1 files changed, 217 insertions, 117 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 54a67dd9ac0..9f7ec15a652 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -17,9 +17,7 @@
  */
 #include "xfs.h"
 #include "xfs_fs.h"
-#include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_inum.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_trans.h"
@@ -396,114 +394,96 @@ xfs_file_splice_write(
 }
 
 /*
- * 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 anyone to read the garbage on the disk.
+ * 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
+ * garbage on the disk.
  */
 STATIC int				/* error (positive) */
 xfs_zero_last_block(
-	xfs_inode_t	*ip,
-	xfs_fsize_t	offset,
-	xfs_fsize_t	isize)
+	struct xfs_inode	*ip,
+	xfs_fsize_t		offset,
+	xfs_fsize_t		isize)
 {
-	xfs_fileoff_t	last_fsb;
-	xfs_mount_t	*mp = ip->i_mount;
-	int		nimaps;
-	int		zero_offset;
-	int		zero_len;
-	int		error = 0;
-	xfs_bmbt_irec_t	imap;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-	zero_offset = XFS_B_FSB_OFFSET(mp, isize);
-	if (zero_offset == 0) {
-		/*
-		 * There are no extra bytes in the last block on disk to
-		 * zero, so return.
-		 */
-		return 0;
-	}
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		last_fsb = XFS_B_TO_FSBT(mp, isize);
+	int			zero_offset = XFS_B_FSB_OFFSET(mp, isize);
+	int			zero_len;
+	int			nimaps = 1;
+	int			error = 0;
+	struct xfs_bmbt_irec	imap;
 
-	last_fsb = XFS_B_TO_FSBT(mp, isize);
-	nimaps = 1;
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	if (error)
 		return error;
+
 	ASSERT(nimaps > 0);
+
 	/*
 	 * If the block underlying isize is just a hole, then there
 	 * is nothing to zero.
 	 */
-	if (imap.br_startblock == HOLESTARTBLOCK) {
+	if (imap.br_startblock == HOLESTARTBLOCK)
 		return 0;
-	}
-	/*
-	 * Zero the part of the last block beyond the EOF, and write it
-	 * out sync.  We need to drop the ilock while we do this so we
-	 * don't deadlock when the buffer cache calls back to us.
-	 */
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	zero_len = mp->m_sb.sb_blocksize - zero_offset;
 	if (isize + zero_len > offset)
 		zero_len = offset - isize;
-	error = xfs_iozero(ip, isize, zero_len);
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	ASSERT(error >= 0);
-	return error;
+	return xfs_iozero(ip, isize, zero_len);
 }
 
 /*
- * Zero any on disk space between the current EOF and the new,
- * larger EOF.  This handles the normal case of zeroing the remainder
- * of the last block in the file and the unusual case of zeroing blocks
- * out beyond the size of the file.  This second case only happens
- * with fixed size extents and when the system crashes before the inode
- * size was updated but after blocks were allocated.  If fill is set,
- * then any holes in the range are filled and zeroed.  If not, the holes
- * are left alone as holes.
+ * Zero any on disk space between the current EOF and the new, larger EOF.
+ *
+ * This handles the normal case of zeroing the remainder of the last block in
+ * the file and the unusual case of zeroing blocks out beyond the size of the
+ * file.  This second case only happens with fixed size extents and when the
+ * system crashes before the inode size was updated but after blocks were
+ * allocated.
+ *
+ * Expects the iolock to be held exclusive, and will take the ilock internally.
  */
-
 int					/* error (positive) */
 xfs_zero_eof(
-	xfs_inode_t	*ip,
-	xfs_off_t	offset,		/* starting I/O offset */
-	xfs_fsize_t	isize)		/* current inode size */
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,		/* starting I/O offset */
+	xfs_fsize_t		isize)		/* current inode size */
 {
-	xfs_mount_t	*mp = ip->i_mount;
-	xfs_fileoff_t	start_zero_fsb;
-	xfs_fileoff_t	end_zero_fsb;
-	xfs_fileoff_t	zero_count_fsb;
-	xfs_fileoff_t	last_fsb;
-	xfs_fileoff_t	zero_off;
-	xfs_fsize_t	zero_len;
-	int		nimaps;
-	int		error = 0;
-	xfs_bmbt_irec_t	imap;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		start_zero_fsb;
+	xfs_fileoff_t		end_zero_fsb;
+	xfs_fileoff_t		zero_count_fsb;
+	xfs_fileoff_t		last_fsb;
+	xfs_fileoff_t		zero_off;
+	xfs_fsize_t		zero_len;
+	int			nimaps;
+	int			error = 0;
+	struct xfs_bmbt_irec	imap;
+
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(offset > isize);
 
 	/*
 	 * First handle zeroing the block on which isize resides.
+	 *
 	 * We only zero a part of that block so it is handled specially.
 	 */
-	error = xfs_zero_last_block(ip, offset, isize);
-	if (error) {
-		ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-		return error;
+	if (XFS_B_FSB_OFFSET(mp, isize) != 0) {
+		error = xfs_zero_last_block(ip, offset, isize);
+		if (error)
+			return error;
 	}
 
 	/*
-	 * Calculate the range between the new size and the old
-	 * where blocks needing to be zeroed may exist.  To get the
-	 * block where the last byte in the file currently resides,
-	 * we need to subtract one from the size and truncate back
-	 * to a block boundary.  We subtract 1 in case the size is
-	 * exactly on a block boundary.
+	 * Calculate the range between the new size and the old where blocks
+	 * needing to be zeroed may exist.
+	 *
+	 * To get the block where the last byte in the file currently resides,
+	 * we need to subtract one from the size and truncate back to a block
+	 * boundary.  We subtract 1 in case the size is exactly on a block
+	 * boundary.
 	 */
 	last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1;
 	start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
@@ -521,23 +501,18 @@ xfs_zero_eof(
 	while (start_zero_fsb <= end_zero_fsb) {
 		nimaps = 1;
 		zero_count_fsb = end_zero_fsb - start_zero_fsb + 1;
+
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb,
 					  &imap, &nimaps, 0);
-		if (error) {
-			ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		if (error)
 			return error;
-		}
+
 		ASSERT(nimaps > 0);
 
 		if (imap.br_state == XFS_EXT_UNWRITTEN ||
 		    imap.br_startblock == HOLESTARTBLOCK) {
-			/*
-			 * This loop handles initializing pages that were
-			 * partially initialized by the code below this
-			 * loop. It basically zeroes the part of the page
-			 * that sits on a hole and sets the page as P_HOLE
-			 * and calls remapf if it is a mapped file.
-			 */
 			start_zero_fsb = imap.br_startoff + imap.br_blockcount;
 			ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
 			continue;
@@ -545,11 +520,7 @@ xfs_zero_eof(
 
 		/*
 		 * There are blocks we need to zero.
-		 * Drop the inode lock while we're doing the I/O.
-		 * We'll still have the iolock to protect us.
 		 */
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 		zero_off = XFS_FSB_TO_B(mp, start_zero_fsb);
 		zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount);
 
@@ -557,22 +528,14 @@ xfs_zero_eof(
 			zero_len = offset - zero_off;
 
 		error = xfs_iozero(ip, zero_off, zero_len);
-		if (error) {
-			goto out_lock;
-		}
+		if (error)
+			return error;
 
 		start_zero_fsb = imap.br_startoff + imap.br_blockcount;
 		ASSERT(start_zero_fsb <= (end_zero_fsb + 1));
-
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
 	}
 
 	return 0;
-
-out_lock:
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	ASSERT(error >= 0);
-	return error;
 }
 
 /*
@@ -593,35 +556,29 @@ xfs_file_aio_write_checks(
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			error = 0;
 
-	xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
 restart:
 	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
-	if (error) {
-		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
+	if (error)
 		return error;
-	}
 
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
 	 * write.  If zeroing is needed and we are currently holding the
-	 * iolock shared, we need to update it to exclusive which involves
-	 * dropping all locks and relocking to maintain correct locking order.
-	 * If we do this, restart the function to ensure all checks and values
-	 * are still valid.
+	 * iolock shared, we need to update it to exclusive which implies
+	 * having to redo all checks before.
 	 */
 	if (*pos > i_size_read(inode)) {
 		if (*iolock == XFS_IOLOCK_SHARED) {
-			xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
+			xfs_rw_iunlock(ip, *iolock);
 			*iolock = XFS_IOLOCK_EXCL;
-			xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
+			xfs_rw_ilock(ip, *iolock);
 			goto restart;
 		}
 		error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
+		if (error)
+			return error;
 	}
-	xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
-	if (error)
-		return error;
 
 	/*
 	 * Updating the timestamps will grab the ilock again from
@@ -629,8 +586,11 @@ restart:
 	 * lock above.  Eventually we should look into a way to avoid
 	 * the pointless lock roundtrip.
 	 */
-	if (likely(!(file->f_mode & FMODE_NOCMTIME)))
-		file_update_time(file);
+	if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
+		error = file_update_time(file);
+		if (error)
+			return error;
+	}
 
 	/*
 	 * If we're writing the file then make sure to clear the setuid and
@@ -638,7 +598,6 @@ restart:
 	 * people from modifying setuid and setgid binaries.
 	 */
 	return file_remove_suid(file);
-
 }
 
 /*
@@ -1007,8 +966,149 @@ xfs_vm_page_mkwrite(
 	return block_page_mkwrite(vma, vmf, xfs_get_blocks);
 }
 
+STATIC loff_t
+xfs_seek_data(
+	struct file		*file,
+	loff_t			start,
+	u32			type)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_bmbt_irec	map[2];
+	int			nmap = 2;
+	loff_t			uninitialized_var(offset);
+	xfs_fsize_t		isize;
+	xfs_fileoff_t		fsbno;
+	xfs_filblks_t		end;
+	uint			lock;
+	int			error;
+
+	lock = xfs_ilock_map_shared(ip);
+
+	isize = i_size_read(inode);
+	if (start >= isize) {
+		error = ENXIO;
+		goto out_unlock;
+	}
+
+	fsbno = XFS_B_TO_FSBT(mp, start);
+
+	/*
+	 * Try to read extents from the first block indicated
+	 * by fsbno to the end block of the file.
+	 */
+	end = XFS_B_TO_FSB(mp, isize);
+
+	error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
+			       XFS_BMAPI_ENTIRE);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * Treat unwritten extent as data extent since it might
+	 * contains dirty data in page cache.
+	 */
+	if (map[0].br_startblock != HOLESTARTBLOCK) {
+		offset = max_t(loff_t, start,
+			       XFS_FSB_TO_B(mp, map[0].br_startoff));
+	} else {
+		if (nmap == 1) {
+			error = ENXIO;
+			goto out_unlock;
+		}
+
+		offset = max_t(loff_t, start,
+			       XFS_FSB_TO_B(mp, map[1].br_startoff));
+	}
+
+	if (offset != file->f_pos)
+		file->f_pos = offset;
+
+out_unlock:
+	xfs_iunlock_map_shared(ip, lock);
+
+	if (error)
+		return -error;
+	return offset;
+}
+
+STATIC loff_t
+xfs_seek_hole(
+	struct file		*file,
+	loff_t			start,
+	u32			type)
+{
+	struct inode		*inode = file->f_mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	loff_t			uninitialized_var(offset);
+	loff_t			holeoff;
+	xfs_fsize_t		isize;
+	xfs_fileoff_t		fsbno;
+	uint			lock;
+	int			error;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -XFS_ERROR(EIO);
+
+	lock = xfs_ilock_map_shared(ip);
+
+	isize = i_size_read(inode);
+	if (start >= isize) {
+		error = ENXIO;
+		goto out_unlock;
+	}
+
+	fsbno = XFS_B_TO_FSBT(mp, start);
+	error = xfs_bmap_first_unused(NULL, ip, 1, &fsbno, XFS_DATA_FORK);
+	if (error)
+		goto out_unlock;
+
+	holeoff = XFS_FSB_TO_B(mp, fsbno);
+	if (holeoff <= start)
+		offset = start;
+	else {
+		/*
+		 * xfs_bmap_first_unused() could return a value bigger than
+		 * isize if there are no more holes past the supplied offset.
+		 */
+		offset = min_t(loff_t, holeoff, isize);
+	}
+
+	if (offset != file->f_pos)
+		file->f_pos = offset;
+
+out_unlock:
+	xfs_iunlock_map_shared(ip, lock);
+
+	if (error)
+		return -error;
+	return offset;
+}
+
+STATIC loff_t
+xfs_file_llseek(
+	struct file	*file,
+	loff_t		offset,
+	int		origin)
+{
+	switch (origin) {
+	case SEEK_END:
+	case SEEK_CUR:
+	case SEEK_SET:
+		return generic_file_llseek(file, offset, origin);
+	case SEEK_DATA:
+		return xfs_seek_data(file, offset, origin);
+	case SEEK_HOLE:
+		return xfs_seek_hole(file, offset, origin);
+	default:
+		return -EINVAL;
+	}
+}
+
 const struct file_operations xfs_file_operations = {
-	.llseek		= generic_file_llseek,
+	.llseek		= xfs_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= xfs_file_aio_read,