1 files changed, 71 insertions, 223 deletions

diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index b572f7e840e0..9d376be0ea38 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -53,6 +53,7 @@
 #include "xfs_log_priv.h"
 #include "xfs_filestream.h"
 #include "xfs_vnodeops.h"
+#include "xfs_trace.h"
 
 int
 xfs_setattr(
@@ -69,7 +70,6 @@ xfs_setattr(
 	uint			commit_flags=0;
 	uid_t			uid=0, iuid=0;
 	gid_t			gid=0, igid=0;
-	int			timeflags = 0;
 	struct xfs_dquot	*udqp, *gdqp, *olddquot1, *olddquot2;
 	int			need_iolock = 1;
 
@@ -134,16 +134,13 @@ xfs_setattr(
 	if (flags & XFS_ATTR_NOLOCK)
 		need_iolock = 0;
 	if (!(mask & ATTR_SIZE)) {
-		if ((mask != (ATTR_CTIME|ATTR_ATIME|ATTR_MTIME)) ||
-		    (mp->m_flags & XFS_MOUNT_WSYNC)) {
-			tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
-			commit_flags = 0;
-			if ((code = xfs_trans_reserve(tp, 0,
-						     XFS_ICHANGE_LOG_RES(mp), 0,
-						     0, 0))) {
-				lock_flags = 0;
-				goto error_return;
-			}
+		tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+		commit_flags = 0;
+		code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp),
+					 0, 0, 0);
+		if (code) {
+			lock_flags = 0;
+			goto error_return;
 		}
 	} else {
 		if (DM_EVENT_ENABLED(ip, DM_EVENT_TRUNCATE) &&
@@ -259,7 +256,7 @@ xfs_setattr(
 		    iattr->ia_size > ip->i_d.di_size) {
 			code = xfs_flush_pages(ip,
 					ip->i_d.di_size, iattr->ia_size,
-					XFS_B_ASYNC, FI_NONE);
+					XBF_ASYNC, FI_NONE);
 		}
 
 		/* wait for all I/O to complete */
@@ -294,15 +291,23 @@ xfs_setattr(
 		 * or we are explicitly asked to change it. This handles
 		 * the semantic difference between truncate() and ftruncate()
 		 * as implemented in the VFS.
+		 *
+		 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME
+		 * is a special case where we need to update the times despite
+		 * not having these flags set.  For all other operations the
+		 * VFS set these flags explicitly if it wants a timestamp
+		 * update.
 		 */
-		if (iattr->ia_size != ip->i_size || (mask & ATTR_CTIME))
-			timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+		if (iattr->ia_size != ip->i_size &&
+		    (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+			iattr->ia_ctime = iattr->ia_mtime =
+				current_fs_time(inode->i_sb);
+			mask |= ATTR_CTIME | ATTR_MTIME;
+		}
 
 		if (iattr->ia_size > ip->i_size) {
 			ip->i_d.di_size = iattr->ia_size;
 			ip->i_size = iattr->ia_size;
-			if (!(flags & XFS_ATTR_DMI))
-				xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		} else if (iattr->ia_size <= ip->i_size ||
 			   (iattr->ia_size == 0 && ip->i_d.di_nextents)) {
@@ -373,9 +378,6 @@ xfs_setattr(
 			ip->i_d.di_gid = gid;
 			inode->i_gid = gid;
 		}
-
-		xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
-		timeflags |= XFS_ICHGTIME_CHG;
 	}
 
 	/*
@@ -392,51 +394,37 @@ xfs_setattr(
 
 		inode->i_mode &= S_IFMT;
 		inode->i_mode |= mode & ~S_IFMT;
-
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		timeflags |= XFS_ICHGTIME_CHG;
 	}
 
 	/*
 	 * Change file access or modified times.
 	 */
-	if (mask & (ATTR_ATIME|ATTR_MTIME)) {
-		if (mask & ATTR_ATIME) {
-			inode->i_atime = iattr->ia_atime;
-			ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
-			ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
-			ip->i_update_core = 1;
-		}
-		if (mask & ATTR_MTIME) {
-			inode->i_mtime = iattr->ia_mtime;
-			ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
-			ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
-			timeflags &= ~XFS_ICHGTIME_MOD;
-			timeflags |= XFS_ICHGTIME_CHG;
-		}
-		if (tp && (mask & (ATTR_MTIME_SET|ATTR_ATIME_SET)))
-			xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
+	if (mask & ATTR_ATIME) {
+		inode->i_atime = iattr->ia_atime;
+		ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
+		ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
+		ip->i_update_core = 1;
 	}
-
-	/*
-	 * Change file inode change time only if ATTR_CTIME set
-	 * AND we have been called by a DMI function.
-	 */
-
-	if ((flags & XFS_ATTR_DMI) && (mask & ATTR_CTIME)) {
+	if (mask & ATTR_CTIME) {
 		inode->i_ctime = iattr->ia_ctime;
 		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
 		ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
 		ip->i_update_core = 1;
-		timeflags &= ~XFS_ICHGTIME_CHG;
+	}
+	if (mask & ATTR_MTIME) {
+		inode->i_mtime = iattr->ia_mtime;
+		ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
+		ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
+		ip->i_update_core = 1;
 	}
 
 	/*
-	 * Send out timestamp changes that need to be set to the
-	 * current time.  Not done when called by a DMI function.
+	 * And finally, log the inode core if any attribute in it
+	 * has been changed.
 	 */
-	if (timeflags && !(flags & XFS_ATTR_DMI))
-		xfs_ichgtime(ip, timeflags);
+	if (mask & (ATTR_UID|ATTR_GID|ATTR_MODE|
+		    ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	XFS_STATS_INC(xs_ig_attrchg);
 
@@ -451,12 +439,10 @@ xfs_setattr(
 	 * mix so this probably isn't worth the trouble to optimize.
 	 */
 	code = 0;
-	if (tp) {
-		if (mp->m_flags & XFS_MOUNT_WSYNC)
-			xfs_trans_set_sync(tp);
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
+		xfs_trans_set_sync(tp);
 
-		code = xfs_trans_commit(tp, commit_flags);
-	}
+	code = xfs_trans_commit(tp, commit_flags);
 
 	xfs_iunlock(ip, lock_flags);
 
@@ -538,9 +524,8 @@ xfs_readlink_bmap(
 		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
 		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
 
-		bp = xfs_buf_read_flags(mp->m_ddev_targp, d, BTOBB(byte_cnt),
-					XBF_LOCK | XBF_MAPPED |
-					XBF_DONT_BLOCK);
+		bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt),
+				  XBF_LOCK | XBF_MAPPED | XBF_DONT_BLOCK);
 		error = XFS_BUF_GETERROR(bp);
 		if (error) {
 			xfs_ioerror_alert("xfs_readlink",
@@ -599,114 +584,9 @@ xfs_readlink(
 }
 
 /*
- * xfs_fsync
- *
- * This is called to sync the inode and its data out to disk.  We need to hold
- * the I/O lock while flushing the data, and the inode lock while flushing the
- * inode.  The inode lock CANNOT be held while flushing the data, so acquire
- * after we're done with that.
+ * Flags for xfs_free_eofblocks
  */
-int
-xfs_fsync(
-	xfs_inode_t	*ip)
-{
-	xfs_trans_t	*tp;
-	int		error = 0;
-	int		log_flushed = 0, changed = 1;
-
-	xfs_itrace_entry(ip);
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return XFS_ERROR(EIO);
-
-	/*
-	 * We always need to make sure that the required inode state is safe on
-	 * disk.  The inode might be clean but we still might need to force the
-	 * log because of committed transactions that haven't hit the disk yet.
-	 * Likewise, there could be unflushed non-transactional changes to the
-	 * inode core that have to go to disk and this requires us to issue
-	 * a synchronous transaction to capture these changes correctly.
-	 *
-	 * This code relies on the assumption that if the update_* fields
-	 * of the inode are clear and the inode is unpinned then it is clean
-	 * and no action is required.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-
-	if (!ip->i_update_core) {
-		/*
-		 * Timestamps/size haven't changed since last inode flush or
-		 * inode transaction commit.  That means either nothing got
-		 * written or a transaction committed which caught the updates.
-		 * If the latter happened and the transaction hasn't hit the
-		 * disk yet, the inode will be still be pinned.  If it is,
-		 * force the log.
-		 */
-
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-		if (xfs_ipincount(ip)) {
-			error = _xfs_log_force(ip->i_mount, (xfs_lsn_t)0,
-				      XFS_LOG_FORCE | XFS_LOG_SYNC,
-				      &log_flushed);
-		} else {
-			/*
-			 * If the inode is not pinned and nothing has changed
-			 * we don't need to flush the cache.
-			 */
-			changed = 0;
-		}
-	} else	{
-		/*
-		 * Kick off a transaction to log the inode core to get the
-		 * updates.  The sync transaction will also force the log.
-		 */
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_FSYNC_TS);
-		error = xfs_trans_reserve(tp, 0,
-				XFS_FSYNC_TS_LOG_RES(ip->i_mount), 0, 0, 0);
-		if (error) {
-			xfs_trans_cancel(tp, 0);
-			return error;
-		}
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-		/*
-		 * Note - it's possible that we might have pushed ourselves out
-		 * of the way during trans_reserve which would flush the inode.
-		 * But there's no guarantee that the inode buffer has actually
-		 * gone out yet (it's delwri).	Plus the buffer could be pinned
-		 * anyway if it's part of an inode in another recent
-		 * transaction.	 So we play it safe and fire off the
-		 * transaction anyway.
-		 */
-		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_trans_ihold(tp, ip);
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		xfs_trans_set_sync(tp);
-		error = _xfs_trans_commit(tp, 0, &log_flushed);
-
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-
-	if ((ip->i_mount->m_flags & XFS_MOUNT_BARRIER) && changed) {
-		/*
-		 * If the log write didn't issue an ordered tag we need
-		 * to flush the disk cache for the data device now.
-		 */
-		if (!log_flushed)
-			xfs_blkdev_issue_flush(ip->i_mount->m_ddev_targp);
-
-		/*
-		 * If this inode is on the RT dev we need to flush that
-		 * cache as well.
-		 */
-		if (XFS_IS_REALTIME_INODE(ip))
-			xfs_blkdev_issue_flush(ip->i_mount->m_rtdev_targp);
-	}
-
-	return error;
-}
+#define XFS_FREE_EOF_TRYLOCK	(1<<0)
 
 /*
  * This is called by xfs_inactive to free any blocks beyond eof
@@ -726,7 +606,6 @@ xfs_free_eofblocks(
 	xfs_filblks_t	map_len;
 	int		nimaps;
 	xfs_bmbt_irec_t	imap;
-	int		use_iolock = (flags & XFS_FREE_EOF_LOCK);
 
 	/*
 	 * Figure out if there are any blocks beyond the end
@@ -768,14 +647,19 @@ xfs_free_eofblocks(
 		 * cache and we can't
 		 * do that within a transaction.
 		 */
-		if (use_iolock)
+		if (flags & XFS_FREE_EOF_TRYLOCK) {
+			if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+				xfs_trans_cancel(tp, 0);
+				return 0;
+			}
+		} else {
 			xfs_ilock(ip, XFS_IOLOCK_EXCL);
+		}
 		error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE,
 				    ip->i_size);
 		if (error) {
 			xfs_trans_cancel(tp, 0);
-			if (use_iolock)
-				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 			return error;
 		}
 
@@ -812,8 +696,7 @@ xfs_free_eofblocks(
 			error = xfs_trans_commit(tp,
 						XFS_TRANS_RELEASE_LOG_RES);
 		}
-		xfs_iunlock(ip, (use_iolock ? (XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL)
-					    : XFS_ILOCK_EXCL));
+		xfs_iunlock(ip, XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL);
 	}
 	return error;
 }
@@ -1103,7 +986,7 @@ xfs_release(
 		 */
 		truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
 		if (truncated && VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
-			xfs_flush_pages(ip, 0, -1, XFS_B_ASYNC, FI_NONE);
+			xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE);
 	}
 
 	if (ip->i_d.di_nlink != 0) {
@@ -1113,7 +996,17 @@ xfs_release(
 		     (ip->i_df.if_flags & XFS_IFEXTENTS))  &&
 		    (!(ip->i_d.di_flags &
 				(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))) {
-			error = xfs_free_eofblocks(mp, ip, XFS_FREE_EOF_LOCK);
+
+			/*
+			 * If we can't get the iolock just skip truncating
+			 * the blocks past EOF because we could deadlock
+			 * with the mmap_sem otherwise.  We'll get another
+			 * chance to drop them once the last reference to
+			 * the inode is dropped, so we'll never leak blocks
+			 * permanently.
+			 */
+			error = xfs_free_eofblocks(mp, ip,
+						   XFS_FREE_EOF_TRYLOCK);
 			if (error)
 				return error;
 		}
@@ -1184,7 +1077,7 @@ xfs_inactive(
 		     (!(ip->i_d.di_flags &
 				(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) ||
 		      (ip->i_delayed_blks != 0)))) {
-			error = xfs_free_eofblocks(mp, ip, XFS_FREE_EOF_LOCK);
+			error = xfs_free_eofblocks(mp, ip, 0);
 			if (error)
 				return VN_INACTIVE_CACHE;
 		}
@@ -1380,7 +1273,6 @@ xfs_lookup(
 	if (error)
 		goto out_free_name;
 
-	xfs_itrace_ref(*ipp);
 	return 0;
 
 out_free_name:
@@ -1526,7 +1418,6 @@ xfs_create(
 	 * At this point, we've gotten a newly allocated inode.
 	 * It is locked (and joined to the transaction).
 	 */
-	xfs_itrace_ref(ip);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	/*
@@ -1986,9 +1877,6 @@ xfs_remove(
 	if (!is_dir && link_zero && xfs_inode_is_filestream(ip))
 		xfs_filestream_deassociate(ip);
 
-	xfs_itrace_exit(ip);
-	xfs_itrace_exit(dp);
-
  std_return:
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_POSTREMOVE)) {
 		XFS_SEND_NAMESP(mp, DM_EVENT_POSTREMOVE, dp, DM_RIGHT_NULL,
@@ -2201,7 +2089,8 @@ xfs_symlink(
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_SYMLINK)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_SYMLINK, dp,
 					DM_RIGHT_NULL, NULL, DM_RIGHT_NULL,
-					link_name->name, target_path, 0, 0, 0);
+					link_name->name,
+					(unsigned char *)target_path, 0, 0, 0);
 		if (error)
 			return error;
 	}
@@ -2285,7 +2174,6 @@ xfs_symlink(
 			goto error_return;
 		goto error1;
 	}
-	xfs_itrace_ref(ip);
 
 	/*
 	 * An error after we've joined dp to the transaction will result in the
@@ -2398,7 +2286,8 @@ std_return:
 					dp, DM_RIGHT_NULL,
 					error ? NULL : ip,
 					DM_RIGHT_NULL, link_name->name,
-					target_path, 0, error, 0);
+					(unsigned char *)target_path,
+					0, error, 0);
 	}
 
 	if (!error)
@@ -2456,46 +2345,6 @@ xfs_set_dmattrs(
 	return error;
 }
 
-int
-xfs_reclaim(
-	xfs_inode_t	*ip)
-{
-
-	xfs_itrace_entry(ip);
-
-	ASSERT(!VN_MAPPED(VFS_I(ip)));
-
-	/* bad inode, get out here ASAP */
-	if (is_bad_inode(VFS_I(ip))) {
-		xfs_ireclaim(ip);
-		return 0;
-	}
-
-	xfs_ioend_wait(ip);
-
-	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
-
-	/*
-	 * If we have nothing to flush with this inode then complete the
-	 * teardown now, otherwise break the link between the xfs inode and the
-	 * linux inode and clean up the xfs inode later. This avoids flushing
-	 * the inode to disk during the delete operation itself.
-	 *
-	 * When breaking the link, we need to set the XFS_IRECLAIMABLE flag
-	 * first to ensure that xfs_iunpin() will never see an xfs inode
-	 * that has a linux inode being reclaimed. Synchronisation is provided
-	 * by the i_flags_lock.
-	 */
-	if (!ip->i_update_core && (ip->i_itemp == NULL)) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		xfs_iflock(ip);
-		xfs_iflags_set(ip, XFS_IRECLAIMABLE);
-		return xfs_reclaim_inode(ip, 1, XFS_IFLUSH_DELWRI_ELSE_SYNC);
-	}
-	xfs_inode_set_reclaim_tag(ip);
-	return 0;
-}
-
 /*
  * xfs_alloc_file_space()
  *      This routine allocates disk space for the given file.
@@ -2868,7 +2717,6 @@ xfs_free_file_space(
 	ioffset = offset & ~(rounding - 1);
 
 	if (VN_CACHED(VFS_I(ip)) != 0) {
-		xfs_inval_cached_trace(ip, ioffset, -1, ioffset, -1);
 		error = xfs_flushinval_pages(ip, ioffset, -1, FI_REMAPF_LOCKED);
 		if (error)
 			goto out_unlock_iolock;