Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (107 commits)
  vfs: use ERR_CAST for err-ptr tossing in lookup_instantiate_filp
  isofs: Remove global fs lock
  jffs2: fix IN_DELETE_SELF on overwriting rename() killing a directory
  fix IN_DELETE_SELF on overwriting rename() on ramfs et.al.
  mm/truncate.c: fix build for CONFIG_BLOCK not enabled
  fs:update the NOTE of the file_operations structure
  Remove dead code in dget_parent()
  AFS: Fix silly characters in a comment
  switch d_add_ci() to d_splice_alias() in "found negative" case as well
  simplify gfs2_lookup()
  jfs_lookup(): don't bother with . or ..
  get rid of useless dget_parent() in btrfs rename() and link()
  get rid of useless dget_parent() in fs/btrfs/ioctl.c
  fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers
  drivers: fix up various ->llseek() implementations
  fs: handle SEEK_HOLE/SEEK_DATA properly in all fs's that define their own llseek
  Ext4: handle SEEK_HOLE/SEEK_DATA generically
  Btrfs: implement our own ->llseek
  fs: add SEEK_HOLE and SEEK_DATA flags
  reiserfs: make reiserfs default to barrier=flush
  ...

Fix up trivial conflicts in fs/xfs/linux-2.6/xfs_super.c due to the new
shrinker callout for the inode cache, that clashed with the xfs code to
start the periodic workers later.

6 files changed, 66 insertions, 43 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index a8251a8..f820e60 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -78,9 +78,6 @@
  *  ->i_mutex			(generic_file_buffered_write)
  *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
  *
- *  ->i_mutex
- *    ->i_alloc_sem             (various)
- *
  *  inode_wb_list_lock
  *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
diff --git a/mm/madvise.c b/mm/madvise.c
index 2221491..74bf193 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -218,7 +218,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 	endoff = (loff_t)(end - vma->vm_start - 1)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* vmtruncate_range needs to take i_mutex and i_alloc_sem */
+	/* vmtruncate_range needs to take i_mutex */
 	up_read(&current->mm->mmap_sem);
 	error = vmtruncate_range(mapping->host, offset, endoff);
 	down_read(&current->mm->mmap_sem);
diff --git a/mm/rmap.c b/mm/rmap.c
index 23295f65..2540a39 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -21,7 +21,6 @@
  * Lock ordering in mm:
  *
  * inode->i_mutex	(while writing or truncating, not reading or faulting)
- *   inode->i_alloc_sem (vmtruncate_range)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
  *       mapping->i_mmap_mutex
diff --git a/mm/swapfile.c b/mm/swapfile.c
index ff8dc1a..1b8c339 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1681,19 +1681,14 @@ out:
 }
 
 #ifdef CONFIG_PROC_FS
-struct proc_swaps {
-	struct seq_file seq;
-	int event;
-};
-
 static unsigned swaps_poll(struct file *file, poll_table *wait)
 {
-	struct proc_swaps *s = file->private_data;
+	struct seq_file *seq = file->private_data;
 
 	poll_wait(file, &proc_poll_wait, wait);
 
-	if (s->event != atomic_read(&proc_poll_event)) {
-		s->event = atomic_read(&proc_poll_event);
+	if (seq->poll_event != atomic_read(&proc_poll_event)) {
+		seq->poll_event = atomic_read(&proc_poll_event);
 		return POLLIN | POLLRDNORM | POLLERR | POLLPRI;
 	}
 
@@ -1783,24 +1778,16 @@ static const struct seq_operations swaps_op = {
 
 static int swaps_open(struct inode *inode, struct file *file)
 {
-	struct proc_swaps *s;
+	struct seq_file *seq;
 	int ret;
 
-	s = kmalloc(sizeof(struct proc_swaps), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
-
-	file->private_data = s;
-
 	ret = seq_open(file, &swaps_op);
-	if (ret) {
-		kfree(s);
+	if (ret)
 		return ret;
-	}
 
-	s->seq.private = s;
-	s->event = atomic_read(&proc_poll_event);
-	return ret;
+	seq = file->private_data;
+	seq->poll_event = atomic_read(&proc_poll_event);
+	return 0;
 }
 
 static const struct file_operations proc_swaps_operations = {
diff --git a/mm/truncate.c b/mm/truncate.c
index e13f22e..003c6c6 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -622,12 +622,11 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
 		return -ENOSYS;
 
 	mutex_lock(&inode->i_mutex);
-	down_write(&inode->i_alloc_sem);
+	inode_dio_wait(inode);
 	unmap_mapping_range(mapping, offset, (end - offset), 1);
 	inode->i_op->truncate_range(inode, offset, end);
 	/* unmap again to remove racily COWed private pages */
 	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	up_write(&inode->i_alloc_sem);
 	mutex_unlock(&inode->i_mutex);
 
 	return 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d036e59..febbc04 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -250,49 +250,90 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 		unsigned long long delta;
 		unsigned long total_scan;
 		unsigned long max_pass;
+		int shrink_ret = 0;
+		long nr;
+		long new_nr;
+		long batch_size = shrinker->batch ? shrinker->batch
+						  : SHRINK_BATCH;
 
+		/*
+		 * copy the current shrinker scan count into a local variable
+		 * and zero it so that other concurrent shrinker invocations
+		 * don't also do this scanning work.
+		 */
+		do {
+			nr = shrinker->nr;
+		} while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+
+		total_scan = nr;
 		max_pass = do_shrinker_shrink(shrinker, shrink, 0);
 		delta = (4 * nr_pages_scanned) / shrinker->seeks;
 		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
-		shrinker->nr += delta;
-		if (shrinker->nr < 0) {
+		total_scan += delta;
+		if (total_scan < 0) {
 			printk(KERN_ERR "shrink_slab: %pF negative objects to "
 			       "delete nr=%ld\n",
-			       shrinker->shrink, shrinker->nr);
-			shrinker->nr = max_pass;
+			       shrinker->shrink, total_scan);
+			total_scan = max_pass;
 		}
 
 		/*
+		 * We need to avoid excessive windup on filesystem shrinkers
+		 * due to large numbers of GFP_NOFS allocations causing the
+		 * shrinkers to return -1 all the time. This results in a large
+		 * nr being built up so when a shrink that can do some work
+		 * comes along it empties the entire cache due to nr >>>
+		 * max_pass.  This is bad for sustaining a working set in
+		 * memory.
+		 *
+		 * Hence only allow the shrinker to scan the entire cache when
+		 * a large delta change is calculated directly.
+		 */
+		if (delta < max_pass / 4)
+			total_scan = min(total_scan, max_pass / 2);
+
+		/*
 		 * Avoid risking looping forever due to too large nr value:
 		 * never try to free more than twice the estimate number of
 		 * freeable entries.
 		 */
-		if (shrinker->nr > max_pass * 2)
-			shrinker->nr = max_pass * 2;
+		if (total_scan > max_pass * 2)
+			total_scan = max_pass * 2;
 
-		total_scan = shrinker->nr;
-		shrinker->nr = 0;
+		trace_mm_shrink_slab_start(shrinker, shrink, nr,
+					nr_pages_scanned, lru_pages,
+					max_pass, delta, total_scan);
 
-		while (total_scan >= SHRINK_BATCH) {
-			long this_scan = SHRINK_BATCH;
-			int shrink_ret;
+		while (total_scan >= batch_size) {
 			int nr_before;
 
 			nr_before = do_shrinker_shrink(shrinker, shrink, 0);
 			shrink_ret = do_shrinker_shrink(shrinker, shrink,
-							this_scan);
+							batch_size);
 			if (shrink_ret == -1)
 				break;
 			if (shrink_ret < nr_before)
 				ret += nr_before - shrink_ret;
-			count_vm_events(SLABS_SCANNED, this_scan);
-			total_scan -= this_scan;
+			count_vm_events(SLABS_SCANNED, batch_size);
+			total_scan -= batch_size;
 
 			cond_resched();
 		}
 
-		shrinker->nr += total_scan;
+		/*
+		 * move the unused scan count back into the shrinker in a
+		 * manner that handles concurrent updates. If we exhausted the
+		 * scan, there is no need to do an update.
+		 */
+		do {
+			nr = shrinker->nr;
+			new_nr = total_scan + nr;
+			if (total_scan <= 0)
+				break;
+		} while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+
+		trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
 	}
 	up_read(&shrinker_rwsem);
 out: