1 files changed, 183 insertions, 159 deletions

diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 18a4b8e11df2..25ea2408118f 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -15,6 +15,7 @@
  * along with this program; if not, write the Free Software Foundation,
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
+
 #include "xfs.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
@@ -52,11 +53,11 @@
 #include "xfs_trans_priv.h"
 #include "xfs_filestream.h"
 #include "xfs_da_btree.h"
-#include "xfs_dir2_trace.h"
 #include "xfs_extfree_item.h"
 #include "xfs_mru_cache.h"
 #include "xfs_inode_item.h"
 #include "xfs_sync.h"
+#include "xfs_trace.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>
@@ -876,12 +877,11 @@ xfsaild(
 {
 	struct xfs_ail	*ailp = data;
 	xfs_lsn_t	last_pushed_lsn = 0;
-	long		tout = 0;
+	long		tout = 0; /* milliseconds */
 
 	while (!kthread_should_stop()) {
-		if (tout)
-			schedule_timeout_interruptible(msecs_to_jiffies(tout));
-		tout = 1000;
+		schedule_timeout_interruptible(tout ?
+				msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
 
 		/* swsusp */
 		try_to_freeze();
@@ -930,13 +930,37 @@ xfs_fs_alloc_inode(
  */
 STATIC void
 xfs_fs_destroy_inode(
-	struct inode	*inode)
+	struct inode		*inode)
 {
-	xfs_inode_t		*ip = XFS_I(inode);
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	xfs_itrace_entry(ip);
 
 	XFS_STATS_INC(vn_reclaim);
-	if (xfs_reclaim(ip))
-		panic("%s: cannot reclaim 0x%p\n", __func__, inode);
+
+	/* bad inode, get out here ASAP */
+	if (is_bad_inode(inode))
+		goto out_reclaim;
+
+	xfs_ioend_wait(ip);
+
+	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
+
+	/*
+	 * We should never get here with one of the reclaim flags already set.
+	 */
+	ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
+	ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
+
+	/*
+	 * We always use background reclaim here because even if the
+	 * inode is clean, it still may be under IO and hence we have
+	 * to take the flush lock. The background reclaim path handles
+	 * this more efficiently than we can here, so simply let background
+	 * reclaim tear down all inodes.
+	 */
+out_reclaim:
+	xfs_inode_set_reclaim_tag(ip);
 }
 
 /*
@@ -973,7 +997,6 @@ xfs_fs_inode_init_once(
 
 	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
 		     "xfsino", ip->i_ino);
-	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
 }
 
 /*
@@ -998,12 +1021,45 @@ xfs_fs_dirty_inode(
 	XFS_I(inode)->i_update_core = 1;
 }
 
-/*
- * Attempt to flush the inode, this will actually fail
- * if the inode is pinned, but we dirty the inode again
- * at the point when it is unpinned after a log write,
- * since this is when the inode itself becomes flushable.
- */
+STATIC int
+xfs_log_inode(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			error;
+
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
+	error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
+
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		/* we need to return with the lock hold shared */
+		xfs_ilock(ip, XFS_ILOCK_SHARED);
+		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);
+	xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
+
+	return error;
+}
+
 STATIC int
 xfs_fs_write_inode(
 	struct inode		*inode,
@@ -1011,7 +1067,7 @@ xfs_fs_write_inode(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	int			error = 0;
+	int			error = EAGAIN;
 
 	xfs_itrace_entry(ip);
 
@@ -1022,35 +1078,55 @@ xfs_fs_write_inode(
 		error = xfs_wait_on_pages(ip, 0, -1);
 		if (error)
 			goto out;
-	}
 
-	/*
-	 * Bypass inodes which have already been cleaned by
-	 * the inode flush clustering code inside xfs_iflush
-	 */
-	if (xfs_inode_clean(ip))
-		goto out;
-
-	/*
-	 * We make this non-blocking if the inode is contended, return
-	 * EAGAIN to indicate to the caller that they did not succeed.
-	 * This prevents the flush path from blocking on inodes inside
-	 * another operation right now, they get caught later by xfs_sync.
-	 */
-	if (sync) {
+		/*
+		 * Make sure the inode has hit stable storage.  By using the
+		 * log and the fsync transactions we reduce the IOs we have
+		 * to do here from two (log and inode) to just the log.
+		 *
+		 * Note: We still need to do a delwri write of the inode after
+		 * this to flush it to the backing buffer so that bulkstat
+		 * works properly if this is the first time the inode has been
+		 * written.  Because we hold the ilock atomically over the
+		 * transaction commit and the inode flush we are guaranteed
+		 * that the inode is not pinned when it returns. If the flush
+		 * lock is already held, then the inode has already been
+		 * flushed once and we don't need to flush it again.  Hence
+		 * the code will only flush the inode if it isn't already
+		 * being flushed.
+		 */
 		xfs_ilock(ip, XFS_ILOCK_SHARED);
-		xfs_iflock(ip);
-
-		error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
+		if (ip->i_update_core) {
+			error = xfs_log_inode(ip);
+			if (error)
+				goto out_unlock;
+		}
 	} else {
-		error = EAGAIN;
+		/*
+		 * We make this non-blocking if the inode is contended, return
+		 * EAGAIN to indicate to the caller that they did not succeed.
+		 * This prevents the flush path from blocking on inodes inside
+		 * another operation right now, they get caught later by xfs_sync.
+		 */
 		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
 			goto out;
-		if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
-			goto out_unlock;
+	}
+
+	if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
+		goto out_unlock;
 
-		error = xfs_iflush(ip, XFS_IFLUSH_ASYNC_NOBLOCK);
+	/*
+	 * Now we have the flush lock and the inode is not pinned, we can check
+	 * if the inode is really clean as we know that there are no pending
+	 * transaction completions, it is not waiting on the delayed write
+	 * queue and there is no IO in progress.
+	 */
+	if (xfs_inode_clean(ip)) {
+		xfs_ifunlock(ip);
+		error = 0;
+		goto out_unlock;
 	}
+	error = xfs_iflush(ip, 0);
 
  out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -1075,6 +1151,20 @@ xfs_fs_clear_inode(
 	XFS_STATS_INC(vn_remove);
 	XFS_STATS_DEC(vn_active);
 
+	/*
+	 * The iolock is used by the file system to coordinate reads,
+	 * writes, and block truncates.  Up to this point the lock
+	 * protected concurrent accesses by users of the inode.  But
+	 * from here forward we're doing some final processing of the
+	 * inode because we're done with it, and although we reuse the
+	 * iolock for protection it is really a distinct lock class
+	 * (in the lockdep sense) from before.  To keep lockdep happy
+	 * (and basically indicate what we are doing), we explicitly
+	 * re-init the iolock here.
+	 */
+	ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
+	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
+
 	xfs_inactive(ip);
 }
 
@@ -1092,8 +1182,6 @@ xfs_fs_put_super(
 	struct super_block	*sb)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
-	struct xfs_inode	*rip = mp->m_rootip;
-	int			unmount_event_flags = 0;
 
 	xfs_syncd_stop(mp);
 
@@ -1109,20 +1197,7 @@ xfs_fs_put_super(
 		xfs_sync_attr(mp, 0);
 	}
 
-#ifdef HAVE_DMAPI
-	if (mp->m_flags & XFS_MOUNT_DMAPI) {
-		unmount_event_flags =
-			(mp->m_dmevmask & (1 << DM_EVENT_UNMOUNT)) ?
-				0 : DM_FLAGS_UNWANTED;
-		/*
-		 * Ignore error from dmapi here, first unmount is not allowed
-		 * to fail anyway, and second we wouldn't want to fail a
-		 * unmount because of dmapi.
-		 */
-		XFS_SEND_PREUNMOUNT(mp, rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL,
-				NULL, NULL, 0, 0, unmount_event_flags);
-	}
-#endif
+	XFS_SEND_PREUNMOUNT(mp);
 
 	/*
 	 * Blow away any referenced inode in the filestreams cache.
@@ -1133,10 +1208,7 @@ xfs_fs_put_super(
 
 	XFS_bflush(mp->m_ddev_targp);
 
-	if (mp->m_flags & XFS_MOUNT_DMAPI) {
-		XFS_SEND_UNMOUNT(mp, rip, DM_RIGHT_NULL, 0, 0,
-				unmount_event_flags);
-	}
+	XFS_SEND_UNMOUNT(mp);
 
 	xfs_unmountfs(mp);
 	xfs_freesb(mp);
@@ -1237,6 +1309,29 @@ xfs_fs_statfs(
 	return 0;
 }
 
+STATIC void
+xfs_save_resvblks(struct xfs_mount *mp)
+{
+	__uint64_t resblks = 0;
+
+	mp->m_resblks_save = mp->m_resblks;
+	xfs_reserve_blocks(mp, &resblks, NULL);
+}
+
+STATIC void
+xfs_restore_resvblks(struct xfs_mount *mp)
+{
+	__uint64_t resblks;
+
+	if (mp->m_resblks_save) {
+		resblks = mp->m_resblks_save;
+		mp->m_resblks_save = 0;
+	} else
+		resblks = xfs_default_resblks(mp);
+
+	xfs_reserve_blocks(mp, &resblks, NULL);
+}
+
 STATIC int
 xfs_fs_remount(
 	struct super_block	*sb,
@@ -1316,11 +1411,27 @@ xfs_fs_remount(
 			}
 			mp->m_update_flags = 0;
 		}
+
+		/*
+		 * Fill out the reserve pool if it is empty. Use the stashed
+		 * value if it is non-zero, otherwise go with the default.
+		 */
+		xfs_restore_resvblks(mp);
 	}
 
 	/* rw -> ro */
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
+		/*
+		 * After we have synced the data but before we sync the
+		 * metadata, we need to free up the reserve block pool so that
+		 * the used block count in the superblock on disk is correct at
+		 * the end of the remount. Stash the current reserve pool size
+		 * so that if we get remounted rw, we can return it to the same
+		 * size.
+		 */
+
 		xfs_quiesce_data(mp);
+		xfs_save_resvblks(mp);
 		xfs_quiesce_attr(mp);
 		mp->m_flags |= XFS_MOUNT_RDONLY;
 	}
@@ -1339,11 +1450,22 @@ xfs_fs_freeze(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
+	xfs_save_resvblks(mp);
 	xfs_quiesce_attr(mp);
 	return -xfs_fs_log_dummy(mp);
 }
 
 STATIC int
+xfs_fs_unfreeze(
+	struct super_block	*sb)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	xfs_restore_resvblks(mp);
+	return 0;
+}
+
+STATIC int
 xfs_fs_show_options(
 	struct seq_file		*m,
 	struct vfsmount		*mnt)
@@ -1504,8 +1626,6 @@ xfs_fs_fill_super(
 		goto fail_vnrele;
 
 	kfree(mtpt);
-
-	xfs_itrace_exit(XFS_I(sb->s_root->d_inode));
 	return 0;
 
  out_filestream_unmount:
@@ -1567,6 +1687,7 @@ static const struct super_operations xfs_super_operations = {
 	.put_super		= xfs_fs_put_super,
 	.sync_fs		= xfs_fs_sync_fs,
 	.freeze_fs		= xfs_fs_freeze,
+	.unfreeze_fs		= xfs_fs_unfreeze,
 	.statfs			= xfs_fs_statfs,
 	.remount_fs		= xfs_fs_remount,
 	.show_options		= xfs_fs_show_options,
@@ -1581,94 +1702,6 @@ static struct file_system_type xfs_fs_type = {
 };
 
 STATIC int __init
-xfs_alloc_trace_bufs(void)
-{
-#ifdef XFS_ALLOC_TRACE
-	xfs_alloc_trace_buf = ktrace_alloc(XFS_ALLOC_TRACE_SIZE, KM_MAYFAIL);
-	if (!xfs_alloc_trace_buf)
-		goto out;
-#endif
-#ifdef XFS_BMAP_TRACE
-	xfs_bmap_trace_buf = ktrace_alloc(XFS_BMAP_TRACE_SIZE, KM_MAYFAIL);
-	if (!xfs_bmap_trace_buf)
-		goto out_free_alloc_trace;
-#endif
-#ifdef XFS_BTREE_TRACE
-	xfs_allocbt_trace_buf = ktrace_alloc(XFS_ALLOCBT_TRACE_SIZE,
-					     KM_MAYFAIL);
-	if (!xfs_allocbt_trace_buf)
-		goto out_free_bmap_trace;
-
-	xfs_inobt_trace_buf = ktrace_alloc(XFS_INOBT_TRACE_SIZE, KM_MAYFAIL);
-	if (!xfs_inobt_trace_buf)
-		goto out_free_allocbt_trace;
-
-	xfs_bmbt_trace_buf = ktrace_alloc(XFS_BMBT_TRACE_SIZE, KM_MAYFAIL);
-	if (!xfs_bmbt_trace_buf)
-		goto out_free_inobt_trace;
-#endif
-#ifdef XFS_ATTR_TRACE
-	xfs_attr_trace_buf = ktrace_alloc(XFS_ATTR_TRACE_SIZE, KM_MAYFAIL);
-	if (!xfs_attr_trace_buf)
-		goto out_free_bmbt_trace;
-#endif
-#ifdef XFS_DIR2_TRACE
-	xfs_dir2_trace_buf = ktrace_alloc(XFS_DIR2_GTRACE_SIZE, KM_MAYFAIL);
-	if (!xfs_dir2_trace_buf)
-		goto out_free_attr_trace;
-#endif
-
-	return 0;
-
-#ifdef XFS_DIR2_TRACE
- out_free_attr_trace:
-#endif
-#ifdef XFS_ATTR_TRACE
-	ktrace_free(xfs_attr_trace_buf);
- out_free_bmbt_trace:
-#endif
-#ifdef XFS_BTREE_TRACE
-	ktrace_free(xfs_bmbt_trace_buf);
- out_free_inobt_trace:
-	ktrace_free(xfs_inobt_trace_buf);
- out_free_allocbt_trace:
-	ktrace_free(xfs_allocbt_trace_buf);
- out_free_bmap_trace:
-#endif
-#ifdef XFS_BMAP_TRACE
-	ktrace_free(xfs_bmap_trace_buf);
- out_free_alloc_trace:
-#endif
-#ifdef XFS_ALLOC_TRACE
-	ktrace_free(xfs_alloc_trace_buf);
- out:
-#endif
-	return -ENOMEM;
-}
-
-STATIC void
-xfs_free_trace_bufs(void)
-{
-#ifdef XFS_DIR2_TRACE
-	ktrace_free(xfs_dir2_trace_buf);
-#endif
-#ifdef XFS_ATTR_TRACE
-	ktrace_free(xfs_attr_trace_buf);
-#endif
-#ifdef XFS_BTREE_TRACE
-	ktrace_free(xfs_bmbt_trace_buf);
-	ktrace_free(xfs_inobt_trace_buf);
-	ktrace_free(xfs_allocbt_trace_buf);
-#endif
-#ifdef XFS_BMAP_TRACE
-	ktrace_free(xfs_bmap_trace_buf);
-#endif
-#ifdef XFS_ALLOC_TRACE
-	ktrace_free(xfs_alloc_trace_buf);
-#endif
-}
-
-STATIC int __init
 xfs_init_zones(void)
 {
 
@@ -1809,7 +1842,6 @@ init_xfs_fs(void)
 	printk(KERN_INFO XFS_VERSION_STRING " with "
 			 XFS_BUILD_OPTIONS " enabled\n");
 
-	ktrace_init(64);
 	xfs_ioend_init();
 	xfs_dir_startup();
 
@@ -1817,13 +1849,9 @@ init_xfs_fs(void)
 	if (error)
 		goto out;
 
-	error = xfs_alloc_trace_bufs();
-	if (error)
-		goto out_destroy_zones;
-
 	error = xfs_mru_cache_init();
 	if (error)
-		goto out_free_trace_buffers;
+		goto out_destroy_zones;
 
 	error = xfs_filestream_init();
 	if (error)
@@ -1858,8 +1886,6 @@ init_xfs_fs(void)
 	xfs_filestream_uninit();
  out_mru_cache_uninit:
 	xfs_mru_cache_uninit();
- out_free_trace_buffers:
-	xfs_free_trace_bufs();
  out_destroy_zones:
 	xfs_destroy_zones();
  out:
@@ -1876,9 +1902,7 @@ exit_xfs_fs(void)
 	xfs_buf_terminate();
 	xfs_filestream_uninit();
 	xfs_mru_cache_uninit();
-	xfs_free_trace_bufs();
 	xfs_destroy_zones();
-	ktrace_uninit();
 }
 
 module_init(init_xfs_fs);