1 files changed, 138 insertions, 138 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 52c91e143725..de5368c803f9 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -38,6 +38,7 @@
 #include "xfs_trace.h"
 #include "xfs_log.h"
 #include "xfs_dinode.h"
+#include "xfs_icache.h"
 
 #include <linux/aio.h>
 #include <linux/dcache.h>
@@ -179,7 +180,7 @@ xfs_file_fsync(
 		return error;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return -XFS_ERROR(EIO);
+		return -EIO;
 
 	xfs_iflags_clear(ip, XFS_ITRUNCATED);
 
@@ -225,46 +226,40 @@ xfs_file_fsync(
 	    !log_flushed)
 		xfs_blkdev_issue_flush(mp->m_ddev_targp);
 
-	return -error;
+	return error;
 }
 
 STATIC ssize_t
-xfs_file_aio_read(
+xfs_file_read_iter(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos)
+	struct iov_iter		*to)
 {
 	struct file		*file = iocb->ki_filp;
 	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	size_t			size = 0;
+	size_t			size = iov_iter_count(to);
 	ssize_t			ret = 0;
 	int			ioflags = 0;
 	xfs_fsize_t		n;
+	loff_t			pos = iocb->ki_pos;
 
 	XFS_STATS_INC(xs_read_calls);
 
-	BUG_ON(iocb->ki_pos != pos);
-
 	if (unlikely(file->f_flags & O_DIRECT))
-		ioflags |= IO_ISDIRECT;
+		ioflags |= XFS_IO_ISDIRECT;
 	if (file->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+		ioflags |= XFS_IO_INVIS;
 
-	ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
-	if (ret < 0)
-		return ret;
-
-	if (unlikely(ioflags & IO_ISDIRECT)) {
+	if (unlikely(ioflags & XFS_IO_ISDIRECT)) {
 		xfs_buftarg_t	*target =
 			XFS_IS_REALTIME_INODE(ip) ?
 				mp->m_rtdev_targp : mp->m_ddev_targp;
-		if ((pos & target->bt_smask) || (size & target->bt_smask)) {
+		/* DIO must be aligned to device logical sector size */
+		if ((pos | size) & target->bt_logical_sectormask) {
 			if (pos == i_size_read(inode))
 				return 0;
-			return -XFS_ERROR(EINVAL);
+			return -EINVAL;
 		}
 	}
 
@@ -289,26 +284,36 @@ xfs_file_aio_read(
 	 * proceeed concurrently without serialisation.
 	 */
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	if ((ioflags & IO_ISDIRECT) && inode->i_mapping->nrpages) {
+	if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
 		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
 
 		if (inode->i_mapping->nrpages) {
-			ret = -filemap_write_and_wait_range(
+			ret = filemap_write_and_wait_range(
 							VFS_I(ip)->i_mapping,
-							pos, -1);
+							pos, pos + size - 1);
 			if (ret) {
 				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
 				return ret;
 			}
-			truncate_pagecache_range(VFS_I(ip), pos, -1);
+
+			/*
+			 * Invalidate whole pages. This can return an error if
+			 * we fail to invalidate a page, but this should never
+			 * happen on XFS. Warn if it does fail.
+			 */
+			ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+					pos >> PAGE_CACHE_SHIFT,
+					(pos + size - 1) >> PAGE_CACHE_SHIFT);
+			WARN_ON_ONCE(ret);
+			ret = 0;
 		}
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
 	}
 
 	trace_xfs_file_read(ip, size, pos, ioflags);
 
-	ret = generic_file_aio_read(iocb, iovp, nr_segs, pos);
+	ret = generic_file_read_iter(iocb, to);
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
@@ -331,7 +336,7 @@ xfs_file_splice_read(
 	XFS_STATS_INC(xs_read_calls);
 
 	if (infilp->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
+		ioflags |= XFS_IO_INVIS;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
@@ -349,47 +354,6 @@ xfs_file_splice_read(
 }
 
 /*
- * xfs_file_splice_write() does not use xfs_rw_ilock() because
- * generic_file_splice_write() takes the i_mutex itself. This, in theory,
- * couuld cause lock inversions between the aio_write path and the splice path
- * if someone is doing concurrent splice(2) based writes and write(2) based
- * writes to the same inode. The only real way to fix this is to re-implement
- * the generic code here with correct locking orders.
- */
-STATIC ssize_t
-xfs_file_splice_write(
-	struct pipe_inode_info	*pipe,
-	struct file		*outfilp,
-	loff_t			*ppos,
-	size_t			count,
-	unsigned int		flags)
-{
-	struct inode		*inode = outfilp->f_mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	int			ioflags = 0;
-	ssize_t			ret;
-
-	XFS_STATS_INC(xs_write_calls);
-
-	if (outfilp->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
-
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
-	trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
-
-	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_write_bytes, ret);
-
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-	return ret;
-}
-
-/*
  * This routine is called to handle zeroing any space in the last block of the
  * file that is beyond the EOF.  We do this since the size is being increased
  * without writing anything to that block and we don't want to read the
@@ -571,7 +535,7 @@ restart:
 			xfs_rw_ilock(ip, *iolock);
 			goto restart;
 		}
-		error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
+		error = xfs_zero_eof(ip, *pos, i_size_read(inode));
 		if (error)
 			return error;
 	}
@@ -624,10 +588,7 @@ restart:
 STATIC ssize_t
 xfs_file_dio_aio_write(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos,
-	size_t			ocount)
+	struct iov_iter		*from)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
@@ -635,15 +596,18 @@ xfs_file_dio_aio_write(
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			ret = 0;
-	size_t			count = ocount;
 	int			unaligned_io = 0;
 	int			iolock;
+	size_t			count = iov_iter_count(from);
+	loff_t			pos = iocb->ki_pos;
 	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
 					mp->m_rtdev_targp : mp->m_ddev_targp;
 
-	if ((pos & target->bt_smask) || (count & target->bt_smask))
-		return -XFS_ERROR(EINVAL);
+	/* DIO must be aligned to device logical sector size */
+	if ((pos | count) & target->bt_logical_sectormask)
+		return -EINVAL;
 
+	/* "unaligned" here means not aligned to a filesystem block */
 	if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
 		unaligned_io = 1;
 
@@ -674,13 +638,23 @@ xfs_file_dio_aio_write(
 	ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
 	if (ret)
 		goto out;
+	iov_iter_truncate(from, count);
 
 	if (mapping->nrpages) {
-		ret = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-						    pos, -1);
+		ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+						    pos, pos + count - 1);
 		if (ret)
 			goto out;
-		truncate_pagecache_range(VFS_I(ip), pos, -1);
+		/*
+		 * Invalidate whole pages. This can return an error if
+		 * we fail to invalidate a page, but this should never
+		 * happen on XFS. Warn if it does fail.
+		 */
+		ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+					pos >> PAGE_CACHE_SHIFT,
+					(pos + count - 1) >> PAGE_CACHE_SHIFT);
+		WARN_ON_ONCE(ret);
+		ret = 0;
 	}
 
 	/*
@@ -695,8 +669,7 @@ xfs_file_dio_aio_write(
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
-	ret = generic_file_direct_write(iocb, iovp,
-			&nr_segs, pos, &iocb->ki_pos, count, ocount);
+	ret = generic_file_direct_write(iocb, from, pos);
 
 out:
 	xfs_rw_iunlock(ip, iolock);
@@ -709,10 +682,7 @@ out:
 STATIC ssize_t
 xfs_file_buffered_aio_write(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos,
-	size_t			ocount)
+	struct iov_iter		*from)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
@@ -721,7 +691,8 @@ xfs_file_buffered_aio_write(
 	ssize_t			ret;
 	int			enospc = 0;
 	int			iolock = XFS_IOLOCK_EXCL;
-	size_t			count = ocount;
+	loff_t			pos = iocb->ki_pos;
+	size_t			count = iov_iter_count(from);
 
 	xfs_rw_ilock(ip, iolock);
 
@@ -729,22 +700,37 @@ xfs_file_buffered_aio_write(
 	if (ret)
 		goto out;
 
+	iov_iter_truncate(from, count);
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
 
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
-	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
-			pos, &iocb->ki_pos, count, 0);
+	ret = generic_perform_write(file, from, pos);
+	if (likely(ret >= 0))
+		iocb->ki_pos = pos + ret;
 
 	/*
-	 * If we just got an ENOSPC, try to write back all dirty inodes to
-	 * convert delalloc space to free up some of the excess reserved
-	 * metadata space.
+	 * If we hit a space limit, try to free up some lingering preallocated
+	 * space before returning an error. In the case of ENOSPC, first try to
+	 * write back all dirty inodes to free up some of the excess reserved
+	 * metadata space. This reduces the chances that the eofblocks scan
+	 * waits on dirty mappings. Since xfs_flush_inodes() is serialized, this
+	 * also behaves as a filter to prevent too many eofblocks scans from
+	 * running at the same time.
 	 */
-	if (ret == -ENOSPC && !enospc) {
+	if (ret == -EDQUOT && !enospc) {
+		enospc = xfs_inode_free_quota_eofblocks(ip);
+		if (enospc)
+			goto write_retry;
+	} else if (ret == -ENOSPC && !enospc) {
+		struct xfs_eofblocks eofb = {0};
+
 		enospc = 1;
 		xfs_flush_inodes(ip->i_mount);
+		eofb.eof_scan_owner = ip->i_ino; /* for locking */
+		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
+		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
 		goto write_retry;
 	}
 
@@ -755,40 +741,29 @@ out:
 }
 
 STATIC ssize_t
-xfs_file_aio_write(
+xfs_file_write_iter(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos)
+	struct iov_iter		*from)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
 	struct inode		*inode = mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret;
-	size_t			ocount = 0;
+	size_t			ocount = iov_iter_count(from);
 
 	XFS_STATS_INC(xs_write_calls);
 
-	BUG_ON(iocb->ki_pos != pos);
-
-	ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
-	if (ret)
-		return ret;
-
 	if (ocount == 0)
 		return 0;
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-		ret = -EIO;
-		goto out;
-	}
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
 
 	if (unlikely(file->f_flags & O_DIRECT))
-		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
+		ret = xfs_file_dio_aio_write(iocb, from);
 	else
-		ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
-						  ocount);
+		ret = xfs_file_buffered_aio_write(iocb, from);
 
 	if (ret > 0) {
 		ssize_t err;
@@ -796,12 +771,10 @@ xfs_file_aio_write(
 		XFS_STATS_ADD(xs_write_bytes, ret);
 
 		/* Handle various SYNC-type writes */
-		err = generic_write_sync(file, pos, ret);
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
 		if (err < 0)
 			ret = err;
 	}
-
-out:
 	return ret;
 }
 
@@ -820,7 +793,8 @@ xfs_file_fallocate(
 
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
-	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+		     FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
 		return -EOPNOTSUPP;
 
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
@@ -828,17 +802,42 @@ xfs_file_fallocate(
 		error = xfs_free_file_space(ip, offset, len);
 		if (error)
 			goto out_unlock;
+	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+
+		if (offset & blksize_mask || len & blksize_mask) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+
+		/*
+		 * There is no need to overlap collapse range with EOF,
+		 * in which case it is effectively a truncate operation
+		 */
+		if (offset + len >= i_size_read(inode)) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+
+		new_size = i_size_read(inode) - len;
+
+		error = xfs_collapse_file_space(ip, offset, len);
+		if (error)
+			goto out_unlock;
 	} else {
 		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
 		    offset + len > i_size_read(inode)) {
 			new_size = offset + len;
-			error = -inode_newsize_ok(inode, new_size);
+			error = inode_newsize_ok(inode, new_size);
 			if (error)
 				goto out_unlock;
 		}
 
-		error = xfs_alloc_file_space(ip, offset, len,
-					     XFS_BMAPI_PREALLOC);
+		if (mode & FALLOC_FL_ZERO_RANGE)
+			error = xfs_zero_file_space(ip, offset, len);
+		else
+			error = xfs_alloc_file_space(ip, offset, len,
+						     XFS_BMAPI_PREALLOC);
 		if (error)
 			goto out_unlock;
 	}
@@ -856,7 +855,7 @@ xfs_file_fallocate(
 	if (ip->i_d.di_mode & S_IXGRP)
 		ip->i_d.di_mode &= ~S_ISGID;
 
-	if (!(mode & FALLOC_FL_PUNCH_HOLE))
+	if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE)))
 		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
 
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -879,7 +878,7 @@ xfs_file_fallocate(
 
 out_unlock:
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-	return -error;
+	return error;
 }
 
 
@@ -912,9 +911,9 @@ xfs_dir_open(
 	 * If there are any blocks, read-ahead block 0 as we're almost
 	 * certain to have the next operation be a read there.
 	 */
-	mode = xfs_ilock_map_shared(ip);
+	mode = xfs_ilock_data_map_shared(ip);
 	if (ip->i_d.di_nextents > 0)
-		xfs_dir3_data_readahead(NULL, ip, 0, -1);
+		xfs_dir3_data_readahead(ip, 0, -1);
 	xfs_iunlock(ip, mode);
 	return 0;
 }
@@ -924,7 +923,7 @@ xfs_file_release(
 	struct inode	*inode,
 	struct file	*filp)
 {
-	return -xfs_release(XFS_I(inode));
+	return xfs_release(XFS_I(inode));
 }
 
 STATIC int
@@ -953,7 +952,7 @@ xfs_file_readdir(
 
 	error = xfs_readdir(ip, ctx, bufsize);
 	if (error)
-		return -error;
+		return error;
 	return 0;
 }
 
@@ -1215,11 +1214,11 @@ xfs_seek_data(
 	uint			lock;
 	int			error;
 
-	lock = xfs_ilock_map_shared(ip);
+	lock = xfs_ilock_data_map_shared(ip);
 
 	isize = i_size_read(inode);
 	if (start >= isize) {
-		error = ENXIO;
+		error = -ENXIO;
 		goto out_unlock;
 	}
 
@@ -1241,7 +1240,7 @@ xfs_seek_data(
 
 		/* No extents at given offset, must be beyond EOF */
 		if (nmap == 0) {
-			error = ENXIO;
+			error = -ENXIO;
 			goto out_unlock;
 		}
 
@@ -1272,7 +1271,7 @@ xfs_seek_data(
 		 * we are reading after EOF if nothing in map[1].
 		 */
 		if (nmap == 1) {
-			error = ENXIO;
+			error = -ENXIO;
 			goto out_unlock;
 		}
 
@@ -1285,7 +1284,7 @@ xfs_seek_data(
 		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
 		start = XFS_FSB_TO_B(mp, fsbno);
 		if (start >= isize) {
-			error = ENXIO;
+			error = -ENXIO;
 			goto out_unlock;
 		}
 	}
@@ -1294,10 +1293,10 @@ out:
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out_unlock:
-	xfs_iunlock_map_shared(ip, lock);
+	xfs_iunlock(ip, lock);
 
 	if (error)
-		return -error;
+		return error;
 	return offset;
 }
 
@@ -1317,13 +1316,13 @@ xfs_seek_hole(
 	int			error;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return -XFS_ERROR(EIO);
+		return -EIO;
 
-	lock = xfs_ilock_map_shared(ip);
+	lock = xfs_ilock_data_map_shared(ip);
 
 	isize = i_size_read(inode);
 	if (start >= isize) {
-		error = ENXIO;
+		error = -ENXIO;
 		goto out_unlock;
 	}
 
@@ -1342,7 +1341,7 @@ xfs_seek_hole(
 
 		/* No extents at given offset, must be beyond EOF */
 		if (nmap == 0) {
-			error = ENXIO;
+			error = -ENXIO;
 			goto out_unlock;
 		}
 
@@ -1402,10 +1401,10 @@ out:
 	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 
 out_unlock:
-	xfs_iunlock_map_shared(ip, lock);
+	xfs_iunlock(ip, lock);
 
 	if (error)
-		return -error;
+		return error;
 	return offset;
 }
 
@@ -1431,12 +1430,12 @@ xfs_file_llseek(
 
 const struct file_operations xfs_file_operations = {
 	.llseek		= xfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= xfs_file_aio_read,
-	.aio_write	= xfs_file_aio_write,
+	.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,
-	.splice_write	= xfs_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.unlocked_ioctl	= xfs_file_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= xfs_file_compat_ioctl,
@@ -1462,6 +1461,7 @@ const struct file_operations xfs_dir_file_operations = {
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_vm_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };