1 files changed, 157 insertions, 46 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a2e1cb8a568b..8121e75352ee 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -38,7 +38,6 @@
 #include "xfs_icache.h"
 #include "xfs_pnfs.h"
 
-#include <linux/aio.h>
 #include <linux/dcache.h>
 #include <linux/falloc.h>
 #include <linux/pagevec.h>
@@ -280,7 +279,7 @@ xfs_file_read_iter(
 
 	XFS_STATS_INC(xs_read_calls);
 
-	if (unlikely(file->f_flags & O_DIRECT))
+	if (unlikely(iocb->ki_flags & IOCB_DIRECT))
 		ioflags |= XFS_IO_ISDIRECT;
 	if (file->f_mode & FMODE_NOCMTIME)
 		ioflags |= XFS_IO_INVIS;
@@ -545,21 +544,22 @@ xfs_zero_eof(
  */
 STATIC ssize_t
 xfs_file_aio_write_checks(
-	struct file		*file,
-	loff_t			*pos,
-	size_t			*count,
+	struct kiocb		*iocb,
+	struct iov_iter		*from,
 	int			*iolock)
 {
+	struct file		*file = iocb->ki_filp;
 	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	int			error = 0;
+	ssize_t			error = 0;
+	size_t			count = iov_iter_count(from);
 
 restart:
-	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
-	if (error)
+	error = generic_write_checks(iocb, from);
+	if (error <= 0)
 		return error;
 
-	error = xfs_break_layouts(inode, iolock);
+	error = xfs_break_layouts(inode, iolock, true);
 	if (error)
 		return error;
 
@@ -569,20 +569,42 @@ restart:
 	 * write.  If zeroing is needed and we are currently holding the
 	 * iolock shared, we need to update it to exclusive which implies
 	 * having to redo all checks before.
+	 *
+	 * We need to serialise against EOF updates that occur in IO
+	 * completions here. We want to make sure that nobody is changing the
+	 * size while we do this check until we have placed an IO barrier (i.e.
+	 * hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
+	 * The spinlock effectively forms a memory barrier once we have the
+	 * XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
+	 * and hence be able to correctly determine if we need to run zeroing.
 	 */
-	if (*pos > i_size_read(inode)) {
+	spin_lock(&ip->i_flags_lock);
+	if (iocb->ki_pos > i_size_read(inode)) {
 		bool	zero = false;
 
+		spin_unlock(&ip->i_flags_lock);
 		if (*iolock == XFS_IOLOCK_SHARED) {
 			xfs_rw_iunlock(ip, *iolock);
 			*iolock = XFS_IOLOCK_EXCL;
 			xfs_rw_ilock(ip, *iolock);
+			iov_iter_reexpand(from, count);
+
+			/*
+			 * We now have an IO submission barrier in place, but
+			 * AIO can do EOF updates during IO completion and hence
+			 * we now need to wait for all of them to drain. Non-AIO
+			 * DIO will have drained before we are given the
+			 * XFS_IOLOCK_EXCL, and so for most cases this wait is a
+			 * no-op.
+			 */
+			inode_dio_wait(inode);
 			goto restart;
 		}
-		error = xfs_zero_eof(ip, *pos, i_size_read(inode), &zero);
+		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
 		if (error)
 			return error;
-	}
+	} else
+		spin_unlock(&ip->i_flags_lock);
 
 	/*
 	 * Updating the timestamps will grab the ilock again from
@@ -644,6 +666,8 @@ xfs_file_dio_aio_write(
 	int			iolock;
 	size_t			count = iov_iter_count(from);
 	loff_t			pos = iocb->ki_pos;
+	loff_t			end;
+	struct iov_iter		data;
 	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
 					mp->m_rtdev_targp : mp->m_ddev_targp;
 
@@ -679,14 +703,16 @@ xfs_file_dio_aio_write(
 		xfs_rw_ilock(ip, iolock);
 	}
 
-	ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
+	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
-	iov_iter_truncate(from, count);
+	count = iov_iter_count(from);
+	pos = iocb->ki_pos;
+	end = pos + count - 1;
 
 	if (mapping->nrpages) {
 		ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-						    pos, pos + count - 1);
+						   pos, end);
 		if (ret)
 			goto out;
 		/*
@@ -696,7 +722,7 @@ xfs_file_dio_aio_write(
 		 */
 		ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
 					pos >> PAGE_CACHE_SHIFT,
-					(pos + count - 1) >> PAGE_CACHE_SHIFT);
+					end >> PAGE_CACHE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
@@ -713,8 +739,22 @@ xfs_file_dio_aio_write(
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
-	ret = generic_file_direct_write(iocb, from, pos);
 
+	data = *from;
+	ret = mapping->a_ops->direct_IO(iocb, &data, pos);
+
+	/* see generic_file_direct_write() for why this is necessary */
+	if (mapping->nrpages) {
+		invalidate_inode_pages2_range(mapping,
+					      pos >> PAGE_CACHE_SHIFT,
+					      end >> PAGE_CACHE_SHIFT);
+	}
+
+	if (ret > 0) {
+		pos += ret;
+		iov_iter_advance(from, ret);
+		iocb->ki_pos = pos;
+	}
 out:
 	xfs_rw_iunlock(ip, iolock);
 
@@ -735,24 +775,22 @@ xfs_file_buffered_aio_write(
 	ssize_t			ret;
 	int			enospc = 0;
 	int			iolock = XFS_IOLOCK_EXCL;
-	loff_t			pos = iocb->ki_pos;
-	size_t			count = iov_iter_count(from);
 
 	xfs_rw_ilock(ip, iolock);
 
-	ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
+	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
 
-	iov_iter_truncate(from, count);
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = inode_to_bdi(inode);
 
 write_retry:
-	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
-	ret = generic_perform_write(file, from, pos);
+	trace_xfs_file_buffered_write(ip, iov_iter_count(from),
+				      iocb->ki_pos, 0);
+	ret = generic_perform_write(file, from, iocb->ki_pos);
 	if (likely(ret >= 0))
-		iocb->ki_pos = pos + ret;
+		iocb->ki_pos += ret;
 
 	/*
 	 * If we hit a space limit, try to free up some lingering preallocated
@@ -804,7 +842,7 @@ xfs_file_write_iter(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	if (unlikely(file->f_flags & O_DIRECT))
+	if (unlikely(iocb->ki_flags & IOCB_DIRECT))
 		ret = xfs_file_dio_aio_write(iocb, from);
 	else
 		ret = xfs_file_buffered_aio_write(iocb, from);
@@ -822,6 +860,11 @@ xfs_file_write_iter(
 	return ret;
 }
 
+#define	XFS_FALLOC_FL_SUPPORTED						\
+		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
+		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
+		 FALLOC_FL_INSERT_RANGE)
+
 STATIC long
 xfs_file_fallocate(
 	struct file		*file,
@@ -835,18 +878,21 @@ xfs_file_fallocate(
 	enum xfs_prealloc_flags	flags = 0;
 	uint			iolock = XFS_IOLOCK_EXCL;
 	loff_t			new_size = 0;
+	bool			do_file_insert = 0;
 
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
-	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
-		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
+	if (mode & ~XFS_FALLOC_FL_SUPPORTED)
 		return -EOPNOTSUPP;
 
 	xfs_ilock(ip, iolock);
-	error = xfs_break_layouts(inode, &iolock);
+	error = xfs_break_layouts(inode, &iolock, false);
 	if (error)
 		goto out_unlock;
 
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+	iolock |= XFS_MMAPLOCK_EXCL;
+
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		error = xfs_free_file_space(ip, offset, len);
 		if (error)
@@ -873,6 +919,27 @@ xfs_file_fallocate(
 		error = xfs_collapse_file_space(ip, offset, len);
 		if (error)
 			goto out_unlock;
+	} else if (mode & FALLOC_FL_INSERT_RANGE) {
+		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+
+		new_size = i_size_read(inode) + len;
+		if (offset & blksize_mask || len & blksize_mask) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+
+		/* check the new inode size does not wrap through zero */
+		if (new_size > inode->i_sb->s_maxbytes) {
+			error = -EFBIG;
+			goto out_unlock;
+		}
+
+		/* Offset should be less than i_size */
+		if (offset >= i_size_read(inode)) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+		do_file_insert = 1;
 	} else {
 		flags |= XFS_PREALLOC_SET;
 
@@ -907,8 +974,19 @@ xfs_file_fallocate(
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = new_size;
 		error = xfs_setattr_size(ip, &iattr);
+		if (error)
+			goto out_unlock;
 	}
 
+	/*
+	 * Perform hole insertion now that the file size has been
+	 * updated so that if we crash during the operation we don't
+	 * leave shifted extents past EOF and hence losing access to
+	 * the data that is contained within them.
+	 */
+	if (do_file_insert)
+		error = xfs_insert_file_space(ip, offset, len);
+
 out_unlock:
 	xfs_iunlock(ip, iolock);
 	return error;
@@ -997,20 +1075,6 @@ xfs_file_mmap(
 }
 
 /*
- * mmap()d file has taken write protection fault and is being made
- * writable. We can set the page state up correctly for a writable
- * page, which means we can do correct delalloc accounting (ENOSPC
- * checking!) and unwritten extent mapping.
- */
-STATIC int
-xfs_vm_page_mkwrite(
-	struct vm_area_struct	*vma,
-	struct vm_fault		*vmf)
-{
-	return block_page_mkwrite(vma, vmf, xfs_get_blocks);
-}
-
-/*
  * This type is designed to indicate the type of offset we would like
  * to search from page cache for xfs_seek_hole_data().
  */
@@ -1385,10 +1449,57 @@ xfs_file_llseek(
 	}
 }
 
+/*
+ * Locking for serialisation of IO during page faults. This results in a lock
+ * ordering of:
+ *
+ * mmap_sem (MM)
+ *   i_mmap_lock (XFS - truncate serialisation)
+ *     page_lock (MM)
+ *       i_lock (XFS - extent map serialisation)
+ */
+STATIC int
+xfs_filemap_fault(
+	struct vm_area_struct	*vma,
+	struct vm_fault		*vmf)
+{
+	struct xfs_inode	*ip = XFS_I(vma->vm_file->f_mapping->host);
+	int			error;
+
+	trace_xfs_filemap_fault(ip);
+
+	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	error = filemap_fault(vma, vmf);
+	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+
+	return error;
+}
+
+/*
+ * mmap()d file has taken write protection fault and is being made writable. We
+ * can set the page state up correctly for a writable page, which means we can
+ * do correct delalloc accounting (ENOSPC checking!) and unwritten extent
+ * mapping.
+ */
+STATIC int
+xfs_filemap_page_mkwrite(
+	struct vm_area_struct	*vma,
+	struct vm_fault		*vmf)
+{
+	struct xfs_inode	*ip = XFS_I(vma->vm_file->f_mapping->host);
+	int			error;
+
+	trace_xfs_filemap_page_mkwrite(ip);
+
+	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	error = block_page_mkwrite(vma, vmf, xfs_get_blocks);
+	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+
+	return error;
+}
+
 const struct file_operations xfs_file_operations = {
 	.llseek		= xfs_file_llseek,
-	.read		= new_sync_read,
-	.write		= new_sync_write,
 	.read_iter	= xfs_file_read_iter,
 	.write_iter	= xfs_file_write_iter,
 	.splice_read	= xfs_file_splice_read,
@@ -1417,7 +1528,7 @@ const struct file_operations xfs_dir_file_operations = {
 };
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
-	.fault		= filemap_fault,
+	.fault		= xfs_filemap_fault,
 	.map_pages	= filemap_map_pages,
-	.page_mkwrite	= xfs_vm_page_mkwrite,
+	.page_mkwrite	= xfs_filemap_page_mkwrite,
 };