Merge branch '2.6.36-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/xfsdev

* '2.6.36-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/xfsdev:
  xfs: do not discard page cache data on EAGAIN
  xfs: don't do memory allocation under the CIL context lock
  xfs: Reduce log force overhead for delayed logging
  xfs: dummy transactions should not dirty VFS state
  xfs: ensure f_ffree returned by statfs() is non-negative
  xfs: handle negative wbc->nr_to_write during sync writeback
  writeback: write_cache_pages doesn't terminate at nr_to_write <= 0
  xfs: fix untrusted inode number lookup
  xfs: ensure we mark all inodes in a freed cluster XFS_ISTALE
  xfs: unlock items before allowing the CIL to commit

fs/xfs/linux-2.6/xfs_aops.c

@@ -852,8 +852,8 @@ xfs_convert_page(
 		SetPageUptodate(page);
 
 	if (count) {
-		wbc->nr_to_write--;
-		if (wbc->nr_to_write <= 0)
+		if (--wbc->nr_to_write <= 0 &&
+		    wbc->sync_mode == WB_SYNC_NONE)
 			done = 1;
 	}
 	xfs_start_page_writeback(page, !page_dirty, count);
@@ -1068,7 +1068,7 @@ xfs_vm_writepage(
 	 * by themselves.
 	 */
 	if ((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == PF_MEMALLOC)
-		goto out_fail;
+		goto redirty;
 
 	/*
 	 * We need a transaction if there are delalloc or unwritten buffers
@@ -1080,7 +1080,7 @@ xfs_vm_writepage(
 	 */
 	xfs_count_page_state(page, &delalloc, &unwritten);
 	if ((current->flags & PF_FSTRANS) && (delalloc || unwritten))
-		goto out_fail;
+		goto redirty;
 
 	/* Is this page beyond the end of the file? */
 	offset = i_size_read(inode);
@@ -1245,12 +1245,15 @@ xfs_vm_writepage(
 	if (iohead)
 		xfs_cancel_ioend(iohead);
 
+	if (err == -EAGAIN)
+		goto redirty;
+
 	xfs_aops_discard_page(page);
 	ClearPageUptodate(page);
 	unlock_page(page);
 	return err;
 
-out_fail:
+redirty:
 	redirty_page_for_writepage(wbc, page);
 	unlock_page(page);
 	return 0;

fs/xfs/linux-2.6/xfs_super.c

@@ -1226,6 +1226,7 @@ xfs_fs_statfs(
 	struct xfs_inode	*ip = XFS_I(dentry->d_inode);
 	__uint64_t		fakeinos, id;
 	xfs_extlen_t		lsize;
+	__int64_t		ffree;
 
 	statp->f_type = XFS_SB_MAGIC;
 	statp->f_namelen = MAXNAMELEN - 1;
@@ -1249,7 +1250,11 @@ xfs_fs_statfs(
 		statp->f_files = min_t(typeof(statp->f_files),
 					statp->f_files,
 					mp->m_maxicount);
-	statp->f_ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree);
+
+	/* make sure statp->f_ffree does not underflow */
+	ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree);
+	statp->f_ffree = max_t(__int64_t, ffree, 0);
+
 	spin_unlock(&mp->m_sb_lock);
 
 	if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) ||
@@ -1402,7 +1407,7 @@ xfs_fs_freeze(
 
 	xfs_save_resvblks(mp);
 	xfs_quiesce_attr(mp);
-	return -xfs_fs_log_dummy(mp);
+	return -xfs_fs_log_dummy(mp, SYNC_WAIT);
 }
 
 STATIC int

fs/xfs/linux-2.6/xfs_sync.c

@@ -34,6 +34,7 @@
 #include "xfs_inode_item.h"
 #include "xfs_quota.h"
 #include "xfs_trace.h"
+#include "xfs_fsops.h"
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
@@ -340,38 +341,6 @@ xfs_sync_attr(
 				     XFS_ICI_NO_TAG, 0, NULL);
 }
 
-STATIC int
-xfs_commit_dummy_trans(
-	struct xfs_mount	*mp,
-	uint			flags)
-{
-	struct xfs_inode	*ip = mp->m_rootip;
-	struct xfs_trans	*tp;
-	int			error;
-
-	/*
-	 * Put a dummy transaction in the log to tell recovery
-	 * that all others are OK.
-	 */
-	tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
-	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return error;
-	}
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-	xfs_trans_ijoin(tp, ip);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-	error = xfs_trans_commit(tp, 0);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	/* the log force ensures this transaction is pushed to disk */
-	xfs_log_force(mp, (flags & SYNC_WAIT) ? XFS_LOG_SYNC : 0);
-	return error;
-}
-
 STATIC int
 xfs_sync_fsdata(
 	struct xfs_mount	*mp)
@@ -432,7 +401,7 @@ xfs_quiesce_data(
 
 	/* mark the log as covered if needed */
 	if (xfs_log_need_covered(mp))
-		error2 = xfs_commit_dummy_trans(mp, SYNC_WAIT);
+		error2 = xfs_fs_log_dummy(mp, SYNC_WAIT);
 
 	/* flush data-only devices */
 	if (mp->m_rtdev_targp)
@@ -563,7 +532,7 @@ xfs_flush_inodes(
 /*
  * Every sync period we need to unpin all items, reclaim inodes and sync
  * disk quotas.  We might need to cover the log to indicate that the
- * filesystem is idle.
+ * filesystem is idle and not frozen.
  */
 STATIC void
 xfs_sync_worker(
@@ -577,8 +546,9 @@ xfs_sync_worker(
 		xfs_reclaim_inodes(mp, 0);
 		/* dgc: errors ignored here */
 		error = xfs_qm_sync(mp, SYNC_TRYLOCK);
-		if (xfs_log_need_covered(mp))
-			error = xfs_commit_dummy_trans(mp, 0);
+		if (mp->m_super->s_frozen == SB_UNFROZEN &&
+		    xfs_log_need_covered(mp))
+			error = xfs_fs_log_dummy(mp, 0);
 	}
 	mp->m_sync_seq++;
 	wake_up(&mp->m_wait_single_sync_task);

fs/xfs/xfs_fsops.c

@@ -604,31 +604,36 @@ xfs_reserve_blocks(
 	return 0;
 }
 
+/*
+ * Dump a transaction into the log that contains no real change. This is needed
+ * to be able to make the log dirty or stamp the current tail LSN into the log
+ * during the covering operation.
+ *
+ * We cannot use an inode here for this - that will push dirty state back up
+ * into the VFS and then periodic inode flushing will prevent log covering from
+ * making progress. Hence we log a field in the superblock instead.
+ */
 int
 xfs_fs_log_dummy(
-	xfs_mount_t	*mp)
+	xfs_mount_t	*mp,
+	int		flags)
 {
 	xfs_trans_t	*tp;
-	xfs_inode_t	*ip;
 	int		error;
 
 	tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1, KM_SLEEP);
-	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
+	error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
+					XFS_DEFAULT_LOG_COUNT);
 	if (error) {
 		xfs_trans_cancel(tp, 0);
 		return error;
 	}
 
-	ip = mp->m_rootip;
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-	xfs_trans_ijoin(tp, ip);
-	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	/* log the UUID because it is an unchanging field */
+	xfs_mod_sb(tp, XFS_SB_UUID);
+	if (flags & SYNC_WAIT)
 		xfs_trans_set_sync(tp);
-	error = xfs_trans_commit(tp, 0);
-
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	return error;
+	return xfs_trans_commit(tp, 0);
 }
 
 int

fs/xfs/xfs_fsops.h

@@ -25,6 +25,6 @@ extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
 extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval,
 				xfs_fsop_resblks_t *outval);
 extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags);
-extern int xfs_fs_log_dummy(xfs_mount_t *mp);
+extern int xfs_fs_log_dummy(xfs_mount_t *mp, int flags);
 
 #endif	/* __XFS_FSOPS_H__ */

fs/xfs/xfs_ialloc.c

@@ -1213,7 +1213,6 @@ xfs_imap_lookup(
 	struct xfs_inobt_rec_incore rec;
 	struct xfs_btree_cur	*cur;
 	struct xfs_buf		*agbp;
-	xfs_agino_t		startino;
 	int			error;
 	int			i;
 
@@ -1227,13 +1226,13 @@ xfs_imap_lookup(
 	}
 
 	/*
-	 * derive and lookup the exact inode record for the given agino. If the
-	 * record cannot be found, then it's an invalid inode number and we
-	 * should abort.
+	 * Lookup the inode record for the given agino. If the record cannot be
+	 * found, then it's an invalid inode number and we should abort. Once
+	 * we have a record, we need to ensure it contains the inode number
+	 * we are looking up.
 	 */
 	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
-	startino = agino & ~(XFS_IALLOC_INODES(mp) - 1);
-	error = xfs_inobt_lookup(cur, startino, XFS_LOOKUP_EQ, &i);
+	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
 	if (!error) {
 		if (i)
 			error = xfs_inobt_get_rec(cur, &rec, &i);
@@ -1246,6 +1245,11 @@ xfs_imap_lookup(
 	if (error)
 		return error;
 
+	/* check that the returned record contains the required inode */
+	if (rec.ir_startino > agino ||
+	    rec.ir_startino + XFS_IALLOC_INODES(mp) <= agino)
+		return EINVAL;
+
 	/* for untrusted inodes check it is allocated first */
 	if ((flags & XFS_IGET_UNTRUSTED) &&
 	    (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino)))

fs/xfs/xfs_inode.c

@@ -1914,6 +1914,11 @@ xfs_iunlink_remove(
 	return 0;
 }
 
+/*
+ * A big issue when freeing the inode cluster is is that we _cannot_ skip any
+ * inodes that are in memory - they all must be marked stale and attached to
+ * the cluster buffer.
+ */
 STATIC void
 xfs_ifree_cluster(
 	xfs_inode_t	*free_ip,
@@ -1945,8 +1950,6 @@ xfs_ifree_cluster(
 	}
 
 	for (j = 0; j < nbufs; j++, inum += ninodes) {
-		int	found = 0;
-
 		blkno = XFS_AGB_TO_DADDR(mp, XFS_INO_TO_AGNO(mp, inum),
 					 XFS_INO_TO_AGBNO(mp, inum));
 
@@ -1965,7 +1968,9 @@ xfs_ifree_cluster(
 		/*
 		 * Walk the inodes already attached to the buffer and mark them
 		 * stale. These will all have the flush locks held, so an
-		 * in-memory inode walk can't lock them.
+		 * in-memory inode walk can't lock them. By marking them all
+		 * stale first, we will not attempt to lock them in the loop
+		 * below as the XFS_ISTALE flag will be set.
 		 */
 		lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
 		while (lip) {
@@ -1977,11 +1982,11 @@ xfs_ifree_cluster(
 							&iip->ili_flush_lsn,
 							&iip->ili_item.li_lsn);
 				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
-				found++;
 			}
 			lip = lip->li_bio_list;
 		}
 
+
 		/*
 		 * For each inode in memory attempt to add it to the inode
 		 * buffer and set it up for being staled on buffer IO
@@ -1993,6 +1998,7 @@ xfs_ifree_cluster(
 		 * even trying to lock them.
 		 */
 		for (i = 0; i < ninodes; i++) {
+retry:
 			read_lock(&pag->pag_ici_lock);
 			ip = radix_tree_lookup(&pag->pag_ici_root,
 					XFS_INO_TO_AGINO(mp, (inum + i)));
@@ -2003,38 +2009,36 @@ xfs_ifree_cluster(
 				continue;
 			}
 
-			/* don't try to lock/unlock the current inode */
+			/*
+			 * Don't try to lock/unlock the current inode, but we
+			 * _cannot_ skip the other inodes that we did not find
+			 * in the list attached to the buffer and are not
+			 * already marked stale. If we can't lock it, back off
+			 * and retry.
+			 */
 			if (ip != free_ip &&
 			    !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
 				read_unlock(&pag->pag_ici_lock);
-				continue;
+				delay(1);
+				goto retry;
 			}
 			read_unlock(&pag->pag_ici_lock);
 
-			if (!xfs_iflock_nowait(ip)) {
-				if (ip != free_ip)
-					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				continue;
-			}
-
+			xfs_iflock(ip);
 			xfs_iflags_set(ip, XFS_ISTALE);
-			if (xfs_inode_clean(ip)) {
-				ASSERT(ip != free_ip);
-				xfs_ifunlock(ip);
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				continue;
-			}
 
+			/*
+			 * we don't need to attach clean inodes or those only
+			 * with unlogged changes (which we throw away, anyway).
+			 */
 			iip = ip->i_itemp;
-			if (!iip) {
-				/* inode with unlogged changes only */
+			if (!iip || xfs_inode_clean(ip)) {
 				ASSERT(ip != free_ip);
 				ip->i_update_core = 0;
 				xfs_ifunlock(ip);
 				xfs_iunlock(ip, XFS_ILOCK_EXCL);
 				continue;
 			}
-			found++;
 
 			iip->ili_last_fields = iip->ili_format.ilf_fields;
 			iip->ili_format.ilf_fields = 0;
@@ -2049,7 +2053,6 @@ xfs_ifree_cluster(
 				xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		}
 
-		if (found)
 		xfs_trans_stale_inode_buf(tp, bp);
 		xfs_trans_binval(tp, bp);
 	}

fs/xfs/xfs_log.c

@@ -3015,7 +3015,8 @@ _xfs_log_force(
 
 	XFS_STATS_INC(xs_log_force);
 
-	xlog_cil_push(log, 1);
+	if (log->l_cilp)
+		xlog_cil_force(log);
 
 	spin_lock(&log->l_icloglock);
 
@@ -3167,7 +3168,7 @@ _xfs_log_force_lsn(
 	XFS_STATS_INC(xs_log_force);
 
 	if (log->l_cilp) {
-		lsn = xlog_cil_push_lsn(log, lsn);
+		lsn = xlog_cil_force_lsn(log, lsn);
 		if (lsn == NULLCOMMITLSN)
 			return 0;
 	}
@@ -3724,7 +3725,7 @@ xfs_log_force_umount(
 	 * call below.
 	 */
 	if (!logerror && (mp->m_flags & XFS_MOUNT_DELAYLOG))
-		xlog_cil_push(log, 1);
+		xlog_cil_force(log);
 
 	/*
 	 * We must hold both the GRANT lock and the LOG lock,

fs/xfs/xfs_log_priv.h

@@ -422,6 +422,7 @@ struct xfs_cil {
 	struct rw_semaphore	xc_ctx_lock;
 	struct list_head	xc_committing;
 	sv_t			xc_commit_wait;
+	xfs_lsn_t		xc_current_sequence;
 };
 
 /*
@@ -562,8 +563,16 @@ int	xlog_cil_init(struct log *log);
 void	xlog_cil_init_post_recovery(struct log *log);
 void	xlog_cil_destroy(struct log *log);
 
-int	xlog_cil_push(struct log *log, int push_now);
-xfs_lsn_t xlog_cil_push_lsn(struct log *log, xfs_lsn_t push_sequence);
+/*
+ * CIL force routines
+ */
+xfs_lsn_t xlog_cil_force_lsn(struct log *log, xfs_lsn_t sequence);
+
+static inline void
+xlog_cil_force(struct log *log)
+{
+	xlog_cil_force_lsn(log, log->l_cilp->xc_current_sequence);
+}
 
 /*
  * Unmount record type is used as a pseudo transaction type for the ticket.

fs/xfs/xfs_trans.c

@@ -1167,7 +1167,7 @@ xfs_trans_del_item(
  * Unlock all of the items of a transaction and free all the descriptors
  * of that transaction.
  */
-STATIC void
+void
 xfs_trans_free_items(
 	struct xfs_trans	*tp,
 	xfs_lsn_t		commit_lsn,
@@ -1653,9 +1653,6 @@ xfs_trans_commit_cil(
 		return error;
 
 	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
-
-	/* xfs_trans_free_items() unlocks them first */
-	xfs_trans_free_items(tp, *commit_lsn, 0);
 	xfs_trans_free(tp);
 	return 0;
 }

fs/xfs/xfs_trans_priv.h

@@ -25,7 +25,8 @@ struct xfs_trans;
 
 void	xfs_trans_add_item(struct xfs_trans *, struct xfs_log_item *);
 void	xfs_trans_del_item(struct xfs_log_item *);
-
+void	xfs_trans_free_items(struct xfs_trans *tp, xfs_lsn_t commit_lsn,
+				int flags);
 void	xfs_trans_item_committed(struct xfs_log_item *lip,
 				xfs_lsn_t commit_lsn, int aborted);
 void	xfs_trans_unreserve_and_mod_sb(struct xfs_trans *tp);

mm/page-writeback.c

@@ -985,24 +985,18 @@ int write_cache_pages(struct address_space *mapping,
 				}
 			}
 
-			if (wbc->nr_to_write > 0) {
-				if (--wbc->nr_to_write == 0 &&
-				    wbc->sync_mode == WB_SYNC_NONE) {
 			/*
-					 * We stop writing back only if we are
-					 * not doing integrity sync. In case of
-					 * integrity sync we have to keep going
-					 * because someone may be concurrently
-					 * dirtying pages, and we might have
-					 * synced a lot of newly appeared dirty
-					 * pages, but have not synced all of the
-					 * old dirty pages.
+			 * We stop writing back only if we are not doing
+			 * integrity sync. In case of integrity sync we have to
+			 * keep going until we have written all the pages
+			 * we tagged for writeback prior to entering this loop.
 			 */
+			if (--wbc->nr_to_write <= 0 &&
+			    wbc->sync_mode == WB_SYNC_NONE) {
 				done = 1;
 				break;
 			}
 		}
-		}
 		pagevec_release(&pvec);
 		cond_resched();
 	}