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
  ...

1 files changed, 59 insertions, 285 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 27ebc0c..a82fbe4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -77,7 +77,7 @@
  *  ->mmap_sem
  *    ->lock_page		(access_process_vm)
  *
- *  ->i_mutex			(generic_file_buffered_write)
+ *  ->i_mutex			(generic_perform_write)
  *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
  *
  *  bdi->wb.list_lock
@@ -1428,7 +1428,8 @@ static void shrink_readahead_size_eio(struct file *filp,
  * do_generic_file_read - generic file read routine
  * @filp:	the file to read
  * @ppos:	current file position
- * @desc:	read_descriptor
+ * @iter:	data destination
+ * @written:	already copied
  *
  * This is a generic file read routine, and uses the
  * mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -1436,8 +1437,8 @@ static void shrink_readahead_size_eio(struct file *filp,
  * This is really ugly. But the goto's actually try to clarify some
  * of the logic when it comes to error handling etc.
  */
-static void do_generic_file_read(struct file *filp, loff_t *ppos,
-		read_descriptor_t *desc)
+static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
+		struct iov_iter *iter, ssize_t written)
 {
 	struct address_space *mapping = filp->f_mapping;
 	struct inode *inode = mapping->host;
@@ -1447,12 +1448,12 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos,
 	pgoff_t prev_index;
 	unsigned long offset;      /* offset into pagecache page */
 	unsigned int prev_offset;
-	int error;
+	int error = 0;
 
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT;
 	prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1);
-	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+	last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
 	offset = *ppos & ~PAGE_CACHE_MASK;
 
 	for (;;) {
@@ -1487,7 +1488,7 @@ find_page:
 			if (!page->mapping)
 				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
-								desc, offset))
+							offset, iter->count))
 				goto page_not_up_to_date_locked;
 			unlock_page(page);
 		}
@@ -1537,24 +1538,23 @@ page_ok:
 		/*
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
-		 *
-		 * The file_read_actor routine returns how many bytes were
-		 * actually used..
-		 * NOTE! This may not be the same as how much of a user buffer
-		 * we filled up (we may be padding etc), so we can only update
-		 * "pos" here (the actor routine has to update the user buffer
-		 * pointers and the remaining count).
 		 */
-		ret = file_read_actor(desc, page, offset, nr);
+
+		ret = copy_page_to_iter(page, offset, nr, iter);
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 		prev_offset = offset;
 
 		page_cache_release(page);
-		if (ret == nr && desc->count)
-			continue;
-		goto out;
+		written += ret;
+		if (!iov_iter_count(iter))
+			goto out;
+		if (ret < nr) {
+			error = -EFAULT;
+			goto out;
+		}
+		continue;
 
 page_not_up_to_date:
 		/* Get exclusive access to the page ... */
@@ -1589,6 +1589,7 @@ readpage:
 		if (unlikely(error)) {
 			if (error == AOP_TRUNCATED_PAGE) {
 				page_cache_release(page);
+				error = 0;
 				goto find_page;
 			}
 			goto readpage_error;
@@ -1619,7 +1620,6 @@ readpage:
 
 readpage_error:
 		/* UHHUH! A synchronous read error occurred. Report it */
-		desc->error = error;
 		page_cache_release(page);
 		goto out;
 
@@ -1630,16 +1630,17 @@ no_cached_page:
 		 */
 		page = page_cache_alloc_cold(mapping);
 		if (!page) {
-			desc->error = -ENOMEM;
+			error = -ENOMEM;
 			goto out;
 		}
 		error = add_to_page_cache_lru(page, mapping,
 						index, GFP_KERNEL);
 		if (error) {
 			page_cache_release(page);
-			if (error == -EEXIST)
+			if (error == -EEXIST) {
+				error = 0;
 				goto find_page;
-			desc->error = error;
+			}
 			goto out;
 		}
 		goto readpage;
@@ -1652,44 +1653,7 @@ out:
 
 	*ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
 	file_accessed(filp);
-}
-
-int file_read_actor(read_descriptor_t *desc, struct page *page,
-			unsigned long offset, unsigned long size)
-{
-	char *kaddr;
-	unsigned long left, count = desc->count;
-
-	if (size > count)
-		size = count;
-
-	/*
-	 * Faults on the destination of a read are common, so do it before
-	 * taking the kmap.
-	 */
-	if (!fault_in_pages_writeable(desc->arg.buf, size)) {
-		kaddr = kmap_atomic(page);
-		left = __copy_to_user_inatomic(desc->arg.buf,
-						kaddr + offset, size);
-		kunmap_atomic(kaddr);
-		if (left == 0)
-			goto success;
-	}
-
-	/* Do it the slow way */
-	kaddr = kmap(page);
-	left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
-	kunmap(page);
-
-	if (left) {
-		size -= left;
-		desc->error = -EFAULT;
-	}
-success:
-	desc->count = count - size;
-	desc->written += size;
-	desc->arg.buf += size;
-	return size;
+	return written ? written : error;
 }
 
 /*
@@ -1747,14 +1711,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct file *filp = iocb->ki_filp;
 	ssize_t retval;
-	unsigned long seg = 0;
 	size_t count;
 	loff_t *ppos = &iocb->ki_pos;
+	struct iov_iter i;
 
 	count = 0;
 	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
 	if (retval)
 		return retval;
+	iov_iter_init(&i, iov, nr_segs, count, 0);
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
@@ -1776,6 +1741,11 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		if (retval > 0) {
 			*ppos = pos + retval;
 			count -= retval;
+			/*
+			 * If we did a short DIO read we need to skip the
+			 * section of the iov that we've already read data into.
+			 */
+			iov_iter_advance(&i, retval);
 		}
 
 		/*
@@ -1792,39 +1762,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		}
 	}
 
-	count = retval;
-	for (seg = 0; seg < nr_segs; seg++) {
-		read_descriptor_t desc;
-		loff_t offset = 0;
-
-		/*
-		 * If we did a short DIO read we need to skip the section of the
-		 * iov that we've already read data into.
-		 */
-		if (count) {
-			if (count > iov[seg].iov_len) {
-				count -= iov[seg].iov_len;
-				continue;
-			}
-			offset = count;
-			count = 0;
-		}
-
-		desc.written = 0;
-		desc.arg.buf = iov[seg].iov_base + offset;
-		desc.count = iov[seg].iov_len - offset;
-		if (desc.count == 0)
-			continue;
-		desc.error = 0;
-		do_generic_file_read(filp, ppos, &desc);
-		retval += desc.written;
-		if (desc.error) {
-			retval = retval ?: desc.error;
-			break;
-		}
-		if (desc.count > 0)
-			break;
-	}
+	retval = do_generic_file_read(filp, ppos, &i, retval);
 out:
 	return retval;
 }
@@ -2335,150 +2273,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-static size_t __iovec_copy_from_user_inatomic(char *vaddr,
-			const struct iovec *iov, size_t base, size_t bytes)
-{
-	size_t copied = 0, left = 0;
-
-	while (bytes) {
-		char __user *buf = iov->iov_base + base;
-		int copy = min(bytes, iov->iov_len - base);
-
-		base = 0;
-		left = __copy_from_user_inatomic(vaddr, buf, copy);
-		copied += copy;
-		bytes -= copy;
-		vaddr += copy;
-		iov++;
-
-		if (unlikely(left))
-			break;
-	}
-	return copied - left;
-}
-
-/*
- * Copy as much as we can into the page and return the number of bytes which
- * were successfully copied.  If a fault is encountered then return the number of
- * bytes which were copied.
- */
-size_t iov_iter_copy_from_user_atomic(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes)
-{
-	char *kaddr;
-	size_t copied;
-
-	BUG_ON(!in_atomic());
-	kaddr = kmap_atomic(page);
-	if (likely(i->nr_segs == 1)) {
-		int left;
-		char __user *buf = i->iov->iov_base + i->iov_offset;
-		left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
-		copied = bytes - left;
-	} else {
-		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
-						i->iov, i->iov_offset, bytes);
-	}
-	kunmap_atomic(kaddr);
-
-	return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
-
-/*
- * This has the same sideeffects and return value as
- * iov_iter_copy_from_user_atomic().
- * The difference is that it attempts to resolve faults.
- * Page must not be locked.
- */
-size_t iov_iter_copy_from_user(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes)
-{
-	char *kaddr;
-	size_t copied;
-
-	kaddr = kmap(page);
-	if (likely(i->nr_segs == 1)) {
-		int left;
-		char __user *buf = i->iov->iov_base + i->iov_offset;
-		left = __copy_from_user(kaddr + offset, buf, bytes);
-		copied = bytes - left;
-	} else {
-		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
-						i->iov, i->iov_offset, bytes);
-	}
-	kunmap(page);
-	return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user);
-
-void iov_iter_advance(struct iov_iter *i, size_t bytes)
-{
-	BUG_ON(i->count < bytes);
-
-	if (likely(i->nr_segs == 1)) {
-		i->iov_offset += bytes;
-		i->count -= bytes;
-	} else {
-		const struct iovec *iov = i->iov;
-		size_t base = i->iov_offset;
-		unsigned long nr_segs = i->nr_segs;
-
-		/*
-		 * The !iov->iov_len check ensures we skip over unlikely
-		 * zero-length segments (without overruning the iovec).
-		 */
-		while (bytes || unlikely(i->count && !iov->iov_len)) {
-			int copy;
-
-			copy = min(bytes, iov->iov_len - base);
-			BUG_ON(!i->count || i->count < copy);
-			i->count -= copy;
-			bytes -= copy;
-			base += copy;
-			if (iov->iov_len == base) {
-				iov++;
-				nr_segs--;
-				base = 0;
-			}
-		}
-		i->iov = iov;
-		i->iov_offset = base;
-		i->nr_segs = nr_segs;
-	}
-}
-EXPORT_SYMBOL(iov_iter_advance);
-
-/*
- * Fault in the first iovec of the given iov_iter, to a maximum length
- * of bytes. Returns 0 on success, or non-zero if the memory could not be
- * accessed (ie. because it is an invalid address).
- *
- * writev-intensive code may want this to prefault several iovecs -- that
- * would be possible (callers must not rely on the fact that _only_ the
- * first iovec will be faulted with the current implementation).
- */
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
-{
-	char __user *buf = i->iov->iov_base + i->iov_offset;
-	bytes = min(bytes, i->iov->iov_len - i->iov_offset);
-	return fault_in_pages_readable(buf, bytes);
-}
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
-
-/*
- * Return the count of just the current iov_iter segment.
- */
-size_t iov_iter_single_seg_count(const struct iov_iter *i)
-{
-	const struct iovec *iov = i->iov;
-	if (i->nr_segs == 1)
-		return i->count;
-	else
-		return min(i->count, iov->iov_len - i->iov_offset);
-}
-EXPORT_SYMBOL(iov_iter_single_seg_count);
-
 /*
  * Performs necessary checks before doing a write
  *
@@ -2585,7 +2379,7 @@ EXPORT_SYMBOL(pagecache_write_end);
 
 ssize_t
 generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long *nr_segs, loff_t pos, loff_t *ppos,
+		unsigned long *nr_segs, loff_t pos,
 		size_t count, size_t ocount)
 {
 	struct file	*file = iocb->ki_filp;
@@ -2646,7 +2440,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
 		}
-		*ppos = pos;
+		iocb->ki_pos = pos;
 	}
 out:
 	return written;
@@ -2692,7 +2486,7 @@ found:
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
 
-static ssize_t generic_perform_write(struct file *file,
+ssize_t generic_perform_write(struct file *file,
 				struct iov_iter *i, loff_t pos)
 {
 	struct address_space *mapping = file->f_mapping;
@@ -2742,9 +2536,7 @@ again:
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
-		pagefault_enable();
 		flush_dcache_page(page);
 
 		mark_page_accessed(page);
@@ -2782,27 +2574,7 @@ again:
 
 	return written ? written : status;
 }
-
-ssize_t
-generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos, loff_t *ppos,
-		size_t count, ssize_t written)
-{
-	struct file *file = iocb->ki_filp;
-	ssize_t status;
-	struct iov_iter i;
-
-	iov_iter_init(&i, iov, nr_segs, count, written);
-	status = generic_perform_write(file, &i, pos);
-
-	if (likely(status >= 0)) {
-		written += status;
-		*ppos = pos + status;
-  	}
-	
-	return written ? written : status;
-}
-EXPORT_SYMBOL(generic_file_buffered_write);
+EXPORT_SYMBOL(generic_perform_write);
 
 /**
  * __generic_file_aio_write - write data to a file
@@ -2824,16 +2596,18 @@ EXPORT_SYMBOL(generic_file_buffered_write);
  * avoid syncing under i_mutex.
  */
 ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs, loff_t *ppos)
+				 unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space * mapping = file->f_mapping;
 	size_t ocount;		/* original count */
 	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
-	loff_t		pos;
-	ssize_t		written;
+	loff_t		pos = iocb->ki_pos;
+	ssize_t		written = 0;
 	ssize_t		err;
+	ssize_t		status;
+	struct iov_iter from;
 
 	ocount = 0;
 	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
@@ -2841,12 +2615,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		return err;
 
 	count = ocount;
-	pos = *ppos;
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
-	written = 0;
-
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
 		goto out;
@@ -2862,45 +2633,47 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (err)
 		goto out;
 
+	iov_iter_init(&from, iov, nr_segs, count, 0);
+
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (unlikely(file->f_flags & O_DIRECT)) {
 		loff_t endbyte;
-		ssize_t written_buffered;
 
-		written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
-							ppos, count, ocount);
+		written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
+							count, ocount);
 		if (written < 0 || written == count)
 			goto out;
+		iov_iter_advance(&from, written);
+
 		/*
 		 * direct-io write to a hole: fall through to buffered I/O
 		 * for completing the rest of the request.
 		 */
 		pos += written;
 		count -= written;
-		written_buffered = generic_file_buffered_write(iocb, iov,
-						nr_segs, pos, ppos, count,
-						written);
+
+		status = generic_perform_write(file, &from, pos);
 		/*
-		 * If generic_file_buffered_write() retuned a synchronous error
+		 * If generic_perform_write() returned a synchronous error
 		 * then we want to return the number of bytes which were
 		 * direct-written, or the error code if that was zero.  Note
 		 * that this differs from normal direct-io semantics, which
 		 * will return -EFOO even if some bytes were written.
 		 */
-		if (written_buffered < 0) {
-			err = written_buffered;
+		if (unlikely(status < 0) && !written) {
+			err = status;
 			goto out;
 		}
-
+		iocb->ki_pos = pos + status;
 		/*
 		 * We need to ensure that the page cache pages are written to
 		 * disk and invalidated to preserve the expected O_DIRECT
 		 * semantics.
 		 */
-		endbyte = pos + written_buffered - written - 1;
+		endbyte = pos + status - 1;
 		err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
 		if (err == 0) {
-			written = written_buffered;
+			written += status;
 			invalidate_mapping_pages(mapping,
 						 pos >> PAGE_CACHE_SHIFT,
 						 endbyte >> PAGE_CACHE_SHIFT);
@@ -2911,8 +2684,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			 */
 		}
 	} else {
-		written = generic_file_buffered_write(iocb, iov, nr_segs,
-				pos, ppos, count, written);
+		written = generic_perform_write(file, &from, pos);
+		if (likely(written >= 0))
+			iocb->ki_pos = pos + written;
 	}
 out:
 	current->backing_dev_info = NULL;
@@ -2941,7 +2715,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	BUG_ON(iocb->ki_pos != pos);
 
 	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {