Merge branch 'mw-3.1-jul25' of git://oss.oracle.com/git/smushran/linux-2.6 into ocfs2-fixes

1 files changed, 15 insertions, 471 deletions

diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index b7a5fe7c52c8..88d121486c52 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -50,430 +50,6 @@
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
 
-int
-xfs_setattr(
-	struct xfs_inode	*ip,
-	struct iattr		*iattr,
-	int			flags)
-{
-	xfs_mount_t		*mp = ip->i_mount;
-	struct inode		*inode = VFS_I(ip);
-	int			mask = iattr->ia_valid;
-	xfs_trans_t		*tp;
-	int			code;
-	uint			lock_flags;
-	uint			commit_flags=0;
-	uid_t			uid=0, iuid=0;
-	gid_t			gid=0, igid=0;
-	struct xfs_dquot	*udqp, *gdqp, *olddquot1, *olddquot2;
-	int			need_iolock = 1;
-
-	trace_xfs_setattr(ip);
-
-	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		return XFS_ERROR(EROFS);
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
-
-	code = -inode_change_ok(inode, iattr);
-	if (code)
-		return code;
-
-	olddquot1 = olddquot2 = NULL;
-	udqp = gdqp = NULL;
-
-	/*
-	 * If disk quotas is on, we make sure that the dquots do exist on disk,
-	 * before we start any other transactions. Trying to do this later
-	 * is messy. We don't care to take a readlock to look at the ids
-	 * in inode here, because we can't hold it across the trans_reserve.
-	 * If the IDs do change before we take the ilock, we're covered
-	 * because the i_*dquot fields will get updated anyway.
-	 */
-	if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
-		uint	qflags = 0;
-
-		if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
-			uid = iattr->ia_uid;
-			qflags |= XFS_QMOPT_UQUOTA;
-		} else {
-			uid = ip->i_d.di_uid;
-		}
-		if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
-			gid = iattr->ia_gid;
-			qflags |= XFS_QMOPT_GQUOTA;
-		}  else {
-			gid = ip->i_d.di_gid;
-		}
-
-		/*
-		 * We take a reference when we initialize udqp and gdqp,
-		 * so it is important that we never blindly double trip on
-		 * the same variable. See xfs_create() for an example.
-		 */
-		ASSERT(udqp == NULL);
-		ASSERT(gdqp == NULL);
-		code = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip),
-					 qflags, &udqp, &gdqp);
-		if (code)
-			return code;
-	}
-
-	/*
-	 * For the other attributes, we acquire the inode lock and
-	 * first do an error checking pass.
-	 */
-	tp = NULL;
-	lock_flags = XFS_ILOCK_EXCL;
-	if (flags & XFS_ATTR_NOLOCK)
-		need_iolock = 0;
-	if (!(mask & ATTR_SIZE)) {
-		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 (need_iolock)
-			lock_flags |= XFS_IOLOCK_EXCL;
-	}
-
-	xfs_ilock(ip, lock_flags);
-
-	/*
-	 * Change file ownership.  Must be the owner or privileged.
-	 */
-	if (mask & (ATTR_UID|ATTR_GID)) {
-		/*
-		 * These IDs could have changed since we last looked at them.
-		 * But, we're assured that if the ownership did change
-		 * while we didn't have the inode locked, inode's dquot(s)
-		 * would have changed also.
-		 */
-		iuid = ip->i_d.di_uid;
-		igid = ip->i_d.di_gid;
-		gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
-		uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
-
-		/*
-		 * Do a quota reservation only if uid/gid is actually
-		 * going to change.
-		 */
-		if (XFS_IS_QUOTA_RUNNING(mp) &&
-		    ((XFS_IS_UQUOTA_ON(mp) && iuid != uid) ||
-		     (XFS_IS_GQUOTA_ON(mp) && igid != gid))) {
-			ASSERT(tp);
-			code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
-						capable(CAP_FOWNER) ?
-						XFS_QMOPT_FORCE_RES : 0);
-			if (code)	/* out of quota */
-				goto error_return;
-		}
-	}
-
-	/*
-	 * Truncate file.  Must have write permission and not be a directory.
-	 */
-	if (mask & ATTR_SIZE) {
-		/* Short circuit the truncate case for zero length files */
-		if (iattr->ia_size == 0 &&
-		    ip->i_size == 0 && ip->i_d.di_nextents == 0) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			lock_flags &= ~XFS_ILOCK_EXCL;
-			if (mask & ATTR_CTIME) {
-				inode->i_mtime = inode->i_ctime =
-						current_fs_time(inode->i_sb);
-				xfs_mark_inode_dirty_sync(ip);
-			}
-			code = 0;
-			goto error_return;
-		}
-
-		if (S_ISDIR(ip->i_d.di_mode)) {
-			code = XFS_ERROR(EISDIR);
-			goto error_return;
-		} else if (!S_ISREG(ip->i_d.di_mode)) {
-			code = XFS_ERROR(EINVAL);
-			goto error_return;
-		}
-
-		/*
-		 * Make sure that the dquots are attached to the inode.
-		 */
-		code = xfs_qm_dqattach_locked(ip, 0);
-		if (code)
-			goto error_return;
-
-		/*
-		 * Now we can make the changes.  Before we join the inode
-		 * to the transaction, if ATTR_SIZE is set then take care of
-		 * the part of the truncation that must be done without the
-		 * inode lock.  This needs to be done before joining the inode
-		 * to the transaction, because the inode cannot be unlocked
-		 * once it is a part of the transaction.
-		 */
-		if (iattr->ia_size > ip->i_size) {
-			/*
-			 * Do the first part of growing a file: zero any data
-			 * in the last block that is beyond the old EOF.  We
-			 * need to do this before the inode is joined to the
-			 * transaction to modify the i_size.
-			 */
-			code = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
-			if (code)
-				goto error_return;
-		}
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		lock_flags &= ~XFS_ILOCK_EXCL;
-
-		/*
-		 * We are going to log the inode size change in this
-		 * transaction so any previous writes that are beyond the on
-		 * disk EOF and the new EOF that have not been written out need
-		 * to be written here. If we do not write the data out, we
-		 * expose ourselves to the null files problem.
-		 *
-		 * Only flush from the on disk size to the smaller of the in
-		 * memory file size or the new size as that's the range we
-		 * really care about here and prevents waiting for other data
-		 * not within the range we care about here.
-		 */
-		if (ip->i_size != ip->i_d.di_size &&
-		    iattr->ia_size > ip->i_d.di_size) {
-			code = xfs_flush_pages(ip,
-					ip->i_d.di_size, iattr->ia_size,
-					XBF_ASYNC, FI_NONE);
-			if (code)
-				goto error_return;
-		}
-
-		/* wait for all I/O to complete */
-		xfs_ioend_wait(ip);
-
-		code = -block_truncate_page(inode->i_mapping, iattr->ia_size,
-					    xfs_get_blocks);
-		if (code)
-			goto error_return;
-
-		tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
-		code = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
-					 XFS_TRANS_PERM_LOG_RES,
-					 XFS_ITRUNCATE_LOG_COUNT);
-		if (code)
-			goto error_return;
-
-		truncate_setsize(inode, iattr->ia_size);
-
-		commit_flags = XFS_TRANS_RELEASE_LOG_RES;
-		lock_flags |= XFS_ILOCK_EXCL;
-
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-		xfs_trans_ijoin(tp, ip);
-
-		/*
-		 * Only change the c/mtime if we are changing the size
-		 * 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 | 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;
-			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)) {
-			/*
-			 * signal a sync transaction unless
-			 * we're truncating an already unlinked
-			 * file on a wsync filesystem
-			 */
-			code = xfs_itruncate_finish(&tp, ip, iattr->ia_size,
-					    XFS_DATA_FORK,
-					    ((ip->i_d.di_nlink != 0 ||
-					      !(mp->m_flags & XFS_MOUNT_WSYNC))
-					     ? 1 : 0));
-			if (code)
-				goto abort_return;
-			/*
-			 * Truncated "down", so we're removing references
-			 * to old data here - if we now delay flushing for
-			 * a long time, we expose ourselves unduly to the
-			 * notorious NULL files problem.  So, we mark this
-			 * vnode and flush it when the file is closed, and
-			 * do not wait the usual (long) time for writeout.
-			 */
-			xfs_iflags_set(ip, XFS_ITRUNCATED);
-		}
-	} else if (tp) {
-		xfs_trans_ijoin(tp, ip);
-	}
-
-	/*
-	 * Change file ownership.  Must be the owner or privileged.
-	 */
-	if (mask & (ATTR_UID|ATTR_GID)) {
-		/*
-		 * CAP_FSETID overrides the following restrictions:
-		 *
-		 * The set-user-ID and set-group-ID bits of a file will be
-		 * cleared upon successful return from chown()
-		 */
-		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
-		    !capable(CAP_FSETID)) {
-			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
-		}
-
-		/*
-		 * Change the ownerships and register quota modifications
-		 * in the transaction.
-		 */
-		if (iuid != uid) {
-			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) {
-				ASSERT(mask & ATTR_UID);
-				ASSERT(udqp);
-				olddquot1 = xfs_qm_vop_chown(tp, ip,
-							&ip->i_udquot, udqp);
-			}
-			ip->i_d.di_uid = uid;
-			inode->i_uid = uid;
-		}
-		if (igid != gid) {
-			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
-				ASSERT(!XFS_IS_PQUOTA_ON(mp));
-				ASSERT(mask & ATTR_GID);
-				ASSERT(gdqp);
-				olddquot2 = xfs_qm_vop_chown(tp, ip,
-							&ip->i_gdquot, gdqp);
-			}
-			ip->i_d.di_gid = gid;
-			inode->i_gid = gid;
-		}
-	}
-
-	/*
-	 * Change file access modes.
-	 */
-	if (mask & ATTR_MODE) {
-		umode_t mode = iattr->ia_mode;
-
-		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
-			mode &= ~S_ISGID;
-
-		ip->i_d.di_mode &= S_IFMT;
-		ip->i_d.di_mode |= mode & ~S_IFMT;
-
-		inode->i_mode &= S_IFMT;
-		inode->i_mode |= mode & ~S_IFMT;
-	}
-
-	/*
-	 * Change file access or modified times.
-	 */
-	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_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;
-	}
-	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;
-	}
-
-	/*
-	 * And finally, log the inode core if any attribute in it
-	 * has been changed.
-	 */
-	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);
-
-	/*
-	 * If this is a synchronous mount, make sure that the
-	 * transaction goes to disk before returning to the user.
-	 * This is slightly sub-optimal in that truncates require
-	 * two sync transactions instead of one for wsync filesystems.
-	 * One for the truncate and one for the timestamps since we
-	 * don't want to change the timestamps unless we're sure the
-	 * truncate worked.  Truncates are less than 1% of the laddis
-	 * mix so this probably isn't worth the trouble to optimize.
-	 */
-	code = 0;
-	if (mp->m_flags & XFS_MOUNT_WSYNC)
-		xfs_trans_set_sync(tp);
-
-	code = xfs_trans_commit(tp, commit_flags);
-
-	xfs_iunlock(ip, lock_flags);
-
-	/*
-	 * Release any dquot(s) the inode had kept before chown.
-	 */
-	xfs_qm_dqrele(olddquot1);
-	xfs_qm_dqrele(olddquot2);
-	xfs_qm_dqrele(udqp);
-	xfs_qm_dqrele(gdqp);
-
-	if (code)
-		return code;
-
-	/*
-	 * XXX(hch): Updating the ACL entries is not atomic vs the i_mode
-	 * 	     update.  We could avoid this with linked transactions
-	 * 	     and passing down the transaction pointer all the way
-	 *	     to attr_set.  No previous user of the generic
-	 * 	     Posix ACL code seems to care about this issue either.
-	 */
-	if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
-		code = -xfs_acl_chmod(inode);
-		if (code)
-			return XFS_ERROR(code);
-	}
-
-	return 0;
-
- abort_return:
-	commit_flags |= XFS_TRANS_ABORT;
- error_return:
-	xfs_qm_dqrele(udqp);
-	xfs_qm_dqrele(gdqp);
-	if (tp) {
-		xfs_trans_cancel(tp, commit_flags);
-	}
-	if (lock_flags != 0) {
-		xfs_iunlock(ip, lock_flags);
-	}
-	return code;
-}
-
 /*
  * The maximum pathlen is 1024 bytes. Since the minimum file system
  * blocksize is 512 bytes, we can get a max of 2 extents back from
@@ -621,13 +197,6 @@ xfs_free_eofblocks(
 		 */
 		tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
 
-		/*
-		 * Do the xfs_itruncate_start() call before
-		 * reserving any log space because
-		 * itruncate_start will call into the buffer
-		 * cache and we can't
-		 * do that within a transaction.
-		 */
 		if (flags & XFS_FREE_EOF_TRYLOCK) {
 			if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
 				xfs_trans_cancel(tp, 0);
@@ -636,13 +205,6 @@ xfs_free_eofblocks(
 		} 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);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-			return error;
-		}
 
 		error = xfs_trans_reserve(tp, 0,
 					  XFS_ITRUNCATE_LOG_RES(mp),
@@ -658,15 +220,12 @@ xfs_free_eofblocks(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip);
 
-		error = xfs_itruncate_finish(&tp, ip,
-					     ip->i_size,
-					     XFS_DATA_FORK,
-					     0);
-		/*
-		 * If we get an error at this point we
-		 * simply don't bother truncating the file.
-		 */
+		error = xfs_itruncate_data(&tp, ip, ip->i_size);
 		if (error) {
+			/*
+			 * If we get an error at this point we simply don't
+			 * bother truncating the file.
+			 */
 			xfs_trans_cancel(tp,
 					 (XFS_TRANS_RELEASE_LOG_RES |
 					  XFS_TRANS_ABORT));
@@ -960,8 +519,11 @@ xfs_release(
 		 * be exposed to that problem.
 		 */
 		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, XBF_ASYNC, FI_NONE);
+		if (truncated) {
+			xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
+			if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
+				xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE);
+		}
 	}
 
 	if (ip->i_d.di_nlink == 0)
@@ -1081,20 +643,9 @@ xfs_inactive(
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
 	if (truncate) {
-		/*
-		 * Do the xfs_itruncate_start() call before
-		 * reserving any log space because itruncate_start
-		 * will call into the buffer cache and we can't
-		 * do that within a transaction.
-		 */
 		xfs_ilock(ip, XFS_IOLOCK_EXCL);
 
-		error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, 0);
-		if (error) {
-			xfs_trans_cancel(tp, 0);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-			return VN_INACTIVE_CACHE;
-		}
+		xfs_ioend_wait(ip);
 
 		error = xfs_trans_reserve(tp, 0,
 					  XFS_ITRUNCATE_LOG_RES(mp),
@@ -1111,16 +662,7 @@ xfs_inactive(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip);
 
-		/*
-		 * normally, we have to run xfs_itruncate_finish sync.
-		 * But if filesystem is wsync and we're in the inactive
-		 * path, then we know that nlink == 0, and that the
-		 * xaction that made nlink == 0 is permanently committed
-		 * since xfs_remove runs as a synchronous transaction.
-		 */
-		error = xfs_itruncate_finish(&tp, ip, 0, XFS_DATA_FORK,
-				(!(mp->m_flags & XFS_MOUNT_WSYNC) ? 1 : 0));
-
+		error = xfs_itruncate_data(&tp, ip, 0);
 		if (error) {
 			xfs_trans_cancel(tp,
 				XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
@@ -2427,6 +1969,8 @@ xfs_zero_remaining_bytes(
 	if (!bp)
 		return XFS_ERROR(ENOMEM);
 
+	xfs_buf_unlock(bp);
+
 	for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
 		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 		nimap = 1;
@@ -2781,7 +2325,7 @@ xfs_change_file_space(
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = startoffset;
 
-		error = xfs_setattr(ip, &iattr, attr_flags);
+		error = xfs_setattr_size(ip, &iattr, attr_flags);
 
 		if (error)
 			return error;