mm: prevent concurrent unmap_mapping_range() on the same inode

commit 2aa15890f3c191326678f1bd68af61ec6b8753ec upstream.

Michael Leun reported that running parallel opens on a fuse filesystem
can trigger a "kernel BUG at mm/truncate.c:475"

Gurudas Pai reported the same bug on NFS.

The reason is, unmap_mapping_range() is not prepared for more than
one concurrent invocation per inode.  For example:

  thread1: going through a big range, stops in the middle of a vma and
     stores the restart address in vm_truncate_count.

  thread2: comes in with a small (e.g. single page) unmap request on
     the same vma, somewhere before restart_address, finds that the
     vma was already unmapped up to the restart address and happily
     returns without doing anything.

Another scenario would be two big unmap requests, both having to
restart the unmapping and each one setting vm_truncate_count to its
own value.  This could go on forever without any of them being able to
finish.

Truncate and hole punching already serialize with i_mutex.  Other
callers of unmap_mapping_range() do not, and it's difficult to get
i_mutex protection for all callers.  In particular ->d_revalidate(),
which calls invalidate_inode_pages2_range() in fuse, may be called
with or without i_mutex.

This patch adds a new mutex to 'struct address_space' to prevent
running multiple concurrent unmap_mapping_range() on the same mapping.

[ We'll hopefully get rid of all this with the upcoming mm
  preemptibility series by Peter Zijlstra, the "mm: Remove i_mmap_mutex
  lockbreak" patch in particular.  But that is for 2.6.39 ]

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reported-by: Michael Leun <lkml20101129@newton.leun.net>
Reported-by: Gurudas Pai <gurudas.pai@oracle.com>
Tested-by: Gurudas Pai <gurudas.pai@oracle.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

7 files changed, 19 insertions, 25 deletions

diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index ebef7ab6e17e..f910999d15d5 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -59,14 +59,7 @@ static void gfs2_init_gl_aspace_once(void *foo)
 	struct address_space *mapping = (struct address_space *)(gl + 1);
 
 	gfs2_init_glock_once(gl);
-	memset(mapping, 0, sizeof(*mapping));
-	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
-	spin_lock_init(&mapping->tree_lock);
-	spin_lock_init(&mapping->i_mmap_lock);
-	INIT_LIST_HEAD(&mapping->private_list);
-	spin_lock_init(&mapping->private_lock);
-	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
-	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+	address_space_init_once(mapping);
 }
 
 /**
diff --git a/fs/inode.c b/fs/inode.c
index ae2727ab0c3a..9fcc6189461a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -280,6 +280,20 @@ static void destroy_inode(struct inode *inode)
 		kmem_cache_free(inode_cachep, (inode));
 }
 
+void address_space_init_once(struct address_space *mapping)
+{
+	memset(mapping, 0, sizeof(*mapping));
+	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
+	spin_lock_init(&mapping->tree_lock);
+	spin_lock_init(&mapping->i_mmap_lock);
+	INIT_LIST_HEAD(&mapping->private_list);
+	spin_lock_init(&mapping->private_lock);
+	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
+	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+	mutex_init(&mapping->unmap_mutex);
+}
+EXPORT_SYMBOL(address_space_init_once);
+
 /*
  * These are initializations that only need to be done
  * once, because the fields are idempotent across use
@@ -293,13 +307,7 @@ void inode_init_once(struct inode *inode)
 	INIT_LIST_HEAD(&inode->i_devices);
 	INIT_LIST_HEAD(&inode->i_wb_list);
 	INIT_LIST_HEAD(&inode->i_lru);
-	INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
-	spin_lock_init(&inode->i_data.tree_lock);
-	spin_lock_init(&inode->i_data.i_mmap_lock);
-	INIT_LIST_HEAD(&inode->i_data.private_list);
-	spin_lock_init(&inode->i_data.private_lock);
-	INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap);
-	INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear);
+	address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
 #ifdef CONFIG_FSNOTIFY
 	INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 5115814cb745..3b008b8bff04 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -35,11 +35,6 @@
 #include "btnode.h"
 
 
-void nilfs_btnode_cache_init_once(struct address_space *btnc)
-{
-	nilfs_mapping_init_once(btnc);
-}
-
 static const struct address_space_operations def_btnode_aops = {
 	.sync_page		= block_sync_page,
 };
diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h
index 79037494f1e0..1b8ebd888c28 100644
--- a/fs/nilfs2/btnode.h
+++ b/fs/nilfs2/btnode.h
@@ -37,7 +37,6 @@ struct nilfs_btnode_chkey_ctxt {
 	struct buffer_head *newbh;
 };
 
-void nilfs_btnode_cache_init_once(struct address_space *);
 void nilfs_btnode_cache_init(struct address_space *, struct backing_dev_info *);
 void nilfs_btnode_cache_clear(struct address_space *);
 struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc,
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 39a5b84e2c9f..bdb8de601562 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -460,9 +460,9 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
 	struct backing_dev_info *bdi = inode->i_sb->s_bdi;
 
 	INIT_LIST_HEAD(&shadow->frozen_buffers);
-	nilfs_mapping_init_once(&shadow->frozen_data);
+	address_space_init_once(&shadow->frozen_data);
 	nilfs_mapping_init(&shadow->frozen_data, bdi, &shadow_map_aops);
-	nilfs_mapping_init_once(&shadow->frozen_btnodes);
+	address_space_init_once(&shadow->frozen_btnodes);
 	nilfs_mapping_init(&shadow->frozen_btnodes, bdi, &shadow_map_aops);
 	mi->mi_shadow = shadow;
 	return 0;
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index fb9e8a8a2038..b7e27268e2e4 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -61,7 +61,6 @@ void nilfs_free_private_page(struct page *);
 int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
 void nilfs_clear_dirty_pages(struct address_space *);
-void nilfs_mapping_init_once(struct address_space *mapping);
 void nilfs_mapping_init(struct address_space *mapping,
 			struct backing_dev_info *bdi,
 			const struct address_space_operations *aops);
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 2940a5853e30..388e26bcf69f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1263,7 +1263,7 @@ static void nilfs_inode_init_once(void *obj)
 #ifdef CONFIG_NILFS_XATTR
 	init_rwsem(&ii->xattr_sem);
 #endif
-	nilfs_btnode_cache_init_once(&ii->i_btnode_cache);
+	address_space_init_once(&ii->i_btnode_cache);
 	ii->i_bmap = &ii->i_bmap_data;
 	inode_init_once(&ii->vfs_inode);
 }