XFS: Prepare for combining the XFS and Linux inodes.

index 7932551..3b6d35e 100644
@@ -40,161 +40,119 @@
 #include "xfs_utils.h"
 
 /*
- * Look up an inode by number in the given file system.
- * The inode is looked up in the cache held in each AG.
- * If the inode is found in the cache, attach it to the provided
- * vnode.
- *
- * If it is not in core, read it in from the file system's device,
- * add it to the cache and attach the provided vnode.
- *
- * The inode is locked according to the value of the lock_flags parameter.
- * This flag parameter indicates how and if the inode's IO lock and inode lock
- * should be taken.
- *
- * mp -- the mount point structure for the current file system.  It points
- *       to the inode hash table.
- * tp -- a pointer to the current transaction if there is one.  This is
- *       simply passed through to the xfs_iread() call.
- * ino -- the number of the inode desired.  This is the unique identifier
- *        within the file system for the inode being requested.
- * lock_flags -- flags indicating how to lock the inode.  See the comment
- *		 for xfs_ilock() for a list of valid values.
- * bno -- the block number starting the buffer containing the inode,
- *	  if known (as by bulkstat), else 0.
+ * Check the validity of the inode we just found it the cache
  */
-STATIC int
-xfs_iget_core(
-	struct inode	*inode,
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	uint		flags,
-	uint		lock_flags,
-	xfs_inode_t	**ipp,
-	xfs_daddr_t	bno)
+static int
+xfs_iget_cache_hit(
+	struct inode		*inode,
+	struct xfs_perag	*pag,
+	struct xfs_inode	*ip,
+	int			flags,
+	int			lock_flags) __releases(pag->pag_ici_lock)
 {
-	struct inode	*old_inode;
-	xfs_inode_t	*ip;
-	int		error;
-	unsigned long	first_index, mask;
-	xfs_perag_t	*pag;
-	xfs_agino_t	agino;
-
-	/* the radix tree exists only in inode capable AGs */
-	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_maxagi)
-		return EINVAL;
-
-	/* get the perag structure and ensure that it's inode capable */
-	pag = xfs_get_perag(mp, ino);
-	if (!pag->pagi_inodeok)
-		return EINVAL;
-	ASSERT(pag->pag_ici_init);
-	agino = XFS_INO_TO_AGINO(mp, ino);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct inode		*old_inode;
+	int			error = 0;
 
-again:
-	read_lock(&pag->pag_ici_lock);
-	ip = radix_tree_lookup(&pag->pag_ici_root, agino);
+	/*
+	 * If INEW is set this inode is being set up
+	 * Pause and try again.
+	 */
+	if (xfs_iflags_test(ip, XFS_INEW)) {
+		error = EAGAIN;
+		XFS_STATS_INC(xs_ig_frecycle);
+		goto out_error;
+	}
 
-	if (ip != NULL) {
+	old_inode = ip->i_vnode;
+	if (old_inode == NULL) {
 		/*
-		 * If INEW is set this inode is being set up
+		 * If IRECLAIM is set this inode is
+		 * on its way out of the system,
 		 * we need to pause and try again.
 		 */
-		if (xfs_iflags_test(ip, XFS_INEW)) {
-			read_unlock(&pag->pag_ici_lock);
-			delay(1);
+		if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
+			error = EAGAIN;
 			XFS_STATS_INC(xs_ig_frecycle);
+			goto out_error;
+		}
+		ASSERT(xfs_iflags_test(ip, XFS_IRECLAIMABLE));
 
-			goto again;
+		/*
+		 * If lookup is racing with unlink, then we
+		 * should return an error immediately so we
+		 * don't remove it from the reclaim list and
+		 * potentially leak the inode.
+		 */
+		if ((ip->i_d.di_mode == 0) &&
+		    !(flags & XFS_IGET_CREATE)) {
+			error = ENOENT;
+			goto out_error;
 		}
+		xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
+
+		xfs_iflags_clear(ip, XFS_IRECLAIMABLE);
+		read_unlock(&pag->pag_ici_lock);
+
+		XFS_MOUNT_ILOCK(mp);
+		list_del_init(&ip->i_reclaim);
+		XFS_MOUNT_IUNLOCK(mp);
 
-		old_inode = ip->i_vnode;
-		if (old_inode == NULL) {
-			/*
-			 * If IRECLAIM is set this inode is
-			 * on its way out of the system,
-			 * we need to pause and try again.
-			 */
-			if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
-				read_unlock(&pag->pag_ici_lock);
-				delay(1);
-				XFS_STATS_INC(xs_ig_frecycle);
-
-				goto again;
-			}
-			ASSERT(xfs_iflags_test(ip, XFS_IRECLAIMABLE));
-
-			/*
-			 * If lookup is racing with unlink, then we
-			 * should return an error immediately so we
-			 * don't remove it from the reclaim list and
-			 * potentially leak the inode.
-			 */
-			if ((ip->i_d.di_mode == 0) &&
-			    !(flags & XFS_IGET_CREATE)) {
-				read_unlock(&pag->pag_ici_lock);
-				xfs_put_perag(mp, pag);
-				return ENOENT;
-			}
-
-			xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
-
-			XFS_STATS_INC(xs_ig_found);
-			xfs_iflags_clear(ip, XFS_IRECLAIMABLE);
-			read_unlock(&pag->pag_ici_lock);
-
-			XFS_MOUNT_ILOCK(mp);
-			list_del_init(&ip->i_reclaim);
-			XFS_MOUNT_IUNLOCK(mp);
-
-			goto finish_inode;
-
-		} else if (inode != old_inode) {
-			/* The inode is being torn down, pause and
-			 * try again.
-			 */
-			if (old_inode->i_state & (I_FREEING | I_CLEAR)) {
-				read_unlock(&pag->pag_ici_lock);
-				delay(1);
-				XFS_STATS_INC(xs_ig_frecycle);
-
-				goto again;
-			}
+	} else if (inode != old_inode) {
+		/* The inode is being torn down, pause and
+		 * try again.
+		 */
+		if (old_inode->i_state & (I_FREEING | I_CLEAR)) {
+			error = EAGAIN;
+			XFS_STATS_INC(xs_ig_frecycle);
+			goto out_error;
+		}
 /* Chances are the other vnode (the one in the inode) is being torn
 * down right now, and we landed on top of it. Question is, what do
 * we do? Unhook the old inode and hook up the new one?
 */
-			cmn_err(CE_PANIC,
-		"xfs_iget_core: ambiguous vns: vp/0x%p, invp/0x%p",
-					old_inode, inode);
-		}
-
-		/*
-		 * Inode cache hit
-		 */
+		cmn_err(CE_PANIC,
+	"xfs_iget_core: ambiguous vns: vp/0x%p, invp/0x%p",
+				old_inode, inode);
+	} else {
 		read_unlock(&pag->pag_ici_lock);
-		XFS_STATS_INC(xs_ig_found);
+	}
 
-finish_inode:
-		if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
-			xfs_put_perag(mp, pag);
-			return ENOENT;
-		}
+	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+		error = ENOENT;
+		goto out;
+	}
 
-		if (lock_flags != 0)
-			xfs_ilock(ip, lock_flags);
+	if (lock_flags != 0)
+		xfs_ilock(ip, lock_flags);
 
-		xfs_iflags_clear(ip, XFS_ISTALE);
-		xfs_itrace_exit_tag(ip, "xfs_iget.found");
-		goto return_ip;
-	}
+	xfs_iflags_clear(ip, XFS_ISTALE);
+	xfs_itrace_exit_tag(ip, "xfs_iget.found");
+	XFS_STATS_INC(xs_ig_found);
+	return 0;
 
-	/*
-	 * Inode cache miss
-	 */
+out_error:
 	read_unlock(&pag->pag_ici_lock);
-	XFS_STATS_INC(xs_ig_missed);
+out:
+	return error;
+}
+
+
+static int
+xfs_iget_cache_miss(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	xfs_trans_t		*tp,
+	xfs_ino_t		ino,
+	struct xfs_inode	**ipp,
+	xfs_daddr_t		bno,
+	int			flags,
+	int			lock_flags)
+{
+	struct xfs_inode	*ip;
+	int			error;
+	unsigned long		first_index, mask;
+	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);
 
 	/*
 	 * Read the disk inode attributes into a new inode structure and get

@@ -202,14 +160,11 @@ finish_inode:
 	 */
 	error = xfs_iread(mp, tp, ino, &ip, bno,
 			  (flags & XFS_IGET_BULKSTAT) ? XFS_IMAP_BULKSTAT : 0);
-	if (error) {
-		xfs_put_perag(mp, pag);
+	if (error)
 		return error;
-	}
 
 	xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
 
-
 	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);

@@ -228,9 +183,8 @@ finish_inode:
 		xfs_ilock(ip, lock_flags);
 
 	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
-		xfs_idestroy(ip);
-		xfs_put_perag(mp, pag);
-		return ENOENT;
+		error = ENOENT;
+		goto out_destroy;
 	}
 
 	/*

@@ -238,37 +192,110 @@ finish_inode:
 	 * write spinlock.
 	 */
 	if (radix_tree_preload(GFP_KERNEL)) {
-		xfs_idestroy(ip);
-		delay(1);
-		goto again;
+		error = EAGAIN;
+		goto out_destroy;
 	}
 	mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
 	first_index = agino & mask;
 	write_lock(&pag->pag_ici_lock);
-	/*
-	 * insert the new inode
-	 */
+
+	/* insert the new inode */
 	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
 	if (unlikely(error)) {
-		BUG_ON(error != -EEXIST);
-		write_unlock(&pag->pag_ici_lock);
-		radix_tree_preload_end();
-		xfs_idestroy(ip);
+		WARN_ON(error != -EEXIST);
 		XFS_STATS_INC(xs_ig_dup);
-		goto again;
+		error = EAGAIN;
+		goto out_unlock;
 	}
 
-	/*
-	 * These values _must_ be set before releasing the radix tree lock!
-	 */
+	/* These values _must_ be set before releasing the radix tree lock! */
 	ip->i_udquot = ip->i_gdquot = NULL;
 	xfs_iflags_set(ip, XFS_INEW);
 
 	write_unlock(&pag->pag_ici_lock);
 	radix_tree_preload_end();
+	*ipp = ip;
+	return 0;
+
+out_unlock:
+	write_unlock(&pag->pag_ici_lock);
+	radix_tree_preload_end();
+out_destroy:
+	xfs_idestroy(ip);
+	return error;
+}
+
+/*
+ * Look up an inode by number in the given file system.
+ * The inode is looked up in the cache held in each AG.
+ * If the inode is found in the cache, attach it to the provided
+ * vnode.
+ *
+ * If it is not in core, read it in from the file system's device,
+ * add it to the cache and attach the provided vnode.
+ *
+ * The inode is locked according to the value of the lock_flags parameter.
+ * This flag parameter indicates how and if the inode's IO lock and inode lock
+ * should be taken.
+ *
+ * mp -- the mount point structure for the current file system.  It points
+ *       to the inode hash table.
+ * tp -- a pointer to the current transaction if there is one.  This is
+ *       simply passed through to the xfs_iread() call.
+ * ino -- the number of the inode desired.  This is the unique identifier
+ *        within the file system for the inode being requested.
+ * lock_flags -- flags indicating how to lock the inode.  See the comment
+ *		 for xfs_ilock() for a list of valid values.
+ * bno -- the block number starting the buffer containing the inode,
+ *	  if known (as by bulkstat), else 0.
+ */
+STATIC int
+xfs_iget_core(
+	struct inode	*inode,
+	xfs_mount_t	*mp,
+	xfs_trans_t	*tp,
+	xfs_ino_t	ino,
+	uint		flags,
+	uint		lock_flags,
+	xfs_inode_t	**ipp,
+	xfs_daddr_t	bno)
+{
+	xfs_inode_t	*ip;
+	int		error;
+	xfs_perag_t	*pag;
+	xfs_agino_t	agino;
+
+	/* the radix tree exists only in inode capable AGs */
+	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_maxagi)
+		return EINVAL;
+
+	/* get the perag structure and ensure that it's inode capable */
+	pag = xfs_get_perag(mp, ino);
+	if (!pag->pagi_inodeok)
+		return EINVAL;
+	ASSERT(pag->pag_ici_init);
+	agino = XFS_INO_TO_AGINO(mp, ino);
+
+again:
+	error = 0;
+	read_lock(&pag->pag_ici_lock);
+	ip = radix_tree_lookup(&pag->pag_ici_root, agino);
+
+	if (ip) {
+		error = xfs_iget_cache_hit(inode, pag, ip, flags, lock_flags);
+		if (error)
+			goto out_error_or_again;
+	} else {
+		read_unlock(&pag->pag_ici_lock);
+		XFS_STATS_INC(xs_ig_missed);
+
+		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, bno,
+							flags, lock_flags);
+		if (error)
+			goto out_error_or_again;
+	}
 	xfs_put_perag(mp, pag);
 
- return_ip:
 	ASSERT(ip->i_df.if_ext_max ==
 	       XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t));
 

@@ -288,6 +315,14 @@ finish_inode:
 	if (ip->i_d.di_mode != 0)
 		xfs_setup_inode(ip);
 	return 0;
+
+out_error_or_again:
+	if (error == EAGAIN) {
+		delay(1);
+		goto again;
+	}
+	xfs_put_perag(mp, pag);
+	return error;
 }
 
 

index 4d9b848..c789950 100644
@@ -888,6 +888,42 @@ xfs_fs_inode_init_once(
 	inode_init_once((struct inode *)vnode);
 }
 
+
+/*
+ * Slab object creation initialisation for the XFS inode.
+ * This covers only the idempotent fields in the XFS inode;
+ * all other fields need to be initialised on allocation
+ * from the slab. This avoids the need to repeatedly intialise
+ * fields in the xfs inode that left in the initialise state
+ * when freeing the inode.
+ */
+void
+xfs_inode_init_once(
+	void			*inode)
+{
+	struct xfs_inode	*ip = inode;
+
+	memset(ip, 0, sizeof(struct xfs_inode));
+	atomic_set(&ip->i_iocount, 0);
+	atomic_set(&ip->i_pincount, 0);
+	spin_lock_init(&ip->i_flags_lock);
+	INIT_LIST_HEAD(&ip->i_reclaim);
+	init_waitqueue_head(&ip->i_ipin_wait);
+
+	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);
+
+	/*
+	 * Because we want to use a counting completion, complete
+	 * the flush completion once to allow a single access to
+	 * the flush completion without blocking.
+	 */
+	init_completion(&ip->i_flush);
+	complete(&ip->i_flush);
+
+}
+
 /*
  * Attempt to flush the inode, this will actually fail
  * if the inode is pinned, but we dirty the inode again

@@ -1841,7 +1877,7 @@ xfs_init_zones(void)
 	xfs_inode_zone =
 		kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
 					KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
-					KM_ZONE_SPREAD, NULL);
+					KM_ZONE_SPREAD, xfs_inode_init_once);
 	if (!xfs_inode_zone)
 		goto out_destroy_efi_zone;
 

index 3b6d35e..12fe37e 100644
@@ -165,20 +165,6 @@ xfs_iget_cache_miss(
 
 	xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
 
-	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);
-	init_waitqueue_head(&ip->i_ipin_wait);
-	atomic_set(&ip->i_pincount, 0);
-
-	/*
-	 * Because we want to use a counting completion, complete
-	 * the flush completion once to allow a single access to
-	 * the flush completion without blocking.
-	 */
-	init_completion(&ip->i_flush);
-	complete(&ip->i_flush);
-
 	if (lock_flags)
 		xfs_ilock(ip, lock_flags);
 

95 lines not on this page · raw message

index 7b50eb4..813c9b0 100644
@@ -504,6 +504,7 @@ int		xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *,
 				     xfs_fsize_t, int, int);
 int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 
+struct xfs_inode * xfs_inode_alloc(struct xfs_mount *, xfs_ino_t);
 void		xfs_idestroy_fork(xfs_inode_t *, int);
 void		xfs_idestroy(xfs_inode_t *);
 void		xfs_idata_realloc(xfs_inode_t *, int, int);

index cf6754a..4f4c939 100644
@@ -594,21 +594,21 @@ xfs_bulkstat(
 						/*
 						 * Get the inode cluster buffer
 						 */
-						ASSERT(xfs_inode_zone != NULL);
-						ip = kmem_zone_zalloc(xfs_inode_zone,
-								      KM_SLEEP);
-						ip->i_ino = ino;
-						ip->i_mount = mp;
-						spin_lock_init(&ip->i_flags_lock);
 						if (bp)
 							xfs_buf_relse(bp);
+						ip = xfs_inode_alloc(mp, ino);
+						if (!ip) {
+							bp = NULL;
+							rval = ENOMEM;
+							break;
+						}
 						error = xfs_itobp(mp, NULL, ip,
 								&dip, &bp, bno,
 								XFS_IMAP_BULKSTAT,
 								XFS_BUF_LOCK);
 						if (!error)
 							clustidx = ip->i_boffset / mp->m_sb.sb_inodesize;
-						kmem_zone_free(xfs_inode_zone, ip);
+						xfs_idestroy(ip);
 						if (XFS_TEST_ERROR(error != 0,
 								   mp, XFS_ERRTAG_BULKSTAT_READ_CHUNK,
 								   XFS_RANDOM_BULKSTAT_READ_CHUNK)) {

index f42f80a..d932579 100644
@@ -191,7 +191,7 @@ xfs_setfilesize(
 		ip->i_d.di_size = isize;
 		ip->i_update_core = 1;
 		ip->i_update_size = 1;
-		mark_inode_dirty_sync(ioend->io_inode);
+		xfs_mark_inode_dirty_sync(ip);
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);

index 095d271..3bfb3c0 100644
@@ -128,7 +128,7 @@ xfs_ichgtime(
 	if (sync_it) {
 		SYNCHRONIZE();
 		ip->i_update_core = 1;
-		mark_inode_dirty_sync(inode);
+		xfs_mark_inode_dirty_sync(ip);
 	}
 }
 

index c789950..8db6806 100644
@@ -949,7 +949,7 @@ xfs_fs_write_inode(
 	 * it dirty again so we'll try again later.
 	 */
 	if (error)
-		mark_inode_dirty_sync(inode);
+		xfs_mark_inode_dirty_sync(XFS_I(inode));
 
 	return -error;
 }