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

Pull vfs updates from Al Viro:
 "The first vfs pile, with deep apologies for being very late in this
  window.

  Assorted cleanups and fixes, plus a large preparatory part of iov_iter
  work.  There's a lot more of that, but it'll probably go into the next
  merge window - it *does* shape up nicely, removes a lot of
  boilerplate, gets rid of locking inconsistencie between aio_write and
  splice_write and I hope to get Kent's direct-io rewrite merged into
  the same queue, but some of the stuff after this point is having
  (mostly trivial) conflicts with the things already merged into
  mainline and with some I want more testing.

  This one passes LTP and xfstests without regressions, in addition to
  usual beating.  BTW, readahead02 in ltp syscalls testsuite has started
  giving failures since "mm/readahead.c: fix readahead failure for
  memoryless NUMA nodes and limit readahead pages" - might be a false
  positive, might be a real regression..."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
  missing bits of "splice: fix racy pipe->buffers uses"
  cifs: fix the race in cifs_writev()
  ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
  kill generic_file_buffered_write()
  ocfs2_file_aio_write(): switch to generic_perform_write()
  ceph_aio_write(): switch to generic_perform_write()
  xfs_file_buffered_aio_write(): switch to generic_perform_write()
  export generic_perform_write(), start getting rid of generic_file_buffer_write()
  generic_file_direct_write(): get rid of ppos argument
  btrfs_file_aio_write(): get rid of ppos
  kill the 5th argument of generic_file_buffered_write()
  kill the 4th argument of __generic_file_aio_write()
  lustre: don't open-code kernel_recvmsg()
  ocfs2: don't open-code kernel_recvmsg()
  drbd: don't open-code kernel_recvmsg()
  constify blk_rq_map_user_iov() and friends
  lustre: switch to kernel_sendmsg()
  ocfs2: don't open-code kernel_sendmsg()
  take iov_iter stuff to mm/iov_iter.c
  process_vm_access: tidy up a bit
  ...

9 files changed, 71 insertions, 118 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5aa372a7380c..bba550826921 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -388,7 +388,7 @@ struct sg_iovec;
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
 				    struct block_device *,
-				    struct sg_iovec *, int, int, gfp_t);
+				    const struct sg_iovec *, int, int, gfp_t);
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
@@ -414,7 +414,8 @@ extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
 extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
 				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
-				     struct rq_map_data *, struct sg_iovec *,
+				     struct rq_map_data *,
+				     const struct sg_iovec *,
 				     int, int, gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 99617cf7dd1a..0d84981ee03f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -835,8 +835,8 @@ extern int blk_rq_map_user(struct request_queue *, struct request *,
 extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct rq_map_data *, struct sg_iovec *, int,
-			       unsigned int, gfp_t);
+			       struct rq_map_data *, const struct sg_iovec *,
+			       int, unsigned int, gfp_t);
 extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index d77797a52b7b..c40302f909ce 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -210,8 +210,8 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 			struct writeback_control *wbc, bh_end_io_t *handler);
 int block_read_full_page(struct page*, get_block_t*);
-int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
-				unsigned long from);
+int block_is_partially_uptodate(struct page *page, unsigned long from,
+				unsigned long count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		unsigned flags, struct page **pagep, get_block_t *get_block);
 int __block_write_begin(struct page *page, loff_t pos, unsigned len,
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 70e8e21c0a30..230f87bdf5ad 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -63,8 +63,6 @@ struct file_operations;
 struct vfsmount;
 struct dentry;
 
-extern void __init files_defer_init(void);
-
 #define rcu_dereference_check_fdtable(files, fdtfd) \
 	rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock))
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 81048f9bc783..7a9c5bca2b76 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -48,6 +48,7 @@ struct cred;
 struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
+struct iov_iter;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -125,6 +126,8 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 
 /* File needs atomic accesses to f_pos */
 #define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
+/* Write access to underlying fs */
+#define FMODE_WRITER		((__force fmode_t)0x10000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
@@ -293,38 +296,6 @@ struct page;
 struct address_space;
 struct writeback_control;
 
-struct iov_iter {
-	const struct iovec *iov;
-	unsigned long nr_segs;
-	size_t iov_offset;
-	size_t count;
-};
-
-size_t iov_iter_copy_from_user_atomic(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes);
-size_t iov_iter_copy_from_user(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes);
-void iov_iter_advance(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
-size_t iov_iter_single_seg_count(const struct iov_iter *i);
-
-static inline void iov_iter_init(struct iov_iter *i,
-			const struct iovec *iov, unsigned long nr_segs,
-			size_t count, size_t written)
-{
-	i->iov = iov;
-	i->nr_segs = nr_segs;
-	i->iov_offset = 0;
-	i->count = count + written;
-
-	iov_iter_advance(i, written);
-}
-
-static inline size_t iov_iter_count(struct iov_iter *i)
-{
-	return i->count;
-}
-
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
@@ -383,7 +354,7 @@ struct address_space_operations {
 	int (*migratepage) (struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 	int (*launder_page) (struct page *);
-	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
+	int (*is_partially_uptodate) (struct page *, unsigned long,
 					unsigned long);
 	void (*is_dirty_writeback) (struct page *, bool *, bool *);
 	int (*error_remove_page)(struct address_space *, struct page *);
@@ -770,9 +741,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 		index <  ra->start + ra->size);
 }
 
-#define FILE_MNT_WRITE_TAKEN	1
-#define FILE_MNT_WRITE_RELEASED	2
-
 struct file {
 	union {
 		struct llist_node	fu_llist;
@@ -810,9 +778,6 @@ struct file {
 	struct list_head	f_tfile_llink;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
-#ifdef CONFIG_DEBUG_WRITECOUNT
-	unsigned long f_mnt_write_state;
-#endif
 } __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
 struct file_handle {
@@ -830,49 +795,6 @@ static inline struct file *get_file(struct file *f)
 #define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
 
-#ifdef CONFIG_DEBUG_WRITECOUNT
-static inline void file_take_write(struct file *f)
-{
-	WARN_ON(f->f_mnt_write_state != 0);
-	f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
-}
-static inline void file_release_write(struct file *f)
-{
-	f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
-}
-static inline void file_reset_write(struct file *f)
-{
-	f->f_mnt_write_state = 0;
-}
-static inline void file_check_state(struct file *f)
-{
-	/*
-	 * At this point, either both or neither of these bits
-	 * should be set.
-	 */
-	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
-	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
-}
-static inline int file_check_writeable(struct file *f)
-{
-	if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
-		return 0;
-	printk(KERN_WARNING "writeable file with no "
-			    "mnt_want_write()\n");
-	WARN_ON(1);
-	return -EINVAL;
-}
-#else /* !CONFIG_DEBUG_WRITECOUNT */
-static inline void file_take_write(struct file *filp) {}
-static inline void file_release_write(struct file *filp) {}
-static inline void file_reset_write(struct file *filp) {}
-static inline void file_check_state(struct file *filp) {}
-static inline int file_check_writeable(struct file *filp)
-{
-	return 0;
-}
-#endif /* CONFIG_DEBUG_WRITECOUNT */
-
 #define	MAX_NON_LFS	((1UL<<31) - 1)
 
 /* Page cache limit. The filesystems should put that into their s_maxbytes 
@@ -2481,16 +2403,13 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
 		unsigned long size, pgoff_t pgoff);
-extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
-extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
-		loff_t *);
+extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long);
 extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
-		unsigned long *, loff_t, loff_t *, size_t, size_t);
-extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
-		unsigned long, loff_t, loff_t *, size_t, ssize_t);
+		unsigned long *, loff_t, size_t, size_t);
+extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 extern int generic_segment_checks(const struct iovec *iov,
@@ -2582,7 +2501,7 @@ extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 
-extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
+extern int readlink_copy(char __user *, int, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
 extern void *page_follow_link_light(struct dentry *, struct nameidata *);
 extern void page_put_link(struct dentry *, struct nameidata *, void *);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 371d346fa270..839bac270904 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -44,6 +44,8 @@ struct mnt_namespace;
 #define MNT_SHARED_MASK	(MNT_UNBINDABLE)
 #define MNT_PROPAGATION_MASK	(MNT_SHARED | MNT_UNBINDABLE)
 
+#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED)
 
 #define MNT_INTERNAL	0x4000
 
@@ -51,6 +53,7 @@ struct mnt_namespace;
 #define MNT_LOCKED		0x800000
 #define MNT_DOOMED		0x1000000
 #define MNT_SYNC_UMOUNT		0x2000000
+#define MNT_MARKED		0x4000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
diff --git a/include/linux/nbd.h b/include/linux/nbd.h
index ae4981ebd18e..f62f78aef4ac 100644
--- a/include/linux/nbd.h
+++ b/include/linux/nbd.h
@@ -24,8 +24,7 @@ struct request;
 struct nbd_device {
 	int flags;
 	int harderror;		/* Code of hard error			*/
-	struct socket * sock;
-	struct file * file; 	/* If == NULL, device is not ready, yet	*/
+	struct socket * sock;	/* If == NULL, device is not ready, yet	*/
 	int magic;
 
 	spinlock_t queue_lock;
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 4d9389c79e61..eb8b8ac6df3c 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -83,23 +83,6 @@ struct pipe_buf_operations {
 	int can_merge;
 
 	/*
-	 * ->map() returns a virtual address mapping of the pipe buffer.
-	 * The last integer flag reflects whether this should be an atomic
-	 * mapping or not. The atomic map is faster, however you can't take
-	 * page faults before calling ->unmap() again. So if you need to eg
-	 * access user data through copy_to/from_user(), then you must get
-	 * a non-atomic map. ->map() uses the kmap_atomic slot for
-	 * atomic maps, you have to be careful if mapping another page as
-	 * source or destination for a copy.
-	 */
-	void * (*map)(struct pipe_inode_info *, struct pipe_buffer *, int);
-
-	/*
-	 * Undoes ->map(), finishes the virtual mapping of the pipe buffer.
-	 */
-	void (*unmap)(struct pipe_inode_info *, struct pipe_buffer *, void *);
-
-	/*
 	 * ->confirm() verifies that the data in the pipe buffer is there
 	 * and that the contents are good. If the pages in the pipe belong
 	 * to a file system, we may need to wait for IO completion in this
@@ -150,8 +133,6 @@ struct pipe_inode_info *alloc_pipe_info(void);
 void free_pipe_info(struct pipe_inode_info *);
 
 /* Generic pipe buffer ops functions */
-void *generic_pipe_buf_map(struct pipe_inode_info *, struct pipe_buffer *, int);
-void generic_pipe_buf_unmap(struct pipe_inode_info *, struct pipe_buffer *, void *);
 void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
diff --git a/include/linux/uio.h b/include/linux/uio.h
index c55ce243cc09..199bcc34241b 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -9,14 +9,23 @@
 #ifndef __LINUX_UIO_H
 #define __LINUX_UIO_H
 
+#include <linux/kernel.h>
 #include <uapi/linux/uio.h>
 
+struct page;
 
 struct kvec {
 	void *iov_base; /* and that should *never* hold a userland pointer */
 	size_t iov_len;
 };
 
+struct iov_iter {
+	const struct iovec *iov;
+	unsigned long nr_segs;
+	size_t iov_offset;
+	size_t count;
+};
+
 /*
  * Total number of bytes covered by an iovec.
  *
@@ -34,8 +43,51 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 	return ret;
 }
 
+static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
+{
+	return (struct iovec) {
+		.iov_base = iter->iov->iov_base + iter->iov_offset,
+		.iov_len = min(iter->count,
+			       iter->iov->iov_len - iter->iov_offset),
+	};
+}
+
+#define iov_for_each(iov, iter, start)				\
+	for (iter = (start);					\
+	     (iter).count &&					\
+	     ((iov = iov_iter_iovec(&(iter))), 1);		\
+	     iov_iter_advance(&(iter), (iov).iov_len))
+
 unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to);
 
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+size_t iov_iter_copy_from_user(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+void iov_iter_advance(struct iov_iter *i, size_t bytes);
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
+size_t iov_iter_single_seg_count(const struct iov_iter *i);
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i);
+
+static inline void iov_iter_init(struct iov_iter *i,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t count, size_t written)
+{
+	i->iov = iov;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count + written;
+
+	iov_iter_advance(i, written);
+}
+
+static inline size_t iov_iter_count(struct iov_iter *i)
+{
+	return i->count;
+}
+
 int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len);
+
 #endif