Merge commit 'v2.6.35-rc4' into perf/core

Merge reason: Pick up the latest perf fixes

Signed-off-by: Ingo Molnar <mingo@elte.hu>

25 files changed, 315 insertions, 547 deletions

diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index b6ab27c..811384b 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -68,11 +68,7 @@
  * Here we can be a bit looser than the data sections since this
  * needs to only meet arch ABI requirements.
  */
-#ifdef ARCH_SLAB_MINALIGN
-#define FLAT_STACK_ALIGN	(ARCH_SLAB_MINALIGN)
-#else
-#define FLAT_STACK_ALIGN	(sizeof(void *))
-#endif
+#define FLAT_STACK_ALIGN	max_t(unsigned long, sizeof(void *), ARCH_SLAB_MINALIGN)
 
 #define RELOC_FAILED 0xff00ff01		/* Relocation incorrect somewhere */
 #define UNLOADED_LIB 0x7ff000ff		/* Placeholder for unused library */
diff --git a/fs/dcache.c b/fs/dcache.c
index d96047b..c8c78ba 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -590,6 +590,8 @@ static void prune_dcache(int count)
 			up_read(&sb->s_umount);
 		}
 		spin_lock(&sb_lock);
+		/* lock was dropped, must reset next */
+		list_safe_reset_next(sb, n, s_list);
 		count -= pruned;
 		__put_super(sb);
 		/* more work left to do? */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 51e11bf..9d175d6 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -733,12 +733,14 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 {
 	while (fa) {
 		struct fown_struct *fown;
+		unsigned long flags;
+
 		if (fa->magic != FASYNC_MAGIC) {
 			printk(KERN_ERR "kill_fasync: bad magic number in "
 			       "fasync_struct!\n");
 			return;
 		}
-		spin_lock(&fa->fa_lock);
+		spin_lock_irqsave(&fa->fa_lock, flags);
 		if (fa->fa_file) {
 			fown = &fa->fa_file->f_owner;
 			/* Don't send SIGURG to processes which have not set a
@@ -747,7 +749,7 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 			if (!(sig == SIGURG && fown->signum == 0))
 				send_sigio(fown, fa->fa_fd, band);
 		}
-		spin_unlock(&fa->fa_lock);
+		spin_unlock_irqrestore(&fa->fa_lock, flags);
 		fa = rcu_dereference(fa->fa_next);
 	}
 }
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1d1088f..0609607 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -63,24 +63,16 @@ struct bdi_work {
 };
 
 enum {
-	WS_USED_B = 0,
-	WS_ONSTACK_B,
+	WS_INPROGRESS = 0,
+	WS_ONSTACK,
 };
 
-#define WS_USED (1 << WS_USED_B)
-#define WS_ONSTACK (1 << WS_ONSTACK_B)
-
-static inline bool bdi_work_on_stack(struct bdi_work *work)
-{
-	return test_bit(WS_ONSTACK_B, &work->state);
-}
-
 static inline void bdi_work_init(struct bdi_work *work,
 				 struct wb_writeback_args *args)
 {
 	INIT_RCU_HEAD(&work->rcu_head);
 	work->args = *args;
-	work->state = WS_USED;
+	__set_bit(WS_INPROGRESS, &work->state);
 }
 
 /**
@@ -95,43 +87,16 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 	return !list_empty(&bdi->work_list);
 }
 
-static void bdi_work_clear(struct bdi_work *work)
-{
-	clear_bit(WS_USED_B, &work->state);
-	smp_mb__after_clear_bit();
-	/*
-	 * work can have disappeared at this point. bit waitq functions
-	 * should be able to tolerate this, provided bdi_sched_wait does
-	 * not dereference it's pointer argument.
-	*/
-	wake_up_bit(&work->state, WS_USED_B);
-}
-
 static void bdi_work_free(struct rcu_head *head)
 {
 	struct bdi_work *work = container_of(head, struct bdi_work, rcu_head);
 
-	if (!bdi_work_on_stack(work))
-		kfree(work);
-	else
-		bdi_work_clear(work);
-}
-
-static void wb_work_complete(struct bdi_work *work)
-{
-	const enum writeback_sync_modes sync_mode = work->args.sync_mode;
-	int onstack = bdi_work_on_stack(work);
+	clear_bit(WS_INPROGRESS, &work->state);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&work->state, WS_INPROGRESS);
 
-	/*
-	 * For allocated work, we can clear the done/seen bit right here.
-	 * For on-stack work, we need to postpone both the clear and free
-	 * to after the RCU grace period, since the stack could be invalidated
-	 * as soon as bdi_work_clear() has done the wakeup.
-	 */
-	if (!onstack)
-		bdi_work_clear(work);
-	if (sync_mode == WB_SYNC_NONE || onstack)
-		call_rcu(&work->rcu_head, bdi_work_free);
+	if (!test_bit(WS_ONSTACK, &work->state))
+		kfree(work);
 }
 
 static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
@@ -147,7 +112,7 @@ static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
 		list_del_rcu(&work->list);
 		spin_unlock(&bdi->wb_lock);
 
-		wb_work_complete(work);
+		call_rcu(&work->rcu_head, bdi_work_free);
 	}
 }
 
@@ -185,9 +150,9 @@ static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work)
  * Used for on-stack allocated work items. The caller needs to wait until
  * the wb threads have acked the work before it's safe to continue.
  */
-static void bdi_wait_on_work_clear(struct bdi_work *work)
+static void bdi_wait_on_work_done(struct bdi_work *work)
 {
-	wait_on_bit(&work->state, WS_USED_B, bdi_sched_wait,
+	wait_on_bit(&work->state, WS_INPROGRESS, bdi_sched_wait,
 		    TASK_UNINTERRUPTIBLE);
 }
 
@@ -213,37 +178,28 @@ static void bdi_alloc_queue_work(struct backing_dev_info *bdi,
 }
 
 /**
- * bdi_sync_writeback - start and wait for writeback
- * @bdi: the backing device to write from
+ * bdi_queue_work_onstack - start and wait for writeback
  * @sb: write inodes from this super_block
  *
  * Description:
- *   This does WB_SYNC_ALL data integrity writeback and waits for the
- *   IO to complete. Callers must hold the sb s_umount semaphore for
+ *   This function initiates writeback and waits for the operation to
+ *   complete. Callers must hold the sb s_umount semaphore for
  *   reading, to avoid having the super disappear before we are done.
  */
-static void bdi_sync_writeback(struct backing_dev_info *bdi,
-			       struct super_block *sb)
+static void bdi_queue_work_onstack(struct wb_writeback_args *args)
 {
-	struct wb_writeback_args args = {
-		.sb		= sb,
-		.sync_mode	= WB_SYNC_ALL,
-		.nr_pages	= LONG_MAX,
-		.range_cyclic	= 0,
-	};
 	struct bdi_work work;
 
-	bdi_work_init(&work, &args);
-	work.state |= WS_ONSTACK;
+	bdi_work_init(&work, args);
+	__set_bit(WS_ONSTACK, &work.state);
 
-	bdi_queue_work(bdi, &work);
-	bdi_wait_on_work_clear(&work);
+	bdi_queue_work(args->sb->s_bdi, &work);
+	bdi_wait_on_work_done(&work);
 }
 
 /**
  * bdi_start_writeback - start writeback
  * @bdi: the backing device to write from
- * @sb: write inodes from this super_block
  * @nr_pages: the number of pages to write
  *
  * Description:
@@ -252,25 +208,34 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi,
  *   completion. Caller need not hold sb s_umount semaphore.
  *
  */
-void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
-			 long nr_pages)
+void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
 {
 	struct wb_writeback_args args = {
-		.sb		= sb,
 		.sync_mode	= WB_SYNC_NONE,
 		.nr_pages	= nr_pages,
 		.range_cyclic	= 1,
 	};
 
-	/*
-	 * We treat @nr_pages=0 as the special case to do background writeback,
-	 * ie. to sync pages until the background dirty threshold is reached.
-	 */
-	if (!nr_pages) {
-		args.nr_pages = LONG_MAX;
-		args.for_background = 1;
-	}
+	bdi_alloc_queue_work(bdi, &args);
+}
 
+/**
+ * bdi_start_background_writeback - start background writeback
+ * @bdi: the backing device to write from
+ *
+ * Description:
+ *   This does WB_SYNC_NONE background writeback. The IO is only
+ *   started when this function returns, we make no guarentees on
+ *   completion. Caller need not hold sb s_umount semaphore.
+ */
+void bdi_start_background_writeback(struct backing_dev_info *bdi)
+{
+	struct wb_writeback_args args = {
+		.sync_mode	= WB_SYNC_NONE,
+		.nr_pages	= LONG_MAX,
+		.for_background = 1,
+		.range_cyclic	= 1,
+	};
 	bdi_alloc_queue_work(bdi, &args);
 }
 
@@ -561,48 +526,30 @@ select_queue:
 	return ret;
 }
 
-static void unpin_sb_for_writeback(struct super_block *sb)
-{
-	up_read(&sb->s_umount);
-	put_super(sb);
-}
-
-enum sb_pin_state {
-	SB_PINNED,
-	SB_NOT_PINNED,
-	SB_PIN_FAILED
-};
-
 /*
- * For WB_SYNC_NONE writeback, the caller does not have the sb pinned
+ * For background writeback the caller does not have the sb pinned
  * before calling writeback. So make sure that we do pin it, so it doesn't
  * go away while we are writing inodes from it.
  */
-static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc,
-					      struct super_block *sb)
+static bool pin_sb_for_writeback(struct super_block *sb)
 {
-	/*
-	 * Caller must already hold the ref for this
-	 */
-	if (wbc->sync_mode == WB_SYNC_ALL) {
-		WARN_ON(!rwsem_is_locked(&sb->s_umount));
-		return SB_NOT_PINNED;
-	}
 	spin_lock(&sb_lock);
+	if (list_empty(&sb->s_instances)) {
+		spin_unlock(&sb_lock);
+		return false;
+	}
+
 	sb->s_count++;
+	spin_unlock(&sb_lock);
+
 	if (down_read_trylock(&sb->s_umount)) {
-		if (sb->s_root) {
-			spin_unlock(&sb_lock);
-			return SB_PINNED;
-		}
-		/*
-		 * umounted, drop rwsem again and fall through to failure
-		 */
+		if (sb->s_root)
+			return true;
 		up_read(&sb->s_umount);
 	}
-	sb->s_count--;
-	spin_unlock(&sb_lock);
-	return SB_PIN_FAILED;
+
+	put_super(sb);
+	return false;
 }
 
 /*
@@ -681,24 +628,31 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
 		struct inode *inode = list_entry(wb->b_io.prev,
 						 struct inode, i_list);
 		struct super_block *sb = inode->i_sb;
-		enum sb_pin_state state;
 
-		if (wbc->sb && sb != wbc->sb) {
-			/* super block given and doesn't
-			   match, skip this inode */
-			redirty_tail(inode);
-			continue;
-		}
-		state = pin_sb_for_writeback(wbc, sb);
+		if (wbc->sb) {
+			/*
+			 * We are requested to write out inodes for a specific
+			 * superblock.  This means we already have s_umount
+			 * taken by the caller which also waits for us to
+			 * complete the writeout.
+			 */
+			if (sb != wbc->sb) {
+				redirty_tail(inode);
+				continue;
+			}
 
-		if (state == SB_PIN_FAILED) {
-			requeue_io(inode);
-			continue;
+			WARN_ON(!rwsem_is_locked(&sb->s_umount));
+
+			ret = writeback_sb_inodes(sb, wb, wbc);
+		} else {
+			if (!pin_sb_for_writeback(sb)) {
+				requeue_io(inode);
+				continue;
+			}
+			ret = writeback_sb_inodes(sb, wb, wbc);
+			drop_super(sb);
 		}
-		ret = writeback_sb_inodes(sb, wb, wbc);
 
-		if (state == SB_PINNED)
-			unpin_sb_for_writeback(sb);
 		if (ret)
 			break;
 	}
@@ -911,7 +865,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 		 * If this isn't a data integrity operation, just notify
 		 * that we have seen this work and we are now starting it.
 		 */
-		if (args.sync_mode == WB_SYNC_NONE)
+		if (!test_bit(WS_ONSTACK, &work->state))
 			wb_clear_pending(wb, work);
 
 		wrote += wb_writeback(wb, &args);
@@ -920,7 +874,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 		 * This is a data integrity writeback, so only do the
 		 * notification when we have completed the work.
 		 */
-		if (args.sync_mode == WB_SYNC_ALL)
+		if (test_bit(WS_ONSTACK, &work->state))
 			wb_clear_pending(wb, work);
 	}
 
@@ -978,42 +932,32 @@ int bdi_writeback_task(struct bdi_writeback *wb)
 }
 
 /*
- * Schedule writeback for all backing devices. This does WB_SYNC_NONE
- * writeback, for integrity writeback see bdi_sync_writeback().
+ * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
+ * the whole world.
  */
-static void bdi_writeback_all(struct super_block *sb, long nr_pages)
+void wakeup_flusher_threads(long nr_pages)
 {
+	struct backing_dev_info *bdi;
 	struct wb_writeback_args args = {
-		.sb		= sb,
-		.nr_pages	= nr_pages,
 		.sync_mode	= WB_SYNC_NONE,
 	};
-	struct backing_dev_info *bdi;
 
-	rcu_read_lock();
+	if (nr_pages) {
+		args.nr_pages = nr_pages;
+	} else {
+		args.nr_pages = global_page_state(NR_FILE_DIRTY) +
+				global_page_state(NR_UNSTABLE_NFS);
+	}
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		if (!bdi_has_dirty_io(bdi))
 			continue;
-
 		bdi_alloc_queue_work(bdi, &args);
 	}
-
 	rcu_read_unlock();
 }
 
-/*
- * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
- * the whole world.
- */
-void wakeup_flusher_threads(long nr_pages)
-{
-	if (nr_pages == 0)
-		nr_pages = global_page_state(NR_FILE_DIRTY) +
-				global_page_state(NR_UNSTABLE_NFS);
-	bdi_writeback_all(NULL, nr_pages);
-}
-
 static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 {
 	if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
@@ -1218,12 +1162,17 @@ void writeback_inodes_sb(struct super_block *sb)
 {
 	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
 	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
-	long nr_to_write;
+	struct wb_writeback_args args = {
+		.sb		= sb,
+		.sync_mode	= WB_SYNC_NONE,
+	};
+
+	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
-	nr_to_write = nr_dirty + nr_unstable +
+	args.nr_pages = nr_dirty + nr_unstable +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
 
-	bdi_start_writeback(sb->s_bdi, sb, nr_to_write);
+	bdi_queue_work_onstack(&args);
 }
 EXPORT_SYMBOL(writeback_inodes_sb);
 
@@ -1237,7 +1186,9 @@ EXPORT_SYMBOL(writeback_inodes_sb);
 int writeback_inodes_sb_if_idle(struct super_block *sb)
 {
 	if (!writeback_in_progress(sb->s_bdi)) {
+		down_read(&sb->s_umount);
 		writeback_inodes_sb(sb);
+		up_read(&sb->s_umount);
 		return 1;
 	} else
 		return 0;
@@ -1253,7 +1204,16 @@ EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
  */
 void sync_inodes_sb(struct super_block *sb)
 {
-	bdi_sync_writeback(sb->s_bdi, sb);
+	struct wb_writeback_args args = {
+		.sb		= sb,
+		.sync_mode	= WB_SYNC_ALL,
+		.nr_pages	= LONG_MAX,
+		.range_cyclic	= 0,
+	};
+
+	WARN_ON(!rwsem_is_locked(&sb->s_umount));
+
+	bdi_queue_work_onstack(&args);
 	wait_sb_inodes(sb);
 }
 EXPORT_SYMBOL(sync_inodes_sb);
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 46d4b5d..cb6306e 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -122,11 +122,20 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
 	return size;
 }
 
+static void pad_len_spaces(struct seq_file *m, int len)
+{
+	len = 25 + sizeof(void*) * 6 - len;
+	if (len < 1)
+		len = 1;
+	seq_printf(m, "%*c", len, ' ');
+}
+
 /*
  * display a single VMA to a sequenced file
  */
 static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	unsigned long ino = 0;
 	struct file *file;
 	dev_t dev = 0;
@@ -155,11 +164,14 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 		   MAJOR(dev), MINOR(dev), ino, &len);
 
 	if (file) {
-		len = 25 + sizeof(void *) * 6 - len;
-		if (len < 1)
-			len = 1;
-		seq_printf(m, "%*c", len, ' ');
+		pad_len_spaces(m, len);
 		seq_path(m, &file->f_path, "");
+	} else if (mm) {
+		if (vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack) {
+			pad_len_spaces(m, len);
+			seq_puts(m, "[stack]");
+		}
 	}
 
 	seq_putc(m, '\n');
diff --git a/fs/super.c b/fs/super.c
index 5c35bc7..938119a 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -374,6 +374,8 @@ void sync_supers(void)
 			up_read(&sb->s_umount);
 
 			spin_lock(&sb_lock);
+			/* lock was dropped, must reset next */
+			list_safe_reset_next(sb, n, s_list);
 			__put_super(sb);
 		}
 	}
@@ -405,6 +407,8 @@ void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
 		up_read(&sb->s_umount);
 
 		spin_lock(&sb_lock);
+		/* lock was dropped, must reset next */
+		list_safe_reset_next(sb, n, s_list);
 		__put_super(sb);
 	}
 	spin_unlock(&sb_lock);
@@ -585,6 +589,8 @@ static void do_emergency_remount(struct work_struct *work)
 		}
 		up_write(&sb->s_umount);
 		spin_lock(&sb_lock);
+		/* lock was dropped, must reset next */
+		list_safe_reset_next(sb, n, s_list);
 		__put_super(sb);
 	}
 	spin_unlock(&sb_lock);
diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c
index bbd69bd..fcc498e 100644
--- a/fs/sysv/ialloc.c
+++ b/fs/sysv/ialloc.c
@@ -25,6 +25,7 @@
 #include <linux/stat.h>
 #include <linux/string.h>
 #include <linux/buffer_head.h>
+#include <linux/writeback.h>
 #include "sysv.h"
 
 /* We don't trust the value of
@@ -139,6 +140,9 @@ struct inode * sysv_new_inode(const struct inode * dir, mode_t mode)
 	struct inode *inode;
 	sysv_ino_t ino;
 	unsigned count;
+	struct writeback_control wbc = {
+		.sync_mode = WB_SYNC_NONE
+	};
 
 	inode = new_inode(sb);
 	if (!inode)
@@ -168,7 +172,7 @@ struct inode * sysv_new_inode(const struct inode * dir, mode_t mode)
 	insert_inode_hash(inode);
 	mark_inode_dirty(inode);
 
-	sysv_write_inode(inode, 0);	/* ensure inode not allocated again */
+	sysv_write_inode(inode, &wbc);	/* ensure inode not allocated again */
 	mark_inode_dirty(inode);	/* cleared by sysv_write_inode() */
 	/* That's it. */
 	unlock_super(sb);
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index 076ca50..c8ff0d1 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -62,7 +62,9 @@
  */
 static void shrink_liability(struct ubifs_info *c, int nr_to_write)
 {
+	down_read(&c->vfs_sb->s_umount);
 	writeback_inodes_sb(c->vfs_sb);
+	up_read(&c->vfs_sb->s_umount);
 }
 
 /**
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index 846b75a..e7839ee 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -128,13 +128,12 @@ xfs_nfs_get_inode(
 		return ERR_PTR(-ESTALE);
 
 	/*
-	 * The XFS_IGET_BULKSTAT means that an invalid inode number is just
-	 * fine and not an indication of a corrupted filesystem.  Because
-	 * clients can send any kind of invalid file handle, e.g. after
-	 * a restore on the server we have to deal with this case gracefully.
+	 * The XFS_IGET_UNTRUSTED means that an invalid inode number is just
+	 * fine and not an indication of a corrupted filesystem as clients can
+	 * send invalid file handles and we have to handle it gracefully..
 	 */
-	error = xfs_iget(mp, NULL, ino, XFS_IGET_BULKSTAT,
-			 XFS_ILOCK_SHARED, &ip, 0);
+	error = xfs_iget(mp, NULL, ino, XFS_IGET_UNTRUSTED,
+			 XFS_ILOCK_SHARED, &ip);
 	if (error) {
 		/*
 		 * EINVAL means the inode cluster doesn't exist anymore.
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 699b60c..e59a810 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -679,10 +679,9 @@ xfs_ioc_bulkstat(
 		error = xfs_bulkstat_single(mp, &inlast,
 						bulkreq.ubuffer, &done);
 	else	/* XFS_IOC_FSBULKSTAT */
-		error = xfs_bulkstat(mp, &inlast, &count,
-			(bulkstat_one_pf)xfs_bulkstat_one, NULL,
-			sizeof(xfs_bstat_t), bulkreq.ubuffer,
-			BULKSTAT_FG_QUICK, &done);
+		error = xfs_bulkstat(mp, &inlast, &count, xfs_bulkstat_one,
+				     sizeof(xfs_bstat_t), bulkreq.ubuffer,
+				     &done);
 
 	if (error)
 		return -error;
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index 9287135..52ed49e 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -237,15 +237,12 @@ xfs_bulkstat_one_compat(
 	xfs_ino_t	ino,		/* inode number to get data for */
 	void		__user *buffer,	/* buffer to place output in */
 	int		ubsize,		/* size of buffer */
-	void		*private_data,	/* my private data */
-	xfs_daddr_t	bno,		/* starting bno of inode cluster */
 	int		*ubused,	/* bytes used by me */
-	void		*dibuff,	/* on-disk inode buffer */
 	int		*stat)		/* BULKSTAT_RV_... */
 {
 	return xfs_bulkstat_one_int(mp, ino, buffer, ubsize,
-				    xfs_bulkstat_one_fmt_compat, bno,
-				    ubused, dibuff, stat);
+				    xfs_bulkstat_one_fmt_compat,
+				    ubused, stat);
 }
 
 /* copied from xfs_ioctl.c */
@@ -298,13 +295,11 @@ xfs_compat_ioc_bulkstat(
 		int res;
 
 		error = xfs_bulkstat_one_compat(mp, inlast, bulkreq.ubuffer,
-				sizeof(compat_xfs_bstat_t),
-				NULL, 0, NULL, NULL, &res);
+				sizeof(compat_xfs_bstat_t), 0, &res);
 	} else if (cmd == XFS_IOC_FSBULKSTAT_32) {
 		error = xfs_bulkstat(mp, &inlast, &count,
-			xfs_bulkstat_one_compat, NULL,
-			sizeof(compat_xfs_bstat_t), bulkreq.ubuffer,
-			BULKSTAT_FG_QUICK, &done);
+			xfs_bulkstat_one_compat, sizeof(compat_xfs_bstat_t),
+			bulkreq.ubuffer, &done);
 	} else
 		error = XFS_ERROR(EINVAL);
 	if (error)
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 2d8b7bc..8c117ff 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -1632,10 +1632,7 @@ xfs_qm_dqusage_adjust(
 	xfs_ino_t	ino,		/* inode number to get data for */
 	void		__user *buffer,	/* not used */
 	int		ubsize,		/* not used */
-	void		*private_data,	/* not used */
-	xfs_daddr_t	bno,		/* starting block of inode cluster */
 	int		*ubused,	/* not used */
-	void		*dip,		/* on-disk inode pointer (not used) */
 	int		*res)		/* result code value */
 {
 	xfs_inode_t	*ip;
@@ -1660,7 +1657,7 @@ xfs_qm_dqusage_adjust(
 	 * the case in all other instances. It's OK that we do this because
 	 * quotacheck is done only at mount time.
 	 */
-	if ((error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip, bno))) {
+	if ((error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip))) {
 		*res = BULKSTAT_RV_NOTHING;
 		return error;
 	}
@@ -1796,12 +1793,13 @@ xfs_qm_quotacheck(
 		 * Iterate thru all the inodes in the file system,
 		 * adjusting the corresponding dquot counters in core.
 		 */
-		if ((error = xfs_bulkstat(mp, &lastino, &count,
-				     xfs_qm_dqusage_adjust, NULL,
-				     structsz, NULL, BULKSTAT_FG_IGET, &done)))
+		error = xfs_bulkstat(mp, &lastino, &count,
+				     xfs_qm_dqusage_adjust,
+				     structsz, NULL, &done);
+		if (error)
 			break;
 
-	} while (! done);
+	} while (!done);
 
 	/*
 	 * We've made all the changes that we need to make incore.
@@ -1889,14 +1887,14 @@ xfs_qm_init_quotainos(
 		    mp->m_sb.sb_uquotino != NULLFSINO) {
 			ASSERT(mp->m_sb.sb_uquotino > 0);
 			if ((error = xfs_iget(mp, NULL, mp->m_sb.sb_uquotino,
-					     0, 0, &uip, 0)))
+					     0, 0, &uip)))
 				return XFS_ERROR(error);
 		}
 		if (XFS_IS_OQUOTA_ON(mp) &&
 		    mp->m_sb.sb_gquotino != NULLFSINO) {
 			ASSERT(mp->m_sb.sb_gquotino > 0);
 			if ((error = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino,
-					     0, 0, &gip, 0))) {
+					     0, 0, &gip))) {
 				if (uip)
 					IRELE(uip);
 				return XFS_ERROR(error);
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 92b002f..b448776 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -262,7 +262,7 @@ xfs_qm_scall_trunc_qfiles(
 	}
 
 	if ((flags & XFS_DQ_USER) && mp->m_sb.sb_uquotino != NULLFSINO) {
-		error = xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &qip, 0);
+		error = xfs_iget(mp, NULL, mp->m_sb.sb_uquotino, 0, 0, &qip);
 		if (!error) {
 			error = xfs_truncate_file(mp, qip);
 			IRELE(qip);
@@ -271,7 +271,7 @@ xfs_qm_scall_trunc_qfiles(
 
 	if ((flags & (XFS_DQ_GROUP|XFS_DQ_PROJ)) &&
 	    mp->m_sb.sb_gquotino != NULLFSINO) {
-		error2 = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, 0, 0, &qip, 0);
+		error2 = xfs_iget(mp, NULL, mp->m_sb.sb_gquotino, 0, 0, &qip);
 		if (!error2) {
 			error2 = xfs_truncate_file(mp, qip);
 			IRELE(qip);
@@ -417,12 +417,12 @@ xfs_qm_scall_getqstat(
 	}
 	if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) {
 		if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino,
-					0, 0, &uip, 0) == 0)
+					0, 0, &uip) == 0)
 			tempuqip = B_TRUE;
 	}
 	if (!gip && mp->m_sb.sb_gquotino != NULLFSINO) {
 		if (xfs_iget(mp, NULL, mp->m_sb.sb_gquotino,
-					0, 0, &gip, 0) == 0)
+					0, 0, &gip) == 0)
 			tempgqip = B_TRUE;
 	}
 	if (uip) {
@@ -1109,10 +1109,7 @@ xfs_qm_internalqcheck_adjust(
 	xfs_ino_t	ino,		/* inode number to get data for */
 	void		__user *buffer,	/* not used */
 	int		ubsize,		/* not used */
-	void		*private_data,	/* not used */
-	xfs_daddr_t	bno,		/* starting block of inode cluster */
 	int		*ubused,	/* not used */
-	void		*dip,		/* not used */
 	int		*res)		/* bulkstat result code */
 {
 	xfs_inode_t		*ip;
@@ -1134,7 +1131,7 @@ xfs_qm_internalqcheck_adjust(
 	ipreleased = B_FALSE;
  again:
 	lock_flags = XFS_ILOCK_SHARED;
-	if ((error = xfs_iget(mp, NULL, ino, 0, lock_flags, &ip, bno))) {
+	if ((error = xfs_iget(mp, NULL, ino, 0, lock_flags, &ip))) {
 		*res = BULKSTAT_RV_NOTHING;
 		return (error);
 	}
@@ -1205,15 +1202,15 @@ xfs_qm_internalqcheck(
 		 * Iterate thru all the inodes in the file system,
 		 * adjusting the corresponding dquot counters
 		 */
-		if ((error = xfs_bulkstat(mp, &lastino, &count,
-				 xfs_qm_internalqcheck_adjust, NULL,
-				 0, NULL, BULKSTAT_FG_IGET, &done))) {
+		error = xfs_bulkstat(mp, &lastino, &count,
+				 xfs_qm_internalqcheck_adjust,
+				 0, NULL, &done);
+		if (error) {
+			cmn_err(CE_DEBUG, "Bulkstat returned error 0x%x", error);
 			break;
 		}
-	} while (! done);
-	if (error) {
-		cmn_err(CE_DEBUG, "Bulkstat returned error 0x%x", error);
-	}
+	} while (!done);
+
 	cmn_err(CE_DEBUG, "Checking results against system dquots");
 	for (i = 0; i < qmtest_hashmask; i++) {
 		xfs_dqtest_t	*d, *n;
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 5bba29a..7f159d2 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -69,7 +69,9 @@ xfs_swapext(
 		goto out;
 	}
 
-	if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) {
+	if (!(file->f_mode & FMODE_WRITE) ||
+	    !(file->f_mode & FMODE_READ) ||
+	    (file->f_flags & O_APPEND)) {
 		error = XFS_ERROR(EBADF);
 		goto out_put_file;
 	}
@@ -81,6 +83,7 @@ xfs_swapext(
 	}
 
 	if (!(tmp_file->f_mode & FMODE_WRITE) ||
+	    !(tmp_file->f_mode & FMODE_READ) ||
 	    (tmp_file->f_flags & O_APPEND)) {
 		error = XFS_ERROR(EBADF);
 		goto out_put_tmp_file;
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 9d884c1..c7142a0 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -1203,6 +1203,63 @@ error0:
 	return error;
 }
 
+STATIC int
+xfs_imap_lookup(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		agno,
+	xfs_agino_t		agino,
+	xfs_agblock_t		agbno,
+	xfs_agblock_t		*chunk_agbno,
+	xfs_agblock_t		*offset_agbno,
+	int			flags)
+{
+	struct xfs_inobt_rec_incore rec;
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agbp;
+	xfs_agino_t		startino;
+	int			error;
+	int			i;
+
+	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+	if (error) {
+		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
+				"xfs_ialloc_read_agi() returned "
+				"error %d, agno %d",
+				error, agno);
+		return error;
+	}
+
+	/*
+	 * 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.
+	 */
+	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);
+	if (!error) {
+		if (i)
+			error = xfs_inobt_get_rec(cur, &rec, &i);
+		if (!error && i == 0)
+			error = EINVAL;
+	}
+
+	xfs_trans_brelse(tp, agbp);
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	if (error)
+		return error;
+
+	/* for untrusted inodes check it is allocated first */
+	if ((flags & XFS_IGET_UNTRUSTED) &&
+	    (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino)))
+		return EINVAL;
+
+	*chunk_agbno = XFS_AGINO_TO_AGBNO(mp, rec.ir_startino);
+	*offset_agbno = agbno - *chunk_agbno;
+	return 0;
+}
+
 /*
  * Return the location of the inode in imap, for mapping it into a buffer.
  */
@@ -1235,8 +1292,11 @@ xfs_imap(
 	if (agno >= mp->m_sb.sb_agcount || agbno >= mp->m_sb.sb_agblocks ||
 	    ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
 #ifdef DEBUG
-		/* no diagnostics for bulkstat, ino comes from userspace */
-		if (flags & XFS_IGET_BULKSTAT)
+		/*
+		 * Don't output diagnostic information for untrusted inodes
+		 * as they can be invalid without implying corruption.
+		 */
+		if (flags & XFS_IGET_UNTRUSTED)
 			return XFS_ERROR(EINVAL);
 		if (agno >= mp->m_sb.sb_agcount) {
 			xfs_fs_cmn_err(CE_ALERT, mp,
@@ -1263,6 +1323,23 @@ xfs_imap(
 		return XFS_ERROR(EINVAL);
 	}
 
+	blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_blocklog;
+
+	/*
+	 * For bulkstat and handle lookups, we have an untrusted inode number
+	 * that we have to verify is valid. We cannot do this just by reading
+	 * the inode buffer as it may have been unlinked and removed leaving
+	 * inodes in stale state on disk. Hence we have to do a btree lookup
+	 * in all cases where an untrusted inode number is passed.
+	 */
+	if (flags & XFS_IGET_UNTRUSTED) {
+		error = xfs_imap_lookup(mp, tp, agno, agino, agbno,
+					&chunk_agbno, &offset_agbno, flags);
+		if (error)
+			return error;
+		goto out_map;
+	}
+
 	/*
 	 * If the inode cluster size is the same as the blocksize or
 	 * smaller we get to the buffer by simple arithmetics.
@@ -1277,24 +1354,6 @@ xfs_imap(
 		return 0;
 	}
 
-	blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_blocklog;
-
-	/*
-	 * If we get a block number passed from bulkstat we can use it to
-	 * find the buffer easily.
-	 */
-	if (imap->im_blkno) {
-		offset = XFS_INO_TO_OFFSET(mp, ino);
-		ASSERT(offset < mp->m_sb.sb_inopblock);
-
-		cluster_agbno = xfs_daddr_to_agbno(mp, imap->im_blkno);
-		offset += (agbno - cluster_agbno) * mp->m_sb.sb_inopblock;
-
-		imap->im_len = XFS_FSB_TO_BB(mp, blks_per_cluster);
-		imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog);
-		return 0;
-	}
-
 	/*
 	 * If the inode chunks are aligned then use simple maths to
 	 * find the location. Otherwise we have to do a btree
@@ -1304,50 +1363,13 @@ xfs_imap(
 		offset_agbno = agbno & mp->m_inoalign_mask;
 		chunk_agbno = agbno - offset_agbno;
 	} else {
-		xfs_btree_cur_t	*cur;	/* inode btree cursor */
-		xfs_inobt_rec_incore_t chunk_rec;
-		xfs_buf_t	*agbp;	/* agi buffer */
-		int		i;	/* temp state */
-
-		error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
-		if (error) {
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
-					"xfs_ialloc_read_agi() returned "
-					"error %d, agno %d",
-					error, agno);
-			return error;
-		}
-
-		cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
-		error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
-		if (error) {
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
-					"xfs_inobt_lookup() failed");
-			goto error0;
-		}
-
-		error = xfs_inobt_get_rec(cur, &chunk_rec, &i);
-		if (error) {
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
-					"xfs_inobt_get_rec() failed");
-			goto error0;
-		}
-		if (i == 0) {
-#ifdef DEBUG
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
-					"xfs_inobt_get_rec() failed");
-#endif /* DEBUG */
-			error = XFS_ERROR(EINVAL);
-		}
- error0:
-		xfs_trans_brelse(tp, agbp);
-		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+		error = xfs_imap_lookup(mp, tp, agno, agino, agbno,
+					&chunk_agbno, &offset_agbno, flags);
 		if (error)
 			return error;
-		chunk_agbno = XFS_AGINO_TO_AGBNO(mp, chunk_rec.ir_startino);
-		offset_agbno = agbno - chunk_agbno;
 	}
 
+out_map:
 	ASSERT(agbno >= chunk_agbno);
 	cluster_agbno = chunk_agbno +
 		((offset_agbno / blks_per_cluster) * blks_per_cluster);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 75df75f..8f8b91b 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -259,7 +259,6 @@ xfs_iget_cache_miss(
 	xfs_trans_t		*tp,
 	xfs_ino_t		ino,
 	struct xfs_inode	**ipp,
-	xfs_daddr_t		bno,
 	int			flags,
 	int			lock_flags)
 {
@@ -272,7 +271,7 @@ xfs_iget_cache_miss(
 	if (!ip)
 		return ENOMEM;
 
-	error = xfs_iread(mp, tp, ip, bno, flags);
+	error = xfs_iread(mp, tp, ip, flags);
 	if (error)
 		goto out_destroy;
 
@@ -358,8 +357,6 @@ out_destroy:
  *        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.
  */
 int
 xfs_iget(
@@ -368,8 +365,7 @@ xfs_iget(
 	xfs_ino_t	ino,
 	uint		flags,
 	uint		lock_flags,
-	xfs_inode_t	**ipp,
-	xfs_daddr_t	bno)
+	xfs_inode_t	**ipp)
 {
 	xfs_inode_t	*ip;
 	int		error;
@@ -397,7 +393,7 @@ again:
 		read_unlock(&pag->pag_ici_lock);
 		XFS_STATS_INC(xs_ig_missed);
 
-		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, bno,
+		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
 							flags, lock_flags);
 		if (error)
 			goto out_error_or_again;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index d53c39d..b76a829 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -177,7 +177,7 @@ xfs_imap_to_bp(
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
 						XFS_ERRTAG_ITOBP_INOTOBP,
 						XFS_RANDOM_ITOBP_INOTOBP))) {
-			if (iget_flags & XFS_IGET_BULKSTAT) {
+			if (iget_flags & XFS_IGET_UNTRUSTED) {
 				xfs_trans_brelse(tp, bp);
 				return XFS_ERROR(EINVAL);
 			}
@@ -787,7 +787,6 @@ xfs_iread(
 	xfs_mount_t	*mp,
 	xfs_trans_t	*tp,
 	xfs_inode_t	*ip,
-	xfs_daddr_t	bno,
 	uint		iget_flags)
 {
 	xfs_buf_t	*bp;
@@ -797,11 +796,9 @@ xfs_iread(
 	/*
 	 * Fill in the location information in the in-core inode.
 	 */
-	ip->i_imap.im_blkno = bno;
 	error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
 	if (error)
 		return error;
-	ASSERT(bno == 0 || bno == ip->i_imap.im_blkno);
 
 	/*
 	 * Get pointers to the on-disk inode and the buffer containing it.
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 9965e40..78550df 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -442,7 +442,7 @@ static inline void xfs_ifunlock(xfs_inode_t *ip)
  * xfs_iget.c prototypes.
  */
 int		xfs_iget(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
-			 uint, uint, xfs_inode_t **, xfs_daddr_t);
+			 uint, uint, xfs_inode_t **);
 void		xfs_iput(xfs_inode_t *, uint);
 void		xfs_iput_new(xfs_inode_t *, uint);
 void		xfs_ilock(xfs_inode_t *, uint);
@@ -500,7 +500,7 @@ do { \
  * Flags for xfs_iget()
  */
 #define XFS_IGET_CREATE		0x1
-#define XFS_IGET_BULKSTAT	0x2
+#define XFS_IGET_UNTRUSTED	0x2
 
 int		xfs_inotobp(struct xfs_mount *, struct xfs_trans *,
 			    xfs_ino_t, struct xfs_dinode **,
@@ -509,7 +509,7 @@ int		xfs_itobp(struct xfs_mount *, struct xfs_trans *,
 			  struct xfs_inode *, struct xfs_dinode **,
 			  struct xfs_buf **, uint);
 int		xfs_iread(struct xfs_mount *, struct xfs_trans *,
-			  struct xfs_inode *, xfs_daddr_t, uint);
+			  struct xfs_inode *, uint);
 void		xfs_dinode_to_disk(struct xfs_dinode *,
 				   struct xfs_icdinode *);
 void		xfs_idestroy_fork(struct xfs_inode *, int);
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index b1b801e..2b86f86 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -49,24 +49,40 @@ xfs_internal_inum(
 		 (ino == mp->m_sb.sb_uquotino || ino == mp->m_sb.sb_gquotino)));
 }
 
-STATIC int
-xfs_bulkstat_one_iget(
-	xfs_mount_t	*mp,		/* mount point for filesystem */
-	xfs_ino_t	ino,		/* inode number to get data for */
-	xfs_daddr_t	bno,		/* starting bno of inode cluster */
-	xfs_bstat_t	*buf,		/* return buffer */
-	int		*stat)		/* BULKSTAT_RV_... */
+/*
+ * Return stat information for one inode.
+ * Return 0 if ok, else errno.
+ */
+int
+xfs_bulkstat_one_int(
+	struct xfs_mount	*mp,		/* mount point for filesystem */
+	xfs_ino_t		ino,		/* inode to get data for */
+	void __user		*buffer,	/* buffer to place output in */
+	int			ubsize,		/* size of buffer */
+	bulkstat_one_fmt_pf	formatter,	/* formatter, copy to user */
+	int			*ubused,	/* bytes used by me */
+	int			*stat)		/* BULKSTAT_RV_... */
 {
-	xfs_icdinode_t	*dic;	/* dinode core info pointer */
-	xfs_inode_t	*ip;		/* incore inode pointer */
-	struct inode	*inode;
-	int		error;
+	struct xfs_icdinode	*dic;		/* dinode core info pointer */
+	struct xfs_inode	*ip;		/* incore inode pointer */
+	struct inode		*inode;
+	struct xfs_bstat	*buf;		/* return buffer */
+	int			error = 0;	/* error value */
+
+	*stat = BULKSTAT_RV_NOTHING;
+
+	if (!buffer || xfs_internal_inum(mp, ino))
+		return XFS_ERROR(EINVAL);
+
+	buf = kmem_alloc(sizeof(*buf), KM_SLEEP | KM_MAYFAIL);
+	if (!buf)
+		return XFS_ERROR(ENOMEM);
 
 	error = xfs_iget(mp, NULL, ino,
-			 XFS_IGET_BULKSTAT, XFS_ILOCK_SHARED, &ip, bno);
+			 XFS_IGET_UNTRUSTED, XFS_ILOCK_SHARED, &ip);
 	if (error) {
 		*stat = BULKSTAT_RV_NOTHING;
-		return error;
+		goto out_free;
 	}
 
 	ASSERT(ip != NULL);
@@ -127,77 +143,16 @@ xfs_bulkstat_one_iget(
 		buf->bs_blocks = dic->di_nblocks + ip->i_delayed_blks;
 		break;
 	}
-
 	xfs_iput(ip, XFS_ILOCK_SHARED);
-	return error;
-}
 
-STATIC void
-xfs_bulkstat_one_dinode(
-	xfs_mount_t	*mp,		/* mount point for filesystem */
-	xfs_ino_t	ino,		/* inode number to get data for */
-	xfs_dinode_t	*dic,		/* dinode inode pointer */
-	xfs_bstat_t	*buf)		/* return buffer */
-{
-	/*
-	 * The inode format changed when we moved the link count and
-	 * made it 32 bits long.  If this is an old format inode,
-	 * convert it in memory to look like a new one.  If it gets
-	 * flushed to disk we will convert back before flushing or
-	 * logging it.  We zero out the new projid field and the old link
-	 * count field.  We'll handle clearing the pad field (the remains
-	 * of the old uuid field) when we actually convert the inode to
-	 * the new format. We don't change the version number so that we
-	 * can distinguish this from a real new format inode.
-	 */
-	if (dic->di_version == 1) {
-		buf->bs_nlink = be16_to_cpu(dic->di_onlink);
-		buf->bs_projid = 0;
-	} else {
-		buf->bs_nlink = be32_to_cpu(dic->di_nlink);
-		buf->bs_projid = be16_to_cpu(dic->di_projid);
-	}
+	error = formatter(buffer, ubsize, ubused, buf);
 
-	buf->bs_ino = ino;
-	buf->bs_mode = be16_to_cpu(dic->di_mode);
-	buf->bs_uid = be32_to_cpu(dic->di_uid);
-	buf->bs_gid = be32_to_cpu(dic->di_gid);
-	buf->bs_size = be64_to_cpu(dic->di_size);
-	buf->bs_atime.tv_sec = be32_to_cpu(dic->di_atime.t_sec);
-	buf->bs_atime.tv_nsec = be32_to_cpu(dic->di_atime.t_nsec);
-	buf->bs_mtime.tv_sec = be32_to_cpu(dic->di_mtime.t_sec);
-	buf->bs_mtime.tv_nsec = be32_to_cpu(dic->di_mtime.t_nsec);
-	buf->bs_ctime.tv_sec = be32_to_cpu(dic->di_ctime.t_sec);
-	buf->bs_ctime.tv_nsec = be32_to_cpu(dic->di_ctime.t_nsec);
-	buf->bs_xflags = xfs_dic2xflags(dic);
-	buf->bs_extsize = be32_to_cpu(dic->di_extsize) << mp->m_sb.sb_blocklog;
-	buf->bs_extents = be32_to_cpu(dic->di_nextents);
-	buf->bs_gen = be32_to_cpu(dic->di_gen);
-	memset(buf->bs_pad, 0, sizeof(buf->bs_pad));
-	buf->bs_dmevmask = be32_to_cpu(dic->di_dmevmask);
-	buf->bs_dmstate = be16_to_cpu(dic->di_dmstate);
-	buf->bs_aextents = be16_to_cpu(dic->di_anextents);
-	buf->bs_forkoff = XFS_DFORK_BOFF(dic);
+	if (!error)
+		*stat = BULKSTAT_RV_DIDONE;
 
-	switch (dic->di_format) {
-	case XFS_DINODE_FMT_DEV:
-		buf->bs_rdev = xfs_dinode_get_rdev(dic);
-		buf->bs_blksize = BLKDEV_IOSIZE;
-		buf->bs_blocks = 0;
-		break;
-	case XFS_DINODE_FMT_LOCAL:
-	case XFS_DINODE_FMT_UUID:
-		buf->bs_rdev = 0;
-		buf->bs_blksize = mp->m_sb.sb_blocksize;
-		buf->bs_blocks = 0;
-		break;
-	case XFS_DINODE_FMT_EXTENTS:
-	case XFS_DINODE_FMT_BTREE:
-		buf->bs_rdev = 0;
-		buf->bs_blksize = mp->m_sb.sb_blocksize;
-		buf->bs_blocks = be64_to_cpu(dic->di_nblocks);
-		break;
-	}
+ out_free:
+	kmem_free(buf);
+	return error;
 }
 
 /* Return 0 on success or positive error */
@@ -217,118 +172,17 @@ xfs_bulkstat_one_fmt(
 	return 0;
 }
 
-/*
- * Return stat information for one inode.
- * Return 0 if ok, else errno.
- */
-int		   	    		/* error status */
-xfs_bulkstat_one_int(
-	xfs_mount_t	*mp,		/* mount point for filesystem */
-	xfs_ino_t	ino,		/* inode number to get data for */
-	void		__user *buffer,	/* buffer to place output in */
-	int		ubsize,		/* size of buffer */
-	bulkstat_one_fmt_pf formatter,	/* formatter, copy to user */
-	xfs_daddr_t	bno,		/* starting bno of inode cluster */
-	int		*ubused,	/* bytes used by me */
-	void		*dibuff,	/* on-disk inode buffer */
-	int		*stat)		/* BULKSTAT_RV_... */
-{
-	xfs_bstat_t	*buf;		/* return buffer */
-	int		error = 0;	/* error value */
-	xfs_dinode_t	*dip;		/* dinode inode pointer */
-
-	dip = (xfs_dinode_t *)dibuff;
-	*stat = BULKSTAT_RV_NOTHING;
-
-	if (!buffer || xfs_internal_inum(mp, ino))
-		return XFS_ERROR(EINVAL);
-
-	buf = kmem_alloc(sizeof(*buf), KM_SLEEP);
-
-	if (dip == NULL) {
-		/* We're not being passed a pointer to a dinode.  This happens
-		 * if BULKSTAT_FG_IGET is selected.  Do the iget.
-		 */
-		error = xfs_bulkstat_one_iget(mp, ino, bno, buf, stat);
-		if (error)
-			goto out_free;
-	} else {
-		xfs_bulkstat_one_dinode(mp, ino, dip, buf);
-	}
-
-	error = formatter(buffer, ubsize, ubused, buf);
-	if (error)
-		goto out_free;
-
-	*stat = BULKSTAT_RV_DIDONE;
-
- out_free:
-	kmem_free(buf);
-	return error;
-}
-
 int
 xfs_bulkstat_one(
 	xfs_mount_t	*mp,		/* mount point for filesystem */
 	xfs_ino_t	ino,		/* inode number to get data for */
 	void		__user *buffer,	/* buffer to place output in */
 	int		ubsize,		/* size of buffer */
-	void		*private_data,	/* my private data */
-	xfs_daddr_t	bno,		/* starting bno of inode cluster */
 	int		*ubused,	/* bytes used by me */
-	void		*dibuff,	/* on-disk inode buffer */
 	int		*stat)		/* BULKSTAT_RV_... */
 {
 	return xfs_bulkstat_one_int(mp, ino, buffer, ubsize,
-				    xfs_bulkstat_one_fmt, bno,
-				    ubused, dibuff, stat);
-}
-
-/*
- * Test to see whether we can use the ondisk inode directly, based
- * on the given bulkstat flags, filling in dipp accordingly.
- * Returns zero if the inode is dodgey.
- */
-STATIC int
-xfs_bulkstat_use_dinode(
-	xfs_mount_t	*mp,
-	int		flags,
-	xfs_buf_t	*bp,
-	int		clustidx,
-	xfs_dinode_t	**dipp)
-{
-	xfs_dinode_t	*dip;
-	unsigned int	aformat;
-
-	*dipp = NULL;
-	if (!bp || (flags & BULKSTAT_FG_IGET))
-		return 1;
-	dip = (xfs_dinode_t *)
-			xfs_buf_offset(bp, clustidx << mp->m_sb.sb_inodelog);
-	/*
-	 * Check the buffer containing the on-disk inode for di_mode == 0.
-	 * This is to prevent xfs_bulkstat from picking up just reclaimed
-	 * inodes that have their in-core state initialized but not flushed
-	 * to disk yet. This is a temporary hack that would require a proper
-	 * fix in the future.
-	 */
-	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
-	    !XFS_DINODE_GOOD_VERSION(dip->di_version) ||
-	    !dip->di_mode)
-		return 0;
-	if (flags & BULKSTAT_FG_QUICK) {
-		*dipp = dip;
-		return 1;
-	}
-	/* BULKSTAT_FG_INLINE: if attr fork is local, or not there, use it */
-	aformat = dip->di_aformat;
-	if ((XFS_DFORK_Q(dip) == 0) ||
-	    (aformat == XFS_DINODE_FMT_LOCAL) ||
-	    (aformat == XFS_DINODE_FMT_EXTENTS && !dip->di_anextents)) {
-		*dipp = dip;
-		return 1;
-	}
-	return 1;
+				    xfs_bulkstat_one_fmt, ubused, stat);
 }
 
 #define XFS_BULKSTAT_UBLEFT(ubleft)	((ubleft) >= statstruct_size)
@@ -342,10 +196,8 @@ xfs_bulkstat(
 	xfs_ino_t		*lastinop, /* last inode returned */
 	int			*ubcountp, /* size of buffer/count returned */
 	bulkstat_one_pf		formatter, /* func that'd fill a single buf */
-	void			*private_data,/* private data for formatter */
 	size_t			statstruct_size, /* sizeof struct filling */
 	char			__user *ubuffer, /* buffer with inode stats */
-	int			flags,	/* defined in xfs_itable.h */
 	int			*done)	/* 1 if there are more stats to get */
 {
 	xfs_agblock_t		agbno=0;/* allocation group block number */
@@ -380,14 +232,12 @@ xfs_bulkstat(
 	int			ubelem;	/* spaces used in user's buffer */
 	int			ubused;	/* bytes used by formatter */
 	xfs_buf_t		*bp;	/* ptr to on-disk inode cluster buf */
-	xfs_dinode_t		*dip;	/* ptr into bp for specific inode */
 
 	/*
 	 * Get the last inode value, see if there's nothing to do.
 	 */
 	ino = (xfs_ino_t)*lastinop;
 	lastino = ino;
-	dip = NULL;
 	agno = XFS_INO_TO_AGNO(mp, ino);
 	agino = XFS_INO_TO_AGINO(mp, ino);
 	if (agno >= mp->m_sb.sb_agcount ||
@@ -612,37 +462,6 @@ xfs_bulkstat(
 							irbp->ir_startino) +
 						((chunkidx & nimask) >>
 						 mp->m_sb.sb_inopblog);
-
-					if (flags & (BULKSTAT_FG_QUICK |
-						     BULKSTAT_FG_INLINE)) {
-						int offset;
-
-						ino = XFS_AGINO_TO_INO(mp, agno,
-								       agino);
-						bno = XFS_AGB_TO_DADDR(mp, agno,
-								       agbno);
-
-						/*
-						 * Get the inode cluster buffer
-						 */
-						if (bp)
-							xfs_buf_relse(bp);
-
-						error = xfs_inotobp(mp, NULL, ino, &dip,
-								    &bp, &offset,
-								    XFS_IGET_BULKSTAT);
-
-						if (!error)
-							clustidx = offset / mp->m_sb.sb_inodesize;
-						if (XFS_TEST_ERROR(error != 0,
-								   mp, XFS_ERRTAG_BULKSTAT_READ_CHUNK,
-								   XFS_RANDOM_BULKSTAT_READ_CHUNK)) {
-							bp = NULL;
-							ubleft = 0;
-							rval = error;
-							break;
-						}
-					}
 				}
 				ino = XFS_AGINO_TO_INO(mp, agno, agino);
 				bno = XFS_AGB_TO_DADDR(mp, agno, agbno);
@@ -658,35 +477,13 @@ xfs_bulkstat(
 				 * when the chunk is used up.
 				 */
 				irbp->ir_freecount++;
-				if (!xfs_bulkstat_use_dinode(mp, flags, bp,
-							     clustidx, &dip)) {
-					lastino = ino;
-					continue;
-				}
-				/*
-				 * If we need to do an iget, cannot hold bp.
-				 * Drop it, until starting the next cluster.
-				 */
-				if ((flags & BULKSTAT_FG_INLINE) && !dip) {
-					if (bp)
-						xfs_buf_relse(bp);
-					bp = NULL;
-				}
 
 				/*
 				 * Get the inode and fill in a single buffer.
-				 * BULKSTAT_FG_QUICK uses dip to fill it in.
-				 * BULKSTAT_FG_IGET uses igets.
-				 * BULKSTAT_FG_INLINE uses dip if we have an
-				 * inline attr fork, else igets.
-				 * See: xfs_bulkstat_one & xfs_dm_bulkstat_one.
-				 * This is also used to count inodes/blks, etc
-				 * in xfs_qm_quotacheck.
 				 */
 				ubused = statstruct_size;
-				error = formatter(mp, ino, ubufp,
-						ubleft, private_data,
-						bno, &ubused, dip, &fmterror);
+				error = formatter(mp, ino, ubufp, ubleft,
+						  &ubused, &fmterror);
 				if (fmterror == BULKSTAT_RV_NOTHING) {
 					if (error && error != ENOENT &&
 						error != EINVAL) {
@@ -778,8 +575,7 @@ xfs_bulkstat_single(
 	 */
 
 	ino = (xfs_ino_t)*lastinop;
-	error = xfs_bulkstat_one(mp, ino, buffer, sizeof(xfs_bstat_t),
-				 NULL, 0, NULL, NULL, &res);
+	error = xfs_bulkstat_one(mp, ino, buffer, sizeof(xfs_bstat_t), 0, &res);
 	if (error) {
 		/*
 		 * Special case way failed, do it the "long" way
@@ -788,8 +584,7 @@ xfs_bulkstat_single(
 		(*lastinop)--;
 		count = 1;
 		if (xfs_bulkstat(mp, lastinop, &count, xfs_bulkstat_one,
-				NULL, sizeof(xfs_bstat_t), buffer,
-				BULKSTAT_FG_IGET, done))
+				sizeof(xfs_bstat_t), buffer, done))
 			return error;
 		if (count == 0 || (xfs_ino_t)*lastinop != ino)
 			return error == EFSCORRUPTED ?
diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
index 20792bf..97295d9 100644
--- a/fs/xfs/xfs_itable.h
+++ b/fs/xfs/xfs_itable.h
@@ -27,10 +27,7 @@ typedef int (*bulkstat_one_pf)(struct xfs_mount	*mp,
 			       xfs_ino_t	ino,
 			       void		__user *buffer,
 			       int		ubsize,
-			       void		*private_data,
-			       xfs_daddr_t	bno,
 			       int		*ubused,
-			       void		*dip,
 			       int		*stat);
 
 /*
@@ -41,13 +38,6 @@ typedef int (*bulkstat_one_pf)(struct xfs_mount	*mp,
 #define BULKSTAT_RV_GIVEUP	2
 
 /*
- * Values for bulkstat flag argument.
- */
-#define BULKSTAT_FG_IGET	0x1	/* Go through the buffer cache */
-#define BULKSTAT_FG_QUICK	0x2	/* No iget, walk the dinode cluster */
-#define BULKSTAT_FG_INLINE	0x4	/* No iget if inline attrs */
-
-/*
  * Return stat information in bulk (by-inode) for the filesystem.
  */
 int					/* error status */
@@ -56,10 +46,8 @@ xfs_bulkstat(
 	xfs_ino_t	*lastino,	/* last inode returned */
 	int		*count,		/* size of buffer/count returned */
 	bulkstat_one_pf formatter,	/* func that'd fill a single buf */
-	void		*private_data,	/* private data for formatter */
 	size_t		statstruct_size,/* sizeof struct that we're filling */
 	char		__user *ubuffer,/* buffer with inode stats */
-	int		flags,		/* flag to control access method */
 	int		*done);		/* 1 if there are more stats to get */
 
 int
@@ -82,9 +70,7 @@ xfs_bulkstat_one_int(
 	void			__user *buffer,
 	int			ubsize,
 	bulkstat_one_fmt_pf	formatter,
-	xfs_daddr_t		bno,
 	int			*ubused,
-	void			*dibuff,
 	int			*stat);
 
 int
@@ -93,10 +79,7 @@ xfs_bulkstat_one(
 	xfs_ino_t		ino,
 	void			__user *buffer,
 	int			ubsize,
-	void			*private_data,
-	xfs_daddr_t		bno,
 	int			*ubused,
-	void			*dibuff,
 	int			*stat);
 
 typedef int (*inumbers_fmt_pf)(
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index ed0684c..9ac5cfa 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3198,7 +3198,7 @@ xlog_recover_process_one_iunlink(
 	int				error;
 
 	ino = XFS_AGINO_TO_INO(mp, agno, agino);
-	error = xfs_iget(mp, NULL, ino, 0, 0, &ip, 0);
+	error = xfs_iget(mp, NULL, ino, 0, 0, &ip);
 	if (error)
 		goto fail;
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d59f4e8..69f62d8 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1300,7 +1300,7 @@ xfs_mountfs(
 	 * Get and sanity-check the root inode.
 	 * Save the pointer to it in the mount structure.
 	 */
-	error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip, 0);
+	error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip);
 	if (error) {
 		cmn_err(CE_WARN, "XFS: failed to read root inode");
 		goto out_log_dealloc;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 1644551..a2d32ce 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -2277,12 +2277,12 @@ xfs_rtmount_inodes(
 	sbp = &mp->m_sb;
 	if (sbp->sb_rbmino == NULLFSINO)
 		return 0;
-	error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip, 0);
+	error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip);
 	if (error)
 		return error;
 	ASSERT(mp->m_rbmip != NULL);
 	ASSERT(sbp->sb_rsumino != NULLFSINO);
-	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip, 0);
+	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
 	if (error) {
 		IRELE(mp->m_rbmip);
 		return error;
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 785ff10..2559dfe 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -62,7 +62,7 @@ xfs_trans_iget(
 {
 	int			error;
 
-	error = xfs_iget(mp, tp, ino, flags, lock_flags, ipp, 0);
+	error = xfs_iget(mp, tp, ino, flags, lock_flags, ipp);
 	if (!error && tp)
 		xfs_trans_ijoin(tp, *ipp, lock_flags);
 	return error;
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index a06bd62..c164683 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -1269,7 +1269,7 @@ xfs_lookup(
 	if (error)
 		goto out;
 
-	error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp, 0);
+	error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp);
 	if (error)
 		goto out_free_name;