_sync_read,
+	.read_iter = ll_file_read_iter,
+	.write	  = new_sync_write,
+	.write_iter = ll_file_write_iter,
 	.unlocked_ioctl = ll_file_ioctl,
 	.open	   = ll_file_open,
 	.release	= ll_file_release,
@@ -3158,10 +3084,10 @@ struct file_operations ll_file_operations = {
 };
 
 struct file_operations ll_file_operations_flock = {
-	.read	   = ll_file_read,
-	.aio_read    = ll_file_aio_read,
-	.write	  = ll_file_write,
-	.aio_write   = ll_file_aio_write,
+	.read	   = new_sync_read,
+	.read_iter    = ll_file_read_iter,
+	.write	  = new_sync_write,
+	.write_iter   = ll_file_write_iter,
 	.unlocked_ioctl = ll_file_ioctl,
 	.open	   = ll_file_open,
 	.release	= ll_file_release,
@@ -3176,10 +3102,10 @@ struct file_operations ll_file_operations_flock = {
 
 /* These are for -o noflock - to return ENOSYS on flock calls */
 struct file_operations ll_file_operations_noflock = {
-	.read	   = ll_file_read,
-	.aio_read    = ll_file_aio_read,
-	.write	  = ll_file_write,
-	.aio_write   = ll_file_aio_write,
+	.read	   = new_sync_read,
+	.read_iter    = ll_file_read_iter,
+	.write	  = new_sync_write,
+	.write_iter   = ll_file_write_iter,
 	.unlocked_ioctl = ll_file_ioctl,
 	.open	   = ll_file_open,
 	.release	= ll_file_release,

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

@@ -917,8 +917,7 @@ struct vvp_io_args {
 	union {
 		struct {
 			struct kiocb      *via_iocb;
-			struct iovec      *via_iov;
-			unsigned long      via_nrsegs;
+			struct iov_iter   *via_iter;
 		} normal;
 		struct {
 			struct pipe_inode_info  *via_pipe;

drivers/staging/lustre/lustre/llite/rw.c

@@ -151,8 +151,7 @@ static struct ll_cl_context *ll_cl_init(struct file *file,
 		result = cl_io_rw_init(env, io, CIT_WRITE, pos, PAGE_CACHE_SIZE);
 		if (result == 0) {
 			cio->cui_fd = LUSTRE_FPRIVATE(file);
-			cio->cui_iov = NULL;
-			cio->cui_nrsegs = 0;
+			cio->cui_iter = NULL;
 			result = cl_io_iter_init(env, io);
 			if (result == 0) {
 				result = cl_io_lock(env, io);

drivers/staging/lustre/lustre/llite/rw26.c

@@ -218,14 +218,11 @@ static void ll_free_user_pages(struct page **pages, int npages, int do_dirty)
 	int i;
 
 	for (i = 0; i < npages; i++) {
-		if (pages[i] == NULL)
-			break;
 		if (do_dirty)
 			set_page_dirty_lock(pages[i]);
 		page_cache_release(pages[i]);
 	}
-
-	OBD_FREE_LARGE(pages, npages * sizeof(*pages));
+	kvfree(pages);
 }
 
 ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io,
@@ -363,18 +360,16 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io,
 #define MAX_DIO_SIZE ((MAX_MALLOC / sizeof(struct brw_page) * PAGE_CACHE_SIZE) & \
 		      ~(DT_MAX_BRW_SIZE - 1))
 static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
-			       const struct iovec *iov, loff_t file_offset,
-			       unsigned long nr_segs)
+			       struct iov_iter *iter, loff_t file_offset)
 {
 	struct lu_env *env;
 	struct cl_io *io;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct ccc_object *obj = cl_inode2ccc(inode);
-	long count = iov_length(iov, nr_segs);
-	long tot_bytes = 0, result = 0;
+	ssize_t count = iov_iter_count(iter);
+	ssize_t tot_bytes = 0, result = 0;
 	struct ll_inode_info *lli = ll_i2info(inode);
-	unsigned long seg = 0;
 	long size = MAX_DIO_SIZE;
 	int refcheck;
 
@@ -392,11 +387,8 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 	       MAX_DIO_SIZE >> PAGE_CACHE_SHIFT);
 
 	/* Check that all user buffers are aligned as well */
-	for (seg = 0; seg < nr_segs; seg++) {
-		if (((unsigned long)iov[seg].iov_base & ~CFS_PAGE_MASK) ||
-		    (iov[seg].iov_len & ~CFS_PAGE_MASK))
+	if (iov_iter_alignment(iter) & ~CFS_PAGE_MASK)
 		return -EINVAL;
-	}
 
 	env = cl_env_get(&refcheck);
 	LASSERT(!IS_ERR(env));
@@ -411,37 +403,26 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 		mutex_lock(&inode->i_mutex);
 
 	LASSERT(obj->cob_transient_pages == 0);
-	for (seg = 0; seg < nr_segs; seg++) {
-		long iov_left = iov[seg].iov_len;
-		unsigned long user_addr = (unsigned long)iov[seg].iov_base;
+	while (iov_iter_count(iter)) {
+		struct page **pages;
+		size_t offs;
 
+		count = min_t(size_t, iov_iter_count(iter), size);
 		if (rw == READ) {
 			if (file_offset >= i_size_read(inode))
 				break;
-			if (file_offset + iov_left > i_size_read(inode))
-				iov_left = i_size_read(inode) - file_offset;
+			if (file_offset + count > i_size_read(inode))
+				count = i_size_read(inode) - file_offset;
 		}
 
-		while (iov_left > 0) {
-			struct page **pages;
-			int page_count, max_pages = 0;
-			long bytes;
-
-			bytes = min(size, iov_left);
-			page_count = ll_get_user_pages(rw, user_addr, bytes,
-						       &pages, &max_pages);
-			if (likely(page_count > 0)) {
-				if (unlikely(page_count <  max_pages))
-					bytes = page_count << PAGE_CACHE_SHIFT;
+		result = iov_iter_get_pages_alloc(iter, &pages, count, &offs);
+		if (likely(result > 0)) {
+			int n = (result + offs + PAGE_SIZE - 1) / PAGE_SIZE;
 			result = ll_direct_IO_26_seg(env, io, rw, inode,
 						     file->f_mapping,
-							     bytes, file_offset,
-							     pages, page_count);
-				ll_free_user_pages(pages, max_pages, rw==READ);
-			} else if (page_count == 0) {
-				GOTO(out, result = -EFAULT);
-			} else {
-				result = page_count;
+						     result, file_offset,
+						     pages, n);
+			ll_free_user_pages(pages, n, rw==READ);
 		}
 		if (unlikely(result <= 0)) {
 			/* If we can't allocate a large enough buffer
@@ -462,12 +443,9 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 
 			GOTO(out, result);
 		}
-
+		iov_iter_advance(iter, result);
 		tot_bytes += result;
 		file_offset += result;
-			iov_left -= result;
-			user_addr += result;
-		}
 	}
 out:
 	LASSERT(obj->cob_transient_pages == 0);

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

@@ -211,27 +211,26 @@ static int vvp_mmap_locks(const struct lu_env *env,
 	struct cl_lock_descr   *descr = &cti->cti_descr;
 	ldlm_policy_data_t      policy;
 	unsigned long	   addr;
-	unsigned long	   seg;
 	ssize_t		 count;
 	int		     result;
+	struct iov_iter i;
+	struct iovec iov;
 
 	LASSERT(io->ci_type == CIT_READ || io->ci_type == CIT_WRITE);
 
 	if (!cl_is_normalio(env, io))
 		return 0;
 
-	if (vio->cui_iov == NULL) /* nfs or loop back device write */
+	if (vio->cui_iter == NULL) /* nfs or loop back device write */
 		return 0;
 
 	/* No MM (e.g. NFS)? No vmas too. */
 	if (mm == NULL)
 		return 0;
 
-	for (seg = 0; seg < vio->cui_nrsegs; seg++) {
-		const struct iovec *iv = &vio->cui_iov[seg];
-
-		addr = (unsigned long)iv->iov_base;
-		count = iv->iov_len;
+	iov_for_each(iov, i, *(vio->cui_iter)) {
+		addr = (unsigned long)iov.iov_base;
+		count = iov.iov_len;
 		if (count == 0)
 			continue;
 
@@ -527,9 +526,7 @@ static int vvp_io_read_start(const struct lu_env *env,
 	switch (vio->cui_io_subtype) {
 	case IO_NORMAL:
 		LASSERT(cio->cui_iocb->ki_pos == pos);
-		result = generic_file_aio_read(cio->cui_iocb,
-					       cio->cui_iov, cio->cui_nrsegs,
-					       cio->cui_iocb->ki_pos);
+		result = generic_file_read_iter(cio->cui_iocb, cio->cui_iter);
 		break;
 	case IO_SPLICE:
 		result = generic_file_splice_read(file, &pos,
@@ -595,12 +592,11 @@ static int vvp_io_write_start(const struct lu_env *env,
 
 	CDEBUG(D_VFSTRACE, "write: [%lli, %lli)\n", pos, pos + (long long)cnt);
 
-	if (cio->cui_iov == NULL) /* from a temp io in ll_cl_init(). */
+	if (cio->cui_iter == NULL) /* from a temp io in ll_cl_init(). */
 		result = 0;
 	else
-		result = generic_file_aio_write(cio->cui_iocb,
-						cio->cui_iov, cio->cui_nrsegs,
-						cio->cui_iocb->ki_pos);
+		result = generic_file_write_iter(cio->cui_iocb, cio->cui_iter);
+
 	if (result > 0) {
 		if (result < cnt)
 			io->ci_continue = 0;
@@ -1162,10 +1158,9 @@ int vvp_io_init(const struct lu_env *env, struct cl_object *obj,
 		 *  results."  -- Single Unix Spec */
 		if (count == 0)
 			result = 1;
-		else {
+		else
 			cio->cui_tot_count = count;
-			cio->cui_tot_nrsegs = 0;
-		}
+
 		/* for read/write, we store the jobid in the inode, and
 		 * it'll be fetched by osc when building RPC.
 		 *

drivers/usb/gadget/storage_common.c

@@ -220,11 +220,11 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
 	 * If we can't read the file, it's no good.
 	 * If we can't write the file, use it read-only.
 	 */
-	if (!(filp->f_op->read || filp->f_op->aio_read)) {
+	if (!(filp->f_mode & FMODE_CAN_READ)) {
 		LINFO(curlun, "file not readable: %s\n", filename);
 		goto out;
 	}
-	if (!(filp->f_op->write || filp->f_op->aio_write))
+	if (!(filp->f_mode & FMODE_CAN_WRITE))
 		ro = 1;
 
 	size = i_size_read(inode->i_mapping->host);

fs/9p/vfs_addr.c

@@ -259,8 +259,7 @@ static int v9fs_launder_page(struct page *page)
  *
  */
 static ssize_t
-v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-	       loff_t pos, unsigned long nr_segs)
+v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
 	/*
 	 * FIXME
@@ -269,7 +268,7 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	 */
 	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n",
 		 iocb->ki_filp->f_path.dentry->d_name.name,
-		 (long long)pos, nr_segs);
+		 (long long)pos, iter->nr_segs);
 
 	return -EINVAL;
 }

fs/9p/vfs_file.c

@@ -692,7 +692,7 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
 {
 	if (filp->f_flags & O_DIRECT)
 		return v9fs_direct_read(filp, data, count, offset);
-	return do_sync_read(filp, data, count, offset);
+	return new_sync_read(filp, data, count, offset);
 }
 
 /**
@@ -760,7 +760,7 @@ err_out:
 
 buff_write:
 	mutex_unlock(&inode->i_mutex);
-	return do_sync_write(filp, data, count, offsetp);
+	return new_sync_write(filp, data, count, offsetp);
 }
 
 /**
@@ -778,7 +778,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data,
 
 	if (filp->f_flags & O_DIRECT)
 		return v9fs_direct_write(filp, data, count, offset);
-	return do_sync_write(filp, data, count, offset);
+	return new_sync_write(filp, data, count, offset);
 }
 
 
@@ -847,8 +847,8 @@ const struct file_operations v9fs_cached_file_operations = {
 	.llseek = generic_file_llseek,
 	.read = v9fs_cached_file_read,
 	.write = v9fs_cached_file_write,
-	.aio_read = generic_file_aio_read,
-	.aio_write = generic_file_aio_write,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
 	.open = v9fs_file_open,
 	.release = v9fs_dir_release,
 	.lock = v9fs_file_lock,
@@ -860,8 +860,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = {
 	.llseek = generic_file_llseek,
 	.read = v9fs_cached_file_read,
 	.write = v9fs_cached_file_write,
-	.aio_read = generic_file_aio_read,
-	.aio_write = generic_file_aio_write,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
 	.open = v9fs_file_open,
 	.release = v9fs_dir_release,
 	.lock = v9fs_file_lock_dotl,

fs/adfs/file.c

@@ -23,12 +23,12 @@
 
 const struct file_operations adfs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= generic_file_fsync,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.splice_read	= generic_file_splice_read,
 };
 

fs/affs/file.c

@@ -27,10 +27,10 @@ static int affs_file_release(struct inode *inode, struct file *filp);
 
 const struct file_operations affs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.open		= affs_file_open,
 	.release	= affs_file_release,

fs/afs/file.c

@@ -31,10 +31,10 @@ const struct file_operations afs_file_operations = {
 	.open		= afs_open,
 	.release	= afs_release,
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= afs_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= afs_file_write,
 	.mmap		= generic_file_readonly_mmap,
 	.splice_read	= generic_file_splice_read,
 	.fsync		= afs_fsync,

fs/afs/internal.h

@@ -747,8 +747,7 @@ extern int afs_write_end(struct file *file, struct address_space *mapping,
 extern int afs_writepage(struct page *, struct writeback_control *);
 extern int afs_writepages(struct address_space *, struct writeback_control *);
 extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *);
-extern ssize_t afs_file_write(struct kiocb *, const struct iovec *,
-			      unsigned long, loff_t);
+extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
 extern int afs_writeback_all(struct afs_vnode *);
 extern int afs_fsync(struct file *, loff_t, loff_t, int);
 

fs/afs/write.c

@@ -625,15 +625,14 @@ void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
 /*
  * write to an AFS file
  */
-ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
-		       unsigned long nr_segs, loff_t pos)
+ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
 	ssize_t result;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(from);
 
-	_enter("{%x.%u},{%zu},%lu,",
-	       vnode->fid.vid, vnode->fid.vnode, count, nr_segs);
+	_enter("{%x.%u},{%zu},",
+	       vnode->fid.vid, vnode->fid.vnode, count);
 
 	if (IS_SWAPFILE(&vnode->vfs_inode)) {
 		printk(KERN_INFO
@@ -644,7 +643,7 @@ ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!count)
 		return 0;
 
-	result = generic_file_aio_write(iocb, iov, nr_segs, pos);
+	result = generic_file_write_iter(iocb, from);
 	if (IS_ERR_VALUE(result)) {
 		_leave(" = %zd", result);
 		return result;

fs/aio.c

@@ -1241,6 +1241,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 
 typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
 			    unsigned long, loff_t);
+typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *);
 
 static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
 				     int rw, char __user *buf,
@@ -1298,7 +1299,9 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
 	int rw;
 	fmode_t mode;
 	aio_rw_op *rw_op;
+	rw_iter_op *iter_op;
 	struct iovec inline_vec, *iovec = &inline_vec;
+	struct iov_iter iter;
 
 	switch (opcode) {
 	case IOCB_CMD_PREAD:
@@ -1306,6 +1309,7 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
 		mode	= FMODE_READ;
 		rw	= READ;
 		rw_op	= file->f_op->aio_read;
+		iter_op	= file->f_op->read_iter;
 		goto rw_common;
 
 	case IOCB_CMD_PWRITE:
@@ -1313,12 +1317,13 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
 		mode	= FMODE_WRITE;
 		rw	= WRITE;
 		rw_op	= file->f_op->aio_write;
+		iter_op	= file->f_op->write_iter;
 		goto rw_common;
 rw_common:
 		if (unlikely(!(file->f_mode & mode)))
 			return -EBADF;
 
-		if (!rw_op)
+		if (!rw_op && !iter_op)
 			return -EINVAL;
 
 		ret = (opcode == IOCB_CMD_PREADV ||
@@ -1347,7 +1352,12 @@ rw_common:
 		if (rw == WRITE)
 			file_start_write(file);
 
+		if (iter_op) {
+			iov_iter_init(&iter, rw, iovec, nr_segs, req->ki_nbytes);
+			ret = iter_op(req, &iter);
+		} else {
 			ret = rw_op(req, iovec, nr_segs, req->ki_pos);
+		}
 
 		if (rw == WRITE)
 			file_end_write(file);